Merge current master into debug-pangwenjie

# Conflicts:
#	docs/cordis-catalog/events.md
#	docs/core-data-structures/core.md
#	docs/core-data-structures/tools.md
#	docs/event-producer-consumer.md
#	docs/rfc/implemented/feature/2026-06-30-interception-seams.md
#	docs/tool-execution-pipeline.md
#	packages/core/agent-loop/src/agent.ts
#	packages/core/agent-loop/src/loop.ts
#	packages/core/agent-loop/tests/loop.spec.ts
#	packages/core/agent/README.md
#	packages/core/tools/src/index.ts
#	scripts/gen-doc-graphs.ts

.github/workflows/e2e.yml

@@ -110,9 +110,14 @@ jobs:
           fi
           echo "DEEPSEEK_API_KEY present."
 
+      # The e2e suites boot the example bins in `lib` mode (DSH_EXAMPLE_MODE=lib):
+      # the built artifact under plain Node, resolving plugins through real package
+      # exports — the shape a real consumer runs. That requires a prior build.
+      - name: Build (lib for the e2e example bins)
+        run: pnpm run build
+
       # Real-API end-to-end tests only. The keyless gates (lint/typecheck/
-      # coverage/snapshot/build/etc.) already run in ci.yml on every push/PR;
-      # no need to repeat them or build first (tests run unbuilt via tsx).
+      # coverage/snapshot/etc.) already run in ci.yml on every push/PR.
       # DEEPSEEK_BASE_URL is pinned to the external API; the secret is scoped to
       # this step (and preflight) only — never exposed to checkout/setup/install.
       - name: E2E tests (real DeepSeek API)
@@ -120,4 +125,5 @@ jobs:
           DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY_EXTERNAL }}
           DEEPSEEK_BASE_URL: https://api.deepseek.com
           DSH_E2E_MAX_WORKERS: 14
+          DSH_EXAMPLE_MODE: lib
         run: pnpm run test:e2e

.gitignore

@@ -11,6 +11,7 @@ examples/*/*.jsonl
 examples/*/.sessions/
 coverage/
 .doc-typecheck-*/
+.node-next-types-*/
 .humanize/
 tmp/
 .claude/commands/

AGENTS.md

@@ -10,8 +10,9 @@ DeepSeek Harness SDK is a plugin-based agent harness on vendored Cordis: **every
 
 ```
 vendor/      Vendored Cordis source — manifest + sync procedure in vendor/README.md
-packages/    Harness packages at packages/<group>/<pkg>/, all named @deepseek-ai/dsh-<pkg>
+packages/    @deepseek-ai/dsh-<pkg> workspaces at packages/<group>/<pkg>/
   core/        product API spine: session, system-prompt, tools, agent, agent-loop
+  prompt/      workspace instructions
   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
@@ -34,6 +35,7 @@ python/      Python SDK and bundled runtime (see python/README.md)
 examples/    Runnable cordis.yml leaves over packages/examples bundles (see examples/AGENTS.md)
 docs/        architecture, generated catalogs, RFCs, postmortems, cookbook (see docs/AGENTS.md)
 scripts/     repo gates and generators
+website/     VitePress docs site (zh-CN); api/ pages generated from source
 ```
 
 Package groups: [packages/README.md](packages/README.md).
@@ -53,12 +55,17 @@ pnpm run duplication    # cross-file TypeScript clone detection
 pnpm run build          # tsc emits lib/types, tsdown bundles runtime
 pnpm run hygiene        # knip + publint + workspace constraints + NodeNext consumer check
 pnpm run doc-sync       # all documentation gates; see the doc-sync script in package.json
+pnpm run website:build  # VitePress build (doubles as the site's dead-link check)
 pnpm run demo:echo      # mock-model REPL, no key needed
 pnpm run demo:repl      # real REPL coding agent (needs DEEPSEEK_API_KEY)
 pnpm run demo:cordis    # self-referential demo: the agent modifies its own runtime (needs key)
 pnpm run demo:acp       # ACP server agent (needs DEEPSEEK_API_KEY)
 ```
 
+### Host sandbox failures
+
+When required `gh`, `pnpm`, build, test, or generator commands fail because the agent sandbox blocks credentials, network, IPC, file watching, or nested `sandbox-exec`, retry unchanged with the narrowest host escalation before diagnosing authentication or project failure. Require sandbox evidence; never bypass genuine test failures or the product sandbox under test.
+
 ### Run the CI gates locally before marking a PR ready
 
 Run narrow checks during implementation and this CI-equivalent sequence before marking a PR ready. Fresh worktrees need `pnpm run build` before publint and NodeNext inspect `lib/`:
@@ -71,6 +78,7 @@ pnpm run duplication
 pnpm run test:coverage
 pnpm run test:snapshot
 pnpm run doc-sync
+pnpm run website:build
 pnpm run verify-module-graph
 pnpm run build
 pnpm run hygiene
@@ -91,7 +99,7 @@ Real-API tests and demos read `DEEPSEEK_API_KEY`, optional `DEEPSEEK_BASE_URL`,
 ## Conventions
 
 - Every npm package is `@deepseek-ai/dsh-<name>`; vendored packages keep upstream names and are `private: true`. `cordis` is a peerDependency (+ dev) of every harness package.
-- ESM everywhere (`"type": "module"`). Cross-package imports use package names, never relative paths; in-package relative imports use explicit `.ts` extensions. Dev/test/demo run unbuilt via tsx + the root tsconfig `paths` map; builds are for outside consumers only.
+- ESM everywhere (`"type": "module"`). Cross-package imports use package names; in-package relative imports include `.ts`. CI subprocesses that boot examples or Cordis configs run built `lib/` under plain Node; only explicit source-path regressions use tsx ([testing policy](docs/testing.md#test-subprocess-launch-modes)).
 - **Registrations are effects**: every contribution goes through `ctx.effect()` / `ctx.on()`; a registry's `register()` returns the disposer.
 - **Typed events use declaration merging** and merge-extensible maps. Event JSDoc needs `@mode` and payload `@param`; scoped keys absent from payloads need `@dshScopeScan unsupported`. Public service methods document parameters and non-void returns.
 - **Switch on discriminant tags.** Closed unions end in `assertNever`; merge-extensible unions fall through a documented default.

docs/agent-lifecycle.md

@@ -45,6 +45,8 @@ sequenceDiagram
   Driver-->>SDK: <code>agent/status</code> idle
 ```
 
+The `assistant/message` edge records every successful provider call, including content-less and `max-tokens` finishes. Empty content stays out of derived history while the durable anchor retains usage and exact chunk provenance, including an explicit empty source set.
+
 SDK users that need replayable transcript data should consume `session/event`; `agent/*` is the live coordination surface for queue/status, prompt interception, request shaping, steering, continuation, and errors.
 
 Maintenance mode: curated Mermaid sequence; exact event signatures live in the generated Cordis catalog.

docs/architecture.md

@@ -24,6 +24,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service
 | ctx key | Package family | Role |
 |---|---|---|
 | `ctx.llm` | [`llm/`](../packages/llm/README.md) | adapter registry and streaming model calls |
+| `ctx.tokenMeter` | [`llm/token-meter`](../packages/llm/token-meter/README.md) | singleton replay-aware request/surface pressure |
 | `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 |
@@ -35,7 +36,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service
 | `ctx.tasks` | [`tasks/`](../packages/tasks/README.md) | background task registry + generic `task_*` control tools |
 | `ctx.workflows` | [`workflow/`](../packages/workflow/README.md) | script-driven multi-agent orchestration |
 | `ctx.sessionPersistence` | [`session-persistence/`](../packages/session-persistence/README.md) | durable storage for session logs |
-| `ctx.sessionQuery` | [`session-query/`](../packages/session-query/README.md) | live-preferred logical-corpus and exact-event reads |
+| `ctx.sessionQuery` | [`session-query/`](../packages/session-query/README.md) | live-preferred logical-corpus exact reads and relationship traces |
 
 ## Event
 
@@ -43,9 +44,9 @@ Events form the service extension API; see the exhaustive [events catalog](cordi
 
 ### Event Domains
 
-- **Session events** are durable, replayable facts. Turn and step boundaries, user input, assistant output, tool calls, tool results, steering, compaction records, and tool-owned durable facts append to the session log and flow through `session/event`.
-- **Agent events** carry the live `Agent` handle for status, diagnostics, prompt admission, call-config shaping, result validation, and continuation policy.
-- **Capability events** belong to the seam that owns the action. `tools/*`, `llm/*`, `system-prompt/*`, `fs/*`, and `subagent/*` let policy and adapters attach without importing the loop.
+- **Session events** are durable, replayable facts: boundaries, messages, tool activity, steering, compaction, and tool-owned records append to the log and flow through `session/event`.
+- **Agent events** carry the live `Agent` handle for status, diagnostics, prompt admission, request shaping, result validation, and continuation policy.
+- **Capability events** belong to their owning seam; `tools/*`, `llm/*`, `system-prompt/*`, `fs/*`, and `subagent/*` attach policy and adapters without importing the loop.
 
 ### Interception Semantics
 
@@ -53,7 +54,7 @@ Waterfall events behave like around-middleware: a listener delegates by calling
 
 ## Default Loop Lifecycle
 
-The shipped loop drains work, assembles requests, streams model answers, executes tools, applies continuation policy, and checkpoints state. Every pause is a service call or event available to plugins.
+The shipped loop drains work from prompt through checkpoint. Every pause is a service call or event available to plugins.
 
 A **session** is one agent's append-only event log. A **turn** drains one queued batch and runs until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points.
 
@@ -81,7 +82,7 @@ forever:
       agent/request (config only) -> log request/header -> llm/stream (frozen)
         'assistant/chunk'
       agent/step-result
-      'assistant/message'
+      'assistant/message' (transformed content or empty success anchor after step-result rejection)
       each tool call:
         'tool/call'
         tools/pre-execute -> monotonic guards -> tools/execute -> tools/post-execute -> tools/result
@@ -95,23 +96,23 @@ forever:
     checkpoint persistence and notify idle/running status
 ```
 
-The loop renders one prompt assembly per step. Plugins contribute ordered sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn instead of shipping a hole. `dsh-system-prompt` owns the harness identity and default deployment persona; an agent-scoped persona may shadow the default. The loop supplies `model` and `cwd`. See the [prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md).
+Each step assembles ordered prompt sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn. `dsh-system-prompt` owns the harness identity and default persona, which an agent scope may shadow. The loop supplies `model` and `cwd` ([prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)).
 
 Context accepted during tool execution—including async `agent.inject()` notices and post-tool `additionalContext`—waits for settlement, then follows every recorded result. Successful batches preserve call/result adjacency; interrupted batches drain that context before turn closure. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved.
 
 ### Failure Boundaries
 
-The turn is the containment boundary. A throwing listener, adapter error finish, or failed step ends the current turn with an error reason and reports live diagnostics through `agent/error`; it does not kill the driver loop. `cancel()` clears queued and steering work, aborts the active model/tool boundary when possible, and records the appropriate turn end. Disposal stops the loop, awaits quiescence, unregisters the agent, and lets service disposers drain.
+The turn is the containment boundary. A throwing listener, adapter error finish, or failed step ends it with an error reason and reports `agent/error` without killing the driver. `cancel()` clears queued and steering work, aborts the active model/tool boundary when possible, and records the turn end. Disposal stops the loop, awaits quiescence, unregisters the agent, and drains service disposers.
 
-Every session event is turn-enclosed. Reloading a crashed session preserves the interrupted tail and closes it with a synthetic `interrupted` turn end. A failure after the durable turn has closed reports through `agent/error` only because no safe in-turn position remains. A turn ends with one `TurnEndReason` (`completed`, `aborted`, `error`, `disposed`, `max-tokens`, `rejected`, or `interrupted`); per-variant semantics are in [session.md § TurnEndReasonMap](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap).
+Every session event is turn-enclosed. Reloading preserves an interrupted tail and closes it with a synthetic `interrupted` turn end. Failures after durable turn close report only through `agent/error` because no safe in-turn position remains. Each turn has one `TurnEndReason`; [TurnEndReasonMap](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap) owns the variants.
 
 ### Agent Handles
 
-`ctx.agents` owns live agents and returns `AgentHandle { agent, dispose() }`. Plugins drive `Agent` through `send()`, `steer()`, `inject()`, `cancel()`, and `whenIdle()`. The caller fiber and factory provider structurally co-own programmatic lifecycles; the consumer handle is the only other teardown capability, and all owners await one disposer.
+`ctx.agents` owns live agents and returns `AgentHandle { agent, dispose() }`. Plugins drive `Agent` through `send()`, `steer()`, `inject()`, `cancel()`, and `whenIdle()`. The caller fiber and factory provider structurally co-own programmatic lifecycles; the consumer handle is the only other teardown capability. All owners await one disposer.
 
 ### Agent Scope
 
-Every live agent owns a scoped `agent.ctx`. Its registrations shadow same-named globals, receive only that agent's dispatches, and unwind with the agent; async effects such as background-task cleanup are awaited. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. The [semantic-gates RFC](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md) defines typed resolvers that derive carrier checks from merged `Events` signatures and `scopeTarget`, eliminating the handwritten event table. See the [agent-scope RFC](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md); subagent composition controls are documented [separately](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md).
+Every live agent owns a scoped `agent.ctx`. Its registrations shadow globals, receive only that agent's dispatches, and unwind with it; async effects such as background-task cleanup are awaited. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. Typed resolvers derive carrier checks from merged `Events` signatures and `scopeTarget` ([semantic-gates RFC](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md)). See the [agent-scope RFC](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md) and [subagent composition controls](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md).
 
 ## State
 
@@ -125,9 +126,9 @@ Durability is a plugin concern. Persistence backends buffer synchronous `session
 
 ### Model Content
 
-Messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`). The union derives from the merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types are coordinated across adapters, UI bridges, compaction pricing, and persistence, so block types remain a repo-wide contract.
+Messages contain typed blocks (`text`, `reasoning`, `tool-call`, `tool-result`) derived from merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types coordinate adapters, UI bridges, compaction pricing, token metering, and persistence as one repo-wide contract; replay measurement types live in [token-meter.md](core-data-structures/token-meter.md).
 
-Streaming is a raw chunk protocol (`block-start` through `finish`) with `BlockAssembler` as the shared chunk-to-block assembler. The loop logs raw chunks while assembling them for dispatch. `LlmAdapter` is the provider seam: subclass, implement `stream()`, and register with `ctx.llm.registerAdapter(models, adapter)`. StreamChunk conventions live in [llm-streaming.md](core-data-structures/llm-streaming.md).
+Streaming uses raw chunks (`block-start` through `finish`) and `BlockAssembler`. The loop logs and assembles chunks, storing provider/model provenance plus replay state. An `LlmAdapter` implements `stream()`, registers provider routes, and may expose selector metadata; it resolves and validates model ids. Replay state reaches targets only when both routes map to one adapter instance, which owns validation and conversion. The contract lives in [llm-streaming.md](core-data-structures/llm-streaming.md).
 
 ## Extension And Composition
 
@@ -135,11 +136,13 @@ Streaming is a raw chunk protocol (`block-start` through `finish`) with `BlockAs
 
 A swappable capability usually splits into **interface / implementation / consumer**: the interface owns its `ctx` key and events, an implementation registers a backend, and a consumer exposes model behavior through tools or prompts. Bash is the reference; the [capability graph](capability-seams.md) shows every family.
 
-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)).
+Some seams bend the template deliberately: LLM combines interface and consumer because adapters implement it; filesystem wraps provider primitives with policy; web keeps search/fetch provider registries behind one service; skills and subagents use named providers. Subagents spawn fresh, fork a completed-turn prefix, or use ACP children ([subagent.md](core-data-structures/subagent.md)).
+
+`dsh-workspace-context` composes baselines on `agent/session-prefix` and appends `ctx.fs`-discovered nested changes on `tools/post-execute`; its [RFC](rfc/implemented/feature/2026-06-24-workspace-context.md) records isolation. `dsh-paths` owns shared paths.
 
 ### Bundles And Apps
 
-`dsh-agent-spine-demo` is the default composition bundle: one plugin loading the shared spine ([README](../packages/examples/agent-spine-demo/README.md)). App packages compose it with a front door and boot `bin`: `dsh-stdio-demo` for terminal REPL, and `dsh-acp-demo` for ACP over JSON-RPC stdio with no stdout logger ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` instead boots an external `cordis.yml`; the Python SDK injects the package default only when no explicit config channel is set and drives `dsh-jsonrpc` over line-delimited stdio JSON-RPC ([Python SDK](../python/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-spine-demo` bundles the default spine ([README](../packages/examples/agent-spine-demo/README.md)). `dsh-stdio-demo` adds a terminal front door; `dsh-acp-demo` adds stdout-pure ACP over JSON-RPC ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` boots external `cordis.yml`; the Python SDK supplies its default only without an explicit config channel and drives `dsh-jsonrpc` over line-delimited JSON-RPC ([Python SDK](../python/README.md)). Deployments remain thin leaves with swappable backends 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
 

docs/capability-seams.md

@@ -14,6 +14,8 @@ flowchart LR
   pkg_llm_replay["llm-replay"]
   pkg_agent_loop["agent-loop"]
   pkg_compact_basic["compact-basic"]
+  pkg_token_meter["token-meter"]
+  svc_tokenMeter["ctx.tokenMeter<br/>Replay token measurement"]
   pkg_session["session"]
   svc_sessions["ctx.sessions<br/>In-memory session store"]
   pkg_agent["agent"]
@@ -24,8 +26,11 @@ flowchart LR
   svc_sessionPersistence["ctx.sessionPersistence<br/>Durable session persistence seam"]
   pkg_session_persistence_jsonl["session-persistence-jsonl"]
   pkg_session_persistence_sqlite["session-persistence-sqlite"]
+  pkg_tool_bash["tool-bash"]
+  pkg_hooks_claude["hooks-claude"]
+  pkg_hooks_codex["hooks-codex"]
   pkg_acp["acp"]
-  svc_sessionQuery["ctx.sessionQuery<br/>Exact session-history reads"]
+  svc_sessionQuery["ctx.sessionQuery<br/>Exact session-history reads and traces"]
   pkg_system_prompt["system-prompt"]
   svc_systemPrompt["ctx.systemPrompt<br/>System prompt assembly registry"]
   pkg_tools["tools"]
@@ -33,7 +38,6 @@ flowchart LR
   pkg_tool_web["tool-web"]
   svc_tools["ctx.tools<br/>Tool registry and guarded execution pipeline"]
   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"]
@@ -51,8 +55,7 @@ flowchart LR
   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"]
+  svc_bashEnv["ctx.bashEnv<br/>Managed bash environment registry"]
   pkg_sandbox["sandbox"]
   svc_sandbox["ctx.sandbox<br/>Process-sandbox seam"]
   pkg_sandbox_local["sandbox-local"]
@@ -84,6 +87,10 @@ flowchart LR
   pkg_web_search_perplexity["web-search-perplexity"]
   pkg_web_search_deepseek["web-search-deepseek"]
   pkg_web_fetch_local["web-fetch-local"]
+  pkg_spill["spill"]
+  svc_spillStore["ctx.spillStore<br/>Spill storage seam"]
+  pkg_spill_local["spill-local"]
+  pkg_spill_policy["spill-policy"]
   pkg_workflow["workflow"]
   svc_workflows["ctx.workflows<br/>Workflow script engine"]
   pkg_workflow_workerthread["workflow-workerthread"]
@@ -116,6 +123,8 @@ flowchart LR
   pkg_session_query --> svc_sessionQuery
   pkg_skill --> svc_skills
   pkg_skill_local --> svc_skills
+  pkg_spill --> svc_spillStore
+  pkg_spill_local --> svc_spillStore
   pkg_stdio_demo --> svc_userInteraction
   pkg_subagent --> svc_subagents
   pkg_subagent_acp --> svc_subagents
@@ -124,6 +133,8 @@ flowchart LR
   pkg_subagent_spawn --> svc_subagents
   pkg_system_prompt --> svc_systemPrompt
   pkg_tasks --> svc_tasks
+  pkg_token_meter --> svc_tokenMeter
+  pkg_tool_bash --> svc_bashEnv
   pkg_tools --> svc_tools
   pkg_user_interaction --> svc_userInteraction
   pkg_web --> svc_web
@@ -153,7 +164,10 @@ flowchart LR
   svc_sandbox --> pkg_bash_sandbox
   svc_sessionPersistence --> pkg_acp
   svc_sessionPersistence --> pkg_agent_loop
+  svc_sessionPersistence --> pkg_hooks_claude
+  svc_sessionPersistence --> pkg_hooks_codex
   svc_sessionPersistence --> pkg_session_query
+  svc_sessionPersistence --> pkg_tool_bash
   svc_sessions --> pkg_agent
   svc_sessions --> pkg_agent_loop
   svc_sessions --> pkg_invariants
@@ -161,6 +175,7 @@ flowchart LR
   svc_sessions --> pkg_session_query
   svc_sessions --> pkg_subagent_inprocess
   svc_skills --> pkg_tool_skill
+  svc_spillStore --> pkg_spill_policy
   svc_subagents --> pkg_tool_subagent
   svc_systemPrompt --> pkg_agent_loop
   svc_systemPrompt --> pkg_tool_fs
@@ -169,6 +184,7 @@ flowchart LR
   svc_tasks --> pkg_tool_bash
   svc_tasks --> pkg_tool_subagent
   svc_tasks --> pkg_tool_tasks
+  svc_tokenMeter --> pkg_compact_basic
   svc_tools --> pkg_acp
   svc_tools --> pkg_agent_loop
   svc_tools --> pkg_tool_ask_user
@@ -190,9 +206,10 @@ flowchart LR
 | ctx key | Role | Owner | Implementations | Direct consumers | Companion plugins | Note |
 | --- | --- | --- | --- | --- | --- | --- |
 | `ctx.llm` | `seam` | [`llm`](../packages/llm/llm) | [`llm-deepseek`](../packages/llm/llm-deepseek), [`llm-pi-ai`](../packages/llm/llm-pi-ai), [`llm-replay`](../packages/support/llm-replay) | [`agent-loop`](../packages/core/agent-loop), [`compact-basic`](../packages/compact/compact-basic) | - | Adapters register provider implementations; the loop and compaction call the provider-neutral stream service. |
+| `ctx.tokenMeter` | `core` | [`token-meter`](../packages/llm/token-meter) | - | [`compact-basic`](../packages/compact/compact-basic) | - | Owns isolated per-session replay folds; pressure consumers share immutable revisioned measurements. |
 | `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`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), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. |
-| `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads. |
+| `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), [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. |
+| `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads and relationship traces. |
 | `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-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 capabilities, owns Code Mode transport, and routes calls through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation. |
 | `ctx.userInteraction` | `seam` | [`user-interaction`](../packages/ui/user-interaction) | [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | [`tool-ask-user`](../packages/ui/tool-ask-user), [`stdio-demo`](../packages/examples/stdio-demo), [`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. |
@@ -200,6 +217,7 @@ flowchart LR
 | `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-demo`](../packages/examples/stdio-demo), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles and the create/resume factory seam. |
 | `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | - | 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), [`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.bashEnv` | `core` | [`tool-bash`](../packages/bash/tool-bash) | - | - | - | Plugins declare effect-scoped DSH_* facts; tool-bash collects one trusted snapshot per execution and the executor rebuilds the namespace. |
 | `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.permission` | `core` | [`permission`](../packages/ui/permission) | - | [`acp`](../packages/ui/acp) | - | User-facing preset table (`workspace-write`/`danger-full-access`) bundling the sandbox-mode and approval-policy knobs; a switch writes one `permission/preset` event through to both knob events. |
@@ -209,6 +227,7 @@ flowchart LR
 | `ctx.subagents` | `seam` | [`subagent`](../packages/subagent/subagent) | [`subagent-spawn`](../packages/subagent/subagent-spawn), [`subagent-fork`](../packages/subagent/subagent-fork), [`subagent-acp`](../packages/subagent/subagent-acp), [`subagent-mock`](../packages/support/subagent-mock) | [`tool-subagent`](../packages/subagent/tool-subagent) | - | Providers implement transports; tool-subagent exposes one configured provider as a model-facing tool name. |
 | `ctx.tasks` | `core` | [`tasks`](../packages/tasks/tasks) | - | [`tool-bash`](../packages/bash/tool-bash), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-tasks`](../packages/tasks/tool-tasks) | - | Producers (tool-bash background commands, tool-subagent background delegations) register running work; tool-tasks is the model-facing control surface that reads, lists, and kills it. |
 | `ctx.web` | `seam` | [`web`](../packages/web/web) | [`web-search-exa`](../packages/web/web-search-exa), [`web-search-perplexity`](../packages/web/web-search-perplexity), [`web-search-deepseek`](../packages/web/web-search-deepseek), [`web-fetch-local`](../packages/web/web-fetch-local) | [`tool-web`](../packages/web/tool-web) | - | Search and fetch providers register into one ctx.web seam; tool-web owns the stable model-facing names. |
+| `ctx.spillStore` | `seam` | [`spill`](../packages/spill/spill) | [`spill-local`](../packages/spill/spill-local) | [`spill-policy`](../packages/spill/spill-policy) | - | The backend saves oversized tool text and returns a model-facing locator plus retrieval hint; spill-policy is the tools/post-execute consumer that decides when to spill. |
 | `ctx.workflows` | `seam` | [`workflow`](../packages/workflow/workflow) | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | [`tool-workflow`](../packages/workflow/tool-workflow) | - | One engine per context (bash shape, no named-provider registry); the worker-thread engine fans agent() calls out through ctx.subagents. |
 
 Maintenance mode: hybrid: services are discovered from Cordis declarations; interface/implementation/consumer roles are classified in `scripts/gen-doc-graphs.ts` with a completeness guard.

docs/config-catalog.md

@@ -11,11 +11,13 @@ A `Requires:` line lists the service keys the plugin `inject`s: its `cordis.yml`
 
 ## `@deepseek-ai/dsh-acp`
 
-Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInteraction`
+Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInteraction` · `llm` · `systemPrompt`
 
 ```ts config-catalog
 /** Plugin config: the agent template ACP sessions are created from. */
 export interface AcpConfig {
+  /** Provider route for created agents. */
+  provider?: string
   /** Model name for created agents (must have a registered adapter). */
   model?: string
   /** Runtime-only transport override for tests; production uses stdio. */
@@ -25,13 +27,13 @@ export interface AcpConfig {
 
 Depends on: `Stream` (`@agentclientprotocol/sdk`)
 
-Source: [`packages/ui/acp/src/index.ts:203`](../packages/ui/acp/src/index.ts)
+Source: [`packages/ui/acp/src/index.ts:208`](../packages/ui/acp/src/index.ts)
 
 ## `@deepseek-ai/dsh-acp-demo`
 
 ```ts config-catalog
 /**
- * App config: the swappable per-deployment values. `model` configures the
+ * App config: the swappable per-deployment values. `provider` and `model` configure the
  * agent template the ACP bridge creates each session's agent from (NOT a
  * pre-created agent — ACP creates agents at `session/new`); `persona` is the
  * deployment persona (forwarded to the system-prompt plugin); `toolOrder` is
@@ -40,6 +42,8 @@ Source: [`packages/ui/acp/src/index.ts:203`](../packages/ui/acp/src/index.ts)
  * through agent-spine-demo); `persistenceRoot` is the JSONL backend's directory.
  */
 export interface Config {
+  /** Provider route for ACP-created agents. */
+  provider: string
   /** Model name for ACP-created agents (must have a registered adapter). */
   model: string
   /** Deployment persona (the system-prompt plugin's `persona` config). */
@@ -48,8 +52,12 @@ export interface Config {
   toolOrder?: string[]
   /** Tool-registry config — its presentation `mode` (forwarded through agent-spine-demo; see dsh-tools). */
   tools?: ToolsConfig
+  /** DeepSeek Harness home directory exposed to bash and used for local skill discovery. */
+  dshHome?: string
   /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */
   persistenceRoot?: string
+  /** Controls automatic AGENTS.md/CLAUDE.md loading; configure a byte budget or set `false`. */
+  workspaceContext: agentCore.Config['workspaceContext']
   /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-spine-demo. */
   skills?: agentCore.SkillConfig
   /** Model-facing bash tool config forwarded through agent-core. */
@@ -61,7 +69,7 @@ export interface Config {
 
 Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools)
 
-Source: [`packages/examples/acp-demo/src/index.ts:31`](../packages/examples/acp-demo/src/index.ts)
+Source: [`packages/examples/acp-demo/src/index.ts:32`](../packages/examples/acp-demo/src/index.ts)
 
 ## `@deepseek-ai/dsh-agent-loop`
 
@@ -95,14 +103,14 @@ Source: [`packages/core/agent-loop/src/index.ts:322`](../packages/core/agent-loo
  * 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`),
- * and `toolBash`/`toolTasks` to the two model-facing tool plugins this bundle
- * owns. Producer opt-in stays producer-local: `toolBash` configures bash only;
- * future background-capable tools remain independently composed plugins.
- * 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.
+ * `dshHome` to bash environment and local skill discovery, `skills` to the
+ * skill registry/local provider/tool consumer, `workspaceContext` to the
+ * workspace-context loader, and `toolBash`/`toolTasks` to the model-facing tool
+ * plugins this bundle owns. Owner schemas supply defaults for optional input;
+ * workspace context instead requires an explicit byte budget or `false` because
+ * it changes model-visible input. Producer opt-in stays producer-local:
+ * `toolBash` configures bash only; independently composed producers keep their
+ * own config.
  */
 export interface Config {
   /** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */
@@ -113,6 +121,10 @@ export interface Config {
   toolOrder?: SystemPromptConfig['toolOrder']
   /** The tool registry's config — its presentation `mode` (see dsh-tools' `Config`). */
   tools?: ToolsConfig
+  /** DeepSeek Harness home directory shared by shell context and local skill discovery. */
+  dshHome?: string
+  /** Workspace-context loader controls with an explicit byte budget; set `false` for hermetic prompts. */
+  workspaceContext: workspaceContext.Config | false
   /** Skill registry, local provider, and model-facing consumer config. */
   skills?: SkillConfig
   /** Model-facing bash tool config, including this producer's background opt-in. */
@@ -132,9 +144,9 @@ export interface SkillConfig {
 }
 ```
 
-Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts)
+Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts) · [`workspaceContext`](../packages/context/workspace-context/src/index.ts)
 
-Source: [`packages/examples/agent-spine-demo/src/index.ts:55`](../packages/examples/agent-spine-demo/src/index.ts)
+Source: [`packages/examples/agent-spine-demo/src/index.ts:57`](../packages/examples/agent-spine-demo/src/index.ts)
 
 ## `@deepseek-ai/dsh-bash-local`
 
@@ -221,44 +233,29 @@ Source: [`packages/code-runtime/code-runtime-worker/src/index.ts:21`](../package
 
 ## `@deepseek-ai/dsh-compact-basic`
 
-Requires: `llm`
+Requires: `llm` · `tokenMeter`
 
 ```ts config-catalog
-/**
- * Backend configuration. Every knob is REQUIRED except `auto` and
- * `charsPerToken`: there is no concrete data yet to justify default
- * thresholds/budgets, so a consumer must state each value explicitly rather
- * than inherit a guessed default. `auto` alone defaults to `true`
- * (auto-compaction is the intended posture), and `charsPerToken` defaults to
- * the English-text heuristic its estimator was calibrated on.
- */
+/** Basic compaction configuration; every common field has a deployment default. */
 export interface BasicCompactConfig {
-  /** Context window size in tokens. */
-  contextWindow: number
-  /** Compact when estimated token usage exceeds this fraction of context window. */
-  thresholdRatio: number
-  /** Number of tokens of recent context to retain during compaction. */
-  retainTokens: number
-  /** Model to use for summarization (`''` — uses the agent's model). */
-  summarizationModel: string
-  /** Provider generation cap for the summarization call. */
-  maxTokens: number
-  /** Extra compaction attempts when the first compacted surface is still over threshold. */
-  compactionRetries: number
-  /** Enable automatic compaction on the `agent/pre-step` seam (default true). */
+  /** Compact at this fraction of the token meter's context window. Defaults to `0.8`. */
+  thresholdRatio?: number
+  /** Recent surface tokens retained verbatim. Defaults to `floor(contextWindow * 0.16)`. */
+  retainTokens?: number
+  /** Summary provider; `''` resolves the latest routed pair, then the agent pair. Defaults to `''`. */
+  summarizationProvider?: string
+  /** Summary model; `''` resolves the latest routed pair, then the agent pair. Defaults to `''`. */
+  summarizationModel?: string
+  /** Provider generation cap for summarization. Defaults to `8192`. */
+  maxTokens?: number
+  /** Extra attempts after the first compaction when pressure remains above threshold. Defaults to `1`. */
+  compactionRetries?: number
+  /** Enable the automatic `agent/pre-step` pressure listener. Defaults to `true`. */
   auto?: boolean
-  /**
-   * Text density for the token estimator: estimated tokens = chars /
-   * `charsPerToken`. Defaults to 4 (typical English text). A CJK-heavy
-   * deployment should set ~1-2 — CJK runs at roughly 1-2 chars per token, so
-   * the default UNDERestimates several-fold and compaction fires far too late.
-   * May be fractional.
-   */
-  charsPerToken?: number
 }
 ```
 
-Source: [`packages/compact/compact-basic/src/types.ts:20`](../packages/compact/compact-basic/src/types.ts)
+Source: [`packages/compact/compact-basic/src/types.ts:8`](../packages/compact/compact-basic/src/types.ts)
 
 ## `@deepseek-ai/dsh-fs-local`
 
@@ -270,7 +267,7 @@ export interface Config {
 }
 ```
 
-Source: [`packages/fs/fs-local/src/index.ts:35`](../packages/fs/fs-local/src/index.ts)
+Source: [`packages/fs/fs-local/src/index.ts:38`](../packages/fs/fs-local/src/index.ts)
 
 ## `@deepseek-ai/dsh-hooks-claude`
 
@@ -306,7 +303,7 @@ export interface Config {
 }
 ```
 
-Source: [`packages/hooks/hooks-claude/src/index.ts:43`](../packages/hooks/hooks-claude/src/index.ts)
+Source: [`packages/hooks/hooks-claude/src/index.ts:44`](../packages/hooks/hooks-claude/src/index.ts)
 
 ## `@deepseek-ai/dsh-hooks-codex`
 
@@ -331,7 +328,7 @@ export interface Config {
 }
 ```
 
-Source: [`packages/hooks/hooks-codex/src/index.ts:41`](../packages/hooks/hooks-codex/src/index.ts)
+Source: [`packages/hooks/hooks-codex/src/index.ts:42`](../packages/hooks/hooks-codex/src/index.ts)
 
 ## `@deepseek-ai/dsh-jsonrpc`
 
@@ -369,47 +366,70 @@ export interface Config {
   apiKey?: string
   /** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */
   baseURL?: string
-  /** Model names to register (sent verbatim on the wire). */
-  models?: string[]
   /** Thinking-mode default for every request (provider default: enabled). */
   thinking?: 'enabled' | 'disabled'
   /** Thinking effort (only meaningful with thinking enabled). */
   reasoningEffort?: 'high' | 'max'
+  /** Advisory models shown by discovery consumers; defaults to V4 Flash and V4 Pro. */
+  models?: DeepSeekCatalogModel[]
+}
+
+/** One optional model entry advertised by the hand-written adapter. */
+export interface DeepSeekCatalogModel {
+  /** Wire model id accepted by the configured endpoint. */
+  id: string
+  /** Selector label; defaults to {@link id}. */
+  name?: string
+  /** Optional selector detail for deployments with similar model variants. */
+  description?: string
 }
 ```
 
-Source: [`packages/llm/llm-deepseek/src/index.ts:30`](../packages/llm/llm-deepseek/src/index.ts)
+Source: [`packages/llm/llm-deepseek/src/index.ts:36`](../packages/llm/llm-deepseek/src/index.ts)
 
 ## `@deepseek-ai/dsh-llm-pi-ai`
 
 Requires: `llm`
 
 ```ts config-catalog
-/**
- * Plugin config, validated by the same-named schemastery schema. Every field
- * is optional in yml: credentials/endpoint fall back to the environment (a
- * missing API key fails plugin load, not the first call).
- */
+/** Plugin configuration: the non-empty provider profiles this instance owns. */
 export interface Config {
-  /** API key; falls back to $DEEPSEEK_API_KEY. Required one way or the other. */
+  /** Non-empty set of pi-ai provider routes this adapter instance owns. */
+  providers: PiAiProviderProfile[]
+}
+
+/** Configuration for one pi-ai provider route. */
+export interface PiAiProviderProfile {
+  /** pi-ai provider catalog name and Harness route key. */
+  provider: string
+  /** Provider credential; when absent pi-ai uses its provider-native ambient discovery. */
   apiKey?: string
-  /** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */
+  /** Override the selected catalog model's endpoint without changing its protocol metadata. */
   baseURL?: string
-  /** Model names to register (sent verbatim on the wire). */
-  models?: string[]
-  /**
-   * Thinking level for every request: 'off' disables thinking mode; 'high'
-   * and 'xhigh' (wire 'max') set the effort. Omitted = provider default
-   * (thinking enabled), matching llm-deepseek's omission semantics.
-   */
-  reasoning?: PiAiReasoning
+  /** Provider request headers; Harness attribution wins reserved names. */
+  headers?: Record<string, string>
+  /** Provider-neutral pi-ai reasoning level. */
+  reasoning?: ThinkingLevel
+  /** Token budgets used by reasoning providers that support them. */
+  thinkingBudgets?: ThinkingBudgets
+  /** Prompt-cache retention preference. */
+  cacheRetention?: CacheRetention
+  /** Streaming transport preference. */
+  transport?: Transport
+  /** HTTP/provider SDK timeout in milliseconds. */
+  timeoutMs?: number
+  /** WebSocket connection timeout in milliseconds. */
+  websocketConnectTimeoutMs?: number
+  /** Provider SDK retry count. */
+  maxRetries?: number
+  /** Maximum provider-requested retry delay in milliseconds. */
+  maxRetryDelayMs?: number
 }
-
-/** Reasoning levels surfaced by this adapter (DeepSeek wire: high|max). */
-export type PiAiReasoning = 'off' | 'high' | 'xhigh'
 ```
 
-Source: [`packages/llm/llm-pi-ai/src/index.ts:37`](../packages/llm/llm-pi-ai/src/index.ts)
+Depends on: `CacheRetention` (`@earendil-works/pi-ai`) · `ThinkingBudgets` (`@earendil-works/pi-ai`) · `ThinkingLevel` (`@earendil-works/pi-ai`) · `Transport` (`@earendil-works/pi-ai`)
+
+Source: [`packages/llm/llm-pi-ai/src/config.ts:40`](../packages/llm/llm-pi-ai/src/config.ts)
 
 ## `@deepseek-ai/dsh-llm-replay`
 
@@ -428,10 +448,32 @@ export interface Config {
    * a nested-agent scenario; absent/empty for a single-session scenario.
    */
   childFiles?: string[]
+  /** Optional replay-only provider catalog; absent or empty selects catch-all waterfall replay. */
+  providers?: ReplayProviderConfig[]
+}
+
+/** One provider route exposed by the replay adapter. */
+export interface ReplayProviderConfig {
+  /** Provider route used for replay requests. */
+  id: string
+  /** Selector label; defaults to {@link id}. */
+  name?: string
+  /** Advisory models exposed to clients such as ACP editors. */
+  models?: ReplayModelConfig[]
+}
+
+/** One model exposed by a replay-only provider catalog. */
+export interface ReplayModelConfig {
+  /** Model id used for replay requests. */
+  id: string
+  /** Selector label; defaults to {@link id}. */
+  name?: string
+  /** Optional selector description. */
+  description?: string
 }
 ```
 
-Source: [`packages/support/llm-replay/src/index.ts:306`](../packages/support/llm-replay/src/index.ts)
+Source: [`packages/support/llm-replay/src/index.ts:375`](../packages/support/llm-replay/src/index.ts)
 
 ## `@deepseek-ai/dsh-mcp-client`
 
@@ -592,7 +634,7 @@ export interface Config {
 }
 ```
 
-Source: [`packages/session-persistence/session-persistence-jsonl/src/index.ts:23`](../packages/session-persistence/session-persistence-jsonl/src/index.ts)
+Source: [`packages/session-persistence/session-persistence-jsonl/src/index.ts:24`](../packages/session-persistence/session-persistence-jsonl/src/index.ts)
 
 ## `@deepseek-ai/dsh-session-persistence-sqlite`
 
@@ -627,14 +669,14 @@ export interface Config {
 export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist'
 ```
 
-Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:38`](../packages/session-persistence/session-persistence-sqlite/src/index.ts)
+Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:39`](../packages/session-persistence/session-persistence-sqlite/src/index.ts)
 
 ## `@deepseek-ai/dsh-session-query`
 
 Requires: `sessions`
 
 ```ts config-catalog
-/** Configuration for exact session-query reads. */
+/** Configuration for exact session-query reads and traces. */
 export interface Config {
   /** Maximum accepted raw read context on either side. Defaults to 50. */
   readWindowMax?: number
@@ -671,7 +713,41 @@ export interface Config {
 }
 ```
 
-Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-local/src/index.ts)
+Source: [`packages/skill/skill-local/src/index.ts:40`](../packages/skill/skill-local/src/index.ts)
+
+## `@deepseek-ai/dsh-spill-local`
+
+```ts config-catalog
+/** Plugin config (all optional — `static Config` supplies the defaults). */
+export interface Config {
+  /**
+   * Root directory for spill files. Omitted uses a lazily-created private
+   * (0700) per-process directory under the OS temp dir — the safe default for
+   * a local deployment. Set it to keep spill files under a known location.
+   */
+  root?: string
+}
+```
+
+Source: [`packages/spill/spill-local/src/index.ts:22`](../packages/spill/spill-local/src/index.ts)
+
+## `@deepseek-ai/dsh-spill-policy`
+
+Requires: `tools`
+
+```ts config-catalog
+/** Plugin config. */
+export interface Config {
+  /**
+   * The model-facing context cap for a plain-text tool result, in UTF-8 bytes.
+   * Omitted disables the policy entirely (no-op). When set, a result larger than
+   * this is spilled and replaced with a preview derived from this same budget.
+   */
+  maxInlineBytes?: number
+}
+```
+
+Source: [`packages/spill/spill-policy/src/index.ts:45`](../packages/spill/spill-policy/src/index.ts)
 
 ## `@deepseek-ai/dsh-stdio`
 
@@ -694,7 +770,7 @@ Source: [`packages/ui/stdio/src/index.ts:30`](../packages/ui/stdio/src/index.ts)
 ```ts config-catalog
 /**
  * App config: the swappable per-demo values, each routed to where the app wires
- * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through
+ * it. `provider`/`model`/`resumeSessionId` configure the pre-created `main` agent (through
  * {@link @deepseek-ai/dsh-agent-spine-demo}'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);
@@ -703,6 +779,8 @@ Source: [`packages/ui/stdio/src/index.ts:30`](../packages/ui/stdio/src/index.ts)
  * `welcome` is the UI banner.
  */
 export interface Config {
+  /** Provider route for the `main` agent. */
+  provider: string
   /** Model name for the `main` agent (must have a registered adapter). */
   model: string
   /** Deployment persona (the system-prompt plugin's `persona` config). */
@@ -711,6 +789,8 @@ export interface Config {
   toolOrder?: string[]
   /** Tool-registry config — its presentation `mode` (forwarded through agent-spine-demo; see dsh-tools). */
   tools?: ToolsConfig
+  /** DeepSeek Harness home directory exposed to bash and used for local skill discovery. */
+  dshHome?: string
   /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */
   persistenceRoot?: string
   /** stdin-chat banner printed once on start. Defaults to `'ready.'`. */
@@ -727,12 +807,14 @@ export interface Config {
    * (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`).
    */
   resumeSessionId?: string
+  /** Controls automatic AGENTS.md/CLAUDE.md loading; configure a byte budget or set `false`. */
+  workspaceContext: agentCore.Config['workspaceContext']
 }
 ```
 
 Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools)
 
-Source: [`packages/examples/stdio-demo/src/index.ts:36`](../packages/examples/stdio-demo/src/index.ts)
+Source: [`packages/examples/stdio-demo/src/index.ts:37`](../packages/examples/stdio-demo/src/index.ts)
 
 ## `@deepseek-ai/dsh-subagent-acp`
 
@@ -867,33 +949,47 @@ Source: [`packages/core/system-prompt/src/index.ts:143`](../packages/core/system
 
 ## `@deepseek-ai/dsh-time-context`
 
-Requires: `systemPrompt`
+Requires: `agents`
 
 ```ts config-catalog
-/** Request-time clock formatting and refresh policy. Invalid values fail plugin load. */
+/** Request-preparation clock formatting and append scheduling. Invalid values fail plugin load. */
 export interface Config {
   /** IANA time zone used for the rendered timestamp. Omit to resolve the Node process's system zone at plugin load. */
   timeZone?: string
-  /** Maximum age of a reading within one turn, in milliseconds (default 60,000; `0` refreshes every step). */
+  /** Minimum milliseconds between durable injections in one session. Omit or set to 0 to inject on every eligible pre-step attempt. */
   refreshIntervalMs?: number
 }
 ```
 
-Source: [`packages/context/time-context/src/index.ts:22`](../packages/context/time-context/src/index.ts)
+Source: [`packages/context/time-context/src/index.ts:20`](../packages/context/time-context/src/index.ts)
+
+## `@deepseek-ai/dsh-token-meter`
+
+```ts config-catalog
+/** Token-meter plugin configuration. */
+export interface TokenMeterConfig {
+  /** Service-wide context-window capacity in tokens. Defaults to `128000`. */
+  contextWindow?: number
+}
+```
+
+Source: [`packages/llm/token-meter/src/types.ts:10`](../packages/llm/token-meter/src/types.ts)
 
 ## `@deepseek-ai/dsh-tool-bash`
 
 Requires: `tools` · `bash` · `systemPrompt`
 
 ```ts config-catalog
-/** Configures whether the model may background commands. */
+/** Configuration for the bash tool and its managed child environment. */
 export interface Config {
   /** Expose `run_in_background` (default true); disabled calls are also rejected. */
   enableRunInBackground?: boolean
+  /** DeepSeek Harness home directory exposed as `DSH_HOME`; defaults to `$DSH_HOME` or `~/.dsh`. */
+  dshHome?: string
 }
 ```
 
-Source: [`packages/bash/tool-bash/src/index.ts:30`](../packages/bash/tool-bash/src/index.ts)
+Source: [`packages/bash/tool-bash/src/index.ts:39`](../packages/bash/tool-bash/src/index.ts)
 
 ## `@deepseek-ai/dsh-tool-cordis`
 
@@ -933,6 +1029,28 @@ export interface Config {
 
 Source: [`packages/fs/tool-fs/src/index.ts:22`](../packages/fs/tool-fs/src/index.ts)
 
+## `@deepseek-ai/dsh-tool-fs-search`
+
+Requires: `tools` · `systemPrompt` · `bash`
+
+```ts config-catalog
+/** Plugin config (all optional — `Config` supplies the defaults). */
+export interface Config {
+  /** Max paths one `glob` call retains inline; later paths go to the formatted spill file. */
+  globMaxResults?: number
+  /** Max flat matches one `grep` call retains inline; later matches go to the formatted spill file. */
+  grepMaxMatches?: number
+  /** Max bytes retained for one matched-line preview (the cut preserves UTF-8 boundaries). */
+  grepMaxLineBytes?: number
+  /** Max complete raw `rg` stdout bytes a search will parse; larger raw output fails with `SEARCH_RAW_OUTPUT_OVERFLOW`. */
+  rawOutputMaxBytes?: number
+  /** Cooperative tool-call timeout budget (ms) on both tools, enforced by `@deepseek-ai/dsh-timeout-policy` through `exec.signal`. */
+  timeoutMs?: number
+}
+```
+
+Source: [`packages/fs/tool-fs-search/src/index.ts:59`](../packages/fs/tool-fs-search/src/index.ts)
+
 ## `@deepseek-ai/dsh-tool-skill`
 
 Requires: `tools` · `skills`
@@ -1073,7 +1191,7 @@ export interface Config {
 export type ToolPresentationMode = 'native' | 'code' | 'both'
 ```
 
-Source: [`packages/core/tools/src/index.ts:307`](../packages/core/tools/src/index.ts)
+Source: [`packages/core/tools/src/index.ts:322`](../packages/core/tools/src/index.ts)
 
 ## `@deepseek-ai/dsh-user-approval`
 
@@ -1245,6 +1363,26 @@ export interface Config {
 
 Source: [`packages/workflow/workflow-workerthread/src/index.ts:32`](../packages/workflow/workflow-workerthread/src/index.ts)
 
+## `@deepseek-ai/dsh-workspace-context`
+
+```ts config-catalog
+/** User-facing workspace instruction loader configuration. */
+export interface Config {
+  /** Harness home containing the fixed user-global `AGENTS.md`; defaults to `$DSH_HOME` or `~/.dsh`. */
+  dshHome?: string
+  /** Directory entries that identify the project root while walking upward from the session cwd. */
+  projectRootMarkers?: string[]
+  /** UTF-8 byte cap for one rendered baseline or dynamic batch; non-positive or non-finite disables loading. */
+  maxBytes: number
+  /** Maximum UTF-8 bytes read from one instruction file; larger files are ignored. */
+  maxSourceBytes?: number
+  /** Ordered same-directory project candidates; the first existing regular file wins in each scope. */
+  instructionFileCandidates?: string[]
+}
+```
+
+Source: [`packages/context/workspace-context/src/config.ts:16`](../packages/context/workspace-context/src/config.ts)
+
 ## Loadable plugins with no config
 
 These load from a `cordis.yml` entry with no `config:` block; they declare no config surface.
@@ -1271,6 +1409,7 @@ Abstract service classes — a deployment loads a concrete implementation packag
 - `@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-spill` — abstract `SpillStore` ([`packages/spill/spill/src/index.ts`](../packages/spill/spill/src/index.ts))
 - `@deepseek-ai/dsh-workflow` — abstract `WorkflowService` ([`packages/workflow/workflow/src/index.ts`](../packages/workflow/workflow/src/index.ts))
 
 ## Library packages (no plugin entry)
@@ -1279,12 +1418,16 @@ Imported as libraries by other packages; a `cordis.yml` cannot load them.
 
