Merge remote-tracking branch 'origin/master' into worktree/web-multimodal-image-input

# Conflicts:
#	apps/cli/src/web.ts
#	apps/web/tests/smoke-fixture.e2e.ts
#	docs/architecture.i18n.yaml
#	packages/client/connection/src/client/fixture.ts
#	packages/client/runtime/src/client/sessions/conversation.ts
#	packages/client/runtime/src/client/sessions/session.ts
#	packages/client/ui-conversation/package.json
#	packages/client/ui-conversation/src/client/contract/slots.ts
#	packages/client/ui-conversation/src/client/index.ts
#	packages/client/ui-conversation/src/client/service.ts
#	packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx
#	packages/client/ui-conversation/tests/apply-inject.spec.tsx
#	packages/client/ui-conversation/tests/service-orchestration.spec.ts
#	packages/host/runtime/src/api-proxy.ts
#	packages/host/runtime/src/boot.ts
#	packages/host/webserver/tests/webserver.spec.ts
#	pnpm-lock.yaml

.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md

@@ -4,23 +4,24 @@ Status: implemented
 
 ## Problem
 
-`dsh-session-persistence-jsonl` and `dsh-session-persistence-sqlite` intentionally prove the same `SessionPersistence` contract over different storage media, but their write-path orchestration was duplicated: per-session state, `session/created` adoption, backend-specific prefix reads, write-behind buffers, serialized flush chains, HMR seeding, and dispose drains. The pure seed-prefix collision and serializability guards had already moved into the seam package; the remaining orchestration was still correctness-heavy and received the same fixes twice. A code-level diff showed the two backends were byte-identical — or same-algorithm — for ALL of it: the four maps (`states`/`buffers`/`chains`/`inits`), `installWritePath`, `initFor`, `onCreated`'s four cases, `flush`, `drain`, `serialize`, `adopt`, `adoptLivePrefix`, `assertVersion`, and the `create`/`append`/`load` skeletons. Only the storage primitives (write bytes vs. INSERT rows) differed.
+`dsh-session-persistence-jsonl` and `dsh-session-persistence-sqlite` intentionally prove the same `SessionPersistence` contract over different storage media, but their write-path orchestration was duplicated: per-session state, `session/created` adoption, backend-specific prefix reads, write-behind control, per-id operation serialization, HMR seeding, and dispose drains. The pure seed-prefix collision and serializability guards had already moved into the seam package; the remaining orchestration was still correctness-heavy and received the same fixes twice. Only the storage primitives (write bytes vs. INSERT rows) differed.
 
 ## Decision
 
-Extract a backend-agnostic `PersistenceCoordinator` into `dsh-session-persistence`. The coordinator owns the orchestration once; each first-party backend composes one (`new PersistenceCoordinator(ctx, this)`), implements a small `PersistenceBackend` hook interface, and delegates its four public service methods (`create`/`append`/`load`/`list`) to it.
+Extract a backend-agnostic `PersistenceCoordinator` into `dsh-session-persistence`. The coordinator owns the orchestration once; each first-party backend composes one (`new PersistenceCoordinator(ctx, this)`), implements a small `PersistenceBackend` hook interface, and delegates its stateful public methods (`create`/`append`/`load`/`inspect`) to it. Backend-owned metadata and revision listing bypass the coordinator.
 
-Composition, not inheritance. The coordinator is a concrete class the backend holds, not a base class the backend extends. The Agent Note'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.
+Composition, not inheritance. The coordinator is a concrete class the backend holds, not a base class the backend extends. The Agent Note's risk — "a coordinator must not make unusual backends fight an inheritance hierarchy" — is avoided: a backend exposes only the hooks and cannot reach the coordinator's private orchestration state. A third-party backend MAY still implement the abstract service directly without the coordinator, including the non-mutating `inspect` contract used by read models.
 
-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 coordinator holds one controller for each exact live `Session`; the controller combines initialization, pending events, and the shared flush promise. Each `session/event` starts an eager drain, and `session/flush` observes quiescence rather than initiating the ordinary write path. The [flush-controller simplification](../simplification/2026-07-23-collapse-persistence-flush-state.md) owns this lifecycle.
+
+The coordinator retires a session from `session/disposed`: it waits for the controller's initialization and current flush, serializes a final drain, and removes the controller and owned per-id state only after success. A failure leaves the controller discoverable for backend teardown to retry. Settled per-id chain tails remove themselves only when they are still current, so a completion cannot erase a newer operation for the same id. Backend teardown unregisters write-path listeners, flushes every remaining controller, awaits per-id operations, and 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:
+Five required members plus an optional lifecycle hook form the only boundary between the coordinator and storage:
 
 - `name` — backend label for the dispose-failure `AggregateError`.
-- `loadStored(id)` — read a stored prefix by id, scanning ANY storage scope (every JSONL cwd bucket; SQLite's id is globally unique). Used by resume/load and, via `!== undefined`, the create-collision probe.
-- `loadLive(id, cwd)` — read a stored prefix SCOPED to `cwd`. **Deliberately distinct from `loadStored`**: HMR live-adoption must only adopt a persisted log at the SAME cwd as the live session; a same-id log at a different cwd is a collision, not a resume. Collapsing the two reintroduces a cross-cwd adoption bug. SQLite ignores `cwd`.
+- `loadStored(id)` — read one stored prefix by id across every storage scope (every JSONL cwd bucket; SQLite's id is globally unique). Resume/load, non-mutating inspection, live adoption, and the create-collision probe share this lookup. The coordinator asserts the returned id and rejects a stored/live cwd mismatch before repair or state publication.
 - `appendBatch(meta, events, isMaterialized)` — durably append a contiguous batch, lazily materializing the session ATOMICALLY when not yet materialized (the materialize-write and the first event batch must commit together — a crash between them must not leave a materialized-but-empty session; this is why there is no separate `materialize` hook).
 - `commitRepair(meta, tornMarker, closers)` — make a crash repair durable: truncate the torn tail (iff `tornMarker !== undefined`) and append `closers`. **NOT required to be atomic** — JSONL legitimately truncates-then-appends in two fsync'd steps, SQLite does DELETE+INSERT in one transaction. Used by `load` (truncate + synthetic closers) and live-adoption (truncate only, `closers = []`).
 - `list()` — list all stored metadata.
@@ -32,13 +33,13 @@ 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. `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.
+The shared `runPersistenceContract` (public-API contract) runs for every backend and proves that `inspect` leaves interrupted logs and revisions unchanged before `load` performs recovery. `runCoordinatorContract` (`tests/coordinator-contract.ts`) covers adoption, HMR, collision, session and backend disposal drains, and crash-tail repair through an in-memory reference, JSONL, and SQLite. Coordinator-specific tests cover eager follow-up batches, live-controller cleanup, same-id chain-tail races, failed-drain retry, and close ordering. The per-backend specs retain storage mechanics only. A through-coordinator torn-tail repair test per real backend keeps the opaque-marker branch covered because the contract crash case produces synthetic closers without a torn marker.
 
 ## Alternatives considered
 
 - **A base class the backends extend** — rejected for composition: a backend exposes only the hooks, cannot reach the coordinator's private orchestration state, and a third-party backend may still implement the abstract service directly without the coordinator at all.
-- **A wider hook surface** — each candidate hook folded away: there is no separate `materialize` hook (the materialize-write must commit atomically with the first event batch inside `appendBatch`), no separate create-collision probe (it is `loadStored(id) !== undefined`), and no coordinator pass-through for `list()` (listing needs none of the orchestration).
+- **A wider hook surface** — each candidate hook folds away: there is no scope-specific live lookup because `loadStored` plus the coordinator's cwd check preserves the collision boundary, no storage-locator generic because validated JSONL metadata reproduces its path while SQLite is already id-bound, no separate `materialize` hook because the first batch must commit atomically with materialization, no separate create-collision probe because it is `loadStored(id) !== undefined`, and no coordinator pass-through for `list()` because listing needs none of the orchestration.
 
 ## Consequences
 
-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.
+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 pending events in the live controller, and makes backend teardown the quiescence boundary. Its hook surface stays narrow: identity, adoption, collision checks, and non-mutating inspection reuse `loadStored`; materialization stays atomic inside `appendBatch`; and listing bypasses the coordinator. Read models use `inspect` rather than `load`, so observing a persisted open turn cannot race a new live owner by committing interruption closers. New backends implement storage primitives rather than copy the eager write lifecycle.

.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.md

@@ -24,7 +24,7 @@ Each example is now **mostly an invocation of an app package**, splitting the wi
 
 The proposal listed `hmr` among the interactive app's baked-in front-door cluster. Validating against the code, baking `hmr` into the app package fights Cordis in two ways, so it ships as a **leaf `cordis.yml` entry** instead:
 
-1. `@cordisjs/plugin-hmr` is a Loader-only, subprocess-only dev plugin — its constructor throws without `node --expose-internals` + a live `loader` service, so it can only run in the real `demo:*`/bin subprocess, never in the in-process unit/coverage tier.
+1. `@cordisjs/plugin-hmr` is a Loader-only, subprocess-only dev plugin — it requires the live `loader` service and its internal module access, so it can only run in the real `demo:*`/bin subprocess, never in the in-process unit/coverage tier.
 2. The in-process test tier (vitest) cannot even *import* the vendored `hmr` module (its class-decorator `@Inject` form fails under Vite's transform), so a package whose `apply` statically imported it could never satisfy the per-file 100% coverage gate on its headline function.
 
 Crucially, `hmr` is not a stdout-purity footgun: a stray entry in the ACP config does not corrupt JSON-RPC frames. Every shipped app omits a stdout console logger; the app or protocol driver alone owns stdout.

.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md

@@ -21,7 +21,9 @@ Long-running tools are producers. `dsh-tool-bash` adapts a `BashProcess` into in
 
 ## Runtime contract
 
-The literal types live in the [task data-structure catalog](../../../../docs/core-data-structures/tasks.md). A producer calls `ctx.tasks.start()` with a kind, label, optional owning `Agent`, and a `run()` function. The runtime completes all failable preflight work before calling `run()` and invokes it once. After `run()` returns hooks, registration commits without another failable step; a producer cannot start work that lacks a collectable task id.
+The literal types live in the [task data-structure catalog](../../../../docs/core-data-structures/tasks.md). A producer calls `ctx.tasks.start()` with a kind, label, optional owning `Agent`, optional positive `outputLimitBytes`, and a `run()` function. The runtime completes all failable preflight work before calling `run()` and invokes it once. After `run()` returns hooks, registration commits without another failable step; a producer cannot start work that lacks a collectable task id.
+
+`outputLimitBytes` is producer-owned presentation policy, not a registry buffer. The registry validates and projects it unchanged into `TaskSnapshot`; generic control surfaces apply the cap to complete model-facing output after adding their own status or notice metadata. Omitting it preserves the existing surface behavior, so the runtime does not impose a hidden default on unrelated producer families.
 
 A model-facing producer exposes that committed id in its canonical success value, normally `{ kind: 'background', taskId }`; Native rendering may keep human-readable prose. A pre-aborted background call fails rather than returning a no-op because no task exists to satisfy the promised handle. Once registration publishes the id, cancellation belongs to the task's own controller and the task runtime: later cancellation of the producing tool call must not kill the published task. `task_kill`, owner disposal, and service teardown request cancellation; foreground execution remains coupled to the call's `exec.signal`.
 
@@ -75,11 +77,11 @@ Stream reads share one task-scoped consuming cursor because the owning model is
 
 The system prompt tells the model to retain task ids, continue independent work instead of busy-polling or duplicating a running task, collect relevant tasks before its final answer, and kill work that no longer matters. Completion injects a logged `context/message` into the exact owner's session; it becomes durable context for the next request but does not wake an idle agent.
 
-The runtime marks a terminal task `reported` when a read or wait delivers it, when a live waiter has claimed delivery at settlement, or when the model explicitly kills it. Reported tasks do not inject redundant completion notices. Listener failures are logged independently, do not stop later listeners, and are not awaited by waiters or teardown.
+The runtime marks a terminal task `reported` when a read or wait delivers it, when a live waiter has claimed delivery at settlement, or when the model explicitly kills it. Reported tasks do not inject redundant completion notices. Listener failures are logged independently, do not stop later listeners, and are not awaited by waiters or teardown. When a snapshot carries `outputLimitBytes`, `dsh-tool-tasks` preserves UTF-8 boundaries and reuses an existing producer truncation marker rather than duplicating it. Reads reserve status suffixes and retain the output tail; completion notices reserve the stable `background task <id>` prefix and `task_output` instruction before truncating variable kind, label, status, detail, or the truncation marker itself, so the minimum PTY cap still identifies the task to collect. The task surface resolves the caller-visible producer cap in a prepended pre-execute listener before policy can deny or short-circuit dispatch, then applies it through the task definitions' last-mile `finalizeContent` callback so normalized tool errors, outer pipeline failures, and single-text policy results cannot escape the bound; deliberately structured multi-block policy results retain policy ownership of their shape and size.
 
