Merge remote-tracking branch 'origin/master' into codex/agent-session-jsonl-location

# Conflicts:
#	docs/module-graph.md
#	docs/tool-catalog.md
#	examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/text-turn/session.jsonl
#	packages/bash/tool-bash/README.md
#	packages/bash/tool-bash/package.json
#	packages/bash/tool-bash/src/index.ts
#	packages/cordis/tool-cordis/src/api-catalog.ts

.github/workflows/ci.yml

@@ -82,6 +82,20 @@ jobs:
       - name: Install (immutable)
         run: pnpm install --frozen-lockfile
 
+      # The snapshot lane REPLAYS the sandbox example's recorded scenarios,
+      # re-executing their bash calls under a real runner. ubuntu-latest has
+      # no bubblewrap preinstalled and no built Landlock launcher, so without
+      # this the confined executions fail closed (SANDBOX_UNAVAILABLE). Same
+      # install as sandbox.yml's bwrap leg (incl. the Ubuntu 24.04 AppArmor
+      # userns knob).
+      - name: Install bubblewrap (unrestrict userns)
+        if: matrix.lane == 'snapshot'
+        run: |
+          sudo apt-get update -q
+          sudo apt-get install -yq bubblewrap
+          sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 \
+            || echo "apparmor userns knob absent — the functional probe decides"
+
       - uses: actions/cache@v4
         if: matrix.lane == 'lint'
         with:

.github/workflows/e2e.yml

@@ -82,6 +82,20 @@ jobs:
       - name: Install (immutable)
         run: pnpm install --frozen-lockfile
 
+      # The with-key escalation e2e (examples/sandbox-acp-agent/tests/
+      # escalation.e2e.ts) self-skips without a usable runner — without this
+      # step it would never actually execute anywhere (CI had no bwrap, dev
+      # macs run Seatbelt instead), which is exactly how a broken harness
+      # composition once survived unseen. Same recipe as ci.yml's bwrap
+      # steps; the userns knob is best-effort (absent on pre-24.04 kernels,
+      # the probe decides).
+      - name: Install bubblewrap (unrestrict userns)
+        run: |
+          sudo apt-get update -q
+          sudo apt-get install -yq bubblewrap
+          sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 \
+            || echo "apparmor userns knob absent — the functional probe decides"
+
       # Guard against a false green: the e2e suites self-skip when the key is
       # absent, so a missing/misconfigured secret would otherwise pass as
       # "all skipped". This job only runs on trusted events (the `if:` above

.github/workflows/sandbox.yml

@@ -0,0 +1,124 @@
+# Sandbox CI: the keyless real-kernel confinement proofs. A separate workflow
+# from ci.yml because the axis is different — these jobs fan out over
+# OS×runner (kernel capabilities), not node versions. The Landlock launcher
+# arrives from the registry with `pnpm install` (the npm package family
+# `node-addon-landlock-run`, built and released from its own repository), so
+# these legs exercise the true consumer path — nothing is compiled here.
+name: Sandbox
+
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+
+jobs:
+  # Keyless real-kernel sandbox proofs (sandbox RFC § Testing): each ladder
+  # rung is only provable on a host where it enforces, so this job fans out
+  # an OS×runner matrix — bwrap and Landlock on Linux (separate legs: the
+  # Landlock files force the bwrap rung off, so each leg proves exactly one
+  # rung; Landlock twice, once per architecture, each confining through the
+  # registry-installed launcher), Seatbelt on macOS (sandbox-exec ships with
+  # the OS). One node
+  # version only: kernel confinement does not vary by node, and ci.yml's
+  # node matrix already covers the node axis.
+  #
+  # The e2e files self-skip where their runner is absent, so a leg that lost
+  # its runner (no bwrap, kernel without Landlock, macOS without
+  # sandbox-exec) would otherwise pass as a false green — the same trap
+  # e2e.yml's key preflight guards against. Each leg therefore asserts BOTH
+  # its platform files actually ran: `Test Files  2 passed (2)`, no skips.
+  sandbox-e2e:
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - os: ubuntu-latest
+            runner: bwrap
+          - os: ubuntu-24.04
+            runner: landlock
+          - os: ubuntu-24.04-arm
+            runner: landlock
+          - os: macos-latest
+            runner: seatbelt
+    name: sandbox e2e (${{ matrix.runner }}, ${{ matrix.os }})
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 20
+    steps:
+      - uses: actions/checkout@v6
+
+      - uses: actions/setup-node@v6
+        with:
+          node-version: 24
+
+      - name: Enable corepack (pnpm)
+        run: corepack enable
+
+      - name: Install (immutable)
+        run: pnpm install --frozen-lockfile
+
+      # The bwrap rung needs bubblewrap on PATH and unprivileged user
+      # namespaces. Ubuntu 24.04 gates the latter behind an AppArmor knob;
+      # lift it best-effort — on images where the knob is absent the
+      # functional probe (and the run-guard below) is the arbiter anyway.
+      - name: Install bubblewrap (unrestrict userns)
+        if: matrix.runner == 'bwrap'
+        run: |
+          sudo apt-get update -q
+          sudo apt-get install -yq bubblewrap
+          sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 \
+            || echo "apparmor userns knob absent — the functional probe decides"
+
+      # The unit suite runs on ubuntu in `checks`; this is the one darwin leg
+      # in the workflow, so run it here too — the platform-dependent unit
+      # expectations (Seatbelt path canonicalization: /tmp IS /private/tmp)
+      # take their darwin branch only on this runner.
+      - name: Unit tests (darwin parity)
+        if: matrix.runner == 'seatbelt'
+        run: pnpm run test
+
+      - name: Sandbox e2e (real kernel confinement, world-verified)
+        # NO_COLOR: vitest force-enables ANSI color under GITHUB_ACTIONS even
+        # without a TTY, which would thread escape codes through the summary
+        # line the run-guard greps.
+        env:
+          NO_COLOR: 1
+        run: |
+          set -u +e -o pipefail
+          out=$(pnpm exec vitest run --config vitest.e2e.config.ts \
+            packages/sandbox/sandbox-local/tests/${{ matrix.runner }}.e2e.ts \
+            packages/bash/bash-sandbox/tests/${{ matrix.runner }}.e2e.ts 2>&1); status=$?
+          echo "$out"
+          [ "$status" -eq 0 ]
+          # Both platform files must have RUN — a self-skip (runner missing on
+          # the very platform that exists to prove it) is a failure, not a pass.
+          echo "$out" | grep -qE 'Test Files[[:space:]]+2 passed \(2\)'
+
+      # Publish-path rehearsal, Landlock legs only (the pack gates need built
+      # lib/). The e2e packs the workspace closure, installs the tarballs
+      # into a throwaway consumer — npm pulling `node-addon-landlock-run`
+      # and its platform package from the registry, the true consumer path —
+      # and confines through the INSTALLED launcher, asserting it executable
+      # apart (a mode-stripped binary must not masquerade as a non-enforcing
+      # kernel). Same no-silent-skip guard as above.
+      - name: Build packages (lib/ for the pack rehearsal)
+        if: matrix.runner == 'landlock'
+        run: pnpm run build
+
+      - name: Packed-distribution e2e (pack → install → confine)
+        if: matrix.runner == 'landlock'
+        env:
+          NO_COLOR: 1
+        run: |
+          set -u +e -o pipefail
+          out=$(pnpm exec vitest run --config vitest.e2e.config.ts \
+            packages/sandbox/sandbox-local/tests/packed-install.e2e.ts 2>&1); status=$?
+          echo "$out"
+          [ "$status" -eq 0 ]
+          echo "$out" | grep -qE 'Test Files[[:space:]]+1 passed \(1\)'

AGENTS.md

@@ -15,6 +15,7 @@ packages/    Harness packages at packages/<group>/<pkg>/, all named @deepseek-ai
   llm/         LLM seam + the DeepSeek adapters (hand-rolled + pi-ai design twin)
   bash/        bash executor seam + local impl + model-facing bash tools
   fs/          filesystem seam + local impl + policy gate + read/write/edit tools
+  skill/       skill provider registry + local impl + catalog/loader tool
   web/         web seam + search/fetch providers + model-facing web tools
   compact/     compaction seam + basic backend
   subagent/    subagent seam + spawn/fork/ACP backends + delegation tool
@@ -24,7 +25,7 @@ packages/    Harness packages at packages/<group>/<pkg>/, all named @deepseek-ai
   cordis/      self-referential toolset: the agent inspects/mounts plugins in its own runtime
   hooks/       Claude Code / Codex hook bridges + shared wire-protocol library
   session-persistence/  persistence seam + JSONL/SQLite backends
-  ui/          ACP bridge, app-boot glue, stdio/ACP app bins, user-interaction seam, ask-user tool
+  ui/          ACP bridge, app-boot glue, stdio/ACP app bins, user-approval and user-interaction seams, ask-user tool
   support/     dev/test infrastructure packages
   util/        zero-dependency utilities
 examples/    Runnable demos: thin cordis.yml leaves over the app packages (see examples/AGENTS.md)
@@ -71,7 +72,7 @@ pnpm run hygiene
 out=$(printf 'echo ci smoke\n' | pnpm run demo:echo 2>&1)
 printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})'
 printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE'
-ls .sessions/_no-cwd/main-session-*.jsonl >/dev/null
+test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)"
 rm -rf .sessions
 pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts
 ```

docs/architecture.md

@@ -1,6 +1,6 @@
 # DeepSeek Harness Architecture
 
-The project is an SDK for building agent harnesses. The idea is to have **everything as a plugin**. For example, the agent loop is just one plugin shipped by default.
+The **DeepSeek Harness SDK** builds agent harnesses on Cordis. The principle is simple: **everything is a plugin**. The shipped loop is one plugin, not a privileged kernel.
 
 ## Overview
 
@@ -26,8 +26,10 @@ Composition is preferred over inheritance. `packages/core/` is a repository grou
 |---|---|---|
 | `ctx.llm` | [`llm/`](../packages/llm/README.md) | adapter registry and streaming model calls |
 | `ctx.bash` | [`bash/`](../packages/bash/README.md) | foreground/background command execution |
+| `ctx.sandbox` | [`sandbox/`](../packages/sandbox/README.md) | same-world process confinement (argv wrapping, per-call policy) |
 | `ctx.codeRuntime` | [`code-runtime/`](../packages/code-runtime/README.md) | model-written program execution |
 | `ctx.fs` | [`fs/`](../packages/fs/README.md) | filesystem provider primitives and policy events |
+| `ctx.skills` | [`skill/`](../packages/skill/README.md) | skill provider registry and progressive disclosure |
 | `ctx.web` | [`web/`](../packages/web/README.md) | search/fetch provider registries |
 | `ctx.compact` | [`compact/`](../packages/compact/README.md) | session-log compaction |
 | `ctx.subagents` | [`subagent/`](../packages/subagent/README.md) | named delegation providers |
@@ -127,11 +129,11 @@ Streaming is a raw chunk protocol (`block-start` through `finish`) with `BlockAs
 
 A swappable capability usually splits into **interface / implementation / consumer**: the interface owns the `ctx` key and event names; an implementation registers a backend; a consumer exposes model-facing behavior through `ctx.tools` or prompt assembly. The bash trio is the reference shape, and the [capability graph](capability-seams.md) shows the current package families.
 
-Some cases bend the template deliberately. LLM keeps interface and consumer event names together because adapters are the implementations. Filesystem adds policy checks around provider primitives. Web is one service with search and fetch provider registries, so provider swaps do not rename model tools. Subagents use a named provider registry because multiple delegation backends can coexist; `spawn` starts fresh, `fork` seeds from the parent's completed-turn prefix, and ACP can drive an out-of-process child ([subagent.md](core-data-structures/subagent.md)).
+Some seams bend the template deliberately. LLM keeps interface and consumer vocabulary together because adapters are the implementations. Filesystem adds policy gates around provider primitives. Web is one service with search and fetch provider registries, so provider swaps do not rename model tools. Skills and subagents use named provider registries; local skills scan project/user roots, and other providers can add embedded or remote catalogs without registry/tool changes. Subagents spawn fresh, fork from the parent's completed-turn prefix, or use ACP children ([subagent.md](core-data-structures/subagent.md)).
 
 ### Bundles And Apps
 
-`dsh-agent-core` is the default bundle: one plugin loading the agent loop ([README](../packages/core/agent-core/README.md)). App packages compose it with a front end and own the entrypoint `bin`: `dsh-stdio-agent` for the terminal REPL, and `dsh-acp-agent` for ACP over JSON-RPC stdio with no stdout logger ([ui/](../packages/ui/README.md)). A deployment is a thin `cordis.yml` leaf: swappable backends, one app entry, and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)).
+`dsh-agent-core` is the default composition bundle: one plugin loading the shared spine ([README](../packages/core/agent-core/README.md)). App packages compose it with a front door and boot `bin`: `dsh-stdio-agent` for terminal REPL, and `dsh-acp-agent` for ACP over JSON-RPC stdio with no stdout logger ([ui/](../packages/ui/README.md)). A deployment is a thin `cordis.yml` leaf: swappable backends, one app entry, and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)).
 
 ### Where New Behavior Goes
 
@@ -143,6 +145,7 @@ New behavior should attach to a documented extension point; changing the shipped
 | Add a model-facing capability | register a tool on `ctx.tools`; schemas flow into prompt assembly |
 | Add command execution | implement and register a `ctx.bash` backend |
 | Add filesystem access or policy | implement a `ctx.fs` provider or listen on `fs/*` policy events |
+| Confine spawned processes | a `ctx.sandbox` backend; consumers wrap their argv before spawning |
 | Intercept prompts, requests, tool use, or continuation | listen on the relevant `agent/*` or `tools/*` waterfall |
 | Add a session-stable request prefix outside history | compose it on `agent/session-prefix`, once per loop instance; logged on the request header |
 | Add UI or editor integration | drive `ctx.agents` and render from `session/event` |
@@ -156,4 +159,4 @@ The [extension cookbook](cookbook/extension-cookbook.md) carries plugin skeleton
 - Exact event and service signatures in [events](cordis-catalog/events.md)
 - [services](cordis-catalog/services.md) catalogs
 - package contracts in the [package map](../packages/README.md)
-- [RFCs](rfc/README.md)
+- [RFCs](rfc/README.md)

docs/capability-seams.md

@@ -33,19 +33,29 @@ flowchart LR
   pkg_tool_ask_user["tool-ask-user"]
   pkg_tool_bash["tool-bash"]
   pkg_tool_cordis["tool-cordis"]
+  pkg_tool_skill["tool-skill"]
   pkg_tool_subagent["tool-subagent"]
   pkg_tool_todo["tool-todo"]
   pkg_user_interaction["user-interaction"]
   svc_userInteraction["ctx.userInteraction<br/>Human question/answer seam"]
   pkg_stdio_agent["stdio-agent"]
+  pkg_skill["skill"]
+  svc_skills["ctx.skills<br/>Skill provider registry"]
+  pkg_skill_local["skill-local"]
   svc_agents["ctx.agents<br/>Agent registry"]
   svc_agentLoop["ctx.agentLoop<br/>Concrete loop driver"]
   pkg_agent_core["agent-core"]
   pkg_bash["bash"]
   svc_bash["ctx.bash<br/>Bash executor seam"]
   pkg_bash_local["bash-local"]
+  pkg_bash_sandbox["bash-sandbox"]
   pkg_hooks_claude["hooks-claude"]
   pkg_hooks_codex["hooks-codex"]
+  pkg_sandbox["sandbox"]
+  svc_sandbox["ctx.sandbox<br/>Process-sandbox seam"]
+  pkg_sandbox_local["sandbox-local"]
+  pkg_approval["approval"]
+  svc_approval["ctx.approval<br/>Approval seam"]
   pkg_code_runtime["code-runtime"]
   svc_codeRuntime["ctx.codeRuntime<br/>Code-execution seam"]
   pkg_code_runtime_worker["code-runtime-worker"]
@@ -71,11 +81,14 @@ flowchart LR
   svc_workflows["ctx.workflows<br/>Workflow script engine"]
   pkg_workflow_workerthread["workflow-workerthread"]
   pkg_tool_workflow["tool-workflow"]
+  pkg_acp --> svc_approval
   pkg_acp --> svc_userInteraction
   pkg_agent --> svc_agents
   pkg_agent_loop --> svc_agentLoop
+  pkg_approval --> svc_approval
   pkg_bash --> svc_bash
   pkg_bash_local --> svc_bash
+  pkg_bash_sandbox --> svc_bash
   pkg_code_runtime --> svc_codeRuntime
   pkg_code_runtime_worker --> svc_codeRuntime
   pkg_compact --> svc_compact
@@ -86,10 +99,14 @@ flowchart LR
   pkg_llm_deepseek --> svc_llm
   pkg_llm_pi_ai --> svc_llm
   pkg_llm_replay --> svc_llm
+  pkg_sandbox --> svc_sandbox
+  pkg_sandbox_local --> svc_sandbox
   pkg_session --> svc_sessions
   pkg_session_persistence --> svc_sessionPersistence
   pkg_session_persistence_jsonl --> svc_sessionPersistence
   pkg_session_persistence_sqlite --> svc_sessionPersistence
+  pkg_skill --> svc_skills
+  pkg_skill_local --> svc_skills
   pkg_stdio_agent --> svc_userInteraction
   pkg_subagent --> svc_subagents
   pkg_subagent_acp --> svc_subagents
@@ -112,6 +129,8 @@ flowchart LR
   svc_agents --> pkg_invariants
   svc_agents --> pkg_stdio_agent
   svc_agents --> pkg_subagent_inprocess
+  svc_approval --> pkg_tool_bash
+  svc_approval --> pkg_tools
   svc_bash --> pkg_hooks_claude
   svc_bash --> pkg_hooks_codex
   svc_bash --> pkg_tool_bash
@@ -120,6 +139,7 @@ flowchart LR
   svc_fs --> pkg_tool_fs
   svc_llm --> pkg_agent_loop
   svc_llm --> pkg_compact_basic
+  svc_sandbox --> pkg_bash_sandbox
   svc_sessionPersistence --> pkg_acp
   svc_sessionPersistence --> pkg_agent_loop
   svc_sessions --> pkg_agent
@@ -127,6 +147,7 @@ flowchart LR
   svc_sessions --> pkg_invariants
   svc_sessions --> pkg_session_persistence
   svc_sessions --> pkg_subagent_inprocess
+  svc_skills --> pkg_tool_skill
   svc_subagents --> pkg_tool_subagent
   svc_systemPrompt --> pkg_agent_loop
   svc_systemPrompt --> pkg_tool_fs
@@ -138,6 +159,7 @@ flowchart LR
   svc_tools --> pkg_tool_bash
   svc_tools --> pkg_tool_cordis
   svc_tools --> pkg_tool_fs
+  svc_tools --> pkg_tool_skill
   svc_tools --> pkg_tool_subagent
   svc_tools --> pkg_tool_todo
   svc_tools --> pkg_tool_web
@@ -155,11 +177,14 @@ flowchart LR
 | `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. |
 | `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. |
 | `ctx.systemPrompt` | `core` | [`system-prompt`](../packages/core/system-prompt) | - | [`agent-loop`](../packages/core/agent-loop), [`tools`](../packages/core/tools), [`tool-fs`](../packages/fs/tool-fs), [`tool-web`](../packages/web/tool-web) | - | Collects prompt sections and model-facing tool schemas for each step. |
-| `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers tool definitions, exposes schemas to the prompt, and routes calls through tools/pre-execute and tools/post-execute. |
+| `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-skill`](../packages/skill/tool-skill), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers tool definitions, exposes schemas to the prompt, and routes calls through tools/pre-execute and tools/post-execute. |
 | `ctx.userInteraction` | `seam` | [`user-interaction`](../packages/ui/user-interaction) | [`stdio-agent`](../packages/ui/stdio-agent), [`acp`](../packages/ui/acp) | [`tool-ask-user`](../packages/ui/tool-ask-user), [`stdio-agent`](../packages/ui/stdio-agent), [`acp`](../packages/ui/acp) | - | UI front doors provide the active human-answer provider; tool-ask-user pauses a tool call on the provider-neutral ask() promise. |
+| `ctx.skills` | `seam` | [`skill`](../packages/skill/skill) | [`skill-local`](../packages/skill/skill-local) | [`tool-skill`](../packages/skill/tool-skill) | - | Merges provider skill catalogs; tool-skill renders the session-prefix catalog and loads complete skill bodies. |
 | `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-agent`](../packages/ui/stdio-agent), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles and the create/resume factory seam. |
 | `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-core`](../packages/core/agent-core) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. |
-| `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors can replace bash-local. |
+| `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local), [`bash-sandbox`](../packages/bash/bash-sandbox) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them. |
+| `ctx.sandbox` | `seam` | [`sandbox`](../packages/sandbox/sandbox) | [`sandbox-local`](../packages/sandbox/sandbox-local) | [`bash-sandbox`](../packages/bash/bash-sandbox) | - | Consumers hand over the exact argv they are about to spawn; same-world backends wrap it under a per-call policy and report enforcement. |
+| `ctx.approval` | `seam` | `approval` | [`acp`](../packages/ui/acp) | [`tools`](../packages/core/tools), [`tool-bash`](../packages/bash/tool-bash) | - | One-shot permission decisions dispatched over the `approval/request` waterfall; answerers are listeners (the ACP bridge for its own agents), absence fails closed to `unavailable`. |
 | `ctx.codeRuntime` | `seam` | [`code-runtime`](../packages/code-runtime/code-runtime) | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | [`tools`](../packages/core/tools) | - | Runs one model-written program against host-provided async bindings; backends differ by substrate and language (the tool registry consumes it for Code Mode). |
 | `ctx.fs` | `seam` | [`fs`](../packages/fs/fs) | [`fs-local`](../packages/fs/fs-local) | [`tool-fs`](../packages/fs/tool-fs) | [`fs-policy`](../packages/fs/fs-policy) | tool-fs executes read/write/edit through ctx.fs; fs-policy contributes observed-state checks through the fs/* event gate. |
 | `ctx.compact` | `seam` | [`compact`](../packages/compact/compact) | [`compact-basic`](../packages/compact/compact-basic) | [`compact-basic`](../packages/compact/compact-basic) | - | The basic backend currently consumes the pre-step event directly; a model-facing compact tool remains deferred. |

docs/config-catalog.md

@@ -31,7 +31,7 @@ export interface AcpConfig {
 
 Depends on: `Stream` (`@agentclientprotocol/sdk`)
 
-Source: [`packages/ui/acp/src/index.ts:236`](../packages/ui/acp/src/index.ts)
+Source: [`packages/ui/acp/src/index.ts:248`](../packages/ui/acp/src/index.ts)
 
 ## `@deepseek-ai/dsh-acp-agent`
 
@@ -56,10 +56,12 @@ export interface Config {
   tools?: ToolsConfig
   /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */
   persistenceRoot?: string
+  /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */
+  skills?: agentCore.SkillConfig
 }
 ```
 
-Depends on: [`ToolsConfig`](#deepseek-aidsh-tools)
+Depends on: [`agentCore`](../packages/core/agent-core/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools)
 
 Source: [`packages/ui/acp-agent/src/index.ts:52`](../packages/ui/acp-agent/src/index.ts)
 
@@ -71,12 +73,12 @@ Source: [`packages/ui/acp-agent/src/index.ts:52`](../packages/ui/acp-agent/src/i
  * `agents` to the agent loop (an app that pre-creates no agents, like the ACP
  * bridge, simply omits it), `persona` and `toolOrder` to the system-prompt
  * plugin (the deployment's persona section and the explicit model-facing tool
- * order), the `tools` object to the tool registry (its presentation `mode`).
- * Every field is optional INPUT here because each owner's schema
- * supplies the default (`[]` / `''` / absent — lexicographic / `native`); the
- * schema is the INTERSECTION of the owners' own schemas (the registry's
- * nested under its `tools` key), so validation and defaulting can never
- * drift from them.
+ * order), the `tools` object to the tool registry (its presentation `mode`),
+ * and `skills` to the skill registry/local provider/tool consumer. Every field
+ * is optional INPUT here because each owner's schema supplies the default;
+ * the schema is the INTERSECTION of the owners' own schemas (with registry
+ * schemas nested under their bundle keys), so validation and defaulting can
+ * never drift from them.
  */
 export interface Config {
   /** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */
@@ -87,12 +89,24 @@ export interface Config {
   toolOrder?: SystemPromptConfig['toolOrder']
   /** The tool registry's config — its presentation `mode` (see dsh-tools' `Config`). */
   tools?: ToolsConfig
+  /** Skill registry, local provider, and model-facing consumer config. */
+  skills?: SkillConfig
+}
+
+/** Skill bundle config forwarded to the registry, local provider, and model-facing consumer. */
+export interface SkillConfig {
+  /** Registry-level discovery cache settings. */
+  registry?: SkillRegistryConfig
+  /** Local filesystem skill provider settings. */
+  local?: SkillLocal.Config
+  /** Model-facing skill catalog and tool settings. */
+  tool?: toolSkill.Config
 }
 ```
 
-Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`ToolsConfig`](#deepseek-aidsh-tools)
+Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts)
 
-Source: [`packages/core/agent-core/src/index.ts:71`](../packages/core/agent-core/src/index.ts)
+Source: [`packages/core/agent-core/src/index.ts:87`](../packages/core/agent-core/src/index.ts)
 
 ## `@deepseek-ai/dsh-agent-loop`
 
@@ -108,6 +122,8 @@ export interface Config {
   agents: (AgentOptions & {
     /** Agent id to register under; also seeds the fresh per-run session id (`${id}-session-<uuid>`). */
     id: AgentId
+    /** Optional workspace cwd for the config-created fresh session. */
+    cwd?: string
     /**
      * If set, the config agent RESUMES this persisted session id instead of
      * starting a fresh `${id}-session-<uuid>`. Sourced from an env var in
@@ -150,6 +166,33 @@ export interface Config {
 
 Source: [`packages/bash/bash-local/src/index.ts:29`](../packages/bash/bash-local/src/index.ts)
 
+## `@deepseek-ai/dsh-bash-sandbox`
+
+Requires: `sandbox`
+
+```ts config-catalog
+/**
+ * Plugin config: the local executor's knobs plus the sandbox policy. All
+ * optional — `static Config` supplies the defaults (`mode: 'read-only'` is the
+ * fail-safe default; an example that wants a workspace-writable agent opts in
+ * explicitly). The runner choice is NOT configured here: which platform
+ * backend confines the command is the `ctx.sandbox` provider's config.
+ */
+export interface Config extends LocalConfig {
+  /** File-sandbox mode commands run under (default: `read-only`). */
+  mode?: SandboxMode
+  /**
+   * Root directory `workspace-write` mode may write under (default: the
+   * executor's default working directory — `cwd`, else `process.cwd()`).
+   */
+  workspaceRoot?: string
+}
+```
+
+Depends on: [`LocalConfig`](#deepseek-aidsh-bash-local) · [`SandboxMode`](core-data-structures/sandbox.md)
+
+Source: [`packages/bash/bash-sandbox/src/index.ts:60`](../packages/bash/bash-sandbox/src/index.ts)
+
 ## `@deepseek-ai/dsh-code-runtime-worker`
 
 ```ts config-catalog
@@ -430,6 +473,53 @@ export interface Config {
 
 Source: [`packages/guard/repeat-tool-guard/src/index.ts:55`](../packages/guard/repeat-tool-guard/src/index.ts)
 
+## `@deepseek-ai/dsh-sandbox-local`
+
+```ts config-catalog
+/** Plugin config. All optional — `static Config` supplies the defaults. */
+export interface Config {
+  /**
+   * Override the sandbox runner argv (the bwrap-shaped profile arguments are
+   * appended). A NON-EMPTY argv is the operator's assertion that this runner
+   * exists and FULLY enforces the profile (confinement reports
+   * `enforcement: 'full'`, and — the runner's kernel mechanism being unknown
+   * — carries both Linux file-denial dialects as its denial signatures) —
+   * the runner chain and its probes are skipped,
+   * and a broken runner fails loudly at execution time. The operator also
+   * supplies {@link runnerFailureSignatures}, which distinguish the runner
+   * refusing its profile from the wrapped command failing normally.
+   * Absent (or empty — the schema normalizes an omitted array to `[]`): the
+   * built-in platform chains — Linux `bwrap` then the Landlock launcher
+   * (probed in that order), darwin `sandbox-exec` (the sole candidate,
+   * selected without a probe). Used for custom/alternative runners and
+   * for deterministic fake runners in keyless test tiers.
+   */
+  runnerCommand?: string[]
+  /**
+   * Case-insensitive stderr substrings emitted when a configured
+   * {@link runnerCommand} refuses its profile before executing the wrapped
+   * command. Required and non-empty with `runnerCommand`; rejected without
+   * it. Missing/unexecutable runner errors are added automatically from
+   * `runnerCommand[0]`, while these signatures cover an executable runner's
+   * own failure dialect.
+   */
+  runnerFailureSignatures?: string[]
+  /**
+   * Per-probe timeout in milliseconds for the chain's functional probes
+   * (default: 5000; must be a positive finite number — Node treats a 0
+   * `spawnSync` timeout as UNBOUNDED, so 0 is rejected at construction). A
+   * probe that exceeds it reads as an unusable rung, so a
+   * host slow enough to trip the default — cold NFS mounts, heavily loaded
+   * CI — would otherwise be misclassified `SANDBOX_UNAVAILABLE` with no
+   * config escape. Bounds ONE probe, and the chain walk runs each at most once
+   * per provider lifetime.
+   */
+  probeTimeoutMs?: number
+}
+```
+
+Source: [`packages/sandbox/sandbox-local/src/index.ts:36`](../packages/sandbox/sandbox-local/src/index.ts)
+
 ## `@deepseek-ai/dsh-session-persistence-jsonl`
 
 Requires: `sessions`
@@ -483,6 +573,36 @@ export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist'
 
 Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:51`](../packages/session-persistence/session-persistence-sqlite/src/index.ts)
 
+## `@deepseek-ai/dsh-skill`
+
+```ts config-catalog
+/** Skill registry configuration. */
+export interface Config {
+  /** Maximum number of completed cwd/provider catalog snapshots kept in memory. */
+  collectCacheMaxEntries?: number
+}
+```
+
+Source: [`packages/skill/skill/src/index.ts:112`](../packages/skill/skill/src/index.ts)
+
+## `@deepseek-ai/dsh-skill-local`
+
+Requires: `skills`
+
+```ts config-catalog
+/** Local filesystem skill provider configuration. */
+export interface Config {
+  /** DeepSeek Harness config root. Defaults to `$DSH_HOME` or `~/.dsh`. */
+  dshHome?: string
+  /** Shared agent config root. Defaults to `$DSH_AGENTS_HOME` or `~/.agents`. */
+  agentsHome?: string
+  /** Additional skill roots scanned after project roots and before user roots. */
+  customSkillDirs?: string[]
+}
+```
+
+Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-local/src/index.ts)
+
 ## `@deepseek-ai/dsh-stdio-agent`
 
 ```ts config-catalog
@@ -492,7 +612,9 @@ Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:5
  * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is
  * the deployment persona (forwarded to the system-prompt plugin); `toolOrder`
  * is the explicit model-facing tool order (forwarded to the system-prompt plugin);
- * `persistenceRoot` is the JSONL backend's directory; `welcome` is the UI banner.
+ * fresh sessions use `process.cwd()` as their workspace cwd; resumed sessions
+ * keep their persisted cwd. `persistenceRoot` is the JSONL backend's directory;
+ * `welcome` is the UI banner.
  */
 export interface Config {
   /** Model name for the `main` agent (must have a registered adapter). */
@@ -507,6 +629,8 @@ export interface Config {
   persistenceRoot?: string
   /** stdin-chat banner printed once on start. Defaults to `'ready.'`. */
   welcome?: string
+  /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */
+  skills?: agentCore.SkillConfig
   /**
    * If set, the `main` agent RESUMES this persisted session id instead of
    * starting fresh. Sourced from an env var in the leaf `cordis.yml`
@@ -516,9 +640,9 @@ export interface Config {
 }
 ```
 
-Depends on: [`ToolsConfig`](#deepseek-aidsh-tools)
+Depends on: [`agentCore`](../packages/core/agent-core/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools)
 
-Source: [`packages/ui/stdio-agent/src/index.ts:63`](../packages/ui/stdio-agent/src/index.ts)
+Source: [`packages/ui/stdio-agent/src/index.ts:65`](../packages/ui/stdio-agent/src/index.ts)
 
 ## `@deepseek-ai/dsh-subagent-acp`
 
@@ -721,6 +845,20 @@ export interface Config {
 
 Source: [`packages/fs/tool-fs/src/index.ts:48`](../packages/fs/tool-fs/src/index.ts)
 
+## `@deepseek-ai/dsh-tool-skill`
+
+Requires: `tools` · `skills`
+
+```ts config-catalog
+/** Model-facing skill catalog configuration. */
+export interface Config {
+  /** Maximum normalized description length rendered in the session catalog; minimum 3. */
+  catalogDescriptionMaxLength?: number
+}
+```
+
+Source: [`packages/skill/tool-skill/src/index.ts:19`](../packages/skill/tool-skill/src/index.ts)
+
 ## `@deepseek-ai/dsh-tool-subagent`
 
 Requires: `tools` · `subagents`
@@ -818,7 +956,38 @@ export interface Config {
 export type ToolPresentationMode = 'native' | 'code' | 'both'
 ```
 
-Source: [`packages/core/tools/src/index.ts:319`](../packages/core/tools/src/index.ts)
+Source: [`packages/core/tools/src/index.ts:323`](../packages/core/tools/src/index.ts)
+
+## `@deepseek-ai/dsh-user-approval`
+
+```ts config-catalog
+/** Plugin config. All optional — `static Config` supplies the defaults. */
+export interface Config {
+  /**
+   * The deployment's default {@link ApprovalPolicy} for sessions without an
+   * `approval/policy` override — `'ask'` delegates to the composed answerers
+   * (fail-closed with none); `'never'` auto-rejects every ask without
+   * prompting (the deterministic CI/unattended stance).
+   */
+  policy?: ApprovalPolicy
+}
+
+/**
+ * A session's approval policy — what happens to an {@link ApprovalService}
+ * ask BEFORE any interactive answerer sees it:
+ *
+ * - `'ask'` (the default) — delegate to the composed answerers; with none
+ *   composed the chain falls through to the fail-closed `'unavailable'`
+ *   (exactly today's behavior).
+ * - `'never'` — never prompt anyone: every ask resolves `'rejected'`
+ *   deterministically. The strict headless stance (CI, unattended runs) and
+ *   the only policy value stated in the system prompt — unlike `'ask'`, its
+ *   outcome is knowable without asking, so stating it cannot overclaim.
+ */
+export type ApprovalPolicy = 'ask' | 'never'
+```
+
+Source: [`packages/ui/user-approval/src/index.ts:258`](../packages/ui/user-approval/src/index.ts)
 
 ## `@deepseek-ai/dsh-web`
 
@@ -984,6 +1153,7 @@ Abstract service classes — a deployment loads a concrete implementation packag
 - `@deepseek-ai/dsh-code-runtime` — abstract `CodeRuntime` ([`packages/code-runtime/code-runtime/src/index.ts`](../packages/code-runtime/code-runtime/src/index.ts))
 - `@deepseek-ai/dsh-compact` — abstract `CompactService` ([`packages/compact/compact/src/index.ts`](../packages/compact/compact/src/index.ts))
 - `@deepseek-ai/dsh-fs` — abstract `FileSystem` ([`packages/fs/fs/src/index.ts`](../packages/fs/fs/src/index.ts))
+- `@deepseek-ai/dsh-sandbox` — abstract `SandboxProvider` ([`packages/sandbox/sandbox/src/index.ts`](../packages/sandbox/sandbox/src/index.ts))
 - `@deepseek-ai/dsh-session-persistence` — abstract `SessionPersistence` ([`packages/session-persistence/session-persistence/src/index.ts`](../packages/session-persistence/session-persistence/src/index.ts))
 - `@deepseek-ai/dsh-workflow` — abstract `WorkflowService` ([`packages/workflow/workflow/src/index.ts`](../packages/workflow/workflow/src/index.ts))
 

docs/cookbook/extension-cookbook.md

@@ -56,7 +56,7 @@ export function apply(ctx: Context) {
 
 A *client driver* is a UI plugin whose "user" is another program speaking a wire protocol rather than a human at a terminal. It owns the process's stdio (so it must run with **no stdout logger** — every non-protocol byte corrupts the stream), creates/resumes agents on demand through the `dsh-agent` factory seam, translates harness events (`session/event`, `agent/*`) into outbound protocol messages, and translates inbound requests back into `agent.send()` / `agent.cancel()`. Two harness-specific contracts make it correct: resolve each request exactly once off a settle signal (settle from the durable `turn/end` session event — the boundary is a session event, not an `agent/*` mirror — with `agent/status` as the fallback if a peer listener starved yours), and tear each agent down through its `AgentHandle.dispose()` (which stops the loop, `await`s its exit, and unregisters), not just `cancel()` — disposal must *reach* quiescence, not merely request it.
 
-`packages/ui/acp` is the worked example: it bridges the agent to the Agent Client Protocol (JSON-RPC over stdio) so Zed and other ACP editors can drive it. See its README for the full method surface and the deferred-permission-gate note.
+`packages/ui/acp` is the worked example: it bridges the agent to the Agent Client Protocol (JSON-RPC over stdio) so Zed and other ACP editors can drive it. See its README for the full method surface and the permission-prompt answerer it registers on the approval seam.
 
 ```ts
 import type { Context } from 'cordis'
@@ -100,7 +100,7 @@ Every product feature maps to a listener on a documented extension seam — the
 | AGENTS.md (subdir, on-touch) + file-change notices | `agent.inject()` from a watcher / tool-result listener |
 | Built-in tools | `ctx.tools.register()`; schemas flow into the assembly automatically — the `dsh-tool-*` families (bash, fs, web, subagent, todo) are the shipped examples |
 | ToolSearch / progressive disclosure | filter tools at `system-prompt/assemble` (the assembly carries the schemas; the loop logs the result as the request header, so disclosure stays reconstructable) |
-| Tool sandbox (landlock / sandbox-exec) | `tools/pre-execute` (deny), or a sandboxing `BashExecutor` on the `dsh-bash` seam |
+| Subprocess sandbox (landlock / sandbox-exec) | `tools/pre-execute` (deny), or a sandboxing `BashExecutor` on the `dsh-bash` seam |
 | Permission system / AskUserQuestion | `tools/pre-execute` (deny/ask); register an ask tool |
 | Plan mode | `tools/pre-execute` (deny writes) + a mode prompt section via `ctx.systemPrompt.section()` or `agent.inject()` (model-visible ⟺ logged: `agent/request` shapes call config only) |
 | Sub-agent delegation | the `ctx.subagents` provider registry (`dsh-subagent-spawn`/`-fork`/`-acp`) + `dsh-tool-subagent` exposing one configured provider to the model |

docs/cordis-catalog/events.md

@@ -163,6 +163,20 @@ Types: [Agent](../core-data-structures/core.md)
 
 Source: [`packages/core/agent/src/types.ts:464`](../../packages/core/agent/src/types.ts)
 
+## `approval/*`
+
+### `approval/request` — waterfall
+
+Waterfall asking the composed answerers to decide one approval request. Dispatched only from ApprovalService.request — callers go through the service (which owns cancellation and the audit events), never through `ctx.waterfall` directly. A listener that can answer for this request's agent returns an outcome WITHOUT calling `next()` (the decision slot is single-occupancy, first listener to answer wins); a listener that does not recognize the agent MUST call `next()` so another answerer — or the fail-closed default `'unavailable'` — gets the question. Throwing is contained by the service and yields `'unavailable'`.
+
+```ts cordis-catalog
+'approval/request'(this: ApprovalService, req: ApprovalRequest, next: () => Promise<ApprovalOutcome>): Promise<ApprovalOutcome>
+```
+
+Types: [ApprovalOutcome](../core-data-structures/approval.md) · [ApprovalRequest](../core-data-structures/approval.md)
+
+Source: [`packages/ui/user-approval/src/index.ts:64`](../../packages/ui/user-approval/src/index.ts)
+
 ## `fs/*`
 
 ### `fs/edit-intent` — waterfall
@@ -249,6 +263,28 @@ Awaited durability checkpoint. The agent loop awaits `ctx.parallel('session/flus
 
 Source: [`packages/core/session/src/index.ts:57`](../../packages/core/session/src/index.ts)
 
+## `skill/*`
+
+### `skill/provider-added` — emit
+
+A skill provider became resolvable in the `ctx.skills` registry. Consumers can observe this instead of depending on Cordis plugin load order, which is concurrent for sibling plugins.
+
+```ts cordis-catalog
+'skill/provider-added'(provider: SkillProvider): void
+```
+
+Source: [`packages/skill/skill/src/index.ts:130`](../../packages/skill/skill/src/index.ts)
+
+### `skill/provider-removed` — emit
+
+A skill provider left the registry because its plugin fiber was disposed.
+
+```ts cordis-catalog
+'skill/provider-removed'(name: string): void
+```
+
+Source: [`packages/skill/skill/src/index.ts:136`](../../packages/skill/skill/src/index.ts)
+
 ## `subagent/*`
 
 ### `subagent/end` — emit
@@ -323,7 +359,7 @@ A tool was registered or unregistered (the available tool set changed).
 'tools/change'(): void
 ```
 
-Source: [`packages/core/tools/src/index.ts:132`](../../packages/core/tools/src/index.ts)
+Source: [`packages/core/tools/src/index.ts:135`](../../packages/core/tools/src/index.ts)
 
 ### `tools/execute` — waterfall
 
@@ -335,7 +371,7 @@ Around-dispatch waterfall wrapping the registry's core tool dispatch, between th
 
 Types: [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md)
 
-Source: [`packages/core/tools/src/index.ts:111`](../../packages/core/tools/src/index.ts)
+Source: [`packages/core/tools/src/index.ts:114`](../../packages/core/tools/src/index.ts)
 
 ### `tools/post-execute` — waterfall
 
@@ -347,11 +383,11 @@ Waterfall AFTER a tool runs — where hook plugins inspect the result and accept
 
 Types: [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md)
 
-Source: [`packages/core/tools/src/index.ts:127`](../../packages/core/tools/src/index.ts)
+Source: [`packages/core/tools/src/index.ts:130`](../../packages/core/tools/src/index.ts)
 
 ### `tools/pre-execute` — waterfall
 
-Waterfall BEFORE a tool runs — the gate where sandbox, permission, and hook plugins allow or deny a call (Claude Code's `PreToolUse`). Listeners receive `(exec, next)`: call `next()` to delegate to the default (allow), or return a PreToolDecision without calling `next()` to short-circuit. A `deny` skips dispatch and yields an `isError` result; the tool body never runs. Input rewrite is deliberately NOT offered here (see PreToolDecision); `ask` degrades to deny until the permission system lands (`FIXME(permissions)`).
+Waterfall BEFORE a tool runs — the gate where sandbox, permission, and hook plugins allow or deny a call (Claude Code's `PreToolUse`). Listeners receive `(exec, next)`: call `next()` to delegate to the default (allow), or return a PreToolDecision without calling `next()` to short-circuit. A `deny` skips dispatch and yields an `isError` result; the tool body never runs. Input rewrite is deliberately NOT offered here (see PreToolDecision); `ask` is serviced by the `ctx.approval` seam when one is mounted, and degrades to deny otherwise.
 
 ```ts cordis-catalog
 'tools/pre-execute'(this: ToolRegistry, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>
@@ -359,7 +395,7 @@ Waterfall BEFORE a tool runs — the gate where sandbox, permission, and hook pl
 
 Types: [ToolExecution](../core-data-structures/tools.md)
 
-Source: [`packages/core/tools/src/index.ts:91`](../../packages/core/tools/src/index.ts)
+Source: [`packages/core/tools/src/index.ts:94`](../../packages/core/tools/src/index.ts)
 
 ## `workflow/*`
 

docs/cordis-catalog/services.md

@@ -16,12 +16,12 @@ The agent-loop plugin (`ctx.agentLoop`): creates ReactLoopAgents, runs their loo
 The loop itself is deliberately thin — every behavior beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy declared in @deepseek-ai/dsh-agent.
 
 ```ts cordis-catalog
-create(id: AgentId, options: AgentOptions = {}): ReactLoopAgent
+create(id: AgentId, options: AgentOptions = {}, meta: Pick<SessionHeader, 'cwd'> = {}): ReactLoopAgent
 createAgent(options: CreateAgentOptions): AgentHandle
 async resume(options: ResumeAgentOptions): Promise<AgentHandle>
 ```
 
-Source: [`packages/core/agent-loop/src/index.ts:68`](../../packages/core/agent-loop/src/index.ts)
+Source: [`packages/core/agent-loop/src/index.ts:70`](../../packages/core/agent-loop/src/index.ts)
 
 ## `ctx.agents` — `AgentRegistry`
 
@@ -40,6 +40,20 @@ Types: [Agent](../core-data-structures/core.md)
 
 Source: [`packages/core/agent/src/index.ts:117`](../../packages/core/agent/src/index.ts)
 
+## `ctx.approval` — `ApprovalService`
+
+The `ctx.approval` service: dispatches ApprovalRequests to the `approval/request` waterfall and audits every ask/outcome pair to the requesting agent's session log. Stateless between requests — grants are returned to the caller, never stored here.
+
+Owns the policy tier too (`effective = fold(the session's 'approval/policy' events) ?? config.policy`): `request()` resolves `'never'` to `'rejected'` before dispatching any interactive answerer, a per-agent prompt section states a `'never'` policy (and only that one in prose — an `'ask'` promise could overclaim an answerer that headless compositions do not have), and an `agent/pre-step` narrator injects at most one coalesced notice when a session's effective policy moved past what the model was last told.
+
+```ts cordis-catalog
+async request(req: ApprovalRequest): Promise<ApprovalOutcome>
+```
+
+Types: [ApprovalOutcome](../core-data-structures/approval.md) · [ApprovalRequest](../core-data-structures/approval.md)
+
+Source: [`packages/ui/user-approval/src/index.ts:282`](../../packages/ui/user-approval/src/index.ts)
+
 ## `ctx.bash` — `BashExecutor` (abstract seam)
 
 Abstract bash execution service. Subclass, implement the abstract methods, and load the subclass as a plugin — it registers as `ctx.bash` (one implementation per context; loading a second throws, which is cordis' standard duplicate-service behavior).
@@ -65,7 +79,7 @@ onTaskDone(listener: BashTaskListener): () => void
 
 Types: [BashExecRequest](../core-data-structures/bash.md) · [BashExecSpec](../core-data-structures/bash.md) · [BashRunResult](../core-data-structures/bash.md) · [BashTask](../core-data-structures/bash.md) · [BashTaskRead](../core-data-structures/bash.md)
 
-Source: [`packages/bash/bash/src/index.ts:59`](../../packages/bash/bash/src/index.ts)
+Source: [`packages/bash/bash/src/index.ts:62`](../../packages/bash/bash/src/index.ts)
 
 ## `ctx.codeRuntime` — `CodeRuntime` (abstract seam)
 
@@ -147,6 +161,24 @@ Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../co
 
 Source: [`packages/llm/llm/src/index.ts:88`](../../packages/llm/llm/src/index.ts)
 
+## `ctx.sandbox` — `SandboxProvider` (abstract seam)
+
+Abstract process-sandbox service. Subclass, implement confine, and load the subclass as a plugin — it registers as `ctx.sandbox` (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior).
+
+Semantics every implementation must honor:
+
+- confine either returns an argv whose runner ENFORCES the policy or fails closed — at `confine` time with SandboxUnavailableError (no backend for this host), or at EXECUTION time by the runner itself refusing to run the command (exiting without exec'ing it, identified by ConfinedArgv.runnerFailureSignatures). A silent unconfined passthrough is never a legal outcome on either path.
+- Probing exists to ARBITRATE between multiple candidate backends and may be skipped when a platform has exactly one: the sole candidate is selected directly and the runner's exec-time fail-closed refusal carries the safety property. When probing does run, it is functional (actually enforcing a profile, not a version check), at most once per provider lifetime; `confine` itself spawns nothing beyond that one-time probing.
+- The returned ConfinedArgv.enforcement states the backend's actual completeness for THIS host; `partial` is reported, never silently upgraded to `full`.
+
+```ts cordis-catalog
+abstract confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv
+```
+
+Types: [ConfinedArgv](../core-data-structures/sandbox.md) · [SandboxPolicy](../core-data-structures/sandbox.md)
+
+Source: [`packages/sandbox/sandbox/src/index.ts:180`](../../packages/sandbox/sandbox/src/index.ts)
+
 ## `ctx.sessionPersistence` — `SessionPersistence` (abstract seam)
 
 Abstract durable session-persistence service. Subclass, implement the abstract methods, and load the subclass as a plugin — it registers as `ctx.sessionPersistence` (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior).
@@ -188,6 +220,19 @@ fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId):
 
 Source: [`packages/core/session/src/index.ts:405`](../../packages/core/session/src/index.ts)
 
+## `ctx.skills` — `SkillService`
+
+Registry of skill providers. It merges provider catalogs with stable first-wins duplicate handling, exposes sorted model-visible summaries, and loads full skill bodies on demand.
+
+```ts cordis-catalog
+registerProvider(provider: SkillProvider): () => void
+register(skill: SkillRegistration): () => void
+async list(options: SkillLookupOptions = {}): Promise<SkillSummary[]>
+async get(name: string, options: SkillLookupOptions = {}): Promise<SkillDefinition | undefined>
+```
+
+Source: [`packages/skill/skill/src/index.ts:157`](../../packages/skill/skill/src/index.ts)
+
 ## `ctx.subagents` — `SubagentService`
 
 The `subagents` service: a registry of named SubagentProviders and a capability-checked start surface.
@@ -227,7 +272,7 @@ async execute(exec: ToolExecution): Promise<ToolExecutionResult>
 
 Types: [ToolDefinition](../core-data-structures/tools.md) · [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md)
 
-Source: [`packages/core/tools/src/index.ts:345`](../../packages/core/tools/src/index.ts)
+Source: [`packages/core/tools/src/index.ts:349`](../../packages/core/tools/src/index.ts)
 
 ## `ctx.userInteraction` — `UserInteractionService`
 

docs/core-data-structures/approval.md

@@ -0,0 +1,64 @@
+# User Approval
+
+The user-approval seam of [dsh-user-approval](../../packages/ui/user-approval) answers one question: may this specific action proceed? It owns the shared request/outcome vocabulary, the `ctx.approval` dispatch service, the `approval/request` answerer waterfall, the log-only audit pair, and the per-session `ask`/`never` policy. UI channels such as [dsh-acp](../../packages/ui/acp) provide answerers; callers such as [dsh-tools](../../packages/core/tools) and [dsh-tool-bash](../../packages/bash/tool-bash) consume the closed outcome and fail closed unless it is `allowed-once`.
+
+Source: [`packages/ui/user-approval/src/index.ts`](../../packages/ui/user-approval/src/index.ts)
+
+## Identity and outcome
+
+Every request receives a fresh `ApprovalRequestId`. The brand pairs the `approval/asked` and `approval/decided` audit events without making approval ids interchangeable with tool-call, session, or agent ids.
+
+```ts type-equiv
+type ApprovalRequestId = Branded<'ApprovalRequestId'>
+```
+
+`ApprovalOutcome` is closed and fail-closed. `allowed-once` grants only the asked-about action; callers deny on `rejected`, `cancelled`, and `unavailable`. A missing, non-owning, throwing, or non-conforming answerer becomes `unavailable` rather than opening the gate.
+
+```ts type-equiv
+type ApprovalOutcome = 'allowed-once' | 'rejected' | 'cancelled' | 'unavailable'
+```
+
+## Per-session policy
+
+`ApprovalPolicy` determines what happens before interactive answerers run. `ask` delegates to the composed answerer chain, whose no-answer default is `unavailable`; `never` deterministically returns `rejected` without dispatching any answerer. The effective value is the last `approval/policy` event in the session log, falling back to the service config. `setApprovalPolicy(session, policy)` is the single write path, so replay reconstructs the override.
+
+```ts type-equiv
+type ApprovalPolicy = 'ask' | 'never'
+```
+
+The prompt section states the deterministic `never` behavior and records either policy with a source-owned marker. The pre-step narrator reads that marker from the logged request header after restart; it does not infer state from deployment persona prose. An idle ACP switch is held in the bridge until the next `turn/start`, because approval audit and policy events must remain turn-enclosed for durable replay.
+
+## Approval request
+
+`ApprovalRequest` identifies the agent and tool action closely enough to route and audit the question. It deliberately omits tool arguments: an answerer attaches the prompt to the already-streamed tool call through `callId` instead of rendering a second copy that could drift.
+
+```ts type-equiv
+interface ApprovalRequest {
+  /**
+   * The agent on whose behalf the question is asked. Routes the question (a
+   * UI answerer only answers for agents it owns) and receives the audit
+   * events on its session log.
+   */
+  agent: Agent
+  /** The tool the question is about (presentation and audit). */
+  toolName: string
+  /**
+   * The exact tool call being decided, when the asker has one — lets a UI
+   * attach the prompt to the tool call it already streamed.
+   */
+  callId?: CallId
+  /** The asker's human-readable explanation of WHY it is asking. */
+  reason?: string
+  /**
+   * Aborting withdraws the question: the request settles `'cancelled'`
+   * immediately and a late answer from a still-pending answerer is discarded.
+   */
+  signal?: AbortSignal
+}
+```
+
+## Dispatch and audit
+
+`ctx.approval.request(req)` requires the requesting session to be inside an open turn. It appends `approval/asked`, obtains one outcome, appends the matching `approval/decided`, and resolves with that outcome. The `never` policy is enforced inside the service before waterfall dispatch, so even an answerer registered later with `prepend` cannot bypass it. Answerers return an outcome when they own the request or call `next()` to delegate; the first answer occupies the single decision slot.
+
+The audit events are log-only and do not enter the model transcript. Model-visible behavior is the caller's derived tool result, while the request header records the prompt policy that the model actually saw. Service disposal removes its prompt section and pre-step narrator together; answerer listeners are independently effect-bound to their owning plugins.