 - `@deepseek-ai/create-sdk` ([`packages/sdk/create-sdk/src/index.ts`](../packages/sdk/create-sdk/src/index.ts))
 - `@deepseek-ai/dsh-acp-snapshot` ([`packages/support/acp-snapshot/src/index.ts`](../packages/support/acp-snapshot/src/index.ts))
+- `@deepseek-ai/dsh-agent-loop-testkit` ([`packages/support/agent-loop-testkit/src/index.ts`](../packages/support/agent-loop-testkit/src/index.ts))
 - `@deepseek-ai/dsh-app-boot` ([`packages/ui/app-boot/src/index.ts`](../packages/ui/app-boot/src/index.ts))
 - `@deepseek-ai/dsh-brand` ([`packages/util/brand/src/index.ts`](../packages/util/brand/src/index.ts))
 - `@deepseek-ai/dsh-helper` ([`packages/sdk/helper/src/index.ts`](../packages/sdk/helper/src/index.ts))
+- `@deepseek-ai/dsh-home` ([`packages/util/home/src/index.ts`](../packages/util/home/src/index.ts))
 - `@deepseek-ai/dsh-hook-protocol` ([`packages/hooks/hook-protocol/src/index.ts`](../packages/hooks/hook-protocol/src/index.ts))
 - `@deepseek-ai/dsh-jsonrpc-demo` ([`packages/examples/jsonrpc-demo/src/index.ts`](../packages/examples/jsonrpc-demo/src/index.ts))
 - `@deepseek-ai/dsh-loader-smoke` ([`packages/support/loader-smoke/src/index.ts`](../packages/support/loader-smoke/src/index.ts))
+- `@deepseek-ai/dsh-paths` ([`packages/util/paths/src/index.ts`](../packages/util/paths/src/index.ts))
+- `@deepseek-ai/dsh-retention` ([`packages/util/retention/src/index.ts`](../packages/util/retention/src/index.ts))
 - `@deepseek-ai/dsh-scope` ([`packages/core/scope/src/index.ts`](../packages/core/scope/src/index.ts))
 - `@deepseek-ai/dsh-scripts` ([`packages/sdk/scripts/src/index.ts`](../packages/sdk/scripts/src/index.ts))
 - `@deepseek-ai/dsh-subagent-inprocess` ([`packages/subagent/subagent-inprocess/src/index.ts`](../packages/subagent/subagent-inprocess/src/index.ts))

docs/cookbook/adding-an-llm-adapter.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-adding-an-llm-adapter.md: 70306ccf119f523dd812a859eef1e8628383bb48
-adding-an-llm-adapter.zh.md: e6d151adfc793a829a876031d5d7280ba078c8e9
+adding-an-llm-adapter.md: f20442b8c2ce823452a3ea13409f202185d12d04
+adding-an-llm-adapter.zh.md: 2864dd1e18742c7449e24f22504a5a38976ab450

docs/cookbook/adding-an-llm-adapter.md

@@ -16,11 +16,11 @@ export const inject = ['llm']
 export const Config: z<Config> = z.object({ apiKey: z.string(), … })
 
 export function apply(ctx: Context, config: Config) {
-  ctx.llm.registerAdapter(['model-a', 'model-b'], new MyAdapter(…))
+  ctx.llm.registerAdapter(['my-provider'], new MyAdapter(…))
 }
 ```
 
-Registration is effect-based (HMR-safe); one adapter per model name — duplicates throw. Secrets are cordis-native: schemastery Config with env fallbacks, fed from cordis.yml via `!!js process.env.MY_KEY`. Never read ad-hoc key files in code.
+Registration is effect-based (HMR-safe); one adapter per provider route — duplicates throw, and multi-route registration is all-or-nothing. `options.provider` selects the adapter and `options.model` is the provider model id, so a dynamic catalog adapter can serve new models without lifecycle reconfiguration. Secrets are cordis-native: schemastery Config with env fallbacks, fed from cordis.yml via `!!js process.env.MY_KEY`. Never read ad-hoc key files in code.
 
 ## Protocol obligations (the contract two implementations verified)
 
@@ -30,6 +30,7 @@ Registration is effect-based (HMR-safe); one adapter per model name — duplicat
 - Errors have exactly two sanctioned paths: THROW from `stream()` (transport and protocol failures — use `LlmError` with a stable code), or end the stream with `finish {kind: 'error' | 'aborted'}` (provider in-band failures). Consumers handle both; pick per failure class and document it.
 - Honor `options.signal` (pass it to fetch / your SDK).
 - A `GenerateOptions` field your provider cannot honor (e.g. a `stop` list on a provider without stop sequences): throw `LlmError(..., 'UNSUPPORTED')` rather than silently dropping it.
+- If the provider requires response ids, signatures, or other native metadata on follow-up calls, emit the minimal lossless-JSON projection as `finish.replayState`. Validate it when rebuilding history. `LlmService` passes it only when the historical provider route and target provider route are currently owned by the exact same adapter instance; your adapter decides whether same-model, cross-model, or cross-provider restoration is legal. Never infer native replay from provider/model names alone when state is absent.
 
 Provider-specific request knobs (thinking modes, effort levels) belong in the ADAPTER's Config, not in `GenerateOptions` — the core vocabulary stays provider-neutral.
 
@@ -41,5 +42,5 @@ Split the adapter into testable stages (llm-deepseek's layout): wire types (`typ
 
 - **Unit: mock the provider, not the harness.** A scripted `node:http` server speaking the provider's wire format covers happy paths, every error status, malformed payloads, premature closes, and aborts — no network, and it drives the 100% per-file coverage gate. Works for SDK-backed adapters too (point the SDK's baseURL at the mock).
 - **Hostile framing tests.** Split stream payloads at arbitrary byte positions (including mid-UTF-8) — real networks do.
-- **E2E: `tests/*.e2e.ts`** under `pnpm run test:e2e`, gated with `describe.skipIf(!process.env.MY_KEY)` so CI (no secrets) stays green. Cover each model × each provider mode you map (thinking on/off, effort levels), a tool-call round trip INCLUDING the follow-up turn with results in history, and loose assertions only (substring/structure, bounded maxTokens — real models are nondeterministic).
+- **E2E: `tests/*.e2e.ts`** under `pnpm run test:e2e`, gated with `describe.skipIf(!process.env.MY_KEY)` so CI (no secrets) stays green. Cover representative model/provider/API families and every provider mode you map, a tool-call round trip INCLUDING the follow-up turn with results in history, and loose assertions only (substring/structure, bounded maxTokens — real models are nondeterministic).
 - Register the e2e file pattern in `knip.json` (per-workspace `entry` override) or knip flags it unused.

docs/cookbook/adding-an-llm-adapter.zh.md

@@ -16,11 +16,11 @@ export const inject = ['llm']
 export const Config: z<Config> = z.object({ apiKey: z.string(), … })
 
 export function apply(ctx: Context, config: Config) {
-  ctx.llm.registerAdapter(['model-a', 'model-b'], new MyAdapter(…))
+  ctx.llm.registerAdapter(['my-provider'], new MyAdapter(…))
 }
 ```
 
-注册基于副作用（HMR 安全）；每个模型名称对应一个适配器，重复注册会抛出异常。密钥采用 Cordis 原生方式管理：schemastery Config 带环境变量回退，通过 cordis.yml 的 `!!js process.env.MY_KEY` 注入。代码中禁止临时读取密钥文件。
+注册基于副作用（HMR 安全）；每个提供方路由仅对应一个适配器，重复注册会抛出异常，多路由注册要么全部成功，要么全部失败。`options.provider` 用于选择适配器，`options.model` 是提供方模型 ID，因此动态模型目录适配器无需重新配置生命周期即可提供新模型。密钥采用 Cordis 原生方式管理：schemastery Config 带环境变量回退，通过 cordis.yml 的 `!!js process.env.MY_KEY` 注入。代码中禁止临时读取密钥文件。
 
 ## 协议义务（两个实现共同验证的契约）
 
@@ -30,6 +30,7 @@ export function apply(ctx: Context, config: Config) {
 - 错误有且仅有两条合法路径：从 `stream()` **抛出**（传输与协议故障——使用带稳定 code 的 `LlmError`），或以 `finish {kind: 'error' | 'aborted'}` 结束流（提供方带内故障）。消费方两者都处理；按故障类别选择路径并加以文档化。
 - 遵守 `options.signal`（将其传递给 fetch 或你的 SDK）。
 - 如果 `GenerateOptions` 中某个字段你的提供方无法支持（例如提供方不支持 stop sequences 时收到 `stop` 列表）：抛出 `LlmError(..., 'UNSUPPORTED')`，而非静默丢弃。
+- 如果提供方在后续调用中需要响应 ID、签名或其他原生元数据，请将其最小无损 JSON 投影作为 `finish.replayState` 发出。重建历史时验证该状态。只有历史提供方路由和目标提供方路由当前由完全相同的适配器实例拥有时，`LlmService` 才会传递该状态；由适配器决定同模型、跨模型或跨提供方恢复是否合法。状态缺失时，切勿仅根据提供方/模型名称推断原生回放。
 
 提供方特有的请求旋钮（thinking 模式、effort 级别）放在**适配器**的 Config 中，而非 `GenerateOptions` 中——核心词汇保持提供方无关。
 
@@ -41,5 +42,5 @@ export function apply(ctx: Context, config: Config) {
 
 - **单元测试：mock 提供方，而非 harness。** 用脚本化的 `node:http` 服务器模拟提供方的协议格式，覆盖正常路径、所有错误状态码、畸形载荷、连接提前关闭和中止——无需网络，且能满足 100% 逐文件覆盖率门禁。对基于 SDK 的适配器同样适用（将 SDK 的 baseURL 指向 mock 服务器）。
 - **恶意分帧测试。** 在任意字节位置（包括 UTF-8 字符中间）切割流载荷——真实网络环境正是如此。
-- **E2E：`tests/*.e2e.ts`**，通过 `pnpm run test:e2e` 运行，以 `describe.skipIf(!process.env.MY_KEY)` 守卫，确保无密钥的 CI 保持绿色。覆盖你映射的每个模型 × 每种提供方模式（thinking 开/关、effort 级别）、一次包含后续轮次（历史中带工具结果）的工具调用往返，以及仅做宽松断言（子串/结构匹配、有界的 maxTokens——真实模型是非确定性的）。
+- **E2E：`tests/*.e2e.ts`**，通过 `pnpm run test:e2e` 运行，以 `describe.skipIf(!process.env.MY_KEY)` 守卫，确保无密钥的 CI 保持绿色。覆盖具有代表性的模型/提供方/API 系列以及你映射的每种提供方模式、一次包含后续轮次（历史中带工具结果）的工具调用往返，以及仅做宽松断言（子串/结构匹配、有界的 maxTokens——真实模型是非确定性的）。
 - 在 `knip.json` 中注册 e2e 文件模式（per-workspace `entry` 覆盖），否则 knip 会将其标记为未使用。

docs/cordis-catalog/events.md

@@ -23,7 +23,7 @@ A fully configured agent and live session were published. Setup is composition-o
 
 Types: [Agent](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:140`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:154`](../../packages/core/agent/src/types.ts)
 
 ### `agent/disposed` — emit
 
@@ -35,7 +35,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence but bef
 
 Types: [Agent](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:149`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:163`](../../packages/core/agent/src/types.ts)
 
 ### `agent/error` — emit
 
@@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w
 
 Types: [Agent](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:284`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:298`](../../packages/core/agent/src/types.ts)
 
 ### `agent/pre-step` — serial
 
@@ -59,7 +59,7 @@ Awaited serial checkpoint for session-surface mutation after prompt assembly and
 
 Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:203`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:217`](../../packages/core/agent/src/types.ts)
 
 ### `agent/prompt-submit` — waterfall
 
@@ -71,7 +71,7 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca
 
 Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:213`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:227`](../../packages/core/agent/src/types.ts)
 
 ### `agent/queued` — emit
 
@@ -83,7 +83,7 @@ Detached, frozen content entered the agent's inbox. Source defaults have already
 
 Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:168`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:182`](../../packages/core/agent/src/types.ts)
 
 ### `agent/request` — waterfall
 
@@ -95,7 +95,7 @@ Replace the frozen call configuration. Model-visible content must use logged cha
 
 Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:225`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:239`](../../packages/core/agent/src/types.ts)
 
 ### `agent/session-prefix` — waterfall
 
@@ -107,7 +107,7 @@ Compose request-only messages placed before derived history. The frozen result i
 
 Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:240`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:254`](../../packages/core/agent/src/types.ts)
 
 ### `agent/session-start` — emit
 
@@ -119,7 +119,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to
 
 Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:181`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:195`](../../packages/core/agent/src/types.ts)
 
 ### `agent/status` — emit
 
@@ -131,7 +131,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no
 
 Types: [Agent](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:158`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:172`](../../packages/core/agent/src/types.ts)
 
 ### `agent/step-result` — waterfall
 
@@ -143,7 +143,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va
 
 Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:251`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:265`](../../packages/core/agent/src/types.ts)
 
 ### `agent/turn-continuation` — waterfall
 
@@ -155,7 +155,7 @@ Override whether the turn continues. The default continues after tool calls or s
 
 Types: [Agent](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:261`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:275`](../../packages/core/agent/src/types.ts)
 
 ### `agent/turn-stop` — serial
 
@@ -167,7 +167,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a
 
 Types: [Agent](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:271`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:285`](../../packages/core/agent/src/types.ts)
 
 ## `approval/*`
 
@@ -195,7 +195,7 @@ Single-slot decision for the next FileSystem.editText. Calling `next()` yields a
 
 Types: [FsTarget](../core-data-structures/filesystem.md) · [FsVersion](../core-data-structures/filesystem.md)
 
-Source: [`packages/fs/fs/src/index.ts:59`](../../packages/fs/fs/src/index.ts)
+Source: [`packages/fs/fs/src/index.ts:61`](../../packages/fs/fs/src/index.ts)
 
 ### `fs/observed` — emit
 
@@ -207,7 +207,7 @@ Record a successful observation. Listeners must be synchronous recorders: throws
 
 Types: [FsTarget](../core-data-structures/filesystem.md) · [FsVersion](../core-data-structures/filesystem.md)
 
-Source: [`packages/fs/fs/src/index.ts:68`](../../packages/fs/fs/src/index.ts)
+Source: [`packages/fs/fs/src/index.ts:70`](../../packages/fs/fs/src/index.ts)
 
 ### `fs/write-intent` — waterfall
 
@@ -219,7 +219,7 @@ Single-slot decision for the next FileSystem.writeText. Calling `next()` yields
 
 Types: [FsTarget](../core-data-structures/filesystem.md) · [FsWriteIntent](../core-data-structures/filesystem.md)
 
-Source: [`packages/fs/fs/src/index.ts:51`](../../packages/fs/fs/src/index.ts)
+Source: [`packages/fs/fs/src/index.ts:53`](../../packages/fs/fs/src/index.ts)
 
 ## `llm/*`
 
@@ -233,7 +233,7 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t
 
 Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md)
 
-Source: [`packages/llm/llm/src/index.ts:39`](../../packages/llm/llm/src/index.ts)
+Source: [`packages/llm/llm/src/index.ts:40`](../../packages/llm/llm/src/index.ts)
 
 ## `session/*`
 
@@ -245,7 +245,7 @@ Creation announcement during session publication. A synchronous throw vetoes and
 'session/created'(this: Scoped<Session>, session: Session): void
 ```
 
-Source: [`packages/core/session/src/index.ts:47`](../../packages/core/session/src/index.ts)
+Source: [`packages/core/session/src/index.ts:46`](../../packages/core/session/src/index.ts)
 
 ### `session/disposed` — emit
 
@@ -255,7 +255,7 @@ Emitted once when an announced session leaves the store, including publication r
 'session/disposed'(this: Scoped<Session>, session: Session): void
 ```
 
-Source: [`packages/core/session/src/index.ts:57`](../../packages/core/session/src/index.ts)
+Source: [`packages/core/session/src/index.ts:56`](../../packages/core/session/src/index.ts)
 
 ### `session/event` — emit
 
@@ -267,7 +267,7 @@ Post-commit, fire-and-forget append feed. The listener snapshot resolves before
 
 Types: [SessionEvent](../core-data-structures/core.md)
 
-Source: [`packages/core/session/src/index.ts:69`](../../packages/core/session/src/index.ts)
+Source: [`packages/core/session/src/index.ts:68`](../../packages/core/session/src/index.ts)
 
 ### `session/flush` — parallel
 
@@ -277,7 +277,7 @@ Awaited parallel durability checkpoint: every listener runs and the caller await
 'session/flush'(this: Scoped<Session>, session: Session): Promise<void> | void
 ```
 
-Source: [`packages/core/session/src/index.ts:79`](../../packages/core/session/src/index.ts)
+Source: [`packages/core/session/src/index.ts:78`](../../packages/core/session/src/index.ts)
 
 ## `subagent/*`
 
@@ -469,14 +469,14 @@ Source: [`packages/workflow/workflow/src/index.ts:45`](../../packages/workflow/w
 
 The framework events every plugin also sees, beyond the harness vocabulary above. This is pinned vendor source ([vendoring policy](../../vendor/README.md)); it is summarized here so the page is a complete picture of the event bus, without elevating framework internals to the harness tier's prominence.
 
-- `internal/plugin` — A plugin fiber was created. ([`vendor/cordis/src/events.ts:197`](../../vendor/cordis/src/events.ts))
-- `internal/status` — A fiber changed lifecycle state. ([`vendor/cordis/src/events.ts:198`](../../vendor/cordis/src/events.ts))
-- `internal/service` — Interception hook for a service binding (no core producer). ([`vendor/cordis/src/events.ts:199`](../../vendor/cordis/src/events.ts))
-- `internal/update` — Waterfall: a fiber config update is being applied. ([`vendor/cordis/src/events.ts:200`](../../vendor/cordis/src/events.ts))
-- `internal/get` — Waterfall: a service is being read from the store. ([`vendor/cordis/src/events.ts:201`](../../vendor/cordis/src/events.ts))
-- `internal/set` — Waterfall: a service is being written to the store. ([`vendor/cordis/src/events.ts:202`](../../vendor/cordis/src/events.ts))
-- `internal/listener` — A listener was registered. ([`vendor/cordis/src/events.ts:203`](../../vendor/cordis/src/events.ts))
-- `internal/dispatch` — An event is being dispatched to listeners. ([`vendor/cordis/src/events.ts:204`](../../vendor/cordis/src/events.ts))
+- `internal/plugin` — A plugin fiber was created. ([`vendor/cordis/src/events.ts:328`](../../vendor/cordis/src/events.ts))
+- `internal/status` — A fiber changed lifecycle state. ([`vendor/cordis/src/events.ts:330`](../../vendor/cordis/src/events.ts))
+- `internal/service` — Interception hook for a service binding (no core producer). ([`vendor/cordis/src/events.ts:332`](../../vendor/cordis/src/events.ts))
+- `internal/update` — Waterfall: a fiber config update is being applied. ([`vendor/cordis/src/events.ts:334`](../../vendor/cordis/src/events.ts))
+- `internal/get` — Waterfall: a service is being read from the store. ([`vendor/cordis/src/events.ts:336`](../../vendor/cordis/src/events.ts))
+- `internal/set` — Waterfall: a service is being written to the store. ([`vendor/cordis/src/events.ts:338`](../../vendor/cordis/src/events.ts))
+- `internal/listener` — A listener was registered. ([`vendor/cordis/src/events.ts:340`](../../vendor/cordis/src/events.ts))
+- `internal/dispatch` — An event is being dispatched to listeners. ([`vendor/cordis/src/events.ts:342`](../../vendor/cordis/src/events.ts))
 - `hmr/change` — A watched source file changed on disk. ([`vendor/hmr/src/index.ts:20`](../../vendor/hmr/src/index.ts))
 - `hmr/reload` — Plugins are being reloaded after a change. ([`vendor/hmr/src/index.ts:21`](../../vendor/hmr/src/index.ts))
 - `exit` — The process is exiting on a signal. ([`vendor/loader/src/index.ts:23`](../../vendor/loader/src/index.ts))

docs/cordis-catalog/services.md

@@ -71,7 +71,21 @@ abstract start(spec: BashExecSpec): BashProcess
 
 Types: [BashExecRequest](../core-data-structures/bash.md) · [BashExecSpec](../core-data-structures/bash.md) · [BashRunResult](../core-data-structures/bash.md)
 
-Source: [`packages/bash/bash/src/index.ts:46`](../../packages/bash/bash/src/index.ts)
+Source: [`packages/bash/bash/src/index.ts:49`](../../packages/bash/bash/src/index.ts)
+
+## `ctx.bashEnv` — `BashEnvRegistry`
+
+Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables. The namespace is rebuilt for every model bash call: ambient `DSH_*` values are discarded by the executor, then the registry's current snapshot is injected. Built-in shell facts remain owned by the registry itself while plugins can register additional, enumerable facts with effect-scoped disposal.
+
+```ts cordis-catalog
+register(contributor: BashEnvContributor): () => void
+collect(execution: ToolExecution): DshEnvironment
+list(): BashEnvVariableInfo[]
+```
+
+Types: [ToolExecution](../core-data-structures/tools.md)
+
+Source: [`packages/bash/tool-bash/src/index.ts:102`](../../packages/bash/tool-bash/src/index.ts)
 
 ## `ctx.codeRuntime` — `CodeRuntime` (abstract seam)
 
@@ -87,7 +101,7 @@ Source: [`packages/code-runtime/code-runtime/src/index.ts:30`](../../packages/co
 
 ## `ctx.compact` — `CompactService` (abstract seam)
 
-Abstract compaction service. Implementations own token estimation, retention, and summarization, but a successful run must replace the selected surface span with one summary node and prevent concurrent compaction of the same session. Load one implementation per context as `ctx.compact`.
+Abstract compaction service. Implementations own trigger policy, retention, and summarization, and may consume a separate measurement service. A successful run replaces the selected surface span with one summary node and prevents concurrent compaction of the same session. Load one implementation per context as `ctx.compact`.
 
 ```ts cordis-catalog
 abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise<CompactionResult | null>
@@ -96,15 +110,16 @@ abstract compactRegion( session: Session, start: number, end: number, agent: Com
 
 Types: [Message](../core-data-structures/core.md)
 
-Source: [`packages/compact/compact/src/index.ts:36`](../../packages/compact/compact/src/index.ts)
+Source: [`packages/compact/compact/src/index.ts:38`](../../packages/compact/compact/src/index.ts)
 
 ## `ctx.fs` — `FileSystem` (abstract seam)
 
 Abstract filesystem provider. Targets must preserve identity across aliases; reads expose regular UTF-8 text or typed errors, listings are stable and content-free, and mutations are atomic. Optional guards add stale protection without changing the unguarded provider contract.
 
 ```ts cordis-catalog
-abstract resolve(path: string, opts?: { cwd?: string }): Promise<FsTarget>
+abstract resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise<FsTarget>
 abstract stat(target: FsTarget, signal?: AbortSignal): Promise<FsInfo | undefined>
+abstract lstat(path: string, opts?: { cwd?: string }, signal?: AbortSignal): Promise<FsPathInfo | undefined>
 abstract readText(target: FsTarget, signal?: AbortSignal): Promise<string>
 abstract streamText(target: FsTarget, signal?: AbortSignal): Promise<AsyncIterable<string>>
 abstract listDir(target: FsTarget, signal?: AbortSignal): Promise<FsDirEntry[]>
@@ -114,21 +129,22 @@ abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: F
 
 Types: [FsEditOutcome](../core-data-structures/filesystem.md) · [FsEditRequest](../core-data-structures/filesystem.md) · [FsInfo](../core-data-structures/filesystem.md) · [FsTarget](../core-data-structures/filesystem.md) · [FsVersion](../core-data-structures/filesystem.md) · [FsWriteIntent](../core-data-structures/filesystem.md) · [FsWriteOutcome](../core-data-structures/filesystem.md)
 
-Source: [`packages/fs/fs/src/index.ts:78`](../../packages/fs/fs/src/index.ts)
+Source: [`packages/fs/fs/src/index.ts:80`](../../packages/fs/fs/src/index.ts)
 
 ## `ctx.llm` — `LlmService`
 
 The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall.
 
 ```ts cordis-catalog
-registerAdapter(models: string[], adapter: LlmAdapter): () => void
-models(): string[]
+registerAdapter(providers: string[], adapter: LlmAdapter): () => void
+listProviders(): LlmProviderInfo[]
+async listModels(provider: string): Promise<LlmModelInfo[]>
 stream(options: GenerateOptions): AsyncIterable<StreamChunk>
 ```
 
 Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md)
 
-Source: [`packages/llm/llm/src/index.ts:75`](../../packages/llm/llm/src/index.ts)
+Source: [`packages/llm/llm/src/index.ts:96`](../../packages/llm/llm/src/index.ts)
 
 ## `ctx.permission` — `PermissionService`
 
@@ -162,6 +178,7 @@ Source: [`packages/sandbox/sandbox/src/index.ts:111`](../../packages/sandbox/san
 Durable append-only session storage. Implementations preserve contiguous, losslessly JSON-serializable events; append resolves only after durability, and load balances a complete interrupted tail without rewriting committed events.
 
 ```ts cordis-catalog
+abstract locate(meta: SessionHeader): SessionLocation | undefined
 abstract create(meta: SessionHeader): Promise<void>
 abstract append(id: SessionId, events: readonly SessionEvent[]): Promise<void>
 abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }>
@@ -170,19 +187,21 @@ abstract list(): Promise<SessionHeader[]>
 
 Types: [SessionEvent](../core-data-structures/core.md)
 
-Source: [`packages/session-persistence/session-persistence/src/index.ts:30`](../../packages/session-persistence/session-persistence/src/index.ts)
+Source: [`packages/session-persistence/session-persistence/src/index.ts:42`](../../packages/session-persistence/session-persistence/src/index.ts)
 
 ## `ctx.sessionQuery` — `SessionQueryService`
 
-Live-preferred logical-corpus and exact-event read service.
+Live-preferred logical-corpus exact-read and relationship-tracing service.
 
 ```ts cordis-catalog
 listSessions(): Promise<SessionRecord[]>
 async listEvents(sessionId: SessionId): Promise<SessionEventRecord[]>
+async traceSession(sessionId: SessionId): Promise<SessionLineageTrace>
+async traceEvent(request: SessionEventTraceRequest): Promise<SessionEventTrace>
 async readEvent(request: SessionEventReadRequest): Promise<SessionEventWindow>
 ```
 
-Source: [`packages/session-query/session-query/src/index.ts:35`](../../packages/session-query/session-query/src/index.ts)
+Source: [`packages/session-query/session-query/src/index.ts:38`](../../packages/session-query/session-query/src/index.ts)
 
 ## `ctx.sessions` — `SessionStore`
 
@@ -201,7 +220,7 @@ list(): Session[]
 fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session
 ```
 
-Source: [`packages/core/session/src/index.ts:564`](../../packages/core/session/src/index.ts)
+Source: [`packages/core/session/src/index.ts:580`](../../packages/core/session/src/index.ts)
 
 ## `ctx.skills` — `SkillService`
 
@@ -216,6 +235,22 @@ async get(name: string, options: SkillLookupOptions = {}): Promise<SkillDefiniti
 
 Source: [`packages/skill/skill/src/index.ts:141`](../../packages/skill/skill/src/index.ts)
 
+## `ctx.spillStore` — `SpillStore` (abstract seam)
+
+Abstract spill storage service. Subclass, implement saveText, and load the subclass as a plugin — it registers as `ctx.spillStore` (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior).
+
+Semantics every implementation must honor:
+
+- saveText persists the FULL `content` verbatim and returns an opaque locator, exact byte length, and model-facing retrieval guidance.
+- Storage is scoped by the request's SaveTextSpill.owner session; the backend chooses a private (not world-readable) location and a collision-free name derived from — never equal to — the caller's `suggestedName`.
+- `saveText` REJECTS on a real storage failure (permissions, ENOSPC, backend unavailable); the caller decides how to degrade (the spill policy treats a rejection as best-effort and keeps the inline result).
+
+```ts cordis-catalog
+abstract saveText(input: SaveTextSpill): Promise<SpillRef>
+```
+
+Source: [`packages/spill/spill/src/index.ts:45`](../../packages/spill/spill/src/index.ts)
+
 ## `ctx.subagents` — `SubagentService`
 
 Named provider registry and capability-checked start surface.
@@ -261,6 +296,19 @@ Types: [Agent](../core-data-structures/core.md)
 
 Source: [`packages/tasks/tasks/src/index.ts:76`](../../packages/tasks/tasks/src/index.ts)
 
+## `ctx.tokenMeter` — `TokenMeterService`
+
+Replay owner for one service-wide estimator and isolated per-session folds.
+
+```ts cordis-catalog
+measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement
+estimateMessage(message: Message): number
+```
+
+Types: [Message](../core-data-structures/core.md)
+
+Source: [`packages/llm/token-meter/src/index.ts:106`](../../packages/llm/token-meter/src/index.ts)
+
 ## `ctx.tools` — `ToolRegistry`
 
 Tool registry and execution pipeline. Scoped registrations shadow globals; one visibility resolver feeds presentation, lookup, and dispatch.
@@ -276,7 +324,7 @@ async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>
 
 Types: [ToolDefinition](../core-data-structures/tools.md) · [ToolExecutionInput](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md)
 
-Source: [`packages/core/tools/src/index.ts:363`](../../packages/core/tools/src/index.ts)
+Source: [`packages/core/tools/src/index.ts:378`](../../packages/core/tools/src/index.ts)
 
 ## `ctx.userInteraction` — `UserInteractionService`
 
@@ -325,12 +373,12 @@ Source: [`packages/workflow/workflow/src/index.ts:159`](../../packages/workflow/
 
 The framework `ctx` surface every plugin also sees, beyond the harness services above. This is pinned vendor source ([vendoring policy](../../vendor/README.md)); it is summarized here so the page is a complete picture of what `ctx` offers, without elevating framework internals to the harness tier's prominence.
 
-- `ctx.on / ctx.once` — Register an event listener (disposable). ([`vendor/cordis/src/events.ts:29`](../../vendor/cordis/src/events.ts))
-- `ctx.emit / ctx.parallel / ctx.serial / ctx.bail / ctx.waterfall` — Dispatch an event (sync / awaited / first-bail / veto-chain). ([`vendor/cordis/src/events.ts:29`](../../vendor/cordis/src/events.ts))
-- `ctx.plugin / ctx.inject` — Load a plugin / declare required services. ([`vendor/cordis/src/registry.ts:144`](../../vendor/cordis/src/registry.ts))
+- `ctx.on / ctx.once` — Register an event listener (disposable). ([`vendor/cordis/src/events.ts:34`](../../vendor/cordis/src/events.ts))
+- `ctx.emit / ctx.parallel / ctx.serial / ctx.bail / ctx.waterfall` — Dispatch an event (sync / awaited / first-bail / veto-chain). ([`vendor/cordis/src/events.ts:34`](../../vendor/cordis/src/events.ts))
+- `ctx.plugin / ctx.inject` — Load a plugin / declare required services. ([`vendor/cordis/src/registry.ts:164`](../../vendor/cordis/src/registry.ts))
 - `ctx.effect` — Register a disposable side effect tied to the fiber. ([`vendor/cordis/src/fiber.ts:9`](../../vendor/cordis/src/fiber.ts))
 - `ctx.get / ctx.set / ctx.provide / ctx.accessor / ctx.mixin` — Low-level service-store access and binding. ([`vendor/cordis/src/reflect.ts:7`](../../vendor/cordis/src/reflect.ts))
-- `ctx.extend / ctx.isolate / ctx.intercept` — Derive a child context (scoped services / isolation / interception). ([`vendor/cordis/src/context.ts:35`](../../vendor/cordis/src/context.ts))
+- `ctx.extend / ctx.isolate / ctx.intercept` — Derive a child context (scoped services / isolation / interception). ([`vendor/cordis/src/context.ts:42`](../../vendor/cordis/src/context.ts))
 - `ctx.root / ctx.scope / ctx.fiber / ctx.registry / ctx.reflect / ctx.events / ctx.logger` — Ambient handles onto the running context graph. ([`vendor/cordis/src/context.ts:16`](../../vendor/cordis/src/context.ts))
 - `ctx.timer (+ interval / timeout / throttle / debounce / setTimeout / setInterval)` — Disposable timer helpers. The `timer` key is provided at runtime; the six helpers are mixed onto ctx directly (declared via Pick). ([`vendor/timer/src/index.ts:4`](../../vendor/timer/src/index.ts))
 - `ctx.loader` — The config Loader that booted the app (present under the loader). ([`vendor/loader/src/index.ts:30`](../../vendor/loader/src/index.ts))

docs/core-data-structures/bash.md

@@ -4,9 +4,21 @@ The bash execution seam is split across interface ([dsh-bash](../../packages/bas
 
 Source: [`packages/bash/bash/src/types.ts`](../../packages/bash/bash/src/types.ts)
 
+## Managed shell environment namespace
+
+`DSH_*` variables are Harness-owned child-process facts. The model-facing bash tool collects them through `ctx.bashEnv` and passes them through `BashExecRequest.dshEnv`; executors remove inherited `DSH_*` names before merging the current snapshot.
+
+```ts type-equiv
+type DshEnvironmentKey = `${typeof DSH_ENV_PREFIX}${string}`
+```
+
+```ts type-equiv
+type DshEnvironment = Readonly<Record<DshEnvironmentKey, string>>
+```
+
 ## Request vs. spec: the `resolve()` split
 
-The seam separates the **model-/plugin-facing request** (optional `workdir`/`timeoutMs`, filled from config) from the **fully-resolved spec** the executor acts on (those fields required). The tool layer calls `ctx.bash.resolve(request)` between them — this is the repo's "explicit > implicit at package seams" rule made concrete: the reader of a `BashExecSpec` never wonders where the working directory came from.
+The seam separates the **model-/plugin-facing request** (optional `workdir`/`timeoutMs`/`stdoutMaxBytes`, filled from config or request policy) from the **fully-resolved spec** the executor acts on (those fields required). The tool layer calls `ctx.bash.resolve(request)` between them — this is the repo's "explicit > implicit at package seams" rule made concrete: the reader of a `BashExecSpec` never wonders where the working directory or output budget came from.
 
 ```ts type-equiv
 interface BashExecRequest {
@@ -15,6 +27,13 @@ interface BashExecRequest {
   workdir?: string | undefined
   /** Timeout override in milliseconds (implementations cap it). */
   timeoutMs?: number | undefined
+  /**
+   * Foreground stdout capture budget in bytes. Absent uses the executor's
+   * default output cap. Trusted in-process consumers use this when they must
+   * parse complete stdout up to their own bounded limit; the model-facing bash
+   * tool does not expose it as a parameter.
+   */
+  stdoutMaxBytes?: number | undefined
   /** Abort signal — implementations kill the command when it fires. */
   signal?: AbortSignal | undefined
   /**
@@ -26,15 +45,20 @@ interface BashExecRequest {
    */
   stdin?: string | undefined
   /**
-   * Extra environment entries for the command, merged AFTER the
-   * implementation's credential scrub (so an explicit entry here is honored even
-   * when its name matches the scrub pattern — the caller named a value it holds,
-   * not the harness's ambient secret). Set by in-process plugins (the hooks
-   * bridges set `CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, …); the model-facing
-   * bash tool does not expose it as a parameter (a model that needs an env var
-   * uses shell syntax like `FOO=bar cmd`).
+   * Ordinary environment entries for the command, merged after the credential
+   * scrub. `DSH_*` is reserved for {@link dshEnv} and implementations reject it
+   * here. Set by in-process plugins (the hooks bridges set
+   * `CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, …); the model-facing bash tool
+   * does not expose it as a parameter.
    */
   env?: Record<string, string> | undefined
+  /**
+   * Harness-owned `DSH_*` variables for this execution. Executors discard
+   * ambient `DSH_*` entries before merging this snapshot, so an unavailable
+   * current fact cannot inherit a stale value from the harness process, and
+   * reject non-`DSH_*` names supplied through this managed channel.
+   */
+  dshEnv?: DshEnvironment | undefined
   /**
    * Explicit per-call sandbox-policy input, overriding the executor's
    * configured default mode for THIS call. Never a silent default: a
@@ -57,6 +81,11 @@ interface BashExecSpec {
   command: string
   workdir: string
   timeoutMs: number
+  /**
+   * Resolved foreground stdout capture budget in bytes. `run()` uses it for
+   * stdout; background tasks and stderr keep the executor's own output cap.
+   */
+  stdoutMaxBytes: number
   /** Abort signal — implementations kill the command when it fires. */
   signal?: AbortSignal | undefined
   /**
@@ -73,6 +102,8 @@ interface BashExecSpec {
    * config default, absent means "no extra env".
    */
   env?: Record<string, string> | undefined
+  /** Managed `DSH_*` snapshot; implementations reject ordinary names. */
+  dshEnv?: DshEnvironment | undefined
   /**
    * The sandbox mode this call executes under, required-but-nullable so every
    * resolved spec states its policy. A sandboxing executor's `resolve()` stamps
@@ -88,6 +119,8 @@ interface BashExecSpec {
 
 `stdin` and `env` are trusted in-process plugin inputs and are not exposed by `dsh-tool-bash`. The local executor scrubs ambient credentials before merging explicit caller-supplied env. See [the bash-stdin-env RFC](../rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md).
 
+`stdoutMaxBytes` is also trusted-plugin-only. It lets a foreground consumer request complete stdout up to a bounded parser budget without changing stderr, background tasks, or the model-facing bash tool's ordinary output cap.
+
 ## Foreground runs: `BashRunResult`
 
 The outcome of one completed (or killed) foreground run. Orthogonal outcomes are reported **independently** — a process can both time out AND exit 0 because it trapped the signal — so `timedOut`, `aborted`, `signal`, and `exitCode` are each their own field; a caller never reads a cut-short run as a clean success.

docs/core-data-structures/compaction.md

@@ -11,7 +11,7 @@ Compaction extends [`SessionEventMap`](session.md) with three event types via de
 | Event | Payload | Role |
 |---|---|---|
 | `compact/start` | `{ turn }` | acquires the log-recorded lock |
-| `compact/summary` | `{ summary, shadowedRange, shadowedSeqs, shadowedTokenCount, model, maxTokens? }` | provenance: the summary blocks, the shadowed surface-boundary pair (`start`/`end` seqs — a position span, not a numeric interval), the shadowed seqs in surface order, the estimated token count, and the summarize call's envelope (`model`, plus its generation cap when one applied) — logged so the one-shot request is reconstructable from log + code (the reconstructability RFC) |
+| `compact/summary` | `{ summary, shadowedRange, shadowedSeqs, shadowedTokenCount, provider, model, maxTokens? }` | provenance: the summary blocks, the shadowed surface-boundary pair (`start`/`end` seqs — a position span, not a numeric interval), the shadowed seqs in surface order, the estimated token count, and the summarize call's envelope (`provider`, `model`, plus its generation cap when one applied) — logged so the one-shot request is reconstructable from log + code (the reconstructability RFC) |
 | `compact/end` | `{ turn, error? }` | releases the lock (`error` set when summarization threw) |
 
 The lock brackets the **whole** operation: `compact/start` is appended first, then summarization, the `compact/summary` provenance record, and the `user/message` replacement all land, and only then `compact/end`. Releasing the lock last turns a crash mid-operation into a detectable orphaned lock (a `compact/start` with no matching `compact/end`) rather than a `compact/end` that falsely claims compaction finished.
@@ -50,6 +50,8 @@ interface CompactionResult {
 
 ## The service
 
-`CompactService` exposes `compactIfNeeded(...)` for pressure-triggered compaction, returning `null` when no compaction is needed, and `compactRegion(...)` for an explicit inclusive surface range. The pre-step caller supplies the agent, full prompt, session prefix, and abort signal; implementations must forward that signal to summarization. Estimation, retention, event sequencing, and summarization remain backend policy.
+`CompactService` exposes `compactIfNeeded(...)` for pressure-triggered compaction, returning `null` when no compaction is needed, and `compactRegion(...)` for an explicit inclusive surface range. The pre-step caller supplies the agent, full prompt, session prefix, and abort signal; implementations must forward that signal to summarization. The seam owns no pricing API: [`ctx.tokenMeter`](token-meter.md) directly owns estimation and replay, while `dsh-compact-basic` owns retention, event sequencing, routed summarization calls, and their configuration.
 
 Auto-compaction runs at serial `agent/pre-step`, before the step and request derivation, so it can replace surface nodes while keeping trace events outside the step. Region boundaries preserve tool-call/result pairing but do not preserve whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns the retention and failure details.
+
+The seam exports `toolPairingBalancedBefore(session, seq)` and `toolPairingBalancedAfter(session, seq)` for those edge checks. Both validate current surface membership and reject missing seqs and orphan results; the [package contract](../../packages/compact/compact/README.md#tool-pairing-boundaries) owns their cache semantics.

docs/core-data-structures/core.md

@@ -16,10 +16,11 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t
 | Sub-page | Owns |
 |---|---|
 | [llm-streaming.md](llm-streaming.md) | the `StreamChunk` wire protocol + adapter contract, `BlockAssembler`, the `LlmAdapter` seam |
+| [token-meter.md](token-meter.md) | immutable scalar and positional replay measurements with consumed-log revisions |
 | [scope.md](scope.md) | scoped registration identity, dispatch carriers, and the owned `Scope` context |
 | [session.md](session.md) | the full `SessionEventMap` variant catalog, `TurnTrigger`/`TurnEndReason`, `deriveMessages()`, the turn-enclosure invariant |
 | [persistence.md](persistence.md) | the durability seam: `SessionPersistence`, JSONL + SQLite backends, `session/flush`, crash recovery, `SessionHeader` |
-| [session-query.md](session-query.md) | logical session/event records and bounded exact-event reads |
+| [session-query.md](session-query.md) | logical records, bounded exact-event reads, and relationship traces |
 | [system-prompt.md](system-prompt.md) | per-assembly context, tool-provider results, prompt sections, and cooperative assembly |
 | [tools.md](tools.md) | `ToolDefinition` full fields, the schema DSL, `ToolExecution`/`ToolResult`, tool-presentation UI types, and the guarded execution pipeline |
 | [user-interaction.md](user-interaction.md) | the UI-backed human question/answer seam: `AskUserQuestionRequest`, answer/options vocabulary, provider API, error taxonomy |
@@ -32,6 +33,7 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t
 | [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 availability, `WebError` |
+| [spill.md](spill.md) | the spill storage seam: `SaveTextSpill`, `SpillOwner`/`SpillSource`, `SpillRef`, the branded `SpillLocator` |
 | [workflow.md](workflow.md) | the workflow seam: `WorkflowStartRequest`, `WorkflowMeta`, `WorkflowRun`/`Result`, the `workflow/*` event payloads, `WorkflowError` fatality |
 
 > Type definitions on this page are pasted **verbatim** from source and drift-checked by `pnpm run verify-type-equiv` (see [development.md](../development.md#documenting-types-verbatim-ts-type-equiv)). Inline JSDoc is omitted for readability; follow the source link for the full contracts.
@@ -103,12 +105,29 @@ interface ContentBlockMap {
 
 The block interfaces (full fields in source): `TextBlock` (`text`), `ReasoningBlock` (thinking, distinct from visible text), `ToolCallBlock` (`id: CallId`, `name`, raw-JSON `arguments`), `ToolResultBlock` (`toolCallId`, nested `content: ContentBlock[]`, `isError?`). `ContentBlock = ContentBlockMap[ContentBlockType]`. The core set is limited to blocks every shipping path honors — multimodal content (images, audio, …) has no core block type; a feature that needs one adds it via the merge-extensible map together with the adapter/UI/compaction support that honors it.
 
-A `Message` is a role plus blocks:
+A `Message` is a role plus blocks. Loop-derived assistant messages carry their durable provider/model identity and optional adapter-private replay metadata:
+
+```ts type-equiv
+interface AssistantProvenance {
+  /** Provider route that produced the message. */
+  provider: string
+  /** Provider model id that produced the message. */
+  model: string
+  /**
+   * Lossless-JSON adapter state needed to replay the provider response.
+   * `LlmService` exposes it to a target adapter only when that adapter instance
+   * currently owns both this historical provider and the target provider.
+   */
+  replayState?: unknown
+}
+```
 
 ```ts type-equiv
 interface Message {
   role: 'system' | 'user' | 'assistant'
   content: ContentBlock[]
+  /** Present only on assistant messages produced by a routed adapter. */
+  provenance?: AssistantProvenance
 }
 ```
 
@@ -133,8 +152,34 @@ One model call is a fully-assembled `GenerateOptions`. The adapter answers with
 
 Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts)
 
+Provider and model discovery uses small provider-neutral descriptors. A model catalog is advisory: routing still keys on a registered provider, and an adapter may accept unlisted model ids.
+
+```ts type-equiv
+interface LlmProviderInfo {
+  /** Provider route key used by {@link GenerateOptions.provider}. */
+  id: string
+  /** Human-readable provider name for selectors and diagnostics. */
+  name: string
+}
+```
+
+```ts type-equiv
+interface LlmModelInfo {
+  /** Provider route that owns this model entry. */
+  provider: string
+  /** Model id passed to {@link GenerateOptions.model}. */
+  id: string
+  /** Human-readable model name for selectors. */
+  name: string
+  /** Optional user-facing distinction from otherwise similar models. */
+  description?: string
+}
+```
+
 ```ts type-equiv
 interface GenerateOptions {
+  /** Registered provider route selecting the adapter instance. */
+  provider: string
   model: string
   /**
    * Ordered conversation messages, exactly as the provider sees them (after
@@ -193,9 +238,9 @@ The model-facing `ToolSchema` is the wire shape; the registered `ToolDefinition`
 
 ### The request envelope: `LlmCallConfig` and the logged header
 
-The loop builds each request from logged state. `EpochHeader` records call config, rendered prompt, authoritative returned tool order (configured by `toolOrder`, or lexicographic when unset), and session prefix through `request/header` snapshots and deltas. Together with derived history, this makes the request reconstructable from the session log. See [session.md](session.md#the-request-header-events-requestheader-and-requestheader-delta) and the [reconstructability RFC](../rfc/implemented/architecture/2026-07-05-reconstructable-requests.md).
+The loop builds each request from logged state. `EpochHeader` records call config, rendered prompt, authoritative returned tool order (configured by `toolOrder`, or lexicographic when unset), and session prefix through full `request/header` snapshots. Together with derived history, this makes the request reconstructable from the session log. See [session.md](session.md#the-request-header-event-requestheader) and the [reconstructability RFC](../rfc/implemented/architecture/2026-07-05-reconstructable-requests.md).
 
-`agent/request` receives a frozen call-config seed and may return a replacement. `agent/session-prefix` composes request-only prefix messages once per loop instance, and the header records the exact result used. Requests reaching `llm/stream` are deep-frozen, so mutation throws.
+`agent/request` receives a frozen call-config seed and may return a replacement to switch provider, model, or sampling. `agent/session-prefix` composes request-only prefix messages once per loop instance, and the header records the exact result used. Requests reaching `llm/stream` are deep-frozen, so mutation throws.
 
 On the wire, a loop-built request reads in this order: the `system` slot (the rendered prompt assembly) → `messagePrefix` (the frozen session prefix) → the derived history — the boundary snapshot, whose tail is the newest `user/message` on a turn's first step and the previous step's tool results on later steps. The prefix never enters the derived history; its durable record is the header events, and the dev invariant recomputes exactly this equation against every loop-built request.
 
@@ -203,6 +248,7 @@ FIXME(call-config-shape): revisit the exact definition of this type — which fi
 
 ```ts type-equiv
 interface LlmCallConfig {
+  provider: string
   model: string
   temperature?: number
   maxTokens?: number
@@ -238,7 +284,7 @@ type SessionEvent<T extends SessionEventType = SessionEventType> = {
 }[T]
 ```
 
-The fifteen event variants (`turn/start`, `turn/end`, `step/start`, `step/end`, `user/message`, `prompt/blocked`, `context/message`, `assistant/chunk`, `assistant/message`, `tool/call`, `tool/result`, `steering/message`, `todo/write`, `request/header`, `request/header-delta`), the `deriveMessages()` projection rules, the `TurnTrigger`/`TurnEndReason` reasons, and the turn-enclosure invariant are on **[session.md](session.md)**. How the log is made durable — the `SessionPersistence` seam, JSONL/SQLite backends, the `session/flush` checkpoint, crash recovery, and `SessionHeader` — is on **[persistence.md](persistence.md)**.
+The fourteen event variants (`turn/start`, `turn/end`, `step/start`, `step/end`, `user/message`, `prompt/blocked`, `context/message`, `assistant/chunk`, `assistant/message`, `tool/call`, `tool/result`, `steering/message`, `todo/write`, `request/header`), the `deriveMessages()` projection rules, the `TurnTrigger`/`TurnEndReason` reasons, and the turn-enclosure invariant are on **[session.md](session.md)**. How the log is made durable — the `SessionPersistence` seam, JSONL/SQLite backends, the `session/flush` checkpoint, crash recovery, and `SessionHeader` — is on **[persistence.md](persistence.md)**.
 
 ## The agent handle
 
@@ -246,6 +292,15 @@ The fifteen event variants (`turn/start`, `turn/end`, `step/start`, `step/end`,
 
 Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts)
 
+`InjectOptions` extends ordinary message attribution with context-only framing and durable model-hidden JSON metadata:
+
+```ts type-equiv
+interface InjectOptions extends SendOptions {
+  envelope?: ContextEnvelope
+  meta?: JsonValue
+}
+```
+
 ```ts type-equiv
 interface Agent {
   readonly id: AgentId
@@ -281,9 +336,11 @@ interface Agent {
 
   /**
    * Inject in-session context (file-change notices, skill content, cron
-   * notifications, …): accepts context for a `context/message` session event
-   * the next model request sees, rendered as tagged synthetic context rather
-   * than a user prompt. Does not run the model.
+   * notifications, …): appends a `context/message` session event the next model
+   * request sees at its chronological position, rendered as synthetic context
+   * rather than a user prompt. The default uses the canonical context tag;
+   * `options.envelope: 'raw'` preserves caller-owned framing. Does not run the
+   * model.
    *
    * In an open turn, inject appends at the current log position except while
    * the current tool-call batch executes: accepted context waits FIFO until the
@@ -298,11 +355,11 @@ interface Agent {
    * (inject is synchronous): a failing flush is reported via `agent/error`
    * (step `0`) and the logger, never thrown into the caller.
    *
-   * Live-adapter review has validated the tagged-envelope rendering against
-   * current DeepSeek behavior; provider-specific mismatches belong in that
-   * adapter, not in the canonical session vocabulary.
+   * Live-adapter review has validated the canonical tagged-envelope rendering
+   * against current DeepSeek behavior; provider-specific mismatches belong in
+   * that adapter, not in the canonical session vocabulary.
    */
-  inject(content: ContentBlock[], options?: SendOptions): void
+  inject(content: ContentBlock[], options?: InjectOptions): void
 
   /**
    * Cancel ALL pending work for the agent. `cancel()`:
@@ -352,13 +409,13 @@ interface Agent {
 }
 ```
 
-`AgentStatus` is `'idle' | 'running' | 'disposed'`, and `AgentId` is branded. `AgentOptions` is merge-extensible and currently includes `model?`. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default.
+`AgentStatus` is `'idle' | 'running' | 'disposed'`, and `AgentId` is branded. `AgentOptions` is merge-extensible and currently includes `provider?` and `model?`; dispatch requires both after `agent/request`. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default.
 
 The [event taxonomy](../architecture.md#event) owns the `agent/*` lifecycle, checkpoint, and waterfall contracts. Turn and step boundaries are durable session events rather than agent emits.
 
 ## Interception decisions
 
-Each `agent/*` interception waterfall returns a small, seam-specific typed union — the unified Decision idiom (the tool seams' `PreToolDecision`/`PostToolDecision` in [tools.md](tools.md) follow the same shape). A CC/Codex hook bridge maps its `permissionDecision`/`decision`/`continue`/`additionalContext` fields onto these; a native plugin returns them directly. They share one envelope for model-facing context, `HookContext`, which is `inject()`ed as a `context/message` and so carries a REQUIRED `source` (a missing source would default to `{kind:'user'}` and mislabel plugin context as a user prompt).
+Each `agent/*` interception waterfall returns a small, seam-specific typed union — the unified Decision idiom (the tool seams' `PreToolDecision`/`PostToolDecision` in [tools.md](tools.md) follow the same shape). A CC/Codex hook bridge maps its `permissionDecision`/`decision`/`continue`/`additionalContext` fields onto these; a native plugin returns them directly. Prompt and post-tool decisions share one model-facing context shape, `HookContext`, which is `inject()`ed as a `context/message` and therefore carries a REQUIRED `source` (a missing source would default to `{kind:'user'}` and mislabel plugin context as a user prompt). Its optional `envelope` selects the canonical context tag or caller-owned raw framing, while JSON `meta` persists plugin state without exposing it to the model. Both decisions carry `additionalContexts[]` so every entry preserves its own provenance, framing, and metadata. Continuation reasons are steering messages instead and deliberately use the narrower content/source shape.
 
 Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts)
 
@@ -366,23 +423,25 @@ Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types
 interface HookContext {
   content: ContentBlock[]
   source: MessageSource
+  envelope?: ContextEnvelope
+  meta?: JsonValue
 }
 ```
 
-`agent/prompt-submit` returns a `PromptDecision` (allow a drained queued message — optionally rewriting its `content` or attaching `additionalContext` — or block it; a batch whose every prompt is blocked opens a zero-step turn that ends `rejected`):
+`agent/prompt-submit` returns a `PromptDecision` (allow a drained queued message — optionally rewriting its `content` or attaching `additionalContexts` — or block it; a batch whose every prompt is blocked opens a zero-step turn that ends `rejected`):
 
 ```ts type-equiv
 type PromptDecision =
-  | { kind: 'allow'; content?: ContentBlock[]; additionalContext?: HookContext }
+  | { kind: 'allow'; content?: ContentBlock[]; additionalContexts?: HookContext[] }
   | { kind: 'block'; reason: string }
 ```
 
-`agent/turn-continuation` returns a `ContinuationDecision` (the loop's default is `continue` when the step had tool calls or steering was injected, else `stop`; a `continue` `reason` is recorded as next-step steering in the same turn — the typed `/goal` pattern):
+`agent/turn-continuation` returns a `ContinuationDecision` (the loop's default is `continue` when the step had tool calls or steering was injected, else `stop`; a `continue` `reason` is recorded as next-step steering in the same turn and therefore carries no context envelope or metadata — the typed `/goal` pattern):
 
 ```ts type-equiv
 type ContinuationDecision =
   | { action: 'stop' }
-  | { action: 'continue'; reason?: HookContext }
+  | { action: 'continue'; reason?: { content: ContentBlock[]; source: MessageSource } }
 ```
 
 `agent/turn-stop` returns the stop-only `ContinuationStop` subset or `undefined`. The loop calls this serial checkpoint after folding the ordinary decision, its reason, and pending steering; a stop is terminal and discards pending steering.

docs/core-data-structures/filesystem.md

@@ -37,6 +37,16 @@ interface FsInfo {
 }
 ```
 
+`lstat` is the path-level no-follow metadata primitive. It takes a path instead of an `FsTarget` because `resolve` intentionally follows symlinks to produce stable identity; consumers that need trust-boundary checks can call `lstat` first and reject `symlink` before resolving.
+
+```ts type-equiv
+interface FsPathInfo {
+  version: FsVersion
+  type: 'file' | 'directory' | 'symlink' | 'other'
+  size?: number
+}
+```
+
 `listDir` returns direct child entries in stable name order. Each entry carries the child basename, type, resolved target, and cheap metadata when the backend can report it. It must not read file contents, so `size` is only for regular files and `version` is metadata-derived. Broken or disappeared children may be returned as `other` without metadata; permission or backend I/O failures while listing or resolving child metadata fail the whole listing with `FS_PERMISSION_DENIED` or `FS_IO_ERROR`.
 
 ```ts type-equiv
@@ -144,4 +154,4 @@ type FsErrorCode =
 
 ## The service and the plugin
 
-`FileSystem` (`ctx.fs`, abstract) owns the provider primitives: `resolve`, `stat`, `readText`, `streamText`, `listDir`, `writeText`, and `editText`. `dsh-fs-policy` registers **no service** — it is a plugin that adds policy through the `fs/*` event gate: it decides the write/edit intent waterfalls (supplying `createIfAbsent`/`replaceIfVersion`/`{ version }` or throwing `FS_NOT_OBSERVED`) and records on `fs/observed`. The executor is `dsh-tool-fs`: it reads/writes/edits through `ctx.fs`, dispatches the waterfalls, and emits the recording event. The generated wiring catalog shows the exact `ctx.fs` signatures on [services.md](../cordis-catalog/services.md#ctxfs--filesystem-abstract-seam).
+`FileSystem` (`ctx.fs`, abstract) owns the provider primitives: `resolve`, `stat`, `lstat`, `readText`, `streamText`, `listDir`, `writeText`, and `editText`. `dsh-fs-policy` registers **no service** — it is a plugin that adds policy through the `fs/*` event gate: it decides the write/edit intent waterfalls (supplying `createIfAbsent`/`replaceIfVersion`/`{ version }` or throwing `FS_NOT_OBSERVED`) and records on `fs/observed`. The executor is `dsh-tool-fs`: it reads/writes/edits through `ctx.fs`, dispatches the waterfalls, and emits the recording event. The generated wiring catalog shows the exact `ctx.fs` signatures on [services.md](../cordis-catalog/services.md#ctxfs--filesystem-abstract-seam).

docs/core-data-structures/llm-streaming.md

@@ -16,7 +16,12 @@ type StreamChunk =
   | { type: 'tool-call-delta'; index: number; id: CallId; name?: string; argumentsDelta: string }
   | { type: 'block-end'; index: number; block: ContentBlock }
   | { type: 'usage'; usage: TokenUsage }
-  | { type: 'finish'; reason: FinishReason }
+  | {
+    type: 'finish'
+    reason: FinishReason
+    /** Adapter-private lossless-JSON state for replaying a successful response. */
+    replayState?: unknown
+  }
 ```
 
 ## The adapter contract
@@ -27,8 +32,9 @@ Every adapter MUST obey these, and every consumer may rely on them:
 - **Tool-call `arguments` stay raw JSON strings end-to-end.** Partial fragments stream via `argumentsDelta`; a provider that hands back parsed objects re-stringifies at `block-end`.
 - **Two sanctioned error paths.** A failure may either THROW from `stream()` (transport/protocol errors) **or** end the stream with `finish {kind:'error'|'aborted'}` (provider in-band errors, for adapters that can't throw mid-stream). Consumers must handle *both*. The agent loop translates a finish-error/aborted into a turn error — it never logs a normal completed assistant message for a failed step.
 - **Every provider HTTP request carries the app-attribution header.** Adapters send `attributionHeaders()` (below) - the `User-Agent` baseline - and prove it with a wire-level test (mock server asserting the received header, or the library's header hook for a library-backed adapter).
+- **Replay state is adapter-owned.** A successful `finish` may carry lossless-JSON state needed to reconstruct a native provider response. The loop stores it with the assembled assistant message unless an `agent/step-result` listener rewrote the content. On a later request, `LlmService` passes the state only when the historical provider and target provider are currently registered to the exact same adapter instance. That adapter validates the state and owns any cross-model or cross-provider conversion; other adapters receive the provider-neutral content and provenance without the private state.
 
-This contract is why two adapters exist as a deliberate pair: `dsh-llm-deepseek` (hand-rolled fetch/SSE) and `dsh-llm-pi-ai` (the same endpoint through `@earendil-works/pi-ai`). Two independent internals over one contract is what pinned the protocol down — the library-backed adapter can't throw mid-stream, so it exercises the finish-chunk error path the hand-rolled one might not.
+This contract was pinned down by two deliberately independent implementations: `dsh-llm-deepseek` (hand-rolled fetch/SSE) and `dsh-llm-pi-ai` (a generic multi-provider adapter through `@earendil-works/pi-ai`). The library-backed adapter cannot throw mid-stream, so it exercises the finish-chunk error path the hand-rolled one might not.
 
 ## `AppIdentity` — app attribution
 
@@ -58,11 +64,11 @@ interface TokenUsage {
 
 ## `BlockAssembler`
 
-`BlockAssembler` ([`packages/llm/llm/src/assembler.ts`](../../packages/llm/llm/src/assembler.ts)) is the single shared implementation that folds a `StreamChunk` stream back into `ContentBlock`s and a final `Message`. The loop logs the raw chunks (for replay fidelity) while feeding the same chunks through an assembler — so the canonical log keeps token-level detail and the derived message is rebuilt deterministically. A consumer that needs the assembled result without re-implementing the fold uses this.
+`BlockAssembler` ([`packages/llm/llm/src/assembler.ts`](../../packages/llm/llm/src/assembler.ts)) is the single shared implementation that folds a `StreamChunk` stream back into `ContentBlock`s, usage, finish reason, and replay state. The loop logs the raw chunks while feeding the same chunks through an assembler, then stores the assembled assistant content with its provider/model provenance. A consumer that needs the assembled result without re-implementing the fold uses this.
 
 ## The seam
 
-`LlmAdapter` is the provider seam: subclass, implement `stream()`, register with `ctx.llm.registerAdapter(models, adapter)`. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm).
+`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerInfo()` and asynchronous `listModels()` methods feed `LlmService.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm).
 
 `ContentBlockType` (the key set the `index`-correlated blocks carry) derives from `ContentBlockMap`:
 

docs/core-data-structures/persistence.md

@@ -2,7 +2,7 @@
 
 The **durability seam** for the event log. [session.md](session.md) describes the in-memory `Session` — the append-only `SessionEvent` log that is the source of truth. This page describes how that log is made durable: the abstract `SessionPersistence` service, its backends, the flush checkpoint, crash recovery, and the metadata header that travels alongside the log. The event vocabulary the log carries is enumerated, member by member, in the generated [persistence log event catalog](../persistence-catalog.md).
 
-The seam is a textbook [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md): one abstract service ([dsh-session-persistence](../../packages/session-persistence/session-persistence), `ctx.sessionPersistence`) defining create/append/load/list over the existing `SessionEvent` — **no parallel persisted type** — and two interchangeable backends that pass the same `runPersistenceContract` suite. See the [session-persistence RFC](../rfc/implemented/architecture/2026-06-14-session-persistence.md).
+The seam is a textbook [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md): one abstract service ([dsh-session-persistence](../../packages/session-persistence/session-persistence), `ctx.sessionPersistence`) defining locate/create/append/load/list over the existing `SessionEvent` — **no parallel persisted type** — and two interchangeable backends that pass the same `runPersistenceContract` suite. See the [session-persistence RFC](../rfc/implemented/architecture/2026-06-14-session-persistence.md).
 
 ## The flush checkpoint
 
@@ -12,6 +12,19 @@ The seam is a textbook [capability seam](../rfc/implemented/architecture/2026-06
 
 A backend that reloads a log crashed mid-turn finds an open `turn/start` with no `turn/end`. It does **not** truncate — a single turn can be huge in a long-horizon task (many steps, large tool output), and those events were durably appended before the crash. Instead it closes the orphaned turn with a synthetic `turn/end { reason: { kind: 'interrupted' } }`, keeping the log balanced and the turn-enclosure invariant intact. `interrupted` is the one `TurnEndReason` no loop emits (see [session.md](session.md#why-a-turn-ended-turnendreasonmap)).
 
+## `SessionLocation` — optional per-session artifact target
+
+`SessionPersistence.locate(meta)` synchronously resolves a backend-owned independent artifact without reading, creating, or flushing it. JSONL returns its absolute target path; SQLite returns `undefined` because sessions share one database. A returned path can therefore name a file that does not yet exist or lacks the current unflushed turn; it is a location hint, not authorization or a freshness guarantee.
+
+```ts type-equiv
+interface SessionLocation {
+  /** Backend-specific artifact kind, for example `jsonl`. */
+  readonly kind: string
+  /** Absolute path to this session's backend-owned artifact. */
+  readonly path: string
+}
+```
+
 ## `SessionHeader` — metadata beside the log
 
 Per-session metadata travels **separately** from the event log: format version, cwd, lineage, and the seed boundary are storage concerns, not conversation events, so they stay out of `SessionEventMap` and never reach `deriveMessages()`. The header is attached to a `Session` via `session.header`.
@@ -80,7 +93,7 @@ Replay/fork is therefore `ctx.sessions.create(id, { seed: seedEvents })`; resumi
 
 ## The backends
 
-Both implement the same abstract `SessionPersistence` (create/append/load/list over `SessionEvent`) and pass `runPersistenceContract`, proving the seam is genuinely backend-agnostic:
+Both implement the same abstract `SessionPersistence` (locate/create/append/load/list over `SessionEvent`) and pass `runPersistenceContract`, proving the seam is genuinely backend-agnostic:
 
 - **[dsh-session-persistence-jsonl](../../packages/session-persistence/session-persistence-jsonl)** — an append-only JSONL log per session with crash-safe atomic writes, the interrupted-turn crash recovery above, and a read/replay path.
 - **[dsh-session-persistence-sqlite](../../packages/session-persistence/session-persistence-sqlite)** — `node:sqlite`, one row per `SessionEvent`. The row shape `(session_id, seq, type, time, data, source_event_seqs, surface_op)` maps 1:1 onto the event, including optional surface metadata, so there is no parallel persisted schema to keep in sync.

docs/core-data-structures/session-query.md

@@ -1,6 +1,6 @@
 # Session Query
 
-Exact reads over the live-preferred logical session corpus. The [package contract](../../packages/session-query/session-query) owns source precedence, dynamic optional persistence, cloning, surface classification, bounded windows, and typed failures. Full-text search is a separate proposed SQLite phase.
+Exact reads and relationship traces over the live-preferred logical session corpus. The [package contract](../../packages/session-query/session-query) owns source precedence, dynamic optional persistence, cloning, surface classification, bounded windows, tracing validation, and typed failures. Full-text search is a separate proposed SQLite package.
 
 Source: [`packages/session-query/session-query/src/types.ts`](../../packages/session-query/session-query/src/types.ts)
 
@@ -30,6 +30,34 @@ export interface SessionEventRecord {
 }
 ```
 
+## Session lineage
+
+`SessionLineageTrace` carries known parents in immediate-to-outward order and a forest of recursively nested direct descendants. The completeness discriminant makes a known root and a missing parent mutually exclusive.
+
+```ts type-equiv
+export interface SessionLineageNode {
+  session: SessionRecord
+  descendants: SessionLineageNode[]
+}
+```
+
+```ts type-equiv
+export type SessionLineageTrace = {
+  target: SessionRecord
+  ancestors: SessionRecord[]
+  descendants: SessionLineageNode[]
+} & (
+  | {
+    complete: true
+    root: SessionRecord
+  }
+  | {
+    complete: false
+    unresolvedParentId: SessionId
+  }
+)
+```
+
 ## Bounded event reads
 
 The request addresses one raw seq and optional neighboring counts. The result carries a `SessionHeader` rather than availability flags so a known live target can remain independent of persistence health.
@@ -53,6 +81,28 @@ export interface SessionEventWindow {
 }
 ```
 
+## Event relationships
+
+Event traces distinguish positional surface replacement from logged provenance. Every seq list contains direct links except `replacementChain`, which follows immediate replacers from the target to the final positional replacement.
+
+```ts type-equiv
+export interface SessionEventTraceRequest {
+  sessionId: SessionId
+  seq: number
+}
+```
+
+```ts type-equiv
+export interface SessionEventTrace {
+  target: SessionEventRecord
+  replacedBy?: number
+  replacementChain: number[]
+  replacedEventSeqs: number[]
+  sourceEventSeqs: number[]
+  derivedEventSeqs: number[]
+}
+```
+
 ## Errors
 
 The closed code union distinguishes request validation, missing targets, malformed surface logs, optional-backend failure, and contradictory source metadata.
@@ -61,6 +111,7 @@ The closed code union distinguishes request validation, missing targets, malform
 export type SessionQueryErrorCode =
   | 'SESSION_QUERY_EVENT_NOT_FOUND'
   | 'SESSION_QUERY_INVALID_CONFIG'
+  | 'SESSION_QUERY_INVALID_LINEAGE'
   | 'SESSION_QUERY_INVALID_SURFACE'
   | 'SESSION_QUERY_INVALID_WINDOW'
   | 'SESSION_QUERY_PERSISTENCE_FAILED'

docs/core-data-structures/session.md

@@ -4,6 +4,14 @@ The in-memory, event-sourced model of [dsh-session](../../packages/core/session)
 
 Source: [`packages/core/session/src/types.ts`](../../packages/core/session/src/types.ts)
 
+## Context framing
+
+`ContextEnvelope` selects the standard tagged projection or preserves a producer-owned complete frame. The latter changes framing only; the event remains a user-role `context/message` in chronological history.
+
+```ts type-equiv
+type ContextEnvelope = 'context' | 'raw'
+```
+
 ## `SessionEventMap` — the event vocabulary
 
 The append-only event types. Merge-extensible: a plugin declares extra event types via declaration merging — e.g. the [compaction seam](compaction.md) adds `compact/start` / `compact/summary` / `compact/end`, and `@deepseek-ai/dsh-hook-protocol` adds log-only `hook/invoked` / `hook/result` provenance for a hook bridge. Like `compact/*`, these are NOT `SurfaceEventType`s (no `surfaceOp`). The generated [persistence log event catalog](../persistence-catalog.md) enumerates every member — core and merged — with its payload, surface badge, and declaration site.
@@ -30,9 +38,16 @@ interface SessionEventMap {
   /**
    * In-session context injection (file-change notices, subdir AGENTS.md,
    * skill content, cron notifications, …). Rendered into the derived history
-   * as tagged synthetic context — NOT a user prompt.
+   * as synthetic context — NOT a user prompt. `envelope: 'raw'` lets a caller
+   * supply its own complete framing; `meta` is persisted JSON hidden from the
+   * model.
    */
-  'context/message': { content: ContentBlock[]; source: MessageSource }
+  'context/message': {
+    content: ContentBlock[]
+    source: MessageSource
+    envelope?: ContextEnvelope
+    meta?: JsonValue
+  }
   /** Raw stream chunk — token-level replay fidelity. */
   'assistant/chunk': { turn: number; step: number; chunk: StreamChunk }
   /**
@@ -41,7 +56,7 @@ interface SessionEventMap {
    * the model output and its accounting travel together (there is no separate
    * usage record). `usage` is absent when the adapter reported none.
    */
-  'assistant/message': { turn: number; step: number; content: ContentBlock[]; usage?: TokenUsage }
+  'assistant/message': { turn: number; step: number; content: ContentBlock[]; provenance: AssistantProvenance; usage?: TokenUsage }
   'tool/call': { turn: number; step: number; callId: CallId; name: string; arguments: string }
   'tool/result': { turn: number; step: number; callId: CallId; content: ContentBlock[]; isError: boolean; error?: { name: string; code: string }; meta?: unknown }
   /** Steering content injected between steps of a running turn. */
@@ -64,25 +79,14 @@ interface SessionEventMap {
    * Full snapshot of the {@link EpochHeader} the NEXT request is built under,
    * with the {@link RequestHeaderReason} it was recorded whole. Appended by
    * the loop inside the step, before dispatch, on a loop instance's first
-   * request-building step (`'initial'`/`'resume'`) or when a delta failed its
-   * round-trip guard (`'fallback'`); always records what the request actually
-   * used, post-`agent/request`. Anchors the header fold: reconstruction reads
-   * the latest snapshot and applies the deltas after it. NOT a
+   * request-building step (`'initial'`/`'resume'`) or when a later request's
+   * header changes (`'change'`); always records what the request actually
+   * used, post-`agent/request`. Reconstruction reads the latest snapshot. NOT a
    * {@link SurfaceEventType}: it produces no LLM message — it is the request
    * envelope, logged so every request is a pure function of the session log
    * (the reconstructability RFC).
    */
   'request/header': { header: EpochHeader; reason: RequestHeaderReason }
-  /**
-   * Amendment to the folded {@link EpochHeader}: system line-trim, name-keyed
-   * tools delta, whole replacement config, or whole replacement session
-   * prefix (an EMPTY array encodes the transition to "none"). The
-   * writer verifies `applyHeaderDelta(previous, delta)` reproduces the new
-   * header exactly and falls back to a `'fallback'` `request/header` snapshot
-   * when it cannot, so a logged delta ALWAYS round-trips. NOT a
-   * {@link SurfaceEventType}.
-   */
-  'request/header-delta': { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig; messagePrefix?: Message[] }
 }
 ```
 
@@ -97,13 +101,13 @@ export interface TodoItem {
 }
 ```
 
-### The request header events: `request/header` and `request/header-delta`
+### The request header event: `request/header`
 
-The request envelope — the `EpochHeader` (call config + rendered system prompt + assembled tool schemas + the session prefix) — is logged session state, so every conversation request is a pure function of the log (the reconstructability RFC). A `request/header` snapshot (reason `'initial' | 'resume' | 'fallback'`) anchors the fold at conversation birth, process boundaries, and delta-encoding fallbacks; `request/header-delta` events amend it mid-run. `foldRequestHeader(events)` reconstructs the header any request was built under; the writer round-trip-verifies every delta before logging it, so a well-formed log always folds. Neither is a `SurfaceEventType` — they produce no LLM message.
+The request envelope — the `EpochHeader` (call config + rendered system prompt + assembled tool schemas + the session prefix) — is logged session state, so every conversation request is a pure function of the log (the reconstructability RFC). A full `request/header` snapshot with reason `'initial'` or `'resume'` records each loop-instance boundary; a later changed request records another full snapshot with reason `'change'`. `foldRequestHeader(events)` reconstructs the header by selecting the latest snapshot. The event is not a `SurfaceEventType`: it produces no LLM message.
 