 ## Producer opt-in
 
-Each producer owns whether its schema exposes `run_in_background` through defaulted config. `dsh-tool-bash` and each `dsh-tool-subagent` instance use `enableRunInBackground`, defaulting to true. A disabled instance omits the parameter and also rejects a forced background argument at execution because the generic argument validator permits undeclared keys. Schema omission advertises the capability; the execution check enforces it.
+Each producer owns whether its schema exposes `run_in_background` through defaulted config. `dsh-tool-bash`, `dsh-tool-pty`, and each `dsh-tool-subagent` instance use `enableRunInBackground`, defaulting to true. A disabled instance omits the parameter and also rejects a forced background argument at execution because the generic argument validator permits undeclared keys. Schema omission advertises the capability; the execution check enforces it.
 
 `ctx.tasks` does not rewrite producer schemas. A bundle forwards configuration only for producers it owns. If a background call reaches `start()` without an attached surface, the runtime fence fails before execution.
 
@@ -121,7 +123,7 @@ Authorization, not unguessability, is the access boundary, and ids do not derive
 
 ## Testing
 
-Unit coverage pins preflight atomicity, per-kind ids, stream and final reads, wait timeout and abort races, cancellation, first-wins settlement, listener containment, notice suppression, owner isolation, stale owner instances, owner cleanup, service teardown, and the no-surface fence. Producer tests cover bash process mapping, subagent startup cancellation, terminal mapping, and disposal. Snapshot coverage pins the control-tool schemas and prompt guidance.
+Unit coverage pins preflight atomicity, per-kind ids, output-limit validation and projection, complete UTF-8 result bounds, stream and final reads, wait timeout and abort races, cancellation, first-wins settlement, listener containment, notice suppression, owner isolation, stale owner instances, owner cleanup, service teardown, and the no-surface fence. Producer tests cover bash process mapping, subagent startup cancellation, terminal mapping, and disposal. Snapshot coverage pins the control-tool schemas and prompt guidance.
 
 ## Consequences
 

.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md

@@ -218,7 +218,7 @@ A fresh registry-assigned Symbol provides collision-free execution identity with
 
 Arguments are materialized once where model/tool JSON enters the pipeline. Pre-, around-, and post-execute listeners operate on the typed execution and decisions. Call ID correlation, approval, monotonic guards, and Code Mode nesting remain explicit relational checks.
 
-After the last post-execute listener, the registry materializes and freezes the accepted final result once. Every synchronous `tools/result` observer receives that exact committed object, and observer failures are contained individually. An outer pipeline failure is normalized into a committed error result, so observers can discard staged work against the same authoritative boundary.
+After post-execute or outer pipeline normalization, the registry losslessly snapshots the candidate result, converting a snapshot failure into an ordinary error, invokes the call's snapshotted optional `ToolDefinition.finalizeContent` callback, then materializes and freezes the accepted final result once. The callback may replace only content, so structured error identity, contexts, and metadata remain registry-owned even when a tool enforces a last-mile result bound. Every synchronous `tools/result` observer receives that exact committed object, and observer failures are contained individually. An outer pipeline or candidate-snapshot failure is normalized before final content, so observers can discard staged work against the same authoritative boundary.
 
 ### The assembly waterfall owns the final model-visible composition
 

.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.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
-2026-07-19-cooperative-tool-cancellation.md: 559012f10d41963698cc932727125de1b9ccfef7
-2026-07-19-cooperative-tool-cancellation.zh.md: 6af8e57349bba026ab22f257014c084c5c3c3f54
+2026-07-19-cooperative-tool-cancellation.md: be237f6ca9475699bb4af76896772a1a7409033d
+2026-07-19-cooperative-tool-cancellation.zh.md: 9ad212c2073063ccb0c838c08ab8f89c9285b26b

.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md

@@ -36,7 +36,7 @@ An around-dispatch wrapper may replace `exec.signal` for its delegated lifetime
 
 ### Pre-aborted entry short-circuits after materialization
 
-The registry first creates the call token and losslessly snapshots and freezes the arguments. A materialization failure wins even when the caller signal is already aborted. After successful materialization, a pre-aborted signal skips `tools/pre-execute`, approval, `tools/execute`, `tools/post-execute`, and the tool body, then publishes exactly one frozen authoritative `tools/result` with `ABORTED_BEFORE_DISPATCH`.
+The registry first creates the call token, snapshots the visible definition's optional final-content callback, and losslessly snapshots and freezes the arguments. An argument-materialization failure wins even when the caller signal is already aborted. Before final content, the registry also losslessly snapshots the candidate result and converts a result-snapshot failure into an ordinary error, so the callback can still enforce its content invariant. After successful argument materialization, a pre-aborted signal skips `tools/pre-execute`, approval, `tools/execute`, `tools/post-execute`, and the tool body, then passes `ABORTED_BEFORE_DISPATCH` through that content-only callback before publishing exactly one frozen authoritative `tools/result`.
 
 ### Started work still reaches quiescence
 

.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md

@@ -36,7 +36,7 @@ Status: implemented
 
 ### 进入时已中止会在物化后短路
 
-注册表先创建调用 token，并对参数进行无损快照和冻结。即使调用方信号已经中止，参数物化失败仍优先返回。物化成功后，进入时已中止的信号会跳过 `tools/pre-execute`、审批、`tools/execute`、`tools/post-execute` 和工具主体，然后发布且只发布一次冻结的权威 `tools/result`，其代码为 `ABORTED_BEFORE_DISPATCH`。
+注册表先创建调用 token，对可见工具定义的可选 `finalizeContent` callback 做快照，并对参数进行无损快照和冻结。即使调用方信号已经中止，参数物化失败仍优先返回。在最终内容处理之前，注册表还会对候选结果进行无损快照，并把结果快照失败转换为普通错误，从而使该 callback 仍能保证其内容不变量成立。参数物化成功后，进入时已中止的信号会跳过 `tools/pre-execute`、审批、`tools/execute`、`tools/post-execute` 和工具主体，然后先由该仅处理内容的 callback 处理 `ABORTED_BEFORE_DISPATCH`，再发布且只发布一次冻结的权威 `tools/result`。
 
 ### 已启动工作仍必须完全停稳
 

.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.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
-2026-07-19-gui-layering-and-rpc-protocol.md: 65fb01f44698c61e6bf6958e332e1854fbb77fa9
-2026-07-19-gui-layering-and-rpc-protocol.zh.md: e8b15789846ea124fb6a90f2afef437184d4348a
+2026-07-19-gui-layering-and-rpc-protocol.md: 63db4786adcc007d09b7a58824a59f4d1e1e8be1
+2026-07-19-gui-layering-and-rpc-protocol.zh.md: b3037ceb8c172925581d2862ea675e53a7f8c54e

.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md

@@ -25,9 +25,10 @@ Directories layer as follows:
 
 - `packages/host/*`: packages provide host-side capability only (representing the Node.js engineering core built on the existing harness plugin system), and additionally
     - the unified backend protocol (fetch, HTTP, streaming interfaces…) — definitions and support, see the "Message protocol" sections below
-- `packages/client/*`: packages provide client-side capability only; every package stays single-sided. Two kinds live here:
-    - **Pure libraries** (`ui-slots`, `web-react`, `ui-primitives`): ordinary root-index packages, statically bundled into the shell and seeded into the browser plugin loader's module table.
-    - **dshClient plugin packages** (`connection`, `runtime`, `ui-theme`, `i18n`, `ui-layout`, `ui-sidebar`, `ui-conversation`, `ui-trajectory`): dual-entry — the root index is the node half (an empty `apply`, existing so the host Loader governs lifecycle and the web plugin registry discovers the package.json `dshClient` declaration); the entire implementation and its types live under `src/client/`, shipped as the `./client` subpath (a tsdown closure-factory bundle), and cross-package consumption imports the `/client` form. `runtime` additionally exports `./loader` (the shell-held browser bundle loader — a loader cannot load itself).
+- `packages/client/*`: packages provide client-side capability only; every package stays single-sided. Three kinds live here (the axes are owned by the [client plugin loading RFC](2026-07-23-client-plugin-loading-model.md)):
+    - **Pure libraries** (`ui-slots`, `web-react`, `ui-primitives`, plus the `loader` kernel package): ordinary root-index packages, statically bundled into the shell; the first three are seeded into the module table.
+    - **Static-arrival entry packages** (`connection`, `runtime`, `ui-theme`, `i18n`, `hmr`): no `dshClient` key and no browser bundle — the shell bundles their `src/client/` half and registers it with `ctx.modules`; they are governed as entries of the host-authored graph like everything else.
+    - **Fetch-arrival plugin packages** (`ui-layout`, `ui-sidebar`, `ui-conversation`, `ui-trajectory`): dual-entry — the root index is the node half (an empty `apply`, existing so the host Loader governs lifecycle and the web plugin registry discovers the package.json `dshClient` declaration); the implementation lives under `src/client/`, shipped as the `./client` subpath (a tsdown closure-factory bundle). Cross-plugin consumption of `/client` is type-only; value cooperation goes through cordis services.
 - `apps/` holds the externally exported application shapes, assembled from Client / Host mixtures.
     - `apps/web` (`dsh-frontend`) is the vite application: a thin `main.ts` over the shell surface exported by `dsh-client-web`.
     - `apps/cli` (`@deepseek-ai/dsh`) dispatches shapes: `dsh web` = startHost + webserver + the built `dsh-frontend` dist; `dsh -p` = headless in-process calls, zero HTTP.
@@ -51,7 +52,7 @@ Direction discipline (every rule auditable from package deps):
 - `runtime → apiproxy` is one-way; apiproxy depends only on type definitions.
 - Client-side packages **never import** host-side package runtime (they consume only the two browser-safe subpaths `/api` and `/client`).
 - `webserver` does not depend on `runtime`: it provides a `{ fetch }`-shaped implementation — "webserver ← runtime" is a runtime injection relationship, not a package dependency.
-- Cross-package client imports use the `/client` subpath for plugin packages (a bare package name would inline a second runtime instance into a browser bundle; the tsdown purity gate rewrites or rejects it).
+- Cross-package client imports use the `/client` subpath for plugin packages, and between plugin packages they are type-only — a cross-plugin value import is a build error at the tsdown purity gate (value cooperation goes through cordis services; the [client plugin loading RFC](2026-07-23-client-plugin-loading-model.md) owns the edge rules).
 
 TypeScript checks in **two aggregate programs** referenced by a solution root (`tsconfig.json` = solution; `tsconfig.host.json` = host side + tests, excluding `packages/client`; `tsconfig.client.json` = client packages and their tests): both sides merge the cordis `Context` interface under the same keys (`sessions`, `loader`) with different services, so one program would see both declaration merges and report a collision. Shared leaves (session/llm/tools/apiproxy…) build once and are referenced by both programs ([topology](../process/2026-07-22-tsconfig-solution-root-two-aggregates.md)).
 
@@ -70,7 +71,7 @@ On the protocol side: TS interfaces (`packages/host/apiproxy/src/api/`, zero Nod
 
 #### Naming rule
 
-Packages under `packages/host/*` and `packages/client/*` **must carry the directory-group prefix in the package name**: host/runtime → `dsh-host-runtime`, client/runtime → `dsh-client-runtime`. The directory name does not repeat the group prefix (host/ already expresses it). The package-name tail therefore ≠ the directory name, so the `dsh-*` wildcard in tsconfig.base.json (which resolves by directory name) misses them — **each package in these two groups needs an explicit paths entry**, including separate entries for the plugin packages' `/client` (and runtime's `/loader`) subpaths so source-level resolution matches the exports map.
+Packages under `packages/host/*` and `packages/client/*` **must carry the directory-group prefix in the package name**: host/runtime → `dsh-host-runtime`, client/runtime → `dsh-client-runtime`. The directory name does not repeat the group prefix (host/ already expresses it). The package-name tail therefore ≠ the directory name, so the `dsh-*` wildcard in tsconfig.base.json (which resolves by directory name) misses them — **each package in these two groups needs an explicit paths entry**, including separate entries for the client packages' `/client` subpaths so source-level resolution matches the exports map.
 