docs/core-data-structures/bash.md

@@ -44,6 +44,20 @@ interface BashExecRequest {
    * ownerless background start (a non-agent caller).
    */
   owner?: OwnerToken | undefined
+  /**
+   * Explicit per-call sandbox-policy input, overriding the executor's
+   * configured default mode for THIS call. Never a silent default: a
+   * consumer sets it only from an explicit policy source — an
+   * `'allowed-once'` grant a human just issued through `ctx.approval` (the
+   * escalation flow in the sandbox RFC § Escalation, which outranks), or the
+   * session's standing override folded from its own `bash/sandbox-mode`
+   * events (the sandbox RFC § Per-session mode switching — the user's recorded per-session
+   * choice). A sandboxing executor confines THIS call under the given mode;
+   * a non-sandboxing executor carries the field and confines nothing (the
+   * tool layer stamps neither escalation nor overrides without a sandboxing
+   * executor — see {@link BashExecutor.sandboxMode}).
+   */
+  sandboxMode?: SandboxMode | undefined
 }
 ```
 
@@ -79,6 +93,16 @@ interface BashExecSpec {
    * task. `start()` stores it; `run()` (foreground) ignores it.
    */
   owner: OwnerToken | undefined
+  /**
+   * The sandbox mode this call executes under, REQUIRED-but-nullable for the
+   * same visibility reason as `owner`. A sandboxing executor's `resolve()`
+   * stamps the effective mode (the request's explicit override, else its
+   * configured default) so `run()`/`start()` read the spec, never the config;
+   * a non-sandboxing executor carries the request value through verbatim and
+   * ignores it (`undefined` under such an executor means what its README says:
+   * unconfined execution).
+   */
+  sandboxMode: SandboxMode | undefined
 }
 ```
 
@@ -106,6 +130,12 @@ interface BashRunResult {
   timeoutMs: number
   stdout: CollectedOutput
   stderr: CollectedOutput
+  /**
+   * Sandbox facts, present iff a sandboxing executor ran the command — an
+   * unsandboxed executor (e.g. `dsh-bash-local`) never sets it. See
+   * {@link BashSandboxInfo} for the `denied` classification semantics.
+   */
+  sandbox?: BashSandboxInfo
 }
 ```
 
@@ -122,9 +152,52 @@ interface CollectedOutput {
 }
 ```
 
+## File sandbox: `BashSandboxInfo`
+
+A sandbox-consuming executor (`dsh-bash-sandbox`) exposes its configured fallback through `BashExecutor.sandboxMode`. The tool layer folds each agent session's durable `bash/sandbox-mode` override, stamps the effective mode onto the request, states it in the per-agent prompt, and may replace it for one user-approved strictly wider call. The mode/enforcement vocabulary is owned and cataloged by the [`@deepseek-ai/dsh-sandbox` seam](sandbox.md), whose provider wraps the executor's argv; modes govern FILE effects only, not network or process visibility.
+
+A sandboxed run always reports the facts it executed under on `BashRunResult.sandbox`: `denied` is the executor's conservative classification of a failure as sandbox-caused (a failed exit whose stderr carries a filesystem-permission signature — never a clean exit or a signal kill), read from the collected stderr tail; `enforcement` reports how completely the selected backend governs the mode's file effects (`SandboxEnforcement = 'full' | 'partial'` — `partial` when an older Landlock ABI governs only a subset of the requested accesses; absent under `danger-full-access`, where nothing is confined); `runnerFailed` marks the opposite of a denial — the sandbox RUNNER itself failed and the command never ran (stamped only on settled background tasks; a foreground run surfaces the same condition as the thrown `SANDBOX_UNAVAILABLE` error):
+
+```ts type-equiv
+interface BashSandboxInfo {
+  /** The mode the command actually ran under. */
+  mode: SandboxMode
+  /**
+   * True when the executor classifies this run's failure as the sandbox
+   * denying a file operation. The classification is CONSERVATIVE (a failed
+   * exit whose stderr carries a filesystem-permission signature) and reads
+   * the COLLECTED stderr — the bounded in-memory tail per
+   * {@link CollectedOutput} semantics, so a signature that survives only in a
+   * spill file is missed toward `denied: false`. A plain command failure
+   * keeps `denied: false` even under a sandboxed mode.
+   */
+  denied: boolean
+  /**
+   * How completely the runner enforced `mode`'s file effects — see
+   * {@link SandboxEnforcement}. Absent exactly when `mode` is
+   * `danger-full-access`: nothing is confined, so there is no enforcement to
+   * report.
+   */
+  enforcement?: SandboxEnforcement
+  /**
+   * True when the executor classifies this failure as the SANDBOX RUNNER
+   * itself failing (missing binary, refused profile, fail-closed refusal
+   * before exec) — the command NEVER RAN; this is a sandbox failure, not a
+   * task failure, and it outranks `denied` (a runner's own error text can
+   * contain denial words). Only ever stamped on settled BACKGROUND tasks: a
+   * foreground run surfaces the same condition as the thrown
+   * `SANDBOX_UNAVAILABLE` error instead (the foreground path has an error
+   * channel; a settled task's facts are its only channel).
+   */
+  runnerFailed?: boolean
+}
+```
+
+One more piece completes the vocabulary: the `SANDBOX_UNAVAILABLE` error code (owned by the [sandbox seam](sandbox.md)) is what the `ctx.sandbox` provider throws — and the executor propagates — when a confined mode has no usable backend. A selected runner refusing its profile reaches the same fail-closed foreground error; a settled background task records `runnerFailed`. The model sees the current effective mode in the prompt, receives denial/runner facts in results, and can request a one-shot strictly wider retry through `sandbox_permissions` plus `justification`; `ctx.approval` must grant that exact call before anything executes. The complete policy and switching design is the [sandbox RFC](../rfc/implemented/feature/2026-07-06-sandbox.md).
+
 ## Background tasks: `BashTask`
 
-A long-running command started with `start()` is tracked as a `BashTask`. `BashTaskStatus` is `'running' | 'completed' | 'killed'`; `done` resolves when the underlying process closes and never rejects.
+A long-running command started with `start()` is tracked as a `BashTask`. `BashTaskStatus` is `'running' | 'completed' | 'killed'`; `done` resolves when the underlying process closes and never rejects. A sandboxing executor stamps `sandbox` once the task settles — classification runs against the settled task's collected stderr — so the field is absent while running and under an unsandboxed executor.
 
 ```ts type-equiv
 interface BashTask {
@@ -137,6 +210,16 @@ interface BashTask {
   signal: NodeJS.Signals | null
   /** Resolves when the underlying process closes (never rejects). */
   readonly done: Promise<void>
+  /**
+   * Sandbox facts for this task's execution, stamped by a sandboxing executor
+   * once the task settles and BEFORE completion listeners are notified — an
+   * `onTaskDone` consumer and a `done` awaiter both see it. Denial
+   * classification runs against the settled task's collected stderr, so the
+   * field cannot exist earlier: absent while the task is running and under an
+   * executor that does not sandbox. See {@link BashSandboxInfo} for the
+   * `denied` semantics.
+   */
+  sandbox?: BashSandboxInfo
 }
 ```
 

docs/core-data-structures/core.md

@@ -20,9 +20,12 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t
 | [persistence.md](persistence.md) | the durability seam: `SessionPersistence`, JSONL + SQLite backends, `session/flush`, crash recovery, `SessionHeader` |
 | [tools.md](tools.md) | `ToolDefinition` full fields, the schema DSL, `ToolExecution`/`ToolResult`, tool-presentation UI types, the `tools/pre-execute`/`tools/post-execute` pipeline |
 | [user-interaction.md](user-interaction.md) | the UI-backed human question/answer seam: `AskUserQuestionRequest`, answer/options vocabulary, provider API, error taxonomy |
+| [approval.md](approval.md) | the one-shot user-approval seam: `ApprovalRequest`, `ApprovalOutcome`, per-session policy, audit and answerer contracts |
 | [bash.md](bash.md) | the bash executor seam: `BashExecRequest`/`Spec`, `BashRunResult`, background `BashTask`s |
+| [sandbox.md](sandbox.md) | the process-confinement seam: file-effect modes, `SandboxPolicy`, `ConfinedArgv`, enforcement and fail-closed errors |
 | [code-runtime.md](code-runtime.md) | the code-execution seam: `CodeRunRequest`/`Result`, binding namespaces, captured logs, the `CodeRunFailure` taxonomy |
 | [filesystem.md](filesystem.md) | the filesystem seam: `FsTarget`, read/write/edit outcomes, observed-file state, `FsErrorCode` |
+| [skills.md](skills.md) | the skill service: discovery priority, `SkillSummary`/`SkillDefinition`, session-prefix catalog, model-facing `skill` loading |
 | [compaction.md](compaction.md) | the compaction seam: the `compact/*` session events, `CompactionResult`, the `CompactService` interface |
 | [subagent.md](subagent.md) | the subagent seam: the named-provider registry, `SubagentStartRequest`/`Result`/`Run`, the start-time-vs-runtime capability split |
 | [web.md](web.md) | the web access seam: `WebSearchRequest`/`Result`, `WebFetchRequest`/`Result`, `WebFetchBody`, provider/capability status, `WebError` |

docs/core-data-structures/sandbox.md

@@ -0,0 +1,82 @@
+# Process Sandbox
+
+The process-sandbox seam of [dsh-sandbox](../../packages/sandbox/sandbox) wraps a same-world subprocess argv in a file-effect policy without coupling consumers to a platform runner. [dsh-sandbox-local](../../packages/sandbox/sandbox-local) supplies the Linux bwrap/Landlock and macOS Seatbelt backends; [dsh-bash-sandbox](../../packages/bash/bash-sandbox) is the first consumer. Containers, microVMs, and remote execution are sibling implementations of whole capability seams, not providers of `ctx.sandbox`.
+
+Source: [`packages/sandbox/sandbox/src/index.ts`](../../packages/sandbox/sandbox/src/index.ts)
+
+## Modes and enforcement
+
+`SandboxMode` governs filesystem effects only. `read-only` denies writes except the required `/dev/null` sink; `workspace-write` permits writes under the workspace root and the backend's promised temp area; `danger-full-access` bypasses confinement. Network and process visibility are outside this vocabulary.
+
+```ts type-equiv
+type SandboxMode = 'read-only' | 'workspace-write' | 'danger-full-access'
+```
+
+Only the first two modes can be sent to a provider. A `danger-full-access` consumer spawns its original argv and does not call `ctx.sandbox`.
+
+```ts type-equiv
+type ConfinedSandboxMode = Exclude<SandboxMode, 'danger-full-access'>
+```
+
+Enforcement is a reported fact. `full` means the backend governs every file effect promised by the mode; `partial` means an active backend or older kernel ABI governs only a subset, so consumers that require the absolute promise must reject or surface that distinction.
+
+```ts type-equiv
+type SandboxEnforcement = 'full' | 'partial'
+```
+
+## Per-call policy
+
+The policy is fully resolved and carried per call. This permits concurrent consumers and one-shot escalated retries to ask the same provider for different boundaries without mutating provider state.
+
+```ts type-equiv
+interface SandboxPolicy {
+  /** The file-effect mode this execution runs under. */
+  mode: ConfinedSandboxMode
+  /** Absolute root directory `workspace-write` may write under. */
+  workspaceRoot: string
+}
+```
+
+## Wrapped argv and classification dialects
+
+`ConfinedArgv` is what the consumer spawns. Besides the replacement argv, it carries the backend's enforcement fact and two orthogonal stderr dialects. `denialSignatures` identify the confined command being blocked while the sandbox works correctly. `runnerFailureSignatures` identify the sandbox runner refusing or failing before it executes the command; consumers check these first and surface a sandbox infrastructure failure, never an ordinary task failure.
+
+```ts type-equiv
+interface ConfinedArgv {
+  /** The wrapped argv (runner, profile, separator, then the caller's argv). */
+  argv: string[]
+  /** How completely the selected backend enforces the policy's file effects. */
+  enforcement: SandboxEnforcement
+  /**
+   * The selected backend's denial DIALECT: the case-insensitive stderr
+   * substrings a file effect denied by THIS backend produces (EROFS text
+   * under bwrap's read-only binds, EACCES under Landlock, EPERM under
+   * Seatbelt). A consumer that infers denials from a failed run's stderr
+   * matches against exactly these rather than a cross-backend union — the
+   * union claims denials a given backend never produces.
+   */
+  denialSignatures: readonly string[]
+  /**
+   * How the RUNNER ITSELF failing identifies itself: case-insensitive stderr
+   * substrings produced when the sandbox binary is missing, refuses its
+   * profile, or fails closed before exec'ing the command (`bwrap: `,
+   * `landlock-run: `, `sandbox-exec: ` — each covers both the runner's own
+   * error prefix and the shell's runner-not-found message). ORTHOGONAL to
+   * {@link denialSignatures}: a denial is the confined COMMAND being blocked
+   * (the sandbox working as designed); a runner failure means the command
+   * NEVER RAN and must surface as a sandbox failure, not a task failure —
+   * consumers check these signatures FIRST (a runner's own error text may
+   * contain denial words, e.g. an unopenable grant root reporting
+   * `Permission denied`).
+   */
+  runnerFailureSignatures: readonly string[]
+}
+```
+
+An operator-configured local runner must supply at least one `runnerFailureSignatures` entry for its own pre-exec refusal dialect; the provider adds outer-shell missing and unexecutable forms automatically. This makes an executable custom runner rejecting its profile distinguishable from the wrapped command exiting with the same status.
+
+## Provider and fail-closed errors
+
+`ctx.sandbox.confine(argv, policy)` returns a `ConfinedArgv` or throws `SandboxUnavailableError` with code `SANDBOX_UNAVAILABLE` when no usable backend exists. A selected runner can also fail closed at execution time, in which case its failure signature carries the same infrastructure meaning. Silent unconfined passthrough is never legal for a confined policy.
+
+Provider probing arbitrates between multiple candidates and is cached for the provider lifetime. A platform with one candidate may select it directly; execution-time refusal retains the safety property. The local provider reports bwrap and Seatbelt as full and preserves the Landlock launcher's full/partial kernel verdict.

docs/core-data-structures/skills.md

@@ -0,0 +1,116 @@
+# Skills
+
+The [skill capability family](../../packages/skill) is split across three packages: the registry ([dsh-skill](../../packages/skill/skill), `ctx.skills`) merges provider catalogs; the local provider ([dsh-skill-local](../../packages/skill/skill-local)) scans project/custom/user directories; the consumer ([dsh-tool-skill](../../packages/skill/tool-skill)) owns the session-prefix catalog and model-facing `skill` tool. Skills are optional instructions, not session events, so their vocabulary lives here rather than in [core.md](core.md).
+
+Source: [`packages/skill/skill/src/index.ts`](../../packages/skill/skill/src/index.ts), [`packages/skill/skill-local/src/index.ts`](../../packages/skill/skill-local/src/index.ts), and [`packages/skill/tool-skill/src/index.ts`](../../packages/skill/tool-skill/src/index.ts).
+
+## Provider registry
+
+`ctx.skills` is a multi-provider registry. Providers can represent local directories, embedded plugin data, HTTP catalogs, or another source. Provider plugins register synchronously during `apply()`; remote initialization, authentication, and discovery are awaited by `list()`. The registry validates candidates, resolves duplicate skill names first-wins by rank/provider order/local order, and sorts the final summaries by `name` for deterministic consumers. A provider `list()` rejection is logged and skipped without caching the degraded catalog; malformed candidates still fail fast because they violate the provider contract.
+
+```ts type-equiv
+interface SkillProvider {
+  name: string
+  list(options: SkillLookupOptions): Promise<SkillCandidate[]>
+  get(candidate: SkillCandidate, options: SkillLookupOptions): Promise<SkillDefinition | undefined>
+}
+```
+
+## Local discovery priority
+
+The shipped local provider scans roots in rank order:
+
+| Rank | Source | Root |
+|---|---|---|
+| 100 | `project-dsh` | `<projectRoot>/.dsh/skills` |
+| 200 | `project-agents` | `<projectRoot>/.agents/skills` |
+| 300 | `custom` | `Config.customSkillDirs` |
+| 400 | `user-dsh` | `<dshHome>/skills` |
+| 500 | `user-agents` | `<agentsHome>/skills` |
+
+The project root is the nearest ancestor containing `.git`; without one, the current cwd is used. When `ctx.fs` is available, the git-root walk probes `.git` through the filesystem service so remote or sandboxed workspaces do not fall back to the host filesystem boundary. The user DSH root skips its `.system` child, and DeepSeek Harness no longer ships built-in system skills from the local provider. Additional built-ins can be supplied later by another provider.
+
+## Skill identity
+
+Skill names are kebab-case (`^[a-z0-9]+(?:-[a-z0-9]+)*$`). The local provider accepts directory bundles (`<name>/SKILL.md`) and flat Markdown files (`<name>.md`). Nested recursive `**/SKILL.md` discovery is intentionally outside v1.
+
+```ts type-equiv
+type SkillSource = 'project-dsh' | 'project-agents' | 'runtime' | 'user-dsh' | 'user-agents' | 'custom' | (string & {})
+```
+
+## Summaries, candidates, and complete definitions
+
+`SkillSummary` is the registry's model-invocable summary shape. Consumers choose which fields to render; the session catalog uses only `name` and `description`, never the body or absolute file path. `disableModelInvocation` hides a skill from model listings while allowing trusted code to load it by name.
+
+```ts type-equiv
+interface SkillSummary {
+  name: string
+  description: string
+  whenToUse?: string
+  disableModelInvocation?: boolean
+  source: SkillSource
+  provider: string
+  resourceBase?: SkillResourceBase
+}
+```
+
+`SkillCandidate` is the provider-to-registry shape. `locator` is opaque provider state; the registry only stores it and gives it back to the winning provider's `get()`.
+
+```ts type-equiv
+interface SkillCandidate extends SkillSummary {
+  rank: number
+  locator: unknown
+  path?: string
+  metadata?: Record<string, unknown>
+}
+```
+
+`SkillDefinition` is the complete parsed result returned by `ctx.skills.get()` and used by the `skill` tool. `resourceBase` tells the tool how to render relative-resource guidance for local, URL, or provider-managed skills.
+
+```ts type-equiv
+type SkillResourceBase =
+  | { kind: 'directory'; path: string }
+  | { kind: 'url'; url: string }
+  | { kind: 'opaque'; description: string }
+```
+
+```ts type-equiv
+interface SkillDefinition extends SkillSummary {
+  content: string
+  path?: string
+  metadata?: Record<string, unknown>
+}
+```
+
+Runtime skills use the same complete shape and participate in the same first-wins collection order. The returned disposer removes the contribution and invalidates discovery caches.
+
+```ts type-equiv
+type SkillRegistration = Omit<SkillDefinition, 'provider'> & {
+  provider?: string
+}
+```
+
+## Lookup and configuration
+
+Skill lookup is cwd-sensitive because providers may expose workspace-local skills, and its optional signal cancels provider work for the caller. If no git root is found, the local provider treats the supplied cwd itself as the project root.
+
+```ts type-equiv
+interface SkillLookupOptions {
+  cwd?: string | undefined
+  signal?: AbortSignal | undefined
+}
+```
+
+The registry owns only its discovery-cache bound. The local provider owns filesystem roots (`dshHome`, `agentsHome`, and `customSkillDirs`). The consumer owns its catalog description bound.
+
+```ts type-equiv
+interface Config {
+  collectCacheMaxEntries?: number
+}
+```
+
+## Session catalog and tool contract
+
+`dsh-tool-skill` contributes a user-role `<system-reminder>` through `agent/session-prefix`. The catalog contains sorted skill `name` and normalized, XML-escaped `description` only; it omits bodies, paths, sources, providers, and routing hints. Prefix discovery forwards the caller's abort signal through `SkillLookupOptions`. `catalogDescriptionMaxLength` is the consumer config for the description bound, with default `500` and integer minimum `3`. Its request-only, header-logged lifecycle is defined by the [session-prefix RFC](../rfc/implemented/feature/2026-07-07-session-prefix.md).
+
+The model-facing `skill({ name })` tool validates the kebab-case name, loads the complete definition for the calling agent cwd, reports an unresolved skill as unknown or no longer available, rejects `disableModelInvocation` skills, and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` resolves explicitly referenced scripts, references, and assets only as needed; the loaded result does not enumerate a skill directory. The tool result is the model-visible path for complete instructions.

docs/event-producer-consumer.md

@@ -10,15 +10,16 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:265`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`emit`) | [`stdio-agent`](../packages/ui/stdio-agent) |
 | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:272`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`emit`) | [`stdio-agent`](../packages/ui/stdio-agent) |
 | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:476`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
-| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:357`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic) |
-| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:370`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
+| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:357`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) |
+| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:370`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
 | `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:290`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
 | `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:394`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
-| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:441`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
+| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:441`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) |
 | `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:305`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
 | `agent/status` | `emit` | [`packages/core/agent/src/types.ts:281`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) |
 | `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:451`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
 | `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:464`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
+| `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:64`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) |
 | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:123`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
 | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) |
 | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:109`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
@@ -26,16 +27,18 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 | `session/created` | `emit` | [`packages/core/session/src/index.ts:39`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`emit`) | [`invariants`](../packages/support/invariants), [`session-persistence`](../packages/session-persistence/session-persistence) |
 | `session/event` | `emit` | [`packages/core/session/src/index.ts:47`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`emit`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) |
 | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:57`](../packages/core/session/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`parallel`) | [`session-persistence`](../packages/session-persistence/session-persistence) |
+| `skill/provider-added` | `emit` | [`packages/skill/skill/src/index.ts:130`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - |
+| `skill/provider-removed` | `emit` | [`packages/skill/skill/src/index.ts:136`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - |
 | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:98`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) |
 | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:72`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) |
 | `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | - | [`tool-subagent`](../packages/subagent/tool-subagent) |
 | `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:91`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) |
 | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:38`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - |
 | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:44`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - |
-| `tools/change` | `emit` | [`packages/core/tools/src/index.ts:132`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - |
-| `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:111`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`timeout-policy`](../packages/timeout/timeout-policy) |
-| `tools/post-execute` | `waterfall` | [`packages/core/tools/src/index.ts:127`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
-| `tools/pre-execute` | `waterfall` | [`packages/core/tools/src/index.ts:91`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
+| `tools/change` | `emit` | [`packages/core/tools/src/index.ts:135`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - |
+| `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:114`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`timeout-policy`](../packages/timeout/timeout-policy) |
+| `tools/post-execute` | `waterfall` | [`packages/core/tools/src/index.ts:130`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
+| `tools/pre-execute` | `waterfall` | [`packages/core/tools/src/index.ts:94`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
 | `workflow/agent-end` | `emit` | [`packages/workflow/workflow/src/index.ts:96`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
 | `workflow/agent-start` | `emit` | [`packages/workflow/workflow/src/index.ts:85`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
 | `workflow/end` | `emit` | [`packages/workflow/workflow/src/index.ts:106`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |

docs/module-graph.md

@@ -27,6 +27,7 @@ flowchart TD
   subgraph group_bash["packages/bash"]
     pkg_bash["bash"]
     pkg_bash_local["bash-local"]
+    pkg_bash_sandbox["bash-sandbox"]
     pkg_tool_bash["tool-bash"]
   end
   subgraph group_fs["packages/fs"]
@@ -35,6 +36,11 @@ flowchart TD
     pkg_fs_policy["fs-policy"]
     pkg_tool_fs["tool-fs"]
   end
+  subgraph group_skill["packages/skill"]
+    pkg_skill["skill"]
+    pkg_skill_local["skill-local"]
+    pkg_tool_skill["tool-skill"]
+  end
   subgraph group_compact["packages/compact"]
     pkg_compact["compact"]
     pkg_compact_basic["compact-basic"]
@@ -87,6 +93,7 @@ flowchart TD
     pkg_app_boot["app-boot"]
     pkg_stdio_agent["stdio-agent"]
     pkg_tool_ask_user["tool-ask-user"]
+    pkg_user_approval["user-approval"]
     pkg_user_interaction["user-interaction"]
   end
   subgraph group_code_runtime["packages/code-runtime"]
@@ -96,30 +103,37 @@ flowchart TD
   subgraph group_guard["packages/guard"]
     pkg_repeat_tool_guard["repeat-tool-guard"]
   end
+  subgraph group_sandbox["packages/sandbox"]
+    pkg_sandbox["sandbox"]
+    pkg_sandbox_local["sandbox-local"]
+  end
   subgraph group_workflow["packages/workflow"]
     pkg_tool_workflow["tool-workflow"]
     pkg_workflow["workflow"]
     pkg_workflow_workerthread["workflow-workerthread"]
   end
   pkg_llm --> pkg_brand
-  pkg_bash --> pkg_brand
   pkg_code_runtime_worker --> pkg_code_runtime
   pkg_llm_deepseek --> pkg_llm
   pkg_llm_pi_ai --> pkg_llm
   pkg_session --> pkg_brand
   pkg_session --> pkg_llm
   pkg_system_prompt --> pkg_llm
-  pkg_bash_local --> pkg_bash
-  pkg_bash_local --> pkg_timeout
   pkg_fs --> pkg_brand
   pkg_fs --> pkg_llm
   pkg_web --> pkg_llm
+  pkg_sandbox --> pkg_llm
   pkg_agent --> pkg_brand
   pkg_agent --> pkg_llm
   pkg_agent --> pkg_session
   pkg_agent --> pkg_system_prompt
+  pkg_bash --> pkg_brand
+  pkg_bash --> pkg_sandbox
+  pkg_bash --> pkg_session
   pkg_fs_local --> pkg_fs
   pkg_fs_policy --> pkg_fs
+  pkg_skill_local --> pkg_fs
+  pkg_skill_local --> pkg_skill
   pkg_compact --> pkg_llm
   pkg_compact --> pkg_session
   pkg_web_fetch_local --> pkg_timeout
@@ -127,20 +141,19 @@ flowchart TD
   pkg_web_search_deepseek --> pkg_web
   pkg_web_search_exa --> pkg_web
   pkg_web_search_perplexity --> pkg_web
-  pkg_hook_protocol --> pkg_bash
-  pkg_hook_protocol --> pkg_session
   pkg_session_persistence --> pkg_session
   pkg_llm_replay --> pkg_llm
   pkg_llm_replay --> pkg_session
-  pkg_tools --> pkg_agent
-  pkg_tools --> pkg_code_runtime
-  pkg_tools --> pkg_llm
-  pkg_tools --> pkg_session
-  pkg_tools --> pkg_system_prompt
+  pkg_sandbox_local --> pkg_llm
+  pkg_sandbox_local --> pkg_sandbox
+  pkg_bash_local --> pkg_bash
+  pkg_bash_local --> pkg_timeout
   pkg_compact_basic --> pkg_agent
   pkg_compact_basic --> pkg_compact
   pkg_compact_basic --> pkg_llm
   pkg_compact_basic --> pkg_session
+  pkg_hook_protocol --> pkg_bash
+  pkg_hook_protocol --> pkg_session
   pkg_session_persistence_jsonl --> pkg_session
   pkg_session_persistence_jsonl --> pkg_session_persistence
   pkg_session_persistence_sqlite --> pkg_session
@@ -148,11 +161,25 @@ flowchart TD
   pkg_invariants --> pkg_agent
   pkg_invariants --> pkg_llm
   pkg_invariants --> pkg_session
+  pkg_user_approval --> pkg_agent
+  pkg_user_approval --> pkg_brand
+  pkg_user_approval --> pkg_llm
+  pkg_user_approval --> pkg_session
+  pkg_user_approval --> pkg_system_prompt
   pkg_user_interaction --> pkg_agent
   pkg_user_interaction --> pkg_llm
   pkg_workflow --> pkg_agent
   pkg_workflow --> pkg_brand
   pkg_workflow --> pkg_llm
+  pkg_tools --> pkg_agent
+  pkg_tools --> pkg_code_runtime
+  pkg_tools --> pkg_llm
+  pkg_tools --> pkg_session
+  pkg_tools --> pkg_system_prompt
+  pkg_tools --> pkg_user_approval
+  pkg_bash_sandbox --> pkg_bash
+  pkg_bash_sandbox --> pkg_bash_local
+  pkg_bash_sandbox --> pkg_sandbox
   pkg_agent_loop --> pkg_agent
   pkg_agent_loop --> pkg_llm
   pkg_agent_loop --> pkg_session
@@ -162,14 +189,20 @@ flowchart TD
   pkg_tool_bash --> pkg_agent
   pkg_tool_bash --> pkg_bash
   pkg_tool_bash --> pkg_llm
+  pkg_tool_bash --> pkg_sandbox
   pkg_tool_bash --> pkg_session_persistence
   pkg_tool_bash --> pkg_system_prompt
   pkg_tool_bash --> pkg_tools
+  pkg_tool_bash --> pkg_user_approval
   pkg_tool_fs --> pkg_fs
   pkg_tool_fs --> pkg_llm
   pkg_tool_fs --> pkg_session
   pkg_tool_fs --> pkg_system_prompt
   pkg_tool_fs --> pkg_tools
+  pkg_tool_skill --> pkg_agent
+  pkg_tool_skill --> pkg_llm
+  pkg_tool_skill --> pkg_skill
+  pkg_tool_skill --> pkg_tools
   pkg_subagent --> pkg_agent
   pkg_subagent --> pkg_llm
   pkg_subagent --> pkg_tools
@@ -191,10 +224,13 @@ flowchart TD
   pkg_hooks_codex --> pkg_session_persistence
   pkg_hooks_codex --> pkg_tools
   pkg_acp --> pkg_agent
+  pkg_acp --> pkg_bash
   pkg_acp --> pkg_llm
+  pkg_acp --> pkg_sandbox
   pkg_acp --> pkg_session
   pkg_acp --> pkg_session_persistence
   pkg_acp --> pkg_tools
+  pkg_acp --> pkg_user_approval
   pkg_acp --> pkg_user_interaction
   pkg_tool_ask_user --> pkg_agent
   pkg_tool_ask_user --> pkg_tools
@@ -211,8 +247,11 @@ flowchart TD
   pkg_agent_core --> pkg_invariants
   pkg_agent_core --> pkg_llm
   pkg_agent_core --> pkg_session
+  pkg_agent_core --> pkg_skill
+  pkg_agent_core --> pkg_skill_local
   pkg_agent_core --> pkg_system_prompt
   pkg_agent_core --> pkg_tool_bash
+  pkg_agent_core --> pkg_tool_skill
   pkg_agent_core --> pkg_tools
   pkg_subagent_acp --> pkg_agent
   pkg_subagent_acp --> pkg_llm
@@ -271,52 +310,59 @@ flowchart TD
 | --- | --- | --- |
 | [`brand`](../packages/util/brand) | `util` | — |
 | [`timeout`](../packages/util/timeout) | `util` | — |
+| [`skill`](../packages/skill/skill) | `skill` | — |
 | [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | `subagent` | — |
 | [`acp-snapshot`](../packages/support/acp-snapshot) | `support` | — |
 | [`app-boot`](../packages/ui/app-boot) | `ui` | — |
 | [`code-runtime`](../packages/code-runtime/code-runtime) | `code-runtime` | — |
 | [`llm`](../packages/llm/llm) | `llm` | [`brand`](../packages/util/brand) |
-| [`bash`](../packages/bash/bash) | `bash` | [`brand`](../packages/util/brand) |
 | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | `code-runtime` | [`code-runtime`](../packages/code-runtime/code-runtime) |
 | [`llm-deepseek`](../packages/llm/llm-deepseek) | `llm` | [`llm`](../packages/llm/llm) |
 | [`llm-pi-ai`](../packages/llm/llm-pi-ai) | `llm` | [`llm`](../packages/llm/llm) |
 | [`session`](../packages/core/session) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) |
 | [`system-prompt`](../packages/core/system-prompt) | `core` | [`llm`](../packages/llm/llm) |
-| [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) |
 | [`fs`](../packages/fs/fs) | `fs` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) |
 | [`web`](../packages/web/web) | `web` | [`llm`](../packages/llm/llm) |
+| [`sandbox`](../packages/sandbox/sandbox) | `sandbox` | [`llm`](../packages/llm/llm) |
 | [`agent`](../packages/core/agent) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
+| [`bash`](../packages/bash/bash) | `bash` | [`brand`](../packages/util/brand), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session) |
 | [`fs-local`](../packages/fs/fs-local) | `fs` | [`fs`](../packages/fs/fs) |
 | [`fs-policy`](../packages/fs/fs-policy) | `fs` | [`fs`](../packages/fs/fs) |
+| [`skill-local`](../packages/skill/skill-local) | `skill` | [`fs`](../packages/fs/fs), [`skill`](../packages/skill/skill) |
 | [`compact`](../packages/compact/compact) | `compact` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
 | [`web-fetch-local`](../packages/web/web-fetch-local) | `web` | [`timeout`](../packages/util/timeout), [`web`](../packages/web/web) |
 | [`web-search-deepseek`](../packages/web/web-search-deepseek) | `web` | [`web`](../packages/web/web) |
 | [`web-search-exa`](../packages/web/web-search-exa) | `web` | [`web`](../packages/web/web) |
 | [`web-search-perplexity`](../packages/web/web-search-perplexity) | `web` | [`web`](../packages/web/web) |
-| [`hook-protocol`](../packages/hooks/hook-protocol) | `hooks` | [`bash`](../packages/bash/bash), [`session`](../packages/core/session) |
 | [`session-persistence`](../packages/session-persistence/session-persistence) | `session-persistence` | [`session`](../packages/core/session) |
 | [`llm-replay`](../packages/support/llm-replay) | `support` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
-| [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
+| [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) |
+| [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) |
 | [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
+| [`hook-protocol`](../packages/hooks/hook-protocol) | `hooks` | [`bash`](../packages/bash/bash), [`session`](../packages/core/session) |
 | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) |
 | [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) |
 | [`invariants`](../packages/support/invariants) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
+| [`user-approval`](../packages/ui/user-approval) | `ui` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
 | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) |
 | [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) |
+| [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) |
+| [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) |
 | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
-| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
+| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
 | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
+| [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) |
 | [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) |
 | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) |
 | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
 | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
 | [`tool-cordis`](../packages/cordis/tool-cordis) | `cordis` | [`tools`](../packages/core/tools) |
 | [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools) |
-| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
+| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) |
 | [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
 | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) |
 | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
-| [`agent-core`](../packages/core/agent-core) | `core` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tool-bash`](../packages/bash/tool-bash), [`tools`](../packages/core/tools) |
+| [`agent-core`](../packages/core/agent-core) | `core` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tools`](../packages/core/tools) |
 | [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) |
 | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
 | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) |

docs/persistence-catalog.md

@@ -11,6 +11,40 @@ The on-disk envelope around every payload is `SessionEvent` — `type`, monotoni
 
 ## Events
 
+### `approval/*`
+
+#### `approval/asked` — log-only
+
+An approval question was put to the answerer chain — log-only audit (like `hook/*`; NOT a surface event, carries no `surfaceOp`). `id` pairs it with the `approval/decided` that always follows; `toolName` is the tool the question is about, `callId` the exact tool call when the asker had one, `reason` the asker's human-readable explanation (e.g. a hook's permission-decision reason).
+
+```ts persistence-catalog
+'approval/asked': { id: ApprovalRequestId; toolName: string; callId?: CallId; reason?: string }
+```
+
+Types: [CallId](core-data-structures/core.md)
+
+Source: [`packages/ui/user-approval/src/index.ts:78`](../packages/ui/user-approval/src/index.ts)
+
+#### `approval/decided` — log-only
+
+The outcome of a prior `approval/asked` (same `id`) — log-only audit. Exactly one per ask, appended when the outcome is known: a decision, a cancellation, or the fail-closed `'unavailable'`.
+
+```ts persistence-catalog
+'approval/decided': { id: ApprovalRequestId; outcome: ApprovalOutcome }
+```
+
+Source: [`packages/ui/user-approval/src/index.ts:89`](../packages/ui/user-approval/src/index.ts)
+
+#### `approval/policy` — log-only
+
+The session's approval policy was switched — log-only, durable, replayable, never in the model transcript (the model learns the policy from the prompt section and the narrator's notices). The LAST such event is the session's override (effectiveApprovalPolicy); who asked for it is derivable from position (an event after the log's last `request/header*` was a runtime switch by the user).
+
+```ts persistence-catalog
+'approval/policy': { policy: ApprovalPolicy }
+```
+
+Source: [`packages/ui/user-approval/src/index.ts:101`](../packages/ui/user-approval/src/index.ts)
+
 ### `assistant/*`
 
 #### `assistant/chunk` — log-only
@@ -37,6 +71,18 @@ Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-st
 
 Source: [`packages/core/session/src/types.ts:320`](../packages/core/session/src/types.ts)
 
+### `bash/*`
+
+#### `bash/sandbox-mode` — log-only
+
+The session's sandbox mode was switched — log-only (like `approval/*`; NOT a surface event, carries no `surfaceOp`): durable and replayable, never in the model transcript. The LAST such event is the session's override (effectiveSandboxMode); who asked for it is derivable from position (an event after the log's last `request/header*` was a runtime switch by the user; see the tool layer's narrator).
+
+```ts persistence-catalog
+'bash/sandbox-mode': { mode: SandboxMode }
+```
+
+Source: [`packages/bash/bash/src/session-mode.ts:31`](../packages/bash/bash/src/session-mode.ts)
+
 ### `compact/*`
 
 #### `compact/end` — log-only

docs/rfc/INDEX.md

@@ -8,8 +8,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
 
 | Title | First proposed |
 |---|---|
-| [Agent Client Protocol (ACP) support — drive the coding agent from external editors](proposed/feature/2026-06-14-acp-agent-client-protocol.md) | 2026-06-14 |
-| [Multiplex concurrent ACP sessions over one connection](proposed/feature/2026-06-14-acp-multi-session.md) | 2026-06-14 |
 | [Pre-tool input rewrite — a consistent design](proposed/feature/2026-06-30-pre-tool-input-rewrite.md) | 2026-06-30 |
 | [Claude Code and Codex subagent backends (out-of-process delegation to external coding agents)](proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md) | 2026-07-07 |
 
@@ -49,6 +47,8 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
 
 | Title | First proposed |
 |---|---|
+| [Agent Client Protocol (ACP) support — drive the coding agent from external editors](implemented/feature/2026-06-14-acp-agent-client-protocol.md) | 2026-06-14 |
+| [Multiplex concurrent ACP sessions over one connection](implemented/feature/2026-06-14-acp-multi-session.md) | 2026-06-14 |
 | [Code Mode — the model writes TypeScript against the tool registry](implemented/feature/2026-06-15-code-mode.md) | 2026-06-15 |
 | [Filesystem tool schemas — model-facing read/write/edit shapes](implemented/feature/2026-06-17-filesystem-tool-schemas.md) | 2026-06-17 |
 | [Rich ACP bash rendering — the terminal card via the `_meta` convention](implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md) | 2026-06-18 |
@@ -63,7 +63,10 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
 | [SessionStore fork API](implemented/feature/2026-06-30-session-store-fork-api.md) | 2026-06-30 |
 | [Subagent lifecycle enrichment — lastAssistantMessage (observe-only)](implemented/feature/2026-06-30-subagent-observe-enrich.md) | 2026-06-30 |
 | [Dynamic workflows — a script-driven multi-agent orchestration seam](implemented/feature/2026-07-05-dynamic-workflows.md) | 2026-07-05 |
+| [Skill system — progressive disclosure instructions for agents](implemented/feature/2026-07-05-skill-system.md) | 2026-07-05 |
+| [The approval seam — one-shot permission decisions over a waterfall of answerers](implemented/feature/2026-07-06-approval-seam.md) | 2026-07-06 |
 | [Explicit model-facing tool order](implemented/feature/2026-07-06-explicit-tool-order.md) | 2026-07-06 |
+| [The subprocess sandbox — confinement seam, native runners, escalation, and per-session modes](implemented/feature/2026-07-06-sandbox.md) | 2026-07-06 |
 | [The session prefix — request-only messages in front of the derived history](implemented/feature/2026-07-07-session-prefix.md) | 2026-07-07 |
 | [Repeat-tool-call guard plugin](implemented/feature/2026-07-08-repeat-tool-guard.md) | 2026-07-08 |
 | [The self-referential cordis toolset](implemented/feature/2026-07-08-self-referential-cordis-toolset.md) | 2026-07-08 |

docs/rfc/implemented/architecture/2026-06-14-session-persistence.md

@@ -6,7 +6,7 @@ Status: implemented
 
 ## Problem
 
-Sessions lived only in memory. The example `session-jsonl.ts` plugin (duplicated byte-for-byte in both examples) was write-only telemetry: it buffered `session/event` and appended JSON lines, with no read/replay path, no crash-safety (no fsync, no atomic write, a fire-and-forget dispose drain), no listing, and no format versioning. Nothing could rehydrate a past session from disk into a live agent, so durable resume ("continue yesterday's task"), durable forking, and the ACP `session/load` method ([ACP support](../../proposed/feature/2026-06-14-acp-agent-client-protocol.md)) were all impossible.
+Sessions lived only in memory. The example `session-jsonl.ts` plugin (duplicated byte-for-byte in both examples) was write-only telemetry: it buffered `session/event` and appended JSON lines, with no read/replay path, no crash-safety (no fsync, no atomic write, a fire-and-forget dispose drain), no listing, and no format versioning. Nothing could rehydrate a past session from disk into a live agent, so durable resume ("continue yesterday's task"), durable forking, and the ACP `session/load` method ([ACP support](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md)) were all impossible.
 
 The [event-sourced model](2026-06-11-event-sourced-sessions.md) makes the append-only log the single source of truth and derives LLM history from it. Persistence had to stay faithful to that: persist the existing `SessionEvent` directly, with no parallel "persisted message" type that the log is converted to and from. The backend also had to be swappable — a file store now, a database store later — behind one interface.
 
@@ -33,4 +33,4 @@ Format versioning: the header carries a `version`; `load` rejects any non-curren
 
 ## Consequences
 
-Two new packages and the metadata seam in `dsh-session` (`session.header`, the `create(id?, options?)` signature). Bought: durable resume/fork, a read/replay path, crash tolerance, and the foundation the ACP `session/load` ([ACP support](../../proposed/feature/2026-06-14-acp-agent-client-protocol.md)) needs — all over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only / contiguous-seq / lazy-materialization / serializability semantics. This completes [event-sourced sessions](2026-06-11-event-sourced-sessions.md)'s deferred "real persistence backend" and resolves its `TODO(review)` on the event vocabulary: persisting the log freezes its shape, and the `assistant/chunk` fidelity question is answered above (persist verbatim).
+Two new packages and the metadata seam in `dsh-session` (`session.header`, the `create(id?, options?)` signature). Bought: durable resume/fork, a read/replay path, crash tolerance, and the foundation the ACP `session/load` ([ACP support](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md)) needs — all over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only / contiguous-seq / lazy-materialization / serializability semantics. This completes [event-sourced sessions](2026-06-11-event-sourced-sessions.md)'s deferred "real persistence backend" and resolves its `TODO(review)` on the event vocabulary: persisting the log freezes its shape, and the `assistant/chunk` fidelity question is answered above (persist verbatim).

docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md

@@ -0,0 +1,57 @@
+# RFC: Agent Client Protocol (ACP) support — drive the coding agent from external editors
+
+Status: implemented
+
+## Problem
+
+The harness originally exposed agents only through a readline loop. That surface could carry text, but it gave an editor no structured way to create or resume sessions, correlate prompt completion, stream reasoning and tool activity, render tool-specific UI, ask for permission, or cancel one conversation without disturbing another. ACP defines those interactions as JSON-RPC over stdio, and Zed is the target client used to make concrete compatibility decisions.
+
+The bridge must preserve the harness's existing ownership boundaries. It cannot depend on the concrete agent loop, bypass the tool registry, execute shell commands in the editor, or invent a second source of session truth. stdout is also the protocol transport, so any accidental log output corrupts the connection.
+
+## Decision
+
+`@deepseek-ai/dsh-acp` is a UI/client-driver plugin under `packages/ui/acp`. It uses `@agentclientprotocol/sdk`'s `AgentSideConnection` over stdin/stdout and programs only interface services: the agent create/resume factory, session persistence, tool registry, user interaction, and optional approval/bash capabilities. It does not change the agent loop and is not a capability-seam implementation.
+
+The bridge implements the following stable session path:
+
+- `initialize` negotiates the protocol version, advertises text plus `resource_link` prompts, and advertises `loadSession`.
+- `session/new` validates an absolute `cwd`, stores it in `SessionHeader`, creates an agent through `ctx.agents`, and returns any composition-backed config options.
+- `session/load` validates the requested cwd against persisted metadata before constructing an agent, reserves the id across the asynchronous resume, replays user/assistant/tool events as ACP updates, and reports the resumed config-option fold.
+- `session/prompt` accepts text and resource links, rejects unsupported or empty content, allows one in-flight prompt per session, and settles against that prompt's owning `turn/end`. An error turn rejects the RPC; other closed turn reasons map through a total ACP stop-reason codec.
+- `session/cancel` calls the queue-aware agent cancel path and settles only the addressed session's prompt.
+
+Tool-call presentation remains tool-owned. A tool's `presentCall` and `presentResult` return the `generic`, `terminal`, or `diff` render-intent variants; the bridge switches on that union and maps it to ACP. Presenter-less tools receive a generic fallback. Bash terminal cards use Zed's capability-gated `_meta.terminal_info`, `_meta.terminal_output`, and `_meta.terminal_exit` convention; the harness still executes the command through `ctx.bash`, preserving sandbox, environment scrub, ownership, and cwd. Clients without that extension receive ordinary text content. Filesystem tools provide diff cards and file locations without hard-coded tool-name branches in the bridge.
+
+Permission handling is an answerer on the [user-approval seam](2026-07-06-approval-seam.md), not an ask-every-tool policy in ACP. An `approval/request` for a bridge-owned agent with a call id becomes `session/request_permission` on that agent's editor session, with one-shot allow/reject choices. Foreign or call-less requests delegate; a missing or failed answerer remains fail-closed. The plugin that asks—such as a pre-execute policy or bash escalation—owns the decision to ask.
+
+The bridge advertises ACP config options instead of session modes. `sandbox-mode` exists only when the mounted bash executor reports sandbox capability, and `approval-policy` exists only when `ctx.approval` is composed. Each option is an independent select whose current value is the session event fold over the composition default. `session/set_config_option` validates against the owning domain vocabulary and writes through `setSandboxMode` or `setApprovalPolicy`. An open-turn switch appends immediately; an idle switch is overlaid in the response and anchored at the next turn start. Until that anchor it is memory-only and a crash reverts to the durable fold. ACP session modes are deliberately not modeled because one mode list cannot represent these orthogonal knobs and config options are the forward protocol surface. Runtime model selection remains outside this decision; `AcpConfig.model` is connection-wide.
+
+The bridge also provides the ACP-backed `UserInteractionProvider`: `ask_user_question` requests become form elicitations on the owning session. Select, multi-select, option descriptions, and custom-answer override semantics are preserved.
+
+Lifecycle ownership is explicit. The bridge holds an `AgentHandle` per live session. Disconnect and Cordis disposal cancel pending prompts, dispose every handle in parallel, await loop quiescence and persistence flush, and then remove the records. Stream notification failures are contained so a vanished client cannot corrupt an agent turn. The ACP app composition loads no stdout logger; a test guards stdout as framed JSON-RPC only.
+
+The precise supported and deferred protocol rows live in [`packages/ui/acp/acp-feature-support.md`](../../../../packages/ui/acp/acp-feature-support.md); the package README is the operational contract.
+
+## Alternatives considered
+
+**A prepended `tools/execute` listener that asks on every ACP-owned call** — rejected. It would hard-code permission policy into the UI bridge, ask even when no policy requires it, and could not serve approval requests that arise after execution begins. The shared user-approval seam keeps mechanism, asking policy, and UI answerer separate.
+
+**Inject the concrete `agentLoop`** — rejected. Agent creation, resume, idle observation, and disposal are interface-level ownership operations on `dsh-agent`; a UI plugin does not need a dependency-rule exception.
+
+**Execute bash through ACP `terminal/*`** — rejected. That would move execution outside the harness and bypass its sandbox, credential scrub, task ownership, cwd resolution, and session log. Terminal metadata is presentation only.
+
+**Represent sandbox and approval as ACP session modes** — rejected. They are independent composable settings, while a single current mode is mutually exclusive. ACP config options represent both without a cross-product and match the protocol's forward direction.
+
+**Hijack stdout defensively** — rejected. Process-wide monkey-patching is outside Cordis effect ownership and races the protocol transport. The app composition owns stdout purity.
+
+## Consequences
+
+Editors can create, load, prompt, cancel, render, ask, and reconfigure multiple harness sessions over one ACP connection without a loop-specific dependency. The session event log remains the durable source for replay, prompt settlement, cwd, and per-session configuration. Tool presentation and human-answer channels remain extensible plugin contracts instead of ACP-specific behavior.
+
+The bridge deliberately does not implement session list/delete/resume/close capabilities, MCP passthrough, additional directories, image/audio/embedded-resource prompts, runtime model selection, plans, slash commands, usage updates, editor filesystem delegation, or the ACP terminal execution sub-protocol. The feature checklist records these as unsupported rather than silently accepting them.
+
+An idle config selection is truthful in the live response but not durable until the next turn anchors it. Crashing before that boundary loses the pending selection; this is the cost of keeping session events turn-enclosed and replay-safe.
+
+## Verification
+
+The ACP suites cover the in-memory protocol codec, create/load replay, exact prompt settlement, cancellation races, unsupported content, tool presentation, terminal capability fallback, permission outcome mapping, config-option validation and persistence, multi-session isolation, disconnect/disposal quiescence, and HMR cleanup. Snapshot and built-bin tests exercise the app composition, while the real-API e2e self-skips without a key.

docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md

@@ -0,0 +1,37 @@
+# RFC: Multiplex concurrent ACP sessions over one connection
+
+Status: implemented
+
+## Problem
+
+An ACP editor can keep several conversations alive over one agent subprocess. A single-active-session bridge would force extra processes and would not match Zed's client model, which tracks multiple session ids and concurrent loads. Multiplexing introduces isolation risks: events, prompt completion, cancellation, permission prompts, config selections, and predictable background-task ids must never cross session boundaries.
+
+## Decision
+
+The ACP bridge stores live sessions in `Map<SessionId, SessionRecord>` and keeps a `WeakMap<Agent, SessionId>` reverse index for agent-scoped callbacks. A record owns its agent handle, in-flight prompt, live tool-call presentation state, pending idle config switches, session cwd, and client capability snapshot. A separate loading-id set reserves each id before asynchronous resume so two pipelined loads cannot construct duplicate agents; distinct ids may load concurrently.
+
+Every `session/event` and `agent/status` callback resolves the owning record before sending or settling anything. Each session permits one in-flight prompt independently. The prompt records a log watermark, captures its own `turn/start`, and settles only on the matching `turn/end`; a late end from a cancelled prior turn cannot resolve a newer prompt. `session/cancel` addresses one record and calls only that agent's queue-aware cancel path.
+
+Permission ownership uses the same reverse index. The ACP `approval/request` answerer prompts only the editor session that owns the requesting agent and delegates foreign requests. User-interaction elicitations likewise route by agent ownership. Per-session sandbox and approval config values fold only that session's events, with pending idle switches stored on that record until the next turn anchors them.
+
+Background bash tasks carry an opaque owner token equal to the owning session id. `bash_output` and `bash_kill` compare the caller's token with the executor's task ownership before reading or killing; a predictable task id alone grants no access. Ownership is stored with the executor task, so a tool plugin reload does not erase it.
+
+Connection teardown clears the live map, settles each pending prompt as cancelled, and disposes all `AgentHandle`s in parallel. Each handle stops and awaits its loop, flushes the session while attached, unregisters the agent, and removes the session. Teardown is memoized and shared by client disconnect and plugin disposal.
+
+## Alternatives considered
+
+**One live session per connection** — rejected. It adds process overhead and contradicts the target client's multi-session shape without removing multiplexing needs from the editor.
+
+**A per-session `ctx.extend()`** — rejected. A child context does not by itself create a child plugin fiber, so listeners would still belong to the bridge fiber. The implemented bridge instead uses global listeners with explicit O(1) demultiplexing and per-session owned records; agent lifecycle is owned by `AgentHandle`.
+
+**Agent object identity as bash-task ownership** — rejected. A resumed or replaced agent object may legitimately represent the same durable session. The opaque session token is the cross-boundary identity that should survive plugin reloads.
+
+## Consequences
+
+N sessions can stream, prompt, request permission, switch config, and run background tasks concurrently without interleaving or cross-settling. A cancel or dispose in one session does not affect its neighbors. The bridge pays for explicit maps and isolation tests, but it does not add one listener set per session and therefore avoids listener fan-out during long-lived connections.
+
+The bridge still exposes no protocol method to close one live session independently. Today records leave together on connection teardown; session close/resume lifecycle capabilities remain deferred in the ACP feature checklist.
+
+## Verification
+
+The multi-session suite drives concurrent sessions through interleaved updates, independent in-flight prompts, targeted cancellation, same-id and distinct-id load races, permission routing, config isolation, and teardown. Tool-bash tests prove one session cannot read or kill another session's background task.

docs/rfc/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md

@@ -4,7 +4,7 @@ Status: implemented
 
 ## Problem
 
-The ACP bridge lets each tool own its call rendering via `presentCall`/`presentResult` (see [tool-call UI presentation](../../proposed/feature/2026-06-14-acp-agent-client-protocol.md) and `packages/core/tools`). For `bash` we surface the exact command as the `tool_call` title, the model's `description` as a content text block, `kind: 'execute'`, and the completed output wrapped in a fenced ` ```console ` text block.
+The ACP bridge lets each tool own its call rendering via `presentCall`/`presentResult` (see [tool-call UI presentation](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) and `packages/core/tools`). For `bash` we surface the exact command as the `tool_call` title, the model's `description` as a content text block, `kind: 'execute'`, and the completed output wrapped in a fenced ` ```console ` text block.
 