 ```ts type-equiv
 export interface EpochHeader {
-  /** The conversation's call configuration (model + sampling scalars). */
+  /** The conversation's call configuration (provider + model + sampling scalars). */
   config: LlmCallConfig
   /** Rendered system prompt text; absent for a system-less request. */
   system?: string
@@ -120,7 +124,7 @@ export interface EpochHeader {
 }
 ```
 
-Canonical form: an empty system prompt, an empty tool list, and an empty session prefix are ABSENT fields, matching how requests are built. `messagePrefix` is the durable record of the `agent/session-prefix` waterfall's product (the request is `messagePrefix + derived history`); composed once per loop instance and anchored by that instance's snapshot, so the loop never produces a prefix delta in practice — the delta arm (whole-array replacement, an empty array encoding the transition back to absence) exists for codec totality. The other delta payloads (`SystemDelta` — a common-prefix/suffix line trim; `ToolsDelta` — name-keyed added/removed/changed) live beside the events in [`packages/core/session/src/types.ts`](../../packages/core/session/src/types.ts).
+Canonical form: an empty system prompt, an empty tool list, and an empty session prefix are absent fields, matching how requests are built. `messagePrefix` is the durable record of the `agent/session-prefix` waterfall's product (the request is `messagePrefix + derived history`); it is composed once per loop instance and included in every full snapshot that instance records. Legacy v0 logs containing the removed `request/header-delta` event or its full-snapshot `fallback` reason are rejected at seed, append, and persistence-load boundaries rather than replayed incompletely.
 
 ## `SessionEvent<T>` — one log entry
 
@@ -150,9 +154,11 @@ type SessionEvent<T extends SessionEventType = SessionEventType> = {
 
 `SessionEventType = keyof SessionEventMap`. Because `SessionEventMap` is merge-extensible, switches over `SessionEvent` must NOT use `assertNever` — a plugin-added variant is a valid unknown value; handle the known cases and fall through `default`.
 
+For `assistant/message`, a present `sourceEventSeqs: []` is a complete known-empty provider stream, while an absent field means legacy or otherwise unrecorded provenance. The loop writes the field for every successful model call; every other surface event requires a non-empty list when the field is present.
+
 ## Surface types
 
-The five message-producing types (`SurfaceEventType` — `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`) carry surface metadata declaring how they join the derived surface linked list. See the [session surface RFC](../rfc/implemented/architecture/2026-06-18-session-surface.md).
+The five message-producing types (`SurfaceEventType` — `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`) carry surface metadata declaring how they join the ordered derived surface. See the [session surface RFC](../rfc/implemented/architecture/2026-06-18-session-surface.md).
 
 ### `SurfaceEventType` — the message-producing subset of event types
 
@@ -173,7 +179,7 @@ export type SurfaceOp =
   | { op: 'replace'; start: number; end: number }
 ```
 
-`'append'` is the normal tail-append path. `replace` shadows surface nodes from `start` through `end` inclusive (both must be valid surface node seqs; `start === end` replaces a single node) and inserts the new node in their place.
+`'append'` is the normal tail-append path. `replace` shadows surface entries from `start` through `end` inclusive (both must be valid surface seqs; `start === end` replaces a single entry) and inserts the new event in their place.
 
 ### `SurfaceIntent` — the parameter to `session.append()`
 
@@ -186,19 +192,11 @@ export interface SurfaceIntent {
 
 Required for `SurfaceEventType` events — every message-producing event must declare how it joins the surface, the sole source of derived history. Non-surface types reject it at compile time.
 
-### `SurfaceNode` — a node in the surface linked list
-
-```ts type-equiv
-export interface SurfaceNode {
-  seq: number
-  prev: number | null
-  next: number | null
-}
-```
+The same provenance distinction applies here: only `assistant/message` may carry a present empty `sourceEventSeqs`; omission does not assert that its source stream was empty.
 
 ### `SurfaceFoldReplacement` and `SurfaceFoldResult` — a complete surface replay
 
-`foldSurface(events)` returns detached current nodes together with the actual node seqs shadowed by each declared replacement range. `SurfaceManager` uses the same transition functions for its incremental cache.
+`foldSurface(events)` returns detached current event sequences together with the actual sequences shadowed by each declared replacement range. `SurfaceManager` uses the same transitions for its incremental cache without retaining replacement history. Its `replaceGeneration` increments for each replacement so incremental consumers can distinguish pure tail growth from a rewrite.
 
 ```ts type-equiv
 export interface SurfaceFoldReplacement {
@@ -211,7 +209,7 @@ export interface SurfaceFoldReplacement {
 
 ```ts type-equiv
 export interface SurfaceFoldResult {
-  nodes: SurfaceNode[]
+  nodes: number[]
   replacements: SurfaceFoldReplacement[]
 }
 ```
@@ -221,11 +219,12 @@ export interface SurfaceFoldResult {
 `Session.deriveMessages()` projects the event log into the `Message[]` the model sees — cached (each surface node projected once, when first seen; a surface rewrite rebuilds) and frozen (a fresh array per call over shared, deep-frozen messages, so mutating logged history through a projection is unrepresentable). `deriveEventMessage(event)` is the per-node pure function the fold applies — public so external reconstructors and the dev invariant project a log prefix with exactly the same rules and cannot disagree with the cache. The projection rules:
 
 - `user/message` → a user message.
-- `assistant/message` → an assistant message. Raw `assistant/chunk` events are replay/UI data and are **skipped** in derivation (the assembled message is authoritative). An **empty-content** `assistant/message` is also skipped — a max-tokens step cut off with no content still records an `assistant/message` to host its `usage`, but a content-less assistant turn must not enter the provider transcript.
+- `assistant/message` → an assistant message with the event's provider/model provenance and optional adapter-private replay state. Raw `assistant/chunk` events are replay/UI data and are **skipped** in derivation (the assembled message is authoritative). An **empty-content** `assistant/message` is also skipped — a max-tokens step cut off with no content still records an `assistant/message` to host its usage/provenance, but a content-less assistant turn must not enter the provider transcript.
 - `tool/result` → a user message carrying a `tool-result` block.
-- `context/message`, `steering/message` → user-role messages wrapped in a tagged envelope (`<context source="…">…</context>`) at their chronological position — the "system-reminder" pattern; the model distinguishes them from real prompts by the envelope.
+- `context/message` → a user-role message at its chronological position. The default `envelope` is `context`, which wraps content as `<context source="…">…</context>`; `envelope: 'raw'` uses caller-owned framing verbatim. Optional JSON `meta` remains in the event log and is never rendered.
+- `steering/message` → a user-role message wrapped in `<steering source="…">…</steering>` at its chronological position.
 
-Everything else (`turn/*`, `step/*`) is structural and does not project into a message. Token usage is observed on `assistant/message.usage` (the step that produced it); an operational error's step number is on `turn/end.reason` for `kind: 'error'`.
+Everything else (`turn/*`, `step/*`) is structural and does not project into a message. Token usage is observed on `assistant/message.usage` (the step that produced it); an operational error's step number is on `turn/end.reason` for `kind: 'error'`. Because this unreleased format intentionally has no compatibility promise, seed/load validation rejects request headers without provider+model and assistant messages without provider/model provenance instead of guessing a route for historical data.
 
 ## Live-session fork API
 

docs/core-data-structures/spill.md

@@ -0,0 +1,56 @@
+# Spill Storage
+
+The spill storage seam — a [capability seam](../rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md) that persists a tool's oversized text and returns a model-facing locator plus retrieval guidance, split across packages: interface ([dsh-spill](../../packages/spill/spill), `ctx.spillStore`), implementation ([dsh-spill-local](../../packages/spill/spill-local), private session-scoped files on the host filesystem), and consumer ([dsh-spill-policy](../../packages/spill/spill-policy), the `tools/post-execute` policy). Spill is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). Preview mechanics stay in [dsh-retention](../../packages/util/retention); this seam only saves the final text the policy hands it.
+
+Source: [`packages/spill/spill/src/types.ts`](../../packages/spill/spill/src/types.ts)
+
+## The save request
+
+`saveText` is the whole seam: persist `content` verbatim, return an opaque locator, a backend-supplied retrieval hint, and the exact byte count. The request carries the save-time storage namespace (`owner`), WHERE it came from (`source`, descriptive provenance for naming and inspection — not access control), and a `suggestedName` the backend may use as a naming hint (it is not a path).
+
+```ts type-equiv
+interface SaveTextSpill {
+  owner: SpillOwner
+  source: SpillSource
+  suggestedName: string
+  content: string
+}
+```
+
+```ts type-equiv
+interface SpillOwner {
+  sessionId: SessionId
+}
+```
+
+`SpillOwner.sessionId` is the save-time storage namespace. Forked sessions inherit existing spill locators from the seeded log; those artifacts are not copied or re-owned, and spills produced after the fork use the child session id. A retention-period cleanup may expire old locators with other old session artifacts; the spill seam does not define a per-session cleanup policy.
+
+```ts type-equiv
+interface SpillSource {
+  toolName: string
+  callId: CallId
+  label: string
+}
+```
+
+## The result
+
+```ts type-equiv
+interface SpillRef {
+  locator: SpillLocator
+  bytes: number
+  retrievalHint: string
+}
+```
+
+`SpillLocator` is a [branded](core.md#branded-ids) model-facing handle returned by the backend. The local backend renders it as a filesystem path; a remote or database backend can render a URI, key, or command token. Consumers treat it as opaque and render it with `retrievalHint` instead of assuming `read` is always the right retrieval mechanism.
+
+```ts type-equiv
+type SpillLocator = Branded<'SpillLocator'>
+```
+
+## The service
+
+`SpillStore` (`ctx.spillStore`, defined in [`packages/spill/spill/src/index.ts`](../../packages/spill/spill/src/index.ts)) is a one-method abstract service: `saveText(input) → Promise<SpillRef>`. It persists the FULL `content` and REJECTS on a real storage failure (permissions, ENOSPC, backend unavailable). The seam owns storage only: no retention policy, no tool-result replacement, no retrieval/search API.
+
+The local backend ([dsh-spill-local](../../packages/spill/spill-local)) writes under `<root>/session-<hash>/<random>-<safeName>` — a configured or lazily-created private (0700) root, a `sha256(sessionId)` session subdir, and an exclusive owner-only (`open(path, 'wx', 0o600)`) write so a planted symlink cannot redirect it. Its `locator` is the local path and its `retrievalHint` tells the model to use `read` or `grep` on that path. The policy consumer ([dsh-spill-policy](../../packages/spill/spill-policy)) replaces an over-`maxInlineBytes` plain-text final result with a retention-library head/tail preview plus the spill reference, best-effort: a save failure keeps the original inline result rather than turning a successful call into an `isError`.

docs/core-data-structures/token-meter.md

@@ -0,0 +1,39 @@
+# Token Meter
+
+`@deepseek-ai/dsh-token-meter` exposes one detached replay snapshot for request pressure and positional surface pricing. `logRevision` is the number of durable events consumed for every field in the measurement.
+
+Source: [`packages/llm/token-meter/src/types.ts`](../../packages/llm/token-meter/src/types.ts)
+
+## `TokenMeasurement`
+
+```ts type-equiv
+interface TokenMeasurement {
+  /** Number of durable events consumed; equal to the next unread event seq. */
+  readonly logRevision: number
+  /** Provider or heuristic anchor used for this measurement. */
+  readonly baseline: TokenMeasurementBaseline
+  /** Signed repricing of current surface content relative to the baseline anchor. */
+  readonly surfaceDeltaTokens: number
+  /** Non-negative current request-and-response pressure. */
+  readonly totalTokens: number
+  /** Total heuristic tokens across the current surface. */
+  readonly surfaceTokens: number
+  /** Current surface nodes in positional head-to-tail order. */
+  readonly nodes: readonly TokenSurfaceNode[]
+}
+```
+
+`baseline.kind === 'usage'` means the latest successful provider call has the same canonical request envelope and its total is no lower than that call's full heuristic anchor. `estimated` means no reusable conservative usage anchor exists, so the service priced the complete envelope and surface with its fixed heuristic. A later successful request replaces the earlier anchor; signed `surfaceDeltaTokens` preserves growth and shrinkage relative to a matching anchor. `totalTokens` remains request-and-response pressure, while `surfaceTokens` is the surface-only heuristic total and equals the sum of the node prices.
+
+## `TokenSurfaceNode`
+
+```ts type-equiv
+interface TokenSurfaceNode {
+  /** Durable sequence number of the surface event. */
+  readonly seq: number
+  /** Heuristic tokens for the exact message projected by this node. */
+  readonly tokens: number
+}
+```
+
+Surface order is authoritative; replacement nodes can have higher durable seqs than later positional nodes. The snapshot is immutable and does not grow when the underlying replay fold advances.

docs/core-data-structures/tools.md

@@ -10,7 +10,7 @@ A `ToolSchema` (the model-facing fields) plus the `execute` function and optiona
 
 ```ts type-equiv
 interface ToolDefinition extends ToolSchema {
-  execute(args: unknown, exec: ToolExecution): Promise<ToolExecuteReturn>
+  execute(args: unknown, exec: ToolRunContext): Promise<ToolExecuteReturn>
   /**
    * Cooperative tool-call timeout budget in milliseconds. Omit for no deadline.
    * Enforced by `@deepseek-ai/dsh-timeout-policy` (a `tools/execute` wrapper); it
@@ -120,6 +120,19 @@ interface ToolExecutionInput {
 }
 ```
 
+A tool body receives the runtime extension. `deferContext()` is the composite-tool channel: it records nested-dispatch context without injecting inside the still-open outer call.
+
+```ts type-equiv
+interface ToolRunContext extends ToolExecution {
+  /**
+   * Defer one nested-dispatch context until this tool's final result reaches
+   * the agent loop. Contexts retain their individual source, envelope, and
+   * metadata and are emitted in call order.
+   */
+  deferContext(context: HookContext): void
+}
+```
+
 ```ts type-equiv
 interface ToolExecution extends ToolExecutionInput {
   /** Registry-assigned identity shared with nested calls only as their opaque `parent` token. */
@@ -146,17 +159,16 @@ interface ToolExecutionResult {
    */
   error?: ToolErrorInfo
   /**
-   * Extra model-facing context a `tools/post-execute` listener attached for the
-   * NEXT request (Claude Code's PostToolUse `additionalContext`). It is NOT part
-   * of this call's `content` — `content`/`feedback` shape the tool RESULT, but
-   * `additionalContext` is a SEPARATE `context/message`. A step can carry
-   * multiple tool calls, so the loop accepts every call's `additionalContext`
-   * into the active-batch FIFO and appends it only when that batch settles. A
-   * successful batch places context AFTER all its `tool/result`s; an interrupted
-   * batch places it after every recorded result and before turn close. Carried
-   * on the result purely to ferry it from `execute()` up to that FIFO.
+   * Extra model-facing contexts deferred by a composite tool or attached by
+   * `tools/post-execute` listeners for the NEXT request. They are not part of
+   * this call's `content`: the loop accepts them into the active-batch FIFO and
+   * appends them after every recorded `tool/result` when the batch settles, even
+   * when execution is interrupted. The array preserves each context's source,
+   * envelope, metadata, and production order. An accepted outer call keeps
+   * deferred contexts before decision contexts; a block retains only contexts
+   * supplied by the blocking decision.
    */
-  additionalContext?: HookContext
+  additionalContexts?: HookContext[]
   /**
    * The tool-private presentation payload from a successful `execute` (the object
    * return form). Threaded onto the `tool/result` session event and back into
@@ -182,8 +194,8 @@ type PreToolDecision =
 
 ```ts type-equiv
 type PostToolDecision =
-  | { kind: 'accept'; content?: ContentBlock[]; additionalContext?: HookContext }
-  | { kind: 'block'; feedback: ContentBlock[]; additionalContext?: HookContext }
+  | { kind: 'accept'; content?: ContentBlock[]; additionalContexts?: HookContext[] }
+  | { kind: 'block'; feedback: ContentBlock[]; additionalContexts?: HookContext[] }
 ```
 
 Call `next()` for the default or return a decision to short-circuit. Pre-policy may deny or ask; only `allowed-once` proceeds, while a non-grant, missing approval channel or service, or agent-less request becomes a denial. Guards may still impose a final denial. Arguments cannot be rewritten because history, audit, UI, and execution must agree.

docs/event-producer-consumer.md

@@ -7,39 +7,39 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 
 | Event | Mode | Declared in | Dispatchers | Listeners |
 | --- | --- | --- | --- | --- |
-| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:140`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) |
-| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:149`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) |
-| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:284`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
-| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:203`](../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:213`](../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:168`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
-| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:225`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
-| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:240`](../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:181`](../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:158`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) |
-| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:251`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
-| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:261`](../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) |
-| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:271`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
+| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:154`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) |
+| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:163`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) |
+| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:298`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
+| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:217`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`time-context`](../packages/context/time-context), [`user-approval`](../packages/ui/user-approval) |
+| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:227`](../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:182`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
+| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp) |
+| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:254`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) |
+| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:195`](../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:172`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) |
+| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:265`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
+| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:275`](../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) |
+| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:285`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
 | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../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:59`](../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:68`](../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:51`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
-| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) |
-| `session/created` | `emit` | [`packages/core/session/src/index.ts:47`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) |
-| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:57`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - |
-| `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio) |
-| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:79`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) |
+| `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:61`](../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:70`](../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:53`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
+| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:40`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) |
+| `session/created` | `emit` | [`packages/core/session/src/index.ts:46`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) |
+| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) |
+| `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter), [`workspace-context`](../packages/context/workspace-context) |
+| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:78`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) |
 | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:108`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) |
 | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:82`](../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:88`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) |
 | `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:99`](../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:27`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - |
+| `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:27`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | [`acp`](../packages/ui/acp) |
 | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:33`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - |
 | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:116`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - |
 | `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:89`](../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:98`](../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/post-execute` | `waterfall` | [`packages/core/tools/src/index.ts:98`](../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), [`spill-policy`](../packages/spill/spill-policy), [`workspace-context`](../packages/context/workspace-context) |
 | `tools/pre-execute` | `waterfall` | [`packages/core/tools/src/index.ts:80`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
-| `tools/result` | `emit` | [`packages/core/tools/src/index.ts:106`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`events.dispatch`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
+| `tools/result` | `emit` | [`packages/core/tools/src/index.ts:106`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`events.dispatch`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`workspace-context`](../packages/context/workspace-context) |
 | `workflow/agent-end` | `emit` | [`packages/workflow/workflow/src/index.ts:81`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
 | `workflow/agent-start` | `emit` | [`packages/workflow/workflow/src/index.ts:70`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
 | `workflow/end` | `emit` | [`packages/workflow/workflow/src/index.ts:91`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |

docs/module-graph.md

@@ -9,12 +9,16 @@ Inter-package dependencies among the `@deepseek-ai/dsh-*` harness packages, deri
 flowchart TD
   subgraph group_util["packages/util"]
     pkg_brand["brand"]
+    pkg_home["home"]
+    pkg_paths["paths"]
+    pkg_retention["retention"]
     pkg_timeout["timeout"]
   end
   subgraph group_llm["packages/llm"]
     pkg_llm["llm"]
     pkg_llm_deepseek["llm-deepseek"]
     pkg_llm_pi_ai["llm-pi-ai"]
+    pkg_token_meter["token-meter"]
   end
   subgraph group_core["packages/core"]
     pkg_agent["agent"]
@@ -35,6 +39,7 @@ flowchart TD
     pkg_fs_local["fs-local"]
     pkg_fs_policy["fs-policy"]
     pkg_tool_fs["tool-fs"]
+    pkg_tool_fs_search["tool-fs-search"]
   end
   subgraph group_skill["packages/skill"]
     pkg_skill["skill"]
@@ -62,6 +67,11 @@ flowchart TD
     pkg_web_search_exa["web-search-exa"]
     pkg_web_search_perplexity["web-search-perplexity"]
   end
+  subgraph group_spill["packages/spill"]
+    pkg_spill["spill"]
+    pkg_spill_local["spill-local"]
+    pkg_spill_policy["spill-policy"]
+  end
   subgraph group_timeout["packages/timeout"]
     pkg_timeout_policy["timeout-policy"]
   end
@@ -86,6 +96,7 @@ flowchart TD
   end
   subgraph group_support["packages/support"]
     pkg_acp_snapshot["acp-snapshot"]
+    pkg_agent_loop_testkit["agent-loop-testkit"]
     pkg_invariants["invariants"]
     pkg_llm_replay["llm-replay"]
     pkg_loader_smoke["loader-smoke"]
@@ -107,6 +118,7 @@ flowchart TD
   end
   subgraph group_context["packages/context"]
     pkg_time_context["time-context"]
+    pkg_workspace_context["workspace-context"]
   end
   subgraph group_examples["packages/examples"]
     pkg_acp_demo["acp-demo"]
@@ -152,6 +164,8 @@ flowchart TD
   pkg_fs --> pkg_llm
   pkg_web --> pkg_llm
   pkg_sandbox --> pkg_llm
+  pkg_token_meter --> pkg_llm
+  pkg_token_meter --> pkg_session
   pkg_agent --> pkg_brand
   pkg_agent --> pkg_llm
   pkg_agent --> pkg_scope
@@ -162,6 +176,7 @@ flowchart TD
   pkg_fs_local --> pkg_fs
   pkg_fs_policy --> pkg_fs
   pkg_skill_local --> pkg_fs
+  pkg_skill_local --> pkg_home
   pkg_skill_local --> pkg_skill
   pkg_compact --> pkg_llm
   pkg_compact --> pkg_session
@@ -170,6 +185,9 @@ flowchart TD
   pkg_web_search_deepseek --> pkg_web
   pkg_web_search_exa --> pkg_web
   pkg_web_search_perplexity --> pkg_web
+  pkg_spill --> pkg_brand
+  pkg_spill --> pkg_llm
+  pkg_spill --> pkg_session
   pkg_session_persistence --> pkg_session
   pkg_llm_replay --> pkg_llm
   pkg_llm_replay --> pkg_session
@@ -181,6 +199,8 @@ flowchart TD
   pkg_compact_basic --> pkg_compact
   pkg_compact_basic --> pkg_llm
   pkg_compact_basic --> pkg_session
+  pkg_compact_basic --> pkg_token_meter
+  pkg_spill_local --> pkg_spill
   pkg_hook_protocol --> pkg_bash
   pkg_hook_protocol --> pkg_session
   pkg_session_persistence_jsonl --> pkg_session
@@ -203,7 +223,6 @@ flowchart TD
   pkg_user_interaction --> pkg_agent
   pkg_user_interaction --> pkg_llm
   pkg_time_context --> pkg_agent
-  pkg_time_context --> pkg_system_prompt
   pkg_tasks --> pkg_agent
   pkg_tasks --> pkg_brand
   pkg_tasks --> pkg_session
@@ -238,8 +257,10 @@ flowchart TD
   pkg_agent_loop --> pkg_tools
   pkg_tool_bash --> pkg_agent
   pkg_tool_bash --> pkg_bash
+  pkg_tool_bash --> pkg_home
   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_tasks
   pkg_tool_bash --> pkg_tools
@@ -249,6 +270,13 @@ flowchart TD
   pkg_tool_fs --> pkg_session
   pkg_tool_fs --> pkg_system_prompt
   pkg_tool_fs --> pkg_tools
+  pkg_tool_fs_search --> pkg_bash
+  pkg_tool_fs_search --> pkg_llm
+  pkg_tool_fs_search --> pkg_retention
+  pkg_tool_fs_search --> pkg_session
+  pkg_tool_fs_search --> pkg_spill
+  pkg_tool_fs_search --> pkg_system_prompt
+  pkg_tool_fs_search --> pkg_tools
   pkg_tool_skill --> pkg_agent
   pkg_tool_skill --> pkg_llm
   pkg_tool_skill --> pkg_skill
@@ -261,6 +289,11 @@ flowchart TD
   pkg_tool_web --> pkg_system_prompt
   pkg_tool_web --> pkg_tools
   pkg_tool_web --> pkg_web
+  pkg_spill_policy --> pkg_llm
+  pkg_spill_policy --> pkg_retention
+  pkg_spill_policy --> pkg_session
+  pkg_spill_policy --> pkg_spill
+  pkg_spill_policy --> pkg_tools
   pkg_timeout_policy --> pkg_llm
   pkg_timeout_policy --> pkg_timeout
   pkg_timeout_policy --> pkg_tools
@@ -273,7 +306,13 @@ flowchart TD
   pkg_hooks_codex --> pkg_hook_protocol
   pkg_hooks_codex --> pkg_llm
   pkg_hooks_codex --> pkg_session
+  pkg_hooks_codex --> pkg_session_persistence
   pkg_hooks_codex --> pkg_tools
+  pkg_agent_loop_testkit --> pkg_agent
+  pkg_agent_loop_testkit --> pkg_llm
+  pkg_agent_loop_testkit --> pkg_session
+  pkg_agent_loop_testkit --> pkg_system_prompt
+  pkg_agent_loop_testkit --> pkg_tools
   pkg_acp --> pkg_agent
   pkg_acp --> pkg_bash
   pkg_acp --> pkg_llm
@@ -281,12 +320,19 @@ flowchart TD
   pkg_acp --> pkg_sandbox
   pkg_acp --> pkg_session
   pkg_acp --> pkg_session_persistence
+  pkg_acp --> pkg_system_prompt
   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
   pkg_tool_ask_user --> pkg_user_interaction
+  pkg_workspace_context --> pkg_agent
+  pkg_workspace_context --> pkg_fs
+  pkg_workspace_context --> pkg_llm
+  pkg_workspace_context --> pkg_paths
+  pkg_workspace_context --> pkg_session
+  pkg_workspace_context --> pkg_tools
   pkg_repeat_tool_guard --> pkg_agent
   pkg_repeat_tool_guard --> pkg_tools
   pkg_mcp_client --> pkg_llm
@@ -319,6 +365,7 @@ flowchart TD
   pkg_hooks_claude --> pkg_hook_protocol
   pkg_hooks_claude --> pkg_llm
   pkg_hooks_claude --> pkg_session
+  pkg_hooks_claude --> pkg_session_persistence
   pkg_hooks_claude --> pkg_subagent
   pkg_hooks_claude --> pkg_tools
   pkg_subagent_mock --> pkg_agent
@@ -331,6 +378,7 @@ flowchart TD
   pkg_jsonrpc --> pkg_subagent
   pkg_agent_spine_demo --> pkg_agent
   pkg_agent_spine_demo --> pkg_agent_loop
+  pkg_agent_spine_demo --> pkg_home
   pkg_agent_spine_demo --> pkg_invariants
   pkg_agent_spine_demo --> pkg_llm
   pkg_agent_spine_demo --> pkg_session
@@ -342,6 +390,7 @@ flowchart TD
   pkg_agent_spine_demo --> pkg_tool_skill
   pkg_agent_spine_demo --> pkg_tool_tasks
   pkg_agent_spine_demo --> pkg_tools
+  pkg_agent_spine_demo --> pkg_workspace_context
   pkg_workflow_workerthread --> pkg_agent
   pkg_workflow_workerthread --> pkg_brand
   pkg_workflow_workerthread --> pkg_llm
@@ -361,6 +410,7 @@ flowchart TD
   pkg_acp_demo --> pkg_session_persistence_jsonl
   pkg_acp_demo --> pkg_tools
   pkg_acp_demo --> pkg_user_interaction
+  pkg_acp_demo --> pkg_workspace_context
   pkg_stdio_demo --> pkg_agent
   pkg_stdio_demo --> pkg_agent_spine_demo
   pkg_stdio_demo --> pkg_app_boot
@@ -371,11 +421,15 @@ flowchart TD
   pkg_stdio_demo --> pkg_tool_ask_user
   pkg_stdio_demo --> pkg_tools
   pkg_stdio_demo --> pkg_user_interaction
+  pkg_stdio_demo --> pkg_workspace_context
 ```
 
 | Package | Group | Depends on |
 | --- | --- | --- |
 | [`brand`](../packages/util/brand) | `util` | — |
+| [`home`](../packages/util/home) | `util` | — |
+| [`paths`](../packages/util/paths) | `util` | — |
+| [`retention`](../packages/util/retention) | `util` | — |
 | [`timeout`](../packages/util/timeout) | `util` | — |
 | [`scope`](../packages/core/scope) | `core` | — |
 | [`skill`](../packages/skill/skill) | `skill` | — |
@@ -396,21 +450,24 @@ flowchart TD
 | [`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) |
+| [`token-meter`](../packages/llm/token-meter) | `llm` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
 | [`agent`](../packages/core/agent) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
 | [`bash`](../packages/bash/bash) | `bash` | [`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) |
+| [`skill-local`](../packages/skill/skill-local) | `skill` | [`fs`](../packages/fs/fs), [`home`](../packages/util/home), [`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) |
+| [`spill`](../packages/spill/spill) | `spill` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`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) |
 | [`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) |
+| [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter) |
+| [`spill-local`](../packages/spill/spill-local) | `spill` | [`spill`](../packages/spill/spill) |
 | [`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) |
@@ -418,7 +475,7 @@ flowchart TD
 | [`invariants`](../packages/support/invariants) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session) |
 | [`user-approval`](../packages/ui/user-approval) | `ui` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`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) |
-| [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt) |
+| [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent) |
 | [`tasks`](../packages/tasks/tasks) | `tasks` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) |
 | [`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), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) |
@@ -426,17 +483,21 @@ flowchart TD
 | [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) |
 | [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) |
 | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`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), [`sandbox`](../packages/sandbox/sandbox), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
+| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`home`](../packages/util/home), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`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-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`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), [`scope`](../packages/core/scope), [`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) |
+| [`spill-policy`](../packages/spill/spill-policy) | `spill` | [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`tools`](../packages/core/tools) |
 | [`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` | [`scope`](../packages/core/scope), [`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), [`tools`](../packages/core/tools) |
-| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`permission`](../packages/ui/permission), [`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) |
+| [`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) |
+| [`agent-loop-testkit`](../packages/support/agent-loop-testkit) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
+| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`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) |
+| [`workspace-context`](../packages/context/workspace-context) | `context` | [`agent`](../packages/core/agent), [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`paths`](../packages/util/paths), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
 | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) |
 | [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) |
 | [`tool-tasks`](../packages/tasks/tool-tasks) | `tasks` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
@@ -444,12 +505,12 @@ flowchart TD
 | [`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), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
-| [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) |
+| [`hooks-claude`](../packages/hooks/hooks-claude) | `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), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) |
 | [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) |
 | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) |
-| [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`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), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools) |
+| [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`home`](../packages/util/home), [`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), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) |
 | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
 | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
 | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
-| [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
-| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
+| [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) |
+| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) |

docs/persistence-catalog.md

@@ -37,7 +37,7 @@ Source: [`packages/ui/user-approval/src/index.ts:56`](../packages/ui/user-approv
 
 #### `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).
+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 }
@@ -57,19 +57,19 @@ Raw stream chunk — token-level replay fidelity.
 
 Types: [StreamChunk](core-data-structures/llm-streaming.md)
 
-Source: [`packages/core/session/src/types.ts:242`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:219`](../packages/core/session/src/types.ts)
 
 #### `assistant/message` — surface
 
 Assembled assistant message for one step (derived history uses this). Carries the step's `usage` when the adapter reported token accounting, so the model output and its accounting travel together (there is no separate usage record). `usage` is absent when the adapter reported none.
 
 ```ts persistence-catalog
-'assistant/message': { turn: number; step: number; content: ContentBlock[]; usage?: TokenUsage }
+'assistant/message': { turn: number; step: number; content: ContentBlock[]; provenance: AssistantProvenance; usage?: TokenUsage }
 ```
 
 Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-structures/llm-streaming.md)
 
-Source: [`packages/core/session/src/types.ts:249`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:226`](../packages/core/session/src/types.ts)
 
 ### `bash/*`
 
@@ -93,7 +93,7 @@ Marks the end of a compaction — log-only, releases the lock. `error` set if su
 'compact/end': { turn: number; error?: string }
 ```
 
-Source: [`packages/compact/compact/src/types.ts:38`](../packages/compact/compact/src/types.ts)
+Source: [`packages/compact/compact/src/types.ts:40`](../packages/compact/compact/src/types.ts)
 
 #### `compact/start` — log-only
 
@@ -110,7 +110,7 @@ Source: [`packages/compact/compact/src/types.ts:15`](../packages/compact/compact
 Provenance record of a completed summarization — log-only, no surfaceOp. The summary content is in `data.summary`; the actual surface replacement is performed by a subsequent `user/message` event that shadows the compacted range.
 
 ```ts persistence-catalog
-'compact/summary': { summary: ContentBlock[]; shadowedRange: { start: number; end: number }; shadowedSeqs: number[]; shadowedTokenCount: number; model: string; maxTokens?: number }
+'compact/summary': { summary: ContentBlock[]; shadowedRange: { start: number; end: number }; shadowedSeqs: number[]; shadowedTokenCount: number; provider: string; model: string; maxTokens?: number }
 ```
 
 Types: [ContentBlock](core-data-structures/core.md)
@@ -121,15 +121,15 @@ Source: [`packages/compact/compact/src/types.ts:22`](../packages/compact/compact
 
 #### `context/message` — surface
 
-In-session context injection (file-change notices, subdir AGENTS.md, skill content, cron notifications, …). Rendered into the derived history as tagged synthetic context — NOT a user prompt.
+In-session context injection (file-change notices, subdir AGENTS.md, skill content, cron notifications, …). Rendered into the derived history as synthetic context — NOT a user prompt. `envelope: 'raw'` lets a caller own the complete model-facing frame; `meta` is durable JSON state omitted from the model projection.
 
 ```ts persistence-catalog
-'context/message': { content: ContentBlock[]; source: MessageSource }
+'context/message': { content: ContentBlock[]; source: MessageSource; envelope?: ContextEnvelope; meta?: JsonValue }
 ```
 
 Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
 
-Source: [`packages/core/session/src/types.ts:240`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:212`](../packages/core/session/src/types.ts)
 
 ### `hook/*`
 
@@ -177,29 +177,19 @@ Durable record of a prompt veto and its reason. It is log-only: the blocked prom
 
 Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
 
-Source: [`packages/core/session/src/types.ts:234`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:204`](../packages/core/session/src/types.ts)
 
 ### `request/*`
 
 #### `request/header` — log-only
 
-Full EpochHeader for the next request, appended inside its step before dispatch. It is log-only and anchors subsequent deltas.
+Full header for the next request, appended inside its step before dispatch. It is log-only; the latest snapshot reconstructs the request header.
 
 ```ts persistence-catalog
 'request/header': { header: EpochHeader; reason: RequestHeaderReason }
 ```
 
-Source: [`packages/core/session/src/types.ts:277`](../packages/core/session/src/types.ts)
-
-#### `request/header-delta` — log-only
-
-Log-only amendment to the folded EpochHeader. System and tools use their delta codecs; config and prefix replace whole, with an empty prefix encoding removal. Writers verify round-trip equality or log a fallback snapshot.
-
-```ts persistence-catalog
-'request/header-delta': { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig; messagePrefix?: Message[] }
-```
-
-Source: [`packages/core/session/src/types.ts:283`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:251`](../packages/core/session/src/types.ts)
 
 ### `steering/*`
 
@@ -213,7 +203,7 @@ Steering content injected between steps of a running turn.
 
 Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
 
-Source: [`packages/core/session/src/types.ts:267`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:244`](../packages/core/session/src/types.ts)
 
 ### `step/*`
 
@@ -225,7 +215,7 @@ Closes step `step` of turn `turn`.
 'step/end': { turn: number; step: number }
 ```
 
-Source: [`packages/core/session/src/types.ts:227`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:197`](../packages/core/session/src/types.ts)
 
 #### `step/start` — log-only
 
@@ -235,13 +225,13 @@ Opens step `step` of turn `turn` — one model call plus the tool executions it
 'step/start': { turn: number; step: number }
 ```
 
-Source: [`packages/core/session/src/types.ts:225`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:195`](../packages/core/session/src/types.ts)
 
 ### `todo/*`
 
 #### `todo/write` — log-only
 
-Whole-list snapshot; the latest write wins on replay. It is log-only UI state and never enters derived model history.
+Whole-list snapshot; latest write wins on replay. Log-only UI state; never derived history.
 
 ```ts persistence-catalog
 'todo/write': { todos: TodoItem[] }
@@ -249,7 +239,7 @@ Whole-list snapshot; the latest write wins on replay. It is log-only UI state an
 
 Types: [TodoItem](core-data-structures/session.md)
 
-Source: [`packages/core/session/src/types.ts:272`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:246`](../packages/core/session/src/types.ts)
 
 ### `tool/*`
 
@@ -263,11 +253,11 @@ The model requested one tool invocation: `name` with the raw `arguments` JSON st
 
 Types: [CallId](core-data-structures/core.md)
 
-Source: [`packages/core/session/src/types.ts:255`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:232`](../packages/core/session/src/types.ts)
 
 #### `tool/code-dispatch` — log-only
 
-One bridged sub-dispatch from a `run_code` program: the parent `run_code` call id, the deterministic sub-call id (`<parent>:code:<n>`), the tool `name` with its JSON-normalized `arguments` — the exact value dispatched, normalized before dispatch, so this append can never fail on payload shape — whether the sub-call errored, and a bounded `resultSummary` of its model-facing text.
+One bridged sub-dispatch from a `run_code` program: the parent `run_code` call id, the deterministic sub-call id (`<parent>:code:<n>`), the tool `name` with its JSON-normalized `arguments` — the exact value dispatched, normalized BEFORE dispatch, so this append can never fail on payload shape — whether the sub-call errored, and a bounded `resultSummary` of its model-facing text. Before bounding, occurrences of a non-root session workspace path are normalized to `.` so host-specific absolute path lengths cannot change the summary. Log-only: `deriveMessages()` ignores it, so sub-calls never re-enter model context; persistence and UIs get every call. Appended inside the parent `run_code`'s execution (the bridge drains its queue before returning), so the turn-enclosure invariant holds by construction.
 
 ```ts persistence-catalog
 'tool/code-dispatch': { parentCallId: CallId; subCallId: CallId; name: string; arguments: unknown; isError: boolean; resultSummary: string }
@@ -275,7 +265,7 @@ One bridged sub-dispatch from a `run_code` program: the parent `run_code` call i
 
 Types: [CallId](core-data-structures/core.md)
 
-Source: [`packages/core/tools/src/code-mode.ts:25`](../packages/core/tools/src/code-mode.ts)
+Source: [`packages/core/tools/src/code-mode.ts:34`](../packages/core/tools/src/code-mode.ts)
 
 #### `tool/result` — surface
 
@@ -287,7 +277,7 @@ A completed tool call's model-facing result, plus an optional tool-private `meta
 
 Types: [CallId](core-data-structures/core.md) · [ContentBlock](core-data-structures/core.md)
 
-Source: [`packages/core/session/src/types.ts:265`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:242`](../packages/core/session/src/types.ts)
 
 ### `turn/*`
 
@@ -301,7 +291,7 @@ Closes turn `turn` with the TurnEndReason that ended it. The loop fires the awai
 
 Types: [TurnEndReason](core-data-structures/session.md)
 
-Source: [`packages/core/session/src/types.ts:223`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:193`](../packages/core/session/src/types.ts)
 
 #### `turn/start` — log-only
 
@@ -313,7 +303,7 @@ Opens turn `turn`. `trigger` records what started it — a drained message batch
 
 Types: [TurnTrigger](core-data-structures/session.md)
 
-Source: [`packages/core/session/src/types.ts:217`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:187`](../packages/core/session/src/types.ts)
 
 ### `user/*`
 
@@ -327,4 +317,4 @@ A user-visible prompt (queued message drained at turn start).
 
 Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
 
-Source: [`packages/core/session/src/types.ts:229`](../packages/core/session/src/types.ts)
+Source: [`packages/core/session/src/types.ts:199`](../packages/core/session/src/types.ts)

docs/rfc/INDEX.md

@@ -9,6 +9,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
 | Title | First proposed |
 |---|---|
 | [Pre-tool input rewrite — a consistent design](proposed/feature/2026-06-30-pre-tool-input-rewrite.md) | 2026-06-30 |
+| [Recallable compaction — index checkpoints, a state checkpoint, and in-session history recall](proposed/feature/2026-07-06-recallable-compaction.md) | 2026-07-06 |
 | [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 |
 | [Interactive side sessions and merge-back](proposed/feature/2026-07-08-interactive-side-sessions.md) | 2026-07-08 |
 | [SQLite FTS5 session search](proposed/feature/2026-07-10-sqlite-session-query-provider.md) | 2026-07-10 |
@@ -21,7 +22,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
 |---|---|
 | [Unify the agent id and the session id](proposed/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 |
 | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 |
-| [Simplify session-log representation](proposed/simplification/2026-07-12-simplify-session-log-representation.md) | 2026-07-12 |
 
 ### Architecture
 
@@ -61,6 +61,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
 | [Compaction as a capability seam (abstract contract + basic backend)](implemented/feature/2026-06-18-compaction-capability-seam.md) | 2026-06-18 |
 | [Subagent capability seam](implemented/feature/2026-06-21-subagent-capability-seam.md) | 2026-06-21 |
 | [ACP subagent backend (out-of-process delegation)](implemented/feature/2026-06-22-acp-subagent-backend.md) | 2026-06-22 |
+| [Workspace context instruction files](implemented/feature/2026-06-24-workspace-context.md) | 2026-06-24 |
 | [Ask-user question capability](implemented/feature/2026-06-25-ask-user-question.md) | 2026-06-25 |
 | [The `todo_write` tool — model task list as event-sourced session state](implemented/feature/2026-06-29-todo-write-tool.md) | 2026-06-29 |
 | [dsh-hooks-claude + dsh-hooks-codex — the Claude Code / Codex hook bridges](implemented/feature/2026-06-30-hook-bridges.md) | 2026-06-30 |
@@ -78,9 +79,13 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
 | [Background subagent tasks](implemented/feature/2026-07-08-background-subagent-tasks.md) | 2026-07-08 |
 | [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 |
+| [Bash-backed grep and glob discovery tools](implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md) | 2026-07-09 |
+| [Expose agent session identity and JSONL location to tools and hooks](implemented/feature/2026-07-10-agent-session-identity-and-log-location.md) | 2026-07-10 |
 | [Exact session query service](implemented/feature/2026-07-10-session-query-service.md) | 2026-07-10 |
 | [Configure subagent persona, tool visibility, and depth](implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) | 2026-07-12 |
+| [Session query relationship tracing](implemented/feature/2026-07-13-session-query-tracing.md) | 2026-07-13 |
 | [Optional time-context plugin](implemented/feature/2026-07-14-time-context-plugin.md) | 2026-07-14 |
+| [Durable per-step time context](implemented/feature/2026-07-16-durable-per-step-time-context.md) | 2026-07-16 |
 
 ### Simplification
 
@@ -107,6 +112,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
 | [Trim unreachable ACP bridge surface — the branding knobs and the kind-sniffing fallback](implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md) | 2026-07-04 |
 | [Drop unconsumed skill provider events](implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 |
 | [Prune unused web seam fields](implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 |
+| [Simplify session-log representation](implemented/simplification/2026-07-12-simplify-session-log-representation.md) | 2026-07-12 |
 
 ### Architecture
 
@@ -126,7 +132,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
 | [Every session event is enclosed in a turn](implemented/architecture/2026-06-15-turn-enclosure-invariant.md) | 2026-06-15 |
 | [Filesystem capability seam — ctx.fs, local backend, and model-facing filesystem tools](implemented/architecture/2026-06-17-filesystem-capability-seam.md) | 2026-06-17 |
 | [Agent lifecycle and ownership seams](implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md) | 2026-06-18 |
-| [Session surface — a linked list over the event log for LLM message derivation](implemented/architecture/2026-06-18-session-surface.md) | 2026-06-18 |
+| [Session surface — an ordered projection over the event log](implemented/architecture/2026-06-18-session-surface.md) | 2026-06-18 |
 | [Shared persistence write coordinator](implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md) | 2026-06-18 |
 | [Branded IDs everywhere they belong](implemented/architecture/2026-06-20-branded-ids.md) | 2026-06-20 |
 | [Extract example apps into packages](implemented/architecture/2026-06-20-extract-example-app-packages.md) | 2026-06-20 |
@@ -145,10 +151,15 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
 | [Every LLM request is reconstructable from the session log](implemented/architecture/2026-07-05-reconstructable-requests.md) | 2026-07-05 |
 | [Subagent provider-lifecycle events — `subagent/provider-added` / `subagent/provider-removed`](implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md) | 2026-07-05 |
 | [A shared timeout/deadline primitive, with hard-kill left to each capability](implemented/architecture/2026-07-06-timeout-deadline-library.md) | 2026-07-06 |
+| [Tool result retention library](implemented/architecture/2026-07-06-tool-result-retention-library.md) | 2026-07-06 |
 | [Tool-call timeout policy as a plugin](implemented/architecture/2026-07-07-tool-call-timeout-policy.md) | 2026-07-07 |
 | [The agent is a registration scope](implemented/architecture/2026-07-08-agent-scope-contexts.md) | 2026-07-08 |
+| [Tool output spill policy](implemented/architecture/2026-07-08-tool-output-spill-files.md) | 2026-07-08 |
 | [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 |
 | [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 |
+| [Provider-routed LLM adapters and a generic pi-ai backend](implemented/architecture/2026-07-14-provider-routed-llm-adapters.md) | 2026-07-14 |
+| [Advisory LLM catalogs and per-session ACP model selection](implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md) | 2026-07-15 |
+| [Replay token meter service](implemented/architecture/2026-07-15-replay-token-meter-service.md) | 2026-07-15 |
 
 ### Process
 
@@ -180,6 +191,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
 | [A gated Known-Limitations section in every package README](implemented/process/2026-07-10-readme-known-limitations-gate.md) | 2026-07-10 |
 | [Package Model Experience contract](implemented/process/2026-07-12-package-model-experience-contract.md) | 2026-07-12 |
 | [TypeScript Program-backed semantic gates](implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md) | 2026-07-14 |
+| [Run CI examples from built lib](implemented/process/2026-07-17-run-ci-examples-from-built-lib.md) | 2026-07-17 |
 
 ### Testing
 

docs/rfc/implemented/architecture/2026-06-17-filesystem-capability-seam.md

@@ -81,7 +81,7 @@ Resolved targets must expose at least three concepts:
 - An opaque `targetKey`, used for stale guards and file-state lookup. The local backend might use a realpath-like key; a remote backend might use a workspace URI or file id. Consumers must not parse or assume this is a local absolute path.
 - A `displayPath`, used for model/UI-facing output. It may be a local absolute path, workspace-relative path, or remote URI depending on the backend.
 
-Read and mutation results must include an opaque file `version`. A local backend can use mtime/size or a hash-like token; a remote backend can use a revision id. The `dsh-fs-policy` plugin records versions for stale checks; consumers may display related metadata but must not interpret the version token.
+Read and mutation results must include an opaque file `version`. The local backend derives its token from bigint stat metadata (`dev`, `ino`, `size`, `mtimeNs`, and `ctimeNs`) so same-size rewrites and inode replacement invalidate consumers reliably; a remote backend can use a revision id or hash-like token. The `dsh-fs-policy` plugin records versions for stale checks; consumers may display related metadata but must not interpret the version token.
 
 The provider hands back decoded text: `readText` returns a whole regular text file, `streamText` streams the same text semantics for large files. Both own regular-file checks, bounded line/output handling is NOT theirs — line windowing, numbered-line rendering, and total-line accounting live in the executor (`dsh-tool-fs`), which reads through `ctx.fs` and renders the model-facing window. The provider owns UTF-8 decoding and binary/NUL rejection; it does not know about line windows or views.
 

docs/rfc/implemented/architecture/2026-06-18-session-surface.md

@@ -1,4 +1,4 @@
-# RFC: Session surface — a linked list over the event log for LLM message derivation
+# RFC: Session surface — an ordered projection over the event log
 
 Status: implemented
 
@@ -8,13 +8,13 @@ The event log is authoritative, but history manipulation had no durable shared m
 
 ## Decision
 
-Add a **surface** — a derived, cached linked list of "surface nodes" (the subset of events that produce LLM messages) — maintained by `surfaceOp` markers in the event log.
+Add a **surface** — a derived, cached order of event sequences (the subset of events that produce LLM messages) — maintained by `surfaceOp` markers in the event log.
 
 ### Two new top-level fields on `SessionEvent`
 
 Every `SessionEvent` gains two optional fields (structural metadata, like `seq`/`time`):
 
-- **`sourceEventSeqs?: number[]`** — seq numbers of events that are provenance sources (e.g., the `assistant/chunk` seqs that built an `assistant/message`, or the surface nodes shadowed by a compaction marker). Provenance is a core design principle; without it, the replace-range operation cannot be validated on replay.
+- **`sourceEventSeqs?: number[]`** — seq numbers of events that are provenance sources (e.g., the `assistant/chunk` seqs that built an `assistant/message`, or the surface nodes shadowed by a compaction marker). A present `[]` is valid only on `assistant/message` and records a known empty provider stream; omission there means legacy or otherwise unrecorded provenance. Other surface events require a non-empty list when the field is present. Provenance is a core design principle; without it, the replace-range operation cannot be validated on replay.
 - **`surfaceOp?: SurfaceOp`** — how this event entered the surface. Absent for non-surface events.
 