 #### How to integrate a new shape (operational checklist)
 

.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md

@@ -23,9 +23,10 @@ Status: implemented
 目录按照如下分层:
 - `packages/host/*`: 包只提供 Host 侧能力（代表了以现在 Harness 实体插件系统为主体的 Node.js 代码核心工程），除此之外，还包含
     - 统一后端协议（fetch、HTTP、流式接口等）定义和支持，见本篇「消息协议」起各节
-- `packages/client/*`：包只提供 Client 侧能力，每包单边不混。这里住两类包：
-    - **纯库**（`ui-slots`、`web-react`、`ui-primitives`）：普通根入口包，静态打包进壳，并播种进浏览器插件 loader 的模块表。
-    - **dshClient 插件包**（`connection`、`runtime`、`ui-theme`、`i18n`、`ui-layout`、`ui-sidebar`、`ui-conversation`、`ui-trajectory`）：双入口——根入口是 node 半边（空 `apply`，其存在是为了让 host Loader 管辖生命周期、让 web 插件注册表发现 package.json 的 `dshClient` 声明）；实现与类型全部住在 `src/client/` 下，经 `./client` 子路径发布（tsdown 闭包工厂 bundle），跨包消费一律 import `/client` 形式。`runtime` 额外导出 `./loader`（壳持有的浏览器 bundle loader——loader 加载不了自己）。
+- `packages/client/*`：包只提供 Client 侧能力，每包单边不混。这里住三类包（两条轴归 [client 插件装载 RFC](2026-07-23-client-plugin-loading-model.md) 所有）：
+    - **纯库**（`ui-slots`、`web-react`、`ui-primitives`，外加内核包 `loader`）：普通根入口包，静态打包进壳；前三者播种进模块表。
+    - **静态到达 entry 包**（`connection`、`runtime`、`ui-theme`、`i18n`、`hmr`）：无 `dshClient` 键、无浏览器 bundle——壳把它们的 `src/client/` 半边打进自己的 bundle 并向 `ctx.modules` 登记；它们与其余单元一样，作为 host 独家撰写的图里的 entry 受治理。
+    - **fetch 到达插件包**（`ui-layout`、`ui-sidebar`、`ui-conversation`、`ui-trajectory`）：双入口——根入口是 node 半边（空 `apply`，其存在是为了让 host Loader 管辖生命周期、让 web 插件注册表发现 package.json 的 `dshClient` 声明）；实现住在 `src/client/` 下，经 `./client` 子路径发布（tsdown 闭包工厂 bundle）。跨插件消费 `/client` 只限类型；值层面的协作走 cordis 服务。
 - `apps/` 作为对外导出的应用形态入口，可以由 Client / Host 混合组装。
     - `apps/web`（`dsh-frontend`）是 vite 应用：`dsh-client-web` 导出的壳表面之上的一层薄 `main.ts`。
     - `apps/cli`（`@deepseek-ai/dsh`）做形态分发：`dsh web` = startHost + webserver + 构建出的 `dsh-frontend` dist；`dsh -p` = headless 进程内直调，零 HTTP。
@@ -49,7 +50,7 @@ harness core packages ──────────────────┘
 - `runtime → apiproxy` 单向；apiproxy 仅依赖类型定义。
 - client 侧包**永不 import** host 侧包的运行时（只吃 `/api`、`/client` 两个浏览器安全子路径）。
 - `webserver` 不依赖 `runtime`：它提供 `{ fetch }` 特定实现 ——「webserver ← runtime」只是运行时注入关系，不是包依赖。
-- client 侧跨包 import 插件包一律走 `/client` 子路径（裸包名会把第二份运行时实例内联进浏览器 bundle；tsdown 纯度门禁会改写或拒收）。
+- client 侧跨包 import 插件包一律走 `/client` 子路径，且插件包之间只限类型 import——跨插件值 import 在 tsdown 纯度门禁处即构建错误（值层面的协作走 cordis 服务；边规则归 [client 插件装载 RFC](2026-07-23-client-plugin-loading-model.md) 所有）。
 
 TypeScript 以 solution 根引用的**两个聚合 program** 检查（`tsconfig.json` = solution；`tsconfig.host.json` = host 侧 + 测试，排除 `packages/client`；`tsconfig.client.json` = client 各包及其测试）：两侧在相同键（`sessions`、`loader`）下以不同服务合并 cordis `Context` 接口，单一 program 会同时看到两份声明合并而报冲突。共享叶子包（session/llm/tools/apiproxy 等）只构建一次，由两个 program 共同引用（[拓扑](../process/2026-07-22-tsconfig-solution-root-two-aggregates.md)）。
 
@@ -68,7 +69,7 @@ TypeScript 以 solution 根引用的**两个聚合 program** 检查（`tsconfig.
 
 #### 命名规则
 
-`packages/host/*` 与 `packages/client/*` 下的包名**必须含目录组前缀**：host/runtime → `dsh-host-runtime`、client/runtime → `dsh-client-runtime`。目录名不重复组前缀（host/ 已表达）。因此包名尾段 ≠ 目录名，tsconfig.base.json 的 `dsh-*` 通配（按目录名解析）命不中——**这两组的每包需显式 paths 条目**，且插件包的 `/client`（以及 runtime 的 `/loader`）子路径要单列条目，使源码级解析与 exports map 一致。
+`packages/host/*` 与 `packages/client/*` 下的包名**必须含目录组前缀**：host/runtime → `dsh-host-runtime`、client/runtime → `dsh-client-runtime`。目录名不重复组前缀（host/ 已表达）。因此包名尾段 ≠ 目录名，tsconfig.base.json 的 `dsh-*` 通配（按目录名解析）命不中——**这两组的每包需显式 paths 条目**，且 client 各包的 `/client` 子路径要单列条目，使源码级解析与 exports map 一致。
 
 #### 怎么接入一个新形态（操作清单）
 

.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.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
-2026-07-19-gui-web-client-architecture.md: 6e1cbc2d1e3e3437480c8005ca06845c23c628df
-2026-07-19-gui-web-client-architecture.zh.md: 9e2b3ef60d97840cd6cbd26e8fdcf922d472391c
+2026-07-19-gui-web-client-architecture.md: eeae5fb3ad8eb3e9842b497ee51258375760bc93
+2026-07-19-gui-web-client-architecture.zh.md: c6f4b10c2a4c2d210c6bd7a7fa1ac470cab7c0a7

.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md

@@ -17,29 +17,22 @@ Both ends run cordis. The host is a cordis plugin tree; the browser runs a secon
 ```
 ┌─ Host ─────────────────────────┐   ┌─ Browser ─────────────────────────────────────────┐
 │ sessions/agents/SessionLog     │   │ client cordis root ctx                             │
-│ apiproxy: RPC + mux/host 双流  │◀─▶│  ├ loader（壳静态持有，不能经自己装载）             │
-│ webserver:                     │   │  ├ immediately 先行组: connection/runtime/         │
-│  ├ GET /plugins/<id>/client.js │   │  │   ui-theme/i18n（动态 bundle，并行先装）        │
-│  └ GET / 注入 __DSH_BOOT__     │   │  ├ 后续组: layout/sidebar/conversation/trajectory  │
-└────────────────────────────────┘   │  └ session scope ×N（观看驱动，惰性建）            │
+│ apiproxy: RPC + mux/host 双流  │◀─▶│  ├ vendored Loader + ctx.modules（内核，壳静态持有）│
+│ webserver:                     │   │  ├ immediately entries: connection/runtime/        │
+│  ├ GET /plugins/<id>/client.js │   │  │   ui-theme/i18n（fetch bundle，boot 预拉）       │
+│  └ GET / 注入 __DSH_BOOT__ 图  │   │  ├ lazy entries: layout/sidebar/                   │
+│                                │   │  │   conversation/trajectory（fetch bundle，按需） │
+└────────────────────────────────┘   │  ├ app-shell 伪行（壳内静态注册，同一治理）        │
+                                     │  └ session scope ×N（观看驱动，惰性建）            │
                                      │ React: loading 页 → settled → 整 UI 一次成型       │
                                      └────────────────────────────────────────────────────┘
 ```
 
 ## The client cordis tree and the loading chain
 
-Every UI plugin is simultaneously a host plugin (dual-entry package): the node half sits in the host's plugin tree so the host Loader governs its lifecycle, and the browser half is a tsdown closure bundle under the package's `exports["./client"]`. The host webserver derives the boot manifest from loaded plugins carrying a `dshClient` manifest field and injects it into the page as `window.__DSH_BOOT__` — the HTML alone tells the browser everything to fetch, zero extra round trips.
+The loading chain — the two package kinds (plain vs dshClient plugin), the module-system/plugin-governor split, the two-phase boot over the host-authored entry graph with revisions, and hot reload — is owned by the [client plugin loading RFC](2026-07-23-client-plugin-loading-model.md). The load-bearing facts for this document: the browser boots the same vendored `@cordisjs/plugin-loader` as the host with a client module system (`ctx.modules`, `packages/client/modules`) filling its `internal` seam; every unit with product behavior is an entry in the host-authored `__DSH_BOOT__` graph — all nine plugin packages (infrastructure included) carry the `dshClient` declaration and arrive as fetched `./client` tsdown closure bundles, `immediately` rows differing only in boot phase-one prefetch, while plain packages (react family, cordis, the not-yet-promoted libraries) stay shell-bundled, seeded, and invisible to the graph; bundles execute `window.__ModuleLoader__.load({ id, factory })` and their `require` is answered from the lazy CJS module table (seed words + registered factories, materialized and memoized on first require — cross-plugin value imports are a build error, cooperation goes through cordis services); plugin CSS is inlined in the bundle and injected as `<style data-plugin="<id>">` at materialization (CSS Modules hashing + ownership tag = isolation, removal on reload); hot reload is live in dev graphs — the webserver stat-polls the bundles it serves and broadcasts `rebuilt` SSE frames, and the `client-hmr` plugin swaps one fiber per frame. The settled flip (`loader.await()` + an all-ACTIVE sweep) still switches the shell from the loading page to the real UI in one pass — settled means every entry is created and every fiber reached ACTIVE, with FAILED/PENDING fibers listed loud; there is no partial-availability mode (progressive rendering is deferred work).
 
-The loading chain, end to end:
-
-1. `GET /` → the shell boots, mounts `ctx.loader` (the loader mechanism is held statically by the shell — a loader cannot load itself; its code home is `packages/client/runtime/src/client/loader/`, imported through the `./loader` subpath so the shell bundle does not swallow the rest of the runtime package), seeds the require module table with the pure-library instances (react, react-dom, cordis, ui-slots, web-react, ui-primitives), and renders a plugin-independent loading page.
-2. `loader.start()` reads `__DSH_BOOT__`. Entries flagged `immediately` form the early-load group (connection, runtime, ui-theme, i18n): fetched in parallel, applied in intra-group `inject` topological order, and **the whole group must land before anything else loads**. Remaining plugins then load in inject order.
-3. Each bundle executes `window.DSHClientProxy.loadPlugin({ id, factory })`. The loader calls `factory(require)` — bundles are closure factories whose external dependencies arrive through the injected `require`, resolved against the module table (no globals, no import maps; an unresolvable specifier fails loud). The factory returns its module export surface (including the cordis `apply`); the loader runs `ctx.plugin(apply)`, then **registers that export surface into the module table under the package name**, so inject topology guarantees later plugins can `require` earlier ones. Plugin CSS is inlined in the bundle and injected as `<style data-plugin="<id>">` (CSS Modules hashing + ownership tag = isolation).
-4. `await loader.settled()` → the shell flips from the loading page to the real UI in one pass. A single failed plugin fails loud on the loading page; there is no partial-availability mode (progressive rendering is deferred work).
-
-**The dual-instance ban**: a module-table package inlined into a plugin bundle would duplicate runtime identity (two React copies, two store registries — the root cause of an actual white-screen P0). The tsdown client preset enforces purity at build time: a bare-name import of a module-table package must resolve external (rewritten to its `/client` form where applicable), and any other workspace leak that is not an inline-safe wire/type layer fails the build (`packages/client/tsdown.client.ts`, pinned by `scripts/client-bundle-purity.spec.ts`).
-
-Dev equals prod: plugins rebuild under `tsdown --watch`, refresh reloads the same chain; vite serves only the shell (`apps/web`). Type universes stay split at the aggregate level — `tsconfig.host.json` is the host program and `tsconfig.client.json` the client program, both referenced by the solution root `tsconfig.json` — because both sides merge cordis `Context` under the same keys (`sessions`, `loader`) with different services; client packages consume the wire vocabulary through pure type subpaths (`@deepseek-ai/dsh-session/types` and kin) so no host augmentation rides into the client program.
+Type universes stay split at the aggregate level — `tsconfig.host.json` is the host program and `tsconfig.client.json` the client program, both referenced by the solution root `tsconfig.json` — because both sides merge cordis `Context` under the same keys (`sessions`, `loader`) with different services; client packages consume the wire vocabulary through pure type subpaths (`@deepseek-ai/dsh-session/types` and kin) so no host augmentation rides into the client program.
 