 That is a correct, capability-free baseline, but not how the reference editors render a *terminal* tool at its best. An editor like Zed has a dedicated terminal tool-call card — a header showing the working directory, the command as the label, the command output rendered as a terminal, and an exit-status pill — but it only builds that card when the `tool_call` carries terminal metadata (below). With a plain text block the output appears as static markdown and there is no cwd header. (Zed also HIDES `rawInput` for `kind: 'execute'`, which is why the command IS the title — both reference adapters do the same. The human-readable description rides as a separate content block above the card; note this is a DELIBERATE divergence — claude-agent-acp DROPS the description in terminal mode and renders only the card — we keep the summary visible alongside.)
 

docs/rfc/implemented/feature/2026-06-30-hook-bridges.md

@@ -53,7 +53,7 @@ Two different cwds, kept distinct on purpose. The hooks **themselves** run in th
 
 - **Tool-input rewrite.** A CC/Codex `updatedInput` is logged + warned, not honored — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite RFC](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)), because the pre-execution args are read by `tool/call` audit + `assistant/message` history + ACP/tool-bash presentation, so an honest rewrite is a design unit, not a field.
 - **Stop loop-guard** (`TODO(stop-loop-guard)`). CC/Codex break an infinite force-continue with `stop_hook_active` (true once a Stop hook fired this run) plus a max-consecutive cap; both are deferred. Today `stop_hook_active` is always `false`, so a Stop hook that unconditionally blocks would force-continue every step — a hook author must self-limit until the guard lands.
-- **Permission `ask`** degrades to `deny` at the `tools/pre-execute` seam (`FIXME(permissions)` in the interception-seams RFC) — there is no interactive permission prompt yet.
+- **Permission `ask`** — deferred at landing, since serviced: the [approval seam](2026-07-06-approval-seam.md) resolves `ask` through `ctx.approval` (ACP prompts over `session/request_permission`), degrading to `deny` only where no approval service is composed.
 - **Hook `continue:false` (hard halt).** A hook can ask to halt the whole run (CC/Codex `continue:false`); the shared merge folds it into `MergedHookOutcome.stop`/`stopReason`, but no bridge acts on it (`TODO(hook-continue-false)`) — the interception seams have no "hard-halt the agent" primitive yet (a Decision blocks/steers a single point, not the run). Deferred with the loop-guard work; the halt request is recorded in the `hook/result` log, and the hook keeps its per-point effect (decision/context) meanwhile.
 - **Config discovery.** The path is explicit in `cordis.yml` and process-level (see above); the full multi-layer CC/Codex precedence walk, per-session project-local discovery, and the trust/hash model are not reimplemented (`TODO(per-session-hook-config)`).
 - **Session-start / subagent-start context is best-effort, not gated (`TODO(session-start-gating)`).** `agent/session-start` is a synchronous emit and the bridge runs its hook on a detached `.then`, so the injected `additionalContext` is not guaranteed to land before the first turn reaches the model — a slow hook can miss the first request (the context then arrives as a later injection). `subagent/start` is sharper: an in-process provider may have already queued the child's prompt before the listener runs, and a short-lived child can finish before the detached inject fires. Making startup context a gated/awaited primitive is a loop-level change deferred to the interception seams; today the contract is "injected as soon as the hook resolves", not "before the first request". The bridge tests do NOT wait on the injection where they assert the guaranteed-timing behavior, so they document the real (best-effort) timing rather than masking it.

docs/rfc/implemented/feature/2026-06-30-interception-seams.md

@@ -36,7 +36,7 @@ Add/​reshape the interception seams so every one returns a small, seam-specifi
 
 ### What this PR does NOT do
 
-It does **not** declare `hook/*` SessionEvents (the durable hook-invocation log) — those belong to the `dsh-hook-protocol` library, because a native plugin can already use the typed Decisions without a durable hook log. A worked native-plugin example/test in this PR (`packages/core/agent-loop/tests/interception.spec.ts`) proves all the seams compose end-to-end through the REAL loop with NO `hook/*` involved — the concrete proof that "native hooks are just a plugin". Compaction (`PreCompact`/`PostCompact`), the Notification hook, Codex `PermissionRequest`, the permission/`ask` system, and the Stop loop-guard remain deferred (`FIXME(permissions)` marks the `ask`→deny degrade).
+It does **not** declare `hook/*` SessionEvents (the durable hook-invocation log) — those belong to the `dsh-hook-protocol` library, because a native plugin can already use the typed Decisions without a durable hook log. A worked native-plugin example/test in this PR (`packages/core/agent-loop/tests/interception.spec.ts`) proves all the seams compose end-to-end through the REAL loop with NO `hook/*` involved — the concrete proof that "native hooks are just a plugin". Compaction (`PreCompact`/`PostCompact`), the Notification hook, Codex `PermissionRequest`, and the Stop loop-guard remain deferred; the permission/`ask` system has since landed as the [approval seam](2026-07-06-approval-seam.md), whose `ctx.approval` services the `ask` this PR shipped degraded to deny.
 
 ## Alternatives considered
 

docs/rfc/implemented/feature/2026-07-05-skill-system.md

@@ -0,0 +1,53 @@
+# RFC: Skill system — progressive disclosure instructions for agents
+
+Status: implemented
+
+## Problem
+
+Agent products have converged on a skill pattern: keep the request prompt small by listing only available instruction bundles, then load the full body when the model decides a task matches. Codex, Claude Code, OpenCode, and Kimi Code differ in details, but all separate discovery metadata from complete instructions so a workspace can carry reusable behavior without paying the full prompt cost on every turn.
+
+DeepSeek Harness uses the same primitive so project-specific review, plugin-authoring, and tool-usage guidance lives next to the workspace or the user's agent configuration instead of being hard-coded into the loop.
+
+## Decision
+
+`@deepseek-ai/dsh-skill` is the pure provider registry (`ctx.skills`), `@deepseek-ai/dsh-skill-local` is the shipped local filesystem provider, and `@deepseek-ai/dsh-tool-skill` owns the session-prefix catalog and model-facing loader tool. `dsh-agent-core` loads the registry, local provider, and consumer by default so stdio and ACP apps get the same behavior while embedded or remote providers contribute skills without changing the registry or consumer. Its `skills` config forwards `registry`, `local`, and `tool` branches to those owners.
+
+Provider plugins register synchronously during `apply()`. Provider catalogs return ranked candidates from awaited `list()` calls, where remote providers perform initialization, authentication, and discovery while honoring the lookup abort signal. The registry validates each candidate, resolves same-name skills first-wins by rank, provider registration order, and provider-local order, then sorts summaries by skill name for deterministic consumers. It caches only completed catalog snapshots and retries when a provider/runtime revision changes during discovery, so an unload cannot freeze a stale, unresolvable skill into a session prefix. Runtime `ctx.skills.register(...)` remains a convenience for embedded in-process skills and uses project-over-user priority; `runtime` is reserved as the registry-owned provider name.
+
+The local provider scans cwd-sensitive project roots, custom roots, and user roots in first-wins rank order: project `.dsh`, project `.agents`, `customSkillDirs`, user `.dsh`, then user `.agents`. The user `.dsh/skills` scan skips `.system` so a system-owned directory is not treated as normal user content. DeepSeek Harness does not ship built-in system skills; embedded or remote providers supply additional skills when configured.
+
+Each skill is either `<name>/SKILL.md` or `<name>.md` with YAML frontmatter. `name` and `description` are required; `whenToUse`, `disableModelInvocation`, and `metadata` are optional. Names are kebab-case. YAML frontmatter is parsed with the `yaml` package instead of `js-yaml` or a hand-written parser: `yaml` is the already-declared modern parser for this package's limited frontmatter needs, and a narrow parser would either reject valid YAML users expect to work or grow into an unreviewed YAML subset.
+
+Local skill filesystem I/O goes through `ctx.fs` when a filesystem service is loaded: project-root lookup probes `.git` with `resolve` and `stat`, root discovery uses `listDir`, and skill reads use `readText`. The Node filesystem remains a fallback for minimal contexts that mount `dsh-skill-local` without the fs seam. Missing roots, unreadable or malformed skill files, and transient provider `list()` failures degrade to warn-and-skip so one bad source does not make every agent request fail; malformed candidates still fail fast because they are provider contract violations.
+
+`dsh-tool-skill` contributes one user-role `<system-reminder>` catalog through [`agent/session-prefix`](2026-07-07-session-prefix.md). The catalog contains sorted skill name and description only; it excludes bodies, paths, sources, providers, and routing hints. Descriptions are whitespace-normalized, XML-escaped, and capped by `catalogDescriptionMaxLength`, whose default is `500` and minimum is `3`. The session-prefix seam freezes the request-only catalog per loop instance and records it in the request header, preserving reconstructability without adding it to durable history. Full skill bodies are never included in the catalog.
+
+The `skill({ name })` tool loads one full skill for the current agent cwd and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` supplies a directory, URL, or opaque provider-managed base for explicitly referenced scripts, references, and assets; resources load only as needed, without directory enumeration. An unresolved name reports that the skill is unknown or no longer available; invalid names and skills marked `disableModelInvocation` retain distinct tool errors. The tool result is the model-visible disclosure path.
+
+The data structures and catalog/tool contract are documented in [skills.md](../../../core-data-structures/skills.md), with service signatures in the generated [services catalog](../../../cordis-catalog/services.md).
+
+## Alternatives considered
+
+**Inject full skill bodies into every system prompt.** Rejected because it destroys progressive disclosure and makes every request pay for instructions that may not apply.
+
+**Expose skills only as slash commands.** Rejected because model-initiated loading is the core capability; slash/ACP command advertisement does not change discovery.
+
+**Put local filesystem scanning directly inside `ctx.skills`.** Rejected because coding agents, web agents, and future plugin ecosystems need different skill sources. A provider registry mirrors the subagent seam: the registry owns conflict resolution and consumers, while implementations own loading.
+
+**Use a system-prompt section.** Rejected because the rendered system prompt is a single string, while the catalog is a user-role `<system-reminder>` message with request-only lifecycle requirements. [`agent/session-prefix`](2026-07-07-session-prefix.md) is the selected mechanism: it places the catalog ahead of derived history and records the composed message in the request header.
+
+**Materialize built-in DSH authoring skills under `~/.dsh/skills/.system`.** Rejected because bundled skills do not write user home on startup, and embedded or remote providers supply configured skills.
+
+**Recursively discover nested `**/SKILL.md`.** Rejected. Flat files and one-level directory bundles cover the configured roots while keeping duplicate handling and catalog order easy to reason about.
+
+**Hand-parse frontmatter.** Rejected because the accepted schema includes an open `metadata` object. A narrow parser would either reject valid YAML users expect to work or grow into an unreviewed YAML subset.
+
+## Consequences
+
+The agent-core spine includes one session-prefix contributor, one local provider, and one model-facing tool. Skill discovery is cwd-sensitive, so callers that create agents with different session cwd values can observe different project skill overrides by design.
+
+The catalog is deterministic for a fixed root set and runtime registration revision, but disk changes are not watched; discovery is memoized until runtime registration invalidates the cache or the process restarts.
+
+## Deferred
+
+Forked skill contexts (`context: fork`), direct user/slash invocation (`user-invocable`), parameter declarations and hints (`arguments` and `argument-hint`), and per-skill tool constraints (`allowed-tools` and `disallowed-tools`) are outside the shipped contract. The registry, local provider, and model-facing tool do not parse, advertise, or enforce these fields.

docs/rfc/implemented/feature/2026-07-06-approval-seam.md

@@ -0,0 +1,141 @@
+# RFC: The approval seam — one-shot permission decisions over a waterfall of answerers
+
+Status: implemented
+
+## Problem
+
+Two callers need to put one question — "may this specific action proceed?" — to a human, and neither has a channel. `tools/pre-execute`'s `ask` decision (produced today by the Claude-Code hook bridge's `permissionDecision: ask`) degrades to deny because nothing services it. The [sandbox RFC](2026-07-06-sandbox.md)'s escalation phase needs the same channel for its post-denial one-shot retry. Without a shared seam, each would invent its own outcome vocabulary, UI routing, cancellation, and audit trail — and a deployment with no UI at all needs a guarantee that an unanswerable question can never grant anything.
+
+The routing problem is ownership: an approval prompt must reach the editor session that owns the asking agent (the ACP bridge multiplexes N sessions over one connection), fail closed for agents nobody owns (in-process subagents, tests), and stay out of deployments that compose no UI (headless, CI).
+
+## Decision
+
+One package, `dsh-user-approval` (`packages/ui/user-approval`), owning the vocabulary and the `ctx.approval` service — the MECHANISM. The POLICY — who answers, and whether a session is asked at all — lives outside it: answerers are `approval/request` waterfall listeners registered by the plugins that own the channel (the ACP bridge; future terminal UIs; test scripts), and a per-session policy tier can decide before any human is involved. Consumers (`dsh-tools`' ask routing, the sandbox escalation gate) resolve a question to a closed outcome and derive their own tool results from it. Deliberately ONE package, not the capability-seam three (see Alternatives).
+
+### How a deployment uses it
+
+One `cordis.yml` entry mounts the seam; not loading it is the opt-out — consumers degrade to their historical fail-closed behavior with zero approval code registered:
+
+```yaml
+- id: approval
+  name: '@deepseek-ai/dsh-user-approval'
+  # config:
+  #   policy: never   # deployment default for sessions without an override; 'ask' when omitted
+```
+
+The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-agent`, as in [the sandbox example](../../../../examples/sandbox-acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws.
+
+What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked.
+
+One ask under this composition, verbatim from the sandbox example's recorded `escalation-approved` scenario — the model requests a sandbox escalation, the gate asks, the bridge prompts the owning editor, the user clicks Allow once:
+
+```
+tool/call        bash {"command": "printf 'escalated\n' > escalated.txt && cat escalated.txt",
+                       "sandbox_permissions": "workspace-write",
+                       "justification": "the user asked to write escalated.txt in the workspace"}
+approval/asked   {"toolName": "bash", "callId": "call_00_…",
+                  "reason": "escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}
+  → session/request_permission {"toolCall": {"toolCallId": "call_00_…"},
+                  "options": [{"optionId": "allow-once", "name": "Allow once", "kind": "allow_once"},
+                              {"optionId": "reject-once", "name": "Reject",     "kind": "reject_once"}]}
+  ← the user picks "Allow once" on the prompt the editor attaches to the streamed bash call
+approval/decided {"outcome": "allowed-once"}
+tool/result      "escalated" — this one call ran under the wider mode; the grant died with it
+```
+
+The `escalation-rejected` twin ends in `{"outcome": "rejected"}` instead: nothing executes, and the model's result carries the asker's verbatim fail-closed text (`the user rejected escalating this command to "workspace-write"`). A hook's `permissionDecision: ask` rides the identical wire; only the asker and its deny texts differ (§ Ask routing in dsh-tools). Headless, the same request skips the prompt entirely and settles `unavailable`.
+
+### Design detail
+
+#### The seam: mechanism and policy split
+
+`ApprovalService.request(req)` always resolves to a closed `ApprovalOutcome` — `allowed-once` / `rejected` / `cancelled` / `unavailable` — and never rejects. The service is the mechanism: it dispatches the `approval/request` waterfall, races the request's `AbortSignal` (abort settles `cancelled`; a late answer is discarded, never double-audited), contains a throwing answerer as `unavailable`, normalizes a rogue non-vocabulary return to `unavailable`, and lands the log-only audit pair `approval/asked`/`approval/decided` (paired by the branded `ApprovalRequestId`) on the requesting agent's session log. Grants are one-shot by definition: `allowed-once` authorizes the single asked-about action, never a class of future ones, and the service stores nothing between requests. The one precondition: `request()` throws (before appending anything) when the agent's session has no open turn — the audit pair must be turn-enclosed, the turn being the durable log's commit/replay boundary (a bare event between turns is dropped as crash tail on reload); every shipped ask path runs mid-turn already, and idle asks are a deferred design.
+
+Answerers are the policy, and they are `approval/request` waterfall listeners. The waterfall buys exactly what the seam needs: with zero listeners the dispatch falls through to the caller-supplied default — `unavailable`, so fail-closed needs no configuration and no code in any deployment; a listener that recognizes the request's agent answers by returning an outcome without calling `next()` (the decision slot is single-occupancy, first answer wins — the same documented semantics as the `fs/write-intent` gate); a listener that does not recognize the agent MUST delegate via `next()` so another answerer or the default gets the question; and listeners dispose with their owning fiber, so an unloaded UI plugin degrades the next ask to `unavailable` instead of leaving a dangling channel. Registration order across sibling plugins is not load-order deterministic (the loader starts siblings concurrently), so a deployment composes ONE terminal answerer and reserves `prepend` listeners for decide-or-delegate gates.
+
+`ApprovalRequest` carries the asking `agent` (routes the question; receives the audit events), the `toolName`, the optional exact `callId`, the asker's human-readable `reason`, and the optional `signal`. The vocabulary is deliberately self-contained — it names the tool-call by the `CallId` brand from `dsh-llm` and never imports `dsh-tools` — because `dsh-tools` depends on `dsh-user-approval` (the ask routing) and a `ToolCallView` import would close a package cycle. It deliberately does NOT carry tool arguments: a UI answerer attaches the prompt to the already-streamed tool call via `callId` instead of re-rendering the call.
+
+#### Ask routing in dsh-tools
+
+`ToolRegistry.execute()` resolves an `ask` decision through the seam before the shared deny path: `allowed-once` proceeds to dispatch, and the three non-grants deny with distinct reasons — "the user rejected…", "…was cancelled", "…no approval channel is available" — so the model can tell a human "no" from an absent channel. The seam is consumed opportunistically (`ctx.get('approval')`, the `tool-bash`/`agent-loop` pattern), not statically injected: a deployment that composes no ApprovalService keeps the historical ask→deny degrade verbatim, an unmount mid-session degrades the same way on the next ask, and the registry's fiber never gates on the seam's presence. An agent-less execution also degrades — without an agent there is no session to audit to and no UI to route to.
+
+#### The per-session policy tier
+
+The seam also owns the session-scoped approval policy — the approval knob of the two-knob per-session switching design ([the sandbox RFC](2026-07-06-sandbox.md) § Per-session modes is the pattern's home: one log-only event per knob, a pure fold, THE write path, ACP config-option advertisement, and turn-anchoring). `ApprovalPolicy` is `'ask' | 'never'`, and `effectiveApprovalPolicy(events) ?? Config.policy` (default `'ask'`) decides every request BEFORE any interactive answerer: the service resolves a `'never'` session to `'rejected'` INSIDE `request()`, before dispatching the waterfall at all — no listener registration, including a later `prepend`, can sit ahead of it — while `'ask'` dispatches unchanged (fail-closed `'unavailable'` with nobody composed, exactly the prior behavior). Visibility follows the switching design's two layers with one asymmetry: the prompt section states ONLY `'never'` (deterministic, availability-independent — "you will be prompted" would overclaim in a composition with no answerer, and absence under a logged header is exactly how the narrator reads `'ask'` back), the narrator injects at most one coalesced notice per switch, and the audit pair still lands on every ask, including the policy's auto-rejections.
+
+#### The ACP answerer
+
+The bridge registers the first real answerer: it resolves the owning session through its existing `WeakMap<Agent, sessionId>` reverse map, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment.
+
+The reverse-map ownership seam [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) laid down is exactly what the answerer routes through, and per-session permission ownership (the blocker recorded in [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md)) is what it implements.
+
+#### Audit, and what the model sees
+
+`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching) and a contained answerer failure.
+
+#### Entities and dependencies
+
+One package, no cycles: `dsh-user-approval` peers on `cordis`, `dsh-session` (event-map merge + append), `dsh-agent` (the `Agent` type), `dsh-llm` (`CallId`, via `dsh-brand`). `dsh-tools` and `dsh-acp` each peer on it; the escalation phase's asker lives in `dsh-tool-bash` (see [the sandbox RFC](2026-07-06-sandbox.md) § Escalation), so the sandbox family keeps its ZERO-edge relation (the executor contributes the per-call override mechanism, and transport seams never ask humans questions). The seam is one package, not the capability-seam three: the service body (dispatch + audit) has no replaceable implementation — the replaceable part is the answerer listeners, and those live with their owners (the bridge; future terminal UIs; test scripts). `@cordisjs/plugin-capability` stays orthogonal (a static grant registry answers "is this already authorized", not "ask the user now"), and `subagent-acp`'s child-side `permission` auto-answer is untouched — routing a child's approvals to the parent session is deferred (§ Deferred).
+
+### Testing
+
+Unit tier: the service's outcome branches (fail-closed default, first-wins slot, delegation, containment, rogue-value normalization, abort-before and abort-during with late-answer discard, fresh ids, fiber-disposal degradation) and the policy tier (both values × dispatch/decide, a `'never'` decision unbypassable even by an answerer prepended AFTER the service, audit pair intact) in `dsh-user-approval`; the ask routing matrix (grant dispatches; three non-grant reasons pinned verbatim; unmounted and agent-less degrades; the registry's own exhaustiveness backstop against a non-conforming stand-in) in `dsh-tools`; the answerer (wire shape of the prompt, outcome mapping, unknown-option conservatism, foreign-agent and call-less delegation) driven through a real bridge + scripted client in `dsh-acp`.
+
+Snapshot tier: the harness accepts scripted permission answers (`permissionAnswers` in a scenario's `input.json`, consumed FIFO; an unscripted prompt answers `cancelled`, fail closed). The seam's wire is recorded end to end in the sandbox example's suite: both escalation branches drive `session/request_permission` through this seam over scripted answers (grant and rejection), and the recorded `mode-switching` scenario pins the `'never'` prompt sentence and the policy-switch notice ([the sandbox RFC](2026-07-06-sandbox.md) § Testing).
+
+## Deferred
+
+- **`allow_always` grant storage** — honoring a persistent grant means designing storage, scope identity (call? path? prefix? session? time window?), and revocation; until designed, only the one-shot options are advertised ([the sandbox RFC](2026-07-06-sandbox.md) § Escalation records the open scope question).
+- **A recorded hook-driven `ask` scenario** — the wire is recorded via the sandbox example's escalation branches; the hook-producer variant stays on the unit tier and the hook matrix's `hook-cc-pretool-ask`, with its deny texts pinned verbatim there.
+- **Routing a child agent's approvals to the parent session** — `subagent-acp`'s child today auto-answers its own `permission` requests; surfacing them to the parent's editor is its own design.
+
+## Alternatives considered
+
+- **A single registered provider instead of waterfall listeners** — rejected: a `registerProvider()` surface forces every composition question — allowlist pre-filters, external hook deciders, scripted test answers, a policy gate in front of a human — inside one provider implementation. The waterfall gets composition, fail-closed absence, and HMR disposal from machinery the runtime already has; the seam's JSDoc pins the single-decision-slot convention instead of inventing a provider registry.
+- **[The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md)'s inline `tools/pre-execute` permission gate** — rejected, and superseded by this seam: prompting for every bridge-owned call hardwires the asking POLICY into the UI plugin, cannot serve a second asker (sandbox escalation happens after execution starts, with no pre-execute moment), and leaves hooks' `ask` — the vocabulary the interception seams already ship — unserviced.
+- **A generic user-interaction seam (`ctx.userInteraction`) instead** — rejected: the two share a skeleton (route by agent, block for a human, handle absence), but approval's contract is narrower in every dimension that matters: a closed outcome vocabulary instead of free text, a protocol-native prompt attached to a tool call instead of a generic form, mandatory fail-closed absence, and audit events. The generic seam has since shipped (`packages/ui/user-interaction`, the `ask_user_question` tool over ACP elicitation) and approval deliberately still does not ride it — an elicitation form is not a permission prompt, and a free-text answer is not a closed outcome; sharing provider plumbing stays open if the two ever converge.
+- **Static optional injection in `dsh-tools`** — rejected: the vendored cordis `Inject` type has no optional flag — the object form maps service names to intercept config, and a declared inject gates the fiber. `ctx.get('approval')` is the documented opportunistic-consumption pattern (the `tool-bash` owner-token lookup, the loop's persistence probe), reads presence per call, and degrades correctly across HMR without extra machinery.
+- **The capability-seam three-package split** — rejected: interface/implementation/consumer fits a seam whose implementation is swappable (bash-local vs bash-sandbox). Here the service body is fixed mechanism and the variable part is listeners that live with their owners — splitting would manufacture an implementation package with nothing in it ("don't split preemptively").
+- **Offering `allow_always` now** — rejected: the protocol can express it, but honoring it means designing grant storage, scope identity, and revocation (§ Deferred). Advertising an option the harness cannot honor manufactures doomed grants.
+
+## Consequences
+
+What shipped pins — the suites in Testing hold each:
+
+- With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason.
+- A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)).
+- Every unanswerable path fails closed to `unavailable`: no service (degrade, verbatim historical text), no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, a dead client connection.
+- Every `request()` lands exactly one `approval/asked`/`approval/decided` pair on the asking agent's log, replayable, invisible to the model transcript.
+- Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor.
+- A deployment that composes nothing new behaves byte-identically (the snapshot suite's goldens are unchanged).
+
+Costs and accepted limits:
+
+- **Two decide-eager answerers race for the slot.** Sibling-plugin listener order is not deterministic, so the seam cannot referee competing terminal answerers — mitigated by convention (one terminal answerer per deployment; `prepend` only for decide-or-delegate gates) rather than a priority mechanism the event bus does not have.
+- **Production exercise rests on one composition.** `ask` has two producer families — the hook bridges through `tools/pre-execute`, and sandbox escalation through its own gate — with the wire recorded in the sandbox example's snapshot suite, so the seam's real-world coverage is that one composition until more deployments compose it.
+- **Ownership keys on `Agent` object identity.** The answerer resolves sessions through the bridge's existing WeakMap; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need session-id matching instead.
+
+## FAQ
+
+Behavioral and usage questions only — every "why not X?" design question lives in [Alternatives considered](#alternatives-considered), whose job is exactly that.
+
+- **What happens in a deployment with no answerer at all (headless, CI)?** Every ask falls through the empty waterfall to `unavailable` and the tool call denies with the "no approval channel is available" reason. Fail-closed is the zero-listener default, not a configuration.
+- **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred).
+- **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel.
+- **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt.
+- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer — one audit pair either way, never two.
+- **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant.
+- **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are unanswerable today by design. `subagent-acp`'s child-side auto-answer is untouched; routing a child's asks to the parent's editor is deferred (§ Deferred).
+- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; the audit pair still lands for every auto-rejection.
+- **What happens across a hot reload, or when the UI plugin unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state.
+- **Where does the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own.
+
+## Prior art
+
+In-repo precedents this design copies or contrasts with:
+
+- The `fs/write-intent` gate (`packages/fs/fs/`) — the documented single-occupancy decision-slot waterfall semantics (first answer wins, delegate via `next()`) the answerer contract reuses.
+- `hook/invoked`/`hook/result` — the log-only audit-pair precedent `approval/asked`/`approval/decided` follows; [the hook-bridges RFC](2026-06-30-hook-bridges.md) ships `permissionDecision: ask`, the first producer.
+- [The interception-seams RFC](2026-06-30-interception-seams.md) — the `tools/pre-execute` `allow`/`deny`/`ask` vocabulary whose `ask` this seam services.
+- [The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) — the `WeakMap<Agent, sessionId>` ownership seam the answerer routes through; [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements.
+- The opportunistic `ctx.get()` consumption pattern (`tool-bash`'s owner-token lookup, the loop's persistence probe) — how `dsh-tools` consumes the seam without gating its fiber on it.

docs/rfc/proposed/feature/2026-06-14-acp-agent-client-protocol.md

@@ -1,84 +0,0 @@
-# RFC: Agent Client Protocol (ACP) support — drive the coding agent from external editors
-
-Status: proposed
-
-> **Implementation status (MVP landed):** steps 1, 2, 3, 4, 6, 7, 8 are implemented in `packages/ui/acp` + `examples/acp-agent`. **Step 5 (the `session/request_permission` permission gate) is deferred** — the bridge ships a pass-through (tools run with the executor's full authority) marked `TODO(rfc010-permission-gate)`, and lays down only the `WeakMap<Agent, sessionId>` ownership seam the gate will build on. Status stays `proposed` until the gate lands. `session/cancel` is the queue-aware `agent.cancel()`: it aborts a running step, clears queued + steering work, and drops a turn that is about to start, so a queued-but-not-yet-started prompt never runs and a later prompt cannot be batched into the cancelled turn. **Per-session `cwd` is now honored** (lifting the original "launch the server in the workspace root" restriction — see § Deferred): `session/new` accepts any absolute `cwd`, and `session/load` requires the request `cwd` to match the persisted session `cwd` so the editor and bash executor agree on the workspace.
-
-## Problem
-
-The coding agent is reachable only through the readline `stdio-chat` plugin: it reads lines from stdin, calls `agent.send()`, and prints the assistant token stream (`session/event` `assistant/chunk`) to stdout. There is no structured protocol, so the agent cannot be embedded in an editor — no streaming render, no tool-call display, no permission UI, no resumable sessions.
-
-Editors are converging on the Agent Client Protocol (ACP), which Zed and others speak: JSON-RPC 2.0 over newline-delimited stdio, modeled on the Language Server Protocol. An editor boots the agent as a subprocess and exchanges `initialize` / `session/new` / `session/prompt`, rendering streamed `session/update` notifications and `session/request_permission` prompts. The goal is for the agent to be a drop-in ACP server — implement the protocol once and run in any ACP client, with no per-editor glue.
-
-This RFC has a hard prerequisite on [session persistence](../../implemented/architecture/2026-06-14-session-persistence.md): it assumes durable session persistence (the `SessionPersistence` service and the async `AgentLoop.resume` seam) is implemented, so resuming a session via `session/load` is in scope. None of those APIs exist yet — `AgentLoop` currently exposes only the synchronous `create` — so ACP must land after, or in the same change as, [session persistence](../../implemented/architecture/2026-06-14-session-persistence.md), and pins to its `resume(agentId, resumeSessionId)` contract. Session persistence persists every `SessionEvent` verbatim (including `assistant/chunk`), so a loaded session has the stream chunks needed to replay turns to the client.
-
-## Proposal
-
-A new plugin package `@deepseek-ai/dsh-acp` — a client-driver / UI plugin, the structured analogue of `stdio-chat`. It is NOT a change to the loop and NOT an [capability seams](../../implemented/architecture/2026-06-13-capability-seams.md) interface/implementation/consumer capability split; it consumes the existing `agent/*` event taxonomy and the `tools/pre-execute`/`tools/post-execute` waterfalls.
-
-It depends on the official `@agentclientprotocol/sdk` (the `AgentSideConnection` class) — Apache-2.0, actively versioned. The SDK declares a `zod` peer dependency and imports `zod/v4` at runtime, so `packages/ui/acp` must declare `zod` itself (per the workspace dependency constraints). This is the renamed successor to `@zed-industries/agent-client-protocol`, which is now deprecated on npm.
-
-The mapping between ACP and existing harness seams — each row names the seam and any required extension:
-
-| ACP (client ⇄ agent) | Harness seam | Notes |
-|---|---|---|
-| `initialize` | static handler | negotiate `protocolVersion` (echo the supported version, else error); advertise text-only `promptCapabilities` and `loadSession: true`; report agent name/version |
-| `session/new {cwd, mcpServers, additionalDirectories}` → `{sessionId}` | the `dsh-agent` create factory (see Dependency note + Plan) | the seam must accept `{ sessionId, meta }` so the ACP-generated `sessionId` becomes the live/persisted session id and the validated `cwd` is attached as the `SessionHeader` (today `AgentLoop.create(id)` hardcodes `${id}-session` and takes no metadata); reject a 2nd session (single-session MVP, see [ACP multi-session](2026-06-14-acp-multi-session.md)); `cwd` validated (require absolute) — any absolute cwd is honored: it becomes the session's `SessionHeader.cwd` and the default bash workdir (per-session cwd, see § Deferred → RESOLVED), so the server need not launch in the workspace; non-empty `mcpServers` and `additionalDirectories` are rejected for the MVP because silently ignoring requested servers/roots would desync the client's tool and filesystem-scope UI |
-| `session/load {sessionId, cwd, mcpServers, additionalDirectories}` | the `dsh-agent` resume factory ([session persistence](../../implemented/architecture/2026-06-14-session-persistence.md) + Dependency note) | load `{ meta, events }`, seed the session, re-derive history via `deriveMessages()`, replay prior turns to the client as `session/update` per the ACP load contract; `mcpServers` and `additionalDirectories` rejected as in `session/new` |
-| `session/prompt {prompt}` | `agent.send()` (idle) | text blocks → `TextBlock`; reject image/audio per advertised capabilities; one in-flight prompt per session |
-| resolve `session/prompt` → `{stopReason}` | the `turn/end` `session/event` (its `reason`) | map the harness kebab `TurnEndReason` to the ACP snake_case `StopReason` wire enum: `completed`→`end_turn`, `max-tokens`→`max_tokens`, `aborted`(cancel)→`cancelled`, plus `refusal`/`max_turn_requests` when applicable; honor the batch-into-one-turn and send-not-synchronously-running settle semantics |
-| `session/update: agent_message_chunk` | `session/event` `assistant/chunk` `text-delta` only | do NOT also emit on `block-end(TextBlock)` — it carries the fully-assembled block and would duplicate the streamed text |
-| `session/update: agent_thought_chunk` | `session/event` `assistant/chunk` `reasoning-delta` | |
-| `session/update: tool_call` (pending→in_progress) | `session/event` `tool/call` | demux via a Session→sessionId map; `kind` inferred from the tool name |
-| `session/update: tool_call_update` (completed/failed) | `session/event` `tool/result` | a throwing `tools/execute` yields NO `tool/result` → fail the pending tool UI from `agent/error`/turn-end |
-| `session/request_permission {sessionId, toolCall, options}` | prepended `tools/execute` listener | no-op unless `exec.agent` is ACP-owned; await the outcome; `selected/allow_*` → `next()`; `reject_*`/`cancelled` → veto `ToolExecutionResult{isError}` |
-| `session/cancel` (notification) | `agent.cancel(reason)` | the queue-aware cancel (abort running step, clear queued + steering, drop an about-to-start turn); settle the in-flight prompt as `cancelled`; resolve any pending permission as `cancelled` exactly once |
-
-The permission gate is the first real consumer of the `tools/execute` veto seam (the documented "single veto/sandbox/permission seam" plus the deferred "Permission system" TODO in [docs/architecture.md](../../../architecture.md)). It is a single global listener registered with `prepend: true` so it runs before any other tool wrapper. `ToolExecution.agent` is optional and the `Agent` interface carries no origin marker, so the bridge tracks ownership itself: it records each agent it creates in a `WeakMap<Agent, sessionId>` and the gate no-ops (calls `next()` immediately) for any `exec.agent` it does not own — non-ACP agents and the no-agent case pass straight through. For an owned agent it resolves the session, issues `session/request_permission`, and stores the pending resolver on that session's record so the outcome — or a `session/cancel`/connection-close — settles it exactly once.
-
-Lifecycle and disposal: the connection, listeners, and in-flight permission promises register via `ctx.effect`/`ctx.on`; teardown is async and must *reach* quiescence, not just request it — close the connection, settle/reject pending permissions, and dispose each owned agent through its `AgentHandle.dispose()` (which stops the loop, `await`s its exit, and unregisters). Owner teardown goes through that handle seam, not the loop's concrete `agent.done` (which exists only on `ReactLoopAgent`); a non-owner that merely wants to *observe* the current work settling without tearing the agent down awaits the interface-level `agent.whenIdle()`. Every listener contains its `send()` exceptions (log, never reject the turn) because stream chunks are emitted inside the model step, so a throwing listener would corrupt the turn.
-
-**Dependency note (architecture rule).** [docs/architecture.md](../../../architecture.md) states "plugins depend on interface packages, never on `dsh-agent-loop`." Creating and resuming agents is currently only on the concrete `AgentLoop` (`ctx.agentLoop`), so this RFC proposes adding an **abstract create/resume factory** to the `dsh-agent` interface (registry-level `create({ sessionId, meta })` / `resume(...)`), implemented by the loop, so `dsh-acp` injects only `agents` (the interface) and the dependency rule holds. The alternative — injecting the concrete `agentLoop` and recording a documented exception in the architecture doc — is explicitly the non-preferred fallback.
-
-## Plan
-
-1. Package scaffold `packages/ui/acp/` per [the cookbook](../../../cookbook/adding-a-package.md); add `@agentclientprotocol/sdk` and `zod`. Add the abstract create/resume factory to `dsh-agent` (the interface) so the bridge can `inject: ['agents', 'sessions', 'tools', 'sessionPersistence']` without depending on the concrete loop; `sessionPersistence` is required because `session/load` advertises `loadSession: true`. (Fallback only if the factory is judged not worth it: inject `agentLoop` directly and record the architecture-rule exception in `docs/architecture.md`.)
-2. Connection plus `initialize`/`session/new`: wire `AgentSideConnection` to stdin/stdout; protocolVersion negotiation; the single-session guard; create the live session through the new `{ sessionId, meta }` factory seam (so the ACP `sessionId` and validated `cwd` become the session's id and header); the `sessionId↔agent` and `Session↔sessionId` maps.
-3. Internal edit — turn-end reason fidelity (sanctioned: edit internals to fit ACP). Extend `TurnEndReasonMap` in the proper places: (a) declaration-merge a `max-tokens` variant in the owning package (`packages/core/session/src/types.ts`, alongside `completed|aborted|error|disposed`) — add `max-tokens` because `FinishReasonMap` produces it (DeepSeek maps `length` → `max-tokens`); do not add `refusal`, since no current adapter produces it (unknown DeepSeek finish reasons collapse to `error`), but leave a comment in `TurnEndReasonMap` noting `refusal` should be added when an adapter first emits it (`FinishReasonMap` is merge-extensible); (b) make `agent-loop`'s `loop.ts` populate the reason from the model `finish` chunk — `assembler.finish` lives inside `runStep`, so `runStep` must return it up to `runTurn`, and the rule is "the last step's finish reason wins, but any `max-tokens` in the turn surfaces as `max-tokens`"; (c) no consumer exhaustively switches over `TurnEndReason` today (the invariants plugin switches on `SessionEventType`, and `deriveMessages` ignores `turn/end`), so adding `max-tokens` is a non-breaking extension — but recheck before landing; (d) update [docs/architecture.md](../../../architecture.md) (the CI-verified loop-lifecycle/event-taxonomy doc) and the affected package READMEs/JSDoc (`dsh-session`, `dsh-agent`, `dsh-agent-loop`) per the repo doc-sync policy. This replaces a fragile "observe the finish chunk in the bridge" hack with a real, documented contract.
-4. Prompt-turn streaming plus load: translate `session/event` (the `assistant/chunk` token stream plus boundaries and tool activity) into `session/update`; resolve `session/prompt` on settle, mapping the harness `TurnEndReason` to the ACP `StopReason` wire enum (`completed`→`end_turn`, `max-tokens`→`max_tokens`, `aborted`→`cancelled`) — a small total function with a test asserting the exact wire strings, since the SDK rejects an unknown `stopReason`. Concrete correlation, since the loop batches queued messages into one turn and `send()` does not synchronously flip to running: install the `session/event` listener before `send()`; capture the prompt's owning turn from its `turn/start` record, then resolve on that turn's `turn/end` (with `agent/status` idle/disposed as a fallback); reject an empty/whitespace prompt up front rather than calling `send()` (no turn would ever start, so the RPC would hang). Implement `session/load` on the session-persistence resume seam.
-5. Permission gate: a single `tools/execute` listener registered with `prepend: true`, owning a `WeakMap<Agent, sessionId>` of bridge-created agents; no-op (`next()`) for unowned/no-agent calls; for owned calls → `session/request_permission` → allow (`next()`) / veto; settle the stored resolver exactly once on outcome, cancel, or connection close.
-6. Example wiring (extract a shared base). `@cordisjs/plugin-include` is itself a plugin entry that resets `ctx.baseUrl` and loads a path, so a child `cordis.yml` can nest-include a shared base; the extraction is safe because every dependent plugin declares `inject` (loader groups initialize via `Promise.all`, so YAML order is NOT the dependency mechanism — never rely on it). Extract the provider/tool core (`llm, sessions, system-prompt, tools, agents, invariants, llm-deepseek, bash-local, tool-bash`) into `examples/base.yml`; have both `coding-agent` and a new `examples/acp-agent/` include it and add their own UI plugin plus logger. Keep `agent-loop` per-example (NOT in the base): `AgentLoop` creates its configured agents in its constructor, and the two examples disagree — `coding-agent` needs a pre-created `main` (its `stdio-chat` calls `ctx.agents.get('main')`), while `acp-agent` must pre-create none (ACP `session/new` creates agents). So `coding-agent` declares `agent-loop` with `agents: [{ id: main, … }]` and `acp-agent` with `agents: []`. `acp-agent` loads `dsh-session-persistence-jsonl` (from [session persistence](../../implemented/architecture/2026-06-14-session-persistence.md) — required for `session/load`), omits the stdout logger (see Risks), and adds `pnpm run demo:acp` plus the Zed `agent_servers` snippet.
-7. Tests (the repo cares a lot here): a property-based test for the protocol shape (precedent: [property-based testing](../../implemented/testing/2026-06-11-property-based-testing.md)) — fuzz arbitrary harness event sequences and assert ACP-stream invariants (never a `tool_call_update` before its `tool_call`; exactly one `session/prompt` resolution per prompt; monotonic, well-formed ordering; `stopReason` in the legal set); codec unit tests over an in-memory `Duplex` pair (drive `AgentSideConnection` without a subprocess; assert exact frames for `initialize`, `session/new`, a full prompt turn); the mandatory HMR-safety test (dispose the fiber; assert the connection closed, all `ctx.on` listeners gone, any in-flight `request_permission` settled); failure-path tests (connection closes mid-stream; closes with a permission pending; a notification `send()` rejects but the turn survives; `finish{kind:'error'|'aborted'}`; a `tools/execute` throw with no `tool/result`; a second `session/new` rejected; a `session/prompt` while one is in flight; an empty prompt rejected without hanging; a `session/load` re-derives identical history and replays it); and an e2e (`*.e2e.ts`, self-skips without `DEEPSEEK_API_KEY`) that boots `examples/acp-agent`, connects a `ClientSideConnection`, sends a real prompt, owns and disposes the harness in `afterEach`, and verifies the world (files on disk), not the agent's self-report.
-8. Docs: module/JSDoc plus a package README; extend [the extension cookbook](../../../cookbook/extension-cookbook.md) with the client-driver pattern. Flip Status to `implemented` on landing; record a decision in this RFC only if it proves durable, contested, and surprising (candidates: the `tools/execute` permission-ownership rule, the npm-dependency choice) — not auto-required.
-
-Deferred (each names its owning future work):
-
-- Multiplexing concurrent sessions → [ACP multi-session](2026-06-14-acp-multi-session.md).
-- ~~`cwd` honoring.~~ **RESOLVED.** Originally there was no path from `session/new.cwd` to the bash workdir (`tool-bash` forwarded only an explicit `args.workdir`; `LocalBashExecutor.resolve` defaulted to its own config or `process.cwd()`), so the MVP validated `cwd` (require absolute) AND required the server to launch in the workspace root, erroring on a mismatch. This is now lifted: the validated `cwd` is stored as `SessionHeader.cwd`, and `dsh-tool-bash` defaults the bash workdir to the calling agent's `session.header.cwd` (an explicit model `workdir` still wins; a relative one resolves against it). Any absolute `cwd` is honored — the server need not launch in the workspace, and N sessions can each target a different directory. Widening scope beyond the single cwd (`additionalDirectories`) remains deferred.
-- Client `terminal/*` proxying (a live editor terminal) and `fs/*` (editor-rendered diffs) — a future `BashExecutor` over the [capability seams](../../implemented/architecture/2026-06-13-capability-seams.md) bash seam, gated on `clientCapabilities.terminal`.
-- Image/audio prompts (blocked on the DeepSeek adapter, which skips `image` blocks today), modes, auth, `available_commands`/slash-commands, `plan`, and `usage_update`.
-
-## Alternatives considered
-
-- **A process-wide stdout hijack inside `dsh-acp`** (defensively monkey-patching `console.log` / `process.stdout.write`) — rejected: it lives outside Cordis' effect-scoped, HMR-friendly plugin model, races the connection's own stdout handoff, and fights the logger. The stdout guarantee is config-only.
-- **Injecting `agentLoop` directly instead of the abstract create/resume factory** — the recorded fallback, taken only if the factory seam is judged not worth it, with the architecture-rule exception recorded in `docs/architecture.md`.
-
-## Acceptance criteria
-
-- The `acp-agent` example speaks ACP over stdio end-to-end: `initialize`, `session/new` with a validated absolute `cwd` honored as the session workspace, streamed `session/update` frames per prompt turn, `session/load` re-deriving identical history, and `session/prompt` resolving with the correct wire `stopReason`.
-- stdout carries only framed JSON-RPC (asserted by test); the permission gate settles every `session/request_permission` exactly once — on outcome, cancel, or connection close.
-- The plan's test set runs green: the property-based protocol invariants, the codec unit tests over an in-memory duplex pair, the HMR-safety test, the failure-path matrix, and the self-skipping real-API e2e that verifies the world.
-
-## Risks
-
-stdout is the protocol — guaranteed by config, not by monkey-patching. The console logger writes through `console.log` to stdout, so any stdout UI/logger plugin corrupts JSON-RPC. The guarantee is config-only: the `acp-agent` example loads no stdout plugin (no console logger, no `stdio-chat`) and, if logging is wanted, uses a stderr exporter. A defensive process-wide `process.stdout.write`/`console.log` hijack inside `dsh-acp` is explicitly rejected — it lives outside Cordis' effect-scoped, HMR-friendly plugin model, races the connection's own stdout handoff, and fights the logger. A test asserts the example emits only framed JSON-RPC on stdout.
-
-New third-party runtime dependency plus protocol drift: `@agentclientprotocol/sdk` is young (0.25.x, recently renamed) and evolving. Pin the version and isolate churn to the one bridge package. This is not a vendoring-policy violation — [vendoring Cordis as source](../../implemented/process/2026-06-11-vendor-cordis-as-source.md) vendors the framework; genuine third-party deps already live on npm (`@earendil-works/pi-ai`).
-
-Turn-settle and prompt-correlation hazards: honor "queued messages batch into one turn" and "`send()` does not synchronously flip to running" (see `stdio-chat.ts` and the defensive-patterns section of [docs/architecture.md](../../../architecture.md)); gate resolution on an observed running→idle transition and handle the empty-prompt / no-work branch so an RPC can't hang.
-
-Permission-await and disposal hangs: a pending `request_permission` whose connection closes or whose turn aborts must settle exactly once; disposal must reach quiescence — tear each owned agent down through `AgentHandle.dispose()` (which stops the loop and awaits its exit), rather than orphaning awaits on a closed pipe.
-
-The 100% per-file coverage gate (repo policy) makes a branch-heavy protocol bridge real work. Accepted deliberately, surfaced so it isn't a surprise at PR time.
-
-ACP protocol-shape details (exact method names, `session/update` variants, permission option kinds, stop reasons) are taken from the ACP spec and the `@agentclientprotocol/sdk` types; they are not independently verifiable until the dependency is added, so the implementation pins the SDK version and conforms to its types rather than to this RFC's prose where they differ.

docs/rfc/proposed/feature/2026-06-14-acp-multi-session.md

@@ -1,48 +0,0 @@
-# RFC: Multiplex concurrent ACP sessions over one connection
-
-Status: proposed
-
-> **Implementation status:** the multi-session bridge (steps 1, 3, 4) and the bash task-ownership isolation are implemented in `packages/ui/acp` + `packages/bash/tool-bash`. **Per-session *permission* ownership is deferred** — it depends on [the ACP support permission gate](2026-06-14-acp-agent-client-protocol.md) (`TODO(rfc010-permission-gate)`), which is itself deferred; the `agent→sessionId` reverse map the gate will route through is in place. Step 2's per-session disposer scope is now implemented (see [agent lifecycle & ownership seams](../../implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md)): the factory returns a per-agent `AgentHandle` whose `dispose()` stops the loop, awaits quiescence, unregisters the agent, and removes its session, so a bare client disconnect leaves no registered agent or session-store entry. Status stays `proposed` until per-session permission ownership lands.
-
-> **Target-client note:** Zed is the current target ACP client, and its ACP client maintains a `HashMap<SessionId, AcpSession>` plus `pending_sessions` for concurrent `session/load` calls. The competing simplification to return to one live session per connection was rejected after checking that target-client shape; this RFC remains the path for finishing multiplexing and per-session permission ownership. See [the rejected simplification](../../rejected/simplification/2026-06-20-single-session-acp-bridge.md).
-
-## Problem
-
-[ACP support](2026-06-14-acp-agent-client-protocol.md) ships with a single active session per connection: a second `session/new` is rejected. Editors expect to run several conversations over one agent subprocess — a user opens multiple threads, or a client pre-warms sessions. The single-session guard is a deliberate MVP scope cut, not an architectural limit; this RFC lifts it.
-
-This paragraph is historical: the multi-session bridge has landed. The remaining proposed work is per-session permission ownership plus the lifecycle seams now tracked in [agent lifecycle and ownership seams](../../implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md).
-
-## Proposal
-
-The harness core already supports many agents (`AgentRegistry.list()` and `AgentLoop.create` impose no count limit), so multiplexing is a bridge-layer change in `@deepseek-ai/dsh-acp`, not a loop or core change.
-
-- Lift the single-session guard in `session/new`; allow N live sessions, each mapped to its own `ReactLoopAgent`.
-- The bridge's `sessionId→agent` and `Session→sessionId` maps (introduced single-entry by [the ACP support RFC](2026-06-14-acp-agent-client-protocol.md)) become true multi-entry, plus a third `agent→sessionId` reverse map: the `tools/execute` permission gate receives only `exec.agent` (no sessionId), so it needs an O(1) reverse lookup to find the owning session. Every `agent/*` event and every `session/event` is demuxed strictly by id, so two sessions streaming at once never interleave their `session/update` notifications.
-- Per-session prompt queues: [the ACP support RFC](2026-06-14-acp-agent-client-protocol.md)'s single-entry in-flight-prompt state becomes multi-entry — one in-flight prompt *per session*, tracked per `sessionId`.
-- Per-session cancel routing: `session/cancel` cancels only its own session's agent (via the queue-aware `agent.cancel()`) and settles only that session's in-flight prompt. The cancel is scoped to that one agent — a per-agent `AbortController` for the running step plus the agent's own queued/steering FIFOs — so it never touches another session's stream or pending prompt.
-- Per-session permission ownership: a `session/request_permission` and its outcome are bound to the originating session via the reverse map, so a permission prompt or a cancel in one session can never resolve another session's pending permission.
-
-## Plan
-
-1. Generalize the two id maps to multi-entry and add the `agent→sessionId` reverse map; add a per-session record holding the agent, the in-flight-prompt state, the pending-permission registry, and the session's disposer scope (see step 2).
-2. Give each session a real per-session disposer scope, NOT `ctx.extend()` — in Cordis `ctx.extend()` only creates a child context/prototype, but `ctx.on()` registered on it is still owned by the current plugin fiber, so disposing it would not remove that session's listeners. Use a genuine child fiber (load a per-session sub-plugin, e.g. `ctx.plugin(...)` returning a fork, or collect each session's `ctx.on` disposers in its session record and call them on teardown). Demux every `agent/*` and `session/event` by id into the right session record. Note the single global `tools/execute` listener stays on the bridge root (it must see all agents) and routes via the reverse map.
-3. Lift the `session/new` guard; keep `session/load` ([from ACP support](2026-06-14-acp-agent-client-protocol.md)) working per session.
-4. Tests for cross-session isolation: two sessions streaming and permission-prompting concurrently never interleave; a cancel/abort in one session leaves the other's stream and pending permission untouched; per-session in-flight-prompt enforcement holds independently; disposing one session leaves the others running.
-
-## Alternatives considered
-
-**A per-session `ctx.extend()` scope** — rejected: in Cordis, `ctx.extend()` only creates a child context/prototype, and `ctx.on()` registered on it is still owned by the current plugin fiber, so disposing it would not remove that session's listeners. A genuine child fiber (or a per-session collection of disposers) is required.
-
-## Acceptance criteria
-
-- N concurrent sessions stream and permission-prompt without interleaving their `session/update` notifications; a cancel in one session leaves every other session's stream, queued prompts, and pending permissions untouched.
-- Disposing one session removes exactly its own listeners; connection teardown reaches quiescence across all sessions.
-- One session's agent cannot read or kill another session's background bash task.
-
-## Risks
-
-Listener fan-out cost: each session adds listeners; ensure disposal of one session removes exactly its own and the connection teardown ([from ACP support](2026-06-14-acp-agent-client-protocol.md)) still reaches quiescence across all sessions.
-
-The subtle correctness trap is cross-session leakage — a cancel or abort on one session settling another session's pending permission. The per-session permission ownership rule (routed via the `agent→sessionId` reverse map) and its isolation test are the guard.
-
-Shared background-task state: the bash executor's task ids are global and predictable (`bash-1`, `bash-2`, …), and `bash_output`/`bash_kill` look up by id without checking the caller. Under one session this is benign; under N sessions one session's agent could read or kill another's background task. This is a pre-existing `tool-bash` gap that multi-session turns into a real isolation hole — fixing it (validate the caller against the task owner) belongs with this RFC or a companion `tool-bash` change.

docs/rfc/rejected/simplification/2026-06-20-single-session-acp-bridge.md

@@ -4,7 +4,7 @@ Status: rejected — Zed is the current target ACP client and its ACP implementa
 
 ## Problem
 
-The ACP bridge now supports multiple live sessions on one JSON-RPC connection. That capability brings multi-entry session maps, reverse session/agent lookups, per-session prompt state, loading ids, demux for every event, cross-session teardown, and isolation concerns for future permission prompts and background tasks. The older [multi-session ACP proposal](../../proposed/feature/2026-06-14-acp-multi-session.md) still tracks the unfinished permission-ownership piece; this RFC is the competing simplification path.
+The ACP bridge now supports multiple live sessions on one JSON-RPC connection. That capability brings multi-entry session maps, reverse session/agent lookups, per-session prompt state, loading ids, demux for every event, cross-session teardown, and isolation concerns for future permission prompts and background tasks. The older [multi-session ACP proposal](../../implemented/feature/2026-06-14-acp-multi-session.md) still tracks the unfinished permission-ownership piece; this RFC is the competing simplification path.
 