 ### SurfaceOp: two operations
@@ -25,13 +25,13 @@ export type SurfaceOp =
   | { op: 'replace'; start: number; end: number }  // shadow [start, end] inclusive
 ```
 
-1. **Append** — add a new node to the tail. Used by `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`. The loop passes `surfaceOp: 'append'` on all such appends, and `sourceEventSeqs` where applicable (e.g., `assistant/message` records its `assistant/chunk` sources; `tool/result` records its `tool/call` source).
+1. **Append** — add the new event seq to the tail. Used by `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`. The loop passes `surfaceOp: 'append'` on all such appends and records `sourceEventSeqs` where applicable: every successful `assistant/message` records its complete `assistant/chunk` source set, including `[]`, while `tool/result` records its `tool/call` source.
 
-2. **Replace** — remove nodes from `start` through `end` (both inclusive) and insert a new node in their place. Both `start` and `end` must be valid surface node seqs in the current surface; `start === end` replaces a single node. The node's `sourceEventSeqs` must contain every shadowed surface node. The shadowed events remain in the log but are no longer on the surface.
+2. **Replace** — remove entries from `start` through `end` (both inclusive) and insert the new event seq in their place. Both `start` and `end` must be present in the current surface; `start === end` replaces one entry. The event's `sourceEventSeqs` must contain every shadowed surface seq. The shadowed events remain in the log but are no longer on the surface.
 
 ### SurfaceManager: delta-based, not full rebuild
 
-A `SurfaceManager` class (private to `Session`) maintains the cached linked list. It tracks `_lastProcessedSeq` and processes only the **delta** (new events since the last access) rather than rescanning the entire log. Because the log is append-only, prior events never change; a seeded log is simply the initial delta folded on first access.
+A `SurfaceManager` class (private to `Session`) maintains one ordered `number[]` of event seqs. It tracks `_lastProcessedSeq` and processes only the new events since the last access rather than rescanning the entire log. Because the log is append-only, prior events never change; a seeded log is simply the initial suffix folded on first access. Replace locates its inclusive endpoints by array position and splices the replacement seq into that range; no link objects or seq-to-node map duplicate the order.
 
 Delta processing is O(1) when no new events and O(new events) when new events arrive.
 
@@ -47,23 +47,24 @@ The `repair.ts` module synthesizes `tool/result` closers for orphaned tool calls
 
 ### Invariants
 
-The dev-mode invariants plugin validates: `sourceEventSeqs` references (non-empty, no duplicates, references earlier events, references known seqs) and `surfaceOp` (replace `start ≤ end`, both endpoints are on the tracked surface, the range is non-reversed in surface position, and `sourceEventSeqs` includes every node the range shadows).
+The dev-mode invariants plugin validates: `sourceEventSeqs` references (only `assistant/message` may use an empty list; otherwise no duplicates, references earlier events, and references known seqs) and `surfaceOp` (replace `start ≤ end`, both endpoints are on the tracked surface, the range is non-reversed in surface position, and `sourceEventSeqs` includes every node the range shadows).
 
 Every surface-eligible event must carry `surfaceOp` or it would disappear from derived history. Typed `append` overloads enforce this for literal event types; runtime checks in `append` and the seed constructor cover widened unions and loaded logs. Invalid seeds are rejected rather than upgraded under the pre-release format policy.
 
 ## Alternatives considered
 
 - **Per-plugin `agent/request` wrapping** (the pre-surface pattern for history manipulation) — listener-ordering fragility, no durable record of what was changed, and every new manipulation forces another change to core `deriveMessages()`.
-- **Half-open `[start, endExclusive)` replace ranges** — rejected: the surface is a doubly-linked list whose ends are naturally named by node seqs, and single-node replacement (`start === end`) reads naturally with inclusive semantics.
+- **Half-open `[start, endExclusive)` replace ranges** — rejected: endpoints are named by surface event seqs, and single-entry replacement (`start === end`) reads naturally with inclusive semantics.
+- **Linked node objects plus a seq map** — rejected: production did not read predecessor links, the only successor use was the next array position, and replacement already required linear `indexOf` lookup. A single seq array preserves the same asymptotic behavior with one representation to validate.
 - **Full rebuild behind a dirty flag** instead of delta processing — O(N²) over a session's lifetime: every single-event append would rescan all prior events.
 
 ## Consequences
 
-- **`packages/core/session`**: New `surface.ts` (`SurfaceManager`), new types (`SurfaceOp`, `SurfaceIntent`), new fields on `SessionEvent`, modified `append()` (third required `SurfaceIntent` param), refactored `deriveMessages()` (walks the surface as the sole derivation path), surface-aware `repair.ts`. The seed constructor rejects a surface-eligible seed event missing its `surfaceOp` marker (see § Invariants).
+- **`packages/core/session`**: `surface.ts` (`SurfaceManager`) maintains one ordered seq array; `SurfaceOp`/`SurfaceIntent` and the top-level session-event fields record how entries join it. `append()` requires a `SurfaceIntent` for surface events, `deriveMessages()` walks the surface as the sole derivation path, and `repair.ts` emits surface-aware closers. The seed constructor rejects a surface-eligible seed event missing its `surfaceOp` marker (see § Invariants).
 - **`packages/core/agent-loop`**: All surface-capable appends pass surface opts. Chunk seqs are collected for `assistant/message` provenance; `tool/call` seqs are captured for `tool/result` provenance.
 - **`packages/session-persistence/session-persistence-sqlite`**: Two new nullable TEXT columns (`source_event_seqs`, `surface_op`) on the `events` table; `SCHEMA_VERSION` bumped (bump-and-reject, no migration).
 - **`packages/support/invariants`**: Surface-related validation rules.
 - **`packages/session-persistence/session-persistence-jsonl`**: No changes required.
 - **`packages/session-persistence/session-persistence`**: Abstract interface unchanged.
 
-The surface is the foundation for future history manipulation. A compaction or tool-result-prune plugin appends one of the existing message-producing event types (a `user/message` carrying the summary, say) with `surfaceOp: { op: 'replace', start, end }` and `sourceEventSeqs` covering the shadowed nodes — the new node takes the range's place on the surface while the plugin's own trace events (e.g. `compaction/start`, `compaction/end`) stay off it. Replay preserves the decision deterministically.
+The surface is the foundation for future history manipulation. A compaction or tool-result-prune plugin appends one of the existing message-producing event types (a `user/message` carrying the summary, say) with `surfaceOp: { op: 'replace', start, end }` and `sourceEventSeqs` covering the shadowed entries — the new event takes the range's place on the surface while the plugin's own trace events (e.g. `compaction/start`, `compaction/end`) stay off it. Replay preserves the decision deterministically.

docs/rfc/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md

@@ -12,6 +12,8 @@ Extract a backend-agnostic `PersistenceCoordinator` into `dsh-session-persistenc
 
 Composition, not inheritance. The coordinator is a concrete class the backend holds, not a base class the backend extends. The RFC's risk — "a coordinator must not make unusual backends fight an inheritance hierarchy" — is avoided: a backend exposes only the hooks; it cannot reach the coordinator's private orchestration state, and the public `SessionPersistence` service shape is unchanged, so a third-party backend MAY still implement the abstract service directly without the coordinator at all.
 
+The coordinator retires each live session from its `session/disposed` notification: it waits for that exact Session object's initialization, serializes a final drain, and then removes the owned state, buffer, and init entries. Failed drains retain their buffers for backend teardown to retry. Settled per-id chain tails remove themselves only when they are still the current tail, so a completion cannot erase a newer operation for the same id. Backend teardown unregisters the write-path listeners before awaiting all admitted retirements, remaining buffers, and chains, then closes the backend.
+
 ### The hook interface (`PersistenceBackend<TornMarker>`)
 
 Six methods (five required + an optional lifecycle hook) — the only seam between the coordinator and storage:
@@ -30,7 +32,7 @@ The single design choice that keeps the seam clean: the crash-repair "where is t
 
 ## Testing
 
-The shared `runPersistenceContract` (public-API contract) keeps running for every backend. A new `runCoordinatorContract` (`tests/coordinator-contract.ts`) holds the write-path orchestration — adoption, HMR, collision, dispose-drain, crash-tail repair — and runs once per backend through a `CoordinatorFixture` (an in-memory reference + jsonl + sqlite). The per-backend specs shrank to storage mechanics only (JSONL: path safety, fsync rollback, bucket listing; SQLite: schema version, `scanRows`, transaction rollback). A through-coordinator torn-tail→load→`commitRepair` test per real backend (via a `corruptTail` fixture hook) keeps the coordinator's torn-marker repair branch covered under the 100% per-file gate — the contract crash test only produces synthetic closers, never a torn marker, so it could not reach that branch.
+The shared `runPersistenceContract` (public-API contract) keeps running for every backend. `runCoordinatorContract` (`tests/coordinator-contract.ts`) holds the write-path orchestration — adoption, HMR, collision, session and backend disposal drains, and crash-tail repair — and runs once per backend through a `CoordinatorFixture` (an in-memory reference + jsonl + sqlite). Coordinator-specific tests pin retirement map cleanup, same-id chain-tail races, failed-drain retry, and close ordering. The per-backend specs retain storage mechanics only (JSONL: path safety, fsync rollback, bucket listing; SQLite: schema version, `scanRows`, transaction rollback). A through-coordinator torn-tail→load→`commitRepair` test per real backend (via a `corruptTail` fixture hook) keeps the coordinator's torn-marker repair branch covered under the 100% per-file gate — the contract crash test only produces synthetic closers, never a torn marker, so it could not reach that branch.
 
 ## Alternatives considered
 
@@ -39,4 +41,4 @@ The shared `runPersistenceContract` (public-API contract) keeps running for ever
 
 ## Consequences
 
-The coordinator adds one indirection and an opaque torn marker, but centralizes correctness-heavy orchestration previously duplicated by every backend. Its hook surface stays narrow: collision checks reuse `loadStored`, materialization stays atomic inside `appendBatch`, and listing bypasses the coordinator. New backends implement storage primitives rather than copy the event-buffer-flush lifecycle.
+The coordinator adds one indirection, an opaque torn marker, and detached session-retirement tasks, but centralizes correctness-heavy orchestration previously duplicated by every backend. Session disposal remains an observe-only event, so the session owner does not await persistence retirement; the coordinator contains failures, preserves uncommitted buffers, and makes backend teardown the quiescence boundary. Its hook surface stays narrow: collision checks reuse `loadStored`, materialization stays atomic inside `appendBatch`, and listing bypasses the coordinator. New backends implement storage primitives rather than copy the event-buffer-flush lifecycle.

docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md

@@ -14,9 +14,9 @@ Add `stdin?: string` and `env?: Record<string, string>` to **both** `BashExecReq
 
 Three deliberate choices:
 
-1. **The model-facing tool omits `stdin` and `env`.** Shell syntax already covers those needs, so duplicate parameters would add surface without authority separation. The tool builds requests only from declared model arguments, signal, and owner; trusted in-process callers may set the seam fields directly.
+1. **The model-facing tool omits `stdin` and `env`.** Shell syntax already covers those needs, so duplicate parameters would add surface without authority separation. The tool builds requests only from declared model arguments, signal, and owner; trusted in-process callers may set the seam fields directly. Harness-owned variables use the separate `dshEnv` channel from the [managed environment decision](../feature/2026-07-10-agent-session-identity-and-log-location.md), so ordinary `env` cannot replace them.
 
-2. **`env` merges AFTER the credential scrub, so an explicit caller entry always wins** — even a credential-shaped name. This is correct because the scrub's job is narrow: stop the harness's *ambient* `process.env` credentials from leaking into a spawned command. A caller that explicitly sets a var has named a value it already holds (not the ambient secret), so the scrub is not a constraint on it. `childEnv(extra?)` layers `scrub(process.env)` → `ENV_OVERRIDES` (the model-friendly `TERM=dumb` etc.) → `extra`, last-wins.
+2. **`env` merges AFTER the credential scrub, so an explicit caller entry wins even on a credential-shaped name.** The later managed-namespace decision reserves `DSH_*`: ambient entries are removed, ordinary `env` cannot set them, and trusted `dshEnv` merges last. The complete order is `scrub(process.env, including DSH_*)` → `ENV_OVERRIDES` → ordinary `env` → `dshEnv`.
 
 3. **`stdin`/`env` are required-absent-OK (plain optional) on the resolved spec, NOT required-but-nullable like `owner`.** `owner` is required-but-nullable because a *silently* missing owner yields an unowned, cross-session-readable task — a security footgun that a visible `undefined` guards against. `stdin`/`env` have no such hazard: a missing one means "no stdin / no extra env", which is the safe, ordinary case (every model-driven call). So they stay plain optionals, matching `signal`.
 

docs/rfc/implemented/architecture/2026-07-02-fs-per-session-cwd.md

@@ -12,7 +12,7 @@ Filesystem resolution used one plugin-load cwd while bash used the session proje
 
 Thread the caller's session cwd into path resolution, exactly as `dsh-tool-bash` already does for `workdir`. The **caller** (the tool) supplies the cwd; the provider does not read a session or agent.
 
-- `FileSystem.resolve` widens to `resolve(path: string, opts?: { cwd?: string }): Promise<FsTarget>`. `opts.cwd` is the base a RELATIVE `path` resolves against; an absolute `path` ignores it; omitting `opts.cwd` uses the backend's own default. An options object (not a positional `cwd?`) leaves room for future resolution hints without another signature change.
+- `FileSystem.resolve` accepts `resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise<FsTarget>`. `opts.cwd` is the base a RELATIVE `path` resolves against; an absolute `path` ignores it; omitting `opts.cwd` uses the backend's own default. `opts.signal` cancels resolution when the backend performs I/O. The options object keeps both caller-owned resolution controls together without positional growth.
 - `dsh-fs-local.resolve` uses `resolveLocalTarget(opts?.cwd ?? this.config.cwd, path)`. `config.cwd` stays the default for a caller that supplies none (non-ACP / no-session use, and the single-session stdio demo where `process.cwd()` IS the workspace).
 - `dsh-tool-fs`'s `read`/`write`/`edit` derive the session cwd through a shared `sessionCwd(exec)` helper (`exec.agent?.session.header.cwd`, mirroring bash's `resolveWorkdir`) and pass it to `resolve`. A non-agent / headerless caller yields `undefined`, so the backend applies its default.
 

docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md

@@ -18,13 +18,13 @@ Prefix-cache stability is corollary #1, not the headline: an append-only log pro
 
 ### The mechanism
 
-**Messages.** `Session.deriveMessages()` is cached: each surface node is projected exactly once, when first seen, through the public per-node function `deriveEventMessage(event)`; a surface rewrite (a compaction `replace` — `SurfaceManager.replaceGeneration`) rebuilds. Callers get a fresh array per call over shared, deep-frozen messages: mutating logged history through a projection is unrepresentable (it throws), replacing the old clone-per-call isolation. External reconstructors fold the same public function over a log prefix, so no two paths can disagree.
+**Messages.** `Session.deriveMessages()` is cached: each surface entry is projected exactly once, when first seen, through the public per-event function `deriveEventMessage(event)`; a surface rewrite (a compaction `replace` — `SurfaceManager.replaceGeneration`) rebuilds. Callers get a fresh array per call over shared, deep-frozen messages: mutating logged history through a projection is unrepresentable (it throws), replacing the old clone-per-call isolation. External reconstructors fold the same public function over a log prefix, so no two paths can disagree.
 
-`EpochHeader` records the request's non-history state: call config, rendered system prompt, tool schemas, and session prefix, with empty values canonicalized to absence. `request/header` writes a full initial, resume, or fallback snapshot. `request/header-delta` encodes system changes by common-prefix/suffix line trim, tools by name-keyed additions/removals/changes, and config or prefix by full replacement. `foldRequestHeader`, `diffHeader`, and `applyHeaderDelta` are the pure codec. Each loop instance writes a snapshot on its first request to anchor process boundaries. Deltas are only an optimization: the writer verifies round-trip equality and falls back to a full snapshot for unrepresentable changes such as pure tool reordering.
+`EpochHeader` records the request's non-history state: call config, rendered system prompt, tool schemas, and session prefix, with empty values canonicalized to absence. `request/header` always writes a full snapshot: the first loop instance uses reason `initial`, later instances use `resume`, and an in-instance change uses `change`. `foldRequestHeader` selects the latest snapshot. Legacy `request/header-delta` events and the removed `fallback` reason are rejected when appended or loaded.
 
 Each step rebuilds prompt assembly. On the instance's first step, `agent/session-prefix` extends a frozen empty seed with request-only opener messages; the result is frozen and cached for that loop instance. `agent/pre-step` then receives the composed prefix before messages are snapshotted immediately ahead of `step/start`. The first call config starts from explicit `AgentOptions`, preserving fork overrides and resume reconfiguration; later calls start from the folded header. `agent/request` may replace only that frozen config seed, while model-visible content enters through logged channels. The loop records the owed header event—the prefix's only durable home—builds `GenerateOptions` from prefix, snapshot, and header, and deep-freezes it while leaving `AbortSignal` live. Per-instance state is only the cached prefix and whether its anchoring snapshot has been written.
 
-**`step/start` is the reconstruction boundary.** A step derives messages from events before that sequence. Injection after the snapshot joins the next request, and reentrant appends are rejected during event publication. `agent/pre-step` is the seam for content needed by the current request. Header reconstruction folds through the step's own `request/header*` event, or carries the prior fold when no new header is written.
+**`step/start` is the reconstruction boundary.** A step derives messages from events before that sequence. Injection after the snapshot joins the next request, and reentrant appends are rejected during event publication. `agent/pre-step` is the seam for content needed by the current request. Header reconstruction selects the step's `request/header`, or carries the prior snapshot when no new header is written.
 
 **Enforcement.** In development, `dsh-invariants` independently rebuilds each loop request through a fresh `Session`, so the live cache cannot vouch for itself, then compares messages and folded header fields at `llm/stream`. Loop requests are identified by their frozen shape and session id; direct one-shots are excluded. Correctness depends on sequence-bounded reconstruction rather than listener order. A with-key e2e requires positive cache-read tokens after the first request; per-step usage is the production signal, and a header change or compaction appears as a cache-read drop on the next step.
 
@@ -39,15 +39,16 @@ Like MiniCode, the conversation advances append-only and resets only when model-
 - **Per-call request scalars** (a freely mutable config handed to each `agent/request` dispatch): a listener flips the model per call with zero accounting, silently abandoning the provider cache this design exists to protect. Config is per-conversation logged state; the waterfall proposes, the log records.
 - **Detect-and-report** (compare consecutive requests, warn on divergence): catches violations after the fact; a violating request is still constructible and ships. Rejected for interface-level unrepresentability.
 - **Event-driven assembly** (re-render only on change signals): a missed-signal bug class — a tool registered mid-session emits `tools/change`, not `system-prompt/change`, and a third-party provider may emit nothing. Per-step render + value compare is robust with zero signal discipline.
-- **Narrative fields on the header events** (a `reason`/`changed` list on deltas): derivable by diffing consecutive events — one home per fact; snapshots carry a reason because an anchor's cause is NOT derivable from the data.
+- **A custom header-delta codec** (system line edits, name-keyed tool edits, whole config/prefix replacements): reduced repeated bytes but duplicated the representation and its diff/apply/fallback machinery. Full snapshots retain one replay representation.
+- **Narrative changed-field lists on header snapshots**: derivable by comparing consecutive snapshots. The `reason` remains because an instance boundary is not derivable from the snapshot values.
 
 ## Consequences
 
 - A request that is not explained by the log cannot be constructed by accident — not by the loop, not by a listener; mutating a built request throws; every header change is a durable, diffable log event.
-- Choosing between the advisory channels is a change-frequency decision, and the design makes the stable one structural: an `agent/session-prefix` contribution is composed once per loop instance and reused verbatim, so it extends the cacheable prefix at zero marginal cost and CANNOT bust the provider cache mid-session; content that changes mid-session flows through the append-only history channels — `agent.inject()`, a `tools/post-execute` decision's `additionalContext`, prompt-submit `additionalContext` — each a durable `context/message` paid once and prefix-cached thereafter, at the price of accumulating in history and the log. Route session-frozen openers to the prefix and change notices to the history channels; a per-step request-only tail slot was deliberately dropped (no consumer, and a durable append covers every current update pattern).
-- What still costs full price at the provider is inherent and logged: compaction (its `compact/*` events and replace node), a real prompt/tool change (`request/header-delta`), a config switch (ditto), a process boundary with drift (`'resume'` snapshot differing from its predecessor). The provider's own reasoning-content exclusion is managed server-side.
+- Choosing between the advisory channels is a change-frequency decision, and the design makes the stable one structural: an `agent/session-prefix` contribution is composed once per loop instance and reused verbatim, so it extends the cacheable prefix at zero marginal cost and CANNOT bust the provider cache mid-session; content that changes mid-session flows through the append-only history channels — `agent.inject()` and tool/prompt-submit `additionalContexts` — each a durable `context/message` paid once and prefix-cached thereafter, at the price of accumulating in history and the log. Route session-frozen openers to the prefix and change notices to the history channels; a per-step request-only tail slot was deliberately dropped (no consumer, and a durable append covers every current update pattern).
+- What still costs full price at the provider is inherent and logged: compaction (its `compact/*` events and replacement entry), a real prompt, tool, or config change (`request/header` with reason `change`), or a process boundary with drift (a differing `resume` snapshot). The provider's own reasoning-content exclusion is managed server-side.
 - The `step/start`-listener behavior change (above) is the one observable semantics change for plugins; `agent/pre-step` is the current-request seam.
-- Tool-result trimming (planned) needs no new mechanism: a logged single-node surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic.
-- Session logs grow one `request/header` snapshot per conversation (system + tool schemas: the dominant term), plus deltas on real changes — small next to `assistant/chunk` volume; `SESSION_FORMAT_VERSION` stays `0` (pre-release churn is absorbed, backends reject-not-migrate).
+- Tool-result trimming (planned) needs no new mechanism: a logged single-entry surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic.
+- Session logs grow one `request/header` snapshot per loop instance plus snapshots on real changes. This is larger than a delta codec but small beside chunk-heavy logs and retains one replay representation. `SESSION_FORMAT_VERSION` stays `0`; legacy delta events are rejected rather than migrated.
 - Snapshot goldens changed once (every transcript gains its header events); the fs-writing fixtures are stored in the normalized authored form with cwd-relative tool arguments, because replay only round-trips cwd-independent argument paths.
 - FIXME(call-config-shape): revisit `LlmCallConfig`'s exact field set — which fields are genuinely epoch-level for cache purposes (`model` certainly; the sampling scalars sit there out of caution), and where provider-specific extras (reasoning options, extra body params) belong when an adapter needs them.

docs/rfc/implemented/architecture/2026-07-06-tool-result-retention-library.md

@@ -0,0 +1,155 @@
+# RFC: Tool result retention library
+
+Status: implemented
+
+## Problem
+
+Several model-facing tools already bound the amount of context they return, but each one owns a different local mechanism and vocabulary: bash keeps a tail plus spill files, web search caps source lists, web fetch caps body content, and `glob` / `grep` discovery needs an inline first page while keeping exact omission metadata for the full result set. A single `truncate(text)` helper cannot cover those cases: item tools need item counts and grouping outside the primitive, while text tools need byte budgets and UTF-8-safe head/tail cuts.
+
+The shared abstraction the tools need is **retention**, not generic collection. A caller feeds items or text chunks into a bounded object and later receives the retained content plus exact omission metadata. Tool-specific code still owns business semantics: file grouping, line numbering, exit codes, provider error states, spill files, and model-facing prose. The common library owns only the mechanical question "what did we keep, and what did we omit?"
+
+## Decision
+
+`@deepseek-ai/dsh-retention` lives under `packages/util/` (peer to `dsh-brand` and `dsh-timeout`) and owns bounded model-facing output. It is a library of pure classes and functions, **not** a Cordis service or plugin: it takes no `ctx`, registers nothing, holds no cross-call state, and emits no events. Tool packages import it directly when they need bounded output.
+
+The library has two independent retainers:
+
+- `ItemRetainer<T>` handles ordered logical units such as paths, grep matches, or search sources. It supports `head` retention only in v1, while keeping the retainer shape open to additional retention strategies later.
+- `TextRetainer` handles byte-oriented text streams such as bash stdout/stderr or web response bodies. It supports `head`, `tail`, and `headTail` retention while preserving UTF-8 boundaries at `finish()`.
+
+Both retainers return a small `PushDecision` after each `push()` so callers can tell whether that unit/chunk was fully retained and whether the accumulated result is now truncated. Omission counts are exact because callers keep feeding every observed item/chunk.
+
+```ts ignore-check
+/**
+ * How much content the retainer omitted.
+ *
+ * `unknown` is reserved for callers that omit without a count; the retainers
+ * themselves return `none` or `exact`.
+ */
+type Omitted =
+  | { kind: 'none' }
+  | { kind: 'exact'; count: number }
+  | { kind: 'unknown' }
+
+interface PushDecision {
+  kept: boolean
+  truncated: boolean
+}
+
+/**
+ * Final result for ordered logical units.
+ */
+interface RetainedItems<T> {
+  items: T[]
+  truncated: boolean
+  seen: number
+  kept: number
+  omitted: Omitted
+}
+
+/**
+ * Final result for text streams.
+ *
+ * The returned `text` is safe to send to a formatter; the retainer does not add
+ * tool-specific headers, exit markers, XML tags, or recovery instructions.
+ */
+interface RetainedText {
+  text: string
+  truncated: boolean
+  omittedBytes: Omitted
+}
+```
+
+### Strategies
+
+Item retention supports a head window. Text retention supports head, tail, and headTail byte windows.
+
+```ts ignore-check
+type ItemRetentionStrategy =
+  | {
+      /** Keep the first `maxItems` units. Use for `glob`, `grep`, and web sources. */
+      kind: 'head'
+      maxItems: number
+    }
+
+type TextRetentionStrategy =
+  | {
+      /** Keep the first `maxBytes` bytes. */
+      kind: 'head'
+      maxBytes: number
+    }
+  | {
+      /** Keep the final `maxBytes` bytes. Requires reading to the end. */
+      kind: 'tail'
+      maxBytes: number
+    }
+  | {
+      /** Keep a stable prefix and suffix, omitting the middle. Requires reading to the end. */
+      kind: 'headTail'
+      headBytes: number
+      tailBytes: number
+    }
+```
+
+### Tool mapping
+
+`read` is intentionally outside the v1 retention library. Its `read-render` helper owns a file-specific pagination contract: `offset` / `limit`, line numbers, `totalLines`, offset-out-of-range errors, per-line preview truncation, and a selected-output byte cap that can stop scanning mid-window. That is a line-window renderer, not a generic retention primitive. It may share future neutral notice helpers, but it should not pass its already-selected window through `ItemRetainer`.
+
+`FsGlobEntry` and `FlatGrepMatch` below are the intended discovery-tool item shapes, not existing retention-library exports. `FsGlobEntry` is one backend-derived path, and `FlatGrepMatch` is one ungrouped grep match before the backend groups retained matches by file.
+
+`glob` uses `ItemRetainer<FsGlobEntry>` with `{ kind: 'head', maxItems: globMaxResults }` after collecting the full sorted path list. The tool keeps the retained first page inline and may save the full list through the spill seam. Path mapping, skipped candidates, and `incomplete` stay outside the retainer.
+
+`grep` uses `ItemRetainer<FlatGrepMatch>` with `{ kind: 'head', maxItems: grepMaxMatches }` before grouping. The executor parses ripgrep output, maps paths, applies per-line preview truncation, and pushes flat matches. After `finish()`, the tool groups retained matches by file and can save the full match list through the spill seam when the inline result is capped. Grouping is not part of the retainer because the cap is total matches, not files; per-match preview truncation and `incomplete` are also separate from result-level retention.
+
+`bash` can use `TextRetainer` with `tail` or `headTail` and reads to process completion. The bash executor still owns spill files, exit status, signal, timeout, and background-task behavior; the retention helper only replaces ad hoc in-memory head/tail accounting where that behavior is desired. Long-running task ownership remains orthogonal to the [generic long-running tool runtime](2026-06-20-generic-long-running-tool-runtime.md).
+
+`web_fetch` can use `TextRetainer` with `head` or `headTail`, or keep provider-owned body caps when the provider must read and decode internally. Either way, the fetch result's `truncated` remains a provider/tool fact, and the library only supplies retained text and omission metadata.
+
+`web_search` can use `ItemRetainer<WebSearchSource>` with `head`. Current providers often return an array, so this is post-hoc but still standardizes notices.
+
+### Notices
+
+The library exposes a neutral notice shape and a tiny formatter hook, but tools provide the user-facing words. A grep footer says "Narrow the pattern, path, or include"; a web fetch footer says "Fetch a more specific URL or section"; bash may point to a spill file. The retainer cannot know those recovery actions.
+
+```ts ignore-check
+interface RetentionNotice {
+  scope: string
+  strategy: 'head' | 'tail' | 'headTail'
+  unit: 'items' | 'bytes' | 'chars' | 'lines'
+  limit: number | { head: number; tail: number }
+  kept: number
+  omitted: Omitted
+}
+
+const formatGrepNotice = (notice: RetentionNotice): string =>
+  formatRetentionNotice(
+    notice,
+    ({ kept }) => `Results capped at ${kept}. Narrow the pattern, path, or include to see more.`,
+  )
+```
+
+The formatter hook is deliberately small: a tool turns a `RetentionNotice` into its own footer text. The helper may standardize omission wording, but it does not own recovery guidance.
+
+`truncated` means the retainer omitted otherwise-available content because of a budget. It does not mean the upstream was incomplete. Tools keep separate fields for permission failures, skipped binary files, provider partial failures, unreadable candidates, invalid UTF-8, and any other "could not inspect" condition.
+
+## Consequences
+
+**What shipped.** `@deepseek-ai/dsh-retention` exports `ItemRetainer`, `TextRetainer`, the result types (`RetainedItems`, `RetainedText`), the strategy types (`ItemRetentionStrategy`, `TextRetentionStrategy`), `Omitted`, `PushDecision`, `RetentionNotice`, and the neutral notice helpers `describeOmitted` / `formatRetentionNotice` — with no dependency on Cordis or any tool package. Unit tests cover item-head retention with exact omission counts, text-head retention, text-tail retention, head-tail byte retention, zero budgets, UTF-8 boundary handling (2-, 3-, and 4-byte codepoints and invalid lead bytes at each cut), and unknown omission wording.
+
+**What is documented but not yet migrated.** `glob`, `grep`, `bash`, `web_fetch`, and `web_search` have their mappings documented in the [package README](../../../../packages/util/retention/README.md), but not every tool has been migrated onto the library in this change; migration is deliberately separate follow-up work. `read` is documented as intentionally out of scope: its `read-render` line-window contract (`offset`/`limit`, `totalLines`, offset-range errors, per-line preview truncation, a byte cap over the selected window) is not generic retention, and one `Omitted` count cannot represent both sides of a line window.
+
+**Boundaries the library holds.** `truncated` means the retainer omitted otherwise-available content because of a budget; it never means the upstream was incomplete. Tool-specific states — `incomplete`, permission failures, provider partial failures, binary skips, bash spill-path recovery, invalid UTF-8 — stay in tool-domain fields, outside the retainer. When a future change migrates a tool, that package's README and tests must prove the model-facing result text is unchanged except for deliberate notice wording.
+
+**Tradeoffs accepted.** The v1 surface deliberately supports only item `head` retention and text `head` / `tail` / `headTail`; windows, grouped budgets, sort-aware caps, and upstream-stop control wait until a second consumer proves the need. Text retention counts bytes for process/body safety, leaving character- and line-level preview budgets as separate tool-owned concerns.
+
+## Alternatives considered
+
+**Post-hoc `truncate(text)` only.** Rejected: it matches Codex's history/tool-output truncation use case but loses item counts, grouping boundaries, UTF-8-safe byte windows, and exact omission metadata.
+
+**One generic `Collector<T>` with pluggable callbacks.** Rejected for v1: it hides the two important resource modes. Logical item retention counts items; text retention counts bytes and preserves UTF-8 boundaries. Separate `ItemRetainer` and `TextRetainer` names make that difference explicit while keeping the API small.
+
+**Put `read` windowing behind `ItemRetainer`.** Rejected for v1: `read` is the only current window consumer, and its semantics are file pagination rather than generic retention. A single `Omitted` count cannot represent both sides of a line window, and `read` also carries `totalLines`, offset-range errors, per-line preview truncation, and a byte cap over selected output. Keeping `read-render` tool-owned avoids growing the shared library around one special case.
+
+**Make truncation part of `ToolExecutionResult`.** Rejected: the tool registry would have to understand tool-specific recovery guidance, grouping, line numbering, exit status, and provider semantics. Retention is a library used before a tool returns `ContentBlock[]`; the model-facing result remains tool-owned.
+
+**Expose limits in every model-facing tool schema.** Rejected as the default: Claude Code's grep exposes `head_limit` / `offset`, but this harness keeps routine budgets as deployment config unless the model genuinely needs pagination control. A future read-like continuation field can be added per tool; it does not belong in the shared retention primitive.

docs/rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md

@@ -0,0 +1,189 @@
+# RFC: Tool output spill policy
+
+Status: implemented
+
+## Problem
+
+Tool outputs need bounded model-facing previews, but some oversized results are still useful later. A fetched page body or a verbose tool response should not consume the next model request in full, but the model should be able to inspect the complete formatted result later with existing file-reading tools.
+
+Before this change the behavior was uneven. `dsh-bash-local` already writes complete stdout/stderr streams to private temp spill files when its in-memory tail overflows, but ordinary text tool results were returned inline unless the tool hand-rolled its own cap. The [tool result retention library](./2026-07-06-tool-result-retention-library.md) owns preview mechanics, but it does not own storage or an execution-pipeline policy that applies those mechanics to final tool results.
+
+The shape matches the timeout policy design: a tool author normally returns the text result, and a policy plugin enforces the deployment's default context budget. Tool-specific early spill remains possible later for outputs that do not survive to the final `ToolExecutionResult`; the first cut proves the default final-result path.
+
+## Decision
+
+A thin spill storage seam plus a default spill policy plugin, in a new `packages/spill/` group:
+
+| Package | Role |
+|---|---|
+| `@deepseek-ai/dsh-spill` | Interface: `ctx.spillStore`, vocabulary types, no storage implementation. |
+| `@deepseek-ai/dsh-spill-local` | Local backend: private, session-scoped file storage on the host filesystem. |
+| `@deepseek-ai/dsh-spill-policy` | Tool-result policy plugin: wraps final text results after dispatch and replaces oversized results with a retained preview plus a spill locator. |
+
+There is no dedicated model-facing consumer package. The consumer is the existing `ctx.tools` execution pipeline: `dsh-spill-policy` consumes final tool results through the `tools/post-execute` waterfall, and the model follows the backend-supplied retrieval hint for the returned locator.
+
+### Spill seam
+
+The storage seam is minimal: save text and return a locator plus retrieval hint.
+
+```ts ignore-check
+interface SpillStore {
+  saveText(input: SaveTextSpill): Promise<SpillRef>
+}
+
+interface SpillSource {
+  toolName: string
+  callId: CallId
+  label: string
+}
+
+interface SaveTextSpill {
+  owner: { sessionId: SessionId }
+  source: SpillSource
+  suggestedName: string
+  content: string
+}
+
+type SpillLocator = Branded<'SpillLocator'>
+
+interface SpillRef {
+  locator: SpillLocator
+  bytes: number
+  retrievalHint: string
+}
+```
+
+`SpillLocator` is a [branded](../../../../packages/util/brand) model-facing handle returned by the backend. The local backend renders it as a filesystem path; a remote or database backend can render a URI, key, or command token. Consumers treat it as opaque and render it with `retrievalHint` instead of assuming `read` is always the right retrieval mechanism. `SpillOwner.sessionId` is the save-time storage namespace: forked sessions inherit existing spill locators from the seeded log without copying or re-owning them, and new spills after the fork use the child session id. A retention-period cleanup may expire old locators with other old session artifacts; the spill seam does not define a per-session cleanup policy.
+
+`dsh-spill-local` owns only storage details: session-scoped directory selection, safe names, path-traversal protection, the write, and returning `{ locator, bytes, retrievalHint }`. It does not own retention policy, tool-result replacement, search, or file inspection. Files land at `<root>/session-<hash>/<random>-<safeName>`, where `root` is a configured path or a lazily-created private (0700) per-process temp dir, the session subdir is a short `sha256(sessionId)` prefix, and the leaf is a random hex prefix plus the caller's `suggestedName` sanitized to one path segment (mirrors the JSONL backend's `encodeSegment`). The write is `open(path, 'wx', 0o600)` — exclusive and owner-only, so a planted symlink cannot redirect it. The locator is the path, and the retrieval hint tells the model it can use `read` or `grep` on that path.
+
+### Spill policy
+
+`dsh-spill-policy` is a `tools/post-execute` result transformer with one configuration knob:
+
+```ts ignore-check
+interface Config {
+  /** Omitted means no automatic spill policy. Present means apply to oversized plain text tool results. */
+  maxInlineBytes?: number
+}
+```
+
+When `maxInlineBytes` is omitted the plugin registers nothing (a true no-op). When set, it applies a default policy to final plain-text tool results:
+
+1. Let the tool run normally, delegating via `next()` so a downstream listener settles the result first.
+2. Flatten the accepted final `ContentBlock[]` only when it is entirely plain text; a result with any non-text block is left untouched.
+3. If its UTF-8 byte size is at or below `maxInlineBytes`, leave it unchanged.
+4. If it is larger, call `ctx.spillStore.saveText()` with the full final text.
+5. Replace the model-facing result with a retained head/tail preview plus the spill reference.
+
+The preview is an implementation default owned by the policy: a head/tail split of `maxInlineBytes` via the retention library's `TextRetainer`. Future config can expose preview sizing only after a second deployment needs it.
+
+The replacement text is intentionally generic because the policy only knows the final formatted tool result, not the tool's internal resource:
+
+```text
+<retained preview>
+
+(Omitted N bytes. Full formatted result stored at: /.../session-.../....txt. Use read with offset/limit, or grep this path to search within it.)
+```
+
+If `ctx.spillStore.saveText()` fails (permissions, ENOSPC, backend unavailable), or the call has no session owner, or no backend is loaded, the plugin logs the reason and returns the original result unchanged. Spill failure never turns a successful tool call into an `isError` result or hides the inline result.
+
+The policy skips `read` to avoid a circular `read -> spill file -> read again` loop. Additional opt-out configuration is deferred until a real second tool needs it.
+
+## Showcase: web_fetch
+
+`web_fetch` is the first showcase because it returns a naturally large text result and needs no tool-specific spill code. The tool is ordinary:
+
+```ts ignore-check
+ctx.tools.register(defineTool({
+  name: 'web_fetch',
+  async execute(args, exec) {
+    const result = await ctx.web.fetch({ url: args.url }, exec.signal ? { signal: exec.signal } : undefined)
+    return [{ type: 'text', text: formatFetchOutput(result) }]
+  },
+}))
+```
+
+With `dsh-spill-policy` configured, a large formatted fetch result is automatically retained and spilled. A deployment demonstrates the behavior by setting the provider resource cap higher than the policy cap:
+
+```yaml
+- id: web-fetch-local
+  name: '@deepseek-ai/dsh-web-fetch-local'
+  config:
+    maxBodyChars: 500000
+
+- id: spill-local
+  name: '@deepseek-ai/dsh-spill-local'
+
+- id: spill-policy
+  name: '@deepseek-ai/dsh-spill-policy'
+  config:
+    maxInlineBytes: 50000
+```
+
+This separation is important. `web-fetch-local` still owns resource caps (`maxResponseBytes`, `maxBodyChars`) to protect network, memory, and decoding work. `spill-policy` owns only the model-facing context cap after the result already exists. If the provider already returned `truncated: true`, the spill file contains the full formatted result the tool returned, not the full original webpage; the policy does not claim otherwise.
+
+## Relationship to retention and early spill
+
+Retention is separate from spill storage:
+
+- `@deepseek-ai/dsh-retention` owns preview mechanics (`TextRetainer`, `ItemRetainer`, and omitted metadata).
+- `@deepseek-ai/dsh-spill` owns saving final text and returning a locator plus retrieval hint.
+- `@deepseek-ai/dsh-spill-policy` applies the default final-result policy in the tool pipeline, composing the two.
+
+The final-result policy cannot replace tool-owned early spill. Some useful content is not present in final `ToolExecutionResult.content`:
+
+- `bash` final output is already a tail plus a temp spill path; the complete stdout/stderr streams live in executor files.
+- `subagent` final output is the child final answer, not the child rollout.
+- Future tools may produce runtime artifacts that are never represented by their final `ToolExecutionResult.content`.
+
+Those cases can consume `ctx.spillStore` directly in later work. They are not part of the first showcase.
+
+## Non-goals
+
+- No new model-facing `artifact_read` or `artifact_search` tool in v1.
+- No per-tool retention configuration in v1.
+- No model-facing timeout/truncation arguments.
+- No migration of `read` output into spill files.
+- No replacement for provider/resource caps such as `web-fetch-local.maxBodyChars`.
+- No bash temp-file normalization or subagent rollout capture in the first cut.
+
+## Deferred
+
+- `saveFile()` / `linkOrCopy` for existing executor spill files, needed for bash normalization.
+- Tool-owned spill for subagent rollouts (`await run.result`, read in-process child session before `run.dispose()`, save JSONL).
+- Per-tool opt-out or per-tool policy declarations if the built-in `read` skip is insufficient.
+- Remote or database storage backends for ACP or remote environments where a local path is not meaningful.
+- Cleanup and retention policy for old spill files, likely tied to session cleanup.
+
+## Testing
+
+- `dsh-spill` unit tests pin the seam contract: registration as `ctx.spillStore`, one-implementation-per-context, and disposal release.
+- `dsh-spill-local` unit tests cover `saveText`, `encodeSegment` sanitization (separators/tilde/whole-segment dots/empty), the session-hash directory, owner-only permissions, distinct paths per save, the configured/private root, and a storage-failure rejection.
+- `dsh-spill-policy` unit tests drive real tools through `ctx.tools.execute`: disabled-mode no-op, oversized-text replacement, small/non-text passthrough, `read` skip, best-effort fallback (save failure / no backend / no owner), and downstream-composition (bounding a replaced result, preserving `additionalContexts`).
+- `dsh-tool-web` integration drives `web_fetch` through `ctx.tools.execute` with the real `spill-local` backend + policy, proving the model-facing text changes only by the deliberate spill notice while the spill file holds the full formatted result.
+- The `coding-agent` example loads `spill-local` + `spill-policy`, so its keyless Loader smoke exercises the real load path (the namespace-plugin export shape + `inject`).
+
+## Consequences
+
+The default policy only sees final formatted text. It cannot preserve provider-internal content that was already capped or runtime artifacts that were never part of the result. This is acceptable for the first cut because the showcase is final-result spill, not early spill; tool-owned early spill remains deferred work.
+
+Returning real paths from the local backend keeps v1 simple and matches proven agent-tool behavior, while the seam itself only promises an opaque locator plus retrieval hint so remote backends can return non-file locators.
+
+The local-backend value proposition depends on the existing `read`/`grep` tools being able to inspect the returned local path, even when the spill directory is outside the session cwd. That holds today because the filesystem policy records observations and write guards but does not confine reads to the workspace. A future workspace-confinement policy must either allow local spill paths explicitly or use a non-file spill backend whose retrieval hint points at a supported reader.
+
+**Snapshot gap.** No ACP snapshot scenario covers the transcript-visible `web_fetch` spill notice yet. The ACP snapshot harness replays keyless and cannot hit the live web, and a `web_fetch` spill requires a real over-cap HTTP body; a deterministic scenario would need a seeded loopback fetch target the replay tree does not currently wire (the examples do not load `tool-web` at all). The behavior is covered instead by the `dsh-tool-web` integration test against a loopback server. Closing the gap is follow-up work: wire `tool-web` + a seeded fetch target into the ACP example, then record a `web-fetch-spill` scenario.
+
+The policy can become too large if it starts owning tool-specific semantics. It stays narrow: plain-text final results only. Tool-owned early spill remains future work.
+
+## Alternatives considered
+
+**Require each tool to opt in with a retention declaration.** Rejected for v1: the goal is a default behavior similar to Claude Code's generic tool-result persistence. A single `maxInlineBytes` deployment knob is enough to prove the shape.
+
+**Make `tool-results` a broad tool-result platform.** Rejected: a broad package name invites retention policy, result replacement, preview wording, search, and early spill into one seam. The shared storage part is smaller: save text and return a locator plus retrieval hint.
+
+**Use `ctx.fs.writeText` or the model-facing `write` tool.** Rejected: workspace filesystem writes carry project-file semantics, write/edit policy, observation state, and user-facing side effects. Spill files are runtime artifacts, not model-authored workspace edits. The existing `read` tool may inspect them later, but creation belongs to the runtime spill seam.
+
+**Let `web-fetch-local` fetch without caps and rely on spill-policy.** Rejected: spill-policy runs after the final tool result exists and cannot protect network, memory, or decoding resources. Provider resource caps stay mandatory.
+
+**Merge retention into spill.** Rejected: retention and spill have different responsibilities. `TextRetainer`/`ItemRetainer` decide what preview is kept and what was omitted; spill storage only saves the final text the policy asks it to save.

docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-14-provider-routed-llm-adapters.md: 75ef047a7f95621d9a9c018b6dc57439e6f2bb22
+2026-07-14-provider-routed-llm-adapters.zh.md: 75ac9adbe5f8e96930a72a977c1969ff3a119ee8

docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md

@@ -0,0 +1,91 @@
+# RFC: Provider-routed LLM adapters and a generic pi-ai backend
+
+Status: implemented
+
+English | [中文](2026-07-14-provider-routed-llm-adapters.zh.md)
+
+## Problem
+
+`dsh-llm` registered adapters by exact model name. A plugin supplied a model list at Cordis startup, `LlmService` stored one adapter per listed string, and `GenerateOptions.model` selected the adapter and the provider model at once. This worked while both shipping adapters targeted the same two DeepSeek models, but it conflated two independent decisions: which upstream provider owns a request, and which model that provider should run.
+
+The conflation prevents a provider gateway from serving an open-ended model catalog. OpenRouter, for example, is one provider with many model ids, while a private OpenAI-compatible endpoint may add models without changing the Harness plugin tree. Every newly selected model currently needs to have been registered during plugin startup. The same model id can also exist at multiple providers, so model-only registration cannot state which provider the caller intended.
+
+`dsh-llm-pi-ai` exposed none of pi-ai's provider abstraction. It constructed an inline DeepSeek `openai-completions` model, applied DeepSeek-specific payload patches, and stamped every replayed assistant message as DeepSeek. pi-ai itself has a provider/model catalog, selects APIs such as `openai-responses`, `anthropic-messages`, and `google-generative-ai`, and preserves provider-specific response ids and reasoning/tool signatures for later turns. The Harness conversion dropped that provenance, so simply replacing the inline model with a catalog lookup would have made same-model replay and cross-provider handoff incomplete.
+
+The adapter configuration also assumes one DeepSeek API key and endpoint. A generic backend needs independent credentials and endpoint overrides per provider while leaving AWS, Google ADC, OAuth, and other ambient authentication mechanisms to pi-ai.
+
+## Decision
+
+### Provider is the adapter registration key
+
+`GenerateOptions` and `LlmCallConfig` carry `provider: string` beside `model: string`; `AgentOptions` carries the corresponding optional creation field. A loop request is valid only after both values are non-empty, and both values are part of the logged request header. `agent/request` may return a replacement pair on any step, so a session can switch providers and models without changing the Cordis plugin lifecycle.
+
+`LlmService` registers and resolves adapters by provider. `registerAdapter(providers, adapter)` checks the entire provider list before mutating the registry, rejects a duplicate with `DUPLICATE_ADAPTER`, and disposes the whole registration as one effect. Model ids are not registration keys; the selected adapter still validates or forwards them. The later [LLM catalog and ACP selection RFC](2026-07-15-llm-model-catalog-and-acp-selection.md) added advisory `listProviders()` / `listModels()` discovery without turning model membership into request validation.
+
+A provider has exactly one adapter owner in a Cordis context. `dsh-llm-deepseek` registers `deepseek`; `dsh-llm-pi-ai` may also register `deepseek`, but loading both owners is a configuration error rather than an ordering rule or fallback. A deployment that wants the hand-rolled DeepSeek implementation excludes `deepseek` from the pi-ai profiles. A deployment that wants pi-ai's DeepSeek implementation does not mount `dsh-llm-deepseek`.
+
+`dsh-llm-deepseek` removes its model registration list and accepts any model string routed through provider `deepseek`. Its request serialization, `/chat/completions` endpoint, thinking options, SSE parsing, and error behavior remain unchanged; `options.model` is still sent verbatim.
+
+### Explicit pi-ai provider profiles
+
+`dsh-llm-pi-ai` takes one non-empty list of provider profiles. Provider names must be unique within the list and present in pi-ai's `getProviders()` result. Each profile contains the provider name plus optional `apiKey`, `baseURL`, headers, reasoning level and budgets, cache retention, transport, timeouts, and retry settings. Credentials are never global: an explicit key applies only to its profile, while an absent key lets pi-ai resolve its standard environment variable, OAuth token, AWS credential chain, Google ADC, or other provider-native ambient authentication. An explicitly empty key is invalid configuration rather than an environment fallback.
+
+The plugin registers all configured provider names against one `PiAiAdapter` in one all-or-nothing call. A request uses its provider to select the matching profile and finds its model in `getModels(provider)` to obtain the catalog descriptor. An unknown provider fails at plugin load; an unknown model fails before network I/O with `UNKNOWN_MODEL`. The catalog object is never mutated. When a profile supplies `baseURL`, the adapter clones the selected descriptor and overrides only `baseUrl`, so a private endpoint can retain pi-ai's API, capabilities, compatibility flags, context limits, and reasoning map. The private endpoint must implement the selected provider's protocol, and the model id must still exist in the installed pi-ai catalog.
+
+The adapter calls pi-ai's `streamSimple()` so each catalog model chooses its registered API implementation, including OpenAI Responses instead of Chat Completions where the descriptor says `openai-responses`. Harness temperature, maximum tokens, signal, session id, and the profile's common stream options flow through directly. Profile headers merge with the mandatory Harness attribution headers, with Harness attribution winning its reserved names. The adapter no longer maintains DeepSeek-specific payload rewrites or a provider-protocol matrix.
+
+pi-ai's common stream options do not expose stop sequences. `dsh-llm-pi-ai` rejects a defined Harness `stop` option with `UNSUPPORTED_OPTION` rather than silently ignoring it or growing a second provider-specific payload implementation. `dsh-llm-deepseek` continues to support `stop` through its native request serializer.
+
+### Durable assistant provenance and replay state
+
+Assistant messages carry provider-neutral provenance containing the request's `provider` and `model`, plus an optional JSON-serializable adapter replay state. A successful `assistant/message` session event records this provenance and `deriveMessages()` returns it with the assistant message. User, system, context, and tool-result messages carry no assistant provenance. The provider/model fields are authoritative loop data; an adapter owns only its opaque replay-state payload.
+
+A terminal successful `finish` chunk may carry replay state, and `BlockAssembler` retains it alongside usage and finish reason. The loop attaches it to the assistant provenance only when the post-`agent/step-result` content is structurally equal to the assembled provider output. A listener that rewrites content keeps the provider/model provenance but loses the now-stale replay state. Error and aborted responses do not produce a normal assistant message and therefore do not enter future model history.
+
+The pi-ai replay state is a versioned, minimal projection of its successful `AssistantMessage`: source API/provider/model, response id/model, stop reason, and index-aligned text, thinking, and tool-call signatures. It does not duplicate text or tool arguments already carried by Harness content blocks, and it omits diagnostics, timestamps, usage, and errors. On a later request, `LlmService` gives replay state to the target adapter only when the historical provider and target provider are currently owned by the same adapter instance. That adapter combines the logged Harness content with replay state when it can restore the historical response, and owns any required cross-model or cross-provider conversion. An adapter receiving replay state with an unknown version or mismatched block shape fails explicitly; a different adapter receives only provider-neutral content and provenance.
+
+This state is model-visible replay input and therefore follows the existing [reconstructable-request rule](../../implemented/architecture/2026-07-05-reconstructable-requests.md): it is present in both the terminal `finish` chunk and the assembled `assistant/message` provenance that drives derivation. Resume and fork preserve it verbatim. Compaction that shadows the assistant message also removes its replay state from the active surface; the summary is ordinary provider-neutral content.
+
+### Propagate the target through every request producer
+
+Every model-selection surface carries provider and model together: declarative agents, ACP and stdio app config, the JSON-RPC initialize request, subagent overrides and inheritance, workflow child overrides, and direct compaction summarization. Subagents inherit both fields from their parent before applying request overrides. The system-prompt variable set gains `provider` beside `model`.
+
+Compaction configuration gains `summarizationProvider` beside `summarizationModel`. Both are empty to inherit, or both are non-empty to select an explicit target; a half-configured pair fails load. Inheritance uses the last logged request target when one exists and falls back to the agent's creation options. `compact/summary` records both fields with the existing model-call envelope.
+
+The JSON-RPC runtime receives provider and model explicitly. Its convenience fallback mounts `dsh-llm-deepseek` only for provider `deepseek` when that provider has no registered owner; other missing providers fail without guessing an adapter.
+
+The on-disk session format remains the pre-release pinned version `0`, with no compatibility promise. Seed/load validation rejects request headers lacking provider and assistant messages lacking required provenance instead of accepting an old shape that can no longer reconstruct the request.
+
+## Alternatives considered
+
+**Keep model names as registry keys and add wildcard adapters.** A wildcard introduces fallback ordering between exact registrations and catch-all plugins, makes duplicate ownership dependent on listener order, and still cannot distinguish the same model id at two providers without another convention.
+
+**Encode provider and model into one string.** Values such as OpenRouter's `openai/gpt-*` already contain provider-like prefixes and slashes. A delimiter convention would leak routing syntax into every model selector and require escaping rules; two explicit fields are unambiguous and independently loggable.
+
+**Add `backend + provider + model`.** A backend key would allow `dsh-llm-deepseek` and pi-ai's DeepSeek implementation to coexist and switch per request. The accepted deployment rule is instead one adapter owner per provider: implementations of the same upstream are alternatives selected by plugin composition. A third routing dimension would burden every request and configuration for a capability with no current consumer.
+
+**Let `dsh-llm-pi-ai` automatically register every pi-ai provider.** This would claim ambient credentials and provider names the deployment never intended to expose, and would conflict with native adapters such as `dsh-llm-deepseek`. Explicit profiles make capability and credential scope reviewable.
+
+**Mount one pi-ai plugin instance per provider.** Separate instances isolate config but repeat plugin declarations and cannot make profile registration atomic. One adapter already receives provider on every request, so a validated profile map is the smaller lifecycle surface.
+
+**Accept arbitrary inline pi-ai model descriptors.** This would support catalog-external private model ids, but it exposes pi-ai's model and compatibility schema as Harness configuration and makes the adapter responsible for validating protocol-specific combinations. The first version supports custom endpoints by overriding `baseURL` on catalog models; custom descriptors require a separate decision after a real catalog-external deployment is identified.
+
+## Consequences
+
+- Provider names are deployment-wide route ownership keys: two providers may use the same model string, but mounting two adapters for one provider fails at load instead of creating fallback order.
+- Model selection no longer changes the Cordis plugin graph. Catalog-backed adapters can accept any installed catalog model selected after startup, while the native DeepSeek adapter forwards arbitrary DeepSeek model ids.
+- A custom `baseURL` preserves the selected catalog model's protocol and capabilities; it does not make catalog-external model ids valid. Private endpoints must implement that catalog entry's protocol.
+- pi-ai credentials and transport knobs are scoped per provider profile. An omitted key delegates to pi-ai ambient authentication, while an explicitly empty key is invalid.
+- `dsh-llm-pi-ai` rejects stop sequences because pi-ai's common stream API cannot express them; the native DeepSeek adapter retains its stop support.
+- Replay state is portable only within the adapter instance that owns both the historical and target providers. Cross-provider and cross-model restoration is an adapter responsibility, and another adapter receives provider-neutral history without the opaque state.
+- Current pre-release session JSONL requires provider/model request headers and assistant provenance. Older shapes remain version `0` but are rejected rather than migrated.
+
+## Testing
+
+- Unit coverage exercises registry conflicts, request reconstruction, session validation, profile resolution, option forwarding, native API selection including OpenAI Responses, conversion, replay validation, error mapping, cancellation, content rewrites, and same-instance versus different-instance replay dispatch.
+- Keyless loop/session tests and ACP snapshots exercise durable provider/model metadata, resume and fork propagation, workflow/subagent overrides, and unchanged user-visible transcripts; the key-gated DeepSeek e2e retains real provider streaming and tool follow-up coverage.
+- Public JSDoc, package READMEs, architecture and core-data-structure docs, generated catalogs, examples, session fixtures, and Python SDK pairs use provider/model targets consistently and are checked by the repository documentation and type-equivalence gates.
+
+## Risks
+
+This is a repo-wide pre-release API break: model-only request construction, adapter registration, app protocols, fixtures, and persisted version-0 event shapes all change together, with no compatibility aliases. The provider exclusivity rule deliberately prevents two implementations of the same upstream from coexisting in one context. A pi-ai dependency update can change the accepted provider/model catalog, so the lockfile and adapter e2e matrix define the tested set. Custom `baseURL` endpoints inherit the chosen catalog model's protocol assumptions and cannot repair an incompatible proxy. Catalog-external model descriptors and multimodal content remain unsupported. pi-ai replay state may contain opaque encrypted reasoning signatures; it is persisted because the provider requires it for continuity, but it is never rendered or logged outside the existing session record.

docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md

@@ -0,0 +1,91 @@
+# RFC: 基于提供方路由的 LLM 适配器与通用 pi-ai 后端
+
+Status: implemented
+
+[English](2026-07-14-provider-routed-llm-adapters.md) | 中文
+
+## 问题
+
+`dsh-llm` 按精确模型名称注册适配器。插件在 Cordis 启动时提供模型列表，`LlmService` 为列表中的每个字符串保存一个适配器，`GenerateOptions.model` 同时选择适配器与提供方模型。两个正式适配器都只面向相同的两个 DeepSeek 模型时，这种方式可以工作，但它混淆了两个独立决策：由哪个上游提供方承接请求，以及该提供方应运行哪个模型。
+
+这种混淆使提供方网关无法提供开放的模型目录。例如，OpenRouter 是一个包含大量模型 ID 的提供方，私有 OpenAI 兼容端点也可能在不修改 Harness 插件树的情况下增加模型。目前，每个新选择的模型都必须在插件启动期间完成注册。同一个模型 ID 还可能存在于多个提供方中，因此仅按模型注册无法表达调用方预期使用的提供方。
+
+`dsh-llm-pi-ai` 没有暴露 pi-ai 的提供方抽象。它以内联方式构造 DeepSeek `openai-completions` 模型，应用 DeepSeek 专用的 payload 补丁，并将每条回放的助手消息标记为 DeepSeek。pi-ai 自身提供提供方/模型目录，能够选择 `openai-responses`、`anthropic-messages`、`google-generative-ai` 等 API，并保留提供方专用的响应 ID，以及后续轮次所需的推理和工具签名。Harness 转换丢弃了这些来源信息，因此仅将内联模型替换为目录查询，会导致同模型回放与跨提供方移交不完整。
+
+适配器配置同样假定只存在一个 DeepSeek API 密钥和端点。通用后端需要为各提供方分别配置凭据和端点覆盖，同时继续由 pi-ai 处理 AWS、Google ADC、OAuth 等环境认证机制。
+
+## 决策
+
+### 提供方作为适配器注册键
+
+`GenerateOptions` 与 `LlmCallConfig` 在 `model: string` 之外携带 `provider: string`，`AgentOptions` 则携带对应的可选创建字段。只有两个值都非空时，agent loop（智能体循环）请求才有效；两个值也都会写入请求头日志。`agent/request` 可以在任意步骤返回替换后的字段组合，因此会话可以切换提供方与模型，无需改变 Cordis 插件生命周期。
+
+`LlmService` 按提供方注册和解析适配器。`registerAdapter(providers, adapter)` 在修改注册表前检查整个提供方列表，遇到重复项时返回 `DUPLICATE_ADAPTER`，并将整组注册作为一个 effect 释放。模型 ID 不作为注册键；仍由选中的适配器负责验证或转发。后续的 [LLM 目录与 ACP 模型选择 RFC](2026-07-15-llm-model-catalog-and-acp-selection.md) 增加了建议性的 `listProviders()` / `listModels()` 发现接口，但不会把目录成员关系变成请求校验规则。
+
+在一个 Cordis 上下文中，一个提供方只能有一个适配器所有者。`dsh-llm-deepseek` 注册 `deepseek`；`dsh-llm-pi-ai` 也可以注册 `deepseek`，但同时加载两个所有者属于配置错误，不采用顺序规则或回退行为。若部署选择手写的 DeepSeek 实现，需从 pi-ai 配置中排除 `deepseek`；若部署选择 pi-ai 的 DeepSeek 实现，则不挂载 `dsh-llm-deepseek`。
+
+`dsh-llm-deepseek` 移除模型注册列表，接受通过 `deepseek` 提供方路由的任意模型字符串。其请求序列化、`/chat/completions` 端点、thinking 选项、SSE（Server-Sent Events）解析和错误行为保持不变；`options.model` 仍会原样发送。
+
+### 显式 pi-ai 提供方配置
+
+`dsh-llm-pi-ai` 接受一个非空的提供方配置列表。列表内的提供方名称必须唯一，并且存在于 pi-ai 的 `getProviders()` 结果中。每项配置包含提供方名称，以及可选的 `apiKey`、`baseURL`、headers、推理级别和预算、缓存保留设置、传输方式、超时和重试设置。凭据不设全局值：显式密钥仅对所属配置生效；未提供密钥时，pi-ai 使用标准环境变量、OAuth token、AWS 凭据链、Google ADC 或其他提供方原生环境认证。显式空密钥属于无效配置，不会回退到环境认证。
+
+插件通过一次全有或全无调用，将所有已配置的提供方名称注册到同一个 `PiAiAdapter`。请求按 provider 选择对应配置，并在 `getModels(provider)` 中查找模型以取得目录描述符。未知提供方会在插件加载时失败；未知模型会在网络 I/O 前以 `UNKNOWN_MODEL` 失败。适配器不会修改目录对象。当配置提供 `baseURL` 时，适配器复制选中的描述符，仅覆盖 `baseUrl`，使私有端点保留 pi-ai 的 API、能力、兼容标志、上下文限制与推理映射。私有端点必须实现所选提供方的协议，模型 ID 也仍须存在于已安装的 pi-ai 目录中。
+
+适配器调用 pi-ai 的 `streamSimple()`，因此每个目录模型会选择其注册的 API 实现；描述符为 `openai-responses` 时使用 OpenAI Responses，而非 Chat Completions。Harness 的 temperature、最大 token 数、signal、session ID，以及提供方配置中的通用流选项均直接传递。配置 headers 与 Harness 强制归因 headers 合并；发生保留名称冲突时，以 Harness 归因为准。适配器不再维护 DeepSeek 专用 payload 重写或提供方协议矩阵。
+
+pi-ai 的通用流选项不支持停止序列。若 Harness `stop` 选项已定义，`dsh-llm-pi-ai` 会以 `UNSUPPORTED_OPTION` 拒绝请求，不会静默忽略，也不会增加第二套提供方专用 payload 实现。`dsh-llm-deepseek` 继续通过原生请求序列化器支持 `stop`。
+
+### 持久化助手来源信息与回放状态
+
+助手消息携带提供方无关的来源信息，其中包含请求的 `provider` 和 `model`，以及可选的 JSON 可序列化适配器回放状态。成功的 `assistant/message` 会话事件记录这些来源信息，`deriveMessages()` 返回助手消息时也会包含这些信息。用户、system、context 与工具结果消息不携带助手来源信息。provider/model 字段是 agent loop 的权威数据；适配器仅拥有其不透明回放状态 payload。
+
+成功的终止 `finish` 分片可以携带回放状态，`BlockAssembler` 会将其与 token 用量和结束原因一起保留。只有当 `agent/step-result` 处理后的内容与提供方组装输出在结构上相等时，agent loop 才会把回放状态附加到助手来源信息。监听器重写内容后，provider/model 来源信息仍会保留，但已经陈旧的回放状态会被移除。错误或中止响应不会生成正常助手消息，因此不会进入后续模型历史。
+
+pi-ai 回放状态是其成功 `AssistantMessage` 的带版本最小投影，包含源 API/provider/model、响应 ID/model、停止原因，以及按索引对齐的文本、thinking 和工具调用签名。它不会重复 Harness 内容块中已有的文本或工具参数，也不包含诊断信息、时间戳、用量或错误。后续请求中，只有历史提供方和目标提供方当前归同一个适配器实例所有时，`LlmService` 才会把回放状态交给目标适配器。适配器在能够恢复历史响应时，将 Harness 记录的内容与回放状态组合，并负责所需的跨模型或跨提供方转换。适配器收到未知版本或块形状不匹配的回放状态时会显式失败；其他适配器只能收到提供方无关的内容与来源信息。
+
+该状态属于模型可见的回放输入，因此遵循现有的[请求可重建规则](../../implemented/architecture/2026-07-05-reconstructable-requests.md)：它同时存在于终止 `finish` 分片和驱动派生的已组装 `assistant/message` 来源信息中。恢复和 fork 会原样保留该状态。压缩（compaction）遮蔽助手消息时，也会从活动 surface 中移除其回放状态；摘要属于普通的提供方无关内容。
+
+### 在所有请求生产方中传播目标
+
+每个模型选择接口都同时携带 provider 与 model：声明式 agent、ACP（Agent Client Protocol）和 stdio 应用配置、JSON-RPC initialize 请求、subagent 覆盖与继承、工作流子 agent 覆盖，以及直接压缩摘要。subagent 先从父 agent 继承两个字段，再应用请求覆盖。系统提示词变量集合在 `model` 之外增加 `provider`。
+
+压缩配置在 `summarizationModel` 之外增加 `summarizationProvider`。两个值均为空时继承，均非空时选择显式目标；只配置其中一个会导致加载失败。继承优先使用最近一次记录的请求目标，没有时回退到 agent 创建选项。`compact/summary` 使用现有模型调用 envelope 记录两个字段。
+
+JSON-RPC 运行时显式接收 provider 与 model。仅当 `deepseek` 提供方没有注册所有者时，其便利回退才会挂载 `dsh-llm-deepseek`；其他缺失的提供方会直接失败，不会猜测适配器。
+
+磁盘会话格式仍使用预发布阶段固定的版本 `0`，且不承诺兼容性。seed/load 验证会拒绝缺少 provider 的请求头，以及缺少必需来源信息的助手消息，不会接受已无法重建请求的旧格式。
+
+## 考虑过的替代方案
+
+**继续以模型名称作为注册表键，并增加通配适配器。** 通配机制会在精确注册与兜底插件之间引入回退顺序，使重复所有权取决于监听器顺序；若不再增加其他约定，仍无法区分不同提供方中相同的模型 ID。
+
+**将提供方与模型编码到一个字符串中。** OpenRouter 的 `openai/gpt-*` 等值已经包含类似提供方的前缀和斜杠。分隔符约定会把路由语法泄漏到每个模型选择接口，并需要转义规则；两个显式字段更清晰，也可以分别记录日志。
+
+**增加 `backend + provider + model`。** backend 键可以让 `dsh-llm-deepseek` 与 pi-ai 的 DeepSeek 实现共存，并按请求切换。最终采用的部署规则是一个提供方对应一个适配器所有者：同一上游的不同实现属于由插件组合选定的替代项。第三个路由维度会增加每个请求与配置的负担，却没有当前消费方。
+
+**让 `dsh-llm-pi-ai` 自动注册所有 pi-ai 提供方。** 这种方式会占用部署无意暴露的环境凭据和提供方名称，并与 `dsh-llm-deepseek` 等原生适配器冲突。显式配置可以审查能力和凭据范围。
+
+**每个提供方挂载一个 pi-ai 插件实例。** 独立实例可以隔离配置，但会重复插件声明，也无法实现配置注册的原子性。每个请求本就向同一个适配器提供 provider，因此经过验证的配置映射具有更小的生命周期接口。
+
+**接受任意内联 pi-ai 模型描述符。** 这种方式可支持目录外的私有模型 ID，但会将 pi-ai 的模型与兼容性 schema 暴露为 Harness 配置，并要求适配器验证协议专用组合。当前版本通过覆盖目录模型的 `baseURL` 支持自定义端点；只有实际出现目录外部署需求后，才会另行决策是否支持自定义描述符。
+
+## 影响
+
+- 提供方名称是部署范围内的路由所有权键：两个提供方可以使用相同的模型字符串，但为同一个提供方挂载两个适配器会在加载时失败，不会形成回退顺序。
+- 模型选择不再改变 Cordis 插件图。目录型适配器可以接受启动后选择的任意已安装目录模型，原生 DeepSeek 适配器则会转发任意 DeepSeek 模型 ID。
+- 自定义 `baseURL` 会保留所选目录模型的协议与能力，但不会让目录外模型 ID 变为有效。私有端点必须实现该目录项对应的协议。
+- pi-ai 凭据与传输选项按提供方配置隔离。省略密钥时委托 pi-ai 使用环境认证；显式空密钥无效。
+- pi-ai 的通用流 API 无法表达停止序列，因此 `dsh-llm-pi-ai` 会拒绝停止序列；原生 DeepSeek 适配器仍支持停止序列。
+- 仅当历史提供方与目标提供方归同一个适配器实例所有时，回放状态才可移植。适配器负责跨提供方和跨模型恢复；其他适配器只接收不含不透明状态的提供方无关历史。
+- 当前预发布会话 JSONL 要求请求头包含 provider/model，助手消息包含来源信息。旧格式仍使用版本 `0`，但会被拒绝，不执行迁移。
+
+## 测试
+
+- 单元测试覆盖注册表冲突、请求重建、会话验证、配置解析、选项转发、包括 OpenAI Responses 在内的原生 API 选择、转换、回放验证、错误映射、取消、内容重写，以及同一实例与不同实例间的回放分发。
+- 无密钥的 agent loop/会话测试和 ACP 快照覆盖持久化 provider/model 元数据、恢复与 fork 传播、工作流/subagent 覆盖，以及不变的用户可见 transcript（文本记录）；密钥门控的 DeepSeek e2e 测试保留真实提供方的流式输出与工具后续调用覆盖率。
+- 公共 JSDoc、package README、架构与核心数据结构文档、生成目录、示例、会话 fixture（测试前置数据）和 Python SDK 配对文档统一使用 provider/model 目标，并由仓库文档与类型等价门禁校验。
+
+## 风险
+
+这是一次覆盖全仓库的预发布 API 破坏性变更：仅模型的请求构造、适配器注册、应用协议、fixture，以及持久化版本 0 事件格式会同时变化，不提供兼容别名。提供方排他规则有意禁止同一上游的两个实现共存于同一上下文。pi-ai 依赖升级可能改变可接受的提供方/模型目录，因此锁文件与适配器 e2e 矩阵定义已验证集合。自定义 `baseURL` 端点会继承所选目录模型的协议假设，无法修复不兼容的代理。目录外模型描述符与多模态内容仍不受支持。pi-ai 回放状态可能包含不透明的加密推理签名；提供方需要该信息维持连续性，因此系统会持久化该状态，但不会在现有会话记录之外渲染或记录它。

docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-15-llm-model-catalog-and-acp-selection.md: d84fe9fdb75bd2d28a00269c84d29c4223798253
+2026-07-15-llm-model-catalog-and-acp-selection.zh.md: 019819c4aa5ab4ad281b5b32daa76a004c9d6466

docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md

@@ -0,0 +1,66 @@
+# RFC: Advisory LLM catalogs and per-session ACP model selection
+
+Status: implemented
+
+English | [中文](2026-07-15-llm-model-catalog-and-acp-selection.zh.md)
+
+## Problem
+
+Provider-routed adapters let every request choose `provider + model`, but `LlmService` exposed only routing and streaming. A UI could not discover which providers were registered or which models an adapter was prepared to recommend. ACP clients therefore received no `model` session config option, so Zed, JetBrains, and VS Code integrations had no model list even though the request seam already supported runtime switching.
+
+Model discovery cannot become request validation. The hand-written DeepSeek adapter deliberately forwards arbitrary model ids to a public or private endpoint, while pi-ai has a finite installed catalog that is authoritative for its own request resolution. Treating one shared catalog as a whitelist would remove the private-endpoint behavior that provider routing was designed to preserve.
+
+ACP selection must also preserve the provider dimension. The same model id may appear under multiple routes, and switching a global adapter or agent template would leak one editor session's choice into every other session. Prompt variables and request routing must change together; a selection that lands during asynchronous prompt assembly cannot make `{{model}}` name one model while the request reaches another.
+
+## Decision
+
+### Provider-neutral advisory discovery
+
+`LlmAdapter` gains `providerInfo(provider)` and asynchronous `listModels(provider)` methods. Their provider-neutral results are `LlmProviderInfo { id, name }` and `LlmModelInfo { provider, id, name, description? }`. The defaults preserve existing adapter behavior by naming a provider after its route and advertising no models.
+
+`LlmService.listProviders()` returns detached metadata in registration order. `LlmService.listModels(provider)` delegates to the route owner, validates non-empty ids and names, rejects a mismatched provider or duplicate model id with `INVALID_CATALOG`, and returns detached values. Unknown providers still fail with `NO_ADAPTER`. Provider metadata is validated atomically during `registerAdapter()` so a malformed display record cannot leave a partial registration.
+
+Catalog membership is advisory. It drives selectors and diagnostics but never changes `stream()` routing and never rejects an otherwise valid request. Provider ownership remains exclusive and lifecycle-bound; model ids remain request-time adapter input.
+
+`dsh-llm-pi-ai` maps the configured provider's installed `getModels(provider)` entries into the neutral catalog. Its existing request-time catalog lookup remains authoritative and still rejects unknown models with `UNKNOWN_MODEL`. `dsh-llm-deepseek` accepts an optional `models` config containing display entries, defaulting to `deepseek-v4-flash` and `deepseek-v4-pro`. An explicit list replaces those defaults and an empty list disables discovery. The entries improve selector UX for known public or private models, while every unlisted model id continues to pass through unchanged.
+
+### ACP session config option
+
+The ACP bridge advertises one select with `id: model` and `category: model` in `session/new` and `session/load` when the session has a complete target whose provider is registered. Each opaque option value encodes the full provider/model pair. Models are grouped by provider when multiple non-empty provider groups exist; a single group is flattened for clients that render simple selects better.
+
+The session's current target is added to the displayed options when its adapter omits it. This preserves custom DeepSeek and private-endpoint models while keeping the adapter catalog advisory. A target with an unregistered provider is not advertised, and a model-less agent remains available to another `agent/request` supplier.
+
+`session/set_config_option` accepts only values from the current catalog snapshot and updates a target reference owned by that ACP session. No global `LlmService` or `AgentOptions` state changes, so concurrent sessions may select different providers and models. The existing permission select remains independent, and every response returns the complete refreshed option state.
+
+### Prompt/request consistency and durability
+
+Agent setup installs scoped `system-prompt/assemble` and `agent/request` listeners. Prompt assembly snapshots the selected pair once per step, overwrites the assembled `provider` and `model` variables after downstream prompt listeners, and the request listener applies that same snapshot after downstream request listeners. A selection during asynchronous assembly therefore starts on the next step rather than splitting prompt text from routing. Other call-config fields remain untouched.
+
+The request header remains the durable source of truth. When a selected target is actually used, the existing full `request/header` snapshot records it. `session/load` initializes the ACP selection from the folded last request header before falling back to bridge config. A selection that is never used by a request is intentionally in-memory only because it never became model-visible state.
+
+ACP's experimental `providers/*` capability is not used. That draft surface configures provider base URLs, protocols, and headers, including secrets; it does not enumerate models and would give the UI authority to rewrite deployment-owned adapter configuration.
+
+## Alternatives considered
+
+**Return model strings only.** A model-only value loses the provider route and becomes ambiguous as soon as two providers expose the same id.
+
+**Make catalogs mandatory whitelists.** This conflicts with the hand-written adapter's arbitrary model pass-through and private deployments. The selected adapter already owns authoritative request validation.
+
+**Store selection in `AgentOptions` or `LlmService`.** Those are creation-wide or deployment-wide objects. Mutating them would couple concurrent ACP sessions and bypass the logged `agent/request` replacement path.
+
+**Persist a new model-selection session event immediately.** An unused UI selection has not affected a model request. Recording the existing request header when the target is consumed preserves the model-visible-if-and-only-if-logged rule without adding a second source of truth.
+
+**Use ACP `providers/*`.** That unstable API changes endpoint and authentication configuration rather than selecting a model for one session, and its lifecycle and secret-handling semantics do not match this feature.
+
+## Consequences
+
+- Any adapter can expose a dynamic model list without leaking provider-library types into the core seam.
+- Catalog consumers must treat absence as “not advertised,” never “invalid request.”
+- pi-ai-backed ACP deployments automatically inherit the installed pi-ai provider catalogs; hand-written DeepSeek deployments list known choices explicitly and retain arbitrary model support.
+- ACP clients receive a standard stable model config option, with provider-aware values and per-session isolation.
+- Request headers remain compatible with the provider-routed session shape; no new JSONL event or format version is required.
+- A catalog read can be asynchronous. ACP reads a detached snapshot before creating or resuming an agent, so discovery failure cannot leave a partially published session.
+
+## Testing
+
+Unit coverage validates catalog detachment and malformed metadata, pi-ai and DeepSeek catalog projection, ACP provider grouping, custom-current insertion, invalid values, provider/model request routing, prompt-variable alignment, concurrent-session isolation, model-less fallback, and load restoration from the request header. The existing ACP transport suites verify that the additional config option does not change prompt, cancellation, replay, approval, or tool-rendering behavior.

docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md

@@ -0,0 +1,66 @@
+# RFC: 建议性 LLM 目录与 ACP 会话级模型选择
+
+Status: implemented
+
+[English](2026-07-15-llm-model-catalog-and-acp-selection.md) | 中文
+
+## 问题
+
+基于提供方路由的适配器允许每次请求选择 `provider + model`，但 `LlmService` 只暴露路由和流式调用。UI 无法发现已注册的提供方，也无法知道适配器愿意推荐哪些模型。因此，ACP 客户端收不到 `model` 会话配置项；即使请求接缝已经支持运行时切换，Zed、JetBrains 和 VS Code 集成仍没有模型列表。
+
+模型发现不能变成请求校验。手写 DeepSeek 适配器会把任意模型 ID 原样转发给公开或私有端点，而 pi-ai 的有限安装目录则是其自身请求解析的权威依据。将共享目录视为白名单，会破坏提供方路由需要保留的私有端点能力。
+
+ACP 选择还必须保留提供方维度。同一个模型 ID 可能存在于多个路由下；切换全局适配器或 agent 模板会让一个编辑器会话的选择泄漏到其他会话。Prompt 变量与请求路由必须同时变化；如果选择发生在异步 prompt 组装期间，不能让 `{{model}}` 表示一个模型、实际请求却到达另一个模型。
+
+## 决策
+
+### 提供方中立的建议性发现
+
+`LlmAdapter` 增加 `providerInfo(provider)` 与异步 `listModels(provider)` 方法。其提供方中立结果分别为 `LlmProviderInfo { id, name }` 和 `LlmModelInfo { provider, id, name, description? }`。默认实现以路由名称作为提供方名称，并且不展示模型，从而保持现有适配器行为。
+
+`LlmService.listProviders()` 按注册顺序返回分离后的元数据。`LlmService.listModels(provider)` 委托给路由所有者，校验非空 ID 和名称，并在提供方不匹配或模型 ID 重复时以 `INVALID_CATALOG` 失败，最后返回分离后的值。未知提供方仍以 `NO_ADAPTER` 失败。提供方元数据在 `registerAdapter()` 期间进行原子校验，错误展示记录不会留下部分注册。
+
+目录成员关系仅提供建议。它驱动选择器与诊断，但不会改变 `stream()` 路由，也不会拒绝原本有效的请求。提供方所有权仍然具有排他性并绑定生命周期；模型 ID 仍是请求时传给适配器的输入。
+
+`dsh-llm-pi-ai` 将已配置提供方的安装目录 `getModels(provider)` 映射为中立目录。其现有请求时目录查询仍是权威依据，未知模型仍以 `UNKNOWN_MODEL` 失败。`dsh-llm-deepseek` 接受可选的 `models` 配置作为展示条目，默认包含 `deepseek-v4-flash` 和 `deepseek-v4-pro`。显式列表会替换这些默认值，空列表则关闭发现。这些条目改善已知公开或私有模型的选择体验，而所有未列出的模型 ID 仍会原样透传。
+
+### ACP 会话配置项
+
+当会话具有完整目标且目标提供方已注册时，ACP bridge 会在 `session/new` 与 `session/load` 中展示一个 `id: model`、`category: model` 的选择项。每个不透明选项值都编码完整的提供方/模型字段组合。存在多个非空提供方分组时按提供方分组；只有一个分组时将其展开，以便对简单选择器支持更好的客户端展示。
+
+如果适配器目录未包含会话当前目标，该目标仍会加入展示选项。这能保留自定义 DeepSeek 与私有端点模型，同时维持目录的建议性。提供方未注册的目标不会展示；缺少模型的 agent 仍可由其他 `agent/request` 提供者补齐。
+
+`session/set_config_option` 只接受当前目录快照中的值，并更新该 ACP 会话独占的目标引用。它不会修改全局 `LlmService` 或 `AgentOptions` 状态，因此并发会话可以选择不同的提供方和模型。现有权限选择项保持独立，每次响应都返回完整的刷新后配置项状态。
+
+### Prompt/请求一致性与持久化
+
+Agent setup 会安装作用域内的 `system-prompt/assemble` 与 `agent/request` 监听器。Prompt 组装为每个 step 只快照一次选中的字段组合，在下游 prompt 监听器完成后覆盖组装结果中的 `provider` 与 `model` 变量；请求监听器则在下游请求监听器完成后应用同一个快照。因此，异步组装期间发生的选择会从下一个 step 生效，不会导致 prompt 文本与路由分裂。其他调用配置字段保持不变。
+
+请求头仍是持久化事实来源。当选中目标被实际使用时，现有的完整 `request/header` 快照会记录它。`session/load` 先从折叠后的最后请求头初始化 ACP 选择，再回退到 bridge 配置。一个从未被请求使用的选择只保留在内存中，因为它从未成为模型可见状态。
+
+本功能不使用 ACP 的实验性 `providers/*` 能力。该草案接口配置提供方 base URL、协议和 headers，其中可能包含密钥；它不枚举模型，并且会赋予 UI 改写部署所有的适配器配置的权力。
+
+## 考虑过的替代方案
+
+**只返回模型字符串。** 仅模型值会丢失提供方路由；两个提供方暴露相同 ID 时立刻产生歧义。
+
+**将目录设为强制白名单。** 这与手写适配器的任意模型透传和私有部署冲突。请求的权威校验本就属于被选中的适配器。
+
+**将选择存入 `AgentOptions` 或 `LlmService`。** 这些对象分别面向创建过程或整个部署。修改它们会耦合并发 ACP 会话，并绕开带日志归因的 `agent/request` 替换路径。
+
+**立即写入新的模型选择会话事件。** 尚未使用的 UI 选择没有影响模型请求。目标被消费时记录现有请求头，既满足“模型可见当且仅当已记录”的规则，也不会引入第二个事实来源。
+
+**使用 ACP `providers/*`。** 该不稳定 API 用于修改端点与认证配置，而不是为单个会话选择模型；其生命周期和密钥处理语义都不适合本功能。
+
+## 结果
+
+- 任意适配器都能暴露动态模型列表，无需把提供方库类型泄漏到核心接缝。
+- 目录消费者必须把缺失理解为“未展示”，而不是“请求无效”。
+- 基于 pi-ai 的 ACP 部署会自动继承已安装的 pi-ai 提供方目录；手写 DeepSeek 部署显式列出已知选项，同时保留任意模型能力。
+- ACP 客户端会收到稳定标准的模型配置项，其中的值保留提供方信息，并按会话隔离。
+- 请求头继续使用基于提供方路由的会话结构；不需要增加 JSONL 事件或格式版本。
+- 目录读取可以是异步的。ACP 在创建或恢复 agent 前读取分离后的快照，因此发现失败不会留下部分发布的会话。
+
+## 测试
+
+单元测试覆盖目录分离与错误元数据、pi-ai 和 DeepSeek 目录投影、ACP 提供方分组、自定义当前模型补入、无效值、提供方/模型请求路由、prompt 变量一致性、并发会话隔离、无模型回退，以及从请求头恢复选择。现有 ACP 传输测试验证新增配置项不会改变 prompt、取消、回放、审批或工具展示行为。

docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-15-replay-token-meter-service.md: 34df0383d1b8ae8047c4283eef3800de772c3cae
+2026-07-15-replay-token-meter-service.zh.md: 51f319f3c473fe247791e69133eef4280b768002

docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md

@@ -0,0 +1,60 @@
+# RFC: Replay token meter service
+
+Status: implemented
+
+English | [中文](2026-07-15-replay-token-meter-service.zh.md)
+
+## Problem
+
+Context pressure is useful outside compaction. A compaction backend, an overflow guard, or a future request-policy plugin can all need the same answer: how much of the configured context window does the durable request consume? Keeping that fold inside `dsh-compact-basic` duplicates replay logic, makes measurement unavailable without compaction, and encourages callers to reuse stale accounting.
+
+Provider usage is not a complete answer. It describes one successful call under one exact request envelope, while the current surface can grow, shrink, or be replaced afterward. Sessions also switch providers and models, old logs can lack chunk provenance, and usage fields separate input, cache-read, cache-write, output, and reasoning counts. A useful service therefore combines the latest exact anchor with conservative heuristic repricing and exposes the log revision consumed by each result.
+
+## Decision
+
+### One concrete LLM-family service
+
+`@deepseek-ai/dsh-token-meter` is one concrete package under `packages/llm/` and registers `ctx.tokenMeter`. It is not split into an interface and backend before a second implementation exists. `TokenMeterService` itself exposes `contextWindow`, `measure(session, requestHeader?)`, and `estimateMessage(message)`; consumers call the singleton service directly.
+
+The service has one `contextWindow`, defaulting to 128,000 tokens and configurable as a positive integer. Estimation uses a fixed four-characters-per-token heuristic plus structural overhead. There are no model profiles, density settings, tokenizer backends, or language-specific strategies.
+
+### Per-session replay folds
+
+Each session owns one isolated incremental fold. Active folds advance from `session/event`; every read catches up through the durable tail, so listener ordering, seeded sessions, and service reload do not change the answer. The fold tracks canonical full request-header snapshots, step boundaries, surface appends and replacements, assistant usage, and assistant-chunk provenance. A malformed next event fails transactionally and remains unread rather than partially mutating state.
+
+`measure(session, requestHeader?)` synchronizes the fold once and returns scalar pressure together with positional per-node prices. `totalTokens` remains request-and-response pressure; `surfaceTokens` is the surface-only heuristic total and equals the sum of `nodes[].tokens`. A `requestHeader` override changes pressure pricing only, while the surface fields always describe the current session. `estimateMessage(message)` applies the fixed heuristic without session state. Each result is one detached, deeply immutable snapshot carrying one `logRevision`. Every measurement clones the current nodes and is therefore O(surface).
+
+Provider usage is reused only when the measured canonical request envelope equals the latest successful-call anchor. Any provider, model, system, prefix, tool, or call-config change causes complete heuristic repricing. Surface changes remain a signed delta from a matching anchor, including negative values after a shrinking replacement. A later successful request replaces the earlier anchor, including across provider or model switches.
+
+Usage sums the disjoint input, cache-read, cache-write, and output buckets. Reasoning is not added a second time. Every successful model call records an `assistant/message`, including content-less and max-token calls, with its exact earlier chunk seqs. An explicit empty provenance list means a known empty provider stream; absent legacy provenance conservatively treats the durable assistant output as provider output.
+
+### Compact-basic consumes, but does not own, measurement
+
+`dsh-compact-basic` requires `ctx.tokenMeter`; `CompactService` gains no token methods or types. The backend is factored into configuration, automatic triggering, region transaction, and summarizer modules, while `summarize()` remains its sole subclass hook. The singleton service consistently prices pressure, retention, shadowed content, provenance, and non-shrinking-summary rejection.
+
+Automatic compaction uses one unified measurement for each threshold-and-retention decision. The region transaction measures after appending its durable `compact/start` lock and again after asynchronous summarization; any intervening durable append changes `logRevision` and prevents replacement.
+
+Compact policy has service-wide defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, empty summarization provider/model, maximum summary output `8192`, one extra compaction attempt, and automatic triggering enabled. Top-level `thresholdRatio` and `retainTokens` override the pressure policy; retention must remain below the resulting threshold. `summarizationProvider` and `summarizationModel` must both be set or both be empty; an empty pair resolves the latest logged request target, then the `AgentOptions` pair.
+
+The pre-step trigger measures a provisional envelope: the current prompt and prefix override logged values, while the latest logged header supplies provider, model, tools, and other call config. A router-only agent without a complete provider/model pair skips that provisional check because `agent/request` can route later; any routed target can use the singleton estimator.
+
+## Testing
+
+Unit coverage pins service configuration, fixed estimation, envelope invalidation, latest-anchor replacement across provider/model switches, usage and missing-usage paths, seeded append/replace replay, signed deltas, provenance modes, malformed boundaries, unified snapshot detachment and deep immutability, surface-total equality, listener ordering, reload, compact defaults, routing fallback, one-call automatic decisions, retention, convergence, and log-revision rollback. A real Loader/Include YAML fixture loads the exact zero-config token-meter and compact-basic package names in dependency order.
+
+## Alternatives considered
+
+- **Keep estimation inside `CompactService`** — rejected because measurement has consumers and replay semantics independent of compaction; it would also force every compactor to expose the same unrelated API.
+- **Split a token-meter interface from a heuristic backend immediately** — rejected because only one implementation exists. One concrete service preserves the future seam without speculative packages or configuration.
+- **Keep model-keyed windows and density profiles** — rejected because the deployment currently has one context policy and one estimator. Model registries, unknown-model failures, and configurable density add branches without a second behavior to select.
+- **Keep separate scalar and surface measurements** — rejected because callers would need two reads and revision matching for one decision. A scalar-only read could avoid cloning nodes below threshold, but the split API introduces a caller-side race window; the unified snapshot accepts O(surface) cloning in exchange for coherence.
+- **Treat provider usage as portable between envelopes** — rejected because model, tools, prefixes, and call config are request facts. Mismatch reprices the whole current request.
+
+## Consequences
+
+- Token pressure has one replay-aware owner that compaction and future plugins can share.
+- The default makes the bundled composition usable with two zero-config plugin entries; deployments override one context capacity when needed.
+- Fixed heuristic pricing remains an estimate of provider behavior and is not an exact tokenizer or request serializer.
+- Every measurement clones the current positional surface and therefore costs O(surface), including pressure checks that finish below threshold.
+- Measurements fail loudly on malformed durable boundaries. This turns corrupted replay into a named integration failure instead of silently drifting pressure.
+- The pre-step compact integration can skip a router-only first check and can miss tool or routing changes applied later in request middleware.

docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md

@@ -0,0 +1,60 @@
+# RFC: 回放式 token 计量服务
+
+Status: implemented
+
+[English](2026-07-15-replay-token-meter-service.md) | 中文
+
+## 问题
+
+上下文压力并不只对压缩有用。压缩后端、溢出保护或未来的请求策略插件都可能需要回答同一个问题：持久请求占用了已配置上下文窗口的多少容量？如果把该折叠逻辑留在 `dsh-compact-basic` 内部，就会重复实现回放逻辑，使未加载压缩的调用方无法使用计量，并诱使调用方复用陈旧的核算结果。
+
+提供方 usage 也不是完整答案。它只描述某个精确请求信封下的一次成功调用，而当前表层之后还可能增长、缩小或被替换。会话也可能切换提供方与模型，旧日志可能缺少分片来源，usage 字段还会分别报告输入、缓存读取、缓存写入、输出与推理计数。因此，可用的服务必须把最新精确锚点与保守的启发式重新定价结合起来，并公开每个结果已经消费的日志修订号。
+
+## 决策
+
+### 一个具体的 LLM 家族服务
+
+`@deepseek-ai/dsh-token-meter` 是 `packages/llm/` 下的单个具体包，并注册 `ctx.tokenMeter`。在第二种实现出现之前，它不会被拆成接口与后端。`TokenMeterService` 本身公开 `contextWindow`、`measure(session, requestHeader?)` 与 `estimateMessage(message)`；消费方直接调用这个单例服务。
+
+服务只有一个 `contextWindow`，默认值为 128,000 token，并允许配置为正整数。估算采用固定的每 token 四个字符启发式规则，并加上结构开销。服务不提供模型 profile、密度设置、分词器后端或语言专用策略。
+
+### 逐会话回放折叠
+
+每个会话都有一个隔离的增量折叠。活跃折叠通过 `session/event` 前进；每次读取都会追到持久日志尾部，因此监听器顺序、种子会话与服务重载不会改变答案。折叠跟踪规范的完整请求头快照、步骤边界、表层追加与替换、assistant usage，以及 assistant 分片来源。下一个畸形事件会以事务方式失败并保持未读，不会让状态只修改一半。
+
+`measure(session, requestHeader?)` 只同步一次折叠，并在返回标量压力的同时给出逐位置节点价格。`totalTokens` 仍表示请求与响应压力；`surfaceTokens` 是仅针对表层的启发式总量，并等于 `nodes[].tokens` 之和。`requestHeader` 覆盖只改变压力定价，表层字段始终描述当前会话。`estimateMessage(message)` 不依赖会话状态，直接应用固定启发式规则。每个结果都是一个分离且深度不可变的快照，只携带一个 `logRevision`。每次计量都会复制当前节点，因此成本为 O(surface)。
+
+只有当待计量的规范请求信封等于最近一次成功调用的锚点时，服务才复用提供方 usage。提供方、模型、系统提示词、前缀、工具或调用配置任一变化都会触发完整的启发式重新定价。表层变化相对匹配锚点保留有符号增量，包括缩小替换后的负值。后续成功请求会替换先前锚点，提供方或模型切换时也一样。
+
+Usage 会对互不重叠的输入、缓存读取、缓存写入与输出 bucket 求和，不会再次加入推理计数。每次成功模型调用都会记录 `assistant/message`，包括无内容调用与达到 token 上限的调用，并带上精确的更早分片 seq。显式空来源列表表示已知为空的提供方流；旧日志中缺失的来源则保守地把持久 assistant 输出视为提供方输出。
+
+### compact-basic 消费计量，但不拥有计量
+
+`dsh-compact-basic` 要求 `ctx.tokenMeter`；`CompactService` 不增加 token 方法或类型。后端拆分为配置、自动触发、区域事务与摘要器模块，而 `summarize()` 仍是唯一的子类 hook。单例服务一致用于压力、保留、被遮蔽内容、来源以及非缩小摘要拒绝的定价。
+
+自动压缩的每次阈值与保留联合决策只使用一次统一计量。区域事务先追加持久 `compact/start` 锁，再执行一次计量，并在异步摘要完成后再次计量；期间任何持久追加都会改变 `logRevision`，从而阻止替换。
+
+压缩策略采用服务级默认值：阈值比例 `0.8`、保留尾部 `floor(contextWindow × 0.16)`、空的摘要提供方/模型、摘要最大输出 `8192`、一次额外压缩尝试，以及启用自动触发。顶层 `thresholdRatio` 与 `retainTokens` 覆盖压力策略；保留值必须小于最终阈值。`summarizationProvider` 与 `summarizationModel` 必须同时设置或同时为空；空组合先解析最近记录的请求目标，再使用 `AgentOptions` 中的组合。
+
+pre-step 触发器计量临时请求信封：当前提示词与前缀覆盖日志值，最近记录的请求头给出提供方、模型、工具及其他调用配置。没有完整提供方/模型组合的纯路由 agent（智能体）会跳过该临时检查，因为 `agent/request` 仍可稍后路由；任意已路由目标都可使用这个单例估算器。
+
+## 测试
+
+单元覆盖固定服务配置、固定估算、信封失效、提供方/模型切换时替换最新锚点、有无 usage 的路径、种子追加/替换回放、有符号增量、来源模式、畸形边界、统一快照的分离性与深度不可变性、表层总量相等性、监听器顺序、重载、压缩默认值、路由回退、自动决策单次调用、保留、收敛与日志修订回滚。真实 Loader/Include YAML fixture 按依赖顺序加载精确的零配置 token-meter 与 compact-basic 包名称。
+
+## 考虑过的替代方案
+
+- **把估算保留在 `CompactService` 内**——不予采纳，因为计量拥有独立于压缩的消费方与回放语义；它还会强迫每个压缩器暴露同一套无关 API。
+- **立即把 token meter 拆成接口与启发式后端**——不予采纳，因为目前只有一种实现。单个具体服务保留未来接缝，同时避免推测性的包与配置。
+- **保留模型键控的窗口与密度 profile**——不予采纳，因为当前部署只有一种上下文策略与一个估算器。模型注册表、未知模型错误和可配置密度只增加分支，却没有第二种行为可供选择。
+- **保留独立的标量与表层计量**——不予采纳，因为消费方必须为一次决策执行两次读取并匹配修订号。仅读取标量可以避免在低于阈值时复制节点，但拆分 API 会在消费方引入竞态窗口；统一快照接受 O(surface) 复制成本，以换取结果一致性。
+- **在不同信封之间移用提供方 usage**——不予采纳，因为模型、工具、前缀与调用配置都是请求事实。不匹配时会重新定价完整当前请求。
+
+## 后果
+
+- Token 压力拥有一个可供压缩与未来插件共享的回放感知所有者。
+- 默认值让内置组合只需两个零配置插件条目即可使用；部署需要时只覆盖一个上下文容量。
+- 固定启发式定价仍然只是提供方行为的估计，并不是精确分词器或请求序列化器。
+- 每次计量都会复制当前的位置表层，因此成本为 O(surface)，低于阈值即可结束的压力检查也不例外。
+- 遇到畸形持久边界时，计量会明确失败。这会把损坏的回放转化为具名集成错误，而不是让压力静默漂移。
+- pre-step 压缩集成可能跳过纯路由的首次检查，也可能错过请求中间件稍后应用的工具或路由变化。

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

@@ -48,7 +48,7 @@ The precise supported and deferred protocol rows live in [`packages/ui/acp/acp-f
 
 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.
+The bridge deliberately does not implement session list/delete/resume/close capabilities, MCP passthrough, additional directories, image/audio/embedded-resource prompts, plans, slash commands, usage updates, editor filesystem delegation, or the ACP terminal execution sub-protocol. Runtime model selection was added later through standard session config options by the [LLM catalog and ACP selection RFC](../architecture/2026-07-15-llm-model-catalog-and-acp-selection.md).
 
 An idle config selection is truthful in the live response but not durable until the next `agent/prompt-submit` anchors it inside the open turn. Crashing before that boundary loses the pending selection; this is the cost of keeping session events turn-enclosed and replay-safe.
 

docs/rfc/implemented/feature/2026-06-15-code-mode.md

@@ -38,11 +38,11 @@ Three decisions, each elaborated in its own section below:
 
 Under `'code'` and `'both'` the registry owns `run_code` as a reserved presentation transport with one required parameter, `{ code: string }`. It is represented by a normal `ToolDefinition` for dispatch but stays outside the filterable capability layers, so restrictions cannot accidentally remove Code Mode's only entry point. Calls traverse the complete tool pipeline — `tools/pre-execute` → monotonic guards → `tools/execute` around dispatch → `tools/post-execute` → immutable `tools/result` notification — exactly like native calls; a permission plugin can inspect the program text before it runs, and final-result observers see the normalized outer outcome. Its `execute(args, exec)`:
 
-1. **Build bindings.** One run-scoped signal follows outer cancellation and is aborted whenever the run settles. Each visible tool binding JSON-normalizes its arguments—rejecting lossy values before dispatch—waits on the serialization queue, executes with a deterministic call id and the outer token as `parent`, and logs `tool/code-dispatch`. Successful text becomes a string and non-text blocks become placeholders; tool errors reject the binding promise. Every sub-call retains its own immutable execution identity and traverses the full tool pipeline.
+1. **Build bindings.** One run-scoped signal follows outer cancellation and is aborted whenever the run settles. Each visible tool binding JSON-normalizes its arguments—rejecting lossy values before dispatch—waits on the serialization queue, executes with a deterministic call id and the outer token as `parent`, defers returned contexts through the outer execution, and logs `tool/code-dispatch`. Successful text becomes a string and non-text blocks become placeholders; tool errors reject the binding promise. Every sub-call retains its own immutable execution identity and traverses the full tool pipeline.
 2. **Runs the program**: `ctx.codeRuntime.run({ program: args.code, bindings: [{ global: 'tools', functions }], signal: runController.signal })`. The runtime receives the run-scoped signal, not only the caller's outer signal, so any way the outer run settles also aborts work inside the runtime.
 3. **Settle after quiescence.** When the runtime settles, the bridge aborts outstanding work and drains the dispatch queue before returning. Success returns captured output and presentation metadata. A runtime failure becomes `CodeRunFailedError`; backend rejection uses the registry's normal error boundary. Both produce structured error results, and no sub-call can append after `run_code` settles.
 
-**Sub-call `additionalContext` is omitted.** Injecting it during `run_code` would break parent call/result adjacency, while one program can produce many contexts. Supporting it requires a plural channel or loop-level sub-dispatch buffer.
+**Sub-call contexts are deferred through the parent.** Injecting inside `run_code` would break parent call/result adjacency, so `ToolRunContext.deferContext()` collects every sub-result `additionalContexts` entry in dispatch order. The registry carries that array even when the program later throws, and the loop appends each entry only after the outer result and every sibling result in the step. An outer post-execute block discards tool-deferred entries and exposes only contexts explicitly attached by the blocking decision.
 
 **Concurrency is serialized.** Each run owns a dispatch queue, so even `Promise.all` executes tool calls in submission order. Settlement abandons queued calls that have not started. Parallelism requires per-tool concurrency-safety metadata.
 
@@ -86,14 +86,14 @@ The SDK instructs the model to write an async erasable-TypeScript body, call too
 
 ## Consequences
 
-Deployments switching to `'code'` must update any native-only `toolOrder`. Assembly listeners own the integrity of any rewritten protocol surface. Sub-dispatch remains serialized, and the bridge does not propagate per-call `additionalContext` until those contracts are designed for Code Mode.
+Deployments switching to `'code'` must update any native-only `toolOrder`. Assembly listeners own the integrity of any rewritten protocol surface. Sub-dispatch remains serialized, while per-call contexts retain their source, envelope, and metadata through the outer result.
 
 ## Testing
 
 - **Worker runtime:** Real-worker tests cover output and value capture, failure kinds, compute and wall budgets, hostile binding traffic, empty environment, structured-clone fallback, output caps, and disposal to quiescence. A built-package test runs the worker entry under plain Node.
-- **Registry integration:** Tests cover code generation, all presentation modes, reserved-name and restriction rules, scoped visibility, authoritative assembly rewrites, `toolOrder`, runtime compatibility failures, full-pipeline sub-dispatch, parent-token correlation, serialization, cancellation and queue drain, JSON normalization, error propagation, log events, omitted `additionalContext`, and HMR cleanup.
-- **With-key e2e:** A real model composes two bash calls in one program; the test verifies the collapsed request header, correlated dispatch events, resulting file, and curated answer.
-- **Snapshot:** The `code-mode-turn` and `both-mode-turn` fixtures pin the SDK section, header tool list, dispatch events, and result card.
+- **Registry integration:** Tests cover code generation, all presentation modes, reserved-name and restriction rules, scoped visibility, authoritative assembly rewrites, `toolOrder`, runtime compatibility failures, full-pipeline sub-dispatch, parent-token correlation, serialization, cancellation and queue drain, JSON normalization, error propagation, log events, ordered context deferral across successful and failed programs, outer-block suppression, and HMR cleanup.
+- **With-key e2e:** A real model composes two bash calls in one program; another discovers nested workspace instructions through a Code Mode fs dispatch. The tests verify collapsed request headers, correlated dispatch events, resulting files, deferred context, and model behavior.
+- **Snapshot:** The `code-mode-turn`, `both-mode-turn`, and `code-mode-workspace-context` fixtures pin SDK text, header tool lists, dispatch events, deferred context, and result cards.
 
 ## Alternatives considered
 

docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md

@@ -6,9 +6,9 @@ Status: implemented
 
 A long-running agent conversation grows without bound. As the event log accumulates turns, the derived message history eventually approaches the model's context window — the model then truncates mid-response (`max-tokens`) or degrades. **Compaction** is the mitigation: replace a run of older history with a concise summary, keeping recent context intact.
 
-The [session surface](../../implemented/architecture/2026-06-18-session-surface.md) was built as the foundation for exactly this — a linked list over the event log with a `surfaceOp: { op: 'replace', start, end }` operation purpose-built to shadow a range of nodes and insert a replacement, with `sourceEventSeqs` recording provenance so the decision replays deterministically. What remained was the plugin that *decides what to compact and produces the summary*.
+The [session surface](../../implemented/architecture/2026-06-18-session-surface.md) was built as the foundation for exactly this — an ordered projection over the event log with a `surfaceOp: { op: 'replace', start, end }` operation purpose-built to shadow a range of entries and insert a replacement, with `sourceEventSeqs` recording provenance so the decision replays deterministically. What remained was the plugin that *decides what to compact and produces the summary*.
 
-Two forces shape the design. First, compaction is **swappable**: token counting can be a char/4 heuristic or a real tokenizer, and summarization can be a model call, a template, or a remote service — these vary independently of *when* and *which range* to compact. Second, `SurfaceEventType` is closed to five event types (`user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`); only those may carry `surfaceOp`. A bespoke `compaction/*` event therefore **cannot** itself appear on the surface — the compiler rejects `surfaceOp` on it and the invariants plugin rejects it at runtime.
+Two forces shape the design. First, compaction policy and reusable token measurement vary independently: measurement belongs to the LLM-family [`ctx.tokenMeter` service](../../implemented/architecture/2026-07-15-replay-token-meter-service.md), while summarization can be a model call, a template, or a remote service. Second, `SurfaceEventType` is closed to five event types (`user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`); only those may carry `surfaceOp`. A bespoke `compaction/*` event therefore **cannot** itself appear on the surface — the compiler rejects `surfaceOp` on it and the invariants plugin rejects it at runtime.
 
 ## Decision
 
@@ -17,7 +17,7 @@ Two forces shape the design. First, compaction is **swappable**: token counting
 Per the [capability-seams RFC](../../implemented/architecture/2026-06-13-capability-seams.md), compaction ships as separate packages so the contract, the algorithm, and (later) the consumer surface evolve independently:
 
 1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, and the `compact/*` session events. It declares `compactIfNeeded()` and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*.
-2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that owns the entire algorithm — token estimation (chars per token — the `charsPerToken` config, default 4 — + per-block overhead), the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, and the `agent/pre-step` auto-compaction listener. A tokenizer-based or template-based backend is a sibling package (or a subclass overriding the two protected estimation/summarization hooks).
+2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that consumes `ctx.tokenMeter` and owns the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, and the `agent/pre-step` auto-compaction listener. `summarize()` is its sole subclass hook; pricing and replay stay with the meter.
 3. **Consumer** — deferred. A `/compact` tool and slash command will `inject: ['compact']` and call the contract; they are intentionally out of scope here so the seam settles first.
 
 ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation
@@ -28,9 +28,9 @@ This is not a coupling smell — it is the contract's domain. The "only cordis"
 
 ### Abstract `compactIfNeeded` / `compactRegion`, algorithm in the backend
 
-An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface, with only `estimateContentTokens()` and `summarize()` abstract. That recouples the contract to one strategy: a backend that wants a different retention policy or a different event-sequencing would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend, where it belongs, and keeps the interface a pure statement of *what*. The backend remains internally factored — `estimateContentTokens()` and `summarize()` are `protected` hooks a sub-backend can override without reimplementing the walk — but that factoring is the backend's private concern, not the contract's.
+An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold.
 
-`compactIfNeeded(agent, turn, step, fullSystemPrompt, signal)` takes **required** parameters (not the original all-optional shape). The auto-compaction seam (below) always supplies the agent, lifecycle context, assembled system prompt (counted toward the estimate), and the turn's abort signal, so optionality would only invite a hidden default at the seam. The session being compacted comes from the agent context. `compactRegion(session, start, end, agent, turn, step, signal?)` keeps an optional signal (a manual caller may omit it). Passing lifecycle context rather than a concrete model keeps router agents honest: the backend's summarization request can run through `agent/request`, where model-routing plugins already choose the actual model.
+`compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` takes required pressure inputs and cancellation. The session comes from the agent. `compactRegion(session, start, end, agent, signal?)` keeps an optional signal for manual callers and requires `session === agent.session`; implementations reject mismatch before model resolution, lock acquisition, summarization, or log mutation. The pre-step integration resolves a provisional model from the latest logged request header, then `AgentOptions.model`; a model-less router-only first step skips pressure because `agent/request` can route later. The default summarizer resolves its model from explicit config, the latest logged routed model, then agent options.
 
 ### Auto-compaction runs on `agent/pre-step`, a dedicated surface-mutation seam
 
@@ -40,7 +40,7 @@ The fix is a dedicated loop seam, **`agent/pre-step`** (`@mode serial`), fired b
 