 ## The slot system: how the page composes
 

.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.zh.md

@@ -17,29 +17,22 @@ Status: implemented
 ```
 ┌─ Host ─────────────────────────┐   ┌─ Browser ─────────────────────────────────────────┐
 │ sessions/agents/SessionLog     │   │ client cordis root ctx                             │
-│ apiproxy: RPC + mux/host 双流  │◀─▶│  ├ loader（壳静态持有，不能经自己装载）             │
-│ webserver:                     │   │  ├ immediately 先行组: connection/runtime/         │
-│  ├ GET /plugins/<id>/client.js │   │  │   ui-theme/i18n（动态 bundle，并行先装）        │
-│  └ GET / 注入 __DSH_BOOT__     │   │  ├ 后续组: layout/sidebar/conversation/trajectory  │
-└────────────────────────────────┘   │  └ session scope ×N（观看驱动，惰性建）            │
+│ apiproxy: RPC + mux/host 双流  │◀─▶│  ├ vendored Loader + ctx.modules（内核，壳静态持有）│
+│ webserver:                     │   │  ├ immediately entries: connection/runtime/        │
+│  ├ GET /plugins/<id>/client.js │   │  │   ui-theme/i18n（fetch bundle，boot 预拉）       │
+│  └ GET / 注入 __DSH_BOOT__ 图  │   │  ├ lazy entries: layout/sidebar/                   │
+│                                │   │  │   conversation/trajectory（fetch bundle，按需） │
+└────────────────────────────────┘   │  ├ app-shell 伪行（壳内静态注册，同一治理）        │
+                                     │  └ session scope ×N（观看驱动，惰性建）            │
                                      │ React: loading 页 → settled → 整 UI 一次成型       │
                                      └────────────────────────────────────────────────────┘
 ```
 
 ## client cordis 树与装载链
 
-每个 UI 插件同时是一个 host 插件（双入口包）：node 半边住在 host 的插件树里，由 host Loader 管辖其生命周期；浏览器半边是 tsdown 闭包 bundle，挂在包的 `exports["./client"]` 下。host webserver 从带 `dshClient` manifest 字段的已加载插件推导启动清单，注入页面为 `window.__DSH_BOOT__`——HTML 到手即知要拉什么，零额外往返。
+装载链——两类包（普通包 vs dshClient 插件）、模块系统/插件治理器之分、host 独家撰写的带修订号 entry 图之上的双层 boot、热重载——归 [client 插件装载 RFC](2026-07-23-client-plugin-loading-model.md) 所有。本篇赖以立足的事实：浏览器启动与 host 相同的 vendored `@cordisjs/plugin-loader`，由 client 模块系统（`ctx.modules`，`packages/client/modules`）填上其 `internal` seam；凡带产品行为的单元都是 host 独家撰写的 `__DSH_BOOT__` 图里的 entry——全部九个插件包（含基础设施）都携带 `dshClient` 声明、以 fetch 到达的 `./client` tsdown 闭包 bundle 供给，`immediately` 行的差别仅在 boot 第一层预取，而普通包（react 家族、cordis、尚未升格的库）保持打进壳、已播种、对图不可见；bundle 执行 `window.__ModuleLoader__.load({ id, factory })`，其 `require` 由 lazy CJS 模块表应答（种子词条 + 已登记工厂，首次 require 时物化并记忆化——跨插件值 import 是构建错误，协作走 cordis 服务）；插件 CSS 内联在 bundle 里、物化时注入为 `<style data-plugin="<id>">`（CSS Modules 哈希 + 归属标记 = 隔离，重载时移除）；热重载已在 dev 图落地——webserver 对自己供给的 bundle 做 stat 轮询并广播 `rebuilt` SSE 帧，`client-hmr` 插件每帧换掉一个 fiber。settled 翻转（`loader.await()` + 一次全 ACTIVE 扫描）依旧让壳从 loading 页一次切换到真 UI——settled 意味着每个 entry 已创建、每个 fiber 都到达 ACTIVE，FAILED/PENDING 的 fiber 被大声列出；不存在部分可用模式（渐进渲染为后置工作）。
 
-装载链全程：
-
-1. `GET /` → 壳启动，挂 `ctx.loader`（loader 机件由壳静态持有——装载器不能经自己装载；其代码家在 `packages/client/runtime/src/client/loader/`，壳经 `./loader` 子路径 import，避免壳 bundle 吞掉 runtime 包其余部分），把纯库实体（react、react-dom、cordis、ui-slots、web-react、ui-primitives）播种进 require 模块表，渲染一张不依赖任何插件的 loading 页。
-2. `loader.start()` 读取 `__DSH_BOOT__`。带 `immediately` 标记的条目构成先行装载组（connection、runtime、ui-theme、i18n）：并行拉取、按组内 `inject` 拓扑序 apply，**全组就位后才开始装载其余插件**。其余插件随后按 inject 序装载。
-3. 每个 bundle 执行 `window.DSHClientProxy.loadPlugin({ id, factory })`。loader 调 `factory(require)`——bundle 是闭包工厂，external 依赖经注入的 `require` 到达，从模块表解析（无全局变量、无 import map；解析不到的标识符即刻大声失败）。factory 返回其模块导出面（含 cordis `apply`）；loader 执行 `ctx.plugin(apply)`，随后**以包名把该导出面登记进模块表**——inject 拓扑保证后装插件可 `require` 先装插件。插件 CSS 内联在 bundle 里，注入为 `<style data-plugin="<id>">`（CSS Modules 哈希 + 归属标记 = 隔离）。
-4. `await loader.settled()` → 壳从 loading 页一次切换到真 UI。单插件装载失败在 loading 页大声报错；不存在部分可用模式（渐进渲染为后置工作）。
-
-**双实例禁令**：模块表包若被内联进插件 bundle，会复制运行时身份（两份 React、两套 store 注册表——一次真实白屏 P0 的根因）。tsdown client 预设在构建期把守纯度：模块表包的裸名 import 必须解析为 external（适用时改写为其 `/client` 形态），其余任何非 inline 安全 wire/类型层的 workspace 泄漏都令构建大声失败（`packages/client/tsdown.client.ts`，由 `scripts/client-bundle-purity.spec.ts` 钉住）。
-
-dev 与 prod 同链：插件在 `tsdown --watch` 下重编译，刷新即重走同一条链；vite 只管壳（`apps/web`）。类型宇宙在聚合层拆分——`tsconfig.host.json` 是 host program、`tsconfig.client.json` 是 client program，二者由 solution 根 `tsconfig.json` 引用，因为两侧都在相同键（`sessions`、`loader`）上对 cordis `Context` 做声明合并且服务不同；client 包经纯类型子路径（`@deepseek-ai/dsh-session/types` 等）消费协议词汇，host 侧的声明合并不会搭车进入 client program。
+类型宇宙在聚合层拆分——`tsconfig.host.json` 是 host program、`tsconfig.client.json` 是 client program，二者由 solution 根 `tsconfig.json` 引用，因为两侧都在相同键（`sessions`、`loader`）上对 cordis `Context` 做声明合并且服务不同；client 包经纯类型子路径（`@deepseek-ai/dsh-session/types` 等）消费协议词汇，host 侧的声明合并不会搭车进入 client program。
 
 ## slot 体系：页面怎么拼
 
@@ -112,7 +105,7 @@ src/client/
 
 ## 怎么开发
 
-- **新 UI 功能** = 新插件包：package.json 声明 `dshClient`（+ `inject` 拓扑），浏览器半边写在 `src/client/`（apply 挂服务/建 store、注册 slot），无 host 逻辑时 node 半边保持空 apply，用共享预设构建。把插件加进 host 配置；清单与装载随之自动跟上。
+- **新 UI 功能** = 新插件包：package.json 声明 `dshClient`（+ `inject` 拓扑），浏览器半边写在 `src/client/`（apply 挂服务/建 store、注册 slot），无 host 逻辑时 node 半边保持空 apply，用共享预设构建。把插件加进 host 配置；manifest 与装载随之自动跟上。
 - **新 slot**：见 [slot 体系标准 RFC](2026-07-22-slot-type-chain-implementation.md)——契约合并进 `SlotMap`，在父 entry 的 `children` 里声明，经自动注入的 `renderSlot` prop 渲染。永不全局导出组件。
 - **消费新帧类型**：带 sessionId → Session 分发 switch 加一个分支；host 级 → Manager 路由表；UI 需要时给 `ConversationSnapshot` 加字段并守住引用纪律。
 - **状态住哪**：业务数据（事件、流式、待答）→ 永远对象层；父知道的 → renderSlot 现场的 owner props；单组件私有（滚动、搜索词、展开集）→ 组件状态；跨 entry 共享或跨重挂载存活（选中、草稿、面板宽）→ entry 声明的 store（[slot 体系标准](2026-07-22-slot-type-chain-implementation.md)）。

.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.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
-2026-07-20-routed-model-context-and-compaction-policy.md: f0b9288d3d864bfcc2964862b1ff294406daa345
-2026-07-20-routed-model-context-and-compaction-policy.zh.md: cda740a5671a3ef8a5bb415e5cc45ca8397c1c59
+2026-07-20-routed-model-context-and-compaction-policy.md: b637ba24d4ba5fc25c8cdd515a821ee97883a326
+2026-07-20-routed-model-context-and-compaction-policy.zh.md: 084e762ec29ddc0aecb0bf422c147b9d3122726b

.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.md

@@ -16,7 +16,7 @@ Neither obvious configuration owner is sufficient. Compact-basic is optional and
 
 `LlmAdapter.resolveModelContext(provider, model)` optionally returns `LlmModelContext` for one exact route. `LlmService.resolveModelContext()` selects the registered route owner, validates a positive integer `contextWindow`, and returns a detached value. The query is independent of `listModels()`: an unlisted dynamic model may have capacity metadata, and `undefined` means only that the adapter cannot describe capacity.
 
-The hand-rolled DeepSeek adapter accepts optional `contextWindow` on each configured model. Its two default model entries publish 128,000 tokens; an explicit entry without capacity and an unlisted pass-through id return `undefined`. The pi-ai adapter resolves capacity from the same catalog descriptor that authoritatively resolves the request model.
+The hand-rolled DeepSeek adapter accepts optional `contextWindow` on each configured model plus an adapter-wide `defaultContextWindow`. Exact model capacity wins; an entry without capacity and an unlisted pass-through id inherit the adapter default, or return `undefined` when it is absent. The two built-in model entries each publish an exact 128,000-token capacity. The pi-ai adapter resolves capacity from the same catalog descriptor that authoritatively resolves the request model.
 
 ### Token measurement remains model-agnostic
 
@@ -36,7 +36,7 @@ An adapter that lacks capacity metadata remains a valid LLM route. Manual proact
 
 ## Testing
 
-Service tests cover detached context metadata, invalid adapter output, catalog independence, and default absence. Adapter tests cover DeepSeek configured/default/unlisted behavior and pi-ai exact descriptor resolution. Compact tests cover ratio scaling, exact provider/model overrides, load-time rejection of invalid merged ratios, runtime absolute-budget validation, same-model-id provider switches, target-specific warning suppression, and capacity-independent overflow recovery. Loader fixtures reject the removed token-meter capacity setting, and examples configure capacity on adapters.
+Service tests cover detached context metadata, invalid adapter output, catalog independence, and default absence. Adapter tests cover DeepSeek exact/default/unlisted resolution, invalid capacities, and pi-ai exact descriptor resolution. Compact tests cover ratio scaling, exact provider/model overrides, load-time rejection of invalid merged ratios, runtime absolute-budget validation, same-model-id provider switches, target-specific warning suppression, and capacity-independent overflow recovery. Loader fixtures reject the removed token-meter capacity setting, and examples configure capacity on adapters.
 