 The product target has proven it needs concurrent editor conversations over one harness process: Zed's ACP connection owns multiple sessions and load states. The snapshot replay tier still avoids concurrent model streams because its replay entries are positional; that is a test-fixture limitation, not a reason to remove bridge multiplexing.
 
@@ -20,7 +20,7 @@ Remove the multi-session maps and demux where a single `SessionRecord | undefine
 - `session/new` and `session/load` reject while that record exists.
 - Event handlers no longer demux across a `Map<sessionId, record>`.
 - Multi-session tests are removed or moved under the proposal that continues to defend multiplexing.
-- The existing [multi-session ACP proposal](../../proposed/feature/2026-06-14-acp-multi-session.md) is updated to link this RFC and remains the live direction.
+- The existing [multi-session ACP proposal](../../implemented/feature/2026-06-14-acp-multi-session.md) is updated to link this RFC and remains the live direction.
 
 ## What we give up
 

docs/testing.md

@@ -1,17 +1,17 @@
 # Testing policy
 
-How this repo tests, tier by tier, and the rules that keep a green suite meaning something. Commands live in the root [AGENTS.md](../AGENTS.md) § Commands; the RFCs linked per tier carry the design rationale.
+How this repo tests, tier by tier, and the rules that keep a green suite meaningful. Commands live in root [AGENTS.md](../AGENTS.md); linked RFCs carry the rationale.
 
 ## Tiers
 
-- **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Excessive tests are welcome — err toward covering edge cases, error paths, event ordering, and concurrency races; review findings get regression tests (see `packages/core/agent-loop/tests/review-fixes.spec.ts`).
+- **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, and concurrency races; review findings get regression tests (see `packages/core/agent-loop/tests/review-fixes.spec.ts`).
 - **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped.
 - **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e RFC](rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md)).
-- **Snapshot** (`pnpm run test:snapshot`): boots the real example subprocess, replays a recorded session keyless, diffs normalized stdout + the re-persisted log against committed goldens ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). Re-record with `pnpm run test:snapshot:record`; reviewing the golden diff is part of the review. System-prompt/tool-schema content is pinned by ONE scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)).
+- **Snapshot** (`pnpm run test:snapshot`): boots the real example subprocess, replays a recorded session keyless, diffs normalized stdout + the re-persisted log against committed goldens ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). Use `pnpm run test:snapshot:record` when the model transcript should change; use `pnpm run test:snapshot:refresh` when the committed transcript is still the right mock LLM input and replay goldens need keyless rewrite. Review the golden diff. System-prompt/tool-schema content is pinned by ONE scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)).
 
 ## The with-key policy: inference is cheap here
 
-We are DeepSeek — do not ration real-API tests. A no-key test proves the plumbing; only a with-key run proves the agent works against a real model. Write many: real prompts that write files, multi-turn conversations, tool use, cancellation mid-stream. Cheapest and highest-value are **smoke tests** that boot the real example, send one real prompt, and check the world — they catch the "green unit tests, broken product" class that mocks structurally cannot ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md)). The self-skip exists only so secretless CI and keyless contributors aren't blocked; it is not a cost signal. Every example ships a keyless smoke and — unless keyless-by-nature — a with-key smoke ([examples/AGENTS.md](../examples/AGENTS.md)).
+We are DeepSeek — do not ration real-API tests. A no-key test proves plumbing; only a with-key run proves the agent works against a real model. Write many: file-writing prompts, multi-turn conversations, tool use, cancellation mid-stream. Highest-value are **smoke tests** that boot the real example, send one real prompt, and check the world — they catch the "green unit tests, broken product" class that mocks structurally cannot ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md)). The self-skip exists only so secretless CI and keyless contributors aren't blocked; it is not a cost signal. Every example ships a keyless smoke and — unless keyless-by-nature — a with-key smoke ([examples/AGENTS.md](../examples/AGENTS.md)).
 
 ## Prefer the real implementation over a mock
 

docs/tool-catalog.md

@@ -20,6 +20,7 @@ This table connects model-visible tool names to the plugin package and service s
 | `@deepseek-ai/dsh-tool-bash` | `bash`, `bash_kill`, `bash_output` | `ctx.tools`, `ctx.bash` | `tool/call`, `tool/result`, `context/message via agent.inject() for background completion notices` | - | The bash/bash_output/bash_kill tools are model-facing consumers of the bash executor seam. |
 | `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `live plugin-tree mutations (mount/unmount)` | - | Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; the request-header ToolsDelta logs those tool-set changes. |
 | `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after successful file operations`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. |
+| `@deepseek-ai/dsh-tool-skill` | `skill` | `ctx.tools`, `ctx.skills` | `tool/call`, `tool/result` | - | - |
 | `@deepseek-ai/dsh-tool-subagent` | `subagent` | `ctx.tools`, `ctx.subagents` | `tool/call`, `tool/result`, `child session events through the chosen provider` | `subagent`, `subagent_fork` | The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/coding-agent/cordis.yml` and `examples/acp-agent/cordis.yml`. |
 | `@deepseek-ai/dsh-tool-todo` | `todo_write` | `ctx.tools`, `owning Agent session` | `tool/call`, `todo/write`, `tool/result` | - | todo_write is session-owned state; UIs render the latest todo/write event as a checklist or ACP plan. |
 | `@deepseek-ai/dsh-tool-workflow` | `workflow` | `ctx.tools`, `ctx.workflows`, `ctx.systemPrompt`, `a calling Agent (exec.agent parents the script children)` | `tool/call`, `tool/result` | - | - |
@@ -124,7 +125,7 @@ Registered by the tool registry itself under `mode: code` / `mode: both` (see th
 
 ### `bash`
 
-Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.
+Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.
 
 ```json
 {
@@ -370,6 +371,29 @@ Source: [`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts
 
 The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin.
 
+## `@deepseek-ai/dsh-tool-skill`
+
+### `skill`
+
+Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "name": {
+      "type": "string",
+      "description": "The exact skill name from the available skills list."
+    }
+  },
+  "required": [
+    "name"
+  ]
+}
+```
+
+Source: [`packages/skill/tool-skill/src/index.ts`](../packages/skill/tool-skill/src/index.ts)
+
 ## `@deepseek-ai/dsh-tool-subagent`
 
 ### `subagent`

docs/tool-execution-pipeline.md

@@ -11,7 +11,8 @@ flowchart TD
   toolCall["Session event: <code>tool/call</code><br/>logged before execution"]
   presentCall["UI pending card<br/>presentCall(args)"]
   pre["<code>tools/pre-execute</code> waterfall<br/>hooks, permission, sandbox"]
-  denied["deny or ask<br/>tool body skipped"]
+  denied["denied<br/>tool body skipped"]
+  approval["<code>ctx.approval</code> one-shot prompt<br/>absent or unanswerable: deny"]
   around["<code>tools/execute</code> waterfall<br/>timeout, retry, metrics (around dispatch)"]
   toolBody["Registered tool execute() body"]
   fsGate["<code>fs/write-intent</code> or <code>fs/edit-intent</code><br/>tool-fs mutations only"]
@@ -25,7 +26,10 @@ flowchart TD
   toolCall --> pre
   pre -->|allow| around
   around --> toolBody
-  pre -->|deny or ask| denied
+  pre -->|deny| denied
+  pre -->|ask| approval
+  approval -->|allowed-once| around
+  approval -->|rejected, cancelled, unavailable| denied
   denied --> post
   toolBody --> fsGate
   fsGate --> toolBody
@@ -37,6 +41,6 @@ flowchart TD
   toolResult --> presentResult
 ```
 
-Filesystem read-before-edit checks live below `tool-fs` on the `fs/*` event gate; hook bridges and future permission prompts live on the generic pre/post tool waterfalls; and around-dispatch concerns like the tool-call timeout policy (`@deepseek-ai/dsh-timeout-policy`) wrap core dispatch on `tools/execute`. That split lets the same hooks observe bash, fs, web, todo, and subagent calls without coupling those tools to one policy service. Code Mode rides the same pipeline twice over: `run_code` is itself a registered tool body, and each tool call its program makes re-enters `ctx.tools.execute()` through BOTH waterfalls — serialized one at a time, logged as a `tool/code-dispatch` session event, with a deny surfacing to the program as a binding rejection (a sub-call's `additionalContext` is deliberately dropped — no safe outlet mid-run preserves call/result adjacency).
+Filesystem read-before-edit checks live below `tool-fs` on the `fs/*` event gate; hook bridges and the approval seam's permission prompts live on the generic pre/post tool waterfalls; and around-dispatch concerns like the tool-call timeout policy (`@deepseek-ai/dsh-timeout-policy`) wrap core dispatch on `tools/execute`. That split lets the same hooks observe bash, fs, web, todo, and subagent calls without coupling those tools to one policy service.
 
 Maintenance mode: curated Mermaid flow; exact tool schemas and event signatures live in generated catalogs.

eslint.config.mjs

@@ -22,6 +22,7 @@ export default tseslint.config(
       '**/lib/**',
       '**/node_modules/**',
       '**/.sessions/**',
+      '.claude/**', // harness-local state (worktrees, skills) — other checkouts, not this one's sources
       '**/.doc-typecheck-*/**',
       'vendor/**', // vendored source keeps upstream style and idioms
       '**/*.js',
@@ -38,7 +39,14 @@ export default tseslint.config(
     ],
     languageOptions: {
       parserOptions: {
-        project: ['./packages/*/*/tsconfig.json', './tsconfig.json'],
+        // One shared tsserver-style project service instead of 60+ standalone
+        // per-package programs: the old `project` glob built every package's
+        // full dependency closure (sibling sources via the dev `paths` map +
+        // the vendored Cordis stack) as its own program and kept them all
+        // resident — ~5 GB peak, an OOM past node's default heap. The service
+        // resolves each file to its nearest owning tsconfig and shares the
+        // graph.
+        projectService: true,
         tsconfigRootDir: import.meta.dirname,
       },
     },
@@ -89,7 +97,9 @@ export default tseslint.config(
     ],
     languageOptions: {
       parserOptions: {
-        project: ['./tsconfig.json'],
+        // Same shared project service as the src block: test files resolve
+        // through the root tsconfig (its include covers every tests/ tree).
+        projectService: true,
         tsconfigRootDir: import.meta.dirname,
       },
     },

examples/AGENTS.md

@@ -2,7 +2,7 @@
 
 Runnable demos showing how the harness is wired. **Examples are NOT workspaces** — each `examples/*/package.json` is a private, dependency-free stub, never built. They are booted as unbuilt `tsx` subprocesses via the cordis Loader reading a `cordis.yml`; the `@deepseek-ai/dsh-*` plugin names in those YAML files resolve through the root `tsconfig.json` `paths` map, not through `node_modules`.
 
-Because examples are not under the `packages/*/src` coverage gate, an example that grows real, reusable *logic* should extract it into a `packages/` package (where it gets the per-file 100% gate and a README). Keep only example-specific glue here: the `cordis.yml` wiring, demo-only mocks/teaching artifacts, and the e2e/snapshot scenarios. There is no `start.ts` — the boot glue (Loader tail, `.env` load, snapshot-mode selection, stdin-dispose lifecycle) lives in each app package's `bin` (`@deepseek-ai/dsh-stdio-agent`, `@deepseek-ai/dsh-acp-agent`), which the `demo:*` scripts invoke against the leaf `cordis.yml`.
+Because examples are not under the `packages/*/src` coverage gate, an example that grows real, reusable *logic* should extract it into a `packages/` package (where it gets the per-file 100% gate and a README). Keep only example-specific glue here: the `cordis.yml` wiring, demo-only mocks/teaching artifacts, and the e2e/snapshot scenarios. There is no `start.ts` — the boot glue lives in each app package's `bin` (`@deepseek-ai/dsh-stdio-agent`, `@deepseek-ai/dsh-acp-agent`), which the `demo:*` scripts invoke against the leaf `cordis.yml`.
 
 ## Every example ships e2e smokes (keyless + with-key)
 
@@ -13,7 +13,7 @@ Each example must have **both** kinds of end-to-end smoke, because they catch di
 
 **Exception — keyless-by-nature examples.** An example whose model is itself a mock/deterministic stand-in (no real provider) has no meaningful with-key smoke; the keyless smoke is the complete requirement. State the exception inline in the test.
 
-A keyless smoke that spawns the example from a temp cwd must set `TSX_TSCONFIG_PATH` to the repo-root tsconfig — the unbuilt `paths` map is found by searching UP from cwd, so a temp cwd outside the repo would otherwise fall back to stale built `lib/`. Pass `--expose-internals` when the example's `cordis.yml` loads the HMR plugin (mirror the `demo:*` script).
+A keyless smoke that spawns the example from a temp cwd must set `TSX_TSCONFIG_PATH` to the repo-root tsconfig (the unbuilt `paths` map is found by searching UP from cwd), and pass `--expose-internals` when the `cordis.yml` loads the HMR plugin (mirror the `demo:*` script).
 
 ## Current state
 
@@ -22,6 +22,7 @@ A keyless smoke that spawns the example from a temp cwd must set `TSX_TSCONFIG_P
 | `echo-agent` | `tests/echo.e2e.ts` — boots the real `cordis.yml`, drives the echo tool round-trip and the direct canned reply | **N/A — keyless by nature** (the `mock-echo` model has no real provider) |
 | `coding-agent` | `tests/keyless-smoke.e2e.ts` — boots the full real tree (dummy key, no prompt → no model call), asserts banner + clean exit; `tests/code-mode-keyless-smoke.e2e.ts` — the same boot guard for the Code Mode overlay | `tests/{full-loop,coding-task,resume,compaction,todo-write}.e2e.ts` — real model + real bash + real todo_write, world-verified; `tests/code-mode.e2e.ts` — a real model composes two bash calls in one `run_code` program; collapsed header, dispatch events, written file all verified |
 | `cordis-agent` | `tests/keyless-smoke.e2e.ts` — boots the real tree incl. `@deepseek-ai/dsh-tool-cordis` by package name; the tool logic is unit-tested in `packages/cordis/tool-cordis` | `tests/cordis-tools.e2e.ts` — real model mounts a listener (tagged line fires), builds+calls its own tool, composes two mounts via provide/inject |
+| `sandbox-acp-agent` | `escalation.e2e.ts` — boots the real tree (sandbox + approval + bridge) keyless: initialize + `session/new` | same file — denied → escalates → a scripted client grants (the write must land) or rejects (it must not); skips without key/runner |
 | `acp-agent` | `pnpm run test:snapshot` — boots the real ACP subprocess and replays a recorded session keyless (incl. the hook matrix: a scenario per hook point × outcome for BOTH the Claude and Codex bridges — block, deny, ask, context-fold, force-continue); `tests/acp.e2e.ts` also asserts stdout purity without a key | `tests/acp.e2e.ts` — real ACP prompt, verifies a file the agent wrote; `tests/hooks.e2e.ts` — a real `PreToolUse` hook blocks bash, verifies the file is NOT written |
 
 See [the root AGENTS.md](../AGENTS.md) for repo-wide conventions and [docs/architecture.md](../docs/architecture.md) for the design.

examples/README.md

@@ -32,3 +32,9 @@ Run with: `pnpm run demo:cordis` (needs `DEEPSEEK_API_KEY`). See [cordis-agent/R
 An agent demo exposed as an **Agent Client Protocol (ACP)** server over JSON-RPC stdio, via the [`@deepseek-ai/dsh-acp-agent`](../packages/ui/acp-agent) app — drive it from Zed or any other ACP client. Also the home of the keyless snapshot tests.
 
 Run with: `pnpm run demo:acp` (needs `DEEPSEEK_API_KEY`); `pnpm run demo:code-mode acp` boots the same server in Code Mode via the `code-mode.cordis.yml` overlay. See [acp-agent/README.md](acp-agent/README.md) for the Zed setup and the snapshot-test design.
+
+## sandbox-acp-agent
+
+The coding agent with its bash executor swapped for the sandbox stack ([`@deepseek-ai/dsh-sandbox-local`](../packages/sandbox/sandbox-local) + [`@deepseek-ai/dsh-bash-sandbox`](../packages/bash/bash-sandbox) — the one-entry executor swap the `ctx.bash` capability seam exists for), served over ACP with [`@deepseek-ai/dsh-user-approval`](../packages/ui/user-approval) mounted — the first composition where the approval loop is LIVE: a sandbox denial escalated by the model becomes a `session/request_permission` prompt in the editor, and "Allow once" runs exactly that command under the wider mode.
+
+Run with: `pnpm run demo:sandbox-acp` (needs `DEEPSEEK_API_KEY`; bwrap, a Landlock-enforcing kernel, or macOS for confined runs). See [sandbox-acp-agent/README.md](sandbox-acp-agent/README.md).

examples/acp-agent/README.md

@@ -33,8 +33,8 @@ The editor sets each session's `cwd` to the project it opens; both the agent's b
 
 ## Snapshot tests (record-once / replay-deterministic)
 
-This example is the home of the harness's **snapshot tests** — they boot this server as a real subprocess, drive it with a deterministic input script, and diff its normalized output against committed golden files. The model is made deterministic by `@deepseek-ai/dsh-llm-replay`, a function/namespace plugin that installs an `llm/stream` waterfall listener and short-circuits it, serving model streams reconstructed from a recorded **session JSONL** fixture (`<scenario>/session.jsonl`) — so replay needs no API key. The fixture IS the persisted session log: its `assistant/chunk` events carry every `StreamChunk`, so grouping them by `(turn, step)` reconstructs each `stream()` call (one model call per loop step). Recording is therefore "run the real agent once and harvest the `.jsonl`". The two failure modes not expressible as logged chunks — a pure throw before any chunk, and cancel/hang — use an optional `<scenario>/replay.override.json` sidecar (a `ReplayEntry[]` that replaces the derived script). A scenario that needs the agent to operate on existing files ships an optional `<scenario>/workspace/` directory — the harness copies its contents into the temp cwd before the run (see `workspace-edit`). See [the ACP snapshot tests RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) for the full design.
+This example is the home of the harness's **snapshot tests** — they boot this server as a real subprocess, drive it with a deterministic input script, and diff its normalized output against committed golden files. The model is made deterministic by `@deepseek-ai/dsh-llm-replay`, a function/namespace plugin that installs an `llm/stream` waterfall listener and short-circuits it, serving model streams reconstructed from a recorded **session JSONL** fixture (`<scenario>/session.jsonl`) — so replay needs no API key. The fixture IS the persisted session log: its `assistant/chunk` events carry every `StreamChunk`, so grouping them by `(turn, step)` reconstructs each `stream()` call (one model call per loop step). Recording is therefore "run the real agent once and harvest the `.jsonl`"; use `pnpm run test:snapshot:record` when the model transcript itself should change, and `pnpm run test:snapshot:refresh` when the committed model transcript is still the right mock input and only the current replay output/goldens need to be rewritten. The two failure modes not expressible as logged chunks — a pure throw before any chunk, and cancel/hang — use an optional `<scenario>/replay.override.json` sidecar (a `ReplayEntry[]` that replaces the derived script). A scenario that needs the agent to operate on existing files ships an optional `<scenario>/workspace/` directory — the harness copies its contents into the temp cwd before the run (see `workspace-edit`). See [the ACP snapshot tests RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) for the full design.
 
 ## MVP limitations
 
-The bridge supports N concurrent sessions per connection, each in its own workspace `cwd` (RFC 011). Remaining limits: prompts support ACP's baseline `text` and `resource_link` blocks only, `additionalDirectories` and `mcpServers` are rejected, and the tool-permission gate is deferred (`TODO(rfc010-permission-gate)` — tools run with the executor's full authority). See `packages/ui/acp/README.md` for the full contract.
+The bridge supports N concurrent sessions per connection, each in its own workspace `cwd` (RFC 011). Remaining limits: prompts support ACP's baseline `text` and `resource_link` blocks only, and `additionalDirectories` and `mcpServers` are rejected. Permission prompts (`session/request_permission`) are wired through the approval seam, but this example composes no ask-producing policy, so tools run with the executor's full authority. See `packages/ui/acp/README.md` for the full contract.

examples/acp-agent/tests/acp.e2e.ts

@@ -63,7 +63,16 @@ function spawnAcpAgent(cwd: string, env: NodeJS.ProcessEnv = process.env): Spawn
   const child = spawn(
     process.execPath,
     ['--import', tsxLoader, binScript, configPath],
-    { cwd, env: { ...env, TSX_TSCONFIG_PATH: repoTsconfig }, stdio: ['pipe', 'pipe', 'pipe'] },
+    {
+      cwd,
+      env: {
+        ...env,
+        TSX_TSCONFIG_PATH: repoTsconfig,
+        DSH_HOME: join(cwd, '.dsh'),
+        DSH_AGENTS_HOME: join(cwd, '.agents'),
+      },
+      stdio: ['pipe', 'pipe', 'pipe'],
+    },
   )
   const stderr: string[] = []
   child.stderr.setEncoding('utf8')
@@ -80,8 +89,9 @@ function spawnAcpAgent(cwd: string, env: NodeJS.ProcessEnv = process.env): Spawn
       return Promise.resolve()
     },
     requestPermission(_params: RequestPermissionRequest): Promise<RequestPermissionResponse> {
-      // Permission gate is deferred (TODO(rfc010-permission-gate)); the bridge
-      // never requests permission yet, so just allow if it ever does.
+      // This example composes no ask-producing policy (no hooks), so the
+      // bridge never prompts here; answer cancelled (fail closed) if it ever
+      // does — an unexpected prompt must not grant anything.
       return Promise.resolve({ outcome: { outcome: 'cancelled' } })
     },
   })
@@ -150,7 +160,13 @@ describe('acp-agent over real stdio (no key required)', () => {
     // which this purity test never triggers). So this runs WITHOUT real creds.
     const child = spawn(process.execPath, ['--import', tsxLoader, binScript, configPath], {
       cwd: workdir,
-      env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', TSX_TSCONFIG_PATH: repoTsconfig },
+      env: {
+        ...process.env,
+        DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot',
+        TSX_TSCONFIG_PATH: repoTsconfig,
+        DSH_HOME: join(workdir, '.dsh'),
+        DSH_AGENTS_HOME: join(workdir, '.agents'),
+      },
       stdio: ['pipe', 'pipe', 'pipe'],
     })
     const out: string[] = []

examples/acp-agent/tests/acp.snapshot.ts

@@ -1,15 +1,16 @@
 import { fileURLToPath } from 'node:url'
 import { dirname, join } from 'node:path'
-import { defineAcpSnapshotSuite, type Scenario } from '@deepseek-ai/dsh-acp-snapshot'
+import { defineAcpSnapshotSuite, type Scenario, type SnapshotSuiteOptions } from '@deepseek-ai/dsh-acp-snapshot'
 
 /**
  * The acp-agent example's snapshot suite: the scenario table for
  * `dsh-acp-snapshot`'s suite factory, which owns every compare/guard mechanic
- * (golden + re-persisted-log diffs, record write-back, the pinned-header
+ * (golden + re-persisted-log diffs, record/refresh write-back, the pinned-header
  * uniformity guard, the fixture guards). Fixtures live under `snapshots/<name>/`;
- * `pnpm run test:snapshot:record` re-records the `recorded` scenarios against
- * the real API. See the package README (packages/support/acp-snapshot) and the
- * snapshot RFC, docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md.
+ * `pnpm run test:snapshot:record` re-records model transcripts against the real
+ * API; `pnpm run test:snapshot:refresh` rewrites current replay goldens keyless.
+ * See the package README (packages/support/acp-snapshot) and the snapshot RFC,
+ * docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md.
  */
 
 // The dsh-acp-agent bin (the demo:acp entry), this example's cordis.yml, and
@@ -26,6 +27,21 @@ const AGENT = {
 const CODE_MODE_CONFIG = fileURLToPath(new URL('../code-mode.cordis.yml', import.meta.url))
 const BOTH_MODE_CONFIG = fileURLToPath(new URL('../both-mode.cordis.yml', import.meta.url))
 
+function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['mode'] {
+  switch (value) {
+    case undefined:
+    case '':
+    case 'replay':
+      return 'replay'
+    case 'record':
+      return 'record'
+    case 'refresh':
+      return 'refresh'
+    default:
+      throw new Error(`unknown DSH_SNAPSHOT mode: ${value}`)
+  }
+}
+
 const SCENARIOS: Scenario[] = [
   { name: 'handshake', hasModelTurn: false, recorded: false },
   { name: 'reject-extra-dirs', hasModelTurn: false, recorded: false },
@@ -36,6 +52,7 @@ const SCENARIOS: Scenario[] = [
   { name: 'tool-call-turn', hasModelTurn: true, recorded: true },
   { name: 'fs-terminal-card', hasModelTurn: true, recorded: true },
   { name: 'todo-plan', hasModelTurn: true, recorded: true },
+  { name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' },
   { name: 'workspace-edit', hasModelTurn: true, recorded: true },
   { name: 'fs-read', hasModelTurn: true, recorded: true },
   { name: 'fs-write', hasModelTurn: true, recorded: true },
@@ -111,5 +128,5 @@ defineAcpSnapshotSuite({
   agent: AGENT,
   snapshotsDir: join(dirname(fileURLToPath(import.meta.url)), 'snapshots'),
   scenarios: SCENARIOS,
-  mode: process.env.DSH_SNAPSHOT === 'record' ? 'record' : 'replay',
+  mode: snapshotModeFromEnv(process.env.DSH_SNAPSHOT),
 })

examples/acp-agent/tests/snapshots/skill-load/input.json

@@ -0,0 +1,7 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    { "op": "prompt", "text": "Load the snapshot-skill skill with the skill tool, then reply DONE." }
+  ]
+}

examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl

@@ -0,0 +1,8 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Load the requested skill."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill snapshot-skill","kind":"read","status":"in_progress","rawInput":"snapshot-skill"}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skill_load","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<skill_content name=\"snapshot-skill\">\n<skill_resources>\nBase directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n</skill_instructions>\n</skill_content>"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The skill is loaded."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}}
+{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}

examples/acp-agent/tests/snapshots/skill-load/workspace/.dsh/skills/snapshot-skill/SKILL.md

@@ -0,0 +1,7 @@
+---
+name: snapshot-skill
+description: Exercise project skill discovery and loading in snapshot tests.
+---
+
+Follow these snapshot-only instructions.
+Resolve referenced resources relative to this skill directory.

examples/coding-agent/tests/keyless-smoke.e2e.ts

@@ -62,6 +62,8 @@ async function bootAndEof(): Promise<{ stdout: string; code: number }> {
           // A dummy key so llm-deepseek's apply() (key-PRESENT check only) boots.
           // No prompt is sent, so the adapter never streams — no network call.
           DEEPSEEK_API_KEY: 'keyless-smoke-no-call',
+          DSH_HOME: join(cwd, '.dsh'),
+          DSH_AGENTS_HOME: join(cwd, '.agents'),
         },
         stdio: ['pipe', 'pipe', 'pipe'],
       },

examples/echo-agent/README.md

@@ -31,4 +31,4 @@ node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples
 
 Type a message and press Enter. "echo <text>" triggers a tool call round-trip (the mock model requests the `echo` tool, which echoes the text uppercased, and the next model step acknowledges it).
 
-The session is persisted under `.sessions/` relative to the directory you launch the demo from. `pnpm run demo:echo` runs from the repo root, so the logs land in `<repo-root>/.sessions/` (a session with no cwd goes in the `_no-cwd/` bucket, one `.jsonl` log per session). Clean up with: `rm -rf .sessions`
+The session is persisted under `.sessions/` relative to the directory you launch the demo from. `pnpm run demo:echo` runs from the repo root, so the logs land in `<repo-root>/.sessions/cwd-<hash>/` (one `.jsonl` log per session). Clean up with: `rm -rf .sessions`

examples/echo-agent/tests/echo.e2e.ts

@@ -63,7 +63,16 @@ async function runEcho(lines: string[]): Promise<{ stdout: string; code: number
       // requires it (mirrors the `demo:echo` script). The whole point is to boot
       // the example EXACTLY as it really runs, through the bin + Loader.
       ['--expose-internals', '--import', tsxLoader, binScript, configPath],
-      { cwd, env: { ...process.env, TSX_TSCONFIG_PATH: repoTsconfig }, stdio: ['pipe', 'pipe', 'pipe'] },
+      {
+        cwd,
+        env: {
+          ...process.env,
+          TSX_TSCONFIG_PATH: repoTsconfig,
+          DSH_HOME: join(cwd, '.dsh'),
+          DSH_AGENTS_HOME: join(cwd, '.agents'),
+        },
+        stdio: ['pipe', 'pipe', 'pipe'],
+      },
     )
     child = proc
     let stdout = ''

examples/sandbox-acp-agent/README.md

@@ -0,0 +1,16 @@
+# sandbox-acp-agent
+
+The coding agent with its bash executor swapped for the sandbox stack ([`@deepseek-ai/dsh-sandbox-local`](../../packages/sandbox/sandbox-local/) + [`@deepseek-ai/dsh-bash-sandbox`](../../packages/bash/bash-sandbox/) — the one-entry executor swap the `ctx.bash` capability seam exists for), served over the **Agent Client Protocol**, plus [`@deepseek-ai/dsh-user-approval`](../../packages/ui/user-approval/) — which makes this the first composition where the approval loop is LIVE end to end: bash runs under `read-only`, a denial comes back as the structured marker, the model retries once with `sandbox_permissions` + `justification`, the ACP bridge's answerer turns that ask into a `session/request_permission` prompt in your editor, and "Allow once" runs exactly that command under the wider mode ([sandbox RFC § Escalation](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)).
+
+```sh
+pnpm run demo:sandbox-acp   # needs DEEPSEEK_API_KEY; drive it from Zed or any ACP client
+```
+
+Zed setup is the same as [acp-agent](../acp-agent/README.md) with this example's command; only the leaf `cordis.yml` differs (the sandbox stack + the approval entry in place of the local bash executor and the extra tool stacks).
+
+- **Every approval is one-shot** (`Allow once` / `Reject` — no `allow_always`: the harness has no grant storage yet), and a dismissed prompt or a rejected ask fails closed with its own error text; so does every ask when no editor is attached to answer.
+- **Two session config options are live** ([sandbox RFC § Per-session mode switching](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)): a capable client shows `Sandbox` (`read-only`/`workspace-write`/`danger-full-access`) and `Approvals` (`ask`/`never`) selectors per session — a switch is one log-only event on that session's log and execution follows it; the sandbox mode is deliberately NOT stated in the prompt or narrated (the model learns the boundary from the denial marker — behavior, not belief), while an approval switch to `never` is stated and narrated; a resumed session reports its overrides back on `session/load`.
+- **The write boundary is config-fixed**: an escalated `workspace-write` run may write under the launch directory (`workspaceRoot: process.cwd()`) plus the platform temp area — a per-session root is config-phase future work in the [sandbox RFC](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md).
+- **No usable runner fails closed per command** (structured `SANDBOX_UNAVAILABLE`), and the filesystem tools stay unloaded for the same reason as `sandbox-agent`: they would bypass the bash sandbox.
+
+Tests: `tests/escalation.e2e.ts` — keyless, it boots the real `cordis.yml` through the Loader as an ACP subprocess, proves the whole tree (sandbox executor + approval service + bridge) initializes and opens a session, and drives the config options end to end (both advertised with composition currents, switches honored and echoed as complete state, out-of-vocabulary values rejected); with a key and a usable runner, a scripted ACP client plays the human — the real model gets denied, escalates, the client answers `allow-once`, and the retried write must land on disk. `tests/acp.snapshot.ts` (the [shared snapshot kit](../../packages/support/acp-snapshot/) over this composition's `cordis.snapshot.yml` replay overlay) pins four scenarios as committed wire bytes: the keyless config-option exchange, the recorded `mode-switching` arc (the suite's pinned header — both switches, their prompt-section deltas, one "changed by the user" notice per knob, and a confined write landing under the switched mode), and both recorded escalation branches (`session/request_permission` answered allow-once / reject-once). Replay re-executes every recorded bash call under the host's real runner — Seatbelt works out of the box on macOS; on Linux install bubblewrap (or build the Landlock launcher) first, exactly what ci.yml's snapshot lane does. No fixture carries a real denial: denial stderr is backend dialect and would pin a fixture to its recording platform (the rationale comment atop the suite file).

examples/sandbox-acp-agent/cordis.snapshot.yml

@@ -0,0 +1,30 @@
+# Snapshot-test REPLAY overlay for the sandboxed composition: the SAME app
+# tree as cordis.yml, derived from it by an include — the one difference is
+# the model backend. A keyless replay run cannot boot the real adapter
+# (llm-deepseek's apply() throws without DEEPSEEK_API_KEY), so the include
+# patches the live tree at load time: the llm-deepseek entry is disabled by
+# id, and the llm-replay entry (which serves a recorded session JSONL — no
+# API key, no network) is inserted. Every other entry — the sandbox provider,
+# the confined bash executor, the approval seam, the app — IS the live tree.
+# The sandbox provider probes for a platform runner per EXECUTION, not at
+# boot, so a protocol-only scenario (session config options) replays on hosts
+# with no runner at all.
+#
+# The dsh-acp-agent bin selects this file for DSH_SNAPSHOT=replay (the
+# sibling-swap of whatever config path it was handed). The replay fixture
+# path comes from $DSH_SNAPSHOT_FILE, set by the snapshot harness. stdout
+# stays reserved for the ACP JSON-RPC protocol.
+- id: base
+  name: '@cordisjs/plugin-include'
+  config:
+    path: ./cordis.yml
+    patches:
+      # The name is an assertion, not an override: the include skips the patch
+      # (warning) when the id points at a different plugin, so this can never
+      # disable the wrong entry.
+      - id: llm-deepseek
+        name: '@deepseek-ai/dsh-llm-deepseek'
+        disabled: true
+      - insert:
+          - id: llm-replay
+            name: '@deepseek-ai/dsh-llm-replay'

examples/sandbox-acp-agent/cordis.yml

@@ -0,0 +1,63 @@
+# The sandbox-acp-agent plugin tree: the sandboxed coding agent served over the
+# Agent Client Protocol, with the approval seam composed — the first LIVE
+# approval composition. A sandbox denial escalated by the model
+# (sandbox_permissions + justification) reaches the EDITOR as a
+# session/request_permission prompt through the ACP bridge's answerer, and an
+# "Allow once" runs exactly that command under the wider mode.
+#
+# CRITICAL: this tree loads NO stdout logger and NO hmr — stdout is reserved
+# for the ACP JSON-RPC protocol (a property of @deepseek-ai/dsh-acp-agent,
+# same as examples/acp-agent).
+#
+# Requires DEEPSEEK_API_KEY (and optionally DEEPSEEK_BASE_URL) — the
+# dsh-acp-agent bin loads the gitignored repo-root .env first (on STDERR only).
+
+# The DeepSeek adapter.
+- id: llm-deepseek
+  name: '@deepseek-ai/dsh-llm-deepseek'
+  config:
+    apiKey: !!js process.env.DEEPSEEK_API_KEY
+    baseURL: !!js process.env.DEEPSEEK_BASE_URL
+    models:
+      - deepseek-v4-flash
+
+# The sandbox stack: the platform-runner provider (bwrap → per-platform
+# Landlock launcher → Seatbelt, functionally probed), then the confined bash executor.
+# read-only is the fail-safe default; the write boundary for an escalated
+# workspace-write run is workspaceRoot + the platform's temp area. NOTE: the
+# workspace root is CONFIG-FIXED for the executor's lifetime (the launch dir
+# here), while each ACP session has its own cwd — a per-session root is config-
+# phase future work in the sandbox RFC.
+- id: sandbox
+  name: '@deepseek-ai/dsh-sandbox-local'
+- id: bash
+  name: '@deepseek-ai/dsh-bash-sandbox'
+  config:
+    mode: read-only
+    workspaceRoot: !!js process.cwd()
+
+# The approval seam (ctx.approval — mechanism only, no config): with it
+# mounted, the bash tool's escalation gate has a channel, and the ACP bridge
+# inside dsh-acp-agent answers for the sessions it owns by prompting the
+# editor. Without an editor attached nothing can answer, and every ask fails
+# closed.
+- id: approval
+  name: '@deepseek-ai/dsh-user-approval'
+
+# The ACP server app: the agent-core spine + JSONL persistence + the ACP
+# bridge (whose approval answerer completes the loop).
+- id: acp-agent
+  name: '@deepseek-ai/dsh-acp-agent'
+  config:
+    model: deepseek-v4-flash
+    # Persistence root: $DSH_SNAPSHOT_SESSIONS_ROOT when the snapshot harness
+    # sets it (so a record run's logs land where the harness harvests them),
+    # else the local ./.sessions default.
+    persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+    persona: |
+      You are a coding assistant powered by the {{model}} model. Your working
+      directory is {{cwd}}. Your bash tool runs under a file sandbox — a
+      `[sandbox: file access denied …]` result is policy, not a command bug.
+
+      Verify your work by running the code or tests. Keep answers brief and
+      factual.

examples/sandbox-acp-agent/package.json

@@ -0,0 +1,7 @@
+{
+  "name": "sandbox-acp-agent-example",
+  "description": "Runnable demo: the sandboxed coding agent as an ACP server, with sandbox-escalation approval prompts answered by the editor",
+  "private": true,
+  "version": "0.0.1",
+  "type": "module"
+}

examples/sandbox-acp-agent/tests/acp.snapshot.ts

@@ -0,0 +1,82 @@
+import { dirname, join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import { defineAcpSnapshotSuite, type Scenario, type SnapshotSuiteOptions } from '@deepseek-ai/dsh-acp-snapshot'
+
+/**
+ * Snapshot suite for the SANDBOXED composition (`../cordis.yml`, swapped to
+ * the sibling `cordis.snapshot.yml` replay overlay by the bin under
+ * `DSH_SNAPSHOT=replay`). Replay swaps only the MODEL for the recorded
+ * transcript — every bash call re-executes for real under the host's actual
+ * runner (Seatbelt on macOS, bwrap on Linux CI: ci.yml's snapshot lane
+ * installs bubblewrap for exactly this), so the recorded scenarios double as
+ * cross-backend confinement regression: an allowed command a runner change
+ * starts denying fails replay outright. Their commands are limited to
+ * `cat`/`printf` shapes whose bytes are identical across those backends and
+ * across GNU/BSD userlands.
+ *
+ * Deliberately ABSENT: a scenario whose transcript carries a real sandbox
+ * DENIAL. The harness-authored `[sandbox: file access denied …]` marker is
+ * byte-stable, but the denied command's own stderr is the backend's dialect
+ * (bwrap EROFS "Read-only file system", Landlock EACCES "Permission
+ * denied", Seatbelt EPERM "Operation not permitted", GNU vs BSD phrasing on
+ * top), and stderr reaches both compared surfaces — such a fixture replays
+ * only on the platform that recorded it. The denial→marker path stays on
+ * dsh-tool-bash's unit tests and the real-kernel sandbox e2e legs
+ * (.github/workflows/sandbox.yml); the escalation scenarios below sidestep
+ * it by having the USER assert the prior denial, so the recorded model
+ * escalates without a platform-variant denial in the log.
+ */
+const SCENARIOS: Scenario[] = [
+  // Protocol-only (keyless, authored): the session config-option surface
+  // this composition adds — both advertised selects on session/new, the
+  // complete refreshed state every session/set_config_option answers with,
+  // and both rejection shapes — as committed wire bytes. No bash runs, so
+  // this one still replays on runner-less hosts.
+  { name: 'config-options', hasModelTurn: false, recorded: false },
+  // The runtime mode-switching arc, and NECESSARILY the pinned-header
+  // scenario: an approval-policy switch rewrites its prompt section, and the
+  // resulting request/header-delta is legal only in the pinning scenario
+  // (the factory's uniformity guard). The pin commits this composition's
+  // full header — persona, tool schemas WITH the escalation fields — plus
+  // the approval delta and its "changed by the user" notice verbatim. The
+  // SANDBOX switch is deliberately silent (no section, no notice — the
+  // sandbox RFC's visibility asymmetry): the recorded arc proves it by
+  // BEHAVIOR, a confined write landing under the switched mode with no
+  // header change.
+  { name: 'mode-switching', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderDeltas: 1 },
+  // The approval wire end-to-end, under the DEFAULT read-only/ask (a switch
+  // would emit a header-delta the uniformity guard forbids here): the
+  // escalating bash call streams, session/request_permission attaches to it
+  // (allow-once / reject-once), and the scripted answer drives each branch —
+  // an approved run executes CONFINED under the granted workspace-write; a
+  // rejected one executes nothing and fails with the deterministic
+  // rejection text.
+  { name: 'escalation-approved', hasModelTurn: true, recorded: true },
+  { name: 'escalation-rejected', hasModelTurn: true, recorded: true },
+]
+
+function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['mode'] {
+  switch (value) {
+    case undefined:
+    case '':
+    case 'replay':
+      return 'replay'
+    case 'record':
+      return 'record'
+    case 'refresh':
+      return 'refresh'
+    default:
+      throw new Error(`unknown DSH_SNAPSHOT mode: ${value}`)
+  }
+}
+
+defineAcpSnapshotSuite({
+  agent: {
+    binScript: fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)),
+    configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)),
+    tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)),
+  },
+  snapshotsDir: join(dirname(fileURLToPath(import.meta.url)), 'snapshots'),
+  scenarios: SCENARIOS,
+  mode: snapshotModeFromEnv(process.env.DSH_SNAPSHOT),
+})

examples/sandbox-acp-agent/tests/escalation.e2e.ts

@@ -0,0 +1,213 @@
+import { spawn, spawnSync, type ChildProcessWithoutNullStreams } from 'node:child_process'
+import { Readable, Writable } from 'node:stream'
+import { mkdtemp, readFile, rm } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import { afterEach, describe, expect, it } from 'vitest'
+import {
+  ClientSideConnection,
+  ndJsonStream,
+  PROTOCOL_VERSION,
+  type Agent as AcpAgent,
+  type Client,
+  type RequestPermissionRequest,
+  type RequestPermissionResponse,
+  type SessionNotification,
+} from '@agentclientprotocol/sdk'
+
+/**
+ * examples/sandbox-acp-agent end to end.
+ *
+ * Keyless smoke: boot the REAL `cordis.yml` through the `dsh-acp-agent` bin as
+ * an ACP subprocess and drive initialize + session/new — the real-Loader-path
+ * guard (postmortem 0001) for THIS tree's export shapes, which now include the
+ * sandbox executor AND the approval service. No prompt is sent, so neither the
+ * model nor a sandbox runner is ever exercised.
+ *
+ * With-key escalation flow (self-skips without DEEPSEEK_API_KEY or a usable
+ * platform runner): a scripted ACP client plays the human. The real model is
+ * denied under `read-only`, escalates with `sandbox_permissions` +
+ * `justification`, the bridge prompts THIS client over
+ * `session/request_permission`, the client answers `allow-once`, and the
+ * retried write must land ON DISK (world-verified). The session cwd is a temp
+ * dir under the platform temp area, which `workspace-write` grants — so either
+ * escalation target the model picks can land the write.
+ */
+
+const binScript = fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url))
+const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
+const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
+// The subprocess runs from a temp cwd OUTSIDE the repo; point tsx at the repo
+// tsconfig so the unbuilt `paths` map resolves (see examples/AGENTS.md).
+const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
+
+// A usable confining runner, probed the same way the executor suites do:
+// bwrap on Linux, Seatbelt's sandbox-exec on macOS. Without one the strict
+// attempt would fail closed (SANDBOX_UNAVAILABLE) instead of producing the
+// denial this flow starts from.
+const hasBwrap = spawnSync('bwrap', ['--ro-bind', '/', '/', '--dev', '/dev', '--proc', '/proc', '--die-with-parent', '--', 'true'], {
+  timeout: 5_000,
+  stdio: 'ignore',
+}).status === 0
+const hasSeatbelt = process.platform === 'darwin' && spawnSync('sandbox-exec', ['-p', '(version 1)(allow default)', 'true'], {
+  timeout: 5_000,
+  stdio: 'ignore',
+}).status === 0
+const hasRunner = hasBwrap || hasSeatbelt
+
+interface Spawned {
+  child: ChildProcessWithoutNullStreams
+  client: ClientSideConnection
+  updates: SessionNotification['update'][]
+  permissionRequests: RequestPermissionRequest[]
+  stderr: string[]
+}
+
+/** Boot the example as an ACP subprocess; the scripted client answers every permission prompt with `answer`. */
+function spawnSandboxAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawned {
+  const child = spawn(
+    process.execPath,
+    ['--import', tsxLoader, binScript, configPath],
+    {
+      cwd,
+      // A dummy key lets the deepseek adapter boot keyless (presence-checked at
+      // apply, used only on a real model call); the with-key tests carry the
+      // real key, so the fallback is inert there.
+      env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', TSX_TSCONFIG_PATH: repoTsconfig },
+      stdio: ['pipe', 'pipe', 'pipe'],
+    },
+  )
+  const stderr: string[] = []
+  child.stderr.setEncoding('utf8')
+  child.stderr.on('data', (chunk: string) => stderr.push(chunk))
+
+  const updates: SessionNotification['update'][] = []
+  const permissionRequests: RequestPermissionRequest[] = []
+  const stream = ndJsonStream(
+    Writable.toWeb(child.stdin) as WritableStream<Uint8Array>,
+    Readable.toWeb(child.stdout) as ReadableStream<Uint8Array>,
+  )
+  const makeClient = (_agent: AcpAgent): Client => ({
+    sessionUpdate(params: SessionNotification): Promise<void> {
+      updates.push(params.update)
+      return Promise.resolve()
+    },
+    requestPermission(params: RequestPermissionRequest): Promise<RequestPermissionResponse> {
+      permissionRequests.push(params)
+      const option = params.options.find(o => o.optionId === answer)
+      // The scripted human: pick the requested option when the prompt offers
+      // it; an unexpected prompt shape cancels (fail closed, never grants).
+      if (option === undefined) return Promise.resolve({ outcome: { outcome: 'cancelled' } })
+      return Promise.resolve({ outcome: { outcome: 'selected', optionId: option.optionId } })
+    },
+  })
+  const client = new ClientSideConnection(makeClient, stream)
+  return { child, client, updates, permissionRequests, stderr }
+}
+
+let spawned: Spawned | undefined
+let workdir: string | undefined
+
+afterEach(async () => {
+  if (spawned !== undefined && spawned.child.exitCode === null) spawned.child.kill('SIGKILL')
+  spawned = undefined
+  if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
+  workdir = undefined
+})
+
+describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () => {
+  it('boots the tree — sandbox executor + approval service + bridge — and opens a session', async () => {
+    workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-smoke-'))
+    spawned = spawnSandboxAcpAgent(workdir, 'reject-once')
+    const { client } = spawned
+    // A dummy key boots the adapter; no prompt is ever sent, so no model call
+    // and no sandbox runner probe happen. This drives the fiber tree the same
+    // way an editor would, which is what catches a broken export/inject shape.
+    const init = await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    expect(init.protocolVersion).toBe(PROTOCOL_VERSION)
+    const { sessionId } = await client.newSession({ cwd: workdir, mcpServers: [] })
+    expect(sessionId.length).toBeGreaterThan(0)
+  }, 30_000)
+
+  it('advertises both session config options and honors a switch end to end (no key, no model)', async () => {
+    workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-config-'))
+    spawned = spawnSandboxAcpAgent(workdir, 'reject-once')
+    const { client } = spawned
+    await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    // This tree composes bash-sandbox (mode: read-only) + approval → both
+    // knobs advertise, currents from composition config.
+    const created = await client.newSession({ cwd: workdir, mcpServers: [] })
+    const advertised = created.configOptions ?? []
+    expect(advertised.map(option => [option.id, 'currentValue' in option ? option.currentValue : undefined]))
+      .toEqual([['sandbox-mode', 'read-only'], ['approval-policy', 'ask']])
+    // A switch responds with the COMPLETE refreshed state (the spec contract),
+    // and the new currents survive in the response of a second switch.
+    const afterSandbox = await client.setSessionConfigOption({
+      sessionId: created.sessionId, configId: 'sandbox-mode', value: 'workspace-write',
+    })
+    const afterApproval = await client.setSessionConfigOption({
+      sessionId: created.sessionId, configId: 'approval-policy', value: 'never',
+    })
+    const currents = (afterApproval.configOptions ?? []).map(option =>
+      [option.id, 'currentValue' in option ? option.currentValue : undefined])
+    expect(afterSandbox.configOptions?.find(option => option.id === 'sandbox-mode'))
+      .toMatchObject({ currentValue: 'workspace-write' })
+    expect(currents).toEqual([['sandbox-mode', 'workspace-write'], ['approval-policy', 'never']])
+    // An out-of-vocabulary value is a protocol error, never a silent default.
+    await expect(client.setSessionConfigOption({
+      sessionId: created.sessionId, configId: 'sandbox-mode', value: 'yolo',
+    })).rejects.toThrow(/unknown sandbox-mode value/)
+  }, 30_000)
+})
+
+describe.skipIf(!process.env.DEEPSEEK_API_KEY || !hasRunner)('sandbox-acp-agent e2e: the live approval loop', () => {
+  it('denial → model escalation → editor prompt → allow-once → the retried write lands on disk', async () => {
+    workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-e2e-'))
+    spawned = spawnSandboxAcpAgent(workdir, 'allow-once')
+    const { client, permissionRequests } = spawned
+
+    await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const { sessionId } = await client.newSession({ cwd: workdir, mcpServers: [] })
+    const res = await client.prompt({
+      sessionId,
+      prompt: [{ type: 'text', text: `Use the bash tool to create the file ${workdir}/escalated.txt containing exactly "ACP_ESCALATION_OK". `
+        + 'If the sandbox denies it, retry once with sandbox_permissions and a one-sentence justification, then stop.' }],
+    })
+    expect(['end_turn', 'max_tokens']).toContain(res.stopReason)
+
+    // The WORLD: the approved escalated retry landed the write read-only denied.
+    const proof = await readFile(join(workdir, 'escalated.txt'), 'utf8')
+    expect(proof).toContain('ACP_ESCALATION_OK')
+
+    // The CHANNEL: the grant came through a real session/request_permission
+    // prompt attached to the escalating tool call, offering exactly the
+    // one-shot options.
+    expect(permissionRequests.length).toBeGreaterThan(0)
+    const prompt = permissionRequests[0]
+    if (prompt === undefined) throw new Error('expected a permission request')
+    expect(prompt.sessionId).toBe(sessionId)
+    expect(typeof prompt.toolCall.toolCallId).toBe('string')
+    expect(prompt.options.map(o => o.optionId).sort()).toEqual(['allow-once', 'reject-once'])
+  }, 240_000)
+
+  it('a rejected escalation stays denied: no write lands, the turn still ends', async () => {
+    workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-e2e-'))
+    spawned = spawnSandboxAcpAgent(workdir, 'reject-once')
+    const { client, permissionRequests } = spawned
+
+    await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const { sessionId } = await client.newSession({ cwd: workdir, mcpServers: [] })
+    const res = await client.prompt({
+      sessionId,
+      prompt: [{ type: 'text', text: `Use the bash tool to create the file ${workdir}/refused.txt containing "NO". `
+        + 'If the sandbox denies it, retry once with sandbox_permissions and a one-sentence justification. If that is rejected, stop and say so.' }],
+    })
+    expect(['end_turn', 'max_tokens']).toContain(res.stopReason)
+
+    // The WORLD: rejected means the file never appeared.
+    await expect(readFile(join(workdir, 'refused.txt'), 'utf8')).rejects.toThrow()
+    // And the rejection really flowed through a prompt (not a missing channel).
+    expect(permissionRequests.length).toBeGreaterThan(0)
+  }, 240_000)
+})