 ```
 assembly = ctx.systemPrompt.assemble()
-await ctx.serial('agent/pre-step', agent, turn, step, system, signal)  ⟵ compaction mutates the surface here
+await ctx.serial('agent/pre-step', agent, turn, step, system, prefix, signal)  ⟵ compaction mutates the surface here
 session('step/start')                 ⟵ the step opens AFTER the seam
 messages = session.deriveMessages()   ⟵ single derive, reflects the compaction
 request  = waterfall agent/request    ⟵ pure request transform (hooks, model switch)
@@ -52,11 +52,11 @@ The loop derives messages once after `agent/pre-step`. Running before `step/star
 
 Auto-compaction fires before **every** step, not once per turn. This is **load-bearing for runaway-turn survival**: a tool-heavy ReAct turn appends an `assistant/message` + a `tool/result` per step, so the surface grows *within* a turn. A single turn can grow past the window on its own (a "runaway turn") — and the only moment to rescue it before the next model call overflows is the next step's `pre-step` checkpoint. Gating compaction to a turn's first step (or, worse, retaining the whole in-flight turn verbatim) re-opens exactly the hole compaction exists to close: the harness would die when compaction is most needed.
 
-`compactIfNeeded` retains the smallest tail of whole surface units whose estimated size reaches `retainTokens` and compacts older nodes. A unit is a complete closed step or one no-step message. If the token cutoff lands inside a step, retention expands until the cut is tool-pairing balanced. Balance is checked on surface order, not log sequence, because replacement summaries have new sequence numbers at old surface positions. `compactRegion` rejects boundaries that split a tool call from its result. The in-flight turn receives no special retention.
+`compactIfNeeded` retains the smallest tail of whole surface units whose estimated size reaches `retainTokens` and compacts older nodes. A unit is a complete closed step or one no-step message. If the token cutoff lands inside a step, retention expands until the cut is tool-pairing balanced. Balance is checked on surface order, not log sequence, because replacement summaries have new sequence numbers at old surface positions. `dsh-compact` exports the before/after edge helpers; their per-session cache folds only appended surface-tail nodes while `replaceGeneration` is unchanged, does no event reads for log-only growth, and rebuilds current membership and balances after replacement. `compactRegion` rejects boundaries that split a tool call from its result. The in-flight turn receives no special retention.
 
 A runaway turn thus compacts exactly like any other history: its early *closed* steps get summarized while its recent steps stay verbatim. When the only compactable content left is an un-splittable open tail step (its tool-calls have no results yet), compaction declines (`null`) and retries once that step closes.
 
-**Single-unit overflow is out of scope, by design.** If a single retained unit — one closed step, or a large free node such as a pasted `user/message` — *alone* exceeds the budget, compaction cannot help and the next model call may go out over-budget. Bounding an individual unit's size is a separate concern (output truncation), handled elsewhere; compaction makes no promise about it, and the harness without such a mechanism can still break on a single oversized unit. This is named honestly rather than papered over.
+**Single-unit overflow is out of scope, by design.** If a single retained unit — one closed step, or a large free entry such as a pasted `user/message` — *alone* exceeds the budget, compaction cannot help and the next model call may go out over-budget. Bounding an individual unit's size is a separate concern (output truncation), handled elsewhere; compaction makes no promise about it, and the harness without such a mechanism can still break on a single oversized unit. This is named honestly rather than papered over.
 
 ### Head-anchoring: one auto checkpoint, always at the head
 
@@ -64,11 +64,11 @@ Auto-compaction always starts at the surface head, merging the prior checkpoint
 
 ### Approximate convergence invariant
 
-`resolveConfig` validates numeric knobs but does NOT reject based on a pretend summary-length invariant. Convergence is dynamic: provider output caps can be spent on hidden or surfaced reasoning tokens, and the model may emit a summary of unpredictable size. `maxTokens` is only the provider-side generation cap for the summarization call; reasoning blocks are stripped before the checkpoint is stored. If a compacted surface is still over threshold, `compactIfNeeded()` re-compacts the head checkpoint up to `compactionRetries` extra times, but each committed summary must be smaller than the content it shadows. The sole residual is the single-unit-overflow case above (a backward-rounded oversized step can push the retained tail over budget) — which is exactly the out-of-scope concern, not a thrash bug.
+`resolveConfig` supplies usable defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, empty summarization-model override, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. Optional top-level `thresholdRatio` and `retainTokens` override the policy for the token meter's single context window; retention must remain below the resulting threshold. Convergence remains dynamic because provider output caps can be spent on hidden or surfaced reasoning tokens and summary size is unpredictable. If the compacted surface remains over threshold, `compactIfNeeded()` re-compacts the head checkpoint up to the configured retry count, but each committed summary must be smaller than what it shadows.
 
 ### Surface replacement: `compact/*` events are log-only; one `user/message` carries the summary
 
-Because `SurfaceEventType` is closed, the summary cannot ride on a `compact/*` event. The backend instead appends a **single `user/message`** with `surfaceOp: { op: 'replace', start, end }` whose `content` is the (framed) summary and whose `sourceEventSeqs` covers the shadowed nodes *and* the bookkeeping events. The `compact/*` events are pure log records (lock + provenance). The surface mutation sits **inside** the lock — `compact/end` is the last event appended:
+Because `SurfaceEventType` is closed, the summary cannot ride on a `compact/*` event. The backend instead appends a **single `user/message`** with `surfaceOp: { op: 'replace', start, end }` whose `content` is the (framed) summary and whose `sourceEventSeqs` covers the shadowed entries *and* the bookkeeping events. The `compact/*` events are pure log records (lock + provenance). The surface mutation sits **inside** the lock — `compact/end` is the last event appended:
 
 ```
 compact/start    → log-only. Acquires the lock.
@@ -79,7 +79,7 @@ user/message     → surfaceOp { op:'replace', start, end }. THE surface mutatio
 compact/end      → log-only. Releases the lock (carries `error` on a recoverable failure).
 ```
 
-`deriveMessages()` then yields `[summary_as_user_message, ...retained_nodes]`. Reusing `user/message` is honest rather than a workaround: a summary genuinely *is* user-role context.
+`deriveMessages()` then yields `[summary_as_user_message, ...retained_entries]`. Reusing `user/message` is honest rather than a workaround: a summary genuinely *is* user-role context.
 
 ### Checkpoint framing + incremental merge (backend-private)
 
@@ -103,19 +103,19 @@ Two failure paths, both documented:
 
 ## Alternatives considered
 
-- **The full algorithm as concrete interface methods** (only estimation/summarization abstract) — the earlier draft; rejected because it recouples the contract to one retention strategy. Both core methods are abstract; the `protected` estimation/summarization hooks are the backend's private factoring, not the contract's.
+- **The full algorithm as concrete interface methods** — rejected because it recouples the contract to one retention strategy. Both core methods are abstract; reusable measurement is a separate LLM-family service and `summarize()` is basic's sole hook.
 - **Compaction on the `agent/request` waterfall** — the earlier cut; rejected for the double-derive it forced and for handing the listener context it structurally cannot compact. The dedicated `agent/pre-step` seam makes the layering correct by construction.
 - **A separate `compact/error` event** — rejected: `compact/end` keeps an `error?` field, mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling.
 - **Teaching core turn-repair about `compact/*`** — rejected: the log-only orphan is inert, and a core module patched for every future `xxx/start … xxx/end` plugin pair is exactly the coupling the capability-seam architecture exists to avoid.
 
 ## Consequences
 
-- **New packages**: `packages/compact/compact` (interface) and a sibling `compact-basic` (backend) under `packages/compact/`, wired into the root tsconfigs. The consumer tier is deferred.
+- **Packages**: `packages/compact/compact` supplies the interface and `compact-basic` supplies the backend. `packages/llm/token-meter` owns replay-aware measurement independently. The consumer tier is deferred.
 - **New loop seam**: `agent/pre-step` (`@mode serial`) declared in `dsh-agent` and emitted by `dsh-agent-loop` after system assembly and before `step/start`. This is a documented change to the loop — `docs/architecture.md` records it and the generated cordis catalog carries its signature.
 - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry.
-- **`dsh-session`** gains the tool-pairing balance predicate (`isToolPairingBalanced`, in `tool-pairing.ts`, exported from the package index) that `compactRegion`/`compactIfNeeded` use to keep a collapsed region from splitting a step's tool-call/result pair. The surface `replace` op and the surface-metadata runtime guard already existed and are reused.
-- **`dsh-invariants`** drops its `surface replace: start must be <= end` assertion: a head-anchored compaction lands a high-seq replacement node at an older range's *position*, so `start > end` numerically is normal and valid (the range is positional, validated by the surface's `indexOf` checks that remain). The turn-enclosure invariant is reused unchanged.
-- **Wiring**: `dsh-compact-basic` is loaded in `examples/coding-agent`'s `cordis.yml`, so the seam ships in the real demo (it was previously loaded nowhere).
+- **`dsh-compact`** owns `toolPairingBalancedBefore(session, seq)` and `toolPairingBalancedAfter(session, seq)`, the cached surface-edge checks that `compactRegion` and `compactIfNeeded` use to avoid splitting a tool-call/result pair. The cache validates current membership by seq and answers both edges from one per-cut balance sequence; stale or missing seqs and orphan results reject. `dsh-session` continues to own the surface `replace` operation, ordered event sequences, and rewrite generation.
+- **`dsh-invariants`** drops its `surface replace: start must be <= end` assertion: a head-anchored compaction lands a high-seq replacement entry at an older range's *position*, so `start > end` numerically is normal and valid (the range is positional, validated by the surface's `indexOf` checks that remain). The turn-enclosure invariant is reused unchanged.
+- **Wiring**: `examples/coding-agent/cordis.yml` loads zero-config `dsh-token-meter` before `dsh-compact-basic`; the service-wide window and compact defaults make the pair usable without repeated numeric policy.
 