 ## Alternatives considered
 
@@ -51,7 +51,7 @@ Service tests cover detached context metadata, invalid adapter output, catalog i
 - Capacity has one authoritative owner at the provider seam, while compaction policy stays in the optional consuming plugin.
 - The same compact-basic instance safely handles different windows, provider switches, and identical model ids under different providers without consulting discovery metadata.
 - LLM-only and meter-only compositions remain valid; loading compact-basic adds no reverse dependency from adapters.
-- Deployments using explicit DeepSeek model lists must provide `contextWindow` for proactive pressure on those entries. Missing metadata is visible instead of silently applying a wrong global fallback.
+- DeepSeek deployments may set exact per-model capacities, or use `defaultContextWindow` for entries without capacity and unlisted pass-through ids.
 - Ratio defaults scale naturally across models, while exact-target absolute retention remains available for deployment-specific behavior.
 
 This note supersedes the global-capacity and no-model-policy parts of the [replay token meter service Agent Note](2026-07-15-replay-token-meter-service.md). Its single-fold measurement decision remains unchanged.

.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.zh.md

@@ -16,7 +16,7 @@ Status: implemented
 
 `LlmAdapter.resolveModelContext(provider, model)` 可以为一条精确路由返回 `LlmModelContext`。`LlmService.resolveModelContext()` 选择已注册的路由所属方，验证 `contextWindow` 为正整数，并返回分离值。该查询独立于 `listModels()`：不在目录中的动态模型也可以拥有容量元数据，而 `undefined` 只表示适配器无法描述容量。
 
-手写 DeepSeek 适配器允许每个已配置模型提供可选 `contextWindow`。两个默认模型项都公开 128,000 token；未提供容量的显式模型项与未列出的透传 id 返回 `undefined`。pi-ai 适配器从同一个目录描述符解析容量，该描述符也用于权威解析请求模型。
+手写 DeepSeek 适配器允许每个已配置模型提供可选 `contextWindow`，并支持适配器级 `defaultContextWindow`。精确模型容量优先；未提供容量的模型项与未列出的透传 id 会继承适配器默认值，若默认值也不存在则返回 `undefined`。两个内置模型项都公开精确的 128,000 token 容量。pi-ai 适配器从同一个目录描述符解析容量，该描述符也用于权威解析请求模型。
 
 ### Token 计量保持模型无关
 
@@ -36,7 +36,7 @@ Compact-basic 拥有消费方策略。顶层字段定义默认值；`modelPolici
 
 ## 测试
 
-服务测试覆盖分离上下文元数据、无效适配器输出、目录独立性与默认缺失行为。适配器测试覆盖 DeepSeek 的配置值、默认值与未列出行为，以及 pi-ai 的精确描述符解析。压缩测试覆盖比例缩放、精确提供方/模型覆盖、加载期拒绝无效合并比例、运行时校验绝对预算、相同模型 id 的提供方切换、目标专用警告抑制与不依赖容量的溢出恢复。Loader fixture 会拒绝已经移除的 token-meter 容量设置，示例则在适配器上配置容量。
+服务测试覆盖分离上下文元数据、无效适配器输出、目录独立性与默认缺失行为。适配器测试覆盖 DeepSeek 的精确容量、默认容量、未列出模型解析及无效容量，以及 pi-ai 的精确描述符解析。压缩测试覆盖比例缩放、精确提供方/模型覆盖、加载期拒绝无效合并比例、运行时校验绝对预算、相同模型 id 的提供方切换、目标专用警告抑制与不依赖容量的溢出恢复。Loader fixture 会拒绝已经移除的 token-meter 容量设置，示例则在适配器上配置容量。
 
 ## 考虑过的替代方案
 
@@ -51,7 +51,7 @@ Compact-basic 拥有消费方策略。顶层字段定义默认值；`modelPolici
 - 容量在提供方 seam 上拥有唯一权威归属方，而压缩策略留在可选消费插件中。
 - 同一个 compact-basic 实例无需查询发现元数据，就能安全处理不同窗口、提供方切换，以及不同提供方下的相同模型 id。
 - 仅 LLM 与仅 meter 的组合仍然有效；加载 compact-basic 不会让适配器产生反向依赖。
-- 使用显式 DeepSeek 模型列表的部署必须为需要主动压力检查的条目提供 `contextWindow`。系统会暴露缺失元数据，而不是静默应用错误的全局回退值。
+- DeepSeek 部署可以设置精确的逐模型容量，也可以让未提供容量的模型项与未列出的透传 id 使用 `defaultContextWindow`。
 - 比例默认值会随模型自然缩放，同时仍可按精确目标使用绝对保留值，以满足部署专用行为。
 
 本记录取代[回放式 token 计量服务 Agent Note](2026-07-15-replay-token-meter-service.md) 中的全局容量与无模型策略部分，单折叠计量决策保持不变。

.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.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
-2026-07-22-slot-type-chain-implementation.md: 1e9bd711e8316e2556fe238eb0a20d76e1d0d5b1
-2026-07-22-slot-type-chain-implementation.zh.md: 0eab839d033faac2f2c3356900c7ca1cd69d2dc9
+2026-07-22-slot-type-chain-implementation.md: 65b4ebb475fe34d71d8d3a08878b40103b3c95bd
+2026-07-22-slot-type-chain-implementation.zh.md: 4c55171ca0118782568e17f349f83d6cf9211617

.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.md

@@ -34,7 +34,7 @@ ctx.slots.register({
 
 There is no separate slot-definition API. The `children` object both **declares the child slots into existence** and **authorizes this component to render them** — a slot is a hole in the render tree that exists because someone will render it, so its lifecycle is the declaring entry's lifecycle (entry disposed → slots gone, contributions cleared). The values are the runtime spec (`kind`/`scope` drive outlet iteration and binding selection; `SlotMap` is types-only and erased at runtime, which is why an array of keys could not work), statically checked against the `SlotMap` entry so type and value are declared at one point and cross-validated.
 
-Parity rule: **the declaring entry holds the exclusive right to render its child slots**, settled entirely at register time (misconfiguration fails loud at load; the render hot path carries no checks). Loud-at-load cases: a second entry declaring an already-declared slot; registering into an undeclared slot; one store handle mounted under two scopes.
+Parity rule: **the declaring entry holds the exclusive right to render its child slots**, settled entirely at register time (misconfiguration fails loud at load; the render hot path carries no checks). Loud-at-load cases: a second entry declaring an already-declared slot; registering into an undeclared slot; one store handle mounted under two scopes; a chain registration missing its `select`.
 
 `SlotMap` declaration merging remains the type authority, and an entry declares only its own axes plus the **owner share** — the registrant's injected props never enter the global table ("whoever injects it, owns its type").
 
@@ -43,12 +43,20 @@ Parity rule: **the declaring entry holds the exclusive right to render its child
 | Share | Type | Source of truth | Contents |
 |---|---|---|---|
 | runtime | `PropsRuntime<K>` | SlotMap entry for K | `OwnerOf<K>` (render-site params) + session-scope standard `useSession`/`sessionId` + global `useSessions` |
-| child render | `PropsRenderSlots<S>` | register's `children` keys | `renderSlot(key, owner)`, key statically narrowed to S |
+| child render | `PropsRenderSlots<S>` | register's `children` keys | `renderSlot(key, owner)`, key statically narrowed to S; chain keys add `renderSlotChain` |
 | store | `PropsStore<H>` | store factory return type | `useStore` selector hook + `actions.*` (draft-param stripped) |
 | business | `I` | inject return type | plain data + callbacks (hooks banned) |
 
 `sessionId` is framework-supplied wherever `scope: 'session'` is declared — owner params do not carry it. The register call site is the double-lock choke point: a component whose renderSlot keys exceed the `children` declaration, or that misses a declared face, or whose store/inject shapes drift, is a compile error on that line. Delegation is ordinary props passing (hand the `renderSlot` function down, optionally behind a narrower signature) — there is no whitelist face object and no minting API.
 
+### The chain kind: entries self-nominate, first match renders
+
+The fourth `SlotKind`, `'chain'`, inverts routing authority relative to `keyed`: a keyed dispatch site picks its occupant by `entryKey`, while a chain entry nominates itself — the owner dispatches one common currency of owner props and never learns who takes over, so a new takeover package registers with zero owner edits. A chain registration carries a `select` pure selector (`ChainSelect<O, M>`: `(owner) => matched | null`) and an optional `priority` (ascending; ties keep registration = assembly order — the deployment-controllable inject topology — under the same stable sort as list `order`); registering without `select` is one of the loud-at-load cases above. At render, the outlet runs the selectors in chain order: the first non-null return elects its entry and the returned value joins the component's props as `matched` (the component never re-derives its own match), `null` passes the turn to the next entry, and all-null renders the owner's fallback body (`ChainRenderOpts`).
+
+The decline decision lives in `select`, never in a mounted component probing its own props: a component that mounts only to render null still runs its hooks and effects for nothing, and the resulting mount/unmount churn breaks memoization and React key semantics, whereas a selector is a pure function — unit-testable, zero mount side effects — the same discipline as "presentation methods are pure functions of `args`". Purity is the selector's contract: it reads no external mutable state and produces no side effects, so the routing decision is entirely a function of the owner props and safe to run on every dispatch. Selectors route; they never mint — per-dispatch object construction would churn identity every render, so wrapping a matched value in a richer face happens inside the elected component (`useMemo` keyed on `matched`).
+
+In the type chain, a chain entry's SlotMap shape is `{ kind: 'chain'; scope; owner }` with `owner` as the chain's currency; `M` — the `matched` prop's type — is inferred from the select return (a selector narrowing a union member types `matched` automatically), and the component position stays out of `M` inference, the same NoInfer ruling that pins the inject share (rulings below). On the owner side, `renderSlotChain(key, owner, { fallback })` joins `renderSlot` in the `PropsRenderSlots` share, its key domain statically narrowed to the chain-kind keys of the entry's children declaration (`ChainKeysOf`); the dispatch site is one line and holds no derivation or routing logic of its own.
+
 ### The store seat: framework engine, registrant schema
 
 The framework owns exactly one subscription machine: the snapshot store engine (zustand vanilla + immer + optional localStorage persistence) lives in the **runtime package** (`./client` main entry — no subpath), producing bare observable sources; web-react binds them into hooks at the outlet (per-source cached uSES binding). What a store *contains* is the registrant's declaration, written as a factory so no module-level handle exists (a module-scoped handle would be a de-facto singleton surviving plugin reloads):
@@ -93,7 +101,7 @@ Two hardening decisions in the register signature exist because the obvious alte
 
 ## Consequences
 
-Render authority is enforceable rather than conventional: who renders what is a load-time fact, and auditing the UI structure = reading the register calls. Every props surface is statically derived from one source (SlotMap entry, children keys, store factory, inject return), so a schema change propagates by compiler rather than by grep. Plugins carry no subscription machinery of their own — store lifecycle (per-session instances, disposal, persistence) is framework semantics keyed to the entry axis. Costs: registration options are dense (children spec objects); the framework carries real inference machinery (`defineStore`'s init/actions same-round inference may need a curried fallback); and the compile-time double locks mean prototype-stage drift is a hard error, not a warning.
+Render authority is enforceable rather than conventional: who renders what is a load-time fact, and auditing the UI structure = reading the register calls; for chain slots, WHO renders is additionally a render-time fact, but the deciding selectors are register-site declarations, so the audit surface stays the register calls. Every props surface is statically derived from one source (SlotMap entry, children keys, store factory, inject return), so a schema change propagates by compiler rather than by grep. Plugins carry no subscription machinery of their own — store lifecycle (per-session instances, disposal, persistence) is framework semantics keyed to the entry axis. Costs: registration options are dense (children spec objects); the framework carries real inference machinery (`defineStore`'s init/actions same-round inference may need a curried fallback); and the compile-time double locks mean prototype-stage drift is a hard error, not a warning.
 