examples/sandbox-acp-agent/tests/snapshots/config-options/input.json

@@ -0,0 +1,10 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    { "op": "setConfigOption", "configId": "sandbox-mode", "value": "workspace-write" },
+    { "op": "setConfigOption", "configId": "approval-policy", "value": "never" },
+    { "op": "setConfigOptionExpectError", "configId": "sandbox-mode", "value": "yolo" },
+    { "op": "setConfigOptionExpectError", "configId": "reasoning-effort", "value": "max" }
+  ]
+}

examples/sandbox-acp-agent/tests/snapshots/config-options/session.jsonl

@@ -0,0 +1 @@
+{"type":"session","version":0,"id":"00000000-0000-0000-0000-000000000000","createdAt":0}

examples/sandbox-acp-agent/tests/snapshots/config-options/stdout.golden.jsonl

@@ -0,0 +1,6 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"read-only","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"ask","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}}
+{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"ask","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}}
+{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"never","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}}
+{"jsonrpc":"2.0","id":5,"error":{"code":-32602,"message":"Invalid params: unknown sandbox-mode value \"yolo\""}}
+{"jsonrpc":"2.0","id":6,"error":{"code":-32602,"message":"Invalid params: unknown config option \"reasoning-effort\""}}

examples/sandbox-acp-agent/tests/snapshots/escalation-approved/input.json

@@ -0,0 +1,10 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    { "op": "prompt", "text": "The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will approve the permission prompt. After the result, reply with the single word DONE and stop." }
+  ],
+  "permissionAnswers": [
+    { "kind": "allow_once" }
+  ]
+}

examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl

@@ -0,0 +1,149 @@
+{"type":"session","version":0,"id":"8f399407-f505-45e5-9058-0994ff7b0865","createdAt":1783486769425,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-xKPr5d"}
+{"type":"turn/start","seq":0,"time":1783486769426,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
+{"type":"user/message","seq":1,"time":1783486769426,"data":{"content":[{"type":"text","text":"The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will approve the permission prompt. After the result, reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
+{"type":"step/start","seq":2,"time":1783486769427,"data":{"turn":1,"step":1}}
+{"type":"request/header","seq":3,"time":1783486769427,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"assistant/chunk","seq":4,"time":1783486770051,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
+{"type":"assistant/chunk","seq":5,"time":1783486770052,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
+{"type":"assistant/chunk","seq":6,"time":1783486770179,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}
+{"type":"assistant/chunk","seq":7,"time":1783486770212,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}}
+{"type":"assistant/chunk","seq":8,"time":1783486770213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}}
+{"type":"assistant/chunk","seq":9,"time":1783486770214,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}}
+{"type":"assistant/chunk","seq":10,"time":1783486770214,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ret"}}}
+{"type":"assistant/chunk","seq":11,"time":1783486770215,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ry"}}}
+{"type":"assistant/chunk","seq":12,"time":1783486770215,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
+{"type":"assistant/chunk","seq":13,"time":1783486770242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}}
+{"type":"assistant/chunk","seq":14,"time":1783486770243,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}}
+{"type":"assistant/chunk","seq":15,"time":1783486770277,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sand"}}}
+{"type":"assistant/chunk","seq":16,"time":1783486770278,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"box"}}}
+{"type":"assistant/chunk","seq":17,"time":1783486770278,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_per"}}}
+{"type":"assistant/chunk","seq":18,"time":1783486770306,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"missions"}}}
+{"type":"assistant/chunk","seq":19,"time":1783486770307,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" set"}}}
+{"type":"assistant/chunk","seq":20,"time":1783486770335,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}}
+{"type":"assistant/chunk","seq":21,"time":1783486770337,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" workspace"}}}
+{"type":"assistant/chunk","seq":22,"time":1783486770338,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"-w"}}}
+{"type":"assistant/chunk","seq":23,"time":1783486770338,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"rite"}}}
+{"type":"assistant/chunk","seq":24,"time":1783486770338,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
+{"type":"assistant/chunk","seq":25,"time":1783486770368,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" They"}}}
+{"type":"assistant/chunk","seq":26,"time":1783486770369,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" explicitly"}}}
+{"type":"assistant/chunk","seq":27,"time":1783486770430,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" said"}}}
+{"type":"assistant/chunk","seq":28,"time":1783486770431,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" they"}}}
+{"type":"assistant/chunk","seq":29,"time":1783486770431,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" will"}}}
+{"type":"assistant/chunk","seq":30,"time":1783486770458,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" approve"}}}
+{"type":"assistant/chunk","seq":31,"time":1783486770459,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
+{"type":"assistant/chunk","seq":32,"time":1783486770459,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" permission"}}}
+{"type":"assistant/chunk","seq":33,"time":1783486770474,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" prompt"}}}
+{"type":"assistant/chunk","seq":34,"time":1783486770474,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
+{"type":"assistant/chunk","seq":35,"time":1783486770475,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}}
+{"type":"assistant/chunk","seq":36,"time":1783486770475,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}}
+{"type":"assistant/chunk","seq":37,"time":1783486770475,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" proceed"}}}
+{"type":"assistant/chunk","seq":38,"time":1783486770518,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
+{"type":"assistant/chunk","seq":39,"time":1783486770606,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":40,"time":1783486770606,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":""}}}
+{"type":"assistant/chunk","seq":41,"time":1783486770606,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"{"}}}
+{"type":"assistant/chunk","seq":42,"time":1783486770606,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":43,"time":1783486770634,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"command"}}}
+{"type":"assistant/chunk","seq":44,"time":1783486770634,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":45,"time":1783486770634,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":": "}}}
+{"type":"assistant/chunk","seq":46,"time":1783486770634,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":47,"time":1783486770682,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"printf"}}}
+{"type":"assistant/chunk","seq":48,"time":1783486770683,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" '"}}}
+{"type":"assistant/chunk","seq":49,"time":1783486770683,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"es"}}}
+{"type":"assistant/chunk","seq":50,"time":1783486770683,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"cal"}}}
+{"type":"assistant/chunk","seq":51,"time":1783486770694,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"ated"}}}
+{"type":"assistant/chunk","seq":52,"time":1783486770694,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\\\\n"}}}
+{"type":"assistant/chunk","seq":53,"time":1783486770694,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"'"}}}
+{"type":"assistant/chunk","seq":54,"time":1783486770695,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" >"}}}
+{"type":"assistant/chunk","seq":55,"time":1783486770697,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" escalated"}}}
+{"type":"assistant/chunk","seq":56,"time":1783486770697,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":".txt"}}}
+{"type":"assistant/chunk","seq":57,"time":1783486770740,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" &&"}}}
+{"type":"assistant/chunk","seq":58,"time":1783486770740,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" cat"}}}
+{"type":"assistant/chunk","seq":59,"time":1783486770740,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" escalated"}}}
+{"type":"assistant/chunk","seq":60,"time":1783486770740,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":".txt"}}}
+{"type":"assistant/chunk","seq":61,"time":1783486770740,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":62,"time":1783486770802,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":", "}}}
+{"type":"assistant/chunk","seq":63,"time":1783486770802,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":64,"time":1783486770802,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"description"}}}
+{"type":"assistant/chunk","seq":65,"time":1783486770802,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":66,"time":1783486770803,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":": "}}}
+{"type":"assistant/chunk","seq":67,"time":1783486770820,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":68,"time":1783486770821,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"Write"}}}
+{"type":"assistant/chunk","seq":69,"time":1783486770821,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" escalated"}}}
+{"type":"assistant/chunk","seq":70,"time":1783486770909,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":".txt"}}}
+{"type":"assistant/chunk","seq":71,"time":1783486770910,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" and"}}}
+{"type":"assistant/chunk","seq":72,"time":1783486770910,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" cat"}}}
+{"type":"assistant/chunk","seq":73,"time":1783486770910,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" its"}}}
+{"type":"assistant/chunk","seq":74,"time":1783486770924,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" content"}}}
+{"type":"assistant/chunk","seq":75,"time":1783486770925,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":76,"time":1783486770953,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":", "}}}
+{"type":"assistant/chunk","seq":77,"time":1783486770953,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":78,"time":1783486770953,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"sand"}}}
+{"type":"assistant/chunk","seq":79,"time":1783486770953,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"box"}}}
+{"type":"assistant/chunk","seq":80,"time":1783486770981,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"_per"}}}
+{"type":"assistant/chunk","seq":81,"time":1783486770983,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"missions"}}}
+{"type":"assistant/chunk","seq":82,"time":1783486770983,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":83,"time":1783486770983,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":": "}}}
+{"type":"assistant/chunk","seq":84,"time":1783486771018,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":85,"time":1783486771018,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"works"}}}
+{"type":"assistant/chunk","seq":86,"time":1783486771018,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"pace"}}}
+{"type":"assistant/chunk","seq":87,"time":1783486771019,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"-w"}}}
+{"type":"assistant/chunk","seq":88,"time":1783486771019,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"rite"}}}
+{"type":"assistant/chunk","seq":89,"time":1783486771050,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":90,"time":1783486771083,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":", "}}}
+{"type":"assistant/chunk","seq":91,"time":1783486771083,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":92,"time":1783486771083,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"just"}}}
+{"type":"assistant/chunk","seq":93,"time":1783486771083,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"ification"}}}
+{"type":"assistant/chunk","seq":94,"time":1783486771083,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":95,"time":1783486771084,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":": "}}}
+{"type":"assistant/chunk","seq":96,"time":1783486771113,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":97,"time":1783486771114,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"the"}}}
+{"type":"assistant/chunk","seq":98,"time":1783486771114,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" user"}}}
+{"type":"assistant/chunk","seq":99,"time":1783486771114,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" asked"}}}
+{"type":"assistant/chunk","seq":100,"time":1783486771142,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" to"}}}
+{"type":"assistant/chunk","seq":101,"time":1783486771142,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" write"}}}
+{"type":"assistant/chunk","seq":102,"time":1783486771142,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" escalated"}}}
+{"type":"assistant/chunk","seq":103,"time":1783486771142,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":".txt"}}}
+{"type":"assistant/chunk","seq":104,"time":1783486771142,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" in"}}}
+{"type":"assistant/chunk","seq":105,"time":1783486771216,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" the"}}}
+{"type":"assistant/chunk","seq":106,"time":1783486771217,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" workspace"}}}
+{"type":"assistant/chunk","seq":107,"time":1783486771217,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":108,"time":1783486771219,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"}"}}}
+{"type":"assistant/chunk","seq":109,"time":1783486771231,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to retry the command with sandbox_permissions set to workspace-write. They explicitly said they will approve the permission prompt. Let me proceed."}}}}
+{"type":"assistant/chunk","seq":110,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}}}}
+{"type":"assistant/chunk","seq":111,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1255,"outputTokens":160,"cacheReadTokens":0,"reasoningTokens":34}}}}
+{"type":"assistant/chunk","seq":112,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":113,"time":1783486771236,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the command with sandbox_permissions set to workspace-write. They explicitly said they will approve the permission prompt. Let me proceed."},{"type":"tool-call","id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"usage":{"inputTokens":1255,"outputTokens":160,"cacheReadTokens":0,"reasoningTokens":34}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"}
+{"type":"tool/call","seq":114,"time":1783486771236,"data":{"turn":1,"step":1,"callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}}
+{"type":"approval/asked","seq":115,"time":1783486771238,"data":{"id":"4766a1b9-6cf5-4504-a6cc-97037b478964","toolName":"bash","callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}}
+{"type":"approval/decided","seq":116,"time":1783486771243,"data":{"id":"4766a1b9-6cf5-4504-a6cc-97037b478964","outcome":"allowed-once"}}
+{"type":"tool/result","seq":117,"time":1783486771442,"data":{"turn":1,"step":1,"callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[114],"surfaceOp":"append"}
+{"type":"step/end","seq":118,"time":1783486771443,"data":{"turn":1,"step":1}}
+{"type":"step/start","seq":119,"time":1783486771443,"data":{"turn":1,"step":2}}
+{"type":"assistant/chunk","seq":120,"time":1783486771965,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
+{"type":"assistant/chunk","seq":121,"time":1783486771965,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
+{"type":"assistant/chunk","seq":122,"time":1783486772052,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}}
+{"type":"assistant/chunk","seq":123,"time":1783486772113,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" succeeded"}}}
+{"type":"assistant/chunk","seq":124,"time":1783486772113,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
+{"type":"assistant/chunk","seq":125,"time":1783486772113,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" The"}}}
+{"type":"assistant/chunk","seq":126,"time":1783486772114,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}
+{"type":"assistant/chunk","seq":127,"time":1783486772115,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}}
+{"type":"assistant/chunk","seq":128,"time":1783486772115,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}}
+{"type":"assistant/chunk","seq":129,"time":1783486772141,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}}
+{"type":"assistant/chunk","seq":130,"time":1783486772142,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}}
+{"type":"assistant/chunk","seq":131,"time":1783486772142,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}}
+{"type":"assistant/chunk","seq":132,"time":1783486772185,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
+{"type":"assistant/chunk","seq":133,"time":1783486772186,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}}
+{"type":"assistant/chunk","seq":134,"time":1783486772186,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}}
+{"type":"assistant/chunk","seq":135,"time":1783486772186,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" D"}}}
+{"type":"assistant/chunk","seq":136,"time":1783486772204,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}}
+{"type":"assistant/chunk","seq":137,"time":1783486772205,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
+{"type":"assistant/chunk","seq":138,"time":1783486772205,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":139,"time":1783486772205,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}}
+{"type":"assistant/chunk","seq":140,"time":1783486772205,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}}
+{"type":"assistant/chunk","seq":141,"time":1783486772228,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The command succeeded. The user asked me to reply with the single word DONE."}}}}
+{"type":"assistant/chunk","seq":142,"time":1783486772229,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
+{"type":"assistant/chunk","seq":143,"time":1783486772229,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":23,"outputTokens":20,"cacheReadTokens":1408,"reasoningTokens":17}}}}
+{"type":"assistant/chunk","seq":144,"time":1783486772229,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"type":"assistant/message","seq":145,"time":1783486772230,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command succeeded. The user asked me to reply with the single word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":23,"outputTokens":20,"cacheReadTokens":1408,"reasoningTokens":17}},"sourceEventSeqs":[120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144],"surfaceOp":"append"}
+{"type":"step/end","seq":146,"time":1783486772230,"data":{"turn":1,"step":2}}
+{"type":"turn/end","seq":147,"time":1783486772230,"data":{"turn":1,"reason":{"kind":"completed"}}}

examples/sandbox-acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl

@@ -0,0 +1,59 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"read-only","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"ask","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ret"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ry"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sand"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"box"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_per"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"missions"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" set"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" workspace"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"-w"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"rite"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" They"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" explicitly"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" said"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" they"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" will"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" approve"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" permission"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" prompt"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" proceed"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","title":"printf 'escalated\\n' > escalated.txt && cat escalated.txt","kind":"execute","status":"in_progress","rawInput":"printf 'escalated\\n' > escalated.txt && cat escalated.txt","content":[{"type":"content","content":{"type":"text","text":"Write escalated.txt and cat its content"}}]}}}
+{"jsonrpc":"2.0","id":1,"method":"session/request_permission","params":{"sessionId":"{{sessionId}}","toolCall":{"toolCallId":"call_00_ZSEIrZNdgQhL2QJgVHww8689"},"options":[{"optionId":"allow-once","name":"Allow once","kind":"allow_once"},{"optionId":"reject-once","name":"Reject","kind":"reject_once"}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","status":"completed","content":[{"type":"content","content":{"type":"text","text":"```console\nescalated\n```"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" succeeded"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" single"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" D"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}}
+{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}

examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/input.json

@@ -0,0 +1,10 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    { "op": "prompt", "text": "The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will reject the permission prompt; after the rejection, do not retry and do not work around it — explain in one short sentence that the escalation was rejected, then stop." }
+  ],
+  "permissionAnswers": [
+    { "kind": "reject_once" }
+  ]
+}

examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl

@@ -0,0 +1,202 @@
+{"type":"session","version":0,"id":"46ee90bb-006b-477c-9c56-04dd4923aeb6","createdAt":1783486772550,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-OivXMN"}
+{"type":"turn/start","seq":0,"time":1783486772551,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
+{"type":"user/message","seq":1,"time":1783486772551,"data":{"content":[{"type":"text","text":"The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will reject the permission prompt; after the rejection, do not retry and do not work around it — explain in one short sentence that the escalation was rejected, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
+{"type":"step/start","seq":2,"time":1783486772552,"data":{"turn":1,"step":1}}
+{"type":"request/header","seq":3,"time":1783486772552,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"assistant/chunk","seq":4,"time":1783486773136,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
+{"type":"assistant/chunk","seq":5,"time":1783486773136,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
+{"type":"assistant/chunk","seq":6,"time":1783486773275,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}
+{"type":"assistant/chunk","seq":7,"time":1783486773326,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}}
+{"type":"assistant/chunk","seq":8,"time":1783486773328,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}}
+{"type":"assistant/chunk","seq":9,"time":1783486773328,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}}
+{"type":"assistant/chunk","seq":10,"time":1783486773328,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ret"}}}
+{"type":"assistant/chunk","seq":11,"time":1783486773347,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ry"}}}
+{"type":"assistant/chunk","seq":12,"time":1783486773348,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
+{"type":"assistant/chunk","seq":13,"time":1783486773349,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exact"}}}
+{"type":"assistant/chunk","seq":14,"time":1783486773381,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}}
+{"type":"assistant/chunk","seq":15,"time":1783486773382,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}}
+{"type":"assistant/chunk","seq":16,"time":1783486773412,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"printf"}}}
+{"type":"assistant/chunk","seq":17,"time":1783486773413,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" '"}}}
+{"type":"assistant/chunk","seq":18,"time":1783486773413,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"es"}}}
+{"type":"assistant/chunk","seq":19,"time":1783486773413,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"cal"}}}
+{"type":"assistant/chunk","seq":20,"time":1783486773414,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ated"}}}
+{"type":"assistant/chunk","seq":21,"time":1783486773414,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\\n"}}}
+{"type":"assistant/chunk","seq":22,"time":1783486773445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"'"}}}
+{"type":"assistant/chunk","seq":23,"time":1783486773446,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" >"}}}
+{"type":"assistant/chunk","seq":24,"time":1783486773446,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" escalated"}}}
+{"type":"assistant/chunk","seq":25,"time":1783486773446,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".txt"}}}
+{"type":"assistant/chunk","seq":26,"time":1783486773446,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" &&"}}}
+{"type":"assistant/chunk","seq":27,"time":1783486773447,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cat"}}}
+{"type":"assistant/chunk","seq":28,"time":1783486773473,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" escalated"}}}
+{"type":"assistant/chunk","seq":29,"time":1783486773473,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".txt"}}}
+{"type":"assistant/chunk","seq":30,"time":1783486773473,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`"}}}
+{"type":"assistant/chunk","seq":31,"time":1783486773473,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}}
+{"type":"assistant/chunk","seq":32,"time":1783486773474,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}}
+{"type":"assistant/chunk","seq":33,"time":1783486773500,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"sand"}}}
+{"type":"assistant/chunk","seq":34,"time":1783486773501,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"box"}}}
+{"type":"assistant/chunk","seq":35,"time":1783486773501,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_per"}}}
+{"type":"assistant/chunk","seq":36,"time":1783486773501,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"missions"}}}
+{"type":"assistant/chunk","seq":37,"time":1783486773501,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`"}}}
+{"type":"assistant/chunk","seq":38,"time":1783486773542,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" set"}}}
+{"type":"assistant/chunk","seq":39,"time":1783486773543,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}}
+{"type":"assistant/chunk","seq":40,"time":1783486773543,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}}
+{"type":"assistant/chunk","seq":41,"time":1783486773543,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"works"}}}
+{"type":"assistant/chunk","seq":42,"time":1783486773543,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"pace"}}}
+{"type":"assistant/chunk","seq":43,"time":1783486773543,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"-w"}}}
+{"type":"assistant/chunk","seq":44,"time":1783486773568,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"rite"}}}
+{"type":"assistant/chunk","seq":45,"time":1783486773569,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`"}}}
+{"type":"assistant/chunk","seq":46,"time":1783486773569,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}}
+{"type":"assistant/chunk","seq":47,"time":1783486773569,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
+{"type":"assistant/chunk","seq":48,"time":1783486773597,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" justification"}}}
+{"type":"assistant/chunk","seq":49,"time":1783486773632,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" they"}}}
+{"type":"assistant/chunk","seq":50,"time":1783486773667,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specified"}}}
+{"type":"assistant/chunk","seq":51,"time":1783486773668,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
+{"type":"assistant/chunk","seq":52,"time":1783486773669,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" They"}}}
+{"type":"assistant/chunk","seq":53,"time":1783486773685,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" explicitly"}}}
+{"type":"assistant/chunk","seq":54,"time":1783486773716,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" say"}}}
+{"type":"assistant/chunk","seq":55,"time":1783486773731,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" they"}}}
+{"type":"assistant/chunk","seq":56,"time":1783486773732,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" will"}}}
+{"type":"assistant/chunk","seq":57,"time":1783486773732,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reject"}}}
+{"type":"assistant/chunk","seq":58,"time":1783486773746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
+{"type":"assistant/chunk","seq":59,"time":1783486773746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" permission"}}}
+{"type":"assistant/chunk","seq":60,"time":1783486773747,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" prompt"}}}
+{"type":"assistant/chunk","seq":61,"time":1783486773773,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}}
+{"type":"assistant/chunk","seq":62,"time":1783486773773,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" so"}}}
+{"type":"assistant/chunk","seq":63,"time":1783486773774,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" after"}}}
+{"type":"assistant/chunk","seq":64,"time":1783486773774,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" rejection"}}}
+{"type":"assistant/chunk","seq":65,"time":1783486773806,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}}
+{"type":"assistant/chunk","seq":66,"time":1783486773807,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" should"}}}
+{"type":"assistant/chunk","seq":67,"time":1783486773833,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" explain"}}}
+{"type":"assistant/chunk","seq":68,"time":1783486773834,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" in"}}}
+{"type":"assistant/chunk","seq":69,"time":1783486773861,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" one"}}}
+{"type":"assistant/chunk","seq":70,"time":1783486773862,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" short"}}}
+{"type":"assistant/chunk","seq":71,"time":1783486773862,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sentence"}}}
+{"type":"assistant/chunk","seq":72,"time":1783486773862,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}}
+{"type":"assistant/chunk","seq":73,"time":1783486773862,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}}
+{"type":"assistant/chunk","seq":74,"time":1783486773900,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
+{"type":"assistant/chunk","seq":75,"time":1783486773978,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":76,"time":1783486773979,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":""}}}
+{"type":"assistant/chunk","seq":77,"time":1783486774009,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"{"}}}
+{"type":"assistant/chunk","seq":78,"time":1783486774011,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":79,"time":1783486774012,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"command"}}}
+{"type":"assistant/chunk","seq":80,"time":1783486774012,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":81,"time":1783486774012,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":": "}}}
+{"type":"assistant/chunk","seq":82,"time":1783486774049,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":83,"time":1783486774050,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"printf"}}}
+{"type":"assistant/chunk","seq":84,"time":1783486774051,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" '"}}}
+{"type":"assistant/chunk","seq":85,"time":1783486774051,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"es"}}}
+{"type":"assistant/chunk","seq":86,"time":1783486774068,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"cal"}}}
+{"type":"assistant/chunk","seq":87,"time":1783486774068,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"ated"}}}
+{"type":"assistant/chunk","seq":88,"time":1783486774069,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\\\\n"}}}
+{"type":"assistant/chunk","seq":89,"time":1783486774069,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"'"}}}
+{"type":"assistant/chunk","seq":90,"time":1783486774069,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" >"}}}
+{"type":"assistant/chunk","seq":91,"time":1783486774069,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" escalated"}}}
+{"type":"assistant/chunk","seq":92,"time":1783486774107,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":".txt"}}}
+{"type":"assistant/chunk","seq":93,"time":1783486774108,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" &&"}}}
+{"type":"assistant/chunk","seq":94,"time":1783486774108,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" cat"}}}
+{"type":"assistant/chunk","seq":95,"time":1783486774108,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" escalated"}}}
+{"type":"assistant/chunk","seq":96,"time":1783486774108,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":".txt"}}}
+{"type":"assistant/chunk","seq":97,"time":1783486774138,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":98,"time":1783486774162,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":", "}}}
+{"type":"assistant/chunk","seq":99,"time":1783486774162,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":100,"time":1783486774162,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"description"}}}
+{"type":"assistant/chunk","seq":101,"time":1783486774162,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":102,"time":1783486774163,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":": "}}}
+{"type":"assistant/chunk","seq":103,"time":1783486774194,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":104,"time":1783486774194,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"Write"}}}
+{"type":"assistant/chunk","seq":105,"time":1783486774194,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" escalated"}}}
+{"type":"assistant/chunk","seq":106,"time":1783486774194,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":".txt"}}}
+{"type":"assistant/chunk","seq":107,"time":1783486774194,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" with"}}}
+{"type":"assistant/chunk","seq":108,"time":1783486774221,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" workspace"}}}
+{"type":"assistant/chunk","seq":109,"time":1783486774221,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"-w"}}}
+{"type":"assistant/chunk","seq":110,"time":1783486774283,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"rite"}}}
+{"type":"assistant/chunk","seq":111,"time":1783486774283,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" permission"}}}
+{"type":"assistant/chunk","seq":112,"time":1783486774283,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":113,"time":1783486774283,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":", "}}}
+{"type":"assistant/chunk","seq":114,"time":1783486774283,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":115,"time":1783486774283,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"sand"}}}
+{"type":"assistant/chunk","seq":116,"time":1783486774303,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"box"}}}
+{"type":"assistant/chunk","seq":117,"time":1783486774303,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"_per"}}}
+{"type":"assistant/chunk","seq":118,"time":1783486774303,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"missions"}}}
+{"type":"assistant/chunk","seq":119,"time":1783486774304,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":120,"time":1783486774304,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":": "}}}
+{"type":"assistant/chunk","seq":121,"time":1783486774339,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":122,"time":1783486774339,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"works"}}}
+{"type":"assistant/chunk","seq":123,"time":1783486774339,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"pace"}}}
+{"type":"assistant/chunk","seq":124,"time":1783486774339,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"-w"}}}
+{"type":"assistant/chunk","seq":125,"time":1783486774339,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"rite"}}}
+{"type":"assistant/chunk","seq":126,"time":1783486774368,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":127,"time":1783486774392,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":", "}}}
+{"type":"assistant/chunk","seq":128,"time":1783486774395,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":129,"time":1783486774395,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"just"}}}
+{"type":"assistant/chunk","seq":130,"time":1783486774395,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"ification"}}}
+{"type":"assistant/chunk","seq":131,"time":1783486774395,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":132,"time":1783486774440,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":": "}}}
+{"type":"assistant/chunk","seq":133,"time":1783486774441,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":134,"time":1783486774441,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"the"}}}
+{"type":"assistant/chunk","seq":135,"time":1783486774441,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" user"}}}
+{"type":"assistant/chunk","seq":136,"time":1783486774469,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" asked"}}}
+{"type":"assistant/chunk","seq":137,"time":1783486774469,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" to"}}}
+{"type":"assistant/chunk","seq":138,"time":1783486774469,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" write"}}}
+{"type":"assistant/chunk","seq":139,"time":1783486774469,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" escalated"}}}
+{"type":"assistant/chunk","seq":140,"time":1783486774469,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":".txt"}}}
+{"type":"assistant/chunk","seq":141,"time":1783486774470,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" in"}}}
+{"type":"assistant/chunk","seq":142,"time":1783486774480,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" the"}}}
+{"type":"assistant/chunk","seq":143,"time":1783486774480,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" workspace"}}}
+{"type":"assistant/chunk","seq":144,"time":1783486774481,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}}
+{"type":"assistant/chunk","seq":145,"time":1783486774510,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"}"}}}
+{"type":"assistant/chunk","seq":146,"time":1783486774568,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to retry the exact command `printf 'escalated\\n' > escalated.txt && cat escalated.txt` with `sandbox_permissions` set to `workspace-write` and the justification they specified. They explicitly say they will reject the permission prompt, so after rejection I should explain in one short sentence and stop."}}}}
+{"type":"assistant/chunk","seq":147,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}}}}
+{"type":"assistant/chunk","seq":148,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1269,"outputTokens":197,"cacheReadTokens":0,"reasoningTokens":70}}}}
+{"type":"assistant/chunk","seq":149,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":150,"time":1783486774572,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the exact command `printf 'escalated\\n' > escalated.txt && cat escalated.txt` with `sandbox_permissions` set to `workspace-write` and the justification they specified. They explicitly say they will reject the permission prompt, so after rejection I should explain in one short sentence and stop."},{"type":"tool-call","id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"usage":{"inputTokens":1269,"outputTokens":197,"cacheReadTokens":0,"reasoningTokens":70}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"}
+{"type":"tool/call","seq":151,"time":1783486774572,"data":{"turn":1,"step":1,"callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}}
+{"type":"approval/asked","seq":152,"time":1783486774574,"data":{"id":"774d5e97-a3af-4fc9-ae83-25dc2617909b","toolName":"bash","callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}}
+{"type":"approval/decided","seq":153,"time":1783486774578,"data":{"id":"774d5e97-a3af-4fc9-ae83-25dc2617909b","outcome":"rejected"}}
+{"type":"tool/result","seq":154,"time":1783486774579,"data":{"turn":1,"step":1,"callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"workspace-write\""}],"isError":true},"sourceEventSeqs":[151],"surfaceOp":"append"}
+{"type":"step/end","seq":155,"time":1783486774579,"data":{"turn":1,"step":1}}
+{"type":"step/start","seq":156,"time":1783486774580,"data":{"turn":1,"step":2}}
+{"type":"assistant/chunk","seq":157,"time":1783486775719,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
+{"type":"assistant/chunk","seq":158,"time":1783486775719,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
+{"type":"assistant/chunk","seq":159,"time":1783486775820,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}
+{"type":"assistant/chunk","seq":160,"time":1783486775856,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}}
+{"type":"assistant/chunk","seq":161,"time":1783486775857,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}}
+{"type":"assistant/chunk","seq":162,"time":1783486775857,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" escalation"}}}
+{"type":"assistant/chunk","seq":163,"time":1783486775857,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
+{"type":"assistant/chunk","seq":164,"time":1783486775879,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}}
+{"type":"assistant/chunk","seq":165,"time":1783486775879,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}}
+{"type":"assistant/chunk","seq":166,"time":1783486775921,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}}
+{"type":"assistant/chunk","seq":167,"time":1783486775922,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" explain"}}}
+{"type":"assistant/chunk","seq":168,"time":1783486775922,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" in"}}}
+{"type":"assistant/chunk","seq":169,"time":1783486775934,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" one"}}}
+{"type":"assistant/chunk","seq":170,"time":1783486775934,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" short"}}}
+{"type":"assistant/chunk","seq":171,"time":1783486775935,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sentence"}}}
+{"type":"assistant/chunk","seq":172,"time":1783486775935,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}}
+{"type":"assistant/chunk","seq":173,"time":1783486775935,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}}
+{"type":"assistant/chunk","seq":174,"time":1783486775935,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
+{"type":"assistant/chunk","seq":175,"time":1783486775977,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":176,"time":1783486775978,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"The"}}}
+{"type":"assistant/chunk","seq":177,"time":1783486775978,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" escalation"}}}
+{"type":"assistant/chunk","seq":178,"time":1783486775978,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" request"}}}
+{"type":"assistant/chunk","seq":179,"time":1783486776011,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" to"}}}
+{"type":"assistant/chunk","seq":180,"time":1783486776026,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" write"}}}
+{"type":"assistant/chunk","seq":181,"time":1783486776027,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" to"}}}
+{"type":"assistant/chunk","seq":182,"time":1783486776027,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}}
+{"type":"assistant/chunk","seq":183,"time":1783486776057,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" workspace"}}}
+{"type":"assistant/chunk","seq":184,"time":1783486776057,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" was"}}}
+{"type":"assistant/chunk","seq":185,"time":1783486776057,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" rejected"}}}
+{"type":"assistant/chunk","seq":186,"time":1783486776058,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":","}}}
+{"type":"assistant/chunk","seq":187,"time":1783486776128,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" so"}}}
+{"type":"assistant/chunk","seq":188,"time":1783486776128,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}}
+{"type":"assistant/chunk","seq":189,"time":1783486776129,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" command"}}}
+{"type":"assistant/chunk","seq":190,"time":1783486776129,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" was"}}}
+{"type":"assistant/chunk","seq":191,"time":1783486776145,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" not"}}}
+{"type":"assistant/chunk","seq":192,"time":1783486776146,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" executed"}}}
+{"type":"assistant/chunk","seq":193,"time":1783486776184,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"."}}}
+{"type":"assistant/chunk","seq":194,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user rejected the escalation. I need to explain in one short sentence and stop."}}}}
+{"type":"assistant/chunk","seq":195,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The escalation request to write to the workspace was rejected, so the command was not executed."}}}}
+{"type":"assistant/chunk","seq":196,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":341,"outputTokens":36,"cacheReadTokens":1152,"reasoningTokens":17}}}}
+{"type":"assistant/chunk","seq":197,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"type":"assistant/message","seq":198,"time":1783486776186,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user rejected the escalation. I need to explain in one short sentence and stop."},{"type":"text","text":"The escalation request to write to the workspace was rejected, so the command was not executed."}],"usage":{"inputTokens":341,"outputTokens":36,"cacheReadTokens":1152,"reasoningTokens":17}},"sourceEventSeqs":[157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197],"surfaceOp":"append"}
+{"type":"step/end","seq":199,"time":1783486776186,"data":{"turn":1,"step":2}}
+{"type":"turn/end","seq":200,"time":1783486776186,"data":{"turn":1,"reason":{"kind":"completed"}}}

examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl

@@ -0,0 +1,111 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"read-only","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"ask","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ret"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ry"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exact"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"printf"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" '"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"es"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"cal"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ated"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\\n"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" >"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" escalated"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".txt"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" &&"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" cat"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" escalated"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".txt"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"sand"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"box"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_per"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"missions"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" set"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"works"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"pace"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"-w"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"rite"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" justification"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" they"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" specified"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" They"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" explicitly"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" say"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" they"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" will"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reject"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" permission"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" prompt"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" so"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" after"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" rejection"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" explain"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" in"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" one"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" short"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sentence"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" stop"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_ODln9LCQtuvTw4FDZEfe3479","title":"printf 'escalated\\n' > escalated.txt && cat escalated.txt","kind":"execute","status":"in_progress","rawInput":"printf 'escalated\\n' > escalated.txt && cat escalated.txt","content":[{"type":"content","content":{"type":"text","text":"Write escalated.txt with workspace-write permission"}}]}}}
+{"jsonrpc":"2.0","id":1,"method":"session/request_permission","params":{"sessionId":"{{sessionId}}","toolCall":{"toolCallId":"call_00_ODln9LCQtuvTw4FDZEfe3479"},"options":[{"optionId":"allow-once","name":"Allow once","kind":"allow_once"},{"optionId":"reject-once","name":"Reject","kind":"reject_once"}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_ODln9LCQtuvTw4FDZEfe3479","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: the user rejected escalating this command to \"workspace-write\"\n```"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" rejected"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" escalation"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" explain"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" in"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" one"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" short"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sentence"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" stop"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"The"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" escalation"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" request"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" to"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" write"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" to"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" workspace"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" was"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" rejected"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":","}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" so"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" command"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" was"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" not"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" executed"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}

examples/sandbox-acp-agent/tests/snapshots/mode-switching/input.json

@@ -0,0 +1,11 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    { "op": "prompt", "text": "Use the bash tool to run exactly: cat notes.txt. Then reply with the single word DONE and stop." },
+    { "op": "setConfigOption", "configId": "sandbox-mode", "value": "workspace-write" },
+    { "op": "prompt", "text": "Use the bash tool to run exactly this one command in a single call: printf 'switched\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop." },
+    { "op": "setConfigOption", "configId": "approval-policy", "value": "never" },
+    { "op": "prompt", "text": "Without using any tools, state your current approval policy in one short sentence and stop." }
+  ]
+}

examples/sandbox-acp-agent/tests/snapshots/mode-switching/stdout.golden.jsonl

@@ -0,0 +1,134 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"read-only","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"ask","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"cat"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" notes"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".txt"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" using"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" bash"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_I9sT0gKlfz9YP4dlf2pA3899","title":"cat notes.txt","kind":"execute","status":"in_progress","rawInput":"cat notes.txt","content":[{"type":"content","content":{"type":"text","text":"Show contents of notes.txt"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_I9sT0gKlfz9YP4dlf2pA3899","status":"completed","content":[{"type":"content","content":{"type":"text","text":"```console\nhello from the sandboxed workspace\n```"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ran"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" successfully"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" single"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" D"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}}
+{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
+{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"ask","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" specific"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" execute"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" it"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_htXcbtvwTFK0NqfclLWL7784","title":"printf 'switched\\n' > out.txt && cat out.txt","kind":"execute","status":"in_progress","rawInput":"printf 'switched\\n' > out.txt && cat out.txt","content":[{"type":"content","content":{"type":"text","text":"Write and read out.txt"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_htXcbtvwTFK0NqfclLWL7784","status":"completed","content":[{"type":"content","content":{"type":"text","text":"```console\nswitched\n```"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Command"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" executed"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" successfully"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" is"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"sw"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"itched"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}}
+{"jsonrpc":"2.0","id":5,"result":{"stopReason":"end_turn"}}
+{"jsonrpc":"2.0","id":6,"result":{"configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"never","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" state"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" my"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" current"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" approval"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" policy"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" without"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" using"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" any"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tools"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" From"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" context"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" approval"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" policy"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" is"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"never"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" —"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" meaning"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" actions"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" that"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" require"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" approval"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" are"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" rejected"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" automatically"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" not"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" request"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sand"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"box"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" escalation"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"Appro"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"vals"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" are"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" never"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" asked"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":";"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" any"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" action"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" requiring"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" approval"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" is"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" automatically"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" rejected"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"."}}}}
+{"jsonrpc":"2.0","id":7,"result":{"stopReason":"end_turn"}}

examples/sandbox-acp-agent/tests/snapshots/mode-switching/workspace/notes.txt

@@ -0,0 +1 @@
+hello from the sandboxed workspace

knip.json

@@ -1,6 +1,7 @@
 {
   "$schema": "https://unpkg.com/knip@5/schema.json",
   "exclude": ["duplicates"],
+  "ignoreBinaries": ["bwrap", "sandbox-exec"],
   "ignoreWorkspaces": ["vendor/*"],
   "workspaces": {
     ".": {
@@ -18,6 +19,14 @@
       "entry": ["tests/**/*.spec.ts"],
       "project": ["src/**/*.ts", "tests/**/*.ts"]
     },
+    "packages/bash/bash-sandbox": {
+      "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"],
+      "project": ["src/**/*.ts", "tests/**/*.ts"]
+    },
+    "packages/sandbox/sandbox-local": {
+      "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"],
+      "project": ["src/**/*.ts", "tests/**/*.ts"]
+    },
     "packages/util/brand": {
       "project": ["src/**/*.ts"],
       "ignoreDependencies": ["cordis"]

package.json

@@ -22,6 +22,7 @@
     "test:e2e": "vitest run --config vitest.e2e.config.ts",
     "test:snapshot": "vitest run --config vitest.snapshot.config.ts",
     "test:snapshot:record": "DSH_SNAPSHOT=record vitest run --config vitest.snapshot.config.ts --update",
+    "test:snapshot:refresh": "DSH_SNAPSHOT=refresh vitest run --config vitest.snapshot.config.ts",
     "check:ci": "tsx scripts/run-gates.ts ci-primary",
     "check:ci:static": "tsx scripts/run-gates.ts ci-static",
     "check:ci:lint": "tsx scripts/run-gates.ts ci-lint",
@@ -68,6 +69,7 @@
     "demo:code-mode": "node scripts/demo-code-mode.mjs",
     "demo:cordis": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/cordis-agent/cordis.yml",
     "demo:acp": "node --import tsx packages/ui/acp-agent/src/bin.ts examples/acp-agent/cordis.yml",
+    "demo:sandbox-acp": "node --import tsx packages/ui/acp-agent/src/bin.ts examples/sandbox-acp-agent/cordis.yml",
     "postinstall": "node scripts/install-lefthook.mjs"
   },
   "devDependencies": {

packages/README.md

@@ -1,10 +1,10 @@
 # Packages
 
-Harness packages, all under the `@deepseek-ai/dsh-*` scope. Each package is a Cordis plugin (microkernel-style): it exports either a default `Service` subclass or a functional plugin, declares its ctx key/events through declaration merging, and exposes extension points through `ctx.effect()`, `ctx.on()`, and `ctx.waterfall()`. Authoring conventions: [AGENTS.md](AGENTS.md) (subtree) and the root [AGENTS.md](../AGENTS.md) § Conventions.
+Harness packages use the `@deepseek-ai/dsh-*` scope. Each is a Cordis plugin: a default `Service` subclass or functional plugin declaring ctx keys/events through declaration merging and contributing through `ctx.effect()`, `ctx.on()`, or `ctx.waterfall()`. Authoring conventions: [AGENTS.md](AGENTS.md) and root [AGENTS.md](../AGENTS.md) § Conventions.
 