 ## Testing
 

docs/rfc/implemented/feature/2026-06-24-workspace-context.md

@@ -0,0 +1,87 @@
+# RFC: Workspace context instruction files
+
+Status: implemented
+
+## Problem
+
+Repository guidance such as `AGENTS.md` belongs in a coding session's effective context so project conventions, build commands, and review rules arrive without repeated user pasting. The stdio and ACP products need the same behavior, isolated by session cwd: a global system-prompt section leaks one workspace's files into another live ACP session.
+
+Neighboring products establish useful conventions but differ in details. Codex treats `AGENTS.md` as native, Claude Code uses `CLAUDE.md` and familiar system-reminder-style user context, and opencode supports both names with one winner per directory plus lazy nested discovery. The harness needs cross-tool compatibility without loading duplicate or contradictory files from the same scope.
+
+The lifecycle has two distinct classes of content. The initial applicable chain is stable enough to live in the request prefix and benefit from provider prefix caching. Nested files, edits, candidate switches, and removals happen after the session starts and belong in durable append-only history rather than the frozen prefix.
+
+## Decision
+
+The implementation lives in `packages/context/workspace-context` as `@deepseek-ai/dsh-workspace-context`. It is a request-context extension, not a core service or a filesystem backend. `@deepseek-ai/dsh-agent-core` mounts it for both product front doors and forwards its config. The plugin consumes `agent/session-prefix`, `tools/post-execute`, and the optional `ctx.fs` capability.
+
+The plugin does not statically inject `fs`. Providerless product trees therefore boot normally and the plugin no-ops until a filesystem provider exists. All production reads go through that provider. Candidate probes call `lstat` before `resolve`, so a repository-owned final-component symlink is rejected rather than followed outside the workspace. The session-prefix signal and dynamic tool execution signal propagate through resolution, metadata probes, and streaming reads, so cancellation does not wait for an unrelated filesystem scan. Once `lstat` identifies a regular-file winner, a provider exception or disagreement during resolve/stat is classified as unavailable: it is neither interpreted as a deletion nor allowed to fall through to a lower-priority candidate.
+
+### File Names And Precedence
+
+The default per-directory candidate list is `['AGENTS.md', 'CLAUDE.md']`. The list is configurable as `instructionFileCandidates`, and `AGENTS.md` is an ordinary first candidate rather than a hidden priority. In one directory, only the first existing regular-file candidate loads. With defaults, `AGENTS.md` is native and `CLAUDE.md` is a compatibility fallback.
+
+Candidate entries are same-directory file names. Empty entries, `.`/`..`, and entries containing `/` or `\` are ignored. Lowercase names, local variants, and other same-directory names can be opted into explicitly; rule directories and import semantics are outside this contract.
+
+The user-global file is fixed at `$DSH_HOME/AGENTS.md` and is not affected by `instructionFileCandidates`. `$DSH_HOME` defaults to `~/.dsh`, matching the harness-level home role of `~/.codex` or `~/.claude` rather than introducing a plugin-specific home. Tilde expansion and the default live in `dsh-paths` so future harness features share the same convention.
+
+### Baseline Prefix
+
+On the first request of an agent-loop instance, the plugin contributes one user-role message through `agent/session-prefix`. It loads the user-global file first, then finds the project root by walking upward from `agent.session.header.cwd` to a configured root marker (default `.git`), then loads one candidate from each directory from the root to the cwd. A `.git` file and a `.git` directory are both valid markers, covering linked worktrees and submodules. Without a marker, the cwd itself is the root.
+
+The plugin prepends its contribution before `await next()` returns, so session-prefix contributions appear in plugin registration order. In the product spine workspace instructions are registered before a skills catalog and therefore appear first. The loop deep-freezes the composed prefix, logs it in `EpochHeader.messagePrefix`, and reuses it verbatim for that instance. It is request state, not `Session.deriveMessages()` history.
+
+A resumed agent creates a new loop instance and recomposes the baseline from current files, with the new prefix anchored by the resume request header. This permits current baseline content on resume without mutating a prefix already used by an earlier instance.
+
+The baseline is a user-role `<system-reminder>` with `Instructions from: <path>` sections and explicit authority and precedence language. This familiar model-facing frame avoids a harness-specific XML vocabulary. Project paths are root-relative and the user-global path is `~/.dsh/AGENTS.md` for the default home or `$DSH_HOME/AGENTS.md` for a configured home. A literal `</system-reminder>` inside file content is escaped. The package README owns the exact current [prompt shape](../../../../packages/context/workspace-context/README.md#prompt-shape).
+
+### Dynamic Discovery And Refresh
+
+After a successful first-party `read`, `write`, or `edit` call, the `tools/post-execute` listener reconciles the touched descendant chain and every scope already known to the session. A newly reached scope is returned through `additionalContexts` for the next request using an `Additional instructions from: <path>` system-reminder. Under Code Mode, `run_code` defers sub-dispatch contexts onto its outer result, so the same update is appended only after the parent result rather than being injected mid-call.
+
+A content edit appends `Updated instructions from: <path>`, states that the new content replaces the previous content, and includes the complete current file. If precedence changes from one candidate to another, the message also names the previous path and says it no longer applies. If no candidate remains, the plugin appends `Instructions removed: <path>` and states that the previously loaded instructions no longer apply.
+
+Dynamic messages use a raw `context/message` envelope because the plugin owns the complete system-reminder framing. Core context injection therefore supports `envelope: 'raw'`; callers that omit it retain the canonical `<context source="...">` wrapper. `context/message.meta` carries opaque JSON state that is persisted but never rendered to the model.
+
+Shell commands are not discovery triggers. Local bash calls start fresh shells, and inferring reached paths from arbitrary command strings would require shell semantics the prompt plugin does not own.
+
+### Duplicate Suppression And Change Detection
+
+Every dynamic workspace context event stores versioned metadata with `{ action, scope, path, previousPath?, digest? }`, where `digest` is SHA-1 over the loaded content. The model-facing prompt has no HTML comments, hidden markers, or headings that are parsed back into state.
+
+At reconciliation time the plugin scans plugin-owned `context/message` events and derives the latest state for each visible scope. A short per-session pending map begins only after the immutable top-level `tools/result` proves an `additionalContexts` entry survived every post-execute listener, then covers the interval before the loop appends that context to the log. Each entry records the open `{ turn, step }`: an equal durable `context/message` at or after its sequence boundary confirms and removes it, while a matching `step/end` arriving first means the loop discarded its context buffer, so the plugin removes both the pending entry and its version-cache fast path. A nested Code Mode result stages its changes under the parent's opaque execution token so repeated sub-dispatches in one run do not duplicate them; the parent result rolls that provisional state back and commits only contexts retained by outer policy.
+
+An unchanged path and digest is suppressed. A logged removal is a tombstone, so a reappearing candidate becomes a new `set`. Resume works from persisted metadata. If compaction removes an instruction event from the visible surface, that state no longer suppresses a later load, matching the fact that the model can no longer see it. Only changes actually included under the byte budget enter metadata or pending state, so an omitted file remains eligible on a later touch.
+
+The frozen baseline keeps an in-memory path/digest map for comparison. A later successful filesystem touch appends baseline edits or removals as dynamic messages; it never rewrites the prefix. During resumed prefix composition the plugin also reconciles visible dynamic scopes, so nested changes made while the agent was offline can append an update before the first resumed request.
+
+There is intentionally no watcher. Detection occurs at the next successful structured filesystem touch or resumed prefix composition. A provider failure produces no removal; absence is only accepted when all configured candidates in that scope were probed successfully.
+
+### Byte Budget And Bounded Reads
+
+`maxBytes` is required and applies separately to a rendered baseline or one dynamic reconciliation batch; there is no implicit or unbounded render budget. Non-positive and non-finite values disable loading. When content exceeds the budget, broader files are omitted before the most-specific file is truncated. A visible `Workspace instruction budget ...` notice names omitted and truncated paths and byte counts, and output never exceeds the configured bytes.
+
+`maxSourceBytes` is a positive per-file cap with a 1 MiB default. The loader checks reported size before reading and still consumes content through `streamText()` with a running UTF-8 byte count, so missing/stale metadata cannot force an unbounded allocation. An oversized winning candidate is unavailable rather than a reason to fall through to another same-directory name. The plugin deliberately keeps no process-wide cache and never retains instruction prose. It keeps only `{ path, version, digest }` per effective scope in a `WeakMap<Session, Map<scope, state>>`: a matching provider `FsVersion` plus matching effective prompt state skips the read, while a changed version triggers a bounded read and SHA-1 confirmation. SHA-1 remains the cross-provider content identity persisted in visible structured metadata; provider versions are only an in-memory invalidation fast path. Cache transitions for model-visible changes commit only when the corresponding context survives the complete tool-result policy chain, and are invalidated if that accepted context is later dropped with its aborted step before reaching the log.
+
+## Alternatives considered
+
+**Use a global `ctx.systemPrompt.section()`.** Rejected because one Cordis context can host sessions with different cwd values, while repository-owned text is lower-authority context rather than top-authority provider system content.
+
+**Inject the baseline on every `agent/pre-step`.** Rejected because repeated history injection wastes tokens, complicates duplicate state, and prevents a structurally stable provider prefix. Prefix composition gives a frozen, logged, per-instance baseline while dynamic append-only messages handle changes.
+
+**Load both `AGENTS.md` and `CLAUDE.md` in one directory.** Rejected because repositories in transition commonly duplicate guidance across both files. Ordered candidates make precedence explicit and configurable.
+
+**Parse rendered headings or hidden comments to recover loaded state.** Rejected because instruction prose can contain the same text, causing silent false positives. Persisted JSON metadata provides an unambiguous state channel that is invisible to the model.
+
+**Summarize files with a model.** Rejected because instruction files are already curated summaries; another model call is nondeterministic and can erase edge-case requirements. Deterministic full text with byte budgeting is simpler.
+
+## Consequences
+
+Workspace guidance is isolated per session and shared by both product front doors and every tool presentation mode. Initial instructions benefit from stable prefix caching, while nested and changed content remains durable and replayable. The generic session/agent context contract includes optional raw framing and JSON metadata, both propagated through prompt-submit and post-tool `additionalContexts` arrays without flattening entries.
+
+Repository text remains untrusted input. Lower-authority user-role framing, explicit precedence language, delimiter escaping, and symlink rejection reduce risk but do not eliminate prompt injection. Permission and sandbox layers treat workspace files as data rather than authority.
+
+The system is event-driven rather than watch-driven. Edits are not visible at the exact filesystem mutation instant unless that mutation goes through a structured tool; externally changed files are noticed on the next successful structured touch or resume. This keeps the design deterministic and provider-neutral.
+
+## Deferred
+
+Bash-derived path reporting, recursive startup scans, file watchers, lowercase defaults, `.claude/CLAUDE.md`, `.claude/rules/*.md`, import directives, ACP `additionalDirectories`, trust acknowledgements, and model-generated summaries are deferred. Same-directory private variants can be configured today; directory rule systems and imports need their own precedence and trust designs.

docs/rfc/implemented/feature/2026-06-29-todo-write-tool.md

@@ -20,7 +20,7 @@ The list is appended as a `todo/write` event carrying the full `{ todos }` snaps
 
 ### NOT a surface event
 
-`todo/write` is deliberately excluded from `SurfaceEventType`. The surface is the projection that produces the LLM message history (`deriveMessages()`); a todo write produces no conversation message. So it carries no `surfaceOp`, never joins the surface linked list, and never reaches `deriveMessages()` — it is durable, replayable *UI* state that travels alongside the conversation without being part of it. (The dev-mode invariants still require it to sit inside an open turn, which it always does: it is appended mid-step during a tool call.)
+`todo/write` is deliberately excluded from `SurfaceEventType`. The surface is the projection that produces the LLM message history (`deriveMessages()`); a todo write produces no conversation message. So it carries no `surfaceOp`, never joins the ordered surface, and never reaches `deriveMessages()` — it is durable, replayable *UI* state that travels alongside the conversation without being part of it. (The dev-mode invariants still require it to sit inside an open turn, which it always does: it is appended mid-step during a tool call.)
 
 ### Priority synthesized only at the ACP boundary
 

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

@@ -12,8 +12,8 @@ The framing that shapes the whole design: **a bridge is a compatibility adapter,
 
 Two independent plugins in the `packages/hooks/` group, each a function/namespace plugin (`name`/`inject`/`Config`/`apply`, NO default export — see [postmortem 0001](../../../postmortem/0001-acp-default-export-drops-inject.md)) injecting only `bash`:
 
-- **`dsh-hooks-claude`** — the CC dialect. Seven of Claude Code's current hook points: `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `Stop`, `SubagentStart`, and `SubagentStop`. Owns CC-shaped per-event stdin payloads (a base of `session_id`/`cwd`/`hook_event_name` plus per-event fields), `CLAUDE_PROJECT_DIR` plus `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` substitution, and the literal-or-regex matcher mode. A CC hook's stdin carries a **trailing newline**.
-- **`dsh-hooks-codex`** — five of Codex's current hook points: `PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, and `Stop`. It uses an always-regex matcher, Codex-shaped snake_case payloads with `turn_id`/`model`/`permission_mode` extras written WITHOUT a trailing newline, no Codex plugin-env injection or config-time placeholder substitution, and no pre-tool approval or rewrite path. A tool call's payload carries the real `tool_name` in the bridge's reduced `tool_input: { command }` shape.
+- **`dsh-hooks-claude`** — the CC dialect. Seven of Claude Code's current hook points: `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `Stop`, `SubagentStart`, and `SubagentStop`. Owns CC-shaped per-event stdin payloads (a base of `session_id`/`transcript_path`/`cwd`/`hook_event_name` plus per-event fields), `CLAUDE_PROJECT_DIR` plus `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` substitution, and the literal-or-regex matcher mode. `transcript_path` is the persistence locator result or `''`; stdin carries a **trailing newline**.
+- **`dsh-hooks-codex`** — five of Codex's current hook points: `PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, and `Stop`. It uses an always-regex matcher, Codex-shaped snake_case payloads with `turn_id`/`model`/`permission_mode` extras written WITHOUT a trailing newline, no Codex plugin-env injection or config-time placeholder substitution, and no pre-tool approval or rewrite path. `transcript_path` is the same locator result or `null`; tool payloads carry the real `tool_name` in the reduced `tool_input: { command }` shape.
 
 ### Outcome → Decision mapping
 
@@ -35,9 +35,9 @@ The CC bridge's `ask` result is a real permission path, not a terminal bridge de
 
 `agent.inject()` defaults a missing `MessageSource` to `{ kind: 'user' }`, so every bridge `inject()` and `HookContext` passes `{ kind: 'plugin', plugin: 'hooks-claude' | 'hooks-codex' }`. Unit coverage pins the resulting `context/message.source` as the plugin rather than the user.
 
-### Adding context is not a veto — delegate, then fold
+### Adding context is not a veto — delegate, then prepend
 
-A context-only hook must call `next()` and then fold its `additionalContext` into the downstream decision; returning allow or accept directly would bypass later policy listeners. Post-tool block and accept decisions both preserve added context. Prompt allow preserves it, while prompt block drops it because the prompt never reaches the model. Only an explicit hook denial or block short-circuits the waterfall.
+A hook that only attaches `additionalContext` (no block/deny) is NOT a decision the bridge should return on its own: returning `allow`/`accept` from a waterfall listener WITHOUT calling `next()` short-circuits every later `agent/prompt-submit` / `tools/post-execute` listener, so a policy/sandbox plugin registered after the bridge would never see the prompt. Each bridge therefore delegates via `next()` before adding its context to the downstream decision. Both seams carry ordered `additionalContexts` arrays, so the bridge prepends its separately sourced entry while preserving every downstream source, envelope, and metadata field; a downstream prompt block still drops all context because the prompt never reaches the model, while post-tool block semantics may explicitly retain contexts. Code Mode ferries the same array through the outer `run_code` result. Only a real `deny`/`block` from the hook itself short-circuits. Tests assert a later listener can still block a prompt a context-only hook allowed and that retained prompt and post-tool contexts remain separate.
 
 ### CLAUDE_PROJECT_DIR defaults to the session workspace
 

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

@@ -14,9 +14,9 @@ The canonical surface separates transformable policy, around-dispatch control, a
 
 **Agent events** (`dsh-agent`):
 - `agent/session-start(agent, source)` — emit, once before turn 1, carrying a `SessionStartSource` (`startup` for a fresh/forked create, `resume` for a reloaded persisted session; `clear`/`compact` reserved). A pure notification — it CANNOT block startup (a deliberate gap: a bridge logs/injects, it does not gate startup). A listener seeds context via `agent.inject()`.
-- `agent/prompt-submit(agent, content, source, next) → PromptDecision` — waterfall, fired per drained queued message inside the open turn, before the `user/message` append. `allow` (optionally rewriting the prompt `content` or attaching `additionalContext`) or `block` (dropping the prompt; the loop appends a durable `prompt/blocked` in its place — see the dispatch note below).
+- `agent/prompt-submit(agent, content, source, next) → PromptDecision` — waterfall, fired per drained queued message inside the open turn, before the `user/message` append. `allow` (optionally rewriting the prompt `content` or attaching separately sourced `additionalContexts[]`) or `block` (dropping the prompt; the loop appends a durable `prompt/blocked` in its place — see the dispatch note below).
 
-**`agent/turn-continuation`** receives and returns a `ContinuationDecision`. A `{action:'continue', reason?}` may carry model-facing context recorded as next-step steering in the same turn — the typed twin of the `/goal` step-end-steer pattern.
+**`agent/turn-continuation`** receives and returns a `ContinuationDecision`. A `{action:'continue', reason?}` may carry model-facing content and source recorded as next-step steering in the same turn — the typed twin of the `/goal` step-end-steer pattern. It is not a `context/message`, so its type does not offer a context envelope or durable context metadata.
 
 ### The tool pipeline gives each phase one kind of authority
 
@@ -25,7 +25,7 @@ Every call follows `tools/pre-execute` → guards → `tools/execute` → dispat
 - **`tools/pre-execute`** is the extensible waterfall gate. Its `PreToolDecision` allows, denies, or asks. Deny skips `tools/execute` and core dispatch. Ask resolves through the optional approval seam: only `allowed-once` continues through guards and dispatch; rejection, cancellation, an unavailable channel, a missing approval service, or an agent-less call becomes a normalized denial. Every outcome still reaches post-policy and final observers.
 - **`ctx.tools.guard()`** installs synchronous scope-aware policy after the whole pre-execute waterfall. A guard may deny or abstain, never force-allow, so listener ordering cannot resurrect an operation that a final invariant forbids.
 - **`tools/execute`** is the around-dispatch waterfall for timeout, retry, and metrics plugins. A wrapper delegates to core dispatch with `next()`, may add, replace, or remove only `exec.signal` before doing so, and receives the already-normalized result of a thrown or unknown tool; returning its own valid result short-circuits dispatch.
-- **`tools/post-execute`** is the inspect/transform waterfall. Its `PostToolDecision` accepts, blocks with feedback, optionally replaces content, or attaches `additionalContext`; in-place mutation of the result is not a transform channel, because the registry rebuilds the outcome from a protected snapshot plus the returned decision.
+- **`tools/post-execute`** is the inspect/transform waterfall. Its `PostToolDecision` accepts, blocks with feedback, optionally replaces content, or attaches `additionalContexts`. The returned decision is the supported transform channel; after the waterfall, the registry materializes the complete outcome once before final observation.
 - **`tools/result`** is the synchronous contained notification after every transform, lossless-JSON materialization, and the outer error boundary. It receives the same frozen execution identity and an immutable snapshot of the authoritative result; observer failures are contained per listener and cannot change or reject `ToolRegistry.execute()`'s returned outcome.
 
 Core dispatch and the tool body sit inside normalization boundaries, so tool, listener, malformed-result, non-JSON result, and identity-shape failures resolve as JSON-safe `isError` results rather than escaping the turn. A post-execute listener can therefore inspect a thrown tool, and a final observer sees exactly what the caller receives and the session log can persist.
@@ -34,9 +34,9 @@ Core dispatch and the tool body sit inside normalization boundaries, so tool, li
 
 ### Three load-bearing loop decisions
 
-1. **Open the turn before prompt policy.** A fully blocked batch becomes a zero-step `rejected` turn, preserving enclosure and giving ACP a durable terminal event. Every veto also records `prompt/blocked` with the original prompt and reason, so mixed batches retain blocked inputs. Allowed `additionalContext` is injected into the open turn.
+1. **Open the turn before prompt policy.** A fully blocked batch becomes a zero-step `rejected` turn, preserving enclosure and giving ACP a durable terminal event. Every veto also records `prompt/blocked` with the original prompt and reason, so mixed batches retain blocked inputs. Every allowed `additionalContexts` entry is injected into the open turn.
 
-2. **Post-tool `additionalContext` enters the active-batch FIFO and appends when that batch settles.** `content`/`feedback` shape the result `execute()` returns, but `additionalContext` is a SEPARATE `context/message`, and a single step can carry multiple tool calls. Appending context right after each result would interleave `result(c1) → context → result(c2)` and break tool-call/result adjacency. So `execute()` surfaces `additionalContext` on its `ToolExecutionResult`; the loop accepts each context into the same FIFO as asynchronous injections, then appends the FIFO after the complete result batch on success or after every recorded result before an interrupted turn closes.
+2. **Post-tool `additionalContexts` and asynchronous injections enter the active-batch FIFO and append when that batch settles.** `content`/`feedback` shape the result `execute()` returns, but each context is a separate `context/message`, and a single step or composite tool can produce many. Appending context immediately would interleave `result(c1) → context → result(c2)` or place nested context before its outer result, breaking tool-call/result adjacency. `ToolRunContext.deferContext()` therefore collects nested-dispatch context through failures, `execute()` surfaces the ordered array on `ToolExecutionResult`, and the loop accepts it into the same FIFO as `agent.inject()` calls made during execution. The FIFO appends after every recorded result when the batch settles, including before an interrupted turn closes. An accepted outer call preserves deferred contexts before decision contexts; an outer block discards deferred contexts and exposes only contexts explicitly supplied by the blocking decision.
 
 3. **A forced `continue` `reason` is enqueued through the steering channel**, so the next step's top-of-loop drain records it as steering for the continued turn — next-*step* steering within the SAME turn, not a next-*turn* prompt (matching the existing `hasSteering` force-continue override).
 

docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md

@@ -38,7 +38,8 @@ Config plumbing follows the `persona` precedent, and `toolOrder` sits beside it:
 
 - Every registry-built assembly starts with a deterministic tool order on every host; absent an expert listener that deliberately changes it, every `request/header` event and model request inherits that order. The CI-vs-local registration-order flip is structurally gone, and the default is lexicographic.
 - The initial `PromptAssembly.tools` is canonical, so waterfall listeners start from the model-facing order; provider registration order is observable nowhere before that cooperative seam.
-- A pure tool reordering between steps is representable only as a `request/header` `'fallback'` snapshot (the name-keyed `ToolsDelta` cannot express it); with a stable canonical order such reorders no longer occur in practice, so the fallback path stays a safety valve.
+- The snapshot suite's single pinned request-header fixture (`text-turn`) carries the new canonical tool order; every other ACP snapshot keeps the header bulk scrubbed as `{{system}}`/`{{tools}}`, per the pinned-header design.
+- A pure tool reordering between steps is logged like any other header change: a full `request/header` snapshot with reason `'change'`. Stable canonical order prevents registration timing from creating such changes in the ordinary path.
 - The `toolOrder` key rides the app → `agent-core` → `SystemPrompt` forwarding chain, so deployments set it next to `persona` in the app config; `dsh-llm` and the agent loop are untouched.
 - A misspelled or unloaded tool name in `toolOrder` fails the turn at prompt assembly, not the boot: the loop assembles inside the turn (after `turn/start`, before `step/start`), so the rejection reaches the turn's outer catch — the turn closes balanced with an `error` reason carrying the message, `agent/error` mirrors it, no step opens, no `request/header` is logged, no request reaches the adapter, and the agent returns to idle. Every turn fails identically until the config is fixed; the process itself stays up (matching the repo rule that explicit config references must not be silently ignored — the enforcement point is the assembly because no earlier universal moment exists).
 - A tool provider that returns the reserved rest-entry name has the same prompt-assembly failure shape as an unknown listed name. This keeps the sentinel from becoming an ambiguous real tool and preserves the "never drops a tool" ordering contract.

docs/rfc/implemented/feature/2026-07-06-sandbox.md

@@ -155,7 +155,7 @@ Each phase gets its full design when picked up, validated against the code at th
 - **A generic `env/state` facts map with an owner service** — rejected: approval and sandbox compose independently, so neither's state may drag in a third package; single-key folds are one `findLast` each, dissolving the owner service; no invariant spans the knobs, so atomic multi-key patches bought nothing.
 - **Narrate via `agent/user-message` + a bus event** — rejected: it presupposes a turn-entry seam that does not exist (the real seam is `agent/prompt-submit`), and pre-step's position serves both the coalesced turn-entry notice and the mid-turn immediacy bound with one listener.
 - **A standing prompt statement of the sandbox mode (+ a switch narrator)** — shipped first, then removed on live evidence: with `Bash commands run under the "read-only" file sandbox.` in every request, the model refused to ATTEMPT denied-then-escalatable work (five of twelve turns in the first manual session ended with zero tool calls), turning the sandbox into a soft lockout. The denial marker names the mode at the moment it matters and the escalation fields carry the recovery; the approval knob keeps its statement because an auto-rejection is behaviorally indistinguishable from a human "no".
-- **Track "last told" with its own bookkeeping events** — rejected: the `request/header*` fold already records the exact prompt the model saw; parsing the closed candidate sentences back replaces a second bookkeeping stream — events are needed only where they ARE the store.
+- **Track "last told" with its own bookkeeping events** — rejected: the `request/header` fold already records the exact prompt the model saw; parsing the closed candidate sentences back replaces a second bookkeeping stream — events are needed only where they ARE the store.
 - **ACP session modes instead of config options** — rejected: the preset is already one deployment-defined config-option select, and modes are slated for removal in ACP v2.
 
 ## Consequences

docs/rfc/implemented/feature/2026-07-07-session-prefix.md

@@ -15,28 +15,27 @@ The obvious third option — let a plugin edit the request's `messages` on the w
 Three properties carry the design:
 
 - **Request-only, header-logged.** `deriveMessages()` never returns the prefix; its one durable record is `EpochHeader.messagePrefix` on the instance's anchoring `request/header` snapshot — the channel the reconstructable-requests RFC already owns for the request's non-history half, so no new session event exists. The dev invariant ([dsh-invariants](../../../../packages/support/invariants/src/index.ts)) recomputes `messagePrefix + boundary derivation` against every loop-built request; an unlogged prefix cannot reach the wire.
-- **Frozen per instance.** Reuse is structural, not disciplined: the cached product cannot change mid-session, so the provider's prompt cache holds by construction and the prefix extends the cacheable region at zero marginal cost per step. A process restart or `ctx.agents.resume()` is a new instance: it recomposes, and any drift lands attributably on the `'resume'` header snapshot. This is the routing rule the seam creates: session-frozen openers ride the prefix; content that changes mid-session rides the append-only history channels (`agent.inject()`, a `tools/post-execute` decision's `additionalContext`, prompt-submit `additionalContext` — [the interception-seams RFC](2026-06-30-interception-seams.md)), each a durable `context/message` paid once and prefix-cached thereafter.
+- **Frozen per instance.** Reuse is structural, not disciplined: the cached product cannot change mid-session, so the provider's prompt cache holds by construction and the prefix extends the cacheable region at zero marginal cost per step. A process restart or `ctx.agents.resume()` is a new instance: it recomposes, and any drift lands attributably on the `'resume'` header snapshot. This is the routing rule the seam creates: session-frozen openers ride the prefix; content that changes mid-session rides the append-only history channels (`agent.inject()` or tool/prompt-submit `additionalContexts` — [the interception-seams RFC](2026-06-30-interception-seams.md)), each a durable `context/message` paid once and prefix-cached thereafter.
 - **Composed before the pressure gate.** Composition precedes the instance's first `agent/pre-step`, and the seam hands the composed value through: `agent/pre-step` carries a `sessionPrefix` parameter and `CompactService.compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` counts it in its token-pressure estimate — a gate reading the previous instance's folded prefix instead would under-gate a resumed or forked instance whose contributor grew, skipping compaction and shipping an over-window first request. A composition interrupted by a cancel/dispose landing inside the waterfall is discarded, never cached: an abort-aware listener's degraded fallback cannot leak into later requests, and the next turn recomposes under a live signal.
 
 Because composition runs before the boundary snapshot, a composing listener's session append joins the CURRENT request's derived history. Compaction structurally cannot touch the prefix (or the system prompt): it rewrites surface nodes, and header state never enters the surface.
 
 ## Testing
 
-[Interception tests](../../../../packages/core/agent-loop/tests/interception.spec.ts) pin compose-once reuse with no header deltas, prepend order, empty-prefix omission, immutability, and composition before pre-step; [cancellation tests](../../../../packages/core/agent-loop/tests/cancel.spec.ts) pin discard and recomposition. Session codec, invariant, and compaction tests cover header round trips, request reconstruction, and prefix-aware pressure accounting. Snapshot normalization preserves prefix counts, while the [pinned-header scenario](../testing/2026-07-06-pin-request-header-content-in-one-scenario.md) owns content and the default example remains prefix-free. No prefix-specific e2e is needed because the seam is deterministic and provider-independent; the with-key [request-cache e2e](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) covers its cache economics.
+**Unit** — [interception.spec.ts](../../../../packages/core/agent-loop/tests/interception.spec.ts) pins compose-once across turns and steps (one composition and no changed headers), canonical prepend ordering, empty-prefix omission from the header, the frozen seed (in-place push throws), held-reference mutation immunity, and composition-precedes-pre-step with the seam receiving the composed value; [cancel.spec.ts](../../../../packages/core/agent-loop/tests/cancel.spec.ts) pins cancel/dispose landing inside the composition window and the discard-and-recompose stale-cache guard; dsh-session header tests cover canonical prefix snapshots and latest-snapshot folding; dsh-invariants tests pin the `messagePrefix + derivation` equation; dsh-compact-basic tests pin that the pressure estimate counts the handed prefix. **Snapshot** — the acp-snapshot normalizer scrubs header prefixes to count-preserving `{{messagePrefix}}` tokens (unit-covered in dsh-acp-snapshot); header content itself is pinned per [the pinned-header scenario RFC](../testing/2026-07-06-pin-request-header-content-in-one-scenario.md), and the example tree loads no prefix contributor, so live goldens stay prefix-free. **e2e** — none prefix-specific: the seam is provider-independent and deterministic; the with-key cache measurement in [request-cache.e2e.ts](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) already proves the cacheable-prefix economics the design rests on.
 
 ## Alternatives considered
 
-- **Per-request `before`/`after` slots recomputed every step** (the shape first proposed: a waterfall firing on every request, contributing frozen `before` messages ahead of the history and fresh `after` messages behind it) — rejected. A per-step `before` recompose invites silent drift — nothing anchors it to the log short of logging a header delta per step — and an `after` slot sits behind the growing history, so its tokens re-pay on every request and everything after it is uncacheable. Measured against the alternatives, every current update pattern is served cheaper by a durable append (paid once, cache-read thereafter), and the only content with no home was the session-stable opener — which wants freezing, not recomputation.
-- **A system-prompt section** (`system-prompt/assemble`) — rejected for this content: the assembly renders to the single `system` string, so message-shaped openers do not fit, and the system prompt is deliberately re-assembled per step (with header deltas when it changes) while the opener wants instance-frozen semantics.
+- **Per-request `before`/`after` slots recomputed every step** (the shape first proposed: a waterfall firing on every request, contributing frozen `before` messages ahead of the history and fresh `after` messages behind it) — rejected. A per-step `before` recompose invites drift that must be logged as a full changed header, and an `after` slot sits behind the growing history, so its tokens re-pay on every request and everything after it is uncacheable. Measured against the alternatives, every current update pattern is served cheaper by a durable append (paid once, cache-read thereafter), and the only content with no home was the session-stable opener — which wants freezing, not recomputation.
+- **A system-prompt section** (`system-prompt/assemble`) — rejected for this content: the assembly renders to the single `system` string, so message-shaped openers do not fit, and the system prompt is deliberately re-assembled per step (with a full changed header when it changes) while the opener wants instance-frozen semantics.
 - **A durable history opener** (`inject()` at session start) — rejected: permanent history is the failure mode in the problem statement — replayed everywhere, compactable, stale across resumes.
-- **Compose per turn instead of per instance** — rejected: a turn-boundary recompose either desyncs silently from the log or forces a header delta per change, and it busts the provider cache exactly as often as it fires; the legitimate refresh point is the instance boundary, where the `'resume'` snapshot already records drift attributably.
+- **Compose per turn instead of per instance** — rejected: a turn-boundary recompose either desyncs silently from the log or forces a full changed header, and it busts the provider cache exactly as often as it fires; the legitimate refresh point is the instance boundary, where the `'resume'` snapshot already records drift attributably.
 - **Compose lazily at the first request and let compaction read the folded header** (the shape as first merged) — superseded in review: the fold matches the live prefix only from the instance's second request on, so on a resumed/forked instance's first step the pressure gate read the PREVIOUS instance's prefix and could under-gate. Composing before the first pre-step and handing the live value through the seam makes the estimate exact at every step.
-- **A dedicated session event carrying the prefix** — rejected: the header events are the request's non-history record by design; a second event would be a second home for the same fact and another codec to keep total.
+- **A dedicated session event carrying the prefix** — rejected: request headers are the request's non-history record by design; a second event would be a second home for the same fact.
 
 ## Consequences
 
 - `agent/pre-step` and `CompactService.compactIfNeeded` carry a `sessionPrefix` parameter: every pre-step listener and compaction backend sees the real per-instance value (all in-repo implementations updated in the same change, per the pre-release stance).
 - A contributor whose content changes mid-session is not re-read until the next instance — by design. A deployment needing mid-session catalog updates routes the change notice through the append-only history channels and pays one durable `context/message`.
 - The dropped `after` slot leaves no request-only channel near the request tail; nothing in the repo needs one, and adding it back would re-open the every-step re-pay cost the design exists to avoid.
-- The `request/header-delta` `messagePrefix` arm (whole-array replacement, empty array encoding transition to absence) exists for codec totality; the loop never exercises it, because the cached prefix cannot change within an instance.
 - An empty composition is canonical absence: no-contributor deployments log no extra header bytes and their requests are the bare derivation.

docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md

@@ -14,7 +14,7 @@ The guard is a loop-hygiene plugin, not a model-facing tool. It counts consecuti
 
 The plugin is `@deepseek-ai/dsh-repeat-tool-guard` at `packages/guard/repeat-tool-guard/`, opening the `guard/` group for loop-hygiene plugins (single-package groups have precedent: [the todo-write RFC](2026-06-29-todo-write-tool.md) shipped `todo/tool-todo`). It registers three listeners and holds all state in plugin-local maps keyed by `AgentId` — the tool registry is a context-level singleton whose waterfalls interleave every agent's calls (subagents run on the same context), so per-agent keying is correctness, not polish.
 
-- **`tools/post-execute` (waterfall)** — the one detection point. The listener receives `(exec, result)` together, so counting and reminder delivery need no cross-event pending map (the pi extension needs one only because its `tool_call`/`tool_result` hooks are separate events). It always delegates via `next()` and, when a threshold is hit, folds a reminder onto the downstream decision's `additionalContext` — the observe-and-enrich posture [the hooks bridges](2026-06-30-hook-bridges.md) already use, honoring the waterfall contract. Counting happens here rather than in `tools/pre-execute` because post-execute also runs for denied calls (`ToolRegistry.execute` routes a deny through the same pipeline), and a model hammering a denied call is exactly the loop worth breaking.
+- **`tools/post-execute` (waterfall)** — the one detection point. The listener receives `(exec, result)` together, so counting and reminder delivery need no cross-event pending map (the pi extension needs one only because its `tool_call`/`tool_result` hooks are separate events). It always delegates via `next()` and, when a threshold is hit, prepends a reminder to the downstream decision's `additionalContexts` — the observe-and-enrich posture [the hooks bridges](2026-06-30-hook-bridges.md) already use, honoring the waterfall contract. Counting happens here rather than in `tools/pre-execute` because post-execute also runs for denied calls (`ToolRegistry.execute` routes a deny through the same pipeline), and a model hammering a denied call is exactly the loop worth breaking.
 - **`agent/prompt-submit` (waterfall)** — pure reset hook: delegate via `next()`, clear the submitting agent's chain. A user interjection changes the context; repetition across it is not a loop.
 - **`agent/status` (emit)** — on `disposed`, drop the agent's state, bounding the maps over harness lifetime.
 
@@ -29,7 +29,7 @@ Two deliberate rules, both documented in [the package README](../../../../packag
 
 ### Reminder delivery
 
-Reminders use `additionalContext` with the plugin source, preserving the original `tool/result`. The first threshold emits a short nudge; later thresholds include the tool, count, and a bounded argument preview while comparison still uses the full canonical string. Existing downstream context is concatenated under the guard's source because `HookContext` supports one source.
+Reminders ride `additionalContexts` as their own entries (source `{kind: 'plugin', plugin: 'repeat-tool-guard'}` — the label is load-bearing per `HookContext`), never a `content` replacement: the `tool/result` event stays the tool's own output for audit, and the loop appends buffered contexts as `context/message`s after the step's results, which the session renders as tagged synthetic-user envelopes and derived history replays. Thresholds escalate: the first configured threshold gets a short "you are repeating yourself, analyze the previous result" nudge; each later threshold gets the detailed form naming the tool, the repeat count, and the canonical arguments (head-truncated at `argumentsPreviewChars`, default 500 — a looping `write`-sized payload must not ride into the next request unbounded; the chain key always compares the full canonical string), and stating that the calls made no progress. The pi original hardcodes the gentle text to the literal count 3; the guard keys it to `thresholds[0]`, fixing that bug in the port. A downstream hook bridge contribution remains a separate array entry, so both plugins retain their source, envelope, and metadata.
 
 ### Config
 
@@ -53,7 +53,7 @@ Reminders use `additionalContext` with the plugin source, preserving the origina
 
 ## Alternatives considered
 
-- **Append the reminder into the tool result** (`accept` with replaced `content` — the pi extension's mechanism, which patches result content because that is the only channel its API offers) — rejected: it makes the logged `tool/result` lie about what the tool returned, and `additionalContext` exists precisely as the separate sanctioned channel for post-execute commentary, with loop-level buffering that preserves call/result adjacency.
+- **Append the reminder into the tool result** (`accept` with replaced `content` — the pi extension's mechanism, which patches result content because that is the only channel its API offers) — rejected: it makes the logged `tool/result` lie about what the tool returned, and `additionalContexts` is the separate sanctioned channel for post-execute commentary, with loop-level buffering that preserves call/result adjacency.
 - **Count in `tools/pre-execute` with a pending-reminder map** (the pi two-phase shape) — rejected: post-execute alone sees `(exec, result)` together and also fires for denied calls, so one listener with no cross-event state covers strictly more attempts with less machinery.
 - **Escalate to `block` at the highest threshold** — rejected for the initial scope: a blocked call punishes legitimate identical repeats (polling a long-running terminal, re-checking a file the agent expects to change), and an advisory reminder keeps the model in control. Revisit with evidence; the decision shape (`PostToolDecision`) already supports it.
 - **A per-deployment external hook via the CC/Codex bridges** (a `PostToolUse` script) — rejected as the answer: it works for one deployment, but a shipped, unit-tested, `cordis.yml`-configurable plugin is the harness-native form, without per-call subprocess cost.
@@ -65,7 +65,8 @@ Reminders use `additionalContext` with the plugin source, preserving the origina
 
 - The reminder is advisory by design: idempotent polling patterns that repeat identical calls on purpose still receive nudges past the thresholds, and the pressure valves are config (`thresholds`, `exclude`) plus reminder text that explicitly allows finishing when enough evidence has been gathered. Each trigger costs reminder tokens on the next request; thresholds bound the frequency.
 - Chain state is in-memory only: a session resumed from persistence starts with a fresh chain, so a loop spanning a resume draws its reminders later than a live one — accepted, the guard is a heuristic nudge, not a logged invariant, and persisting counter state would buy little for real complexity.
-- When multiple post-execute producers attach context on one call, the fold concatenates under the guard's `source`; ordering between plugins follows listener registration order. The seam cannot represent mixed provenance — a limit inherited from `HookContext`, not owned by this plugin.
+- When multiple post-execute producers attach context on one call, each contribution stays a separate `HookContext`; ordering follows waterfall nesting and each entry retains its own provenance.
+- Implementing the snapshot tier surfaced a hidden assumption in the suite kit: the fixture guard equated "authored model scenario" with "override-driven". The `Scenario` table now carries an explicit `overridden` flag, and the sidecar's presence is checked BOTH ways against it (an unregistered stray sidecar would silently replace the derived script) — the suite kit is stricter than it was before this plugin existed.
 
 ## Deferred
 

docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md

@@ -52,7 +52,7 @@ Freshness is gated like every generated artifact: `pnpm run verify-cordis-api` (
 
 The plugin exposes one config field, validated by schemastery and documented in [the config catalog](../../../config-catalog.md): `vmTimeoutMs` (default 5000), the millisecond bound on the synchronous portion of mount-code evaluation. Tool names, the `cordis-dynamic` group name, and the `dyn-` id prefix are structural vocabulary and stay fixed. All three tools render as `generic` cards per [the tool cookbook](../../../cookbook/adding-a-tool.md) (`cordis_inspect` a `read`, `cordis_mount` an `execute` carrying the code as `rawInput`, `cordis_unmount` a `delete`), with no `presentResult` overrides.
 
-Model-visible ⟺ logged holds with no new session event type: a mount or unmount is visible only through its own `tool/call` / `tool/result` pair, which the loop logs, and the changed tool set a mount induces is logged by the request-header delta the loop already emits when schemas change between steps. There is deliberately no `cordis/mount` provenance event — it would duplicate what the tool-call pair records. Dynamic mounts are process-lifetime, not session state: resuming a persisted session rehydrates the conversation but does not re-mount plugins.
+Model-visible ⟺ logged holds with no new session event type: a mount or unmount is visible only through its own `tool/call` / `tool/result` pair, which the loop logs, and the changed tool set a mount induces is logged by the full changed request header the loop emits when schemas change between steps. There is deliberately no `cordis/mount` provenance event — it would duplicate what the tool-call pair records. Dynamic mounts are process-lifetime, not session state: resuming a persisted session rehydrates the conversation but does not re-mount plugins.
 
 ## Alternatives considered
 
@@ -71,7 +71,7 @@ The correctness investment therefore goes where it pays for every capability at
 
 **A hand-maintained service/event reference in the tool.** The first cut of the inspect tool carried a hand-written table of service method signatures. It was replaced by the generated `api-catalog.ts` because a hand table drifts from the JSDoc the moment a signature changes and nothing gates the drift, whereas the generated artifact is freshness-checked against the same AST the docs use.
 
-**A new `cordis/mount` session event.** A durable provenance event recording each mount (source, name) has clear precedent (`hook/invoked`, `compact/start`). It was declined for v1: mount and unmount are already visible as `tool/call` / `tool/result` pairs and the tool-set change is already logged as a request-header delta, so a dedicated event would only duplicate the record. It remains addable if an audit use case needs mount provenance separable from the tool call.
+**A new `cordis/mount` session event.** A durable provenance event recording each mount (source, name) has clear precedent (`hook/invoked`, `compact/start`). It was declined for v1: mount and unmount are already visible as `tool/call` / `tool/result` pairs and the tool-set change is already logged as a full changed request header, so a dedicated event would only duplicate the record. It remains addable if an audit use case needs mount provenance separable from the tool call.
 
 **A hardened / capability-restricted sandbox.** Trapping Node built-ins and handing mount code a whitelist façade rather than the raw context might suggest an intent to sandbox for safety. It is explicitly not that: the traps and the façade narrow the *surface* mount code sees — steering it onto cordis services and away from leak-prone Node built-ins and framework internals — for correctness and to close the unguarded-context escape, but the capabilities the façade exposes (`ctx.bash`, `ctx.fs`, `ctx.web`) reach the real runtime, so it is not a security boundary. A real one (separate process, permission prompts) was out of scope for a dev/opt-in toolset and would fight the entire point — handing the model the live runtime.
 

docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md

@@ -0,0 +1,166 @@
+# RFC: Bash-backed grep and glob discovery tools
+
+Status: implemented
+
+## Problem
+
+The harness needs model-facing `glob` and `grep` tools, but making them `ctx.fs` provider methods turns a local product convenience into a universal filesystem backend contract. Local workspace discovery is naturally a process-backed `rg` workflow; remote or virtual filesystem backends may expose their own search API, may not share a local `ripgrep` view, or may not support discovery at all. The v1 should not require every filesystem backend to implement search before the file read/write/edit seam has proven that need.
+
+Search output also has two distinct budgets. The tool needs enough raw `rg` output to compute a stable logical result, but the model should receive only a bounded preview plus a recovery path when the formatted result is larger than the inline budget. The generic spill policy only sees the final tool result, so it cannot recover matches that a search tool already omitted. Search therefore needs tool-owned retention and best-effort formatted-result spill.
+
+## Decision
+
+`glob` and `grep` are model-facing tools in `@deepseek-ai/dsh-tool-fs-search`, backed by the bash seam, not by new `ctx.fs` provider methods. The package registers model-facing filesystem discovery tools, but execution uses `ctx.bash.resolve(request)` followed by `ctx.bash.run(spec)` with fixed `rg` command templates assembled by the tool. The tool layer owns schemas, argument validation, shell quoting, result parsing, result formatting, retention, formatted-result spill handoff, and timeout declaration. The bash executor owns request defaulting/capping, subprocess execution, process-group termination, environment scrubbing, raw output capture, and backend substitution across local, sandboxed, or remote bash implementations.
+
+The tools do not use `ctx.bash.start()` and do not create model-visible background tasks. They run as ordinary foreground tools from the agent loop's perspective: the tool call returns only after the `rg` command exits, times out, is aborted, or fails. `defineTool({ timeoutMs })` declares the cooperative tool-call budget, `@deepseek-ai/dsh-timeout-policy` enforces it through `exec.signal`, and the tool forwards that signal into the bash request before `resolve()` / `run()`. The bash backend's own timeout remains a second safety cap; whichever aborts first wins.
+
+The tools align `path` with Claude Code's search tools while binding resolution to the bash workdir, not to `ctx.fs`. The tool derives the bash request workdir from `exec.agent?.session.header.cwd`, mirroring `dsh-tool-bash` and `dsh-tool-fs`; when no session cwd exists, it omits `request.workdir` so the bash implementation applies its configured cwd or process cwd through `resolve()`. For `grep`, `path` is an optional ripgrep target and may be a file or directory; omitted means the resolved bash workdir. For `glob`, `path` is an optional directory search root; omitted means the resolved bash workdir. Relative `path` values resolve against that workdir. Returned paths are displayed relative to the resolved bash workdir when possible and are intended to be follow-up-readable only in co-located deployments where the bash workdir and filesystem `read` root are the same workspace. v1 documents that deployment requirement but does not perform runtime cross-service validation. Remote or virtual filesystem search is deferred until there is a shared workspace/root contract or a provider-specific search backend.
+
+The package does not inject `fs`. It injects `tools`, `systemPrompt`, and `bash`; it deliberately reads `spillStore` with `ctx.get('spillStore')` instead of static inject because formatted-result spill is optional. Existing `@deepseek-ai/dsh-tool-fs` deployments that only want `read` / `write` / `edit` do not need to load bash.
+
+### Package shape
+
+The v1 package stays small. Inside `@deepseek-ai/dsh-tool-fs-search`, the source layout is:
+
+```text
+src/index.ts
+src/glob.ts
+src/grep.ts
+src/search-core.ts
+src/shell-quote.ts
+```
+
+`glob.ts` and `grep.ts` own their parameter validation, command construction, result parsing, formatting, and registration. `shell-quote.ts` is one shared helper because shell quoting is the safety boundary both tools must use; `search-core.ts` is the other (an implementation-time amendment to the original four-file plan): the `SEARCH_*` error vocabulary, the bash-run + raw-output acquisition, the formatted-spill handoff, and workdir-relative display are byte-identical between the two tools, and duplicating that delicate plumbing per tool is exactly the missed extraction the symmetry convention flags. Command builders must not hand-roll quoting or concatenate unquoted model-controlled values into the shell command.
+
+### Schemas and config
+
+`glob` exposes the small discovery shape:
+
+```ts
+interface GlobArgs {
+  pattern: string
+  path?: string
+}
+```
+
+`grep` exposes the OpenCode-style minimal shape:
+
+```ts
+interface GrepArgs {
+  pattern: string
+  path?: string
+  include?: string
+}
+```
+
+Routine budgets stay out of the model-facing schema. `@deepseek-ai/dsh-tool-fs-search` owns these defaulted, validated config fields:
+
+| Field | Default | Role |
+|---|---:|---|
+| `globMaxResults` | `100` | Max paths retained inline; matches Claude Code's default `GlobTool` result limit. |
+| `grepMaxMatches` | `250` | Max flat matches retained inline; matches Claude Code's default `GrepTool` `head_limit`. |
+| `grepMaxLineBytes` | `2000` | Max bytes retained for one matched-line preview, applied with `TextRetainer({ kind: 'head', maxBytes: grepMaxLineBytes })`. |
+| `rawOutputMaxBytes` | `20000000` | Max complete raw `rg` stdout the tool will parse; matches Claude Code's ripgrep raw buffer. |
+| `timeoutMs` | `30000` | Tool-call timeout attached to both tool definitions and enforced by `@deepseek-ai/dsh-timeout-policy`. |
+
+`globMaxResults` and `grepMaxMatches` use `ItemRetainer({ kind: 'head' })`. `grepMaxLineBytes` uses `TextRetainer({ kind: 'head', maxBytes: grepMaxLineBytes })` for each matched line so preview cuts preserve UTF-8 boundaries. This follows the [tool result retention library](../../implemented/architecture/2026-07-06-tool-result-retention-library.md) mapping for discovery items: collect the complete result, retain head items inline, and keep path mapping, grouping, and per-line preview outside the retainer. `grep` does not expose `case_insensitive`, `head_limit`, `offset`, `count`, multiline, context lines, output modes, or file type filters in v1. A model that needs surrounding context reads the matched file with `read`; a model that needs later results follows the returned spill locator's retrieval hint.
+
+The Claude Code values are reference points for the two-layer budget, not model-facing schema precedent. Its dedicated search tools buffer raw ripgrep output up to 20 MB for internal processing, use a 20-second ripgrep timeout on non-WSL platforms (60 seconds on WSL), then apply search-specific caps before the model sees a result: `GrepTool` defaults to `head_limit = 250` and persists formatted results above 20,000 characters, while `GlobTool` defaults to 100 paths and persists formatted results above 100,000 characters. This RFC mirrors the raw-buffer and inline-count defaults, chooses a 30-second default search timeout, and uses this harness's `ctx.spillStore.saveText()` path for formatted-result recovery.
+
+The `path` field follows the same split as Claude Code: `grep.path` is a file-or-directory ripgrep target, while `glob.path` is a directory search root. v1 does not expose a separate cwd/workdir argument on these tools.
+
+`include` is one positive glob filter, not a list and not an exclude syntax. Reject comma-separated or negated include patterns up front with a structured argument error. Every model-controlled value used in a shell command, including `pattern`, `path`, and `include`, must pass through the package-private shell quoting helper.
+
+### Execution
+
+`glob` builds a fixed `rg --files` command rooted at the resolved directory search root (`path` when supplied, else the bash workdir): `rg --files --glob <pattern> --sort=modified --no-ignore --hidden`, plus VCS metadata excludes for `.git`, `.svn`, `.hg`, `.bzr`, `.jj`, and `.sl`. This aligns with Claude Code on hidden/ignored-file discovery and modified-time ordering while keeping VCS internals out of broad searches. The tool parses one path per line, maps results back to paths relative to the bash workdir when possible, pushes each path into `ItemRetainer({ kind: 'head', maxItems: globMaxResults })`, and formats the full sorted path list for a spill artifact when the retained result is capped.
+
+`grep` builds a fixed line-oriented `rg --json` command against the supplied file/directory target (`path` when supplied, else the bash workdir) so file path, line number, and line text are parsed without colon-splitting ambiguity. It consumes `match` records, treats malformed JSON or malformed match records as `SEARCH_FAILED`, maps result paths relative to the bash workdir when possible, applies per-line preview retention with `grepMaxLineBytes`, pushes each match into `ItemRetainer({ kind: 'head', maxItems: grepMaxMatches })`, then groups only the retained preview matches by file for inline output. The spill artifact stores the full formatted match list, not only the omitted tail, so the retrieval hint points at the same logical result the model saw.
+
+Raw `rg` stdout is an internal transport detail. The tool requests `stdoutMaxBytes: rawOutputMaxBytes` through `ctx.bash.resolve()` and parses `stdout.text` only when the executor returns untruncated stdout within that cap. If stdout is larger than `rawOutputMaxBytes`, or the executor still returns `stdout.truncated`, the tool fails with a clear search error telling the model to narrow `pattern`, `path`, or `include`. The tool never exposes raw `rg` output or bash raw spill paths to the model.
+
+Only stdout is a parse source. Stderr is diagnostic text for invalid patterns, missing `rg`, and search failures; if bash truncates stderr, the tool uses the retained stderr tail with a truncation note and does not read `stderr.spillPath`.
+
+If `ctx.bash.run()` reports `aborted` because the tool timeout or caller cancellation fired, the tool returns a structured failure rather than pretending there were no matches. If bash reports its own timeout first, the tool likewise fails with a clear timeout message. Nonzero ripgrep exit semantics are tool-owned: exit 0 is success with matches, exit 1 is success with no matches, invalid pattern / missing `rg` / inaccessible search workdir are failures.
+
+Search failures use a package-owned `HarnessError` subclass with `SEARCH_*` codes, not `FsErrorCode`, because these tools are not `ctx.fs` provider operations. The v1 vocabulary is `SEARCH_INVALID_PATTERN`, `SEARCH_FAILED`, `SEARCH_RAW_OUTPUT_OVERFLOW`, and `SEARCH_ABORTED`. Model argument validation failures such as missing required fields, blank strings, or unsupported negated/list `include` values remain ordinary tool argument errors.
+
+### Formatted result spill
+
+`ctx.spillStore` is optional and used only for model-facing formatted results. This is the first tool-owned spill call pattern in the codebase, and it is intentional because search retention is item-level policy: `globMaxResults` caps paths and `grepMaxMatches` caps matches while the tool still holds the complete logical result. The generic `dsh-spill-policy` caps final text bytes on `tools/post-execute`; by then a search tool would already have omitted later paths or matches, so the policy cannot recover them.
+
+When a search produces more logical results than the inline cap and `ctx.spillStore` is present, the tool saves the complete formatted result with `saveText()`. The spill owner is the calling agent's session header id (`exec.agent?.session.header.id`); without that owner, the search keeps the inline result and reports that the complete result could not be saved. The spill source is the tool execution identity: `{ toolName: exec.name, callId: exec.callId, label: 'result' }`. The suggested filenames are `grep-results.txt` and `glob-results.txt`; the spill backend still treats them as hints, never paths.
+
+When spill storage is absent, the call has no session owner, or saving fails, the tool still returns the inline page and a footer explaining that the complete result could not be saved. Search success must not turn into an `isError` result solely because formatted-result spill storage is unavailable.
+
+The bash raw output stream and the formatted search spill artifact are different artifacts. Raw `rg` stdout is parsed only in memory within the requested bash stdout cap; the formatted spill artifact is the stable model-facing recovery locator produced by `ctx.spillStore.saveText()`.
+
+### Result shape
+
+A capped `glob` result with successful formatted spill returns the inline page and a spill notice:
+
+```text
+<first N paths>
+
+(Showing N of M paths. Full sorted result stored at: /.../session-abc123/9f8e7d-glob-results.txt. Use read with offset/limit, or grep this path to search within it.)
+```
+
+A capped `grep` result with successful formatted spill returns grouped preview matches and a spill notice:
+
+```text
+Found N of M matches
+
+<file>
+Line 12: ...
+
+(Full grep result stored at: /.../session-abc123/9f8e7d-grep-results.txt. Use read with offset/limit, or grep this path to search within it.)
+```
+
+If the complete logical result fits under the inline cap, no formatted spill artifact is created. If the complete logical result is too large but formatted spill is unavailable, the footer says that the result was capped and the complete result could not be saved. The `truncated` / omitted count is a budget fact, not an incomplete-search fact; timeout, invalid regex, missing `rg`, inaccessible workdirs, raw-output overflow, binary skips, and parse failures stay in tool-domain error or incomplete fields.
+
+## Alternatives considered
+
+**Put `glob` / `grep` on `ctx.fs`.** Rejected for v1: it forces every filesystem backend to grow a search API and makes local ripgrep behavior part of the provider seam. Search is useful product behavior, but it is not a universal text-storage primitive like `readText` or `writeText`.
+
+**Directly spawn ripgrep from `dsh-fs-local`.** Rejected for this RFC's v1: direct spawn gives the cleanest argv boundary, stdout/stderr control, and early-stop control, but it duplicates process execution concerns that the bash seam already owns: environment scrubbing, process-group kill, timeout propagation, sandbox/remote executor substitution, and bounded output capture. It remains a reasonable optimization if bash-backed search proves too shell-string-sensitive or if foreground streaming becomes necessary.
+
+**Use `ctx.bash.start()` for streaming early stop.** Rejected: `start()` creates model-visible background task semantics: task ids, owner tokens, `bash_output`, `bash_kill`, completion notifications, and no built-in timeout. `grep` needs a foreground tool result, not a background bash workflow. If streaming search becomes necessary, the right abstraction is a foreground streaming process handle on the bash/process seam, not borrowing the public background-task API.
+
+**Expose bash raw spill paths to the model.** Rejected: a bash raw spill path contains raw `rg` stdout (`rg --json` records for grep), not the stable formatted search result. Search parses raw stdout only as an internal transport; model recovery uses a formatted result saved through `ctx.spillStore.saveText()`.
+
+**Add `spillStore.saveFile()` for bash output normalization first.** Rejected for this RFC's v1: `saveFile()` would help a future bash normalization pass move existing executor spill files into session-scoped spill storage, but search only needs bounded in-memory raw `rg` stdout before producing the model-facing artifact. `saveText()` is sufficient for the formatted search result.
+
+**Rely on the generic `dsh-spill-policy`.** Rejected: generic post-execute spill sees only the final tool result. If `grep` / `glob` return the first page inline, the generic policy cannot recover omitted results. The search tools must save the complete formatted result themselves before returning the bounded model-facing text.
+
+**Expose Claude Code's full `GrepTool` schema.** Rejected for v1: `output_mode`, context flags, multiline, `head_limit`, `offset`, `case_insensitive`, and type filters make the model-facing surface into a ripgrep wrapper. This harness keeps routine budgets and continuation mechanics in deployment policy and spill artifacts.
+
+**Keep early-stop search and skip formatted spill artifacts.** Rejected for this proposal: early stop is more efficient but gives the model no path to inspect later results. The chosen v1 optimizes result recoverability and implementation simplicity, with `timeoutMs`, `rawOutputMaxBytes`, bash backend caps, and formatted spill artifacts as safety backstops.
+
+**Expand the bash seam with a raw-output reader first.** Rejected: a portable `readRawOutput(ref, maxBytes)` API would add reference lifetime, permission, and backend storage semantics. A per-run `stdoutMaxBytes` request is the narrower seam: search either receives complete stdout within `rawOutputMaxBytes` or fails clearly.
+
+## Testing
+
+- Tests prove an aborted `exec.signal` reaches the bash backend (same-reference spec assertion plus the `SEARCH_ABORTED` result), and cover command construction/quoting (malicious patterns, paths with spaces, leading-dash values, quotes, newlines, glob metacharacters — unit assertions plus a real `bash -c` round-trip for every hostile value), `grep.path` as file and directory targets, `glob.path` as a directory search root, invalid pattern handling, no matches, malformed `rg --json` output, matched-line preview truncation, raw-output overflow, timeout/abort, formatted spill success/failure, the package-owned `SEARCH_*` error codes, and the no-background-task invariant.
+- The first-party tool-owned spill precedent is covered directly: spill backend present, spill backend absent, `saveText()` failure, and missing spill owner.
+- The package has real Loader-path coverage for the namespace plugin export shape (`name`, `inject`, `Config`, and `apply`, with no default export).
+- A real-executor integration suite (`dsh-bash-local` + a real `rg`) verifies the world: hostile patterns stay inert, per-session cwd resolution, VCS-metadata exclusion, modification-time ordering, and real ripgrep stderr classification. It self-skips where `rg` is not on PATH (a CI accommodation mirroring the keyless e2e skip); the fake-executor suite alone carries the per-file 100% coverage gate.
+- Snapshot gap note for the transcript-visible spill notice: this landed with the gap note, not a snapshot. The snapshot tier replays the acp-agent tree, and adding the search plugin there changes the assembled system prompt — every golden would need re-recording with a real key, which the implementing environment did not hold. The spill notice's exact transcript text is pinned by unit tests (`formatGlobOutput`/`formatGrepOutput` and the through-the-registry spill tests); wiring the plugin into the acp-agent tree plus a `test:snapshot:record` pass is the follow-up for the next key-holding session.
+
+## Consequences
+
+- `glob` and `grep` are model-facing tools in `@deepseek-ai/dsh-tool-fs-search`, not `ctx.fs` provider methods and not part of the existing `@deepseek-ai/dsh-tool-fs` root plugin. The package injects `tools`, `systemPrompt`, and `bash`; it does not inject `fs`, and `ctx.spillStore` stays optional via `ctx.get('spillStore')`.
+- The schemas are exactly `glob(pattern, path?)` and `grep(pattern, path?, include?)`; search caps and timeout are defaulted, validated Config fields (`globMaxResults`, `grepMaxMatches`, `grepMaxLineBytes`, `rawOutputMaxBytes`, `timeoutMs`).
+- The tools execute through `ctx.bash.resolve(request)` → `ctx.bash.run(spec)`, forward `exec.signal`, never call `ctx.bash.start()`, and never expose a bash task id. The bash request workdir comes from `exec.agent?.session.header.cwd` when available; the resolved `spec.workdir` drives execution and relative-path display.
+- The tools request `stdoutMaxBytes: rawOutputMaxBytes` from the bash seam, parse only untruncated stdout within that cap, and treat over-cap or still-truncated raw output as a clear search failure; raw `rg` output is never exposed to the model.
+- Oversized complete formatted results are saved through `ctx.spillStore.saveText()` when available while inline results stay bounded; spill failure, a missing backend, or a missing owner preserves the inline result and reports the unsaved remainder — never an `isError`.
+- The package README, the generated config catalog, and exported JSDoc document the Config fields and `SEARCH_*` codes; the coding-agent example ships the tools (the acp-agent tree waits on the snapshot re-record above); the fs group README records the co-located bash/filesystem deployment requirement.
+
+## Risks
+
+Full-run `grep` can be slower than an early-stop search on broad patterns. The v1 accepts that cost for simpler implementation and complete-result recovery, bounded by tool timeout, bash timeout, `rawOutputMaxBytes`, and output caps. If this proves too slow, the direct-ripgrep or foreground-streaming alternatives remain available.
+
+Shell command construction is the sharpest safety edge. Because `ctx.bash` accepts a command string rather than an argv vector, the implementation must centralize shell quoting and test malicious patterns, paths with spaces, leading-dash patterns, quotes, newlines, and glob metacharacters.
+
+The v1 assumes a co-located bash/filesystem deployment. If bash searches one workspace and the `read` tool resolves paths against another, returned paths may not be follow-up-readable. The package documents this requirement but does not verify it at runtime.
+
+Spill locators are backend-owned. The current local backend returns local filesystem paths and works in deployments where `read`/`grep` can open those files; remote or workspace-confined deployments can use a backend whose locator and retrieval hint point at a supported retrieval mechanism.

docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md

@@ -0,0 +1,85 @@
+# RFC: Expose agent session identity and JSONL location to tools and hooks
+
+Status: implemented
+
+## Problem
+
+An agent can identify its workspace through `session.header.cwd`, but a model using bash cannot reliably identify the session that owns the call or the durable transcript that records it. Searching `./.sessions` guesses deployment config and JSONL layout; custom roots, alternate persistence backends, resume, forks, and concurrent parent/child agents make that guess unreliable. Hooks have the same need for transcript location, while future plugins may need to expose other harness-owned environment facts to shell commands.
+
+The boundary must preserve two properties: the owner of a fact decides how to resolve it, and every child receives a per-execution snapshot rather than process-global mutable state. In particular, a nested harness must not leak its ambient `DSH_*` values into a child whose current agent, persistence backend, or configuration differs.
+
+## Decision
+
+Extend the [`SessionPersistence`](../../implemented/architecture/2026-06-14-session-persistence.md) seam with a synchronous, side-effect-free location query:
+
+```ts
+import type { SessionHeader } from '@deepseek-ai/dsh-session'
+
+interface SessionLocation {
+  readonly kind: string
+  readonly path: string
+}
+
+interface SessionPersistence {
+  locate(meta: SessionHeader): SessionLocation | undefined
+}
+```
+
+`path` is an absolute local path to the backend's dedicated log for `meta`; `kind` identifies the representation. JSONL returns `{ kind: 'jsonl', path }` using its resolved root and path helpers. SQLite and any backend without an honest local per-session artifact return `undefined`. The query creates and flushes nothing, so it can report a lazy target path before that file exists.
+
+The model-facing bash package owns a `ctx.bashEnv` registry. A contributor declares its stable name, every `DSH_*` key it may return, a description for each key, and `resolve(execution: ToolExecution)`. Duplicate contributor names, duplicate key ownership, reserved keys, malformed declarations, undeclared runtime output, and non-string output fail loudly. Registration is a Cordis effect and is removed with the contributing plugin fiber. `list()` exposes declarations without running resolvers, keeping the environment surface enumerable for diagnostics and future prompt/UI consumers.
+
+The registry rebuilds a trusted overlay for every foreground and background bash `ToolExecution`:
+
+- `DSH_HOME` is always the absolute configured Harness home. The standalone [`@deepseek-ai/dsh-home`](../../../../packages/util/home/README.md) utility owns its precedence: explicit `dshHome`, then ambient `$DSH_HOME`, then `~/.dsh`.
+- `DSH_SHELL=1` is always present and identifies a model bash child managed by DeepSeek Harness.
+- `DSH_SESSION_ID` is present when the execution has an agent and equals `agent.session.header.id`.
+- The built-in persistence translator contributes `DSH_SESSION_JSONL` only when `ctx.sessionPersistence.locate(header)` returns `kind: 'jsonl'`.
+
+Session persistence remains the fact owner: JSONL does not depend on tool-bash or register shell variables itself, and hooks continue to consume `locate()` directly. Tool-bash is the translation layer from the persistence fact into a shell convention. Other plugins that need shell-visible facts depend on the registry and register their own keys; they do not modify `process.env`.
+
+The bash seam exports `DSH_ENV_PREFIX` as the single namespace source and derives `DshEnvironmentKey` from its `typeof`. Tool-bash derives built-in names and model guidance from that constant, while executors use it for filtering and channel validation. The seam carries the managed overlay separately as `BashExecRequest.dshEnv` / `BashExecSpec.dshEnv`. Ordinary `env` remains the general in-process plugin surface used by hooks, but cannot contain managed keys; symmetrically, `dshEnv` cannot contain ordinary keys. The local executor rejects either wrong channel before spawn, removes every inherited ambient managed key, applies its ordinary scrub/terminal environment/explicit `env`, and finally merges the trusted `dshEnv` snapshot. This guarantees that a missing value means absent now rather than inherited from an outer or previous harness. The model-facing tool still ignores model-supplied `env`/`stdin` arguments.
+
+The bash tool description teaches only the durable convention: current harness environment facts are available through managed `$DSH_*` variables and may be inspected when needed. It does not enumerate persistence-specific keys or add a permanent system-prompt section. Tool schemas are already logged in request headers and tool output is logged as `tool/result`, so no new session event is required.
+
+The [Claude Code and Codex hook bridges](../../implemented/feature/2026-06-30-hook-bridges.md) resolve transcript location from the same persistence seam when constructing payloads. Codex uses `transcript_path: string | null`; Claude Code preserves its string field and falls back to `''`. Hook lookup neither materializes nor flushes a session.
+
+## Peer product findings
+
+Peer products separate stable identity from physical storage. Codex injects stable `CODEX_THREAD_ID` into spawned shells while recorder and hook surfaces own transcript paths. Claude Code supplies `session_id` and `transcript_path` as structured hook/status input. OpenCode carries identity in structured tool context; Kimi Code expands a session placeholder; Reasonix keeps the active session path on its controller. The portable rule is to inject identity at the invocation boundary, let storage resolve location, and never use a process-global current-session variable in a concurrent harness.
+
+## Lifecycle and persistence semantics
+
+A fresh session receives its id before the first turn, so its first bash call can read `DSH_SESSION_ID` and a JSONL target. The JSONL file may still be absent until the first successful turn-end checkpoint, and during an open turn it contains only the last flushed prefix. `DSH_SESSION_JSONL` is a location hint, not an authorization credential or freshness guarantee.
+
+Resume reuses the loaded header and therefore the same id and location. Fork and spawn create new session ids and locations. Parent and child calls resolve from their own `ToolExecution.agent`; each command receives an immutable snapshot even when calls overlap. A persistence service replacement affects later collections because the translator queries `ctx.get('sessionPersistence')` at execution time; the registry itself is effect-scoped and HMR-safe.
+
+`dshHome` is session-independent deployment context. Agent-core resolves one value through `@deepseek-ai/dsh-home` and routes it to both tool-bash and local skill discovery; standalone consumers call the same resolver. If top-level `dshHome` and `skills.local.dshHome` are both supplied and resolve differently, composition fails instead of exposing contradictory homes. Persistence may change independently without freezing its facts into the session prefix.
+
+## Testing
+
+Unit coverage pins registry declaration validation, effect disposal, per-execution collection, the `dshHome` precedence, and the local executor's `DSH_*` scrub/rebuild order. Request-recording tests cover foreground/background snapshots, no-agent calls, absent/JSONL persistence, ignored model `env`, and parent/child isolation. JSONL/SQLite locator contract tests and both hook bridge suites pin available and unavailable transcript dialects.
+
+A keyless full-loop integration drives the real agent loop, JSONL persistence, tool-bash, and bash-local on the first turn. The child prints `DSH_HOME`, `DSH_SHELL`, session id, JSONL target, and an inherited stale sentinel; the test verifies current values, absence of the stale variable, pre-flush file absence, and the eventual persisted header. Snapshot coverage pins the generic bash description in the recorded request header. No with-key test is required because the contract is deterministic local execution rather than model choice.
+
+## Alternatives considered
+
+**Only an id plus `find`.** Search cannot know a custom root or backend layout and races under multiple sessions.
+
+**Only an absolute path.** A path can be unavailable, lazy, or representation-specific and is not stable session identity.
+
+**Global `process.env`.** Concurrent agents would overwrite one another and nested harnesses would inherit stale current-session values.
+
+**Put persistence instructions in the session prefix.** A session prefix is frozen while the active service can change across HMR or future backend switching; persistence-specific guidance would become stale.
+
+**A typed waterfall event.** Listeners cannot declare ownership without running, and later listeners can silently overwrite keys. A registry detects key conflicts at registration and remains enumerable.
+
+**Have each persistence backend register bash env directly.** That reverses the dependency from storage into one consumer and forces bash into deployments that do not use it. `locate()` is also still required by hooks.
+
+**A model-facing `session_info` tool.** It adds schema and another call while bash already supplies the query surface; the registry generalizes to future environment facts without one tool per fact.
+
+## Consequences
+
+Every model bash child receives current Harness home and shell identity, and agent calls additionally receive stable session identity. JSONL-backed calls get an optional target path; non-file persistence omits it honestly. The complete `DSH_*` namespace inside these children is managed by the harness: ambient values are removed, current trusted values are re-added, and ordinary callers cannot use `env` to bypass ownership checks.
+
+The namespace is discoverable but not secret. Paths can reveal configured roots, lazy targets can be absent or stale, and a command can override variables inside its own shell syntax. Consumers treat them as correlation and environment facts, verify transcript metadata when attribution matters, and rely on sandbox/filesystem policy rather than variable secrecy for authorization.

docs/rfc/implemented/feature/2026-07-10-session-query-service.md

@@ -4,13 +4,13 @@ Status: implemented
 
 ## Problem
 
-Session history exists in two places: current `SessionStore` objects and an optional persistence backend. Consumers that need exact inspection would otherwise duplicate live-versus-persisted precedence, persistence lifecycle handling, raw-event surface classification, and defensive cloning. Durable state can lag the live log between checkpoints, so persistence alone is not a truthful current source.
+Session history exists in two places: current `SessionStore` objects and an optional persistence backend. Consumers that need exact inspection would otherwise duplicate live-versus-persisted precedence, persistence lifecycle handling, raw-event surface classification, relationship tracing, and defensive cloning. Durable state can lag the live log between checkpoints, so persistence alone is not a truthful current source.
 
 Full-text search is related but materially larger. Designing provider registration, extraction, synchronization, invalidation, ranking, and cursor contracts before a real backend exists creates two speculative state machines: one in the interface service and another in the eventual database package.
 
 ## Decision
 
-`@deepseek-ai/dsh-session-query` owns `ctx.sessionQuery`, a small trusted exact-read service over one logical corpus. It exposes `listSessions()`, `listEvents(sessionId)`, and bounded `readEvent(request)`. It does not expose filters, lineage or provenance traversals, text extractors, search requests, provider registration, or derived-index synchronization.
+`@deepseek-ai/dsh-session-query` owns `ctx.sessionQuery`, a small trusted exact-inspection service over one logical corpus. It exposes `listSessions()`, `listEvents(sessionId)`, bounded `readEvent(request)`, `traceSession(sessionId)`, and `traceEvent(request)`. It does not expose filters, text extractors, search requests, provider registration, or derived-index synchronization. The separate [tracing decision](2026-07-13-session-query-tracing.md) owns lineage and event-relationship semantics.
 
 The service observes the optional `ctx.sessionPersistence` binding dynamically but retains no persisted cache or invalidation listener. Each cross-corpus list asks the active backend for authoritative metadata, then overlays a fresh live-store list. Matching ids become one `SessionRecord`: the live header wins and `live`/`persisted` independently report source availability. Immutable header disagreement is `SESSION_QUERY_SOURCE_CONFLICT`.
 
@@ -18,13 +18,13 @@ An exact target read first checks the live store and snapshots the live header a
 
 ## Surface semantics
 
-`dsh-session` exports `foldSurface(events)`, and `SurfaceManager` uses the same transition functions for its incremental cache. The fold returns detached current nodes and each replacement's actual removed seqs. `listEvents()` uses that result to classify every raw event as `current`, `shadowed`, or `log-only`, so inspection cannot disagree with model-history derivation about positional replacement semantics.
+`dsh-session` exports `foldSurface(events)`, and `SurfaceManager` uses the same transition functions for its incremental cache. The fold returns detached current event sequences and each replacement's actual removed seqs. `listEvents()` and `traceEvent()` use that result to classify every raw event, so inspection cannot disagree with model-history derivation about positional replacement semantics.
 
 `readEvent()` returns the complete target plus raw neighbors by contiguous seq. `before` and `after` default to zero and are independently bounded by `readWindowMax`, default 50. The result carries a cloned `SessionHeader`, not a source-availability record, because determining a live target's persisted flag would violate the guarantee that live exact reads do not depend on persistence health.
 
 ## Security boundary
 
-The service is context-wide trusted infrastructure, not an authorization layer. A future model-facing history tool or human UI applies explicit caller/session scope. This phase adds no model-facing tool and changes no transcript or snapshot surface.
+The service is context-wide trusted infrastructure, not an authorization layer. A future model-facing history tool or human UI applies explicit caller/session scope. The service adds no model-facing tool and changes no transcript or snapshot surface.
 
 ## Alternatives considered
 
@@ -32,10 +32,9 @@ The service is context-wide trusted infrastructure, not an authorization layer.
 - **Query only persistence** — rejected because checkpoints can lag the current live log.
 - **Cache persisted metadata and listen for writes/removals** — rejected because exact reads can ask the authoritative sources directly, while cache invalidation adds lifecycle and concurrency state before scale requires it.
 - **Define a provider-neutral search protocol now** — rejected because no provider consumes it. The first SQLite FTS package should own one reconciliation/transaction state machine; a smaller shared seam can be extracted later only when a second implementation proves the boundary.
-- **Include lineage, provenance, and generic filters in phase one** — rejected because no current consumer requires them and canonical logs remain sufficient to add them with evidence later.
 
 ## Consequences
 
-Phase one has one source-resolution state variable: the currently mounted persistence service. There are no provider queues, fingerprints, extractor registries, observation generations, or derived index updates. Exact reads remain usable in live-only deployments and deterministic when persistence is present.
+The service has one source-resolution state variable: the currently mounted persistence service. There are no provider queues, fingerprints, extractor registries, observation generations, or derived index updates. Exact reads and event traces remain usable in live-only deployments and deterministic when persistence is present.
 
-Cross-corpus listing and persisted exact reads perform backend I/O on each call. That is deliberate: correctness comes from current authoritative state, and scale-oriented search belongs to the phase-two database. Full-text search is unavailable until that package defines and implements its complete contract.
+Cross-corpus listing, lineage tracing, and persisted event operations perform backend I/O on each call. That is deliberate: correctness comes from current authoritative state, and scale-oriented search belongs to the proposed database package. Full-text search is unavailable until that package defines and implements its complete contract.

docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md

@@ -0,0 +1,34 @@
+# RFC: Session query relationship tracing
+
+Status: implemented
+
+## Problem
+
+Session relationships are encoded across immutable headers, positional surface operations, and logged provenance arrays. A consumer reconstructing those relationships directly would need to duplicate corpus precedence, surface folding, malformed-log handling, deterministic lineage ordering, and cloning. Positional replacement and provenance are different graphs, so collapsing them into one generic edge type would also lose meaning.
+
+## Decision
+
+`ctx.sessionQuery` exposes `traceSession(sessionId)` and `traceEvent({ sessionId, seq })` alongside its exact reads. Both are one-shot views over the existing live-preferred corpus: session tracing consumes one complete corpus listing, while event tracing consumes one loaded logical log and one canonical surface fold. The service retains no lineage, reverse-index, or replacement state after a call.
+
+`SessionLineageTrace` returns the target, known parents in immediate-to-outward order, and recursive descendant trees whose siblings sort by creation time and then session id. `complete: true` carries the known root; `complete: false` carries the first unresolved parent id. A cycle connected to the target fails with `SESSION_QUERY_INVALID_LINEAGE`.
+
+`SessionEventTrace` keeps positional and provenance relationships separate. `replacedBy` is the immediate positional replacer, `replacementChain` follows replacers to the final node, and `replacedEventSeqs` lists the actual surface nodes directly removed by the target. `sourceEventSeqs` preserves direct logged source order, while `derivedEventSeqs` lists later direct reverse references in log order. Provenance is not expanded transitively.
+
+## Validation boundary
+
+Event tracing checks target existence before surface analysis. Both event listing and tracing then use `dsh-session`'s one-pass surface fold, which accepts or rejects the loaded log as a whole: event seqs are zero-based and contiguous, surface markers obey event-type eligibility, provenance belongs only to surface event types, present arrays are nonempty and duplicate-free, every source is an earlier seq, and every positional replacement names and cites all surface nodes it removes. Every contract failure uses `SESSION_QUERY_INVALID_SURFACE`; there is no weaker classification-only surface standard.
+
+All returned records and arrays are detached. A known live event trace never consults persistence; persisted event traces preserve the exact-read list/load consistency check. Session lineage is necessarily a cross-corpus operation and therefore preserves cross-corpus persistence failure semantics.
+
+## Alternatives considered
+
+- **Expose standalone tracing helpers** — rejected because the source-precedence and detachment boundary belongs to `ctx.sessionQuery`; public helpers would invite callers to bypass it.
+- **Combine replacement and provenance edges** — rejected because a positional replacement can shadow surface nodes while also citing non-surface construction inputs, and consumers need to distinguish those meanings.
+- **Return transitive provenance closure** — rejected because it obscures logged direct evidence, increases result size, and lets one malformed distant edge alter otherwise local output.
+- **Best-effort traces over malformed provenance** — rejected because a structurally plausible partial graph would look authoritative. Exact inspection fails loudly when the canonical relationship contract is broken.
+
+## Consequences
+
+Consumers receive deterministic relationship views without a cache or second corpus. Event tracing performs whole-log validation and allocation on each call, while lineage tracing lists the complete logical corpus on each call. Those costs keep the source of truth explicit and are separate from the content-bearing full-text-search and filtering API.
+
+The feature has unit and service-level coverage but no snapshot or end-to-end fixture because it introduces no model-facing consumer, transcript change, or cross-process protocol.

docs/rfc/implemented/feature/2026-07-14-time-context-plugin.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-2026-07-14-time-context-plugin.md: 105bf53550f087fdefb1e6fe0ec493f8628d3e18
-2026-07-14-time-context-plugin.zh.md: 60e9004b1453e75e1bcd84870ad7f18d200a95d8
+2026-07-14-time-context-plugin.md: b8b54156e08aa1212866d46500ad1ca65b4f4f14
+2026-07-14-time-context-plugin.zh.md: 0af261c66a9b52cdf250294b4bfdc240176c8434

docs/rfc/implemented/feature/2026-07-14-time-context-plugin.md

@@ -6,6 +6,8 @@ English | [中文](2026-07-14-time-context-plugin.zh.md)
 
 ## Problem
 
+The dynamic system-prompt storage and refresh decision in this record is superseded by [Durable per-step time context](2026-07-16-durable-per-step-time-context.md). The opt-in package, zoned formatting, and validation remain; the follow-up owns the current model-visible and durability contract.
+
 An agent request has no live clock unless a deployment puts one in prompt text or gives the model a query tool. Static text becomes stale, while a tool call adds overhead to ordinary reasoning about dates, deadlines, or idle time. Without elapsed time, the model cannot distinguish an immediate follow-up from one sent hours after the preceding message.
 
 Prompt assembly can derive both facts per step from durable session timestamps, and request-header logging can record the exact rendered value. Accumulating stale readings in conversation history or waking idle agents would violate the existing request lifecycle.
@@ -30,11 +32,11 @@ When `timeZone` is omitted, `Intl.DateTimeFormat` resolves the Node process's sy
 
 ### Logging and token shape
 
-The loop records the temporal block through `request/header` and `request/header-delta` before transmission, satisfying the [reconstructable-requests contract](../architecture/2026-07-05-reconstructable-requests.md). Each request carries one current block; earlier readings do not remain in conversation history. The plugin owns the fact and contributes it through the prompt registry, following the [prompt-variables RFC](../architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md) without a loop special case.
+The loop records the temporal block in full `request/header` snapshots before transmission, satisfying the [reconstructable-requests contract](../architecture/2026-07-05-reconstructable-requests.md). Each request carries one current block; earlier readings do not remain in conversation history. The plugin owns the fact and contributes it through the prompt registry, following the [prompt-variables RFC](../architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md) without a loop special case.
 
 ## Testing
 
-Unit tests pin formatting, baselines, refresh policy, validation, per-agent state, disposal, and load-time system-zone capture. A real agent-loop test pins the transmitted prompt and `request/header-delta`. A keyless subprocess e2e boots a test-only `cordis.yml` through the real Loader and stdio app, omits `timeZone` under a controlled `TZ`, drives two turns, and verifies the persisted request headers externally. Default snapshot compositions omit the plugin, so their transcript fixtures contain no temporal block.
+Unit tests pin formatting, baselines, refresh policy, validation, per-agent state, disposal, and load-time system-zone capture. A real agent-loop test pins the transmitted prompt and full `request/header` snapshots. A keyless subprocess e2e boots a test-only `cordis.yml` through the real Loader and stdio app, omits `timeZone` under a controlled `TZ`, drives two turns, and verifies the persisted request headers externally. Default snapshot compositions omit the plugin, so their transcript fixtures contain no temporal block.
 
 ## Alternatives considered
 
@@ -52,6 +54,6 @@ Unit tests pin formatting, baselines, refresh policy, validation, per-agent stat
 
 - Opted-in models receive a zoned clock and inter-turn duration without a tool call. The system-prompt cost is fixed per request instead of growing with the session.
 - An omitted `timeZone` follows the process's `TZ`, host, or container zone as observed at plugin load. Operators must configure an explicit zone when the deployment environment does not represent the intended user.
-- A refresh changes the request header and can add a `request/header-delta`. `refreshIntervalMs` trades freshness against durable deltas; `0` records a new value on every step whose whole-second rendering changes.
+- A refresh changes the request header and can add a full `request/header` snapshot with reason `change`. `refreshIntervalMs` trades freshness against the number and size of durable full snapshots; `0` records a new value on every step whose whole-second rendering changes.
 - No request exists solely to refresh time. A long-running tool leaves the prior reading until the next step assembles.
 - Duration reflects harness processing time at durable append boundaries, not client-network latency before logging. Preserving a client-origin timestamp requires a separate durable input contract.

docs/rfc/implemented/feature/2026-07-14-time-context-plugin.zh.md

@@ -6,13 +6,15 @@ Status: implemented
 
 ## 问题
 
+本记录中的动态系统提示词存储和刷新决策已由[持久的逐步骤时间上下文](2026-07-16-durable-per-step-time-context.md)取代。需要显式启用的包（package）、分区时间格式和校验仍然保留；后续 RFC 负责当前的模型可见与持久性契约。
+
 如果部署方既未在提示词中提供时钟，也未给模型提供查询工具，agent（智能体）请求就无法获得实时准确的时间。静态文本会变得陈旧，而对于日期、截止时间或闲置时长等常规推理，调用工具会增加开销。缺少已经过去的时长时，模型无法区分紧接着发送的消息与上一条消息几小时后才发送的消息。
 
 提示词组装流程可以在每个步骤中根据持久会话时间戳派生这两项信息，请求头日志则可以记录实际渲染的确切值。在会话历史中累积陈旧读数或唤醒空闲 agent 都会违反现有请求生命周期。
 
 ## 决策
 
-`@deepseek-ai/dsh-time-context` 是位于 `packages/context/time-context/`、需要显式启用的函数插件。`context/` 产品分组用于容纳既不定义工具、也不定义服务的有界请求上下文增强。`dsh-agent-spine-demo` 和仓库提供的示例都不会加载该 package；只有当 token 与信息披露成本可接受时，部署方才显式挂载它。
+`@deepseek-ai/dsh-time-context` 是位于 `packages/context/time-context/`、需要显式启用的函数插件。`context/` 产品分组用于容纳既不定义工具、也不定义服务的有界请求上下文增强。`dsh-agent-spine-demo` 和仓库提供的示例都不会加载该包；只有当 token 与信息披露成本可接受时，部署方才显式挂载它。
 
 该插件注册顺序值为 10 的全局系统提示词区段 `context:time`，位置在部署方角色设定之后、工具指导之前。对于活跃轮次，它会输出带数字 UTC 偏移和 IANA 时区、形似 ISO 的时间戳，以及从轮次开始前最后一条模型可见消息起算的紧凑整秒时长。未绑定 agent 或 agent 处于空闲状态时，该区段为空。
 
@@ -30,11 +32,11 @@ Status: implemented
 
 ### 日志与 token 形态
 
-agent loop（智能体循环）会在发送前通过 `request/header` 和 `request/header-delta` 记录时间区块，从而满足[可重建请求契约](../architecture/2026-07-05-reconstructable-requests.md)。每个请求只携带一个当前区块；先前的读数不会保留在会话历史中。该插件拥有时间信息，并按照[提示词变量 RFC](../architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)通过提示词注册表贡献该信息，无需为循环添加特殊分支。
+agent loop（智能体循环）会在发送前通过完整的 `request/header` 快照记录时间区块，从而满足[可重建请求契约](../architecture/2026-07-05-reconstructable-requests.md)。每个请求只携带一个当前区块；先前的读数不会保留在会话历史中。该插件拥有时间信息，并按照[提示词变量 RFC](../architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)通过提示词注册表贡献该信息，无需为循环添加特殊分支。
 
 ## 测试
 
-单元测试固定格式化、基线、刷新策略、校验、逐 agent 状态、资源释放行为，以及系统时区在加载时的捕获行为。使用真实 agent loop 的测试固定实际发送的提示词和 `request/header-delta`。无密钥子进程端到端测试通过真实 Loader 和 stdio 应用启动测试专用 `cordis.yml`，在受控 `TZ` 下省略 `timeZone`，驱动两个轮次，并从外部校验持久请求头。默认快照组合不包含该插件，因此其中的 transcript（文本记录）fixture（测试前置数据）不包含时间区块。
+单元测试固定格式化、基线、刷新策略、校验、逐 agent 状态、资源释放行为，以及系统时区在加载时的捕获行为。使用真实 agent loop 的测试固定实际发送的提示词和完整的 `request/header` 快照。无密钥子进程端到端测试通过真实 Loader 和 stdio 应用启动测试专用 `cordis.yml`，在受控 `TZ` 下省略 `timeZone`，驱动两个轮次，并从外部校验持久请求头。默认快照组合不包含该插件，因此其中的 transcript（文本记录）fixture（测试前置数据）不包含时间区块。
 
 ## 考虑过的替代方案
 
@@ -46,12 +48,12 @@ agent loop（智能体循环）会在发送前通过 `request/header` 和 `reque
 - **省略配置时仍默认使用 UTC**——不予采纳，因为显式启用的时钟应跟随部署环境，除非运维方选择 UTC。需要 UTC 的部署仍可配置 `timeZone: UTC`。
 - **引入时区探测库**——不予采纳，因为 Node 的 `Intl` 运行时已经能够提供进程的 IANA 时区，而且额外依赖同样无法推断远程用户的时区。
 - **在 `dsh-agent-spine-demo` 中挂载插件**——不予采纳，因为时区、信息披露、token 预算和新鲜度都属于部署策略。选择加入能保持默认上下文稳定。
-- **将 package 放入 `core/`**——不予采纳，因为 `core/` 负责产品 API 主干，而该插件是没有服务键的可选叶节点。
+- **将包放入 `core/`**——不予采纳，因为 `core/` 负责产品 API 主干，而该插件是没有服务键的可选叶节点。
 
 ## 后果
 
 - 选择加入的模型无需调用工具，即可获得分区时钟和轮次间隔时长。每个请求的系统提示词成本固定，不会随会话增长。
 - 省略 `timeZone` 时，插件采用加载时观察到的进程 `TZ`、主机或容器时区。当部署环境不能代表目标用户时，运维方必须显式配置时区。
-- 刷新会改变请求头，并可能新增 `request/header-delta`。`refreshIntervalMs` 用新鲜度换取持久增量记录的数量；设为 `0` 时，每个整秒渲染结果发生变化的步骤都会记录新值。
+- 刷新会改变请求头，并可能新增一份 reason 为 `change` 的完整 `request/header` 快照。`refreshIntervalMs` 用新鲜度换取完整持久快照的数量与大小；设为 `0` 时，每个整秒渲染结果发生变化的步骤都会记录新值。
 - 系统不会仅为刷新时间而创建请求。长时间运行的工具会保留先前读数，直至下一步骤开始组装。
 - 时长反映持久追加边界处的 harness 处理时间，不包含消息进入日志之前的客户端网络延迟。若要保留客户端来源时间戳，需要单独的持久输入契约。

docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-16-durable-per-step-time-context.md: 4a0828111faf9f787c2d338024c42680a4a697e2
+2026-07-16-durable-per-step-time-context.zh.md: f745cf7da7c38f9682abf9d8f210bcba328c8a51

docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.md

@@ -0,0 +1,70 @@
+# RFC: Durable per-step time context
+
+Status: implemented
+
+English | [中文](2026-07-16-durable-per-step-time-context.zh.md)
+
+## Problem
+
+A request-only clock can tell the model the current time, but replacing that value in the system prompt removes the evidence behind earlier time-sensitive reasoning. Multi-step turns need requests to retain the readings that shaped preceding steps. The request must remain reconstructable after restart, and automatic compaction must account for the same timing context the model receives.
+
+A process-local refresh cache makes displayed time depend on state that cannot survive resume or be reconstructed from the durable session. Durable interval scheduling can reduce append frequency without introducing that hidden state.
+
+## Decision
+
+`@deepseek-ai/dsh-time-context` is an opt-in function plugin in `packages/context/time-context/`. It registers a prepended `agent/pre-step` listener and, when an injection is due, calls `agent.inject()` for a pre-step attempt whose signal is not already aborted. The injected `context/message` carries source `{ kind: 'plugin', plugin: 'time-context' }` and append surface metadata; a suppressed attempt appends nothing.
+
+The listener records preparation context before a possible `step/start`. Its prepended registration runs before ordinary automatic compaction listeners, so pressure estimation and any resulting surface rewrite observe a newly appended reading. A later pre-step listener can cancel or fail the attempt before the step opens; the reading remains because the durable log is append-only and this plugin performs no rollback.
+
+The optional `timeZone` config resolves the Node process's IANA zone once at plugin load when omitted; an explicit value is validated by `Intl.DateTimeFormat`. The timestamp includes the numeric UTC offset and resolved IANA zone.
+
+The optional `refreshIntervalMs` config is manually validated at plugin load as a non-negative safe integer. Omission or `0` injects on every eligible preparation attempt. A positive value scans the raw session events for the most recent `context/message` with this plugin's source and injects when none exists, wall time moved backward, or the event is at least the configured age. The raw event timestamp governs even after compaction shadows the message, so scheduling persists across turns and process resume without a timer or process-local cache.
+
+### Text and elapsed baselines
+
+An injected first-step reading is:
+
+```text
+Time sampled while preparing turn <turn>, step 1: <timestamp>
+Elapsed since the preceding model-visible message: <duration-or-unavailable>.
+```
+
+The baseline is the latest preceding user, assistant, tool-result, context, or steering message. This includes the accepted prompt that opened an ordinary message turn. If no model-visible message exists, the duration is `unavailable`.
+
+An injected later-step reading is:
+
+```text
+Time sampled while preparing turn <turn>, step <step>: <timestamp>
+Elapsed since the preceding step context: <duration-or-unavailable>.
+```
+
+Their baseline is the durable event timestamp of the preceding time-context message in the same turn. If interval suppression leaves no earlier same-turn reading, the duration is `unavailable`. Duration formatting uses compact whole-second units and clamps backward wall-clock movement to zero. The explicit turn and step make every retained reading attributable to its historical preparation attempt after later turns append more context.
+
+### Durability and request reconstruction
+
+Each reading remains a normal surface node until compaction shadows it; positive interval scheduling never removes existing readings. A later request therefore sees the cumulative unshadowed readings that affected earlier preparation and steps, rather than a system-prompt value rewritten in place.
+
+The plugin contributes nothing to system-prompt assembly. `request/header` contains no time-context text; request reconstruction obtains the complete durable surface prefix at each `step/start`. Readings and requests need not map one-to-one because a failed preparation can leave a reading while interval suppression can prepare a request without appending one. The plugin depends on the agent registry for its lifecycle listener and does not require the system-prompt service at runtime.
+
+## Testing
+
+Unit and real-loop tests pin formatting, both elapsed baselines, interval omission and zero, threshold boundaries, cross-turn and per-session scheduling, backward-clock behavior, invalid config, resumed raw-event lookup after compaction, aborted-signal behavior, later-listener cancellation and failure, listener disposal, source and surface metadata, cumulative multi-step visibility, and absence from request headers. A keyless subprocess e2e boots the real Loader and stdio app, drives two turns, and verifies the persisted context events externally.
+
+## Supersedes
+
+This decision supersedes the dynamic system-prompt storage and refresh policy in [Optional time-context plugin](2026-07-14-time-context-plugin.md). It keeps the package location, opt-in deployment stance, timestamp formatting, process-zone default, and load-time validation. Durable history replaces the `context:time` prompt section, process-local refresh cache, and request-header deltas; `refreshIntervalMs` controls durable append frequency instead of prompt replacement.
+
+## Alternatives considered
+
+- **Keep the dynamic system-prompt section and process-local refresh cache** — rejected because replacement erases earlier readings, cache state is not replayable, and a frozen request envelope would make the value stale for an entire loop instance.
+- **Replace the preceding context surface node** — rejected because replacement preserves the old node's position or shadows intervening conversation; neither represents when the new reading became visible.
+- **Inject from a background timer** — rejected because idle time has no pending request to consume the value, and timer-driven injection would create durable turns solely to report time passing.
+- **Expose time only through a tool** — rejected because ordinary temporal reasoning would require an avoidable tool round trip and would not guarantee a reading before every step.
+- **Use `agent/session-prefix`** — rejected because one loop-instance prefix cannot represent distinct step timestamps and does not accumulate historically attributable readings.
+
+## Consequences
+
+- Omission or `0` records every eligible preparation attempt; a positive interval reduces append frequency and history growth while preserving durable scheduling across resume.
+- Timing context remains append-only until compaction shadows older surface nodes, including a preparation reading left by a later cancellation or failure.
+- The first-step duration normally measures from the prompt that opened the turn, while later-step durations measure model and tool processing since the preceding step context.
+- An omitted `timeZone` still reflects the deployment process rather than a remote user, and elapsed time still uses durable harness append boundaries rather than client-origin timestamps.

docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.zh.md

@@ -0,0 +1,70 @@
+# RFC: 持久的逐步骤时间上下文
+
+Status: implemented
+
+[English](2026-07-16-durable-per-step-time-context.md) | 中文
+
+## 问题
+
+仅存在于请求中的时钟可以告诉模型当前时间，但在系统提示词中替换这个值会移除先前时效性推理所依据的证据。在包含多个步骤的轮次中，请求需要保留影响先前步骤的读数。系统必须能在重启后重建请求，自动压缩（compaction）也必须核算模型实际收到的同一份时间上下文。
+
+进程本地刷新缓存使显示的时间依赖无法在恢复后保留、也无法从持久会话重建的状态。持久的间隔调度可以减少追加频率，而不引入这种隐藏状态。
+
+## 决策
+
+`@deepseek-ai/dsh-time-context` 是位于 `packages/context/time-context/`、需要显式启用的函数插件。它注册一个前置的 `agent/pre-step` 监听器，并在需要注入时，为信号尚未取消的预步骤尝试调用 `agent.inject()`。注入的 `context/message` 携带来源 `{ kind: 'plugin', plugin: 'time-context' }` 和追加表层元数据；受间隔抑制的尝试不会追加任何内容。
+
+监听器在可能出现的 `step/start` 之前记录准备上下文。它采用前置注册，因此先于普通自动压缩监听器运行，使压力估算和由此产生的表层重写都能观察到新追加的读数。后续预步骤监听器可能在步骤开启前取消尝试或使其失败；持久日志仅追加，且本插件不执行回滚，因此该读数会保留下来。
+
+省略可选配置 `timeZone` 时，插件在加载时解析一次 Node 进程的 IANA 时区；显式值由 `Intl.DateTimeFormat` 校验。时间戳包含数字 UTC 偏移和解析后的 IANA 时区。
+
+插件在加载时手动校验可选配置 `refreshIntervalMs`，其值必须为非负安全整数。省略或设为 `0` 时，每次符合条件的准备尝试都会注入。设为正数时，插件扫描原始会话事件，查找来源属于本插件的最新 `context/message`；不存在此类事件、系统挂钟向后移动，或该事件已达到配置时长时，插件执行注入。即使压缩已隐藏消息，调度仍以原始事件时间戳为准，因此该机制无需计时器或进程本地缓存，也能跨轮次和进程恢复持续生效。
+
+### 文本与时长基线
+
+第一个步骤的注入读数为：
+
+```text
+Time sampled while preparing turn <turn>, step 1: <timestamp>
+Elapsed since the preceding model-visible message: <duration-or-unavailable>.
+```
+
+基线是前一条用户消息、助手消息、工具结果、上下文消息或 steering（中途引导）消息。对于普通消息轮次，这包括开启轮次的已接受提示词。如果不存在模型可见消息，时长为 `unavailable`。
+
+后续步骤的注入读数为：
+
+```text
+Time sampled while preparing turn <turn>, step <step>: <timestamp>
+Elapsed since the preceding step context: <duration-or-unavailable>.
+```
+
+其基线是同一轮次中上一条时间上下文消息的持久事件时间戳。如果间隔抑制导致同一轮次中没有更早的读数，时长为 `unavailable`。时长采用紧凑的整秒单位，并在系统挂钟向后移动时钳制为零。显式的轮次号和步骤号使每个保留的读数在后续轮次追加更多上下文后，仍可归属于对应的历史准备尝试。
+
+### 持久性与请求重建
+
+每个读数都作为普通表层节点保留，直至压缩将其隐藏；正数间隔调度绝不会移除已有读数。因此，后续请求会看到影响先前准备过程和步骤且尚未被隐藏的累计读数，而不是一个被原地改写的系统提示词值。
+
+插件不向系统提示词组装贡献任何内容。`request/header` 不包含时间上下文文本；请求重建从每个 `step/start` 取得完整的持久表层前缀。读数与请求无需一一对应，因为失败的准备过程可能留下读数，而间隔抑制也可能使请求准备过程不追加读数。插件通过 agent 注册表使用生命周期监听器，运行时不需要系统提示词服务。
+
+## 测试
+
+单元测试和真实 agent loop（智能体循环）测试固定格式化、两种时长基线、间隔省略和零值、阈值边界、跨轮次和各会话独立调度、挂钟后退行为、无效配置、压缩后基于恢复会话的原始事件查找、已取消信号行为、后续监听器取消和失败、监听器 dispose（资源释放）、来源与表层元数据、多步骤累计可见性，以及请求头中不存在时间上下文。无密钥子进程 e2e 测试通过真实 Loader 和 stdio 应用启动，驱动两个轮次，并从外部校验持久化的上下文事件。
+
+## 取代的决策
+
+本决策取代[可选时间上下文插件](2026-07-14-time-context-plugin.md)中的动态系统提示词存储和刷新策略。它保留包位置、选择加入式部署、时间戳格式、进程时区默认值和加载时校验。持久历史取代 `context:time` 提示词区段、进程本地刷新缓存和请求头增量；`refreshIntervalMs` 用于控制持久追加频率，而非提示词替换。
+
+## 考虑过的替代方案
+
+- **保留动态系统提示词区段和进程本地刷新缓存**——不予采纳，因为替换会抹去先前读数，缓存状态无法回放，而且冻结的请求内容集合会使该值在整个 agent loop 实例期间保持陈旧。
+- **替换前一条上下文表层节点**——不予采纳，因为替换会保留旧节点的位置或隐藏中间的会话内容；两者都不能表达新读数何时开始可见。
+- **通过后台计时器注入**——不予采纳，因为空闲期间没有待处理请求消费该值，而且计时器驱动的注入会仅为报告时间流逝而创建持久轮次。
+- **只通过工具提供时间**——不予采纳，因为普通时间推理会产生本可避免的工具往返，也不能保证每个步骤之前都有读数。
+- **使用 `agent/session-prefix`**——不予采纳，因为一个 loop 实例前缀无法表示不同的步骤时间戳，也不会累计具有历史归属的读数。
+
+## 后果
+
+- 省略 `refreshIntervalMs` 或设为 `0` 时，每次符合条件的准备尝试都会留下记录；正数间隔会减少追加频率和历史增长，同时使持久调度在恢复后继续生效。
+- 时间上下文仅追加并保留到压缩隐藏旧表层节点为止，其中也包括后续取消或失败所留下的准备读数。
+- 第一个步骤的时长通常从开启轮次的提示词起算，后续步骤的时长则反映自上一条步骤上下文以来的模型与工具处理时间。
+- 省略 `timeZone` 时仍采用部署进程而非远程用户的时区，时长仍采用 harness 的持久追加边界而非客户端来源时间戳。

docs/rfc/implemented/process/2026-07-06-parallel-pre-push-gates.md

@@ -14,9 +14,9 @@ Flattening those members directly into `lefthook.yml` solves the local hook only
 
 [lefthook.yml](../../../../lefthook.yml) keeps one pre-push job named `full check` and runs `pnpm run check:pre-push`. That package script delegates to [scripts/run-gates.ts](../../../../scripts/run-gates.ts), the same bounded scheduler CI uses.
 
-The `pre-push` mode expands into leaf gates for the unit suite, snapshot suite, build, `hygiene` members, `doc-sync` members, and module-graph freshness. The leaf list keeps the same gate vocabulary as the package scripts, including RFC classification and RFC format, while the runner schedules independent checks concurrently and prints one timing/output block per gate.
+The `pre-push` mode expands into leaf gates for the unit suite, snapshot suite, build, `hygiene` members, `doc-sync` members, and module-graph freshness. The leaf list keeps the same gate vocabulary as the package scripts, including RFC classification and RFC format, while the runner schedules independent checks with four active top-level workers by default; `DSH_GATE_CONCURRENCY` overrides that bound.
 
-The build gate makes the hook self-contained from a clean worktree. `publint` and `verify-node-next-types` wait for that build output, while source-only gates continue in parallel.
+The build gate makes the hook self-contained from a clean worktree. `publint`, `verify-node-next-types`, and the pre-push form of `doc-typecheck` wait for that build output, while source-only gates continue in parallel.
 
 [scripts/publint-all.ts](../../../../scripts/publint-all.ts) discovers the package list from `packages/<group>/<pkg>` and runs `publint` with a worker pool sized from `availableParallelism()`. `DSH_PUBLINT_CONCURRENCY` can cap or raise the worker count for local machines and CI runners with different resource profiles. Results are buffered per package and printed in deterministic package order, so parallel execution does not scramble each package's log block.
 

docs/rfc/implemented/process/2026-07-17-run-ci-examples-from-built-lib.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-17-run-ci-examples-from-built-lib.md: aae88ee965b4e2211f3a53aeb9c0ee4944d95c2a
+2026-07-17-run-ci-examples-from-built-lib.zh.md: 0cd3822a71b8f7399be93beaac74b2177fcbe7ca

docs/rfc/implemented/process/2026-07-17-run-ci-examples-from-built-lib.md

@@ -0,0 +1,42 @@
+# RFC: Run CI examples from built lib
+
+Status: implemented
+
+English | [中文](2026-07-17-run-ci-examples-from-built-lib.zh.md)
+
+## Problem
+
+CI boots examples and Cordis-backed test projects through `node --import tsx` and the root tsconfig `paths` map. This adds TypeScript transformation cost and changes package resolution: imports resolve to workspace source instead of following package `exports` into built `lib/`.
+
+These runs therefore do not test the same code or resolution behavior as an installed consumer. A package can pass CI while its built export graph is incomplete or resolves differently.
+
+## Decision
+
+Execution has two modes. `src` is the default local-development mode and uses tsx; `lib` is the strict CI mode and starts built bins with plain Node, without tsx or tsconfig path mapping.
+
+- CI subprocesses that boot an example or a checked-in `cordis.yml` use `lib` mode.
+- TypeScript fixtures that only implement an ACP or MCP peer and do not load Cordis run directly with Node. An explicit source-path regression may remain in `src` mode.
+
+### Resolution topology
+
+Every test Cordis config must resolve its bare modules by walking upward from the config directory.
+
+- `examples/` is one pnpm workspace member and provides the shared `examples/node_modules` resolution root.
+- Every checked-in test Cordis config, including snapshot configs and package-owned fixtures, lives under its corresponding `examples/<agent>/` tree. A config owned by `packages/<group>/<package>/` maps to `examples/<agent>/tests/fixtures/<group>/<package>/cordis.yml`; the test driver and assertions remain package-local.
+- Every package named by an example Cordis config is declared in both `examples/package.json` for `lib` resolution and the root `tsconfig.json` references for `src` mode.
+
+### Launch policy
+
+The shared Loader test harness selects `src` or `lib` from `DSH_EXAMPLE_MODE`. CI builds first and selects `lib`; an unset mode keeps the fast local source loop.
+
+## Alternatives considered
+
+- **Keep CI on tsx** — rejected because it preserves transformation overhead and source-only resolution behavior.
+- **Use lib everywhere** — rejected because local development would require a build before every run. Dual mode keeps that cost out of the development loop.
+- **Build a private `node_modules` tree per test** — rejected because it duplicates consumer scaffolding. The `examples/` workspace root gives every Cordis config one real and declared resolution path.
+
+## Consequences
+
+- CI validates built package exports without tsx changing module resolution; local development retains the no-build source loop.
+- CI must build before these tests, and manual `lib` runs can observe stale local artifacts.
+- Cordis config dependencies are not visible to normal TypeScript import analysis, so `examples/package.json` and the root tsconfig references must stay synchronized with the configs.