 ## Alternatives considered
 
@@ -107,3 +115,5 @@ Render authority is enforceable rather than conventional: who renders what is a
 | Module-level store handles | A module-scope handle is a singleton across plugin reloads and test cases; the factory form scopes identity to apply/test invocation |
 | Components receiving the store instance | `update`/`set` in render code makes the mutation surface unauditable; declared actions keep "what can change" a register-site fact |
 | `FC` at the register position / inferring `I` from the component | FC statics generate covariant noise that rejects valid components; component-side inference absorbs props drift silently (see rulings above) |
+| Keyed dispatch with owner-side routing for takeover slots | The owner accumulates per-entry contracts and a hardcoded routing table (`find` + `entryKey` per takeover); the chain currency keeps new takeover registrations at zero owner edits |
+| Components declining by rendering null | Declining requires mounting first — hooks and effects run for nothing, and mount/unmount churn breaks memoization and key semantics; a pure selector decides without a component instance |

.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.zh.md

@@ -34,7 +34,7 @@ ctx.slots.register({
 
 不存在独立的坑位定义 API。`children` 对象同时做两件事：**把子坑声明出来**，并**授权本组件渲染它们**——坑是渲染树上的一个洞，因为有人要渲染它才存在，所以坑的生命周期就是声明它的 entry 的生命周期（entry 一经 dispose（资源释放），坑随之消亡、坑内既有贡献清空）。children 的值是运行时 spec（`kind`/`scope` 驱动 outlet 的迭代形态与 binding 选择；`SlotMap` 是纯类型、运行时即被擦除，这正是键数组形行不通的原因），并与对应 `SlotMap` entry 静态对齐校验——类型与值在同一点声明、交叉验证。
 
-对等原则：**声明子坑的 entry 独占渲染这些子坑的权力**，全部在 register 时结清（配置错误在装载时大声失败；渲染热径零校验）。装载即炸的情形：第二个 entry 声明已被声明的坑；向未声明的坑 register；同一个 store 句柄挂到两个 scope 之下。
+对等原则：**声明子坑的 entry 独占渲染这些子坑的权力**，全部在 register 时结清（配置错误在装载时大声失败；渲染热径零校验）。装载即炸的情形：第二个 entry 声明已被声明的坑；向未声明的坑 register；同一个 store 句柄挂到两个 scope 之下；chain 注册缺 `select`。
 
 `SlotMap` 声明合并仍是类型权威，且 entry 只声明自己的轴加 **owner 份额**——注册方注入的 props 永不进入全局表（「谁注入的，类型归谁」）。
 
@@ -43,12 +43,20 @@ ctx.slots.register({
 | 份额 | 类型 | 真源 | 内容 |
 |---|---|---|---|
 | 运行时 | `PropsRuntime<K>` | K 对应的 SlotMap entry | `OwnerOf<K>`（渲染现场传参）+ session scope 标配 `useSession`/`sessionId` + 全局 `useSessions` |
-| 子坑渲染 | `PropsRenderSlots<S>` | register 的 `children` 键集 | `renderSlot(key, owner)`，键参静态收窄到 S |
+| 子坑渲染 | `PropsRenderSlots<S>` | register 的 `children` 键集 | `renderSlot(key, owner)`，键参静态收窄到 S；chain 键另有 `renderSlotChain` |
 | store | `PropsStore<H>` | store 工厂的返回类型 | `useStore` selector hook + `actions.*`（剥去 draft 形参） |
 | 业务 | `I` | inject 的返回类型 | 普通数据+回调（禁 hook） |
 
 凡声明 `scope: 'session'` 之处，`sessionId` 一律由框架供给——owner 传参不携带它。register 调用点是双向锁的收口：组件的 renderSlot 键集超出 `children` 声明、漏接某个已声明的面、store/inject 形状漂移，任何一条都在那一行上报编译错误。转授就是普通的 props 传递（把 `renderSlot` 函数递下去，可按需包一层更窄的签名）——不存在白名单面对象，也不存在铸面 API。
 
+### chain kind：entry 自荐，首中即渲
+
+第四种 `SlotKind`——`'chain'`——把路由权相对 `keyed` 反转：keyed 的分派现场以 `entryKey` 点选占坑者，chain 则由 entry 自荐——owner 只分派一份通用货币形态的 owner props，永远不知道谁来接管，新的接管包注册进来 owner 零改动。chain 注册携带一个 `select` 纯选择器（`ChainSelect<O, M>`：`(owner) => matched | null`）与可选的 `priority`（升序；同值保持注册序 = 装配序——部署可控的 inject 拓扑——复用 list `order` 的同一稳定排序）；注册缺 `select` 即上文装载即炸情形之一。渲染时 outlet 按链序依次执行各 select：首个非 null 返回值当选，该值以 `matched` 并入组件 props（组件绝不自行重新推导匹配）；返回 `null` 则轮到下一个 entry；全 null 则渲染 owner 的 fallback 体（`ChainRenderOpts`）。
+
+「不接」的判定住在 `select` 里，绝不在挂载后的组件里自探 props：组件为了渲染 null 也得先挂载，其 hook 与 effect 全部白跑，随之而来的挂载/卸载抖动还会破坏 memo 化与 React key 语义；而选择器是纯函数——可单测、零挂载副作用——与「presentation methods are pure functions of `args`」是同一条纪律。纯，就是选择器的契约：不读外部可变状态、不产副作用，路由判定因此完全是 owner props 的函数，每次分派都可安全执行。选择器只做路由、绝不铸对象——按分派逐次构造对象会让引用每次渲染都换新；把匹配值包成更丰富的面这件事，发生在当选组件内部（以 `matched` 为依赖的 `useMemo`）。
+
+类型链上，chain entry 的 SlotMap 形状是 `{ kind: 'chain'; scope; owner }`，`owner` 即链的货币；`M`——`matched` prop 的类型——从 select 返回值推导（选择器收窄 union 成员时，`matched` 类型自动随之收窄），且组件位不参与 `M` 的推断，与钉住 inject 份额的 NoInfer 裁定同源（见下文裁定）。owner 侧，`renderSlotChain(key, owner, { fallback })` 与 `renderSlot` 同住 `PropsRenderSlots` 份额，其键域静态收窄到本 entry children 声明中 chain kind 的键（`ChainKeysOf`）；分派现场只有一行，不含任何自有的派生或路由逻辑。
+
 ### store 席位：引擎归框架，schema 归注册方
 
 框架拥有恰好一台订阅机械：快照 store 引擎（zustand vanilla + immer + 可选 localStorage 持久化）住 **runtime 包**（`./client` 主出口——无子路径），产出裸的可观察源；web-react 在 outlet 处把它们绑定成 hook（按源缓存的 uSES 绑定）。store 里*装什么*是注册方的声明，且必须写成工厂函数，使模块级句柄根本无从存在（模块级句柄会成为跨插件重载存活的事实单例）：
@@ -93,7 +101,7 @@ register 签名里的两条硬化裁定之所以存在，是因为显然的替
 
 ## Consequences
 
-渲染权威从此可强制执行，而非仅靠约定：谁渲染什么是装载期事实，审计 UI 结构 = 通读 register 调用。每个 props 面都从单一真源静态推导（SlotMap entry、children 键集、store 工厂、inject 返回值），schema 变更由编译器传播，而不靠 grep。插件不再自带任何订阅机械——store 生命周期（每会话实例、dispose、持久化）是钉在 entry 轴上的框架语义。代价：注册选项稠密（children spec 对象）；框架背上实打实的推断机械（`defineStore` 的 init/actions 同轮推断可能需要柯里化兜底）；编译期双向锁意味着原型阶段的漂移直接是硬错误，而非警告。
+渲染权威从此可强制执行，而非仅靠约定：谁渲染什么是装载期事实，审计 UI 结构 = 通读 register 调用；对 chain 坑，「谁来渲染」额外多出一层渲染期事实，但做决定的选择器全是 register 现场的声明，审计面仍是 register 调用。每个 props 面都从单一真源静态推导（SlotMap entry、children 键集、store 工厂、inject 返回值），schema 变更由编译器传播，而不靠 grep。插件不再自带任何订阅机械——store 生命周期（每会话实例、dispose、持久化）是钉在 entry 轴上的框架语义。代价：注册选项稠密（children spec 对象）；框架背上实打实的推断机械（`defineStore` 的 init/actions 同轮推断可能需要柯里化兜底）；编译期双向锁意味着原型阶段的漂移直接是硬错误，而非警告。
 
 ## Alternatives considered
 
@@ -107,3 +115,5 @@ register 签名里的两条硬化裁定之所以存在，是因为显然的替
 | 模块级 store 句柄 | 模块级句柄是跨插件重载与跨测试用例的单例；工厂形把身份圈定在单次 apply/测试调用内 |
 | 组件直收 store 实例 | 渲染代码里能用 `update`/`set`，变更面就无从审计；声明的 actions 让「什么能变」保持为 register 现场的事实 |
 | 注册位用 `FC` / 从组件推断 `I` | FC 静态位产生协变噪音、拒绝合法组件；组件侧推断静默吸收 props 漂移（见上文裁定） |
+| 接管坑用 keyed 分派 + owner 侧路由 | owner 会不断攒下逐 entry 契约与硬编码路由表（每种接管一份 `find` + `entryKey`）；chain 货币让新增接管注册保持 owner 零改动 |
+| 组件靠渲染 null 表示不接 | 不接也得先挂载——hook 与 effect 白跑，挂载/卸载抖动破坏 memo 化与 key 语义；纯选择器无需组件实例即可裁决 |

.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.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
+2026-07-23-client-plugin-loading-model.md: 58651fd258a6b2929c58bb6f93b44adb6e8e1818
+2026-07-23-client-plugin-loading-model.zh.md: f60b06c7bfaa9c70170082ac4384ba2bd899676e