 ## Hierarchy
 
-Packages are grouped by modular role at `packages/<group>/<pkg>/`. The group directory is a pure container (no `package.json` of its own); the package name stays `@deepseek-ai/dsh-<pkg>` regardless of group. **Each group README is the canonical per-package map** — package roles, ctx keys, and the product-vs-support split live there, next to the code.
+Packages are grouped by modular role at `packages/<group>/<pkg>/`. The group directory is a pure container (no `package.json`); the package name stays `@deepseek-ai/dsh-<pkg>` regardless of group. **Each group README is the canonical per-package map** — package roles, ctx keys, and the product-vs-support split live there, next to the code.
 
 | Group | Role | Release expectation |
 |---|---|---|
@@ -12,7 +12,9 @@ Packages are grouped by modular role at `packages/<group>/<pkg>/`. The group dir
 | [`llm/`](llm/README.md) | LLM capability family: the abstract service + provider adapters | Product — stable surface |
 | [`bash/`](bash/README.md) | Bash capability family: the executor seam, a local impl, and the model-facing tool | Product — stable surface |
 | [`code-runtime/`](code-runtime/README.md) | Code-execution capability family: the abstract runtime seam for model-written programs + a worker-thread backend | Product — stable surface |
+| [`sandbox/`](sandbox/README.md) | Process-confinement seam; bwrap/Landlock/Seatbelt backends | Product — stable surface |
 | [`fs/`](fs/README.md) | Filesystem capability family: the abstract seam, a local impl, and the model-facing file tools | Product — stable surface |
+| [`skill/`](skill/README.md) | Skill capability family: the provider registry, local provider, and model-facing catalog/loader | Product — stable surface |
 | [`compact/`](compact/README.md) | Compaction capability family: the abstract seam + a basic backend (tool deferred) | Product — stable surface |
 | [`subagent/`](subagent/README.md) | Subagent capability family: the provider-registry seam and the model-facing delegation tool | Product — stable surface |
 | [`workflow/`](workflow/README.md) | Workflow capability family: the script-engine seam, the worker-thread engine, and the model-facing `workflow` tool | Product — stable surface |
@@ -23,7 +25,7 @@ Packages are grouped by modular role at `packages/<group>/<pkg>/`. The group dir
 | [`cordis/`](cordis/README.md) | Self-referential runtime toolset: inspect the live runtime's plugins and services, mount/unmount model-written plugins ([design](../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)) | Product — stable surface |
 | [`hooks/`](hooks/README.md) | Hook bridges + the shared Claude Code / Codex wire-protocol library | Product — stable surface |
 | [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface |
-| [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, app packages, user-interaction seam, ask-user tool | Product — stable surface |
+| [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, app packages, user-approval and user-interaction seams, ask-user tool | Product — stable surface |
 | [`support/`](support/README.md) | Dev/test/example infrastructure (invariants, replay adapter, subagent mock) | Support — lower compatibility expectations |
 | [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (the `Branded<B>` primitive) | Support — small, stable, harness-dep-free |
 

packages/bash/README.md

@@ -1,11 +1,12 @@
 # bash/ — bash capability family
 
-The canonical three-package capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract executor interface, a concrete local implementation, and the model-facing tool that consumes it. All **product** packages.
+The canonical three-package capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract executor interface, concrete implementations, and the model-facing tool that consumes it. All **product** packages.
 
 | Package | Role | ctx key |
 |---|---|---|
-| `bash/` | Abstract bash executor seam (interface + vocabulary) | `ctx.bash` |
+| `bash/` | Abstract bash executor seam (interface + vocabulary; sandbox result facts carry the [`sandbox/`](../sandbox/README.md) seam's mode/enforcement vocabulary) | `ctx.bash` |
 | `bash-local/` | Local-subprocess `BashExecutor` implementation | (registers `ctx.bash`) |
+| `bash-sandbox/` | Sandbox-consuming `BashExecutor` (wraps every command argv via `ctx.sandbox`, stamps denial/enforcement facts; extends `bash-local`'s mechanics) | (registers `ctx.bash`) |
 | `tool-bash/` | Model-facing `bash`/`bash_output`/`bash_kill` tool schemas | (registers on `ctx.tools`) |
 
-The interface lives at `bash/bash/`. A sandboxed executor would replace `bash-local` without touching the interface or the tool — the split is what makes that possible.
+The interface lives at `bash/bash/`. `bash-sandbox` replacing `bash-local` without touching the interface or the tool is the split doing exactly what it exists for — a leaf `cordis.yml` picks one executor entry, plus a `ctx.sandbox` provider entry for the confined one (see [examples/sandbox-acp-agent](../../examples/sandbox-acp-agent/)).

packages/bash/bash-local/README.md

@@ -27,4 +27,4 @@ Design surveyed against the bash tools of Claude Code, OpenCode, Codex, and pi;
 
 ## Sandboxing
 
-`TODO(permissions/sandbox)`: execution policy does NOT belong in this package. Use the `tools/pre-execute` deny/ask gate or implement a sandboxing `BashExecutor` — see docs/architecture.md § Extending The Harness. Reference points: Claude Code wraps commands in sandbox-exec/bubblewrap; Codex applies seatbelt/landlock plus an execpolicy prefix-rule engine.
+Execution policy does NOT belong in this package: this executor always runs commands unconfined. Confinement is [`dsh-bash-sandbox`](../bash-sandbox/README.md), which extends this executor verbatim and confines commands under the `ctx.sandbox` seam's bwrap/Landlock/Seatbelt backends ([sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)); per-call allow/deny/ask policy belongs on the `tools/pre-execute` gate.

packages/bash/bash-local/src/index.ts

@@ -133,6 +133,10 @@ export class LocalBashExecutor extends BashExecutor {
       // Carry the owner through verbatim (required-but-nullable on the spec):
       // the executor never interprets it — the consumer's access policy does.
       owner: request.owner,
+      // Carry a sandbox-mode override through verbatim: this executor never
+      // confines, so the field is inert here (the seam contract) — a
+      // sandboxing subclass overrides resolve() to stamp its default instead.
+      sandboxMode: request.sandboxMode,
     }
   }
 
@@ -212,6 +216,18 @@ export class LocalBashExecutor extends BashExecutor {
     return this.tasks.get(id)
   }
 
+  /**
+   * Full collected stderr of a tracked task from stream start (bounded by the
+   * in-memory cap; bytes only in the spill file are not re-read). A protected
+   * seam for subclasses that classify a settled task's outcome — reading here
+   * does NOT advance the consumer's {@link readOutput} cursor. An unknown id
+   * (a task already dropped by disposal) reads as empty.
+   */
+  protected collectedStderr(id: BashTaskId): string {
+    const task = this.tasks.get(id)
+    return task === undefined ? '' : task.running.stderr.readFrom(0).text
+  }
+
   ownerOf(id: BashTaskId): OwnerToken | undefined {
     // Unknown id and known-but-ownerless both read as undefined — the consumer
     // treats undefined as "open" and a truly unknown id fails at readOutput/kill.

packages/bash/bash-sandbox/README.md

@@ -0,0 +1,33 @@
+# @deepseek-ai/dsh-bash-sandbox
+
+Sandbox-consuming implementation of the [`@deepseek-ai/dsh-bash`](../bash/) executor seam. Load it **instead of** `@deepseek-ai/dsh-bash-local`, together with a [`ctx.sandbox`](../../sandbox/sandbox/) provider (e.g. [`@deepseek-ai/dsh-sandbox-local`](../../sandbox/sandbox-local/)) — the model-facing tool layer (`dsh-tool-bash`) is untouched; that swap is exactly what the seams exist for.
+
+Every command is confined by handing the provider the exact `['bash', '-c', command]` argv this executor is about to spawn and spawning the returned (wrapped) argv instead. WHICH platform runner confines it — and whether one is usable at all (fail closed with a structured `SANDBOX_UNAVAILABLE` error, never a silent unconfined run) — is the provider's concern; this package owns the bash side only.
+
+| Mode | File effects |
+|---|---|
+| `read-only` (default) | No writes anywhere (of `/dev`, only the `/dev/null` node is writable, so `>/dev/null` keeps working) |
+| `workspace-write` | Writes only under `workspaceRoot` + `/tmp` (ephemeral under bwrap, the host `/tmp` under Landlock, `/private/tmp` plus the per-user temp dir under Seatbelt) |
+| `danger-full-access` | No confinement; the provider is never consulted. Execution is `dsh-bash-local`'s verbatim — foreground results still carry `sandbox: { mode, denied: false }` (no `enforcement`: nothing was confined), background tasks carry no sandbox facts |
+
+Semantics:
+
+- **Denials are result facts.** A failed run whose stderr carries the selected backend's own denial dialect — the signatures the provider stamps on every wrap (EROFS text under bwrap, EACCES under Landlock, EPERM under Seatbelt) — is reported as `BashRunResult.sandbox.denied: true` (conservative classification, read from the collected stderr tail); every CONFINED run also carries the mode it executed under (`result.sandbox.mode`) and the provider's enforcement completeness (`result.sandbox.enforcement`: `full`, or `partial` on an older Landlock ABI).
+- **Runner failures are sandbox failures, never task failures.** A failed run matching the wrap's `runnerFailureSignatures` (the runner's own error prefix — also what the shell prints for a missing runner) means the sandbox itself broke and the command NEVER RAN; the check outranks denial classification because a runner's error text can contain denial words. The foreground path re-throws it as the structured fail-closed `SANDBOX_UNAVAILABLE` error, with the runner's first stderr line as the cause; a settled background task stamps `task.sandbox.runnerFailed` instead (no error channel remains after settle), which `bash_output` renders as its own marker.
+- **Config-time default, per-call policy.** The DEFAULT mode is fixed by this entry's config for the executor's lifetime; `resolve()` stamps it onto every spec, and an explicit request-level `sandboxMode` override — set by the tool layer only for a call whose wider mode a human granted through `ctx.approval` ([the sandbox RFC § Escalation](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)) — makes THAT call run, classify, and report under its own mode while every neighbor keeps the default (background facts are stamped per task at settle). The capability fact `ctx.bash.sandboxMode` reports the configured default so the tool layer advertises escalation only when this executor is mounted. The model learns of the sandbox only through result facts — the static bash tool description explains the denial marker; there is no current-mode statement in the system prompt.
+- **File effects only.** Network and process visibility are deliberately not restricted — the mode vocabulary does not pretend to cover what the backend does not enforce.
+- Process mechanics (spawn, process-group kills, output collection/spill, background tasks, credential scrub) are inherited verbatim from [`dsh-bash-local`](../bash-local/); the runner ladder, probes, and the per-platform Landlock launcher packages live with [`dsh-sandbox-local`](../../sandbox/sandbox-local/).
+
+Deny-only at the seam: a denial is a reported fact, and this executor never negotiates permissions itself — the approval question lives in the tool layer (`dsh-tool-bash`), which drives the override this package honors.
+
+```yaml
+- id: sandbox
+  name: '@deepseek-ai/dsh-sandbox-local'
+- id: bash
+  name: '@deepseek-ai/dsh-bash-sandbox'
+  config:
+    mode: read-only
+    workspaceRoot: !!js process.cwd()
+```
+
+The keyless consumer-integration proofs are `tests/bwrap.e2e.ts`, `tests/landlock.e2e.ts`, and `tests/seatbelt.e2e.ts` (the real provider + real runner driven through `ctx.bash`, world-verified, each self-skipping where its runner is absent); see [`examples/sandbox-acp-agent`](../../../examples/sandbox-acp-agent/) for the runnable demo.

packages/bash/bash-sandbox/package.json

@@ -0,0 +1,41 @@
+{
+  "name": "@deepseek-ai/dsh-bash-sandbox",
+  "description": "Sandbox-consuming implementation of the DeepSeek Harness bash executor seam (confines every command via ctx.sandbox, reports denial/enforcement result facts)",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "peerDependencies": {
+    "@deepseek-ai/dsh-bash": "^0.0.1",
+    "@deepseek-ai/dsh-bash-local": "^0.0.1",
+    "@deepseek-ai/dsh-sandbox": "^0.0.1",
+    "cordis": "^4.0.0-rc.6"
+  },
+  "dependencies": {
+    "schemastery": "^3.18.0"
+  },
+  "devDependencies": {
+    "@deepseek-ai/dsh-bash": "workspace:^",
+    "@deepseek-ai/dsh-bash-local": "workspace:^",
+    "@deepseek-ai/dsh-sandbox": "workspace:^",
+    "@deepseek-ai/dsh-sandbox-local": "workspace:^",
+    "node-addon-landlock-run": "0.0.0-test.0",
+    "cordis": "^4.0.0-rc.6"
+  }
+}

packages/bash/bash-sandbox/src/index.ts

@@ -0,0 +1,302 @@
+/**
+ * `SandboxBashExecutor`: the sandbox-consuming implementation of the
+ * `@deepseek-ai/dsh-bash` executor seam. Every spawned command is wrapped by
+ * the `ctx.sandbox` provider (`@deepseek-ai/dsh-sandbox`) according to the
+ * configured {@link SandboxMode}: the executor hands the provider the exact
+ * `['bash', '-c', command]` argv it is about to spawn and spawns the wrapped
+ * argv instead. WHICH platform runner confines it — and whether one is
+ * usable at all (the provider fails CLOSED with a structured
+ * `SANDBOX_UNAVAILABLE` error rather than passing the argv through) — is the
+ * provider's concern (`@deepseek-ai/dsh-sandbox-local` first).
+ *
+ * Extends `LocalBashExecutor` so all process mechanics — spawn, process-group
+ * kills, timeout escalation, output collection and spill files, background
+ * tasks, the credential scrub — are the local implementation's, verbatim.
+ * This package adds only the seam consumption and the result facts, which is
+ * exactly the split the capability seam was designed for (a sandboxing
+ * executor replaces `dsh-bash-local` without touching `dsh-tool-bash`, and
+ * swapping the confinement backend never touches this package).
+ *
+ * A failed run whose stderr carries the selected backend's own denial
+ * dialect (the signatures the provider stamps on every wrap) is classified
+ * as a sandbox denial on `BashRunResult.sandbox`, and every confined result
+ * also carries how completely the selected runner enforces the mode
+ * (`sandbox.enforcement`, from the provider's wrap). A failure carrying the
+ * backend's RUNNER-FAILURE signature instead means the sandbox itself broke
+ * and the command never ran: the foreground path re-throws it as the
+ * structured fail-closed `SANDBOX_UNAVAILABLE` error (late twin of the
+ * provider's confine-time throw), a settled background task stamps
+ * `sandbox.runnerFailed` — either way a broken sandbox can never read as a
+ * failing command, and the command never slips through unconfined.
+ *
+ * Deny-only at the seam, escalation at the tool: a denial is a reported FACT
+ * here, and the one-shot user-approved escalated retry of a denied action
+ * (docs/rfc/implemented/feature/2026-07-06-sandbox.md) is driven by
+ * `dsh-tool-bash` through `ctx.approval` — this executor's contribution is the
+ * per-call `sandboxMode` override it honors in {@link resolve}: an escalated
+ * call runs (and classifies, and reports) under ITS granted mode while every
+ * neighboring call keeps its session's standing mode (or the configured
+ * default when that session has no override).
+ *
+ * @module @deepseek-ai/dsh-bash-sandbox
+ */
+
+import { resolve } from 'node:path'
+import { Context } from 'cordis'
+import z from 'schemastery'
+import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskId } from '@deepseek-ai/dsh-bash'
+import { SandboxUnavailableError } from '@deepseek-ai/dsh-sandbox'
+import type { ConfinedSandboxMode, SandboxEnforcement, SandboxMode } from '@deepseek-ai/dsh-sandbox'
+import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
+import type { Config as LocalConfig } from '@deepseek-ai/dsh-bash-local'
+
+/**
+ * Plugin config: the local executor's knobs plus the sandbox policy. All
+ * optional — `static Config` supplies the defaults (`mode: 'read-only'` is the
+ * fail-safe default; an example that wants a workspace-writable agent opts in
+ * explicitly). The runner choice is NOT configured here: which platform
+ * backend confines the command is the `ctx.sandbox` provider's config.
+ */
+export interface Config extends LocalConfig {
+  /** File-sandbox mode commands run under (default: `read-only`). */
+  mode?: SandboxMode
+  /**
+   * Root directory `workspace-write` mode may write under (default: the
+   * executor's default working directory — `cwd`, else `process.cwd()`).
+   */
+  workspaceRoot?: string
+}
+
+/**
+ * Quote one string as a single-quoted POSIX shell word (embedded single
+ * quotes become `'\''`), so a wrapped argv element survives the outer
+ * `bash -c` re-parse byte-for-byte.
+ * @param text - the raw argv element to quote.
+ * @returns the single-quoted shell word.
+ */
+export function shellQuote(text: string): string {
+  return `'${text.replaceAll("'", String.raw`'\''`)}'`
+}
+
+/**
+ * Conservative sandbox-denial classifier: a run counts as denied only when it
+ * FAILED (nonzero exit — a signal kill is not a denial) and its stderr
+ * carries one of the SELECTED BACKEND's own denial signatures — the dialect
+ * the provider stamps on every wrap (`ConfinedArgv.denialSignatures`:
+ * `Read-only file system` under bwrap's EROFS mounts, `Permission denied`
+ * under Landlock's EACCES, `Operation not permitted` under Seatbelt's
+ * EPERM). Matching the backend's dialect rather than a cross-backend union
+ * keeps the classifier from claiming denials the active backend never
+ * produces (bare EPERM text under a Linux runner names non-file boundaries —
+ * mount, kill, ptrace — that fail the same way unsandboxed). Text inference
+ * is the fallback signal until a runner provides a structured one (which
+ * wins once it exists); it errs toward NOT claiming a denial, and its known
+ * residual imprecision is non-sandbox text in the active dialect (an ssh
+ * auth failure reads as a denial under Landlock, a refused `kill` under
+ * Seatbelt).
+ * @param result - the settled foreground run to classify.
+ * @param signatures - the active wrap's denial dialect, case-insensitive
+ *   stderr substrings.
+ * @returns whether the run's failure reads as a sandbox denial.
+ */
+export function classifyDenial(result: BashRunResult, signatures: readonly string[]): boolean {
+  return matchesSignature(result.exitCode, result.stderr.text, signatures)
+}
+
+/**
+ * Runner-failure classifier: a failed run whose stderr carries the SELECTED
+ * BACKEND's own runner-failure signature (`ConfinedArgv.
+ * runnerFailureSignatures`: the runner's error prefix, which also matches
+ * the shell's runner-not-found message) means the SANDBOX itself failed and
+ * the command never ran. Checked BEFORE {@link classifyDenial} — a runner's
+ * error text can contain denial words (an unopenable grant root reports
+ * `Permission denied`) — and surfaced as the fail-closed
+ * `SANDBOX_UNAVAILABLE` error on the foreground path, `sandbox.runnerFailed`
+ * on a settled background task. Same conservative-text-inference stance and
+ * residual imprecision as the denial classifier (a failing task that itself
+ * prints the runner's prefix reads as a runner failure).
+ * @param result - the settled foreground run to classify.
+ * @param signatures - the active wrap's runner-failure signatures,
+ *   case-insensitive stderr substrings.
+ * @returns whether the run's failure reads as the runner itself failing.
+ */
+export function classifyRunnerFailure(result: BashRunResult, signatures: readonly string[]): boolean {
+  return matchesSignature(result.exitCode, result.stderr.text, signatures)
+}
+
+/**
+ * The classifier core shared by foreground results and settled background
+ * tasks: failed AND signature present. Lowercases BOTH sides — the seam
+ * declares its signatures case-insensitive, and producers compose them from
+ * runtime data of any case (an `argv0` path, `No such file or directory`).
+ */
+function matchesSignature(exitCode: number | null, stderr: string, signatures: readonly string[]): boolean {
+  if (exitCode === null || exitCode === 0) return false
+  const lowered = stderr.toLowerCase()
+  return signatures.some(signature => lowered.includes(signature.toLowerCase()))
+}
+
+/**
+ * Sandbox-consuming bash executor. Registers as `ctx.bash` (loading it
+ * INSTEAD OF `dsh-bash-local`, together with a `ctx.sandbox` provider, is
+ * the whole swap — the tool layer is untouched). Its configured mode is the
+ * fallback exposed by {@link sandboxMode}; `dsh-tool-bash` folds a session's
+ * durable `bash/sandbox-mode` override and stamps the effective mode onto each
+ * request, while an approved escalation may stamp a strictly wider mode for
+ * one call. The tool's per-agent prompt section states that same effective
+ * mode, and each run's `result.sandbox` reports what actually executed plus
+ * enforcement completeness.
+ */
+export class SandboxBashExecutor extends LocalBashExecutor {
+  static inject = ['sandbox']
+
+  // The sandbox-specific fields intersect the local executor's Config as an
+  // inline schema call: the config catalog walks `static Config` statically.
+  static override Config: z<Config> = z.intersect([
+    LocalBashExecutor.Config,
+    z.object({
+      mode: z.union(['read-only', 'workspace-write', 'danger-full-access'] as const).default('read-only'),
+      workspaceRoot: z.string(),
+    }),
+  ])
+
+  private readonly mode: SandboxMode
+  private readonly workspaceRoot: string
+  /**
+   * Per-task facts, keyed by task id from `start()` until the settle stamp
+   * consumes them: the mode the task runs under (per-call — an escalated task
+   * differs from its neighbors) plus its wrap facts. The seam returns facts
+   * PER WRAP — a provider may legally vary enforcement or dialect between
+   * calls — so overlapping background tasks must each classify against their
+   * OWN wrap; a single latest-wrap field would let a later `start()` clobber
+   * an earlier task's facts before it settles. A `danger-full-access` task
+   * has NO entry (nothing confined it), which is what the settle stamp keys
+   * off.
+   */
+  private readonly taskFacts = new Map<BashTaskId, {
+    mode: ConfinedSandboxMode
+    enforcement: SandboxEnforcement
+    denialSignatures: readonly string[]
+    runnerFailureSignatures: readonly string[]
+  }>()
+
+  constructor(ctx: Context, config: Config) {
+    super(ctx, config)
+    // schemastery (static Config) already filled the defaulted fields — the
+    // cast records that runtime fact (mirrors LocalBashExecutor's config
+    // cast). `workspaceRoot` and `cwd` have NO schema default, so their
+    // fallback chain is real branching.
+    this.mode = config.mode as SandboxMode
+    this.workspaceRoot = resolve(config.workspaceRoot ?? config.cwd ?? process.cwd())
+  }
+
+  /** The configured default mode — the capability fact the tool layer reads. */
+  override get sandboxMode(): SandboxMode {
+    return this.mode
+  }
+
+  /**
+   * Stamp the effective mode onto the spec — the request's explicit override
+   * (an approved escalation), else this executor's configured default — so
+   * defaulting stays an explicit resolve step and `run()`/`start()` read the
+   * spec, never the config.
+   */
+  override resolve(request: BashExecRequest): BashExecSpec {
+    return { ...super.resolve(request), sandboxMode: request.sandboxMode ?? this.mode }
+  }
+
+  override async run(spec: BashExecSpec): Promise<BashRunResult> {
+    // resolve() always stamps the mode; the cast records that invariant
+    // (mirrors the constructor's config casts).
+    const mode = spec.sandboxMode as SandboxMode
+    if (mode === 'danger-full-access') {
+      const result = await super.run(spec)
+      return { ...result, sandbox: { mode, denied: false } }
+    }
+    const confined = this.confine(spec.command, mode)
+    const result = await super.run({ ...spec, command: confined.command })
+    // Runner failure outranks denial: the sandbox itself failed and the
+    // command NEVER RAN — surface the same structured fail-closed error a
+    // confine-time discovery throws (late detection, same outcome), with
+    // the runner's own first stderr line as the cause. Returning it as a
+    // task result would let a broken sandbox read as a failing command.
+    if (classifyRunnerFailure(result, confined.runnerFailureSignatures)) {
+      throw new SandboxUnavailableError(mode, result.stderr.text.trim().split('\n')[0])
+    }
+    return { ...result, sandbox: { mode, denied: classifyDenial(result, confined.denialSignatures), enforcement: confined.enforcement } }
+  }
+
+  override start(spec: BashExecSpec): BashTask {
+    // Same stamped-by-resolve invariant as run().
+    const mode = spec.sandboxMode as SandboxMode
+    if (mode === 'danger-full-access') return super.start(spec)
+    // Sandbox facts are stamped at settle time by {@link notifyTaskDone}
+    // (denial classification runs against the settled task's collected
+    // stderr). The map entry lands synchronously after spawn, strictly
+    // before the earliest possible settle (a process exit reaches us no
+    // sooner than the next tick).
+    const confined = this.confine(spec.command, mode)
+    const task = super.start({ ...spec, command: confined.command })
+    const { enforcement, denialSignatures, runnerFailureSignatures } = confined
+    this.taskFacts.set(task.id, { mode, enforcement, denialSignatures, runnerFailureSignatures })
+    return task
+  }
+
+  /**
+   * Stamp the sandbox facts BEFORE completion listeners run: the base
+   * executor notifies from inside the task's settle path, so overriding the
+   * notification point is what makes `task.sandbox` visible to `onTaskDone`
+   * consumers and `done` awaiters alike. Each task classifies against the
+   * facts of ITS OWN wrap and reports ITS OWN mode (consumed from the
+   * per-task map here — settle is the entry's end of life): with per-call
+   * escalation, tasks under different modes settle side by side, so keying
+   * anything off the configured default would misreport them. A
+   * `danger-full-access` task has no map entry and carries no facts (nothing
+   * confined it); a signal-killed task (null exit code) is never a denial,
+   * mirroring the foreground classifier.
+   */
+  protected override notifyTaskDone(task: BashTask): void {
+    const facts = this.taskFacts.get(task.id)
+    if (facts !== undefined) {
+      this.taskFacts.delete(task.id)
+      const stderr = this.collectedStderr(task.id)
+      // Runner failure outranks denial (the command never ran; the runner's
+      // own error text can contain denial words). A settled task has no
+      // error channel left, so the fact IS the surface here — the foreground
+      // path throws instead.
+      const runnerFailed = matchesSignature(task.exitCode, stderr, facts.runnerFailureSignatures)
+      task.sandbox = {
+        mode: facts.mode,
+        denied: !runnerFailed && matchesSignature(task.exitCode, stderr, facts.denialSignatures),
+        enforcement: facts.enforcement,
+        ...(runnerFailed ? { runnerFailed } : {}),
+      }
+    }
+    super.notifyTaskDone(task)
+  }
+
+  /**
+   * Wrap one shell command via the `ctx.sandbox` provider: hand over the
+   * exact `['bash', '-c', command]` argv this executor would spawn, get back
+   * the confined argv, and re-assemble it into the `exec …` command string
+   * the inherited spawn path runs (the outer `bash -c` that `runBash` spawns
+   * `exec`s into the runner, so no extra shell lingers). Provider errors
+   * (fail-closed `SANDBOX_UNAVAILABLE`) propagate to the caller unchanged.
+   */
+  private confine(command: string, mode: ConfinedSandboxMode): {
+    command: string
+    enforcement: SandboxEnforcement
+    denialSignatures: readonly string[]
+    runnerFailureSignatures: readonly string[]
+  } {
+    const confined = this.ctx.sandbox.confine(['bash', '-c', command], { mode, workspaceRoot: this.workspaceRoot })
+    return {
+      command: `exec ${confined.argv.map(shellQuote).join(' ')}`,
+      enforcement: confined.enforcement,
+      denialSignatures: confined.denialSignatures,
+      runnerFailureSignatures: confined.runnerFailureSignatures,
+    }
+  }
+}
+
+export default SandboxBashExecutor

packages/bash/bash-sandbox/tests/bwrap.e2e.ts

@@ -0,0 +1,101 @@
+import { spawnSync } from 'node:child_process'
+import { existsSync, readFileSync } from 'node:fs'
+import { mkdtemp, rm } from 'node:fs/promises'
+import { homedir } from 'node:os'
+import { join } from 'node:path'
+import { afterEach, describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import { bwrapProfileArgs, LocalSandboxProvider } from '@deepseek-ai/dsh-sandbox-local'
+import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox'
+
+/**
+ * KEYLESS consumer-integration proof under bwrap: the REAL
+ * `LocalSandboxProvider` (nothing forced — bwrap is the ladder's first rung,
+ * so a passing probe selects it) underneath the REAL `SandboxBashExecutor`,
+ * driven through the executor's public run/start paths. Verifies the WORLD
+ * (files exist or don't) plus the stamped result facts — in particular that
+ * bwrap's EROFS denial text classifies as `denied: true` through the
+ * wrap-carried dialect; the backend-only confinement proofs live with
+ * `@deepseek-ai/dsh-sandbox-local`.
+ *
+ * Self-skips wherever the functional probe fails — no `bwrap` on PATH, or a
+ * host that denies unprivileged user namespaces.
+ *
+ * HOME-based dirs on purpose: bwrap's `/tmp` is an ephemeral mount, so only
+ * paths outside it prove the workspace-root boundary.
+ */
+
+const probe = spawnSync('bwrap', [...bwrapProfileArgs({ mode: 'read-only', workspaceRoot: '/' }), '--', 'true'], { timeout: 5_000, stdio: 'ignore' })
+const bwrapUsable = probe.status === 0
+
+let ctx: Context | undefined
+const tempDirs: string[] = []
+
+afterEach(async () => {
+  await ctx?.fiber.dispose()
+  ctx = undefined
+  await Promise.all(tempDirs.splice(0).map(dir => rm(dir, { recursive: true, force: true })))
+})
+
+async function tempDir(base: string): Promise<string> {
+  const dir = await mkdtemp(join(base, 'dsh-bwrap-e2e-'))
+  tempDirs.push(dir)
+  return dir
+}
+
+async function sandboxedBash(workspace: string, mode: 'read-only' | 'workspace-write'): Promise<SandboxBashExecutor> {
+  ctx = new Context()
+  await ctx.plugin(LocalSandboxProvider, {})
+  await ctx.plugin(SandboxBashExecutor, { mode, cwd: workspace, workspaceRoot: workspace, timeoutMs: 30_000 })
+  return ctx.bash as SandboxBashExecutor
+}
+
+describe.skipIf(!bwrapUsable)('bash-sandbox: real bwrap confinement through ctx.bash', () => {
+  it('read-only denies a write — the file must NOT exist, and EROFS text classifies as a denial', async () => {
+    const workdir = await tempDir(homedir())
+    const bash = await sandboxedBash(workdir, 'read-only')
+    const result = await bash.run(bash.resolve({ command: `echo hi > ${workdir}/denied.txt` }))
+    expect(result.exitCode).not.toBe(0)
+    expect(result.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'full' })
+    expect(existsSync(join(workdir, 'denied.txt'))).toBe(false)
+  })
+
+  it('workspace-write lands a write inside the workspace root and still denies one beside it', async () => {
+    const workdir = await tempDir(homedir())
+    const outside = await tempDir(homedir())
+    const bash = await sandboxedBash(workdir, 'workspace-write')
+
+    const inside = await bash.run(bash.resolve({ command: `printf bwrap-ok > ${workdir}/allowed.txt` }))
+    expect(inside.exitCode).toBe(0)
+    expect(inside.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'full' })
+    expect(readFileSync(join(workdir, 'allowed.txt'), 'utf8')).toBe('bwrap-ok')
+
+    const denied = await bash.run(bash.resolve({ command: `echo hi > ${outside}/denied.txt` }))
+    expect(denied.exitCode).not.toBe(0)
+    expect(denied.sandbox).toEqual({ mode: 'workspace-write', denied: true, enforcement: 'full' })
+    expect(existsSync(join(outside, 'denied.txt'))).toBe(false)
+  })
+
+  it('classifies a background denial once the task settles', async () => {
+    const workdir = await tempDir(homedir())
+    const bash = await sandboxedBash(workdir, 'read-only')
+    const task = bash.start(bash.resolve({ command: `echo hi > ${workdir}/bg-denied.txt` }))
+    await task.done
+    expect(task.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'full' })
+    expect(existsSync(join(workdir, 'bg-denied.txt'))).toBe(false)
+  })
+
+  it('an approved escalated retry — the spec-level workspace-write override — lands the exact write read-only denied', async () => {
+    const workdir = await tempDir(homedir())
+    const bash = await sandboxedBash(workdir, 'read-only')
+    const command = `printf escalated > ${workdir}/escalated.txt`
+    const strict = await bash.run(bash.resolve({ command }))
+    expect(strict.exitCode).not.toBe(0)
+    expect(strict.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'full' })
+    expect(existsSync(join(workdir, 'escalated.txt'))).toBe(false)
+    const retried = await bash.run(bash.resolve({ command, sandboxMode: 'workspace-write' }))
+    expect(retried.exitCode).toBe(0)
+    expect(retried.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'full' })
+    expect(readFileSync(join(workdir, 'escalated.txt'), 'utf8')).toBe('escalated')
+  })
+})

packages/bash/bash-sandbox/tests/landlock.e2e.ts

@@ -0,0 +1,100 @@
+import { spawnSync } from 'node:child_process'
+import { existsSync, readFileSync } from 'node:fs'
+import { mkdtemp, rm } from 'node:fs/promises'
+import { homedir, tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { afterEach, describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import { launcherPath } from 'node-addon-landlock-run'
+import { LocalSandboxProvider } from '@deepseek-ai/dsh-sandbox-local'
+import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox'
+
+/**
+ * KEYLESS consumer-integration proof: the REAL `LocalSandboxProvider` (bwrap
+ * rung forced off, so the npm-distributed `landlock-run` confines) underneath the
+ * REAL `SandboxBashExecutor`, driven through the executor's public run/start
+ * paths. Verifies the WORLD (files exist or don't) plus the stamped result
+ * facts; the backend-only confinement proofs live with
+ * `@deepseek-ai/dsh-sandbox-local`.
+ *
+ * Self-skips when the running kernel does not enforce Landlock; the
+ * launcher binary itself arrives with `pnpm install` (`node-addon-landlock-run`).
+ */
+
+const probe = spawnSync(launcherPath(), ['--probe'], { timeout: 5_000, encoding: 'utf8' })
+const landlockUsable = probe.status === 0
+/** The kernel's enforcement level from the probe report — stamped facts below must match it. */
+const enforcement = /partially enforced/.test(probe.stdout ?? '') ? 'partial' : 'full'
+
+let ctx: Context | undefined
+const tempDirs: string[] = []
+
+afterEach(async () => {
+  await ctx?.fiber.dispose()
+  ctx = undefined
+  await Promise.all(tempDirs.splice(0).map(dir => rm(dir, { recursive: true, force: true })))
+})
+
+async function tempDir(base: string): Promise<string> {
+  const dir = await mkdtemp(join(base, 'dsh-landlock-e2e-'))
+  tempDirs.push(dir)
+  return dir
+}
+
+async function sandboxedBash(workspace: string, mode: 'read-only' | 'workspace-write'): Promise<SandboxBashExecutor> {
+  ctx = new Context()
+  await ctx.plugin(LocalSandboxProvider, {})
+  ;(ctx.sandbox as LocalSandboxProvider).internals = { probeBwrap: () => false }
+  await ctx.plugin(SandboxBashExecutor, { mode, cwd: workspace, workspaceRoot: workspace, timeoutMs: 30_000 })
+  return ctx.bash as SandboxBashExecutor
+}
+
+describe.skipIf(!landlockUsable)('bash-sandbox: real Landlock confinement through ctx.bash', () => {
+  it('read-only denies a write — the file must NOT exist, the result carries denial + enforcement facts', async () => {
+    const workdir = await tempDir(tmpdir())
+    const bash = await sandboxedBash(workdir, 'read-only')
+    const result = await bash.run(bash.resolve({ command: `echo hi > ${workdir}/denied.txt` }))
+    expect(result.exitCode).not.toBe(0)
+    expect(result.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement })
+    expect(existsSync(join(workdir, 'denied.txt'))).toBe(false)
+  })
+
+  it('workspace-write lands a write inside the workspace root and still denies one beside it', async () => {
+    const workdir = await tempDir(homedir())
+    const outside = await tempDir(homedir())
+    const bash = await sandboxedBash(workdir, 'workspace-write')
+
+    const inside = await bash.run(bash.resolve({ command: `printf landlock-ok > ${workdir}/allowed.txt` }))
+    expect(inside.exitCode).toBe(0)
+    expect(inside.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement })
+    expect(readFileSync(join(workdir, 'allowed.txt'), 'utf8')).toBe('landlock-ok')
+
+    const denied = await bash.run(bash.resolve({ command: `echo hi > ${outside}/denied.txt` }))
+    expect(denied.exitCode).not.toBe(0)
+    expect(denied.sandbox).toEqual({ mode: 'workspace-write', denied: true, enforcement })
+    expect(existsSync(join(outside, 'denied.txt'))).toBe(false)
+  })
+
+  it('classifies a background denial once the task settles', async () => {
+    const workdir = await tempDir(homedir())
+    const bash = await sandboxedBash(workdir, 'read-only')
+    const task = bash.start(bash.resolve({ command: `echo hi > ${workdir}/bg-denied.txt` }))
+    await task.done
+    expect(task.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement })
+    expect(existsSync(join(workdir, 'bg-denied.txt'))).toBe(false)
+  })
+
+  it('an approved escalated retry — the spec-level workspace-write override — lands the exact write read-only denied', async () => {
+    const workdir = await tempDir(homedir())
+    const bash = await sandboxedBash(workdir, 'read-only')
+    const command = `printf escalated > ${workdir}/escalated.txt`
+    const strict = await bash.run(bash.resolve({ command }))
+    expect(strict.exitCode).not.toBe(0)
+    expect(strict.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: enforcement })
+    expect(existsSync(join(workdir, 'escalated.txt'))).toBe(false)
+    const retried = await bash.run(bash.resolve({ command, sandboxMode: 'workspace-write' }))
+    expect(retried.exitCode).toBe(0)
+    expect(retried.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: enforcement })
+    expect(readFileSync(join(workdir, 'escalated.txt'), 'utf8')).toBe('escalated')
+  })
+})

packages/bash/bash-sandbox/tests/sandbox.spec.ts

@@ -0,0 +1,327 @@
+/**
+ * SandboxBashExecutor tests: the CONSUMER side of the sandbox seam. A fake
+ * `ctx.sandbox` provider (injected as a real cordis service) makes wrapping,
+ * policy hand-off, fail-closed propagation, classification, and fact
+ * stamping all deterministic without any real runner; the real-provider
+ * integration proof lives in `tests/landlock.e2e.ts`. Denials are produced
+ * with plain unix permissions (a 0555 directory), which exercises the same
+ * stderr signature the classifier keys on.
+ */
+
+import { chmodSync, mkdirSync, mkdtempSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { join, resolve } from 'node:path'
+import { describe, expect, it, vi } from 'vitest'
+import { Context } from 'cordis'
+import type { BashRunResult, CollectedOutput } from '@deepseek-ai/dsh-bash'
+import { SANDBOX_UNAVAILABLE, SandboxProvider, SandboxUnavailableError } from '@deepseek-ai/dsh-sandbox'
+import type { ConfinedArgv, SandboxPolicy } from '@deepseek-ai/dsh-sandbox'
+import { classifyDenial, classifyRunnerFailure, SandboxBashExecutor, shellQuote } from '@deepseek-ai/dsh-bash-sandbox'
+import type { Config } from '@deepseek-ai/dsh-bash-sandbox'
+
+const spillDir = mkdtempSync(join(tmpdir(), 'dsh-bash-sandbox-spec-'))
+
+/** One recorded provider call: the argv handed over and the policy it rode with. */
+interface ConfineCall {
+  argv: string[]
+  policy: SandboxPolicy
+}
+
+/** The Linux file-denial dialects the fake wraps carry — matches the unix-permission denials the tests below produce. */
+const UNIX_SIGNATURES = ['read-only file system', 'permission denied'] as const
+
+/** The runner-failure prefix the fake wraps carry (a fake-runner: error line marks the sandbox itself failing). */
+const RUNNER_FAILURE = ['fake-runner: '] as const
+
+/** A passthrough wrap: the caller's argv unchanged, asserted full — commands run unconfined, deterministically. */
+const passthrough = (argv: readonly string[]): ConfinedArgv =>
+  ({ argv: [...argv], enforcement: 'full', denialSignatures: UNIX_SIGNATURES, runnerFailureSignatures: RUNNER_FAILURE })
+
+/**
+ * Boot a context with a recording fake `ctx.sandbox` (behavior injectable
+ * per test) and the executor under test on top of it.
+ */
+async function setup(config: Config = {}, behavior: (argv: readonly string[], policy: SandboxPolicy) => ConfinedArgv = passthrough) {
+  const calls: ConfineCall[] = []
+  class FakeSandboxProvider extends SandboxProvider {
+    confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv {
+      calls.push({ argv: [...argv], policy })
+      return behavior(argv, policy)
+    }
+  }
+  const ctx = new Context()
+  await ctx.plugin(FakeSandboxProvider)
+  await ctx.plugin(SandboxBashExecutor, { graceMs: 200, ...config })
+  const bash = ctx.bash as SandboxBashExecutor
+  bash.internals = { spillDir }
+  return { ctx, bash, calls }
+}
+
+function output(text: string): CollectedOutput {
+  return { text, truncated: false }
+}
+
+function runResult(exitCode: number | null, stderr: string): BashRunResult {
+  return { exitCode, signal: null, timedOut: false, aborted: false, timeoutMs: 1000, stdout: output(''), stderr: output(stderr) }
+}
+
+describe('the provider hand-off', () => {
+  it('hands the provider the exact bash argv and the per-call policy, and runs the returned argv', async () => {
+    const { bash, calls } = await setup()
+    const result = await bash.run(bash.resolve({ command: 'echo \'a b\' "c\'d"' }))
+    expect(result.stdout.text).toBe('a b c\'d\n')
+    expect(result.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'full' })
+    expect(calls).toEqual([{
+      argv: ['bash', '-c', 'echo \'a b\' "c\'d"'],
+      policy: { mode: 'read-only', workspaceRoot: resolve(process.cwd()) },
+    }])
+  })
+
+  it('a wrapped argv from the provider is what actually spawns (prefix survives, quoting round-trips)', async () => {
+    // The fake wraps with `env MARKER=...` — a real (if tiny) runner prefix:
+    // the sentinel only prints if the executor spawned the WRAPPED argv.
+    const { bash } = await setup({}, argv => ({ argv: ['env', 'DSH_WRAP=1', ...argv], enforcement: 'full', denialSignatures: UNIX_SIGNATURES, runnerFailureSignatures: RUNNER_FAILURE }))
+    const result = await bash.run(bash.resolve({ command: 'printf "%s" "$DSH_WRAP"' }))
+    expect(result.stdout.text).toBe('1')
+    expect(result.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'full' })
+  })
+
+  it('workspace-write rides the policy, workspaceRoot falling back to cwd when not configured', async () => {
+    const { bash, calls } = await setup({ mode: 'workspace-write', cwd: tmpdir() })
+    const result = await bash.run(bash.resolve({ command: 'true' }))
+    expect(result.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'full' })
+    expect(calls[0]?.policy).toEqual({ mode: 'workspace-write', workspaceRoot: resolve(tmpdir()) })
+  })
+
+  it('an explicit workspaceRoot wins over cwd', async () => {
+    const { calls, bash } = await setup({ mode: 'workspace-write', workspaceRoot: '/ws', cwd: tmpdir() })
+    await bash.run(bash.resolve({ command: 'true' }))
+    expect(calls[0]?.policy.workspaceRoot).toBe(resolve('/ws'))
+  })
+
+  it('the provider is consulted per wrap (no caching in the consumer): run and start each hand off', async () => {
+    const { bash, calls } = await setup()
+    await bash.run(bash.resolve({ command: 'true' }))
+    const task = bash.start(bash.resolve({ command: 'true' }))
+    await task.done
+    expect(calls).toHaveLength(2)
+  })
+
+  it('shellQuote survives embedded single quotes (the argv re-assembly primitive)', () => {
+    expect(shellQuote('a\'b')).toBe(String.raw`'a'\''b'`)
+  })
+})
+
+describe('fail closed', () => {
+  it('propagates the provider\'s structured SANDBOX_UNAVAILABLE on run() and start()', async () => {
+    const { bash } = await setup({}, () => { throw new SandboxUnavailableError('read-only') })
+    const spec = bash.resolve({ command: 'echo hi' })
+    await expect(bash.run(spec)).rejects.toMatchObject({ name: 'SandboxUnavailableError', code: SANDBOX_UNAVAILABLE })
+    expect(() => bash.start(spec)).toThrow(SandboxUnavailableError)
+  })
+})
+
+describe('danger-full-access', () => {
+  it('runs unwrapped: the provider is never consulted, facts carry no enforcement', async () => {
+    const { bash, calls } = await setup({ mode: 'danger-full-access' })
+    const result = await bash.run(bash.resolve({ command: 'echo free' }))
+    expect(result.stdout.text).toBe('free\n')
+    expect(result.sandbox).toEqual({ mode: 'danger-full-access', denied: false })
+    expect(calls).toHaveLength(0)
+  })
+
+  it('start() passes through unwrapped and stamps nothing at settle', async () => {
+    const { bash, calls } = await setup({ mode: 'danger-full-access' })
+    const task = bash.start(bash.resolve({ command: 'echo free-bg' }))
+    await task.done
+    expect(task.sandbox).toBeUndefined()
+    expect(bash.readOutput(task.id).delta).toContain('free-bg')
+    expect(calls).toHaveLength(0)
+  })
+})
+
+describe('per-call sandboxMode override (the escalation mechanism)', () => {
+  it('exposes the configured default as the capability fact, and resolve() stamps it', async () => {
+    const { bash } = await setup()
+    expect(bash.sandboxMode).toBe('read-only')
+    expect(bash.resolve({ command: 'true' }).sandboxMode).toBe('read-only')
+  })
+
+  it('an explicit override outranks the default at resolve(), and the wrap policy follows it', async () => {
+    const { bash, calls } = await setup()
+    expect(bash.resolve({ command: 'true', sandboxMode: 'workspace-write' }).sandboxMode).toBe('workspace-write')
+    await bash.run(bash.resolve({ command: 'true', sandboxMode: 'workspace-write' }))
+    await bash.run(bash.resolve({ command: 'true' }))
+    expect(calls.map(call => call.policy.mode)).toEqual(['workspace-write', 'read-only'])
+  })
+
+  it('an escalated run reports the mode it ACTUALLY ran under', async () => {
+    const { bash } = await setup()
+    const result = await bash.run(bash.resolve({ command: 'true', sandboxMode: 'workspace-write' }))
+    expect(result.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'full' })
+  })
+
+  it('escalating to danger-full-access bypasses the provider entirely — the grant, not a probe, is the authority there', async () => {
+    const { bash, calls } = await setup()
+    const result = await bash.run(bash.resolve({ command: 'echo free', sandboxMode: 'danger-full-access' }))
+    expect(result.stdout.text).toBe('free\n')
+    expect(result.sandbox).toEqual({ mode: 'danger-full-access', denied: false })
+    expect(calls).toHaveLength(0)
+  })
+
+  it('overlapping background tasks settle with their OWN modes (an escalated task next to a default one)', async () => {
+    // With per-call policy, tasks under different modes are in flight at
+    // once — anything keyed off the configured default would misreport the
+    // escalated one at its settle stamp.
+    const { bash } = await setup()
+    const escalated = bash.start(bash.resolve({ command: 'sleep 0.3; echo "x: Permission denied" >&2; exit 1', sandboxMode: 'workspace-write' }))
+    const plain = bash.start(bash.resolve({ command: 'true' }))
+    await plain.done
+    await escalated.done
+    expect(escalated.sandbox).toEqual({ mode: 'workspace-write', denied: true, enforcement: 'full' })
+    expect(plain.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'full' })
+  })
+
+  it('an escalated danger-full-access background task carries no facts (nothing confined it)', async () => {
+    const { bash, calls } = await setup()
+    const task = bash.start(bash.resolve({ command: 'echo bg-free', sandboxMode: 'danger-full-access' }))
+    await task.done
+    expect(task.sandbox).toBeUndefined()
+    expect(bash.readOutput(task.id).delta).toContain('bg-free')
+    expect(calls).toHaveLength(0)
+  })
+})
+
+describe('classifyDenial', () => {
+  it('never classifies a clean exit or a signal kill as a denial', () => {
+    expect(classifyDenial(runResult(0, 'Permission denied'), UNIX_SIGNATURES)).toBe(false)
+    expect(classifyDenial(runResult(null, 'Permission denied'), UNIX_SIGNATURES)).toBe(false)
+  })
+
+  it('classifies failed runs by the wrap\'s own dialect, conservatively', () => {
+    expect(classifyDenial(runResult(1, 'touch: cannot touch /x: Read-only file system'), UNIX_SIGNATURES)).toBe(true)
+    expect(classifyDenial(runResult(1, 'sh: /x: Permission denied'), UNIX_SIGNATURES)).toBe(true)
+    // Bare EPERM is not a Linux runner's dialect: mount/kill/ptrace fail with
+    // it unsandboxed too, and the mode vocabulary governs file effects only —
+    // claiming a file denial here would tell the model the sandbox blocked
+    // something it never governed.
+    expect(classifyDenial(runResult(1, 'mount: Operation not permitted'), UNIX_SIGNATURES)).toBe(false)
+    expect(classifyDenial(runResult(1, 'No such file or directory'), UNIX_SIGNATURES)).toBe(false)
+  })
+
+  it('matches exactly the active backend\'s dialect: EPERM classifies under Seatbelt, EACCES does not under bwrap', () => {
+    // The same stderr flips meaning with the backend: under Seatbelt, EPERM
+    // text IS how the kernel refuses a governed file write; under bwrap's
+    // EROFS-only dialect, `Permission denied` is ordinary DAC, not the
+    // sandbox — per-wrap signatures are what keep both classifications honest.
+    expect(classifyDenial(runResult(1, 'bash: /etc/x: Operation not permitted'), ['operation not permitted'])).toBe(true)
+    expect(classifyDenial(runResult(1, 'sh: /x: Permission denied'), ['read-only file system'])).toBe(false)
+  })
+})
+
+describe('classifyRunnerFailure', () => {
+  it('matches the dialect case-insensitively on BOTH sides — the seam declares it so, and producers compose signatures from runtime data (an argv0 path, the shell\'s `No such file or directory`)', () => {
+    const signatures = ['exec: /Opt/Runners/bwrap: not found', '/Opt/Runners/bwrap: No such file or directory']
+    expect(classifyRunnerFailure(runResult(127, 'bash: /Opt/Runners/bwrap: No such file or directory'), signatures)).toBe(true)
+    expect(classifyRunnerFailure(runResult(127, 'BASH: LINE 1: EXEC: /OPT/RUNNERS/BWRAP: NOT FOUND'), signatures)).toBe(true)
+  })
+})
+
+describe('result facts', () => {
+  it('reports a real permission failure as a sandbox denial with the mode it ran under', async () => {
+    const { bash } = await setup()
+    const lockedDir = join(mkdtempSync(join(tmpdir(), 'dsh-sandbox-denied-')), 'locked')
+    mkdirSync(lockedDir)
+    chmodSync(lockedDir, 0o555)
+    const result = await bash.run(bash.resolve({ command: `echo x > ${lockedDir}/f` }))
+    expect(result.exitCode).not.toBe(0)
+    expect(result.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'full' })
+  })
+
+  it('carries the provider\'s partial-enforcement fact through unchanged', async () => {
+    const { bash } = await setup({}, argv => ({ argv: [...argv], enforcement: 'partial', denialSignatures: UNIX_SIGNATURES, runnerFailureSignatures: RUNNER_FAILURE }))
+    const result = await bash.run(bash.resolve({ command: 'true' }))
+    expect(result.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'partial' })
+  })
+})
+
+describe('background sandbox facts', () => {
+  it('stamps a settled denial: nonzero exit + permission stderr under a confined mode', async () => {
+    const { bash } = await setup()
+    const task = bash.start(bash.resolve({ command: 'echo "x: Permission denied" >&2; exit 1' }))
+    await task.done
+    expect(task.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'full' })
+  })
+
+  it('a foreground runner failure throws the fail-closed error, never a task result', async () => {
+    // The wrap's runner prefix on a failed run means the SANDBOX broke and
+    // the command never ran — the late twin of the confine-time throw, with
+    // the runner's own first stderr line carried as the cause.
+    const { bash } = await setup()
+    const run = bash.run(bash.resolve({ command: 'echo "fake-runner: ruleset rejected" >&2; exit 125' }))
+    await expect(run).rejects.toThrow(expect.objectContaining({ code: SANDBOX_UNAVAILABLE }))
+    await expect(run).rejects.toThrow('fake-runner: ruleset rejected')
+  })
+
+  it('a foreground runner failure outranks denial: runner error text may contain denial words', async () => {
+    const { bash } = await setup()
+    await expect(bash.run(bash.resolve({ command: 'echo "fake-runner: cannot open rule path: /x: Permission denied" >&2; exit 125' })))
+      .rejects.toThrow(expect.objectContaining({ code: SANDBOX_UNAVAILABLE }))
+  })
+
+  it('a settled background runner failure stamps runnerFailed (no error channel remains), not denied', async () => {
+    const { bash } = await setup()
+    const task = bash.start(bash.resolve({ command: 'echo "fake-runner: cannot open rule path: /x: Permission denied" >&2; exit 125' }))
+    await task.done
+    expect(task.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'full', runnerFailed: true })
+  })
+
+  it('completion listeners already see the stamped facts (stamp precedes notify)', async () => {
+    const { ctx, bash } = await setup({}, argv => ({ argv: [...argv], enforcement: 'partial', denialSignatures: UNIX_SIGNATURES, runnerFailureSignatures: RUNNER_FAILURE }))
+    const seen: unknown[] = []
+    ctx.bash.onTaskDone((task) => { seen.push(task.sandbox) })
+    const task = bash.start(bash.resolve({ command: 'echo "x: Permission denied" >&2; exit 1' }))
+    await task.done
+    expect(seen).toEqual([{ mode: 'read-only', denied: true, enforcement: 'partial' }])
+  })
+
+  it('overlapping background tasks keep their OWN wrap facts (per-task, not latest-wrap)', async () => {
+    // The seam returns facts PER WRAP — a legal provider may vary them
+    // between calls. The slow task settles AFTER the quick one started, so a
+    // latest-wrap field would classify its denial against the quick task's
+    // dialect (missing it) and stamp the wrong enforcement.
+    const wraps: Array<Pick<ConfinedArgv, 'enforcement' | 'denialSignatures'>> = [
+      { enforcement: 'partial', denialSignatures: ['permission denied'] },
+      { enforcement: 'full', denialSignatures: ['read-only file system'] },
+    ]
+    let call = 0
+    const { bash } = await setup({}, (argv) => {
+      const wrap = wraps[Math.min(call++, wraps.length - 1)] as Pick<ConfinedArgv, 'enforcement' | 'denialSignatures'>
+      return { argv: [...argv], ...wrap, runnerFailureSignatures: RUNNER_FAILURE }
+    })
+    const slow = bash.start(bash.resolve({ command: 'sleep 0.4; echo "x: Permission denied" >&2; exit 1' }))
+    const quick = bash.start(bash.resolve({ command: 'true' }))
+    await quick.done
+    await slow.done
+    expect(slow.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'partial' })
+    expect(quick.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'full' })
+  })
+
+  it('a signal-killed task is never a denial (null exit code)', async () => {
+    const { bash } = await setup()
+    const task = bash.start(bash.resolve({ command: 'echo "Permission denied" >&2; sleep 30' }))
+    // Let the stderr land before the kill so the classifier sees the
+    // signature and must still refuse it on the null exit code alone.
+    await vi.waitFor(() => { expect(bash.readOutput(task.id).delta).toContain('Permission denied') })
+    bash.kill(task.id)
+    await task.done
+    expect(task.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'full' })
+  })
+
+  it('disposal kills wrapped background tasks (inherited HMR safety)', async () => {
+    const { ctx, bash } = await setup()
+    const task = bash.start(bash.resolve({ command: 'sleep 30' }))
+    await ctx.fiber.dispose()
+    expect(task.status).toBe('killed')
+  })
+})

packages/bash/bash-sandbox/tests/seatbelt.e2e.ts

@@ -0,0 +1,101 @@
+import { spawnSync } from 'node:child_process'
+import { existsSync, readFileSync } from 'node:fs'
+import { mkdtemp, rm } from 'node:fs/promises'
+import { homedir } from 'node:os'
+import { join } from 'node:path'
+import { afterEach, describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import { LocalSandboxProvider, seatbeltProfileArgs } from '@deepseek-ai/dsh-sandbox-local'
+import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox'
+
+/**
+ * KEYLESS consumer-integration proof on macOS: the REAL `LocalSandboxProvider`
+ * (Linux rungs forced off, so `sandbox-exec`/Seatbelt confines) underneath
+ * the REAL `SandboxBashExecutor`, driven through the executor's public
+ * run/start paths. Verifies the WORLD (files exist or don't) plus the
+ * stamped result facts — in particular that Seatbelt's EPERM denial text
+ * classifies as `denied: true` through the wrap-carried dialect; the
+ * backend-only confinement proofs live with `@deepseek-ai/dsh-sandbox-local`.
+ *
+ * Self-skips wherever the functional probe fails — every non-macOS host, or
+ * a macOS whose `sandbox-exec` refuses the profile.
+ */
+
+const probe = spawnSync('sandbox-exec', [...seatbeltProfileArgs({ mode: 'read-only', workspaceRoot: '/' }), '--', 'true'], { timeout: 5_000, stdio: 'ignore' })
+const seatbeltUsable = probe.status === 0
+
+let ctx: Context | undefined
+const tempDirs: string[] = []
+
+afterEach(async () => {
+  await ctx?.fiber.dispose()
+  ctx = undefined
+  await Promise.all(tempDirs.splice(0).map(dir => rm(dir, { recursive: true, force: true })))
+})
+
+async function tempDir(base: string): Promise<string> {
+  const dir = await mkdtemp(join(base, 'dsh-seatbelt-e2e-'))
+  tempDirs.push(dir)
+  return dir
+}
+
+async function sandboxedBash(workspace: string, mode: 'read-only' | 'workspace-write'): Promise<SandboxBashExecutor> {
+  ctx = new Context()
+  await ctx.plugin(LocalSandboxProvider, {})
+  ;(ctx.sandbox as LocalSandboxProvider).internals = { probeBwrap: () => false, probeLandlock: () => 'unusable' }
+  await ctx.plugin(SandboxBashExecutor, { mode, cwd: workspace, workspaceRoot: workspace, timeoutMs: 30_000 })
+  return ctx.bash as SandboxBashExecutor
+}
+
+describe.skipIf(!seatbeltUsable)('bash-sandbox: real Seatbelt confinement through ctx.bash', () => {
+  it('read-only denies a write — the file must NOT exist, and EPERM text classifies as a denial', async () => {
+    const workdir = await tempDir(homedir())
+    const bash = await sandboxedBash(workdir, 'read-only')
+    const result = await bash.run(bash.resolve({ command: `echo hi > ${workdir}/denied.txt` }))
+    expect(result.exitCode).not.toBe(0)
+    expect(result.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'full' })
+    expect(existsSync(join(workdir, 'denied.txt'))).toBe(false)
+  })
+
+  it('workspace-write lands a write inside the workspace root and still denies one beside it', async () => {
+    // HOME-based dirs on purpose: workspace-write grants /tmp and the
+    // per-user temp dir wholesale, so only paths outside both prove the
+    // workspace-root boundary.
+    const workdir = await tempDir(homedir())
+    const outside = await tempDir(homedir())
+    const bash = await sandboxedBash(workdir, 'workspace-write')
+
+    const inside = await bash.run(bash.resolve({ command: `printf seatbelt-ok > ${workdir}/allowed.txt` }))
+    expect(inside.exitCode).toBe(0)
+    expect(inside.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'full' })
+    expect(readFileSync(join(workdir, 'allowed.txt'), 'utf8')).toBe('seatbelt-ok')
+
+    const denied = await bash.run(bash.resolve({ command: `echo hi > ${outside}/denied.txt` }))
+    expect(denied.exitCode).not.toBe(0)
+    expect(denied.sandbox).toEqual({ mode: 'workspace-write', denied: true, enforcement: 'full' })
+    expect(existsSync(join(outside, 'denied.txt'))).toBe(false)
+  })
+
+  it('classifies a background denial once the task settles', async () => {
+    const workdir = await tempDir(homedir())
+    const bash = await sandboxedBash(workdir, 'read-only')
+    const task = bash.start(bash.resolve({ command: `echo hi > ${workdir}/bg-denied.txt` }))
+    await task.done
+    expect(task.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'full' })
+    expect(existsSync(join(workdir, 'bg-denied.txt'))).toBe(false)
+  })
+
+  it('an approved escalated retry — the spec-level workspace-write override — lands the exact write read-only denied', async () => {
+    const workdir = await tempDir(homedir())
+    const bash = await sandboxedBash(workdir, 'read-only')
+    const command = `printf escalated > ${workdir}/escalated.txt`
+    const strict = await bash.run(bash.resolve({ command }))
+    expect(strict.exitCode).not.toBe(0)
+    expect(strict.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'full' })
+    expect(existsSync(join(workdir, 'escalated.txt'))).toBe(false)
+    const retried = await bash.run(bash.resolve({ command, sandboxMode: 'workspace-write' }))
+    expect(retried.exitCode).toBe(0)
+    expect(retried.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'full' })
+    expect(readFileSync(join(workdir, 'escalated.txt'), 'utf8')).toBe('escalated')
+  })
+})

packages/bash/bash-sandbox/tsconfig.json

@@ -0,0 +1,36 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": [
+    {
+      "path": "../../../vendor/cosmokit"
+    },
+    {
+      "path": "../../../vendor/cordis"
+    },
+    {
+      "path": "../../../vendor/schemastery"
+    },
+    {
+      "path": "../../util/brand"
+    },
+    {
+      "path": "../../llm/llm"
+    },
+    {
+      "path": "../../sandbox/sandbox"
+    },
+    {
+      "path": "../../bash/bash"
+    },
+    {
+      "path": "../../bash/bash-local"
+    }
+  ]
+}

packages/bash/bash/README.md

@@ -2,15 +2,16 @@
 
 The **bash executor seam**: an abstract `BashExecutor` service (`ctx.bash`) defining WHAT a bash backend does — run commands, manage background tasks — without saying HOW.
 