docs/rfc/implemented/process/2026-07-17-run-ci-examples-from-built-lib.zh.md

@@ -0,0 +1,42 @@
+# RFC: 在 CI 中从构建后的 lib 运行示例
+
+Status: implemented
+
+[English](2026-07-17-run-ci-examples-from-built-lib.md) | 中文
+
+## 问题
+
+CI 通过 `node --import tsx` 和根 tsconfig 的 `paths` 映射启动示例与加载 Cordis 配置的测试项目。这种方式既增加了 TypeScript 转换开销，也改变了包解析行为：import 会解析到 workspace 源码，而不是经包的 `exports` 进入构建后的 `lib/`。
+
+因此，这些测试没有覆盖已安装消费方实际运行的代码和解析路径。即使包的构建导出图不完整或解析结果不同，CI 仍可能通过。
+
+## 决策
+
+执行机制包含两种模式。`src` 是本地开发的默认模式并使用 tsx；`lib` 是严格的 CI 模式，通过 plain Node 启动构建后的 bin，不加载 tsx，也不使用 tsconfig 路径映射。
+
+- CI 中启动示例或签入仓库的 `cordis.yml` 的子进程使用 `lib` 模式。
+- 仅实现 ACP 或 MCP 对端、且不加载 Cordis 的 TypeScript fixture（测试前置数据）直接由 Node 运行。只有显式验证源码路径的回归测试可以保留 `src` 模式。
+
+### 解析拓扑
+
+每个测试 Cordis 配置都必须能从配置文件所在目录向上解析裸模块。
+
+- `examples/` 作为一个 pnpm workspace 成员，提供统一的 `examples/node_modules` 解析根目录。
+- 所有签入仓库的测试 Cordis 配置，包括快照配置和包内测试 fixture，都放在对应的 `examples/<agent>/` 目录树下。归属 `packages/<group>/<package>/` 的配置映射到 `examples/<agent>/tests/fixtures/<group>/<package>/cordis.yml`；测试驱动和断言仍留在包内。
+- 示例 Cordis 配置中引用的每个包都同时登记在 `examples/package.json` 和根 `tsconfig.json` 的 references 中，分别支持 `lib` 与 `src` 解析。
+
+### 启动策略
+
+共享 Loader 测试 harness 通过 `DSH_EXAMPLE_MODE` 选择 `src` 或 `lib`。CI 先构建再选择 `lib`；未设置模式时保留快速的本地源码开发回路。
+
+## 曾考虑的替代方案
+
+- **CI 继续使用 tsx**：不予采纳，因为它会保留转换开销和仅适用于源码的解析行为。
+- **所有环境只使用 lib**：不予采纳，因为本地开发每次运行前都必须构建。双模式避免把这项成本带入开发回路。
+- **每个测试单独构造 `node_modules`**：不予采纳，因为它会重复消费方脚手架。以 `examples/` 作为 workspace 根，可让每个 Cordis 配置通过同一条真实且显式声明的路径解析模块。
+
+## 后果
+
+- CI 可以验证构建后的包导出，不再受 tsx 模块解析影响；本地开发仍保留免构建的源码回路。
+- CI 必须先构建再运行这些测试；手动执行 `lib` 模式时可能读取陈旧的本地产物。
+- 常规 TypeScript import 分析无法识别 Cordis 配置依赖，因此 `examples/package.json`、根 tsconfig references 与配置文件必须保持同步。

docs/rfc/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md

@@ -35,7 +35,7 @@ This RFC decided the four-layer split, the provider contract, and the freshness
 `@deepseek-ai/dsh-fs` shrinks to provider text IO plus guarded text mutation:
 
 ```ts ignore-check
-abstract resolve(path: string): Promise<FsTarget>
+abstract resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise<FsTarget>
 abstract stat(target: FsTarget, signal?: AbortSignal): Promise<FsInfo | undefined>
 abstract readText(target: FsTarget, signal?: AbortSignal): Promise<string>
 abstract streamText(target: FsTarget, signal?: AbortSignal): Promise<AsyncIterable<string>>

docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md

@@ -0,0 +1,33 @@
+# RFC: Simplify session-log representation
+
+Status: implemented
+
+## Problem
+
+The session log maintains two representations that cost more machinery than their consumers require: a pseudo-linked surface and custom request-header deltas.
+
+`SurfaceManager` stores the same order in an array, a seq map, and mutable `prev`/`next` links. Production never reads either link: compact's tool-pairing balance answers from per-cut balances cached in surface order. Replacement already uses `indexOf`, so the links do not make its dominant operation constant-time. A seq array with linear replacement lookup has the same asymptotic replacement cost and one representation to validate.
+
+The request-header subsystem implements a custom system/tool delta codec and transmission-decision layer even though its contract says deltas are an encoding optimization, not a reconstructability requirement. Retaining the initial/resume full snapshot at each loop-instance boundary, then writing a canonical full `request/header` whenever that instance's assembled header changes, preserves replay while deleting `SystemDelta`, `ToolsDelta`, round-trip fallback, and the durable `request/header-delta` variant. Codec-only vocabulary disappears with the codec, not because its individual arms were invalid.
+
+The implementation retains append and replacement `sourceEventSeqs`, crash-repair provenance, and all `SessionStartSource` variants because those fields have an audit/interception role that zero current readers does not overturn.
+
+## Decision
+
+`SurfaceManager.nodes` is a `readonly number[]` of event sequences; the public `SurfaceNode` shape, node links, and seq-to-node map are removed. The internal replace-generation signal remains. The complete `foldSurface()` read used by session-query returns the same number-array representation plus replacement metadata without making the incremental manager retain history. Tool-pairing balance and compaction use event sequences and surface positions; the compact-owned per-cut balance cache does not depend on node links.
+
+Request headers use canonical full snapshots only. Initial and resume anchors remain full snapshots even when unchanged; an in-instance change appends another full `request/header` with reason `change`. The delta event, codec types, diff/apply helpers, and codec-only `fallback` reason are removed. Request reconstruction selects the latest snapshot.
+
+`SESSION_FORMAT_VERSION` remains pinned at `0`, so seed, append, and persistence-load validation explicitly reject old v0 `request/header-delta` events and full snapshots carrying the removed `fallback` reason. There is no compatibility fold or migration. JSONL and SQLite tests pin this fail-loud boundary, and the ACP snapshot harness represents legitimate mid-session changes as full pinned headers and full readable prompts.
+
+## Alternatives considered
+
+**Keep linked nodes and compact deltas for possible scale.** Links could help a future cursor API, and deltas can reduce logs when large tool schemas change by a small amount. No shipped cursor uses the links, while full snapshots trade disk size for substantially simpler correctness. If header volume proves material, compression or a measured canonical-delta scheme can be designed around real traces.
+
+## Verification
+
+Unit coverage pins ordered-surface append/replace behavior, tool pairing, compaction, full-header folding/logging, request reconstruction, and dev invariants. Seed validation plus JSONL and SQLite load tests reject the legacy event before replay. The keyless ACP suite exercises record, refresh, replay, changed-header pinning, and the sandbox mode-switch fixture in the new shape.
+
+## Consequences
+
+Full headers increase log volume, and linear replacement lookup could be slower on very large surfaces. Replacements were already linear because the prior implementation called `indexOf`; benchmarks are deferred until real traces show the simpler array is a bottleneck. The format version remains `0`, so explicit legacy-event rejection is a permanent part of the pre-release format boundary. In return, surface order and request-header state each have one representation, deleting link maintenance, maps, codec arms, round-trip fallback, and delta-aware snapshot normalization.

docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md

@@ -8,11 +8,11 @@ An ACP snapshot suite needs to prove the exact composed system prompt and tool-s
 
 ## Decision
 
-Exactly one scenario per header-composition class is flagged `pinsHeader`. Its directory splits the pin by review format: `system-prompt.golden.md` contains the normalized composed prompt as ordinary Markdown, `tool-schemas.golden.json` contains the complete initial schemas and later schema edits as structured JSON, and `session.jsonl` retains config, reason, and any model-visible prefix while storing `header.system` and `header.tools` as `"{{system}}"` / `"{{tools}}"`. Every other JSONL uses the same prompt and tool tokens and also tokenizes session-prefix content. The pin mechanics live in [`dsh-acp-snapshot`](../../../../packages/support/acp-snapshot/README.md), whose suite factory enforces one pin per class.
+Exactly one scenario per header-composition class is flagged `pinsHeader`. Its directory splits the pin by review format: `system-prompt.golden.md` contains the normalized full prompt sequence as ordinary Markdown, `tool-schemas.golden.json` contains the corresponding complete schema sequence as structured JSON, and `session.jsonl` retains config, reason, and any model-visible prefix while storing `header.system` and `header.tools` as `"{{system}}"` / `"{{tools}}"`. Every other JSONL uses the same prompt and tool tokens and also tokenizes session-prefix content. The pin mechanics live in [`dsh-acp-snapshot`](../../../../packages/support/acp-snapshot/README.md), whose suite factory enforces one pin per class.
 
-The pure `scrubSystemPrompts` and `scrubToolSchemas` normalizers apply to every stored session fixture and independently tokenize initial-header content plus header-delta bulk. `scrubRequestHeaders` also tokenizes session-prefix content for non-pinning scenarios while retaining structural facts: system-delta positions and arity, added/removed/changed tool names, prefix message count, field presence, config, and reason. Record and refresh write-back apply the appropriate scrub before writing JSONL and regenerate both sidecars from the normalized live header and deltas, so neither path can reintroduce prompt/schema bulk into JSONL or leave a review artifact stale.
+The pure `scrubSystemPrompts` and `scrubToolSchemas` normalizers independently tokenize every stored full header. `scrubRequestHeaders` also tokenizes session-prefix content for non-pinning scenarios while retaining header count, field presence, config, reason, and prefix message count. Record and refresh write-back apply the appropriate scrub before writing JSONL and regenerate both sidecars from the normalized live full-header sequence, so neither path can reintroduce prompt/schema bulk into JSONL or leave a review artifact stale.
 
-Guards make the split self-enforcing. On disk, every `session*.jsonl` is a fixed point of both prompt and schema scrubbers, only non-pinning fixtures must be fixed points of the full header scrub, both sidecars exist exactly beside pinning fixtures in canonical newline-terminated formats, and each class has one pin. Live, every `request/header` produced by a parent, spawn child, fork child, initial request, or resume must match the reconstructed pin after volatile-value normalization; the pinning run's prompt and schema deltas must also match their sidecars. A header without a string prompt, without an array-valued tool list, or with an undeclared `request/header-delta` fails loud.
+Guards make the split self-enforcing. On disk, every `session*.jsonl` is a fixed point of both prompt and schema scrubbers, only non-pinning fixtures must be fixed points of the full header scrub, both sidecars exist exactly beside pinning fixtures in canonical newline-terminated formats, and each class has one pin. Live, every `request/header` produced by a parent, spawn child, fork child, initial request, resume, or in-instance change must match the reconstructed class sequence after volatile-value normalization. A header without a string prompt, without an array-valued tool list, or beyond the pin's declared changed-header count fails loud.
 
 One pin covers the whole suite because every session — parent, spawn child, fork child — composes the identical tool list and the identical prompt modulo cwd, and the uniformity guard fails the suite the moment that stops holding. If header composition ever becomes session-dependent by design (a restricted subagent toolset, say), the divergent shape gets its own pinning scenario.
 
@@ -26,7 +26,7 @@ One pin covers the whole suite because every session — parent, spawn child, fo
 
 ## Verification
 
-The suite replays every scenario against the split pins. Unit coverage exercises the independent and full scrubbers, both sidecar formats, record/refresh regeneration, normalized prompt/schema extraction, fixed-point enforcement, required-file symmetry, reconstructed-header uniformity, and delta rejection.
+The suite replays every scenario against the split pins. Unit coverage exercises the independent and full scrubbers, both full-header sidecar formats, record/refresh regeneration, normalized prompt/schema extraction, fixed-point enforcement, required-file symmetry, reconstructed-header uniformity, and changed-header count rejection.
 
 ## Consequences
 

docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md

@@ -16,7 +16,7 @@ The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/su
 
 **`src/normalize.ts`** — the pure normalizers, hook-free by policy: when a future event carries a new volatile field (an approval duration, say), the shared normalizer learns it in the same change, keeping one home for what "normalized" means rather than per-suite scrub extensions.
 
-**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.golden.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. The pure helpers (`childFixturePaths`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerDeltaCount`) are exported from the module for direct unit coverage.
+**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.golden.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. A pinning scenario declares any legitimate changed-header count, and its Markdown artifact records every full changed prompt. The pure helpers (`childFixturePaths`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerChangeCount`) are exported from the module for direct unit coverage.
 
 ## Alternatives considered
 

docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md

@@ -0,0 +1,108 @@
+# RFC: Recallable compaction — index checkpoints, a state checkpoint, and in-session history recall
+
+Status: proposed
+
+## Problem
+
+Compaction is a one-way door. The summary the model sees carries no reference to what it shadows — the `shadowedRange` provenance lives only on the log-only `compact/summary` event — and no tool lets the model read a shadowed span back. Whatever the summarizer drops is gone from the model's reachable world, even though the append-only log holds every byte. Repeated compaction compounds this: the head checkpoint is rewritten every pass, so the request prefix takes a full prompt-cache miss each time, and earlier summaries are re-summarized generation after generation.
+
+The root cause is one artifact playing two conflicting roles. An **index** wants to be frozen, chronological, and cheap; the model's **working memory** wants a global view, re-prioritization, and mutability. A single summary can be neither well.
+
+No mainstream coding harness gives the model in-loop recall, and none of the surveyed implementations makes compaction prefix-cache-aware. An event-sourced session — originals durable, seq-addressable, replay-exact — is the natural substrate for both.
+
+## Proposal
+
+Split the checkpoint into two classes and make shadowed history reachable.
+
+### Frozen index checkpoints
+
+Newly stale history splits into chunks by deterministic policy: accumulate toward `chunkTokens`, snap edges with `toolPairingBalancedBefore` / `toolPairingBalancedAfter`, prefer turn boundaries, and place the final boundary as close to the retain boundary as balance allows, so the trailing slice shrinks to roughly one turn. Each chunk is compacted by one `compactRegion` call into an **index stub** (`stubTokens`, ~100–200 tokens):
+
+- two or three lines of what happened;
+- a keyword line of low-frequency literal anchors — exact error strings, values, config keys — grouped by kind;
+- a code-composed footer: `[checkpoint c<summarySeq>: shadows conversation span #<start>–#<end>; originals retrievable via history_read]`. Pointers are assembled from provenance, never model-authored.
+
+A committed stub is never rewritten and never re-enters a later compaction region. A stub call's input is layered: the fixed preamble and the byte-identical pass-start state checkpoint (the shared prefix across all calls in the phase), then the keyword lines of all previously committed stubs — so a new entry indexes what is distinctive to its chunk instead of repeating the directory — the one or two most recent committed stubs for chronological continuity, and the slice itself. Sibling stubs from the same pass are not inputs (the concurrent phase forbids it; turn-aligned boundaries carry local continuity instead), and the state checkpoint is background only, never material to summarize into the stub. A slice consisting of recalled content is stubbed by code alone — a pointer line, no LLM call. A failed stub call degrades the same way: its slice gets a code-only pointer stub and the pass continues, making the state rewrite the only hard LLM dependency in a pass.
+
+### The state checkpoint
+
+One mutable working-memory document (at most one; zero before the first pass), positioned after all stubs and before the retained tail. Each pass rewrites it from the previous state plus this pass's staled content — O(previous + new), under the merge-don't-restate rule already in the summarization prompt — covering decisions, current state, constraints, and next steps. It carries its own footer and a size cap at the scale of today's summary.
+
+An inflation guard bounds the whole pass: if the post-compaction size is not strictly below the pre-compaction size, nothing commits and the turn proceeds; the attempt defers until more stale history accumulates. The guard compares one metric on both sides — provider-reported usage from the request path, falling back to the character estimator on both sides.
+
+### Pass execution
+
+- Chunk slices are surface position ranges. A pass runs two phases: all summarize calls execute concurrently, buffered off-surface; then regions commit strictly left to right — chunks first, trailing slice last — so the state checkpoint lands after every stub through contiguous single-node replaces. Wall-clock stays near one summarize call.
+- The superseded state checkpoint folds into the next pass's first chunk as ordinary history: no tombstone, no new primitive. Its stub omits it, `history_read` renders it labeled `[prior state checkpoint]`, and its footer travels with the rendered text, keeping every trailing slice reachable through the two-hop chain.
+- Range selection is frozen-aware: the compactable span begins after the last committed index checkpoint, at the surface head only when none exists. A legacy session's existing head checkpoint is adopted as state-class — its text the merge base, its node folded like any superseded state.
+- A crash in the summarize phase commits nothing; a crash mid-commit leaves a left-to-right prefix committed, and the resumed pass reads its merge base from the log's latest state-class `compact/summary` event and commits the remaining regions unconditionally — restoring `[stubs…][state][tail]` outranks shrinking.
+
+### The recall tools
+
+A new package `@deepseek-ai/dsh-tool-recall` (consumer-only, over the `dsh-session` and `dsh-compact` vocabularies) registers two model-facing tools:
+
+- `history_read(checkpoint, offset?)` — renders the shadowed span of any checkpoint in the log, including superseded ones, as `User:`/`Assistant:`/`Tool result:` transcript, paginated by a configured budget with a continuation cursor.
+- `history_search(query, checkpoint?, limit?)` — case-insensitive literal scan over every shadowed span; returns snippets with checkpoint ids and coverage metadata (`scanned`/`matched`/`truncated`). The zero-match hint notes the scan is literal and points at direct `history_read` of a plausible checkpoint.
+
+Both read `exec.agent.session.events` (the tool-todo access pattern; non-agent callers rejected), render only surface-type message events, and return ordinary `tool/result`s — recalled bytes land at the context tail, logged, so reconstructability holds with no special casing. There is no new storage and no sidecar index: the session log is the archive, `compact/summary` provenance is the index metadata, and the tools are a read path over both. The tool schemas and the package's one system-prompt section are static strings; checkpoint ids reach the model only through footers. The transcript renderer moves from `compact-basic` into `dsh-session`, shared by summarizer and tools.
+
+### Cache and cost
+
+The request prefix after a pass is `[system][stubs…][state][tail]`. Frozen stubs are byte-stable across passes, so the miss begins at the token replacing the previous state checkpoint and stays O(new chunks + state + tail) — against position zero today. Recall output lands at the tail, leaving the prefix untouched. Per-pass summarize input is roughly twice today's plus an m·S background term, bounded by a `chunkTokens` floor (a small multiple of the state cap) and a validated `stubTokens`/`chunkTokens` ratio ceiling; a shared-prefix input layout (preamble, then the byte-identical pass-start state, slice content in the tail) lets sibling calls earn cached-rate rereads.
+
+### Packaging
+
+The design ships as a new backend `dsh-compact-recallable` on the existing `ctx.compact` seam, enabled by default in the shipped example configs; `compact-basic` remains as the reference implementation and the seam's design twin, in the pattern of the paired LLM adapters. The seam JSDoc's "at most one auto-generated checkpoint, always at the head" clause is relaxed to name both backend behaviors.
+
+### Relation to in-flight work
+
+- **Tool-result pruning** (the in-flight pruning service): its replacement nodes carry `sourceEventSeqs`; the same registry fold lists pruned results as recallable. Follow-up scope; neither blocks the other.
+- **Provider-usage token accounting** (the in-flight move of compaction pressure onto provider-reported usage): supplies the guard's accounting; the implementation stacks after it.
+- **"Query sessions" backlog item**: the cross-session generalization; this RFC scopes to the live session with tool names and rendering chosen so that work extends rather than collides.
+- **Training**: when to recall is a learned behavior. The deterministic footers and keyword anchors give training a stable target, and recall usage is fully visible in the session log for trajectory export; benchmark and RL design proceed with the post-training side.
+
+### Follow-ups
+
+Specified during review, deferred until observation calls for them:
+
+- Guard degradation ladder (code-only rollup of the oldest stub prefix, footers preserved, rolled-up ids remain recall targets; then one summary after the frozen boundary) — on observed guard livelock or stub-region pressure.
+- Echo detection on stub outputs (sentence-scale n-grams, short literals exempt, retry then strip) — on observed division-of-labor leakage.
+- Periodic state refresh from chunk originals — on observed drift in the handoff probe.
+- `stateFallbackThreshold` (full-detail state prompt below a stub count) — on short-session regression.
+- Lazy registration of the recall tools — on measured context tax in never-compacting sessions.
+- Amortized stub drafting at pre-step: as soon as stale-but-uncompacted content accumulates past `chunkTokens`, draft that chunk's stub at the next pre-step (a log-only draft event, written while the chunk's surrounding context is still live) and let the compaction pass commit drafts instead of summarizing in bulk — the deterministic, replay-exact equivalent of background compaction (the Claude Code session-memory pattern; OpenClaw demonstrates the synchronous semantics are identical). Trigger: observed pass latency, or stub-quality gains from drafting near-live proving out.
+- Split summarizer models; model-chosen chunk boundaries; cross-session recall; semantic search fallback — each behind its own evidence.
+- Richer `history_search` query forms — regex, and structured queries over logged JSON tool results (sql/jq-style, or agent-authored queries against an indexed store) — on demand from observed search misses; literal matching ships first because the recall path stays a pure function of the log.
+
+## Alternatives considered
+
+- **Staged delivery** (ship recall tools alone over today's backend; gate the checkpoint split on observed recall usage) — rejected: untrained models under-use any new tool, so the gate would measure training absence rather than design value, while the training side needs the complete mechanism to build environments against; the pre-release window is when persisted-format changes are cheapest; and the cache economics are first-party knowledge, not a hypothesis awaiting telemetry. The implementation still lands as stacked PRs with the recall tools first — construction order, not a decision gate.
+- **All-frozen full-size summaries, no state checkpoint** — rejected: unbounded permanent-prefix growth, self-accelerating toward thrashing, with nothing left to re-prioritize.
+- **Pure stubs, no state checkpoint** — rejected: presumes the model knows what it is missing; fails on unknown unknowns.
+- **LLM aging/consolidation of frozen chunks** — rejected as a routine mechanism: summary-of-summary loss and frozen-prefix churn; the code-only rollup is its surviving form, deferred.
+- **Full prefix as chunk-summarizer input** — rejected: O(N²); the state document gives the same background at O(state).
+- **One summarize call emitting all outputs** — rejected: the summarize path has no structured-output enforcement; parsing one free-text response apart is the fragile seam the fail-closed design avoids.
+- **Model-chosen chunk boundaries** — deferred: parse-and-validate cost against unproven value; chunk policy sits behind config.
+- **Model-authored pointers** — rejected: pointers must be exact; deterministic assembly is.
+- **FTS/vector index sidecar** — rejected in-session: the live log is in memory and bounded, a literal scan under budget suffices; an index earns its keep at cross-session scope.
+- **Semantic search fallback / secondary-model extraction in the recall path** — rejected: an LLM or embedding call there breaks keyless replay determinism; recall stays a pure function of the log.
+- **Raw events instead of rendered transcript** — rejected: leaks log-only vocabulary and chunk noise; the model reads what a model once saw.
+- **Doing nothing (resume/fork as recovery)** — rejected: it makes recovery a human act.
+
+## Acceptance criteria
+
+- Auto-compaction over a long session yields `[stubs…][state][tail]` after every completed pass; prior stubs stay byte-identical across passes; committed stubs never fall inside a later region; the superseded state checkpoint folds without a tombstone, renders labeled, and stays reachable and searchable through the two-hop chain.
+- Every checkpoint's surface text ends with the deterministic footer; footers round-trip through replay byte-identically; the state checkpoint's provenance records its wider input range.
+- Nothing commits before all summaries exist and the guard passes on like-for-like accounting; a guard failure commits nothing and does not fail the turn; a mid-commit kill resumed at the next pre-step completes the pass with the state region committed unconditionally, merge base read from the log; a legacy head checkpoint is adopted as state-class.
+- `history_read` renders any logged checkpoint's span under budget with a working cursor; `history_search` covers every shadowed span with checkpoint-id snippets and coverage metadata, asserted in particular by finding content that exists only in a span shadowed by a superseded state checkpoint — the regression pin for trailing-slice reachability; both reject non-agent callers and never-existing ids or orphaned `compact/start` with typed errors; recalled content appears as ordinary `tool/result`s; request-reconstruction invariants pass over sessions with compaction plus recall; one keyless snapshot scenario covers compact-then-recall end to end; tool schemas and the prompt section are byte-identical across passes.
+- On the long-horizon bench suite: task success does not regress against `compact-basic` at equal budgets; a handoff-fidelity probe (restate K known decisions and constraints after a pass) scores no worse; recall usage frequency and hit usefulness are reported per run via the dsh bench report pipeline, alongside the stub-directory attention measurement and cache-hit telemetry.
+- Seam JSDoc, the compaction capability-seam RFC, `architecture.md`, and the generated tool, config, persistence, and module-graph catalogs update in the same change; all budgets live in config; new source directories hold per-file 100% coverage with HMR disposal tests.
+
+## Risks
+
+- **Recall is a learned behavior**: untrained models will under-use it, and the bench report exists to track the gap while training closes it. Until then the state checkpoint keeps the floor at today's summary quality.
+- **Unknown unknowns remain**: a detail absent from summaries and keywords draws no recall. Recall converts "unreachable even when suspected" into "reachable when suspected".
+- **The stub directory occupies attention**: dozens of stable index cards per request may dilute focus; the bench measurement in the acceptance criteria tracks it against `compact-basic`.
+- **Cost**: per-pass summarize input is roughly twice today's; short sessions sit near today's cost and quality, and the design pays off with session length.
+- **State drift and division-of-labor leakage** are observable through the handoff probe and stub review; their counters are specified follow-ups.
+- **Two backends** are a maintenance surface; the seam contract and the shared recall consumer bound it, and the bench comparison decides the default over time.

docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md

@@ -4,7 +4,7 @@ Status: proposed
 
 ## Problem
 
-The exact-read `ctx.sessionQuery` service deliberately has no derived index. Large persisted histories need full-text search without scanning every event on every query, while current live sessions need an overlay newer than the last durability checkpoint. Search also needs concrete ranking, snippets, filters, pagination, cancellation, and rebuild behavior.
+The exact-read `ctx.sessionQuery` service deliberately has no derived index. Large persisted histories need full-text search without scanning every event on every query, while current live sessions need an overlay newer than the last durability checkpoint. Search also needs concrete ranking, snippets, pagination, cancellation, and rebuild behavior.
 
 Splitting those concerns across a speculative provider coordinator and a database implementation would create two coupled reconciliation state machines. The first real implementation should own the source observation, extraction, SQLite transaction, generation, and query as one lifecycle.
 
@@ -20,7 +20,7 @@ Persisted documents survive restarts. Live overrides are connection-local and sh
 
 The implementation must define both cross-session and within-session scopes from executable use cases. Each searchable event is one document with session metadata, event metadata, surface classification, normalized semantic text, and a bounded plain-text snippet. Session results group by their strongest matching event; numeric backend scores remain private.
 
-Filters compile to parameterized SQL before ranking. Query syntax is treated as data. Ordering includes stable tie fields. Opaque cursors bind to normalized request shape and the smallest relevant generation; unrelated session changes should not invalidate a within-session cursor. Cancellation must stop caller waiting and interrupt SQLite work where the runtime permits.
+Search returns content-bearing result records rather than metadata-only headers. Chainable filters operate on that exact result shape and are designed and implemented with the search API instead of becoming a provider-specific pre-ranking contract. Query syntax is treated as data. Ordering includes stable tie fields. Opaque cursors bind to normalized request shape and the smallest relevant generation; unrelated session changes should not invalidate a within-session cursor. Cancellation must stop caller waiting and interrupt SQLite work where the runtime permits.
 
 Tokenizer choice remains an implementation experiment. FTS5 trigram supports substring recall but rejects useful terms shorter than three characters and increases index size; the proposal must benchmark that tradeoff against the default Unicode tokenizer before making it contract.
 
@@ -41,7 +41,7 @@ Reconciliation may use stable fingerprints to avoid rewriting unchanged persiste
 
 - Restart tests cover unchanged, new, changed, and deleted persisted sessions without rebuilding the whole index.
 - Reopening preserves persisted rows and removes live rows; live rows shadow and then reveal their persisted base.
-- Tests cover both search scopes, metadata filters, surface defaults, snippets, escaping, deterministic ties, pagination, scoped stale cursors, cancellation, dynamic persistence mount/unmount, and recovery after a failed transaction.
+- Tests cover both search scopes, content-bearing results, chainable result filters, surface defaults, snippets, escaping, deterministic ties, pagination, scoped stale cursors, cancellation, dynamic persistence mount/unmount, and recovery after a failed transaction.
 - A schema mismatch resets only the derived database.
 - A keyless end-to-end test combines a real persistence backend with the real SQLite search package.
 - The RFC is amended to the measured tokenizer and public API actually implemented before moving to `implemented/`.

docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md

@@ -1,36 +0,0 @@
-# RFC: Simplify session-log representation
-
-Status: proposed
-
-## Problem
-
-The session log maintains two representations that cost more machinery than their consumers require: a pseudo-linked surface and custom request-header deltas.
-
-`SurfaceManager` stores the same order in an array, a seq map, and mutable `prev`/`next` links. Production never reads `prev`; compact's sole `next` read is the successor of an array position. Replacement already uses `indexOf`, so the links do not make its dominant operation constant-time. A seq array with linear replacement lookup has the same asymptotic replacement cost and one representation to validate.
-
-The request-header subsystem implements a custom system/tool delta codec and transmission-decision layer even though its contract says deltas are an encoding optimization, not a reconstructability requirement. Retaining the initial/resume full snapshot at each loop-instance boundary, then writing a canonical full `request/header` whenever that instance's assembled header changes, preserves replay while deleting `SystemDelta`, `ToolsDelta`, round-trip fallback, and the durable `request/header-delta` variant. Codec-only vocabulary disappears with the codec, not because its individual arms were invalid.
-
-This proposal deliberately retains append and replacement `sourceEventSeqs`, crash-repair provenance, and all `SessionStartSource` variants: implemented RFCs give those fields an audit/interception role that zero current readers does not overturn.
-
-## Proposal
-
-Make `SurfaceManager.nodes` a `readonly number[]` of event sequences and remove the public `SurfaceNode` shape. Keep the internal replace-generation signal; update tool-pairing balance and compaction callers to use array values/indices for predecessor, successor, and replacement ranges, removing node links and the seq-to-node map. Replace post-anchor header deltas with canonical full changed-header snapshots and remove the delta codec/event/tests; initial and resume anchors remain full snapshots even when the folded header is unchanged.
-
-Amend the session-surface and reconstructable-request RFCs where they describe the removed encoding. Update event types/invariants, request logging/replay, persistence fixtures, generated catalogs, package docs, and snapshots. Replace the codec-only `fallback` reason with an explicit `change` reason for post-anchor full snapshots, distinguishing them from the retained `initial` and `resume` anchors.
-
-`SESSION_FORMAT_VERSION` is deliberately pinned at `0`, so an old v0 log containing `request/header-delta` would otherwise pass the version check and silently lose header changes after the delta fold is deleted. Seed/load validation must reject that legacy event fail-loud at the format boundary; no compatibility fold or migration is added.
-
-## Alternatives considered
-
-**Keep linked nodes and compact deltas for possible scale.** Links could help a future cursor API, and deltas can reduce logs when large tool schemas change by a small amount. No shipped cursor uses the links, while full snapshots trade disk size for substantially simpler correctness. If header volume proves material, compression or a measured canonical-delta scheme can be designed around real traces.
-
-## Acceptance criteria
-
-- `SurfaceManager.nodes` is one ordered seq array with no `SurfaceNode`, link fields, or seq-to-node map; incremental append processing and the internal replace-generation signal remain.
-- Replaying full changed-header snapshots reconstructs exactly the same requests; no header-delta event/type/codec remains.
-- A v0 seed or persisted log containing legacy `request/header-delta` is rejected before replay, with coverage for JSONL and SQLite load paths.
-- New-shape v0 JSONL/SQLite replay, provenance, crash repair, compaction, snapshots, invariants, typecheck, coverage, doc-sync, build, and hygiene pass.
-
-## Risks
-
-Full headers increase log volume, and linear replacement lookup could be slower on very large surfaces. Replacements are already linear because the implementation calls `indexOf`; benchmarks should be added only if real traces show the simpler array is a bottleneck. Because the format version remains `0`, forgetting the explicit legacy-event rejection would be silent data corruption rather than a type error; the fail-loud load test is therefore part of the proposal, not optional cleanup.

docs/testing.md

@@ -26,7 +26,12 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword
 - Product-visible plugins require a non-unit REAL-composition test. Hand-built `ctx.plugin(...)` suites are insufficient: boot test-only `cordis.yml` through Loader and app/process, mock only external/nondeterministic boundaries, and assert model-visible request/log, durable state, or user-visible output. Keep opt-ins out of shipped defaults.
 - A guard only guards if the regression actually fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green under a broken export shape — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert.
 - "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.cjs`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero.
-- An e2e that spawns an example from a temp cwd sets `TSX_TSCONFIG_PATH` to the repo-root tsconfig, or it silently falls back to stale built `lib/` ([examples/AGENTS.md](../examples/AGENTS.md)).
+
+## Test subprocess launch modes
+
+- CI and build-having test lanes run every example or Cordis-config subprocess from built `lib/` through the shared dual-mode launcher. Do not hand-write `--import tsx` for these subprocesses.
+- Protocol and operating-system fixtures that do not load Cordis run erasable `.ts` directly with Node, without tsx or the root paths map.
+- Only a test whose subject is source-path resolution may select `src`; state that contract in the test.
 
 ## When a snapshot test is required
 

docs/tool-catalog.md

@@ -18,8 +18,9 @@ This table connects model-visible tool names to the plugin package and service s
 | `@deepseek-ai/dsh-tool-ask-user` | `ask_user_question` | `ctx.tools`, `ctx.userInteraction` | `tool/call`, `tool/result after a UI/provider answers the question` | - | ask_user_question pauses the tool call until the active UI provider returns a human answer. |
 | `@deepseek-ai/dsh-tools` | `run_code` | `ctx.tools`, `ctx.codeRuntime (execution time)`, `ctx.systemPrompt` | `tool/call`, `one tool/code-dispatch per bridged sub-call`, `tool/result` | - | Owned by the tool registry as a reserved transport outside filterable capability layers under `mode: code` / `mode: both` (see the Code Mode RFC). Under `code` it is the registry's only wire contribution; the other visible capabilities are declared in a generated TypeScript SDK section, and a program calls them through serialized bindings that re-enter the complete guarded tool pipeline and link each nested execution to this outer result. |
 | `@deepseek-ai/dsh-tool-bash` | `bash` | `ctx.tools`, `ctx.bash`, `ctx.tasks at call time for run_in_background` | `tool/call`, `tool/result` | - | The bash tool is the model-facing consumer of the bash executor seam. A `run_in_background` run registers with the generic `ctx.tasks` runtime and is collected/stopped through the `task_*` tools from `@deepseek-ai/dsh-tool-tasks`; the `enableRunInBackground` config (default true) removes the parameter entirely when disabled. |
-| `@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-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; a full changed request header 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-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.bash`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are bash-backed discovery tools: they run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. |
 | `@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-tasks` | `task_kill`, `task_list`, `task_output` | `ctx.tools`, `ctx.tasks`, `ctx.systemPrompt` | `tool/call`, `tool/result`, `context/message via agent.inject() for background completion notices` | - | The kind-agnostic background-task control surface: a background bash command and a background subagent are read, listed, and killed through the same three tools. Loading the plugin attaches the control surface that arms producers' `ctx.tasks.start()`. |
@@ -126,7 +127,7 @@ Owned by the tool registry as a reserved transport outside filterable capability
 
 ### `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]`. 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. 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; read its output with `task_output` and stop it with `task_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]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. 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. 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; read its output with `task_output` and stop it with `task_kill`.
 
 ```json
 {
@@ -234,7 +235,7 @@ Dispose a plugin previously mounted with cordis_mount, by id. All its registrati
 
 Source: [`packages/cordis/tool-cordis/src/index.ts`](../packages/cordis/tool-cordis/src/index.ts)
 
-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.
+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; a full changed request header logs those tool-set changes.
 
 ## `@deepseek-ai/dsh-tool-fs`
 
@@ -330,6 +331,64 @@ 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-fs-search`
+
+### `glob`
+
+Find files whose paths match a glob pattern. Returns matching paths sorted by modification time, including hidden and ignored files (VCS metadata directories are excluded). Returns the first 100 paths inline; a capped result reports where the complete list was saved.
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "pattern": {
+      "type": "string",
+      "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\")."
+    },
+    "path": {
+      "type": "string",
+      "description": "Directory to search in. Defaults to the session workspace; a relative path resolves against it."
+    }
+  },
+  "required": [
+    "pattern"
+  ]
+}
+```
+
+Source: [`packages/fs/tool-fs-search/src/index.ts`](../packages/fs/tool-fs-search/src/index.ts)
+
+### `grep`
+
+Search file contents with a ripgrep regular expression. Returns matching lines with line numbers, grouped by file. Returns the first 250 matches inline; a capped result reports where the complete match list was saved. Use read on a matched file for surrounding context.
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "pattern": {
+      "type": "string",
+      "description": "Regular expression to search for (ripgrep syntax)."
+    },
+    "path": {
+      "type": "string",
+      "description": "File or directory to search. Defaults to the session workspace; a relative path resolves against it."
+    },
+    "include": {
+      "type": "string",
+      "description": "One glob filter for which files to search (e.g. \"*.ts\", \"*.{js,jsx}\"). Not a list; negation is not supported."
+    }
+  },
+  "required": [
+    "pattern"
+  ]
+}
+```
+
+Source: [`packages/fs/tool-fs-search/src/index.ts`](../packages/fs/tool-fs-search/src/index.ts)
+
+glob and grep are bash-backed discovery tools: they run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments.
+
 ## `@deepseek-ai/dsh-tool-skill`
 
 ### `skill`
@@ -511,10 +570,10 @@ todo_write is session-owned state; UIs render the latest todo/write event as a c
 
 Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.
 
-The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.
+The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.
 
 Script-body hooks:
-- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.
+- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.
 - `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.
 - `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.
 - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.
@@ -561,6 +620,10 @@ Constraints: concurrency and total-agent caps apply; no filesystem, network, tim
                 "type": "string",
                 "description": "Optional one-line description of the phase."
               },
+              "provider": {
+                "type": "string",
+                "description": "Optional provider override this phase is expected to use."
+              },
               "model": {
                 "type": "string",
                 "description": "Optional model override this phase is expected to use."

docs/tool-execution-pipeline.md

@@ -20,7 +20,7 @@ flowchart TD
   owned["Tool-owned session events<br/><code>todo/write</code>, <code>fs/observed</code>, <code>hook/invoked</code>, <code>hook/result</code>, <code>tool/code-dispatch</code>"]
   post["<code>tools/post-execute</code> waterfall<br/>accept, block, replace, add context"]
   final["<code>tools/result</code> synchronous notification<br/>frozen authoritative outcome"]
-  context["Batch-deferred additionalContext<br/>context/message after recorded tool results"]
+  context["Active-batch additionalContexts FIFO<br/>context/message after recorded tool results"]
   toolResult["Session event: <code>tool/result</code><br/>single model-facing outcome"]
   allResults["Tool batch settled<br/>recorded tool/result events complete"]
   presentResult["UI completed card<br/>presentResult(args, result)"]
@@ -48,6 +48,6 @@ flowchart TD
   allResults --> context
 ```
 
-Filesystem read-before-edit checks stay below `tool-fs` on `fs/*` events. Generic pre/post waterfalls host hooks and approval policy; `ctx.approval` resolves asks before monotonic guards, and owner policy that must not be reordered remains a registered guard. Around-dispatch concerns such as timeouts wrap `tools/execute`, while `tools/result` observes the immutable outcome after transforms, lossless-JSON validation, and outer error normalization. This lets hooks span tool families without coupling the tools to one policy service. Code Mode sends both the reserved `run_code` transport and its serialized sub-calls through the pipeline; sub-calls carry the parent token, log `tool/code-dispatch`, surface denials as binding rejections, and omit `additionalContext` to preserve call/result adjacency.
+Filesystem read-before-edit checks stay below `tool-fs` on `fs/*` events. Generic pre/post waterfalls host hooks and approval policy; `ctx.approval` resolves asks before monotonic guards, and owner policy that must not be reordered remains a registered guard. Around-dispatch concerns such as timeouts wrap `tools/execute`, while `tools/result` observes the immutable outcome after transforms, lossless-JSON validation, and outer error normalization. This lets hooks span tool families without coupling the tools to one policy service. Code Mode sends both the reserved `run_code` transport and its serialized sub-calls through the pipeline; sub-calls carry the parent token, log `tool/code-dispatch`, surface denials as binding rejections, and omit `additionalContexts` to preserve call/result adjacency.
 
 Maintenance mode: curated Mermaid flow; exact tool schemas and event signatures live in generated catalogs.

examples/AGENTS.md

@@ -1,6 +1,6 @@
 # AGENTS.md — Examples
 
-Runnable harness compositions. **Examples are NOT workspaces**: their private `package.json` files are dependency-free stubs, and the cordis Loader boots each `cordis.yml` unbuilt through `tsx` plus the root tsconfig paths.
+Runnable harness compositions. `examples/` is one workspace member and the module-resolution root for runnable and test Cordis configs; it is not a build target. [package.json](package.json) declares the packages loaded by those configs, while each leaf's private `package.json` remains metadata only.
 
 Extract reusable logic into `packages/`, where per-file coverage and README gates apply. Examples keep only `cordis.yml` wiring, demo artifacts, and e2e/snapshot scenarios; app package bins own boot glue.
 
@@ -13,7 +13,7 @@ Each example has both:
 
 Mock-only examples require only the keyless tier; state that exception in the test.
 
-Keyless stdio smokes use `@deepseek-ai/dsh-loader-smoke` for isolation, root-tsconfig loading, subprocess lifecycle, diagnostics, EOF, and cleanup; tests supply paths, environment, input, and assertions.
+Keyless stdio smokes use `@deepseek-ai/dsh-loader-smoke`; tests supply paths, environment, input, and assertions. Every checked-in test Cordis config lives under its corresponding `examples/<agent>/` leaf. Map a package-owned config to `examples/<agent>/tests/fixtures/<group>/<package>/cordis.yml`, keep its driver and assertions package-local, and declare every package it names in both root `tsconfig.json` references and `examples/package.json`.
 
 Do not inventory example tests here; the `tests/` trees and root scripts are authoritative.
 

examples/acp-agent/README.md

@@ -7,7 +7,7 @@ pnpm run demo:acp          # needs DEEPSEEK_API_KEY (repo-root .env or env)
 pnpm run demo:code-mode acp   # the same server in Code Mode: one wire tool, run_code
 ```
 
-The leaf config loads the ACP app, DeepSeek adapter, sandboxed bash, approval and permission services, model-facing tools, and repeat guard. The app bundles the agent spine, JSONL persistence, and bridge, creates agents on `session/new`, and keeps stdout logger-free. [`fs.cordis.yml`](fs.cordis.yml) adds the unconfined in-process filesystem stack for its dedicated scenarios; [`code-mode.cordis.yml`](code-mode.cordis.yml) adds `run_code` and its generated TypeScript SDK. See [Code Mode](../../packages/core/tools/README.md#code-mode).
+The leaf config loads the ACP app, DeepSeek adapter, sandboxed bash, approval and permission services, model-facing tools, and repeat guard. The app bundles the agent spine, JSONL persistence, and bridge, creates agents on `session/new`, and keeps stdout logger-free. [`fs.cordis.yml`](fs.cordis.yml) adds the unconfined in-process filesystem stack and local tool-result spill storage for its dedicated scenarios; [`code-mode.cordis.yml`](code-mode.cordis.yml) adds `run_code` and its generated TypeScript SDK. See [Code Mode](../../packages/core/tools/README.md#code-mode).
 
 ## stdout is the protocol
 

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

@@ -10,8 +10,11 @@
       - id: acp-agent
         name: '@deepseek-ai/dsh-acp-demo'
         config:
+          provider: deepseek
           model: deepseek-v4-flash
           persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+          workspaceContext:
+            maxBytes: 65536
           tools:
             mode: both
           persona: |
@@ -25,3 +28,10 @@
             name: '@deepseek-ai/dsh-tool-cordis'
           - id: llm-replay
             name: '@deepseek-ai/dsh-llm-replay'
+            config:
+              providers:
+                - id: deepseek
+                  name: DeepSeek
+                  models:
+                    - id: deepseek-v4-flash
+                    - id: deepseek-v4-pro

examples/acp-agent/advanced.cordis.yml

@@ -8,8 +8,11 @@
       - id: acp-agent
         name: '@deepseek-ai/dsh-acp-demo'
         config:
+          provider: deepseek
           model: deepseek-v4-flash
           persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+          workspaceContext:
+            maxBytes: 65536
           tools:
             mode: both
           persona: |

examples/acp-agent/both-mode.cordis.snapshot.yml

@@ -12,8 +12,11 @@
       - id: acp-agent
         name: '@deepseek-ai/dsh-acp-demo'
         config:
+          provider: deepseek
           model: deepseek-v4-flash
           persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+          workspaceContext:
+            maxBytes: 65536
           tools:
             mode: both
           persona: |
@@ -25,3 +28,10 @@
             name: '@deepseek-ai/dsh-code-runtime-worker'
           - id: llm-replay
             name: '@deepseek-ai/dsh-llm-replay'
+            config:
+              providers:
+                - id: deepseek
+                  name: DeepSeek
+                  models:
+                    - id: deepseek-v4-flash
+                    - id: deepseek-v4-pro

examples/acp-agent/both-mode.cordis.yml

@@ -10,8 +10,11 @@
       - id: acp-agent
         name: '@deepseek-ai/dsh-acp-demo'
         config:
+          provider: deepseek
           model: deepseek-v4-flash
           persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+          workspaceContext:
+            maxBytes: 65536
           tools:
             mode: both
           persona: |

examples/acp-agent/code-mode-workspace-context.cordis.snapshot.yml

@@ -0,0 +1,37 @@
+# Keyless replay counterpart of code-mode-workspace-context.cordis.yml. It
+# enables the filesystem entries needed by this scenario and swaps in replay.
+- id: base
+  name: '@cordisjs/plugin-include'
+  config:
+    path: ./cordis.yml
+    patches:
+      - id: llm-deepseek
+        name: '@deepseek-ai/dsh-llm-deepseek'
+        disabled: true
+      - id: acp-agent
+        name: '@deepseek-ai/dsh-acp-demo'
+        config:
+          provider: deepseek
+          model: deepseek-v4-flash
+          persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+          workspaceContext:
+            maxBytes: 65536
+          tools:
+            mode: code
+          persona: |
+            You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
+
+            Verify your work by running the code or tests. Keep answers brief and factual.
+      - insert:
+          - id: fs-local
+            name: '@deepseek-ai/dsh-fs-local'
+            config:
+              cwd: !!js process.cwd()
+          - id: fs-policy
+            name: '@deepseek-ai/dsh-fs-policy'
+          - id: tool-fs
+            name: '@deepseek-ai/dsh-tool-fs'
+          - id: code-runtime
+            name: '@deepseek-ai/dsh-code-runtime-worker'
+          - id: llm-replay
+            name: '@deepseek-ai/dsh-llm-replay'

examples/acp-agent/code-mode-workspace-context.cordis.yml

@@ -0,0 +1,32 @@
+# Code Mode workspace-context snapshot recording overlay. The scenario needs
+# filesystem tools to trigger nested instruction discovery after a read.
+- id: base
+  name: '@cordisjs/plugin-include'
+  config:
+    path: ./cordis.yml
+    patches:
+      - id: acp-agent
+        name: '@deepseek-ai/dsh-acp-demo'
+        config:
+          provider: deepseek
+          model: deepseek-v4-flash
+          persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+          workspaceContext:
+            maxBytes: 65536
+          tools:
+            mode: code
+          persona: |
+            You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
+
+            Verify your work by running the code or tests. Keep answers brief and factual.
+      - insert:
+          - id: fs-local
+            name: '@deepseek-ai/dsh-fs-local'
+            config:
+              cwd: !!js process.cwd()
+          - id: fs-policy
+            name: '@deepseek-ai/dsh-fs-policy'
+          - id: tool-fs
+            name: '@deepseek-ai/dsh-tool-fs'
+          - id: code-runtime
+            name: '@deepseek-ai/dsh-code-runtime-worker'

examples/acp-agent/code-mode.cordis.snapshot.yml

@@ -12,8 +12,11 @@
       - id: acp-agent
         name: '@deepseek-ai/dsh-acp-demo'
         config:
+          provider: deepseek
           model: deepseek-v4-flash
           persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+          workspaceContext:
+            maxBytes: 65536
           tools:
             mode: code
           persona: |
@@ -25,3 +28,10 @@
             name: '@deepseek-ai/dsh-code-runtime-worker'
           - id: llm-replay
             name: '@deepseek-ai/dsh-llm-replay'
+            config:
+              providers:
+                - id: deepseek
+                  name: DeepSeek
+                  models:
+                    - id: deepseek-v4-flash
+                    - id: deepseek-v4-pro

examples/acp-agent/code-mode.cordis.yml

@@ -11,8 +11,11 @@
       - id: acp-agent
         name: '@deepseek-ai/dsh-acp-demo'
         config:
+          provider: deepseek
           model: deepseek-v4-flash
           persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+          workspaceContext:
+            maxBytes: 65536
           tools:
             mode: code
           persona: |

examples/acp-agent/cordis.snapshot.yml

@@ -28,3 +28,10 @@
       - insert:
           - id: llm-replay
             name: '@deepseek-ai/dsh-llm-replay'
+            config:
+              providers:
+                - id: deepseek
+                  name: DeepSeek
+                  models:
+                    - id: deepseek-v4-flash
+                    - id: deepseek-v4-pro

examples/acp-agent/cordis.yml

@@ -9,9 +9,6 @@
   config:
     apiKey: !!js process.env.DEEPSEEK_API_KEY
     baseURL: !!js process.env.DEEPSEEK_BASE_URL
-    models:
-      - deepseek-v4-flash
-      - deepseek-v4-pro
 
 # The default composition confines bash to the workspace and asks before a
 # wider retry. Snapshots use danger-full-access; DSH_PERMISSION_MODE overrides
@@ -33,14 +30,17 @@
 - id: permission
   name: '@deepseek-ai/dsh-permission'
 
-# The ACP server app: the agent-core spine + JSONL persistence + the ACP bridge.
+# The ACP server app: the agent-spine-demo spine + JSONL persistence + the ACP bridge.
 # Persistence root: $DSH_SNAPSHOT_SESSIONS_ROOT when the snapshot harness sets it
 # (so it can harvest / isolate the log), else ./.sessions for the demo.
 - id: acp-agent
   name: '@deepseek-ai/dsh-acp-demo'
   config:
+    provider: deepseek
     model: deepseek-v4-flash
     persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+    workspaceContext:
+      maxBytes: 65536
     # Keep the persona to identity and behavior; tool plugins own tool guidance.
     # The loop resolves {{model}} and each ACP session's client-supplied {{cwd}}.
     persona: |

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

@@ -17,5 +17,20 @@
             name: '@deepseek-ai/dsh-fs-policy'
           - id: tool-fs
             name: '@deepseek-ai/dsh-tool-fs'
+          - id: spill-local
+            name: '@deepseek-ai/dsh-spill-local'
+            config:
+              root: !!js process.env.DSH_SNAPSHOT_SPILL_ROOT ?? './.spill'
+          - id: spill-policy
+            name: '@deepseek-ai/dsh-spill-policy'
+            config:
+              maxInlineBytes: 800
           - id: llm-replay
             name: '@deepseek-ai/dsh-llm-replay'
+            config:
+              providers:
+                - id: deepseek
+                  name: DeepSeek
+                  models:
+                    - id: deepseek-v4-flash
+                    - id: deepseek-v4-pro

examples/acp-agent/fs.cordis.yml

@@ -15,3 +15,11 @@
             name: '@deepseek-ai/dsh-fs-policy'
           - id: tool-fs
             name: '@deepseek-ai/dsh-tool-fs'
+          - id: spill-local
+            name: '@deepseek-ai/dsh-spill-local'
+            config:
+              root: !!js process.env.DSH_SNAPSHOT_SPILL_ROOT ?? './.spill'
+          - id: spill-policy
+            name: '@deepseek-ai/dsh-spill-policy'
+            config:
+              maxInlineBytes: !!js process.env.DSH_SNAPSHOT && 800 || 50000

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

@@ -15,6 +15,7 @@ import {
   type RequestPermissionResponse,
   type SessionNotification,
 } from '@agentclientprotocol/sdk'
+import { resolveExampleLaunch } from '@deepseek-ai/dsh-loader-smoke'
 
 /**
  * Boots examples/acp-agent as an ACP subprocess. The key-gated prompt leg
@@ -25,8 +26,6 @@ import {
 // The child runs from a temp cwd, so its bin and config path are absolute.
 const binScript = fileURLToPath(new URL('../../../packages/examples/acp-demo/src/bin.ts', import.meta.url))
 const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
-// Resolve tsx absolutely because the subprocess runs outside the repo.
-const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
 // The root tsconfig supplies unbuilt workspace `paths`; making it explicit
 // avoids accidental resolution through stale built output.
 const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
@@ -38,24 +37,21 @@ interface Spawned {
   stderr: string[]
 }
 
-// TODO(acp-test-harness): this subprocess/client boot glue is duplicated with
-// hooks.e2e.ts and partly with dsh-acp-snapshot's harness. Migrate both e2e
-// files onto that launcher before the TSX/env/permission-stub details drift.
 function spawnAcpAgent(cwd: string, env: NodeJS.ProcessEnv = process.env): Spawned {
-  const child = spawn(
-    process.execPath,
-    ['--import', tsxLoader, binScript, '--config', configPath],
-    {
-      cwd,
-      env: {
-        ...env,
-        TSX_TSCONFIG_PATH: repoTsconfig,
-        DSH_PERMISSION_MODE: 'danger-full-access',
-        DSH_HOME: join(cwd, '.dsh'),
-        DSH_AGENTS_HOME: join(cwd, '.agents'),
-      },
-      stdio: ['pipe', 'pipe', 'pipe'],
+  const launch = resolveExampleLaunch({
+    srcBin: binScript,
+    configArgs: ['--config', configPath],
+    tsconfigPath: repoTsconfig,
+    env: {
+      DSH_PERMISSION_MODE: 'danger-full-access',
+      DSH_HOME: join(cwd, '.dsh'),
+      DSH_AGENTS_HOME: join(cwd, '.agents'),
     },
+  })
+  const child = spawn(
+    launch.command,
+    launch.args,
+    { cwd, env: { ...env, ...launch.env }, stdio: ['pipe', 'pipe', 'pipe'] },
   )
   const stderr: string[] = []
   child.stderr.setEncoding('utf8')
@@ -138,16 +134,20 @@ describe('acp-agent over real stdio (no key required)', () => {
     workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-'))
     // Collect raw stdout bytes directly (bypass the SDK framing) to inspect.
     // A dummy key boots the adapter; this purity test sends no prompt and makes no model call.
-    const child = spawn(process.execPath, ['--import', tsxLoader, binScript, '--config', configPath], {
-      cwd: workdir,
+    const launch = resolveExampleLaunch({
+      srcBin: binScript,
+      configArgs: ['--config', configPath],
+      tsconfigPath: repoTsconfig,
       env: {
-        ...process.env,
         DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot',
-        TSX_TSCONFIG_PATH: repoTsconfig,
         DSH_PERMISSION_MODE: 'danger-full-access',
         DSH_HOME: join(workdir, '.dsh'),
         DSH_AGENTS_HOME: join(workdir, '.agents'),
       },
+    })
+    const child = spawn(launch.command, launch.args, {
+      cwd: workdir,
+      env: { ...process.env, ...launch.env },
       stdio: ['pipe', 'pipe', 'pipe'],
     })
     const out: string[] = []

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

@@ -25,7 +25,9 @@ const AGENT = {
 // The Code Mode overlay configs (include-patched variants of cordis.yml; the
 // replay swap resolves each one's sibling `*cordis.snapshot.yml`).
 const CODE_MODE_CONFIG = fileURLToPath(new URL('../code-mode.cordis.yml', import.meta.url))
+const CODE_MODE_WORKSPACE_CONTEXT_CONFIG = fileURLToPath(new URL('../code-mode-workspace-context.cordis.yml', import.meta.url))
 const BOTH_MODE_CONFIG = fileURLToPath(new URL('../both-mode.cordis.yml', import.meta.url))
+const WORKSPACE_CONTEXT_CONFIG = fileURLToPath(new URL('../workspace-context.cordis.yml', import.meta.url))
 const ADVANCED_CONFIG = fileURLToPath(new URL('../advanced.cordis.yml', import.meta.url))
 const FS_CONFIG = fileURLToPath(new URL('../fs.cordis.yml', import.meta.url))
 
@@ -51,6 +53,7 @@ const SCENARIOS: Scenario[] = [
   // Its prompt and tool-schema sidecars pin the composed header.
   { name: 'text-turn', hasModelTurn: true, recorded: true, pinsHeader: true },
   { name: 'tool-call-turn', hasModelTurn: true, recorded: true },
+  { name: 'bash-spill', hasModelTurn: true, recorded: false, headerClass: 'fs', configPath: FS_CONFIG },
   { 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' },
@@ -62,12 +65,36 @@ const SCENARIOS: Scenario[] = [
   { name: 'fs-read-window', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG },
   { name: 'fs-policy-reject', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG },
   { name: 'multi-turn', hasModelTurn: true, recorded: true },
+  // ACP exposes the adapter catalog as a session-scoped model select. This
+  // scenario pins the default flash request, the switch response, and the
+  // resulting changed request-header snapshot for pro.
+  {
+    name: 'model-switching',
+    hasModelTurn: true,
+    recorded: true,
+    pinsHeader: true,
+    expectedHeaderChanges: 1,
+    headerClass: 'model-switching',
+  },
   { name: 'error-finish', hasModelTurn: true, recorded: false, overridden: true },
   // Keyless, authored (like error-finish/cancel): deterministically forcing a
   // LIVE model to repeat one call three times is not a stable recording, so
   // the fixture scripts five identical todo_write calls and pins BOTH reminder
   // tiers (gentle at 3, detailed at 5) as context/message in transcript and log.
   { name: 'repeat-tool-guard', hasModelTurn: true, recorded: false },
+  // Authored replay: a root AGENTS.md pins the session prefix, then a read in
+  // nested/ discovers its narrower AGENTS.md as a raw, metadata-bearing
+  // context/message. The scenario-specific config keeps home/root discovery
+  // hermetic, and the resulting prefix needs its own pinned header class.
+  {
+    name: 'workspace-context',
+    hasModelTurn: true,
+    recorded: false,
+    overridden: true,
+    pinsHeader: true,
+    headerClass: 'workspace-context',
+    configPath: WORKSPACE_CONTEXT_CONFIG,
+  },
   { name: 'cancel', hasModelTurn: true, recorded: false, overridden: true },
   { name: 'subagent-spawn', hasModelTurn: true, recorded: true, childSessions: 1 },
   { name: 'subagent-multi', hasModelTurn: true, recorded: true, childSessions: 2 },
@@ -116,14 +143,25 @@ const SCENARIOS: Scenario[] = [
   // tools:sdk section rides in the prompt, and the program's tool calls land as
   // tool/code-dispatch events. Each overlay composes and pins its own header class.
   { name: 'code-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'code', configPath: CODE_MODE_CONFIG },
+  // A nested fs dispatch inside run_code discovers workspace instructions. The
+  // context/message must follow the outer result while retaining workspace
+  // provenance, which proves Code Mode carries deferred tool context end to end.
+  {
+    name: 'code-mode-workspace-context',
+    hasModelTurn: true,
+    recorded: true,
+    pinsHeader: true,
+    headerClass: 'code-workspace-context',
+    configPath: CODE_MODE_WORKSPACE_CONTEXT_CONFIG,
+  },
   { name: 'both-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'both', configPath: BOTH_MODE_CONFIG },
-  // The default tree owns the single Permissions select. Snapshot mode starts
-  // in danger-full-access so established fixtures stay runner-independent;
-  // these policy scenarios switch to workspace-write in their input scripts.
+  // The default tree also owns the Permissions select. Snapshot mode starts in
+  // danger-full-access so established fixtures stay runner-independent; these
+  // policy scenarios switch to workspace-write in their input scripts.
   // Real-kernel confinement remains in escalation.e2e.ts and the sandbox
   // packages' e2e suites.
   { name: 'config-options', hasModelTurn: false, recorded: false, headerClass: 'sandbox' },
-  { name: 'permission-switching', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderDeltas: 1, headerClass: 'sandbox' },
+  { name: 'permission-switching', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderChanges: 1, headerClass: 'sandbox' },
   { name: 'escalation-approved', hasModelTurn: true, recorded: true, headerClass: 'sandbox' },
   { name: 'escalation-rejected', hasModelTurn: true, recorded: true, headerClass: 'sandbox' },
 ]

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

@@ -15,6 +15,7 @@ import {
   type RequestPermissionResponse,
   type SessionNotification,
 } from '@agentclientprotocol/sdk'
+import { resolveExampleLaunch } from '@deepseek-ai/dsh-loader-smoke'
 
 /**
  * Exercises the default ACP composition through the real bin and Loader. The
@@ -28,9 +29,8 @@ import {
 
 const binScript = fileURLToPath(new URL('../../../packages/examples/acp-demo/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).
+// tsconfig so the unbuilt `paths` map resolves in src mode (see examples/AGENTS.md).
 const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
 
 // Without a usable bwrap/Seatbelt runner, the strict attempt fails closed with
@@ -55,17 +55,19 @@ interface Spawned {
 
 /** Boot the example as an ACP subprocess; the scripted client answers every permission prompt with `answer`. */
 function spawnAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawned {
+  const launch = resolveExampleLaunch({
+    srcBin: binScript,
+    configArgs: ['--config', configPath],
+    tsconfigPath: repoTsconfig,
+    // 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: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY || 'sk-dummy-for-boot' },
+  })
   const child = spawn(
-    process.execPath,
-    ['--import', tsxLoader, binScript, '--config', 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'],
-    },
+    launch.command,
+    launch.args,
+    { cwd, env: { ...process.env, ...launch.env }, stdio: ['pipe', 'pipe', 'pipe'] },
   )
   const stderr: string[] = []
   child.stderr.setEncoding('utf8')
@@ -115,15 +117,16 @@ describe('default sandbox composition keyless smoke (real cordis.yml via the Loa
     expect(sessionId.length).toBeGreaterThan(0)
   }, 30_000)
 
-  it('advertises the Permissions select and honors a switch end to end (no key, no model)', async () => {
+  it('advertises model and Permissions selects and honors a permission switch without a model call', async () => {
     workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-config-'))
     spawned = spawnAcpAgent(workdir, 'reject-once')
     const { client } = spawned
     await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
     const created = await client.newSession({ cwd: workdir, mcpServers: [] })
     const advertised = created.configOptions ?? []
+    const modelValue = JSON.stringify(['deepseek', 'deepseek-v4-flash'])
     expect(advertised.map(option => [option.id, 'currentValue' in option ? option.currentValue : undefined]))
-      .toEqual([['permission', 'workspace-write']])
+      .toEqual([['model', modelValue], ['permission', 'workspace-write']])
     const afterFullAccess = await client.setSessionConfigOption({
       sessionId: created.sessionId, configId: 'permission', value: 'danger-full-access',
     })
@@ -133,7 +136,7 @@ describe('default sandbox composition keyless smoke (real cordis.yml via the Loa
       sessionId: created.sessionId, configId: 'permission', value: 'danger-full-access',
     })
     expect((again.configOptions ?? []).map(option => [option.id, 'currentValue' in option ? option.currentValue : undefined]))
-      .toEqual([['permission', 'danger-full-access']])
+      .toEqual([['model', modelValue], ['permission', 'danger-full-access']])
     await expect(client.setSessionConfigOption({
       sessionId: created.sessionId, configId: 'permission', value: 'plan',
     })).rejects.toThrow(/unknown permission value/)

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

@@ -15,6 +15,7 @@ import {
   type RequestPermissionResponse,
   type SessionNotification,
 } from '@agentclientprotocol/sdk'
+import { resolveExampleLaunch } from '@deepseek-ai/dsh-loader-smoke'
 
 /**
  * With-key e2e for the Claude hook bridge. The process-level `./hooks.json` is
@@ -25,7 +26,6 @@ import {
 
 const binScript = fileURLToPath(new URL('../../../packages/examples/acp-demo/src/bin.ts', import.meta.url))
 const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
-const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
 const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
 
 interface Spawned {
@@ -36,10 +36,16 @@ interface Spawned {
 }
 
 function spawnAcpAgent(cwd: string): Spawned {
+  const launch = resolveExampleLaunch({
+    srcBin: binScript,
+    configArgs: ['--config', configPath],
+    tsconfigPath: repoTsconfig,
+    env: { DSH_PERMISSION_MODE: 'danger-full-access' },
+  })
   const child = spawn(
-    process.execPath,
-    ['--import', tsxLoader, binScript, '--config', configPath],
-    { cwd, env: { ...process.env, TSX_TSCONFIG_PATH: repoTsconfig, DSH_PERMISSION_MODE: 'danger-full-access' }, stdio: ['pipe', 'pipe', 'pipe'] },
+    launch.command,
+    launch.args,
+    { cwd, env: { ...process.env, ...launch.env }, stdio: ['pipe', 'pipe', 'pipe'] },
   )
   const stderr: string[] = []
   child.stderr.setEncoding('utf8')

examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl

@@ -2,12 +2,12 @@
 {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
 {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"}
 {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
 {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}}
 {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}}
 {"type":"assistant/chunk","seq":7,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
 {"type":"assistant/chunk","seq":8,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
-{"type":"assistant/message","seq":9,"time":1783957884564,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
+{"type":"assistant/message","seq":9,"time":1783957884564,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
 {"type":"step/end","seq":10,"time":1783957884564,"data":{"turn":1,"step":1}}
 {"type":"turn/end","seq":11,"time":1783957884564,"data":{"turn":1,"reason":{"kind":"completed"}}}

examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl

@@ -2,12 +2,12 @@
 {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
 {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"}
 {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
 {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}}
 {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}}
 {"type":"assistant/chunk","seq":7,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
 {"type":"assistant/chunk","seq":8,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
-{"type":"assistant/message","seq":9,"time":1783957884701,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
+{"type":"assistant/message","seq":9,"time":1783957884701,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
 {"type":"step/end","seq":10,"time":1783957884701,"data":{"turn":1,"step":1}}
 {"type":"turn/end","seq":11,"time":1783957884701,"data":{"turn":1,"reason":{"kind":"completed"}}}