.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.md

@@ -0,0 +1,132 @@
+# Agent Note: Client plugin loading — plain packages, dshClient plugins, and the two-phase boot
+
+Status: implemented
+
+English | [中文](2026-07-23-client-plugin-loading-model.zh.md)
+
+> Scope: the browser-side plugin loading machinery — what is a plugin, how code arrives, and how hot reload rides on that model. This note owns the loading chain; the [web client architecture RFC](2026-07-19-gui-web-client-architecture.md) defers to it for loading and keeps owning slots, the data object layer, and the React face.
+
+## Problem
+
+On the host, cordis plugin loading stands on Node's module machinery — the require cache and the internal ESM loader own module identity and bytes. The vendored `@cordisjs/plugin-loader` implements plugin governance and hot reload on top of that substrate, and the two meet at one seam: `Loader.internal`.
+
+The browser client runs the same cordis plugin mechanism, so it needs the same substrate underneath — and the browser has no Node module system.
+
+Conventional frontend engineering digests all dependencies at build time: one bundle, externals resolved by the bundler, nothing left to manage at runtime. Runtime module management on top of that is the unusual requirement here. The client therefore splits into two layers: the upper layer is cordis plugin loading through the same vendored Loader, and the lower layer is module-granular dependency management — `dsh-client-modules`.
+
+The lower layer supplies four capabilities: externals (the platform list), remote arrival (bundle fetch plus lazy factory registration), versioning (content-hash revs), and hot update (invalidate/prefetch).
+
+On top of that, client and host plugins register and load consistently: a package declares `dshClient` once, the host scans the declaration into the boot graph, and the same Loader semantics govern entries on both sides.
+
+The first-generation client loader (`createClientLoader`) hand-wrote both layers in one function. The fusion left no unload/reload path (loads were one-shot, style tags never removed), hand-copied dependency lists that had already drifted across three files, and a module-table backdoor for cross-plugin imports that duplicated cordis's service mechanism while making load order a correctness constraint. The structure below replaced it.
+
+## Decision
+
+### Two package kinds; `dshClient` means plugin, period
+
+What makes a package a plugin? One rule: **a package is a plugin package once its consumption is cordis dependency injection; until then it is a plain package.** How code reaches the page is not part of the taxonomy — arrival follows from the kind instead of defining it.
+
+- **Plain packages** are the absolute base the module system itself needs, plus libraries not yet converted to DI: the react family, cordis, `@deepseek-ai/dsh-client-modules` (the module system itself — it can never be a plugin, because modules precede all modules), the web shell kernel, and — for now — ui-slots, web-react, ui-primitives. Plain packages are shell-bundled, seeded into the module table, and invisible to the host graph.
+- **Plugin packages** are everything else. Each one carries a `dshClient` manifest declaration (`{ platform, inject, immediately? }`) and one uniform shape: the shared tsdown preset emits `lib/client.js`, and `exports["./client"]` points at that bundle. Each is a governed entry of the host-authored graph. Nine exist today: connection, runtime, ui-theme, i18n, hmr (dev graphs only), ui-layout, ui-sidebar, ui-conversation, ui-trajectory.
+
+The manifest owns the package's loading contract: its `inject` dependency edges, plus the optional `immediately` prefetch mark (absent means lazy). The composing app owns only the roster and the `--dev` switch.
+
+To add a plugin package: declare `dshClient`, emit the `./client` bundle through the shared preset, add the name to the composing app's roster. Nothing else changes hands.
+
+When does a plain package become a plugin? The upgrade law, recorded so the migration path stays honest: **a plain package becomes a plugin package when its consumers switch to cordis DI, not before.** Three promotions are queued: ui-slots (will receive the slots machinery now living in runtime — SlotsService, the renderer seam, the root slot), web-react (will take the renderer install into its own `apply`), and ui-primitives (once components are served through slots/services). Until then they stay plain, and their symbol exports stay ordinary static imports.
+
+Four edge rules govern imports across the two kinds. None of them depends on any per-package mark:
+
+- **Plugin ↔ plugin value imports are a build error.** This holds regardless of either side's `immediately` declaration — the rule must not depend on a mark someone can flip. Cooperation goes through cordis inject/services. `import type` is exempt; the type chain is untouched. This rule is why `scopeOf` is a `SessionsService` method and why `transportError` lives in `dsh-host-apiproxy`'s wire layer (its `RpcResult` home, inline-safe).
+- **Plugin → plain package value imports are externals**, judged against the platform list. That list is one constant in the shell (`platform.ts`: react family, cordis, ui-slots, web-react, ui-primitives), imported by both the tsdown preset (for the external judgement) and `seed.ts` (for the table warm-up). One constant, two consumers — the hand-sync drift class stays dead.
+- **The purity gate covers all nine plugin packages.** Its three branches: platform imports become externals; INLINE_SAFE wire layers are inlined; any other workspace leak is a build error. The uniform bundle shape is what makes this coverage total — every plugin builds through the same preset, so no package can sit outside the gate.
+- **The shell is self-sufficient.** The kernel (boot + loading page) value-imports no plugin package; its status stores are hand-rolled. The fail-loud presentation must not depend on the system whose failure it reports.
+
+### One module system, one plugin governor
+
+The browser mirrors the host's division of labor. `dsh-client-modules` (`ClientModuleSystem`) takes the module-system seat that Node's internal ESM loader holds host-side; the same vendored `@cordisjs/plugin-loader` keeps the governance seat on both sides. The line between them in one sentence: **the module system owns module identity and bytes — how code arrives, registers, and becomes an export surface; the Loader owns plugin lifecycle — when a plugin mounts, what it waits for, and how it is torn down.**
+
+`ClientModuleSystem` is a lazy CJS table. Executing a bundle only **registers** its factory — the bundle calls `window.__ModuleLoader__.load({ id, factory })` and nothing else happens. Every module body side effect, CSS injection included, lives inside the factory closure and runs at materialization: the first `require`/import of that id, memoized after that. A factory that requires a registered-but-unmaterialized sibling materializes it recursively, so no sort order exists anywhere. When asked to import an id, the table resolves through a fixed branch order: seed word → memoized record → static registration (shell-own modules, e.g. app-shell) → registered factory → graph-row fetch + execute → loud throw. That final throw is the runtime mirror of the build-time purity gate. The system also keeps per-module bookkeeping — owned `<style data-plugin>` tag ids, observed require edges — and exposes the two verbs HMR needs: `prefetch(id)` (fetch + execute, registration only; concurrent calls share one in-flight task) and `invalidate(id)` (drop factory, record, and consumed text so the next arrival refetches).
+
+The vendored Loader consumes the module system through its `internal` seam — the only call site is `tree.import` — and owns everything entry-shaped: entry creation, fiber activation through cordis service waiting (PENDING until injected services exist, cascading when a service is provided), update/refresh, teardown. The governance code is byte-identical to the host side, per vendor policy. Browserization is compile-time mapping in the shell's vite config: a `node:module` stub alias plus `process.*` defines make `ModuleLoader.fromInternal()` return undefined — exactly the empty slot the shell fills. The module system mounts as `ctx.modules`.
+
+### The loading flow, end to end
+
+What happens between `dsh web` starting and the UI appearing? Three stages: the host composes and serves a graph, the shell prefetches, then cordis orchestrates.
+
+**Host side — compose the graph.**
+
+1. The composing app (`apps/cli`) mounts the roster as in-memory Loader entries via `mountWebPlugins`. The roster is one flat list of the plugin packages, plus the `client-hmr` row under `--dev`. A roster package that fails to import throws loud at mount.
+2. The registry (`createHostWebPluginRegistry`) scans the mounted entries' package.json `dshClient` declarations and composes `window.__DSH_BOOT__`: `{ rev, entries: [{ id, url, rev, inject?, immediately? }] }`. The `inject` edges and the `immediately` mark come from manifests, never hand-copied. It refuses a declared plugin without a built `./client` bundle, and any malformed declaration field — load-time fail loud.
+3. The registry rescans on cordis `internal/plugin`, microtask-debounced; a rescan failure keeps serving the previous graph. Each bundle's content is hashed into its `rev` (cache busting + HMR diff anchor), and the row set into `graph.rev`. Every row is fetch-served: `/plugins/<id>/client.js?rev=…`. The graph types are a wire contract dual-held on both sides, because the webserver keeps zero workspace dependencies.
+
+Why is the roster a hand-written list and not a scan? Because which plugins compose into a deployment is a composition decision, not a package property — a dshClient package existing in the repo does not mean this deployment mounts it, so discovery-by-scan cannot make that call. The roster lives in `apps/cli/web.ts` rather than cordis.yml only because `dsh web`'s host is a hand-assembled `bootHost` with no Loader config tree yet.
+
+**Phase one — the module face.** The shell builds the module system over the graph, then prefetches every `immediately` row in parallel. Prefetch is fetch + execute, which registers factories only. A single row's prefetch failure is swallowed here: phase two's import retries the fetch and owns the loud failure, so one bad row cannot mask the others. `immediately` is a prefetch mark — not a barrier, not an identity. The package declares it, the registry carries it into the row. The infrastructure plugins (connection, runtime, ui-theme, i18n, plus hmr) declare it; UI plugins simply arrive on demand.
+
+**Phase two — the plugin face.**
+
+1. The kernel mounts the vendored Loader and injects the module system as `internal` before any entry exists. Ordering matters: `tree.import`'s bare-import fallback must never run in a browser.
+2. It creates one entry per graph row, plus the app-shell pseudo-row. The assembly entry is shell-own code the kernel appends itself — registered static with the module system, never part of the host graph — so it rides the same entry lifecycle and status coverage as everything else.
+3. Creation order carries no semantics; fibers activate through service waiting.
+4. `settled` = every entry created + `loader.await()` quiescent + an all-ACTIVE sweep. The sweep lists each import-failed, FAILED, or PENDING fiber with its missing services. It exists because cordis inject waits have no timeout — the sweep is the fail-loud floor.
+5. The loading page's boot status is a projection of real fiber states via `internal/status`. The settled flip switches to the real UI in one pass.
+
+### Hot reload: one driver plugin, self-watched bundles
+
+Whether hot reload is active is a composition decision: dev graphs include the `client-hmr` row (a normal plugin package) and turn on bundle watching; prod graphs do neither.
+
+How does a rebuilt bundle become a reload signal? The webserver observes it itself — no builder tells it. The registry scan already holds every plugin's bundle path (`clientPath`), so in dev mode the registry stat-polls each scanned bundle file with `fs.watchFile`. Polling is by design: inotify does not fire on the weka network mount, the same reason the build-side watcher needs `--poll`. On a mtime/size change the registry re-hashes that row (`rebuilt(id)`); when the `rev` actually changed, it broadcasts a `rebuilt` frame on `GET /plugins/events` — a system SSE channel that sends the full graph on connect and `rebuilt` frames on change, presentation-only wire that never enters the session log. Watch set membership follows the table: rescans add watches for new rows and drop them for vanished ones, dispose drops all. The poll interval is a validated config field (default 500ms), not a constant. Rebuilding the bundles is any tsdown watch process's business — `scripts/dev-web.ts` remains as the watch-build entry point, its package list dshClient-discovered by scanning `packages/*/*/package.json` at startup — and builder and host share zero protocol. A torn read of a half-written bundle self-heals: the stats keep changing while the write completes, so the next poll tick re-hashes again and broadcasts the final rev.
+
+On the browser side, the driver reloads one plugin per frame, serialized:
+
+1. `invalidate` — drop the stale factory and record. A live factory would make the next step a no-op.
+2. `prefetch` — fetch + execute + register the fresh factory, while the old fiber still serves.
+3. `registry.delete` — before touching the fiber. A bare fiber dispose trips the vendored Loader's self-dispose branch, which would disable the entry permanently.
+4. Drain the old fiber's disposers.
+5. Remove owned `<style data-plugin>` tags.
+6. `entry.refresh()` — re-imports, materializing the fresh factory. CSS re-injects here, under the same stable tag ids.
+7. `fiber.await()` — rethrows loud.
+
+All nine plugins share this one semantics; an `immediately` row reloads exactly like a lazy one. Dependency cascade costs zero client code: a fiber's activation epoch strings its service providers' uids, so replacing a provider's fiber re-loads every dependent through cordis itself. Reloading connection or runtime cascades the whole UI — correct, if heavy.
+
+The support boundary, stated honestly. Reload is coarse by design: fresh fiber, fresh components, React state lost, data layer untouched — react-refresh-grade state preservation conflicts with "re-executing the bundle re-runs the factory" and is deliberately out. Plain packages (react family, shell kernel, not-yet-promoted libraries) are not entries: changing them means a shell rebuild and a full page reload. No rollback in v1: an import failure leaves the entry fiberless and the next rebuilt frame retries from scratch; an apply failure leaves a FAILED fiber for the status projection; both log loudly. Self-reload works — the in-flight reload finishes in the old bundle's closure and the new apply opens a fresh SSE channel — but frames arriving in the gap are lost, and the next rebuild renotifies. One known dev-only race: a rebuilt frame overlapping a still-in-flight boot arrival shares that arrival's task and may materialize the pre-rebuild bytes; the next frame self-heals.
+
+## Package inventory (today → long term)
+
+| Package | Role | Today | Long term |
+|---|---|---|---|
+| react family / cordis | platform singletons | shell-bundled, seeded | plain forever (absolute base) |
+| vendored `@cordisjs/plugin-loader` | entry governance (same code both sides) | compile-time browserization, kernel-mounted | untouched (vendor policy) |
+| `dsh-client-modules` | the client module system | lazy CJS table; two-phase boot | plain forever (modules precede modules) |
+| `dsh-client-web` | shell kernel + AppRoot + app-shell assembly | self-sufficient (hand-rolled status stores, no plugin value imports) | keeps shrinking |
+| `dsh-client-ui-slots` | slot registry core | plain, seeded | promote to plugin; receive runtime's slots machinery |
+| `dsh-client-web-react` | ctx↔React glue | plain, seeded | promote to plugin; renderer install moves into its apply |
+| `dsh-client-ui-primitives` | base components | plain, seeded | promote to plugin (components via slots/services) |
+| `dsh-client-connection` | wire layer | plugin (dshClient + bundle), declares `immediately` | transport swap (Electron IPC carrier) |
+| `dsh-client-runtime` | session object layer + slots service + store engine | plugin, declares `immediately` | keeps shrinking toward a pure session object layer |
+| `dsh-client-ui-theme` | theme tokens/service | plugin, declares `immediately`, plus the `./styles/*` source channel | Theme Registry (separate ruling) |
+| `dsh-client-i18n` | I18nService | plugin, declares `immediately` | per-deployment locale composition |
+| `dsh-client-hmr` | hot reload driver | plugin, declares `immediately`; dev graphs only | rollback; reconnect handshake |
+| ui-layout / ui-sidebar / ui-conversation / ui-trajectory | UI features | plugins, on-demand | conversation domain split; trajectory real implementation |
+
+## Consequences
+
+One governance implementation runs on both sides of the wire; the browser-specific surface is one module system plus one reload plugin. Plugin packages have one shape, so the purity gate covers them all. Dependency edges and the boot tier live with their owners — the manifests — while the composing app holds only the roster and the `--dev` switch. The drift classes stay structurally closed: share-list hand-sync, load-order coupling, cross-plugin imports, roster/tier double bookkeeping.
+
+Costs accepted: the vendored Loader carries idle machinery in the browser (EntryTree persistence is a no-op, groups/isolation unused); every plugin edit in dev pays a bundle rebuild plus fiber remount; graph `inject` rows are informational — activation truth is service-level — so a mismatch surfaces at the settled sweep, not at graph validation; and the three not-yet-promoted libraries keep their static-import export surface until their DI conversions land.
+
+Roster endgame: when `dsh web` moves to config-tree boot, the roster lands in cordis.yml — client plugin packages become ordinary config-tree entry rows, `mountWebPlugins` and the `CLIENT_PACKAGES` constant disappear, and recomposing a deployment means swapping the yml/overlay. The registry needs zero changes for that move, since its `internal/plugin` subscription already discovers whatever entries the tree mounts.
+
+## Alternatives considered
+
+| Rejected | One-line reason |
+|---|---|
+| Two-axis taxonomy (entry × arrival) with non-dshClient infrastructure packages | Erased manifest dependency edges (inject leaked to the composer), split the plugin shape in two, blinded the purity gate to half the plugins |
+| Keep evolving the hand-written loader into a governor | Re-implements entry/fiber lifecycle the vendored Loader owns; HMR would have no shared skeleton with the host side |
+| Reuse `@cordisjs/plugin-hmr` in the browser | ~80% solves problems the browser doesn't have (fs watching, deep graph coloring, Node's dual caches); the reload skeleton is copied as a shape |
+| Module federation | Independently built remote bundles are exactly the form vite federation does not support |
+| Import maps | Ruled out earlier; the DI require table is the terminal mechanism |
+| Full ctx-ification now (react and libraries via services, no module table) | The module-axis extreme; parked — the upgrade law walks there one package at a time instead |
+| Eager instantiation with a frozen table | Requires arrival-time ordering; lazy CJS registration makes recursive `require` self-ordering and matches the naive-puller phase split |
+| Builder-push rebuild channel (`POST /plugins/rebuilt` from the orchestrator's `onSuccess`) | Couples reload to one blessed builder process and a second wire protocol; the webserver already holds every bundle path, and stat polling covers the torn-write race (re-hash on every stat change) that once justified pushing |