-This package is one third of the bash capability, split so each concern can evolve (and be swapped) independently:
+This package is the interface quarter of the bash capability, split so each concern can evolve (and be swapped) independently:
 
 | Package | Role |
 |---|---|
 | `@deepseek-ai/dsh-bash` (this) | the interface: abstract service + vocabulary types |
 | `@deepseek-ai/dsh-bash-local` | an implementation: local subprocesses |
+| `@deepseek-ai/dsh-bash-sandbox` | an implementation: `dsh-bash-local`'s mechanics with every spawn confined via [`ctx.sandbox`](../../sandbox/sandbox/), denials reported as result facts |
 | `@deepseek-ai/dsh-tool-bash` | the model-facing tool schemas over `ctx.bash` |
 
-The split mirrors the LLM seam (`LlmService`/`LlmAdapter`) and the agent-tool survey: pi hides execution behind a `BashOperations` interface (local shell / SSH / VM backends), Codex behind an exec-server protocol. A future sandboxed, containerized, or remote executor implements this interface and the tool schemas don't change.
+The split mirrors the LLM seam (`LlmService`/`LlmAdapter`) and the agent-tool survey: pi hides execution behind a `BashOperations` interface (local shell / SSH / VM backends), Codex behind an exec-server protocol. `dsh-bash-sandbox` is exactly that swap in action — a sandboxing executor behind the same interface, tool schemas untouched; a containerized or remote executor slots in the same way.
 
 ## Service API (`ctx.bash`)
 
@@ -19,6 +20,7 @@ The split mirrors the LLM seam (`LlmService`/`LlmAdapter`) and the agent-tool su
 | `run(spec)` | Foreground execution. Resolves when the command finishes. **Rejects only for infrastructure failures** (unusable workdir, missing shell, pre-aborted signal); nonzero exits, timeout kills, and abort kills resolve with a descriptive `BashRunResult`. |
 | `start(spec)` | Background execution. Returns a `BashTask` handle immediately; **no timeout applies** (stop tasks via `kill`). |
 | `get(id)` / `list()` | Task lookup. |
+| `sandboxMode` | The capability fact for the tool layer: the default mode a SANDBOXING executor confines under (`undefined` in the base class — "this executor does not sandbox"). `dsh-tool-bash` reads it at registration to advertise the escalation fields only when the composition honors them. |
 | `ownerOf(id)` | The opaque OWNER token recorded for a background task at `start` (from the spec's `owner`), or `undefined` for an unknown id OR a known-but-ownerless task. The executor stores/returns it verbatim and NEVER interprets it — the access POLICY lives in the consumer (`dsh-tool-bash`), which compares `ownerOf(id)` to the caller's token. Storing ownership here (disposed with the executor's fiber) is what makes it survive a consumer HMR reload. |
 | `readOutput(id)` | **Incremental** output read — consecutive reads never re-deliver. Reads that lost data to buffer bounds flag `lossy` and point at full-stream spill files. Throws for unknown ids. |
 | `kill(id)` | Kill a running task. Returns `false` when it already finished; throws for unknown ids. |
@@ -28,6 +30,8 @@ Implementations subclass `BashExecutor`, implement the abstract methods, and cal
 
 ## Vocabulary
 
-`BashExecRequest` (command, workdir?, timeoutMs?, signal?, stdin?, env?, owner?) resolves to `BashExecSpec` (command, workdir, timeoutMs, signal?, stdin?, env?, owner) before execution; `owner` is optional on the request and **required-but-nullable** (`OwnerToken | undefined`) on the resolved spec, so a forgotten owner is a visible `undefined` rather than a silently-absent property. The task id (`BashTaskId`) and the `owner` token (`OwnerToken`) are [branded](../../util/brand) — `OwnerToken` is a DISTINCT brand from `SessionId` (the seam never imports `dsh-session`; the `dsh-tool-bash` consumer is the single boundary that casts its `SessionId` into one). `run()` returns `BashRunResult` (exitCode, signal, timedOut, aborted, timeoutMs, stdout/stderr as `CollectedOutput`) and `start()`/`readOutput()` use `BashTask`/`BashTaskRead` for the background side. See `src/types.ts` for the full contracts.
+`BashExecRequest` (command, workdir?, timeoutMs?, signal?, stdin?, env?, owner?, sandboxMode?) resolves to `BashExecSpec` (command, workdir, timeoutMs, signal?, stdin?, env?, owner, sandboxMode) before execution; `owner` and `sandboxMode` are optional on the request and **required-but-nullable** on the resolved spec, so a forgotten one is a visible `undefined` rather than a silently-absent property. `sandboxMode` is the explicit per-call sandbox-policy input: an escalation grant a human just issued ([the sandbox RFC § Escalation](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md), which outranks) or the session's standing override ([the sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)); a sandboxing executor's `resolve()` stamps its configured default when the request carries none, and a non-sandboxing executor carries the field verbatim and confines nothing.
+
+The seam also owns the per-session mode override vocabulary (the sandbox RFC § Per-session mode switching): the log-only `'bash/sandbox-mode'` session event, the pure fold `effectiveSandboxMode(events)` (last event wins; `undefined` means "apply the executor default"), and THE write path `setSandboxMode(session, mode)` — the session log is the store, so an override survives restart by replay and two sessions can never see each other's mode. Writers must respect turn-enclosure: the ACP bridge anchors an idle switch at the next turn rather than appending between turns. The task id (`BashTaskId`) and the `owner` token (`OwnerToken`) are [branded](../../util/brand) — `OwnerToken` is a DISTINCT brand from `SessionId` (the seam never imports `dsh-session`; the `dsh-tool-bash` consumer is the single boundary that casts its `SessionId` into one). `run()` returns `BashRunResult` (exitCode, signal, timedOut, aborted, timeoutMs, stdout/stderr as `CollectedOutput`) and `start()`/`readOutput()` use `BashTask`/`BashTaskRead` for the background side. A sandboxing executor additionally stamps `sandbox` result facts on results and settled tasks (`BashSandboxInfo`: the mode it executed under, the conservative `denied` classification, and — for confined modes — the backend's `enforcement` completeness); the mode/enforcement vocabulary is owned by the [`dsh-sandbox`](../../sandbox/sandbox/) seam, and the facts are documented in [core-data-structures/bash.md](../../../docs/core-data-structures/bash.md). See `src/types.ts` for the full contracts.
 
 `stdin` and `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload on stdin and its `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` env. The model-facing `dsh-tool-bash` tool does not expose them as parameters — a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), so they would be redundant tool params. This is not a security boundary: the implementation's credential scrub (not these fields) is what keeps the harness's ambient secrets out of a spawned command. They are plain optionals on the resolved spec (unlike `owner`'s required-but-nullable): a missing one means "none", the safe default. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md).

packages/bash/bash/package.json

@@ -23,10 +23,14 @@
   "license": "BSD-3-Clause",
   "peerDependencies": {
     "@deepseek-ai/dsh-brand": "^0.0.1",
+    "@deepseek-ai/dsh-sandbox": "^0.0.1",
+    "@deepseek-ai/dsh-session": "^0.0.1",
     "cordis": "^4.0.0-rc.6"
   },
   "devDependencies": {
     "@deepseek-ai/dsh-brand": "workspace:^",
+    "@deepseek-ai/dsh-sandbox": "workspace:^",
+    "@deepseek-ai/dsh-session": "workspace:^",
     "cordis": "^4.0.0-rc.6"
   }
 }

packages/bash/bash/src/index.ts

@@ -15,13 +15,16 @@
  */
 
 import { Context, Service } from 'cordis'
+import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
 import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskId, BashTaskListener, BashTaskRead, OwnerToken } from './types.ts'
 
 export { BashTaskId, OwnerToken } from './types.ts'
+export { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from './session-mode.ts'
 export type {
   BashExecRequest,
   BashExecSpec,
   BashRunResult,
+  BashSandboxInfo,
   BashTask,
   BashTaskListener,
   BashTaskRead,
@@ -70,6 +73,22 @@ export abstract class BashExecutor extends Service {
     }, 'bash listener teardown')
   }
 
+  /**
+   * The sandbox mode this executor confines commands under BY DEFAULT, or
+   * `undefined` when it does not sandbox at all — the capability fact the
+   * tool and ACP layers read to advertise sandbox controls honestly. The
+   * getter proves a sandboxing executor is mounted and supplies its fallback
+   * mode; a session override may make the effective mode narrower or wider,
+   * so strict escalation widening is checked per call rather than encoded in
+   * this default-relative capability fact. The base class reports
+   * `undefined`; a sandboxing implementation overrides the getter.
+   * @returns the configured default mode of a sandboxing executor;
+   *   `undefined` for an executor that never confines.
+   */
+  get sandboxMode(): SandboxMode | undefined {
+    return undefined
+  }
+
   /**
    * Resolve a caller's {@link BashExecRequest} into a fully-specified
    * {@link BashExecSpec}, applying this implementation's config defaults and

packages/bash/bash/src/session-mode.ts

@@ -0,0 +1,65 @@
+/**
+ * Per-session sandbox-mode override: the session log as the store. A runtime
+ * switch (an ACP `session/set_config_option`, a test scenario) is recorded as
+ * one `bash/sandbox-mode` event on the session it applies to;
+ * `effective = fold(events) ?? the executor's configured default`, so an
+ * override survives restart by replay, two sessions can never see each
+ * other's state, and there is no external config store. The event is
+ * log-only (the `approval/*` precedent): the model learns the mode from the
+ * prompt section and the boundary notices in `@deepseek-ai/dsh-tool-bash`,
+ * never from the event itself. EXECUTION honors the fold in the tool layer —
+ * it stamps the effective mode onto each call's `BashExecRequest.sandboxMode`
+ * (weakest-precedence: an escalation grant for the call outranks it) — the
+ * executor itself stays a config-fixed default plus per-call overrides.
+ *
+ * @module dsh-bash/session-mode
+ */
+
+import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
+import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
+
+declare module '@deepseek-ai/dsh-session' {
+  interface SessionEventMap {
+    /**
+     * The session's sandbox mode was switched — log-only (like `approval/*`;
+     * NOT a surface event, carries no `surfaceOp`): durable and replayable,
+     * never in the model transcript. The LAST such event is the session's
+     * override ({@link effectiveSandboxMode}); who asked for it is derivable
+     * from position (an event after the log's last `request/header*` was a
+     * runtime switch by the user; see the tool layer's narrator).
+     */
+    'bash/sandbox-mode': { mode: SandboxMode }
+  }
+}
+
+/** Every {@link SandboxMode}, for option advertisement and runtime validation of untrusted mode strings. */
+export const SANDBOX_MODES: readonly SandboxMode[] = ['read-only', 'workspace-write', 'danger-full-access']
+
+/**
+ * The session's sandbox-mode override: the last `bash/sandbox-mode` event in
+ * the log, or undefined when the session never switched (callers apply the
+ * executor's configured default). The pure fold — resume needs no catch-up
+ * machinery because replaying the log IS the state.
+ * @param events - session events in log order (other event types are skipped).
+ * @returns the mode of the last switch event, or undefined without one.
+ */
+export function effectiveSandboxMode(events: readonly SessionEvent[]): SandboxMode | undefined {
+  for (let index = events.length - 1; index >= 0; index -= 1) {
+    const event = events[index] as SessionEvent
+    if (event.type === 'bash/sandbox-mode') return event.data.mode
+  }
+  return undefined
+}
+
+/**
+ * THE write path for a session's sandbox-mode override: appends exactly one
+ * `bash/sandbox-mode` event — the switch IS its event; nothing mutates mode
+ * state out of band. Takes effect on the session's next bash call and next
+ * prompt assembly (the consumers fold on every read).
+ * @param session - the session the override belongs to.
+ * @param mode - the mode every subsequent bash call in this session runs
+ *   under (until the next switch).
+ */
+export function setSandboxMode(session: Session, mode: SandboxMode): void {
+  session.append('bash/sandbox-mode', { mode })
+}

packages/bash/bash/src/types.ts

@@ -7,6 +7,7 @@
  */
 
 import type { Branded } from '@deepseek-ai/dsh-brand'
+import type { SandboxEnforcement, SandboxMode } from '@deepseek-ai/dsh-sandbox'
 
 /** Identifies one background task within an executor (generated `bash-N`). */
 export type BashTaskId = Branded<'BashTaskId'>
@@ -40,6 +41,48 @@ export function OwnerToken(id: string): OwnerToken {
   return id as OwnerToken
 }
 
+/**
+ * Sandbox facts for one foreground run — present on {@link BashRunResult} iff
+ * a sandboxing executor ran the command (an unsandboxed executor reports no
+ * `sandbox` field at all). Reported independently of `exitCode`/`signal`
+ * (orthogonal outcomes), so a caller can tell "the command failed on its own"
+ * from "the sandbox blocked a file operation". The mode/enforcement
+ * vocabulary lives on the `@deepseek-ai/dsh-sandbox` seam; this shape is the
+ * bash seam's result-fact carrier for it.
+ */
+export interface BashSandboxInfo {
+  /** The mode the command actually ran under. */
+  mode: SandboxMode
+  /**
+   * True when the executor classifies this run's failure as the sandbox
+   * denying a file operation. The classification is CONSERVATIVE (a failed
+   * exit whose stderr carries a filesystem-permission signature) and reads
+   * the COLLECTED stderr — the bounded in-memory tail per
+   * {@link CollectedOutput} semantics, so a signature that survives only in a
+   * spill file is missed toward `denied: false`. A plain command failure
+   * keeps `denied: false` even under a sandboxed mode.
+   */
+  denied: boolean
+  /**
+   * How completely the runner enforced `mode`'s file effects — see
+   * {@link SandboxEnforcement}. Absent exactly when `mode` is
+   * `danger-full-access`: nothing is confined, so there is no enforcement to
+   * report.
+   */
+  enforcement?: SandboxEnforcement
+  /**
+   * True when the executor classifies this failure as the SANDBOX RUNNER
+   * itself failing (missing binary, refused profile, fail-closed refusal
+   * before exec) — the command NEVER RAN; this is a sandbox failure, not a
+   * task failure, and it outranks `denied` (a runner's own error text can
+   * contain denial words). Only ever stamped on settled BACKGROUND tasks: a
+   * foreground run surfaces the same condition as the thrown
+   * `SANDBOX_UNAVAILABLE` error instead (the foreground path has an error
+   * channel; a settled task's facts are its only channel).
+   */
+  runnerFailed?: boolean
+}
+
 /**
  * A caller's execution REQUEST: `workdir` and `timeoutMs` are optional and
  * filled by {@link BashExecutor.resolve} from the implementation's config.
@@ -81,6 +124,20 @@ export interface BashExecRequest {
    * ownerless background start (a non-agent caller).
    */
   owner?: OwnerToken | undefined
+  /**
+   * Explicit per-call sandbox-policy input, overriding the executor's
+   * configured default mode for THIS call. Never a silent default: a
+   * consumer sets it only from an explicit policy source — an
+   * `'allowed-once'` grant a human just issued through `ctx.approval` (the
+   * escalation flow in the sandbox RFC § Escalation, which outranks), or the
+   * session's standing override folded from its own `bash/sandbox-mode`
+   * events (the sandbox RFC § Per-session mode switching — the user's recorded per-session
+   * choice). A sandboxing executor confines THIS call under the given mode;
+   * a non-sandboxing executor carries the field and confines nothing (the
+   * tool layer stamps neither escalation nor overrides without a sandboxing
+   * executor — see {@link BashExecutor.sandboxMode}).
+   */
+  sandboxMode?: SandboxMode | undefined
 }
 
 /**
@@ -122,6 +179,16 @@ export interface BashExecSpec {
    * task. `start()` stores it; `run()` (foreground) ignores it.
    */
   owner: OwnerToken | undefined
+  /**
+   * The sandbox mode this call executes under, REQUIRED-but-nullable for the
+   * same visibility reason as `owner`. A sandboxing executor's `resolve()`
+   * stamps the effective mode (the request's explicit override, else its
+   * configured default) so `run()`/`start()` read the spec, never the config;
+   * a non-sandboxing executor carries the request value through verbatim and
+   * ignores it (`undefined` under such an executor means what its README says:
+   * unconfined execution).
+   */
+  sandboxMode: SandboxMode | undefined
 }
 
 /** One captured stream: the (possibly truncated) text plus recovery info. */
@@ -148,6 +215,12 @@ export interface BashRunResult {
   timeoutMs: number
   stdout: CollectedOutput
   stderr: CollectedOutput
+  /**
+   * Sandbox facts, present iff a sandboxing executor ran the command — an
+   * unsandboxed executor (e.g. `dsh-bash-local`) never sets it. See
+   * {@link BashSandboxInfo} for the `denied` classification semantics.
+   */
+  sandbox?: BashSandboxInfo
 }
 
 /** Lifecycle of a background task. */
@@ -164,6 +237,16 @@ export interface BashTask {
   signal: NodeJS.Signals | null
   /** Resolves when the underlying process closes (never rejects). */
   readonly done: Promise<void>
+  /**
+   * Sandbox facts for this task's execution, stamped by a sandboxing executor
+   * once the task settles and BEFORE completion listeners are notified — an
+   * `onTaskDone` consumer and a `done` awaiter both see it. Denial
+   * classification runs against the settled task's collected stderr, so the
+   * field cannot exist earlier: absent while the task is running and under an
+   * executor that does not sandbox. See {@link BashSandboxInfo} for the
+   * `denied` semantics.
+   */
+  sandbox?: BashSandboxInfo
 }
 
 /** One incremental {@link BashExecutor.readOutput} read. */

packages/bash/bash/tests/service.spec.ts

@@ -15,6 +15,7 @@ class StubExecutor extends BashExecutor {
       timeoutMs: request.timeoutMs ?? 1000,
       ...request.signal ? { signal: request.signal } : {},
       owner: request.owner,
+      sandboxMode: request.sandboxMode,
     }
   }
 
@@ -96,6 +97,11 @@ describe('BashExecutor service seam', () => {
     expect(result.exitCode).toBe(0)
   })
 
+  it('reports no default sandbox mode (composition truth: the base never confines)', async () => {
+    const { bash } = await setup()
+    expect(bash.sandboxMode).toBeUndefined()
+  })
+
   it('onTaskDone delivers completions to registered listeners', async () => {
     const { bash } = await setup()
     const seen: string[] = []

packages/bash/bash/tsconfig.json

@@ -16,6 +16,12 @@
     },
     {
       "path": "../../util/brand"
+    },
+    {
+      "path": "../../sandbox/sandbox"
+    },
+    {
+      "path": "../../core/session"
     }
   ]
 }

packages/bash/tool-bash/README.md

@@ -4,7 +4,7 @@ The model-facing bash tools — `bash`, `bash_output`, `bash_kill` — registere
 
 Requires a loaded executor implementation (e.g. `@deepseek-ai/dsh-bash-local`); the plugin stays pending until `ctx.bash` exists (`inject: ['tools', 'bash', 'systemPrompt']`).
 
-The plugin also contributes the `tool:bash` prompt section (order 105) — the cross-call habit the per-tool descriptions cannot carry: check the `[exit code: N]` marker on every result and investigate failures before moving on.
+The plugin also contributes the `tool:bash` prompt section (order 105) — the cross-call habit the per-tool descriptions cannot carry: check the `[exit code: N]` marker on every result and investigate failures before moving on. Under a sandboxing executor it additionally contributes the per-agent `env:bash-sandbox` section (order 110) stating each session's EFFECTIVE mode, and the pre-step narrator — see [Per-session mode](#per-session-mode-switching-and-visibility).
 
 ## Tools
 
@@ -17,6 +17,8 @@ The plugin also contributes the `tool:bash` prompt section (order 105) — the c
 | `timeoutMs` | number | Timeout override in milliseconds. The executor applies its configured default and cap. |
 | `workdir` | string | Working directory for this call. Defaults to the calling agent's session cwd (`session.header.cwd`) so each session runs in its own workspace; a relative `workdir` is resolved against that session cwd. |
 | `run_in_background` | boolean | Return a task id immediately; no timeout applies. |
+| `sandbox_permissions` | string enum | ADVERTISED ONLY when the mounted executor sandboxes (`ctx.bash.sandboxMode` reports a confining default): the wider mode a denied command needs, from the closed target vocabulary `workspace-write`/`danger-full-access` (never cut down to the executor's default — the effective mode is per-session; strict widening is checked at execution against it, and a non-widening request fails without prompting anyone). |
+| `justification` | string | Required together with `sandbox_permissions` (each without the other is a validation error): one sentence for the user explaining why this exact command needs the wider access. |
 
 `command`, `workdir`, and `timeoutMs` are resolved against the executor's config defaults via `ctx.bash.resolve()` before execution, so the executor seam (`BashExecSpec`) receives explicit `workdir`/`timeoutMs` values. The workdir default is applied in the tool layer (from the calling agent's `session.header.cwd`) BEFORE `resolve()` — the per-session cwd must come from `exec.agent`, since N sessions share one executor; only when no session cwd is available does the executor fall back to its own config / `process.cwd()`.
 
@@ -26,11 +28,11 @@ Every foreground and background call made for an agent receives `DSH_SESSION_ID=
 
 The overlay is computed from `ToolExecution.agent` for each call and passed through `BashExecRequest.env`; `process.env` is never modified, so concurrent parent/child agents keep separate values. The tool description names both variables so the model can inspect them without a permanent system-prompt section.
 
-Result text: stdout, then a `[stderr]` section, then status markers — `[timed out after Nms]` whenever the executor's timer fired (reported independently of how the process ended, so a command that traps SIGTERM and exits 0 still shows it), `[killed by signal: …]` for a signal death, `[exit code: N]` for a non-zero exit (reported, **not** `isError`: the model decides how to react), and `[output truncated; full output: <path>]` when the tail was kept and a safe spill file is available. If the executor knows output was dropped but cannot safely advertise a complete spill file, the path is reported as `(unavailable)`. Only infrastructure failures (spawn errors, aborts) surface as `isError` results.
+Result text: stdout, then a `[stderr]` section, then status markers — `[sandbox: file access denied under <mode> mode]` when a sandboxing executor classified the failure as a policy denial (reported first so `[exit code: N]` stays the last line; the static description tells the model a denial is policy, not a command bug, and forbids retrying around it), `[timed out after Nms]` whenever the executor's timer fired (reported independently of how the process ended, so a command that traps SIGTERM and exits 0 still shows it), `[killed by signal: …]` for a signal death, `[exit code: N]` for a non-zero exit (reported, **not** `isError`: the model decides how to react), and `[output truncated; full output: <path>]` when the tail was kept and a safe spill file is available. If the executor knows output was dropped but cannot safely advertise a complete spill file, the path is reported as `(unavailable)`. Only infrastructure failures (spawn errors, aborts) surface as `isError` results.
 
 ### `bash_output`
 
-`task_id` → output produced **since the previous `bash_output` call** plus a status line (`running` / `completed, exit code: N` / `killed`). Reads that lost data to buffer bounds say so and point at the full-output spill file when one is safely available, otherwise `(unavailable)`.
+`task_id` → output produced **since the previous `bash_output` call** plus a status line (`running` / `completed, exit code: N` / `killed`). A settled task classified as a sandbox denial carries the same `[sandbox: file access denied under <mode> mode]` marker on every read that sees it (denials are only classifiable once the whole stderr has been collected). Reads that lost data to buffer bounds say so and point at the full-output spill file when one is safely available, otherwise `(unavailable)`.
 
 ### `bash_kill`
 
@@ -52,6 +54,12 @@ When a background task finishes, a short notice is injected into the owning agen
 
 The `BashExecRequest` seam carries optional `stdin` and `env`, used by trusted consumers. This tool does **not** expose them as model parameters: it builds the request from named schema fields and adds only the session overlay above, so model-supplied `env`/`stdin` keys are ignored and cannot replace the trusted values. This is not a trust boundary — a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), and the real defense against leaking ambient secrets is `dsh-bash-local`'s credential scrub. Regression guards assert extra model fields never enter the request while the trusted overlay still does. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md).
 
-## Permissions
+## Permissions and escalation
 
-`TODO(permissions)`: commands run with the executor's full authority. The permission/sandbox seam is the `tools/pre-execute` waterfall (deny or ask) plus sandboxing `BashExecutor` implementations — see docs/architecture.md. `@cordisjs/plugin-capability` (a named-permission service with a session `test()`) is a candidate building block for that work.
+Commands run with the executor's full authority unless a sandboxing executor ([`dsh-bash-sandbox`](../bash-sandbox/)) confines them — the deny-only sandbox reports denials as result facts, rendered here as the denial marker; per-call allow/deny/ask policy is the `tools/pre-execute` waterfall (see docs/architecture.md).
+
+On top of a denial sits the escalation gate ([the sandbox RFC § Escalation](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)): an escalating call (`sandbox_permissions` + `justification`) resolves [`ctx.approval`](../../ui/user-approval/README.md) BEFORE anything executes — `allowed-once` stamps the granted mode onto the bash request as the seam-level `sandboxMode` override (that one call runs, classifies, and reports under the wider mode; its neighbors keep the session's effective mode), while `rejected`/`cancelled`/`unavailable` and the no-service / no-agent paths each fail closed with their own error text and execute nothing. The seam is consumed opportunistically (`ctx.get('approval')`, the dsh-tools ask-routing pattern); the grant is consumed by the very call that asked, and nothing is stored. The static description teaches — and a denied result itself prompts, via the escalation-available marker appended exactly when the fields are advertised — the SAME-TURN flow: on a denial a wider mode would cure, retry the exact command once with `sandbox_permissions` (the narrowest mode that suffices) + `justification` immediately, without detouring through chat (the approval prompt IS the user's consent); never speculatively — an escalation is grounded in a real denial (up-front only when the session already denied the same access), a prompt-stated approvals-disabled policy turns the exception off entirely, and a rejected escalation is final for that command.
+
+## Per-session mode switching
+
+Under a sandboxing executor this plugin makes the session's standing mode override ([the sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md); the `bash/sandbox-mode` fold owned by [`dsh-bash`](../bash/README.md)) real at EXECUTION: every call is stamped `escalation grant > session override > undefined` onto `BashExecRequest.sandboxMode`; without either, the executor's `resolve()` applies its configured default. Nothing is stamped under a non-sandboxing executor (nothing would honor it) or for an agent-less caller (no session to fold). The prompt deliberately does NOT state the mode and a switch is not narrated: a standing declaration teaches the model to refuse preemptively, while the denial marker already names the mode the command ran under exactly when the boundary is hit — behavior, not belief, carries the state.

packages/bash/tool-bash/package.json

@@ -23,9 +23,11 @@
   "license": "BSD-3-Clause",
   "peerDependencies": {
     "@deepseek-ai/dsh-agent": "^0.0.1",
+    "@deepseek-ai/dsh-user-approval": "^0.0.1",
     "@deepseek-ai/dsh-bash": "^0.0.1",
     "@deepseek-ai/dsh-llm": "^0.0.1",
     "@deepseek-ai/dsh-session-persistence": "^0.0.1",
+    "@deepseek-ai/dsh-sandbox": "^0.0.1",
     "@deepseek-ai/dsh-system-prompt": "^0.0.1",
     "@deepseek-ai/dsh-tools": "^0.0.1",
     "cordis": "^4.0.0-rc.6"
@@ -33,9 +35,13 @@
   "devDependencies": {
     "@deepseek-ai/dsh-agent": "workspace:^",
     "@deepseek-ai/dsh-agent-loop": "workspace:^",
+    "@deepseek-ai/dsh-user-approval": "workspace:^",
     "@deepseek-ai/dsh-bash": "workspace:^",
     "@deepseek-ai/dsh-bash-local": "workspace:^",
+    "@deepseek-ai/dsh-bash-sandbox": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-sandbox": "workspace:^",
+    "@deepseek-ai/dsh-sandbox-local": "workspace:^",
     "@deepseek-ai/dsh-session": "workspace:^",
     "@deepseek-ai/dsh-session-persistence": "workspace:^",
     "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",

packages/bash/tool-bash/src/index.ts

@@ -30,10 +30,27 @@
  * completion landing during the reload gap still drops its one notice — the
  * pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.)
  *
- * TODO(permissions): commands run with the executor's full authority. The
- * permission/sandbox seam is the `tools/pre-execute` waterfall (deny/ask) plus
- * sandboxing `BashExecutor` implementations — see docs/architecture.md
- * § Extending The Harness.
+ * Commands run with the executor's full authority unless a sandboxing
+ * executor (`@deepseek-ai/dsh-bash-sandbox`) confines them; per-call
+ * allow/deny/ask policy is the `tools/pre-execute` waterfall — see
+ * docs/architecture.md § Extension And Composition. Under a sandboxing
+ * executor this plugin also advertises the ESCALATION surface
+ * (`sandbox_permissions`/`justification` — the sandbox RFC § Escalation,
+ * docs/rfc/implemented/feature/2026-07-06-sandbox.md): a command the
+ * sandbox denied may be retried once under a strictly wider mode, resolved
+ * through `ctx.approval` BEFORE anything executes and failing closed on every
+ * unanswerable path. The fields exist only when the mounted executor reports
+ * a confining default (`ctx.bash.sandboxMode`) — a lever is never advertised
+ * that the composition cannot honor.
+ *
+ * Per-session mode switching (the sandbox RFC § Per-session mode switching): a session may carry a
+ * standing sandbox-mode override — the `bash/sandbox-mode` event fold from
+ * `@deepseek-ai/dsh-bash` — which this plugin makes real at EXECUTION: each
+ * call is stamped `escalation grant > session override > executor default`.
+ * The prompt deliberately does NOT state the mode and no switch is narrated:
+ * the model learns the boundary from the denial marker (which names the mode
+ * it ran under) exactly when it matters, instead of preemptively refusing
+ * work a standing declaration would discourage.
  *
  * @module @deepseek-ai/dsh-tool-bash
  */
@@ -41,11 +58,17 @@
 import type { Context } from 'cordis'
 import { isAbsolute, resolve as resolvePath } from 'node:path'
 import { defineTool } from '@deepseek-ai/dsh-tools'
-import type { GenericCallView, TerminalCallView, ToolResult, ToolResultView } from '@deepseek-ai/dsh-tools'
+import type { GenericCallView, TerminalCallView, ToolExecution, ToolResult, ToolResultView } from '@deepseek-ai/dsh-tools'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import type {} from '@deepseek-ai/dsh-session-persistence'
+import { assertNever } from '@deepseek-ai/dsh-llm'
 import type {} from '@deepseek-ai/dsh-system-prompt'
-import { BashTaskId, OwnerToken } from '@deepseek-ai/dsh-bash'
+// Side-effect type import: declaration-merges `ctx.approval`, consumed
+// opportunistically by the escalation gate (`ctx.get('approval')` — the seam
+// stays optional at runtime, same pattern as dsh-tools' ask routing).
+import type {} from '@deepseek-ai/dsh-user-approval'
+import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
+import { BashTaskId, OwnerToken, effectiveSandboxMode } from '@deepseek-ai/dsh-bash'
 import type { BashRunResult, BashTask, CollectedOutput } from '@deepseek-ai/dsh-bash'
 
 export const name = 'tool-bash'
@@ -56,16 +79,12 @@ export const inject = ['tools', 'bash', 'systemPrompt']
  * validates parsed args against the SchemaSpec before `execute` runs (the
  * arg-validation RFC), so type/required/enum checks are already done and `args`
  * is the validated `InferArgs` shape here. What remains are value constraints
- * the DSL has no vocabulary for: non-empty strings and a positive, finite
- * timeout.
+ * the DSL has no vocabulary for: non-empty strings, a positive finite timeout,
+ * and the escalation pairing (`sandbox_permissions` and `justification` travel
+ * together — an approval prompt without a reason, or a reason driving nothing,
+ * is a malformed ask).
  */
-function validateBashArgs(args: {
-  command: string
-  description: string
-  timeoutMs?: number
-  workdir?: string
-  run_in_background?: boolean
-}): void {
+function validateBashArgs(args: BashToolArgs): void {
   if (args.command.trim().length === 0) {
     throw new Error('invalid command: expected a non-empty string')
   }
@@ -75,6 +94,15 @@ function validateBashArgs(args: {
   if (args.timeoutMs !== undefined && (!Number.isFinite(args.timeoutMs) || args.timeoutMs <= 0)) {
     throw new Error(`invalid timeoutMs: expected a positive number, got ${JSON.stringify(args.timeoutMs)}`)
   }
+  if (args.sandbox_permissions !== undefined && args.justification === undefined) {
+    throw new Error('invalid escalation: sandbox_permissions requires a justification')
+  }
+  if (args.justification !== undefined && args.sandbox_permissions === undefined) {
+    throw new Error('invalid escalation: justification is only valid together with sandbox_permissions')
+  }
+  if (args.justification !== undefined && args.justification.trim().length === 0) {
+    throw new Error('invalid justification: expected a non-empty sentence')
+  }
 }
 
 /**
@@ -89,6 +117,77 @@ function validateTaskId(value: string): BashTaskId {
   return BashTaskId(value)
 }
 
+/**
+ * The bash tool's validated argument shape — the base parameters plus the two
+ * escalation fields, which are ADVERTISED only when the mounted executor
+ * reports a confining default mode (absent from the schema otherwise, so the
+ * SchemaSpec validator rejects them before `execute` ever sees one).
+ */
+interface BashToolArgs {
+  command: string
+  description: string
+  timeoutMs?: number
+  workdir?: string
+  run_in_background?: boolean
+  sandbox_permissions?: string
+  justification?: string
+}
+
+/**
+ * The strictly-wider table: what a call whose effective mode is the key may
+ * escalate TO. Checked at EXECUTION, never baked into the schema — the
+ * schema's enum is {@link ESCALATION_TARGETS}, because schemas are
+ * registry-global while the effective mode is per-call truth.
+ */
+const WIDER_MODES: Record<string, readonly SandboxMode[]> = {
+  'read-only': ['workspace-write', 'danger-full-access'],
+  'workspace-write': ['danger-full-access'],
+}
+
+/**
+ * The closed escalation-target vocabulary — every mode a call could ever
+ * escalate TO (`read-only` is the floor; nothing escalates to it). Advertised
+ * whenever the mounted executor confines: cutting the enum down to the modes
+ * wider than the executor's DEFAULT would strand a session whose effective
+ * mode sits below it (a `danger-full-access` default would advertise nothing
+ * while a narrower-switched session stays confined with no lever).
+ */
+const ESCALATION_TARGETS: readonly SandboxMode[] = ['workspace-write', 'danger-full-access']
+
+/**
+ * The bash tool's static description. The base text is byte-stable regardless
+ * of composition (it is part of the pinned snapshot header); the escalation
+ * teaching rides only when the mounted executor actually honors the fields —
+ * it names the ONE sanctioned exception to the base text's "do not retry
+ * another way" rule. Its deference clause ("If the session states approval
+ * prompts are disabled…") points at the approval plugin's never-policy prompt
+ * sentence by meaning, not by parsed wording — a rendezvous kept working by
+ * that sentence continuing to open with the approvals-disabled claim.
+ */
+function bashDescription(escalationModes: readonly SandboxMode[]): string {
+  const base = 'Execute a bash command (`bash -c`) and return its stdout/stderr. '
+    + 'Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — '
+    + 'pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. '
+    + 'The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, '
+    + '`$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. '
+    + 'Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). '
+    + 'Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. '
+    + 'Set `run_in_background: true` for long-running commands: the call returns a task id immediately; '
+    + 'poll it with `bash_output` and stop it with `bash_kill`.'
+  if (escalationModes.length === 0) return base
+  return base + ' Attempting a command the sandbox may deny is safe and expected: run it and read the '
+    + 'marker rather than assuming the denial. When a command IS denied and a wider mode would let it '
+    + 'succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry '
+    + 'the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) '
+    + 'plus a one-sentence `justification`. Do not detour through chat to ask permission first — the '
+    + 'approval prompt raised by that retry IS how the user consents. If the session states approval '
+    + 'prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. '
+    + 'Never escalate speculatively: ground the request in a real denial — normally the one THIS command '
+    + 'just hit; escalating up front is fine only when this session already denied the same access. '
+    + 'A rejected escalation is final for THAT command — stop and explain, never work around '
+    + 'it — but it does not forbid attempting or escalating other commands later.'
+}
+
 /** Append the truncation notice (with the full-output spill path) to a stream's text. */
 function streamText(output: CollectedOutput): string {
   if (!output.truncated) return output.text
@@ -101,9 +200,15 @@ function streamText(output: CollectedOutput): string {
  * errored — the model decides how to react; only infrastructure failures
  * (spawn errors, aborts) surface as isError results.
  * @param result - the completed foreground run from the executor.
+ * @param escalationModes - the escalation targets this composition advertises;
+ *   non-empty adds the same-turn escalation hint after a denial marker
+ *   (default `[]`: no hint).
  * @returns the model-facing text: output body (or `(no output)`), then any timeout/signal/exit markers, each on its own line.
  */
-export function renderResult(result: BashRunResult): string {
+export function renderResult(
+  result: BashRunResult,
+  escalationModes: readonly SandboxMode[] = [],
+): string {
   const out = streamText(result.stdout)
   const err = streamText(result.stderr)
 
@@ -116,6 +221,19 @@ export function renderResult(result: BashRunResult): string {
   if (body.length === 0) body = '(no output)'
 
   const markers: string[] = []
+  // The sandbox marker precedes the exit-status markers so `[exit code: N]`
+  // stays the LAST line (exitStatus() anchors its parse there). Denial is a
+  // reported fact like timeout: the model decides how to react.
+  if (result.sandbox?.denied) {
+    markers.push(`[sandbox: file access denied under ${result.sandbox.mode} mode]`)
+    // The same-turn nudge lives at the decision point: only when this
+    // composition advertises the fields (a lever is never hinted that the
+    // schema does not offer), and inside the sandbox marker family so the
+    // exit-code marker stays the last line.
+    if (escalationModes.length > 0) {
+      markers.push('[sandbox: escalation available — retry this exact command once with sandbox_permissions (the narrowest wider mode that suffices) + justification; the approval prompt asks the user]')
+    }
+  }
   // Timeout is reported independently of how the process actually ended: a
   // command can trap SIGTERM and exit 0 after our timer fired (e.g.
   // `trap "exit 0" TERM; sleep 60`), giving timedOut:true / exitCode:0 /
@@ -372,16 +490,87 @@ export function apply(ctx: Context): void {
     }
   })
 
+  // The escalation surface exists whenever the mounted executor confines.
+  // Its enum is the closed target vocabulary, deliberately NOT cut down by
+  // the configured default: a session may switch to a narrower effective mode
+  // while sharing this globally registered schema. Strict widening therefore
+  // belongs to the per-call check below. An executor swap restarts this fiber
+  // (static inject) and re-registers the schema.
+  const defaultMode = ctx.bash.sandboxMode
+  const escalationModes: readonly SandboxMode[] = defaultMode === undefined ? [] : ESCALATION_TARGETS
+
+  /**
+   * The session's standing mode override for an ordinary (non-escalating)
+   * call: the `bash/sandbox-mode` fold of the calling agent's log, stamped
+   * onto the request so EXECUTION follows the same effective mode the prompt
+   * section states. Weakest precedence — an escalation grant (freshly
+   * approved for exactly this call) outranks it, and without either the
+   * executor's `resolve()` applies its configured default. Undefined for a
+   * non-sandboxing executor (nothing honors it) and for agent-less callers
+   * (no session to fold).
+   */
+  const sessionOverride = (exec: ToolExecution): SandboxMode | undefined =>
+    defaultMode === undefined || exec.agent === undefined ? undefined : effectiveSandboxMode(exec.agent.session.events)
+
+  /**
+   * Resolve a sandbox-escalation request through `ctx.approval` BEFORE
+   * anything executes. Returns the granted mode to stamp onto the bash
+   * request; throws the distinct fail-closed text for every other path (no
+   * service composed, an agent-less execution, a rejection, a cancellation,
+   * an unanswerable ask) — the registry turns the throw into this call's
+   * isError result, and nothing has run. The seam is consumed
+   * opportunistically (`ctx.get`, the dsh-tools ask-routing pattern), so a
+   * deployment without it degrades per call, never at registration.
+   */
+  const approveEscalation = async (mode: string, justification: string, exec: ToolExecution): Promise<SandboxMode> => {
+    // Schema validation only checks ADVERTISED keys, so an unadvertised
+    // `sandbox_permissions` (no sandboxing executor) still reaches execute — reject it here so a
+    // human is never prompted to "escalate" a sandbox that is not there. When
+    // the fields ARE advertised, the registry's SchemaSpec enum has already
+    // pinned `mode` to this ladder for every caller.
+    if (escalationModes.length === 0) {
+      throw new Error('sandbox_permissions is not available in this composition (no sandboxing executor to escalate)')
+    }
+    // Strict widening is an EXECUTION check against the call's effective
+    // mode — session override ?? executor default, the same fold ordinary
+    // calls are stamped with — deliberately not a schema constraint (the
+    // enum is the closed target vocabulary; the effective mode is per-call
+    // truth). A non-widening request fails closed here and never prompts a
+    // human.
+    const effectiveMode = (sessionOverride(exec) ?? defaultMode) as SandboxMode
+    if (!(WIDER_MODES[effectiveMode] ?? []).includes(mode as SandboxMode)) {
+      throw new Error(`sandbox escalation to "${mode}" is not strictly wider than this call's current "${effectiveMode}" mode`)
+    }
+    const approval = ctx.get('approval')
+    if (approval === undefined) {
+      throw new Error(`sandbox escalation to "${mode}" requires approval, but no approval service is composed`)
+    }
+    if (exec.agent === undefined) {
+      throw new Error(`sandbox escalation to "${mode}" requires approval, but the call has no agent to route it through`)
+    }
+    const outcome = await approval.request({
+      agent: exec.agent,
+      toolName: 'bash',
+      callId: exec.callId,
+      // Self-contained for the audit trail: approval/asked stores this
+      // reason, and the target mode is part of the grant's identity.
+      reason: `escalate sandbox to ${mode}: ${justification}`,
+      ...exec.signal ? { signal: exec.signal } : {},
+    })
+    switch (outcome) {
+      // The SchemaSpec enum already pinned `mode` to the closed target
+      // vocabulary; the per-call check above proved it is strictly wider.
+      case 'allowed-once': return mode as SandboxMode
+      case 'rejected': throw new Error(`the user rejected escalating this command to "${mode}"`)
+      case 'cancelled': throw new Error(`approval for escalating to "${mode}" was cancelled`)
+      case 'unavailable': throw new Error(`sandbox escalation to "${mode}" requires approval, but no approval channel is available`)
+      default: return assertNever(outcome, 'ApprovalOutcome')
+    }
+  }
+
   ctx.tools.register(defineTool({
     name: 'bash',
-    description: 'Execute a bash command (`bash -c`) and return its stdout/stderr. '
-      + 'Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — '
-      + 'pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. '
-      + 'The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, '
-      + '`$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. '
-      + 'Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. '
-      + 'Set `run_in_background: true` for long-running commands: the call returns a task id immediately; '
-      + 'poll it with `bash_output` and stop it with `bash_kill`.',
+    description: bashDescription(escalationModes),
     parameters: {
       command: { type: 'string', required: true, description: 'The bash command to execute.' },
       description: {
@@ -394,12 +583,33 @@ export function apply(ctx: Context): void {
       timeoutMs: { type: 'number', description: 'Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry.' },
       workdir: { type: 'string', description: 'Working directory for this command. Defaults to the session workspace; a relative path is resolved against it.' },
       run_in_background: { type: 'boolean', description: 'Run in the background and return a task id immediately. No timeout applies.' },
+      ...escalationModes.length > 0 ? {
+        sandbox_permissions: {
+          type: 'string' as const,
+          enum: [...escalationModes],
+          description: 'The wider sandbox mode this command needs. Only valid as a one-shot retry '
+            + 'of a command the sandbox just denied; requires justification and user approval.',
+        },
+        justification: {
+          type: 'string' as const,
+          description: 'Required with sandbox_permissions: one sentence for the user explaining '
+            + 'why this exact command needs the wider access.',
+        },
+      } : {},
     },
-    async execute(args, exec) {
+    async execute(args: BashToolArgs, exec) {
       validateBashArgs(args)
       // `description` is display/logging metadata only (surfaced to UIs via
       // the tool/call session event); it is intentionally NOT forwarded to
       // ctx.bash and has no effect on execution.
+      // An escalating call resolves approval BEFORE anything executes; every
+      // non-grant outcome throws its distinct error text and runs nothing.
+      // (validateBashArgs pinned the pairing, so the double narrow is exact.)
+      // An ordinary call carries the session's standing override instead —
+      // grant > session override > executor default (see sessionOverride).
+      const sandboxMode = args.sandbox_permissions !== undefined && args.justification !== undefined
+        ? await approveEscalation(args.sandbox_permissions, args.justification, exec)
+        : sessionOverride(exec)
       // Default the workdir to the calling agent's session cwd so each ACP
       // session runs in its own workspace (see resolveWorkdir); an explicit
       // model workdir still wins.
@@ -411,6 +621,7 @@ export function apply(ctx: Context): void {
         ...args.timeoutMs !== undefined ? { timeoutMs: args.timeoutMs } : {},
         ...exec.signal ? { signal: exec.signal } : {},
         ...env !== undefined ? { env } : {},
+        ...sandboxMode !== undefined ? { sandboxMode } : {},
       }
       if (args.run_in_background === true) {
         // Stamp the owner token (the agent's session id) onto the spec so the
@@ -422,7 +633,7 @@ export function apply(ctx: Context): void {
       }
       const result = await ctx.bash.run(ctx.bash.resolve(request))
       if (result.aborted) throw new Error('command aborted')
-      return [{ type: 'text', text: renderResult(result) }]
+      return [{ type: 'text', text: renderResult(result, escalationModes) }]
     },
     presentCall: presentBashCall,
     presentResult: presentBashResult,
@@ -449,6 +660,21 @@ export function apply(ctx: Context): void {
         text += `\n[some output was dropped from memory; full output: ${fullOutput}]`
       }
       text += `\n${statusLine(read.task)}`
+      if (read.task.sandbox?.runnerFailed) {
+        // The sandbox RUNNER itself failed — the command never ran. The
+        // foreground path surfaces this as the structured SANDBOX_UNAVAILABLE
+        // error; a settled task's read carries the marker instead.
+        text += `\n[sandbox: the sandbox runner itself failed under ${read.task.sandbox.mode} mode — the command did not run; this is a sandbox problem, not a command failure]`
+      } else if (read.task.sandbox?.denied) {
+        // Mirrors the foreground result marker (and its same-turn escalation
+        // hint). Background denials are only classifiable once the task
+        // settles (the classifier needs the whole stderr), so the marker
+        // rides every read that sees the settled task.
+        text += `\n[sandbox: file access denied under ${read.task.sandbox.mode} mode]`
+        if (escalationModes.length > 0) {
+          text += '\n[sandbox: escalation available — retry this exact command once with sandbox_permissions (the narrowest wider mode that suffices) + justification; the approval prompt asks the user]'
+        }
+      }
       return Promise.resolve([{ type: 'text', text }])
     },
     presentCall: args => presentTaskCall('Read output from', args),

packages/bash/tool-bash/tests/tools.spec.ts

@@ -1,11 +1,12 @@
-import { mkdtempSync } from 'node:fs'
+import { chmodSync, mkdirSync, mkdtempSync } from 'node:fs'
 import { tmpdir } from 'node:os'
 import { join } from 'node:path'
 import { describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
 import { CallId } from '@deepseek-ai/dsh-llm'
-import { BashExecutor, BashTaskId } from '@deepseek-ai/dsh-bash'
+import { BashExecutor, BashTaskId, setSandboxMode } from '@deepseek-ai/dsh-bash'
 import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskRead, OwnerToken } from '@deepseek-ai/dsh-bash'
+import { Session, SessionId } from '@deepseek-ai/dsh-session'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry from '@deepseek-ai/dsh-tools'
 import AgentRegistry from '@deepseek-ai/dsh-agent'
@@ -13,11 +14,29 @@ import type { Agent } from '@deepseek-ai/dsh-agent'
 import SessionStore from '@deepseek-ai/dsh-session'
 import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
 import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
+import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox'
+import { SandboxProvider } from '@deepseek-ai/dsh-sandbox'
+import type { ConfinedArgv } from '@deepseek-ai/dsh-sandbox'
+import { LocalSandboxProvider } from '@deepseek-ai/dsh-sandbox-local'
+import ApprovalService from '@deepseek-ai/dsh-user-approval'
+import type { ApprovalOutcome } from '@deepseek-ai/dsh-user-approval'
 import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
 import { renderResult } from '@deepseek-ai/dsh-tool-bash'
 
 const spillDir = mkdtempSync(join(tmpdir(), 'dsh-tool-bash-spec-'))
 
+// Pure-config passthrough runner (same knob the snapshot tier uses): skips the
+// profile args up to `--` and execs the command unconfined — deterministic
+// without a host bwrap.
+const PASSTHROUGH_RUNNER = ['bash', '-c', 'while [ "$1" != "--" ]; do shift; done; shift; exec "$@"', 'passthrough-runner']
+const PASSTHROUGH_RUNNER_CONFIG = {
+  runnerCommand: PASSTHROUGH_RUNNER,
+  // The script has no pre-exec failure path; the provider still requires an
+  // explicit dialect so a future script change cannot silently turn runner
+  // failure into an ordinary command result.
+  runnerFailureSignatures: ['passthrough-runner: profile rejected'],
+}
+
 async function setup() {
   const ctx = new Context()
   await ctx.plugin(SystemPrompt)
@@ -102,6 +121,7 @@ class LossyReadBashExecutor extends BashExecutor {
       timeoutMs: request.timeoutMs ?? 0,
       ...request.signal ? { signal: request.signal } : {},
       owner: request.owner,
+      sandboxMode: request.sandboxMode,
     }
   }
 
@@ -896,6 +916,7 @@ describe('the model-facing bash tool builds its request from named args only (no
         ...request.stdin !== undefined ? { stdin: request.stdin } : {},
         ...request.env !== undefined ? { env: request.env } : {},
         owner: request.owner,
+        sandboxMode: request.sandboxMode,
       }
     }
     run(): Promise<BashRunResult> {
@@ -1067,3 +1088,512 @@ describe('the model-facing bash tool builds its request from named args only (no
     expect('owner' in request).toBe(true)
   })
 })
+
+describe('sandbox rendering', () => {
+  const sandboxResult = (denied: boolean, exitCode: number): BashRunResult => ({
+    exitCode,
+    signal: null,
+    timedOut: false,
+    aborted: false,
+    timeoutMs: 1000,
+    stdout: { text: '', truncated: false },
+    stderr: { text: denied ? 'bash: /x: Read-only file system' : 'boom', truncated: false },
+    sandbox: { mode: 'read-only', denied },
+  })
+
+  it('renders a denial marker BEFORE the exit-code marker (the $-anchored parse survives)', () => {
+    const text = renderResult(sandboxResult(true, 1))
+    expect(text).toMatch(/\[sandbox: file access denied under read-only mode\]\n\[exit code: 1\]$/)
+  })
+
+  it('appends the same-turn escalation hint to a denial exactly when the fields are advertised', () => {
+    const hinted = renderResult(sandboxResult(true, 1), ['workspace-write', 'danger-full-access'])
+    expect(hinted).toMatch(
+      /denied under read-only mode\]\n\[sandbox: escalation available — retry this exact command once with sandbox_permissions [^\n]+\]\n\[exit code: 1\]$/, // eslint-disable-line @stylistic/max-len -- the hint sentence is pinned verbatim
+    )
+    // Default (no advertisement): no hint — a lever the schema does not offer is never suggested.
+    expect(renderResult(sandboxResult(true, 1))).not.toContain('escalation available')
+    // A non-denied result never hints, advertised or not.
+    expect(renderResult(sandboxResult(false, 2), ['danger-full-access'])).not.toContain('escalation available')
+  })
+
+  it('renders no sandbox marker for a plain failure under a sandboxed mode', () => {
+    expect(renderResult(sandboxResult(false, 2))).not.toContain('[sandbox:')
+  })
+
+  it('bash_output reports a settled background denial with the same marker', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(LocalSandboxProvider, PASSTHROUGH_RUNNER_CONFIG)
+    await ctx.plugin(SandboxBashExecutor, { graceMs: 200 })
+    const bash = ctx.bash as SandboxBashExecutor
+    bash.internals = { spillDir }
+    await ctx.plugin(ToolBash)
+    const started = await call(ctx, 'bash', { command: 'echo "x: Permission denied" >&2; exit 1', description: 'test command', run_in_background: true })
+    const id = text(started).match(/started background task (bash-\d+)/)![1]
+    await bash.list().find(task => task.id === id)!.done
+    const read = await call(ctx, 'bash_output', { task_id: id })
+    expect(text(read)).toMatch(
+      /\[status: completed, exit code: 1\]\n\[sandbox: file access denied under read-only mode\]\n\[sandbox: escalation available[^\n]+\]$/,
+    )
+  })
+
+  it('a settled background denial renders no escalation hint without a confining executor (defensive arm)', async () => {
+    // Structurally near-unreachable through the real stack — every confining
+    // default advertises the static target set — but the read path guards
+    // it anyway: an executor that reports no sandboxMode (fields never
+    // advertised) whose task nonetheless carries denial facts must render
+    // the marker without suggesting a lever the schema does not offer.
+    class FactsOnlyExecutor extends BashExecutor {
+      private readonly task: BashTask = {
+        id: BashTaskId('bash-facts'),
+        command: 'fake',
+        status: 'completed',
+        exitCode: 1,
+        signal: null,
+        done: Promise.resolve(),
+        sandbox: { mode: 'read-only', denied: true },
+      }
+
+      resolve(request: BashExecRequest): BashExecSpec {
+        return {
+          command: request.command,
+          workdir: request.workdir ?? process.cwd(),
+          timeoutMs: request.timeoutMs ?? 0,
+          ...request.signal ? { signal: request.signal } : {},
+          owner: request.owner,
+          sandboxMode: request.sandboxMode,
+        }
+      }
+
+      run(): Promise<BashRunResult> { return Promise.reject(new Error('not used')) }
+      start(): BashTask { return this.task }
+      get(id: string): BashTask | undefined { return id === this.task.id ? this.task : undefined }
+      list(): BashTask[] { return [this.task] }
+      kill(): boolean { return false }
+      ownerOf(): OwnerToken | undefined { return undefined }
+      readOutput(): BashTaskRead {
+        return { task: this.task, delta: '', lossy: false }
+      }
+    }
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(FactsOnlyExecutor)
+    await ctx.plugin(ToolBash)
+    const read = await call(ctx, 'bash_output', { task_id: 'bash-facts' })
+    expect(text(read)).toMatch(/\[sandbox: file access denied under read-only mode\]$/)
+    expect(text(read)).not.toContain('escalation available')
+  })
+
+  it('bash_output reports a settled background RUNNER failure as a sandbox problem, outranking the denial marker', async () => {
+    // A provider whose wrap carries a runner-failure signature: the settled
+    // task's stderr matching it means the sandbox itself broke and the
+    // command never ran — even though the same stderr also carries denial
+    // words (a runner's error text may contain them).
+    class FakeProvider extends SandboxProvider {
+      confine(argv: readonly string[]): ConfinedArgv {
+        return { argv: [...argv], enforcement: 'full', denialSignatures: ['permission denied'], runnerFailureSignatures: ['fake-runner: '] }
+      }
+    }
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(FakeProvider)
+    await ctx.plugin(SandboxBashExecutor, { graceMs: 200 })
+    const bash = ctx.bash as SandboxBashExecutor
+    bash.internals = { spillDir }
+    await ctx.plugin(ToolBash)
+    const started = await call(ctx, 'bash', { command: 'echo "fake-runner: cannot open rule path: /x: Permission denied" >&2; exit 125', description: 'test command', run_in_background: true })
+    const id = text(started).match(/started background task (bash-\d+)/)![1]
+    await bash.list().find(task => task.id === id)!.done
+    const read = await call(ctx, 'bash_output', { task_id: id })
+    expect(text(read)).toMatch(/\[sandbox: the sandbox runner itself failed under read-only mode — the command did not run; /)
+    expect(text(read)).toMatch(/this is a sandbox problem, not a command failure\]$/)
+    expect(text(read)).not.toContain('file access denied')
+  })
+
+  it('classifies an executable configured runner that refuses its profile before the command runs', async () => {
+    const signature = 'custom-runner-rejected'
+    const ctx = new Context()
+    await ctx.plugin(LocalSandboxProvider, {
+      runnerCommand: ['bash', '-c', `printf '${signature}\\n' >&2; exit 125`, 'custom-runner'],
+      runnerFailureSignatures: [signature],
+    })
+    await ctx.plugin(SandboxBashExecutor, { graceMs: 200 })
+    const bash = ctx.bash as SandboxBashExecutor
+    bash.internals = { spillDir }
+
+    await expect(bash.run(bash.resolve({ command: 'echo command-must-not-run' })))
+      .rejects.toMatchObject({ code: 'SANDBOX_UNAVAILABLE' })
+
+    const task = bash.start(bash.resolve({ command: 'echo command-must-not-run' }))
+    await task.done
+    expect(task.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'full', runnerFailed: true })
+  })
+
+  it('reports a real denial end-to-end through the shipping sandbox executor', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(LocalSandboxProvider, PASSTHROUGH_RUNNER_CONFIG)
+    await ctx.plugin(SandboxBashExecutor, { graceMs: 200 })
+    const bash = ctx.bash as SandboxBashExecutor
+    bash.internals = { spillDir }
+    await ctx.plugin(ToolBash)
+    const lockedDir = join(mkdtempSync(join(tmpdir(), 'dsh-tool-bash-denied-')), 'locked')
+    mkdirSync(lockedDir)
+    chmodSync(lockedDir, 0o555)
+    const result = await call(ctx, 'bash', { command: `echo x > ${lockedDir}/f`, description: 'Write into a locked directory' })
+    expect(result.isError).toBe(false)
+    expect(text(result)).toMatch(
+      /denied under read-only mode\]\n\[sandbox: escalation available[^\n]+\]\n\[exit code: \d+\]$/,
+    )
+  })
+})
+
+describe('sandbox escalation (sandbox_permissions / justification)', () => {
+  /** Compose the real sandbox stack (passthrough runner) at a given default mode. */
+  async function setupSandboxed(mode?: 'read-only' | 'workspace-write' | 'danger-full-access', opts: { approval?: boolean; policy?: 'ask' | 'never' } = {}) {
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(LocalSandboxProvider, PASSTHROUGH_RUNNER_CONFIG)
+    await ctx.plugin(SandboxBashExecutor, { graceMs: 200, ...mode !== undefined ? { mode } : {} })
+    const bash = ctx.bash as SandboxBashExecutor
+    bash.internals = { spillDir }
+    if (opts.approval === true) await ctx.plugin(ApprovalService, opts.policy !== undefined ? { policy: opts.policy } : {})
+    await ctx.plugin(ToolBash)
+    return { ctx, bash }
+  }
+
+  /** The registered bash tool's wire schema (what the model actually sees). */
+  function bashSchema(ctx: Context) {
+    const schema = ctx.tools.schemas().find(s => s.name === 'bash')
+    if (!schema) throw new Error('bash tool not registered')
+    return schema as unknown as { description: string; parameters: { properties: Record<string, { enum?: string[] }> } }
+  }
+
+  /**
+   * A fake agent whose session records appends — the approval audit surface.
+   * Seeded mid-turn: an escalating call always runs inside one, and request()
+   * enforces the enclosure.
+   */
+  function escalationAgent(events: Array<{ type: string; data: Record<string, unknown> }>): Agent {
+    return {
+      id: 'agent-esc',
+      session: {
+        header: { version: 0, id: 'sess-esc', createdAt: 0 },
+        events: [{ type: 'turn/start' }],
+        append: (type: string, data: Record<string, unknown>) => { events.push({ type, data }) },
+      },
+    } as unknown as Agent
+  }
+
+  let escCall = 0
+  function callAs(ctx: Context, agent: Agent | undefined, args: unknown) {
+    return ctx.tools.execute({ callId: CallId(`call-esc-${++escCall}`), name: 'bash', arguments: args, ...agent ? { agent } : {} })
+  }
+
+  const ESCALATE = { command: 'true', description: 'test escalation', sandbox_permissions: 'workspace-write', justification: 'the test needs it' }
+
+  it('advertises no escalation surface under a non-sandboxing executor', async () => {
+    const ctx = await setup()
+    expect(ctx.bash.sandboxMode).toBeUndefined()
+    const schema = bashSchema(ctx)
+    expect(schema.parameters.properties['sandbox_permissions']).toBeUndefined()
+    expect(schema.parameters.properties['justification']).toBeUndefined()
+    expect(schema.description).not.toContain('sanctioned exception')
+  })
+
+  it('advertises the full closed target vocabulary under any confining default', async () => {
+    // The enum is deliberately NOT default-relative: a session's effective
+    // mode is per-session and switchable, so every confining composition
+    // advertises every possible target — strict widening is checked at
+    // execution against the call's effective mode instead.
+    for (const mode of [undefined, 'workspace-write', 'danger-full-access'] as const) {
+      const { ctx } = await setupSandboxed(mode)
+      const schema = bashSchema(ctx)
+      expect(schema.parameters.properties['sandbox_permissions']?.enum).toEqual(['workspace-write', 'danger-full-access'])
+      expect(schema.parameters.properties['justification']).toBeDefined()
+      expect(schema.description).toContain('sanctioned exception')
+    }
+  })
+
+  it('a non-widening request fails at execution with its own text and prompts no one', async () => {
+    const { ctx } = await setupSandboxed('danger-full-access', { approval: true })
+    const consulted = vi.fn()
+    ctx.on('approval/request', (_req, next) => { consulted(); return next() })
+    const result = await callAs(ctx, escalationAgent([]), { command: 'true', description: 'd', sandbox_permissions: 'workspace-write', justification: 'already wider' })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('not strictly wider than this call\'s current "danger-full-access" mode')
+    expect(consulted).not.toHaveBeenCalled()
+  })
+
+  it('rejects sandbox_permissions without a justification, and vice versa, and a blank justification', async () => {
+    const { ctx } = await setupSandboxed()
+    const missing = await callAs(ctx, undefined, { command: 'true', description: 'd', sandbox_permissions: 'workspace-write' })
+    expect(missing.isError).toBe(true)
+    expect(text(missing)).toContain('sandbox_permissions requires a justification')
+    const orphan = await callAs(ctx, undefined, { command: 'true', description: 'd', justification: 'why not' })
+    expect(orphan.isError).toBe(true)
+    expect(text(orphan)).toContain('only valid together with sandbox_permissions')
+    const blank = await callAs(ctx, undefined, { command: 'true', description: 'd', sandbox_permissions: 'workspace-write', justification: '   ' })
+    expect(blank.isError).toBe(true)
+    expect(text(blank)).toContain('expected a non-empty sentence')
+  })
+
+  it('the schema enum rejects a mode outside the target vocabulary before execute (registry-level, any caller)', async () => {
+    const { ctx } = await setupSandboxed()
+    const result = await callAs(ctx, undefined, { command: 'true', description: 'd', sandbox_permissions: 'read-only', justification: 'narrow' })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('must be one of')
+  })
+
+  it('rejects an unadvertised sandbox_permissions injection under a non-sandboxing executor', async () => {
+    const ctx = await setup()
+    const result = await callAs(ctx, undefined, { command: 'true', description: 'd', sandbox_permissions: 'workspace-write', justification: 'sneaky' })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('not available in this composition')
+  })
+
+  it('fails closed with its own text when no approval service is composed', async () => {
+    const { ctx } = await setupSandboxed()
+    const result = await callAs(ctx, escalationAgent([]), ESCALATE)
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('no approval service is composed')
+  })
+
+  it('fails closed with its own text for an agent-less escalating call', async () => {
+    const { ctx } = await setupSandboxed('read-only', { approval: true })
+    const result = await callAs(ctx, undefined, ESCALATE)
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('no agent to route it through')
+  })
+
+  it('fails closed with its own text when the service has no answerer', async () => {
+    const { ctx } = await setupSandboxed('read-only', { approval: true })
+    const result = await callAs(ctx, escalationAgent([]), ESCALATE)
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('no approval channel is available')
+  })
+
+  it('a grant runs THAT call under the wider mode — the denial marker names it — and lands the audit pair', async () => {
+    const { ctx } = await setupSandboxed('read-only', { approval: true })
+    ctx.on('approval/request', () => Promise.resolve<ApprovalOutcome>('allowed-once'))
+    const events: Array<{ type: string; data: Record<string, unknown> }> = []
+    // A real unix denial under the passthrough runner: the marker's mode can
+    // only say workspace-write if the override actually rode the spec.
+    const lockedDir = join(mkdtempSync(join(tmpdir(), 'dsh-esc-denied-')), 'locked')
+    mkdirSync(lockedDir)
+    chmodSync(lockedDir, 0o555)
+    const result = await callAs(ctx, escalationAgent(events), {
+      command: `echo x > ${lockedDir}/f`,
+      description: 'write into a locked directory',
+      sandbox_permissions: 'workspace-write',
+      justification: 'must write outside the workspace',
+    })
+    expect(result.isError).toBe(false)
+    expect(text(result)).toMatch(/\[sandbox: file access denied under workspace-write mode\]/)
+    expect(events.map(e => e.type)).toEqual(['approval/asked', 'approval/decided'])
+    expect(events[0]?.data['toolName']).toBe('bash')
+    expect(events[0]?.data['reason']).toBe('escalate sandbox to workspace-write: must write outside the workspace')
+    expect(events[1]?.data['outcome']).toBe('allowed-once')
+  })
+
+  it('a granted background start settles with the wider mode\'s facts', async () => {
+    const { ctx, bash } = await setupSandboxed('read-only', { approval: true })
+    ctx.on('approval/request', () => Promise.resolve<ApprovalOutcome>('allowed-once'))
+    const started = await callAs(ctx, escalationAgent([]), { ...ESCALATE, run_in_background: true })
+    expect(started.isError).toBe(false)
+    const id = text(started).match(/started background task (bash-\d+)/)?.[1]
+    const task = bash.list().find(t => t.id === id)
+    if (!task) throw new Error('escalated task not tracked')
+    await task.done
+    expect(task.sandbox).toMatchObject({ mode: 'workspace-write', denied: false })
+  })
+
+  it('a rejection denies with the user-said-no text and runs nothing', async () => {
+    const { ctx } = await setupSandboxed('read-only', { approval: true })
+    ctx.on('approval/request', () => Promise.resolve<ApprovalOutcome>('rejected'))
+    // A live (non-aborted) signal rides the execution: the gate threads it
+    // into the approval request so a turn cancellation can withdraw the ask.
+    const result = await ctx.tools.execute({
+      callId: CallId(`call-esc-${++escCall}`),
+      name: 'bash',
+      arguments: ESCALATE,
+      agent: escalationAgent([]),
+      signal: new AbortController().signal,
+    })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('the user rejected escalating this command to "workspace-write"')
+  })
+
+  it('a cancellation denies with the cancelled text', async () => {
+    const { ctx } = await setupSandboxed('read-only', { approval: true })
+    ctx.on('approval/request', () => Promise.resolve<ApprovalOutcome>('cancelled'))
+    const result = await callAs(ctx, escalationAgent([]), ESCALATE)
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('approval for escalating to "workspace-write" was cancelled')
+  })
+
+  it('a rogue approval stand-in returning a non-vocabulary outcome hits the exhaustiveness backstop', async () => {
+    const { ctx } = await setupSandboxed()
+    ctx.provide('approval', { request: () => Promise.resolve('yolo') } as unknown as InstanceType<typeof ApprovalService>)
+    const result = await callAs(ctx, escalationAgent([]), ESCALATE)
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('unreachable')
+  })
+
+  it('a never policy rejects an escalation deterministically without consulting any answerer', async () => {
+    // The live-session e.md case: the model requests escalation against a
+    // 'never' session — the prepend gate answers rejected before any
+    // interactive answerer, the fail-closed text is the ordinary rejection
+    // wording, and the audit pair still lands.
+    const { ctx } = await setupSandboxed('read-only', { approval: true, policy: 'never' })
+    const consulted = vi.fn()
+    ctx.on('approval/request', (_req, next) => { consulted(); return next() })
+    const events: Array<{ type: string; data: Record<string, unknown> }> = []
+    const result = await callAs(ctx, escalationAgent(events), ESCALATE)
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('the user rejected escalating this command to "workspace-write"')
+    expect(consulted).not.toHaveBeenCalled()
+    expect(events.map(e => e.type)).toEqual(['approval/asked', 'approval/decided'])
+    expect(events[1]?.data).toMatchObject({ outcome: 'rejected' })
+  })
+
+  it('a plain call under a sandboxing executor never consults approval', async () => {
+    const { ctx } = await setupSandboxed('read-only', { approval: true })
+    const asked = vi.fn()
+    ctx.on('approval/request', (_req, next) => { asked(); return next() })
+    const result = await callAs(ctx, escalationAgent([]), { command: 'echo plain', description: 'plain run' })
+    expect(result.isError).toBe(false)
+    expect(text(result)).toContain('plain')
+    expect(asked).not.toHaveBeenCalled()
+  })
+})
+
+describe('per-session sandbox mode (the bash/sandbox-mode fold)', () => {
+  /** Compose the real sandbox stack (passthrough runner) at a given default mode. */
+  async function setupModal(mode: 'read-only' | 'workspace-write' | 'danger-full-access' = 'read-only', opts: { approval?: boolean } = {}) {
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(LocalSandboxProvider, PASSTHROUGH_RUNNER_CONFIG)
+    await ctx.plugin(SandboxBashExecutor, { graceMs: 200, mode })
+    ;(ctx.bash as SandboxBashExecutor).internals = { spillDir }
+    if (opts.approval === true) await ctx.plugin(ApprovalService)
+    await ctx.plugin(ToolBash)
+    return ctx
+  }
+
+  /**
+   * An agent stand-in over a REAL Session — the stamping folds real events;
+   * the opened turn satisfies approval's enclosure precondition on escalating
+   * calls.
+   */
+  function sessionAgent(id: string): { agent: Agent; session: Session; injected: string[] } {
+    const session = new Session(SessionId(id))
+    session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
+    const injected: string[] = []
+    const agent = {
+      id,
+      session,
+      inject: (content: { type: string; text: string }[]) => { injected.push(content[0]?.text ?? '') },
+    } as unknown as Agent
+    return { agent, session, injected }
+  }
+
+  let modeCall = 0
+  const callAs = (ctx: Context, agent: Agent | undefined, args: unknown) =>
+    ctx.tools.execute({ callId: CallId(`call-mode-${++modeCall}`), name: 'bash', arguments: args, ...agent ? { agent } : {} })
+
+
+  it('stamps calls with grant > session override > nothing (executor default)', async () => {
+    const ctx = await setupModal('read-only', { approval: true })
+    ctx.on('approval/request', () => Promise.resolve<ApprovalOutcome>('allowed-once'))
+    const seen: (string | undefined)[] = []
+    const original = ctx.bash.resolve.bind(ctx.bash)
+    vi.spyOn(ctx.bash, 'resolve').mockImplementation((req) => {
+      seen.push(req.sandboxMode)
+      return original(req)
+    })
+    const { agent, session } = sessionAgent('sess-stamp-1')
+    const run = { command: 'true', description: 'stamp probe' }
+    await callAs(ctx, agent, run)                       // no override yet
+    setSandboxMode(session, 'workspace-write')
+    await callAs(ctx, agent, run)                       // standing override
+    await callAs(ctx, undefined, run)                   // agent-less caller: no session to fold
+    await callAs(ctx, agent, { ...run, sandbox_permissions: 'danger-full-access', justification: 'grant outranks override' })
+    expect(seen).toEqual([undefined, 'workspace-write', undefined, 'danger-full-access'])
+  })
+
+  it('escalates relative to the session effective mode, not the executor default (narrower override)', async () => {
+    // The blocker scenario: a workspace-write default with a read-only
+    // override — the sensible escalation is workspace-write, which a
+    // default-relative ladder could not even express. The static target
+    // vocabulary advertises it and the execution check accepts it as
+    // strictly wider than the CALL's effective (overridden) mode.
+    const ctx = await setupModal('workspace-write', { approval: true })
+    ctx.on('approval/request', () => Promise.resolve<ApprovalOutcome>('allowed-once'))
+    const seen: (string | undefined)[] = []
+    const original = ctx.bash.resolve.bind(ctx.bash)
+    vi.spyOn(ctx.bash, 'resolve').mockImplementation((req) => {
+      seen.push(req.sandboxMode)
+      return original(req)
+    })
+    const { agent, session } = sessionAgent('sess-esc-narrow')
+    setSandboxMode(session, 'read-only')
+    const result = await callAs(ctx, agent, { command: 'true', description: 'd', sandbox_permissions: 'workspace-write', justification: 'the override is narrower than the default' })
+    expect(result.isError).toBe(false)
+    expect(seen).toEqual(['workspace-write'])
+  })
+
+  it('a danger-full-access default still offers the lever to a narrower-switched session', async () => {
+    // Under the default-relative ladder these fields VANISHED (nothing is
+    // wider than the default), stranding a read-only-overridden session
+    // with no escalation path at all.
+    const ctx = await setupModal('danger-full-access', { approval: true })
+    ctx.on('approval/request', () => Promise.resolve<ApprovalOutcome>('allowed-once'))
+    const schema = ctx.tools.schemas().find(t => t.name === 'bash') as unknown as { parameters: { properties: Record<string, { enum?: string[] }> } }
+    expect(schema.parameters.properties['sandbox_permissions']?.enum).toEqual(['workspace-write', 'danger-full-access'])
+    const { agent, session } = sessionAgent('sess-esc-dfa')
+    setSandboxMode(session, 'read-only')
+    const result = await callAs(ctx, agent, { command: 'true', description: 'd', sandbox_permissions: 'workspace-write', justification: 'confined by override under a wide default' })
+    expect(result.isError).toBe(false)
+  })
+
+  it('rejects a non-widening request against the OVERRIDDEN effective mode without prompting', async () => {
+    const ctx = await setupModal('read-only', { approval: true })
+    const consulted = vi.fn()
+    ctx.on('approval/request', (_req, next) => { consulted(); return next() })
+    const { agent, session } = sessionAgent('sess-esc-nonwide')
+    setSandboxMode(session, 'danger-full-access')
+    const result = await callAs(ctx, agent, { command: 'true', description: 'd', sandbox_permissions: 'workspace-write', justification: 'already wider via override' })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('not strictly wider than this call\'s current "danger-full-access" mode')
+    expect(consulted).not.toHaveBeenCalled()
+  })
+
+  it('never stamps an override under a non-sandboxing executor (nothing honors it)', async () => {
+    const ctx = await setup()
+    const seen: (string | undefined)[] = []
+    const original = ctx.bash.resolve.bind(ctx.bash)
+    vi.spyOn(ctx.bash, 'resolve').mockImplementation((req) => {
+      seen.push(req.sandboxMode)
+      return original(req)
+    })
+    const { agent, session } = sessionAgent('sess-stamp-2')
+    setSandboxMode(session, 'danger-full-access')
+    await callAs(ctx, agent, { command: 'true', description: 'plain probe' })
+    expect(seen).toEqual([undefined])
+  })
+
+})

packages/bash/tool-bash/tsconfig.json

@@ -28,6 +28,15 @@
     },
     {
       "path": "../../bash/bash"
+    },
+    {
+      "path": "../../core/system-prompt"
+    },
+    {
+      "path": "../../ui/user-approval"
+    },
+    {
+      "path": "../../sandbox/sandbox"
     }
   ]
 }

packages/cordis/tool-cordis/src/api-catalog.ts

@@ -56,7 +56,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
     key: 'agentLoop',
     summary: 'The agent-loop plugin (`ctx.agentLoop`): creates ReactLoopAgents, runs their loops, and registers them in `ctx.agents`.',
     methods: [
-      'create(id: AgentId, options: AgentOptions = {}): ReactLoopAgent',
+      'create(id: AgentId, options: AgentOptions = {}, meta: Pick<SessionHeader, \'cwd\'> = {}): ReactLoopAgent',
       'createAgent(options: CreateAgentOptions): AgentHandle',
       'async resume(options: ResumeAgentOptions): Promise<AgentHandle>',
     ],
@@ -73,6 +73,13 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
       'list(): Agent[]',
     ],
   },
+  {
+    key: 'approval',
+    summary: 'The `ctx.approval` service: dispatches ApprovalRequests to the `approval/request` waterfall and audits every ask/outcome pair to the requesting agent\'s session log.',
+    methods: [
+      'async request(req: ApprovalRequest): Promise<ApprovalOutcome>',
+    ],
+  },
   {
     key: 'bash',
     summary: 'Abstract bash execution service.',
@@ -125,6 +132,13 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
       'stream(options: GenerateOptions): AsyncIterable<StreamChunk>',
     ],
   },
+  {
+    key: 'sandbox',
+    summary: 'Abstract process-sandbox service.',
+    methods: [
+      'abstract confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv',
+    ],
+  },
   {
     key: 'sessionPersistence',
     summary: 'Abstract durable session-persistence service.',
@@ -149,6 +163,16 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
       'fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session',
     ],
   },
+  {
+    key: 'skills',
+    summary: 'Registry of skill providers.',
+    methods: [
+      'registerProvider(provider: SkillProvider): () => void',
+      'register(skill: SkillRegistration): () => void',
+      'async list(options: SkillLookupOptions = {}): Promise<SkillSummary[]>',
+      'async get(name: string, options: SkillLookupOptions = {}): Promise<SkillDefinition | undefined>',
+    ],
+  },
   {
     key: 'subagents',
     summary: 'The `subagents` service: a registry of named SubagentProviders and a capability-checked start surface.',
@@ -280,6 +304,12 @@ export const EVENT_API: readonly EventApiEntry[] = [
     signature: '\'agent/turn-continuation\'(agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise<ContinuationDecision>): Promise<ContinuationDecision>',
     summary: 'Waterfall: override the turn-continuation decision via a typed ContinuationDecision.',
   },
+  {
+    name: 'approval/request',
+    mode: 'waterfall',
+    signature: '\'approval/request\'(this: ApprovalService, req: ApprovalRequest, next: () => Promise<ApprovalOutcome>): Promise<ApprovalOutcome>',
+    summary: 'Waterfall asking the composed answerers to decide one approval request.',
+  },
   {
     name: 'fs/edit-intent',
     mode: 'waterfall',
@@ -322,6 +352,18 @@ export const EVENT_API: readonly EventApiEntry[] = [
     signature: '\'session/flush\'(session: Session): Promise<void> | void',
     summary: 'Awaited durability checkpoint.',
   },
+  {
+    name: 'skill/provider-added',
+    mode: 'emit',
+    signature: '\'skill/provider-added\'(provider: SkillProvider): void',
+    summary: 'A skill provider became resolvable in the `ctx.skills` registry.',
+  },
+  {
+    name: 'skill/provider-removed',
+    mode: 'emit',
+    signature: '\'skill/provider-removed\'(name: string): void',
+    summary: 'A skill provider left the registry because its plugin fiber was disposed.',
+  },
   {
     name: 'subagent/end',
     mode: 'emit',
@@ -446,6 +488,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [
     name: 'AgentStatus',
     declaration: 'export type AgentStatus = \'idle\' | \'running\' | \'disposed\';',
   },
+  {
+    name: 'ApprovalOutcome',
+    declaration: 'export type ApprovalOutcome = \'allowed-once\' | \'rejected\' | \'cancelled\' | \'unavailable\';',
+  },
+  {
+    name: 'ApprovalRequest',
+    declaration: 'export interface ApprovalRequest {\n    agent: Agent;\n    toolName: string;\n    callId?: CallId;\n    reason?: string;\n    signal?: AbortSignal;\n}',
+  },
   {
     name: 'AskUserQuestionAnswer',
     declaration: 'export interface AskUserQuestionAnswer {\n    answers: AskUserQuestionAnswerItem[];\n}',
@@ -476,19 +526,23 @@ export const TYPE_API: readonly TypeApiEntry[] = [
   },
   {
     name: 'BashExecRequest',
-    declaration: 'export interface BashExecRequest {\n    command: string;\n    workdir?: string | undefined;\n    timeoutMs?: number | undefined;\n    signal?: AbortSignal | undefined;\n    stdin?: string | undefined;\n    env?: Record<string, string> | undefined;\n    owner?: OwnerToken | undefined;\n}',
+    declaration: 'export interface BashExecRequest {\n    command: string;\n    workdir?: string | undefined;\n    timeoutMs?: number | undefined;\n    signal?: AbortSignal | undefined;\n    stdin?: string | undefined;\n    env?: Record<string, string> | undefined;\n    owner?: OwnerToken | undefined;\n    sandboxMode?: SandboxMode | undefined;\n}',
   },
   {
     name: 'BashExecSpec',
-    declaration: 'export interface BashExecSpec {\n    command: string;\n    workdir: string;\n    timeoutMs: number;\n    signal?: AbortSignal | undefined;\n    stdin?: string | undefined;\n    env?: Record<string, string> | undefined;\n    owner: OwnerToken | undefined;\n}',
+    declaration: 'export interface BashExecSpec {\n    command: string;\n    workdir: string;\n    timeoutMs: number;\n    signal?: AbortSignal | undefined;\n    stdin?: string | undefined;\n    env?: Record<string, string> | undefined;\n    owner: OwnerToken | undefined;\n    sandboxMode: SandboxMode | undefined;\n}',
   },
   {
     name: 'BashRunResult',
-    declaration: 'export interface BashRunResult {\n    exitCode: number | null;\n    signal: NodeJS.Signals | null;\n    timedOut: boolean;\n    aborted: boolean;\n    timeoutMs: number;\n    stdout: CollectedOutput;\n    stderr: CollectedOutput;\n}',
+    declaration: 'export interface BashRunResult {\n    exitCode: number | null;\n    signal: NodeJS.Signals | null;\n    timedOut: boolean;\n    aborted: boolean;\n    timeoutMs: number;\n    stdout: CollectedOutput;\n    stderr: CollectedOutput;\n    sandbox?: BashSandboxInfo;\n}',
+  },
+  {
+    name: 'BashSandboxInfo',
+    declaration: 'export interface BashSandboxInfo {\n    mode: SandboxMode;\n    denied: boolean;\n    enforcement?: SandboxEnforcement;\n    runnerFailed?: boolean;\n}',
   },
   {
     name: 'BashTask',
-    declaration: 'export interface BashTask {\n    readonly id: BashTaskId;\n    readonly command: string;\n    status: BashTaskStatus;\n    exitCode: number | null;\n    signal: NodeJS.Signals | null;\n    readonly done: Promise<void>;\n}',
+    declaration: 'export interface BashTask {\n    readonly id: BashTaskId;\n    readonly command: string;\n    status: BashTaskStatus;\n    exitCode: number | null;\n    signal: NodeJS.Signals | null;\n    readonly done: Promise<void>;\n    sandbox?: BashSandboxInfo;\n}',
   },
   {
     name: 'BashTaskId',
@@ -550,6 +604,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [
     name: 'CompactionResult',
     declaration: 'export interface CompactionResult {\n    startSeq: number;\n    summarySeq: number;\n    endSeq: number;\n    summary: ContentBlock[];\n    shadowedRange: {\n        start: number;\n        end: number;\n    };\n    shadowedSeqs: number[];\n    shadowedTokenCount: number;\n}',
   },
+  {
+    name: 'ConfinedArgv',
+    declaration: 'export interface ConfinedArgv {\n    argv: string[];\n    enforcement: SandboxEnforcement;\n    denialSignatures: readonly string[];\n    runnerFailureSignatures: readonly string[];\n}',
+  },
+  {
+    name: 'ConfinedSandboxMode',
+    declaration: 'export type ConfinedSandboxMode = Exclude<SandboxMode, \'danger-full-access\'>;',
+  },
   {
     name: 'ContentBlockMap',
     declaration: 'export interface ContentBlockMap {\n    \'text\': TextBlock;\n    \'reasoning\': ReasoningBlock;\n    \'tool-call\': ToolCallBlock;\n    \'tool-result\': ToolResultBlock;\n}',
@@ -674,6 +736,18 @@ export const TYPE_API: readonly TypeApiEntry[] = [
     name: 'ResumeAgentOptions',
     declaration: 'export interface ResumeAgentOptions {\n    agentId: AgentId;\n    resumeSessionId: SessionId;\n    agentOptions?: AgentOptions;\n}',
   },
+  {
+    name: 'SandboxEnforcement',
+    declaration: 'export type SandboxEnforcement = \'full\' | \'partial\';',
+  },
+  {
+    name: 'SandboxMode',
+    declaration: 'export type SandboxMode = \'read-only\' | \'workspace-write\' | \'danger-full-access\';',
+  },
+  {
+    name: 'SandboxPolicy',
+    declaration: 'export interface SandboxPolicy {\n    mode: ConfinedSandboxMode;\n    workspaceRoot: string;\n}',
+  },
   {
     name: 'SendOptions',
     declaration: 'export interface SendOptions {\n    source?: MessageSource;\n}',
@@ -706,6 +780,38 @@ export const TYPE_API: readonly TypeApiEntry[] = [
     name: 'SessionLocation',
     declaration: 'export interface SessionLocation {\n    readonly kind: string;\n    readonly path: string;\n}',
   },
+  {
+    name: 'SkillCandidate',
+    declaration: 'export interface SkillCandidate extends SkillSummary {\n    rank: number;\n    locator: unknown;\n    path?: string;\n    metadata?: Record<string, unknown>;\n}',
+  },
+  {
+    name: 'SkillDefinition',
+    declaration: 'export interface SkillDefinition extends SkillSummary {\n    content: string;\n    path?: string;\n    metadata?: Record<string, unknown>;\n}',
+  },
+  {
+    name: 'SkillLookupOptions',
+    declaration: 'export interface SkillLookupOptions {\n    cwd?: string | undefined;\n    signal?: AbortSignal | undefined;\n}',
+  },
+  {
+    name: 'SkillProvider',
+    declaration: 'export interface SkillProvider {\n    name: string;\n    list(options: SkillLookupOptions): Promise<SkillCandidate[]>;\n    get(candidate: SkillCandidate, options: SkillLookupOptions): Promise<SkillDefinition | undefined>;\n}',
+  },
+  {
+    name: 'SkillRegistration',
+    declaration: 'export type SkillRegistration = Omit<SkillDefinition, \'provider\'> & {\n    provider?: string;\n};',
+  },
+  {
+    name: 'SkillResourceBase',
+    declaration: 'export type SkillResourceBase = {\n    kind: \'directory\';\n    path: string;\n} | {\n    kind: \'url\';\n    url: string;\n} | {\n    kind: \'opaque\';\n    description: string;\n};',
+  },
+  {
+    name: 'SkillSource',
+    declaration: 'export type SkillSource = \'project-dsh\' | \'project-agents\' | \'runtime\' | \'user-dsh\' | \'user-agents\' | \'custom\' | (string & {});',
+  },
+  {
+    name: 'SkillSummary',
+    declaration: 'export interface SkillSummary {\n    name: string;\n    description: string;\n    whenToUse?: string;\n    disableModelInvocation?: boolean;\n    source: SkillSource;\n    provider: string;\n    resourceBase?: SkillResourceBase;\n}',
+  },
   {
     name: 'StreamChunk',
     declaration: 'export type StreamChunk = {\n    type: \'block-start\';\n    index: number;\n    blockType: ContentBlockType;\n} | {\n    type: \'text-delta\';\n    index: number;\n    text: string;\n} | {\n    type: \'reasoning-delta\';\n    index: number;\n    text: string;\n} | {\n    type: \'tool-call-delta\';\n    index: number;\n    id: CallId;\n    name?: string;\n    argumentsDelta: string;\n} | {\n    type: \'block-end\';\n    index: number;\n    block: ContentBlock;\n} | {\n    type: \'usage\';\n    usage: TokenUsage;\n} | {\n    type: \'finish\';\n    reason: FinishReason;\n};',

packages/core/README.md

@@ -1,6 +1,6 @@
 # core/ — product API spine
 
-The packages every harness build is assembled from: the session log, the system-prompt assembly, the tool registry, the agent vocabulary, and the one concrete loop that drives them. These are **product** packages — the stable surface plugins and consumers build against.
+The session log, system-prompt assembly, tool registry, agent vocabulary, and concrete loop that form the harness's default control spine. These are **product** packages — the stable surface plugins and consumers build against.
 
 | Package | Role | ctx key |
 |---|---|---|
@@ -9,8 +9,8 @@ The packages every harness build is assembled from: the session log, the system-
 | `tools/` | Tool registry + `tools/pre-execute`/`tools/post-execute` pipeline | `ctx.tools` |
 | `agent/` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` |
 | `agent-loop/` | The concrete loop plugin: `ReactLoopAgent` + the loop driver | `ctx.agentLoop` |
-| `agent-core/` | Bundle plugin: the providerless/executor-less/UI-less spine as code | (loads the spine) |
+| `agent-core/` | Bundle plugin: the default executor-less/UI-less spine as code | (loads the spine) |
 
 `agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop; everything else in `core/` is interface/vocabulary. Plugins depend on the `agent` vocabulary, never on `agent-loop` directly, so the loop stays swappable.
 
-`agent-core` is the composition counterpart: one bundle plugin that loads the whole providerless spine (`timer` + `llm` + sessions + system-prompt + tools + agents + invariants + `tool-bash` + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. App packages (`ui/stdio-agent`, `ui/acp-agent`) consume it and add only a front door; a leaf adds the swappable backends plus any optional product tools it wants to expose. It lives in `core/` because it composes exclusively `core/` + interface packages and ships no provider, executor, or UI of its own.
+`agent-core` is the composition counterpart: one bundle plugin that loads the control spine plus selected default capabilities (`timer` + `llm` + sessions + system-prompt + tools + agents + invariants + the local [skill family](../skill/README.md) + `tool-bash` + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. App packages (`ui/stdio-agent`, `ui/acp-agent`) consume it and add only a front door; a leaf adds the swappable backends plus any optional product tools it wants to expose. It lives in `core/` because it composes the shared control spine while leaving executors, LLM adapters, alternate skill providers, and UI front doors outside the bundle.

packages/core/agent-core/README.md

@@ -1,6 +1,6 @@
 # @deepseek-ai/dsh-agent-core
 
-The **providerless, executor-less, UI-less agent spine** as ONE Cordis bundle plugin. It loads the fixed set of services every harness agent needs and forwards the loop's `agents` list as its own config — so an app package composes a working agent by adding only a front door and the swappable backends.
+The **default executor-less, UI-less agent spine** as ONE Cordis bundle plugin. It loads the fixed set of services every harness agent needs, including the local skill provider, and forwards the loop's `agents` list as its own config — so an app package composes a working agent by adding only a front door and the swappable backends.
 
 This is the package to read to see **the whole plugin tree at once** — the teaching role the inlined `echo-agent` `cordis.yml` used to play before the spine moved behind this bundle.
 
@@ -14,9 +14,12 @@ This is the package to read to see **the whole plugin tree at once** — the tea
 @deepseek-ai/dsh-session          event-sourced session log + store
 @deepseek-ai/dsh-system-prompt    prompt-section + tool-schema assembly
 @deepseek-ai/dsh-tools            tool registry + tools/pre-execute/post-execute
+@deepseek-ai/dsh-skill            skill provider registry
+@deepseek-ai/dsh-skill-local      local filesystem skill provider
 @deepseek-ai/dsh-agent            agent registry + agent/* event vocabulary
 @deepseek-ai/dsh-invariants       dev-mode event-contract assertions
 @deepseek-ai/dsh-tool-bash        the model-facing bash/bash_output/bash_kill schemas
+@deepseek-ai/dsh-tool-skill       session-prefix skill catalog + model-facing loader schema
 @deepseek-ai/dsh-agent-loop       THE concrete loop (gets the forwarded `agents`)
                                   (dsh-system-prompt gets the forwarded `persona`)
 ```
@@ -27,6 +30,7 @@ The spine is everything COMMON to every front door. The swappable and front-door
 
 - **the LLM adapter** — the bundle ships the abstract `llm` service; the leaf registers a concrete adapter on `ctx.llm` (`llm-deepseek`, `llm-pi-ai`, `llm-replay`).
 - **the bash executor** — the bundle ships `tool-bash` (the consumer schema); the leaf provides `ctx.bash` (`bash-local` or a sandboxed impl).
+- **non-local skill providers** — the bundle ships the skill registry, the local filesystem provider, and the `skill` tool; deployments can add other providers such as embedded or remote catalogs as siblings.
 - **presentation + per-app infra** — the stdio UI / ACP bridge, a console logger, `hmr`. These form the coupled "front-door cluster" that the app packages ([`dsh-stdio-agent`](../../ui/stdio-agent/README.md), [`dsh-acp-agent`](../../ui/acp-agent/README.md)) bake in. `timer` is in the spine (common to both, stdout-silent); a console logger is NOT (it writes to stdout, which the ACP bridge reserves for JSON-RPC).
 
 This is the [interface/implementation/consumer seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md) raised to the composition level: the bundle owns the shared spine, the leaf owns the backends, the app package owns the front door.
@@ -35,11 +39,11 @@ This is the [interface/implementation/consumer seam](../../../docs/rfc/implement
 
 ```ts
 import type { Config } from '@deepseek-ai/dsh-agent-core'
-// { agents?, persona?, toolOrder? } — the schema is z.intersect([AgentLoop.Config, SystemPrompt.Config]),
-// so validation and defaulting can never drift from the owners'.
+// { agents?, persona?, toolOrder?, tools?, skills? } — the schema intersects the owner schemas,
+// so validation and defaulting can never drift from the owners.
 ```
 
-The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` to `dsh-system-prompt` (default `''`), the deployment's persona section — and `toolOrder` to `dsh-system-prompt` (absent — lexicographic), the explicit model-facing tool order. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure.
+The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure.
 
 ## Why a code bundle, not a shared YAML include
 

packages/core/agent-core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@deepseek-ai/dsh-agent-core",
-  "description": "The providerless/executor-less/UI-less agent spine as one Cordis bundle plugin (timer + llm + sessions + system-prompt + tools + agents + invariants + tool-bash + agent-loop)",
+  "description": "The default executor-less/UI-less agent spine as one Cordis bundle plugin (timer + llm + sessions + system-prompt + tools + skills + agents + invariants + tool-bash + tool-skill + agent-loop)",
   "version": "0.0.1",
   "private": true,
   "type": "module",
@@ -28,8 +28,11 @@
     "@deepseek-ai/dsh-invariants": "^0.0.1",
     "@deepseek-ai/dsh-llm": "^0.0.1",
     "@deepseek-ai/dsh-session": "^0.0.1",
+    "@deepseek-ai/dsh-skill": "^0.0.1",
+    "@deepseek-ai/dsh-skill-local": "^0.0.1",
     "@deepseek-ai/dsh-system-prompt": "^0.0.1",
     "@deepseek-ai/dsh-tool-bash": "^0.0.1",
+    "@deepseek-ai/dsh-tool-skill": "^0.0.1",
     "@deepseek-ai/dsh-tools": "^0.0.1",
     "cordis": "^4.0.0-rc.6"
   },
@@ -40,8 +43,11 @@
     "@deepseek-ai/dsh-invariants": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",
     "@deepseek-ai/dsh-session": "workspace:^",
+    "@deepseek-ai/dsh-skill": "workspace:^",
+    "@deepseek-ai/dsh-skill-local": "workspace:^",
     "@deepseek-ai/dsh-system-prompt": "workspace:^",
     "@deepseek-ai/dsh-tool-bash": "workspace:^",
+    "@deepseek-ai/dsh-tool-skill": "workspace:^",
     "@deepseek-ai/dsh-tools": "workspace:^",
     "cordis": "^4.0.0-rc.6"
   },

packages/core/agent-core/src/index.ts

@@ -1,10 +1,10 @@
 /**
- * The providerless, executor-less, UI-less agent spine as ONE bundle plugin.
+ * The default executor-less, UI-less agent spine as ONE bundle plugin.
  *
  * Loads the fixed set of services every harness agent needs — `timer`, the LLM
  * service, the session store, system-prompt assembly, the tool registry, the
- * agent registry, the dev-mode invariants, the model-facing `bash` tool
- * schemas, and the concrete `agent-loop` — and forwards the loop's `agents`
+ * skill registry plus local skill provider, the agent registry, the dev-mode
+ * invariants, the model-facing `bash` and `skill` tool schemas, and the concrete `agent-loop` — and forwards the loop's `agents`
  * list as its OWN config (default `[]`), so each app supplies its own
  * pre-created agents.
  *
@@ -19,6 +19,9 @@
  *    (a console logger, `hmr`) — these are the coupled "front-door cluster" the
  *    app packages ({@link @deepseek-ai/dsh-stdio-agent},
  *    {@link @deepseek-ai/dsh-acp-agent}) bake in, NOT the shared spine.
+ *  - additional SKILL PROVIDERS; the bundle ships the local filesystem provider
+ *    because local skills are default agent behavior, while embedded or remote
+ *    providers remain deployment choices.
  *
  * This is the interface/implementation/consumer seam at the composition level:
  * the bundle owns the shared spine, the leaf owns the backends, the app package
@@ -49,24 +52,37 @@ import LlmService from '@deepseek-ai/dsh-llm'
 import SessionStore from '@deepseek-ai/dsh-session'
 import SystemPrompt, { type Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools'
+import SkillService, { type Config as SkillRegistryConfig } from '@deepseek-ai/dsh-skill'
+import * as SkillLocal from '@deepseek-ai/dsh-skill-local'
 import AgentRegistry from '@deepseek-ai/dsh-agent'
 import * as invariants from '@deepseek-ai/dsh-invariants'
 import * as toolBash from '@deepseek-ai/dsh-tool-bash'
+import * as toolSkill from '@deepseek-ai/dsh-tool-skill'
 import AgentLoop, { type Config as AgentLoopConfig } from '@deepseek-ai/dsh-agent-loop'
 
 export const name = 'agent-core'
 
+/** Skill bundle config forwarded to the registry, local provider, and model-facing consumer. */
+export interface SkillConfig {
+  /** Registry-level discovery cache settings. */
+  registry?: SkillRegistryConfig
+  /** Local filesystem skill provider settings. */
+  local?: SkillLocal.Config
+  /** Model-facing skill catalog and tool settings. */
+  tool?: toolSkill.Config
+}
+
 /**
  * Bundle config: each field forwarded verbatim to the child that owns it —
  * `agents` to the agent loop (an app that pre-creates no agents, like the ACP
  * bridge, simply omits it), `persona` and `toolOrder` to the system-prompt
  * plugin (the deployment's persona section and the explicit model-facing tool
- * order), the `tools` object to the tool registry (its presentation `mode`).
- * Every field is optional INPUT here because each owner's schema
- * supplies the default (`[]` / `''` / absent — lexicographic / `native`); the
- * schema is the INTERSECTION of the owners' own schemas (the registry's
- * nested under its `tools` key), so validation and defaulting can never
- * drift from them.
+ * order), the `tools` object to the tool registry (its presentation `mode`),
+ * and `skills` to the skill registry/local provider/tool consumer. Every field
+ * is optional INPUT here because each owner's schema supplies the default;
+ * the schema is the INTERSECTION of the owners' own schemas (with registry
+ * schemas nested under their bundle keys), so validation and defaulting can
+ * never drift from them.
  */
 export interface Config {
   /** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */
@@ -77,10 +93,23 @@ export interface Config {
   toolOrder?: SystemPromptConfig['toolOrder']
   /** The tool registry's config — its presentation `mode` (see dsh-tools' `Config`). */
   tools?: ToolsConfig
+  /** Skill registry, local provider, and model-facing consumer config. */
+  skills?: SkillConfig
 }
 
-/** Intersect the owners' schemas so validation + defaulting stay identical (the registry's nested under `tools`). */
-export const Config = z.intersect([AgentLoop.Config, SystemPrompt.Config, z.object({ tools: ToolRegistry.Config })]) as unknown as z<Config>
+/** The skill config schema exported for app packages that forward `skills`. */
+export const SkillConfigSchema: z<SkillConfig> = z.object({
+  registry: SkillService.Config,
+  local: SkillLocal.Config,
+  tool: toolSkill.Config,
+})
+
+/** Intersect the owners' schemas so validation + defaulting stay identical. */
+export const Config = z.intersect([
+  AgentLoop.Config,
+  SystemPrompt.Config,
+  z.object({ tools: ToolRegistry.Config, skills: SkillConfigSchema }),
+]) as unknown as z<Config>
 
 /**
  * Load the spine. Each `ctx.plugin(...)` mounts one child of the bundle fiber;
@@ -106,8 +135,11 @@ export function apply(ctx: Context, config: Config): void {
     ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {},
   })
   ctx.plugin(ToolRegistry, config.tools ?? {})
+  ctx.plugin(SkillService, config.skills?.registry ?? {})
+  ctx.plugin(SkillLocal, config.skills?.local ?? {})
   ctx.plugin(AgentRegistry)
   ctx.plugin(invariants)
   ctx.plugin(toolBash)
+  ctx.plugin(toolSkill, config.skills?.tool ?? {})
   ctx.plugin(AgentLoop, { agents: config.agents ?? [] })
 }