.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.zh.md

@@ -0,0 +1,132 @@
+# Agent Note: client 插件装载——普通包、dshClient 插件与双层 boot
+
+Status: implemented
+
+[English](2026-07-23-client-plugin-loading-model.md) | 中文
+
+> 范围：浏览器侧的插件装载机件——什么是插件、代码怎么到达、热重载如何搭在这套模型上。装载链归本篇所有；[Web 客户端架构 RFC](2026-07-19-gui-web-client-architecture.md) 在装载问题上以本篇为准，继续拥有 slot、数据对象层与 React 面。
+
+## Problem
+
+host 侧，cordis 插件装载站在 Node 的模块机制之上——require cache 与内部 ESM loader 拥有模块身份与字节。vendored `@cordisjs/plugin-loader` 在这层基座之上实现插件治理与热重载，二者在唯一一道 seam 相接：`Loader.internal`。
+
+浏览器客户端跑同一套 cordis 插件机制，因此底下需要同样的基座——而浏览器没有 Node 模块系统。
+
+常规前端工程在构建期消化全部依赖：单一 bundle，external 由打包器解决，运行时无物可管。在此之上再做运行时模块管理，正是这里的特殊需求。client 因此拆成两层：上层是经同一份 vendored Loader 的 cordis 插件装载，下层是模块粒度的依赖管理——`dsh-client-modules`。
+
+下层供给四项能力：external（平台清单）、远程到达（bundle 拉取加惰性工厂登记）、版本化（内容哈希 rev）、热更新（invalidate/prefetch）。
+
+在此之上，client 与 host 插件以一致的方式注册与装载：包声明一次 `dshClient`，host 把声明扫描进 boot 图，同一套 Loader 语义在两侧治理 entry。
+
+第一代 client loader（`createClientLoader`）把这两层手写进了同一个函数。这一融合留下的是：没有卸载/重载路径（装载一次性，style 标签从不移除）、在三个文件间人肉抄写且早已漂移的依赖清单、一条供跨插件 import 走的模块表后门——既复制了 cordis 的服务机制，又把装载顺序变成正确性约束。下文的结构取代了它。
+
+## Decision
+
+### 两类包；`dshClient` 即插件，别无他义
+
+什么让一个包成为插件？只有一条规则：**一个包的消费方式一旦是 cordis 依赖注入，它就是插件包；在此之前它是普通包。**代码怎么到达页面不属于分类体系——到达方式由包的类别推得，而不是反过来定义类别。
+
+- **普通包**是模块系统自身所需的绝对基座，加上尚未转成 DI 的库：react 家族、cordis、`@deepseek-ai/dsh-client-modules`（模块系统本身——它永远不可能是插件，因为模块先于一切模块）、web 壳内核，以及——暂时——ui-slots、web-react、ui-primitives。普通包打进壳 bundle、播种进模块表、对 host 图不可见。
+- **插件包**是其余一切。每个都携带 `dshClient` manifest（元数据清单）声明（`{ platform, inject, immediately? }`）和同一种统一形态：共享 tsdown 预设产出 `lib/client.js`，`exports["./client"]` 指向该 bundle。每个都是 host 独家撰写的图里受治理的 entry。现有九个：connection、runtime、ui-theme、i18n、hmr（仅进 dev 图）、ui-layout、ui-sidebar、ui-conversation、ui-trajectory。
+
+manifest 拥有包的装载契约：它的 `inject` 依赖边，加可选的 `immediately` 预取标记（缺省即 lazy）。负责组合的 app 只拥有名册与 `--dev` 开关。
+
+新增一个插件包：声明 `dshClient`，经共享预设产出 `./client` bundle，把包名加进负责组合的 app 的名册。除此之外无需任何交接。
+
+普通包何时升格为插件？升级法则，记录在案让迁移路径保持诚实：**普通包在其消费方改用 cordis DI 之时升格为插件包，绝不提前。**三项升格在排队：ui-slots（将接收现居 runtime 的 slots 机件——SlotsService、渲染器 seam、root slot）、web-react（将把渲染器安装收进自己的 `apply`）、ui-primitives（组件经 slot/服务供给之时）。在那之前它们保持普通包身份，符号导出保持普通的静态 import。
+
+四条边规则治理横跨两类包的 import。没有一条依赖任何单包标记：
+
+- **插件 ↔ 插件的值 import 是构建错误。**与两侧的 `immediately` 声明无关——规则不得依赖一个人人可翻转的标记。协作走 cordis inject/服务。`import type` 豁免；类型链分毫未动。这条规则正是 `scopeOf` 是 `SessionsService` 方法、`transportError` 住在 `dsh-host-apiproxy` wire 层（它的 `RpcResult` 老家，内联安全）的原因。
+- **插件 → 普通包的值 import 外置为 external**，按平台清单判定。清单是壳里的一个常量（`platform.ts`：react 家族、cordis、ui-slots、web-react、ui-primitives），tsdown 预设（external 判定）与 `seed.ts`（模块表预热）都 import 它。一个常量、两个消费方——人肉同步这一漂移缺陷类死透。
+- **纯度门禁覆盖全部九个插件包。**它的三条分支：平台 import 外置为 external；INLINE_SAFE wire 层内联；其余任何 workspace 泄漏即构建错误。正是统一的 bundle 形态让这一覆盖不留死角——每个插件都经同一预设构建，没有包能坐在门禁之外。
+- **壳自足。**内核（boot + loading 页）对任何插件包零值 import；其状态 store 为手写。大声失败的呈现不得依赖它所报告失败的那个系统。
+
+### 一套模块系统，一个插件治理器
+
+浏览器复刻 host 侧的分工。`dsh-client-modules`（`ClientModuleSystem`）坐上 host 侧由 Node 内部 ESM loader 占据的模块系统席位；同一份 vendored `@cordisjs/plugin-loader` 在两侧都坐治理席。二者的分界线一句话说尽：**模块系统拥有模块身份与字节——代码怎么到达、怎么登记、怎么变成导出面；Loader 拥有插件生命周期——插件何时挂载、等待什么、如何拆除。**
+
+`ClientModuleSystem` 是一张 lazy CJS 表。执行 bundle 只**登记**其工厂——bundle 调用 `window.__ModuleLoader__.load({ id, factory })`，此外什么都不发生。模块体的一切副作用（包括 CSS 注入）都住在工厂闭包里，在物化时运行：物化即该 id 的首次 `require`/import，此后记忆化。工厂若 require 一个已登记未物化的同伴，就递归物化它，因此任何地方都不存在排序。被要求 import 一个 id 时，表按固定分支顺序解析：种子词条 → 记忆化的记录 → 静态登记（壳自有模块，如 app-shell）→ 已登记的工厂 → 图行 fetch + 执行 → 大声抛错。最后这一抛是构建期纯度门禁在运行期的镜像。系统还保管逐模块的簿记——名下 `<style data-plugin>` 标签 id、观测到的 require 边——并暴露 HMR（热模块替换）需要的两个动词：`prefetch(id)`（fetch + 执行、只登记；并发调用共享同一在途任务）与 `invalidate(id)`（丢弃工厂、记录与已消费文本，下次到达即重新拉取）。
+
+vendored Loader 经其 `internal` seam 消费模块系统——唯一调用点是 `tree.import`——并拥有一切 entry 形状的事务：entry 创建、fiber 经 cordis 服务等待的激活（注入的服务未就位即保持 PENDING，服务 provide 时级联激活）、update/refresh、拆除。治理代码按 vendor 政策与 host 侧逐字节相同。浏览器化是壳 vite 配置里的编译期映射：一个 `node:module` stub 别名加若干 `process.*` define，使 `ModuleLoader.fromInternal()` 返回 undefined——这正是留给壳来填的空槽。模块系统挂载为 `ctx.modules`。
+
+### 装载流程，端到端
+
+从 `dsh web` 启动到 UI 出现之间发生了什么？三个阶段：host 组合并供给一张图，壳预取，然后 cordis 编排。
+
+**host 侧——组合这张图。**
+
+1. 负责组合的 app（`apps/cli`）经 `mountWebPlugins` 把名册挂载为内存中的 Loader entry。名册是插件包的一张平铺清单，`--dev` 下外加 `client-hmr` 行。名册里 import 失败的包在挂载时大声抛错。
+2. 注册表（`createHostWebPluginRegistry`）扫描已挂载 entry 的 package.json `dshClient` 声明，组合出 `window.__DSH_BOOT__`：`{ rev, entries: [{ id, url, rev, inject?, immediately? }] }`。`inject` 边与 `immediately` 标记都来自 manifest，永不人肉抄写。它拒绝声明了插件却没有已构建 `./client` bundle 的包，也拒绝任何畸形的声明字段——装载期大声失败。
+3. 注册表在 cordis `internal/plugin` 上重扫，微任务去抖；重扫失败则继续供给上一张图。每个 bundle 的内容哈希进其 `rev`（缓存失效 + HMR diff 锚点），行集合哈希进 `graph.rev`。每一行都经 fetch 供给：`/plugins/<id>/client.js?rev=…`。图的类型是两侧各持一份的 wire 契约，因为 webserver 保持零 workspace 依赖。
+
+为什么名册是手写清单而不是扫描？因为哪些插件组合进一次部署是组合决策，不是包属性——一个 dshClient 包存在于仓库里，不代表这次部署要挂载它，扫描发现无从替人做这个决定。名册住在 `apps/cli/web.ts` 而非 cordis.yml，只是因为 `dsh web` 的 host 还是一个手工装配的 `bootHost`，没有 Loader 配置树。
+
+**第一层——模块面。**壳在图之上建起模块系统，然后并行预取每个 `immediately` 行。预取即 fetch + 执行，只登记工厂。单行预取失败在这里被吞下：第二层 import 时会重试 fetch 并拥有那次大声失败，因此一个坏行藏不住其他行。`immediately` 是预取标记——不是屏障，不是身份。包声明它，注册表把它带进图行。基础设施插件（connection、runtime、ui-theme、i18n，外加 hmr）声明它；UI 插件则径直按需到达。
+
+**第二层——插件面。**
+
+1. 内核挂载 vendored Loader，在任何 entry 存在之前就把模块系统注入为 `internal`。顺序有讲究：`tree.import` 的裸 import 兜底分支在浏览器里绝不能跑到。
+2. 它为图中每一行创建 entry，外加 app-shell 伪行。装配 entry 是内核自己追加的壳自有代码——向模块系统静态登记，绝不进 host 图——因此与其余一切共乘同一套 entry 生命周期与状态覆盖。
+3. 创建顺序不携带任何语义；fiber 经服务等待激活。
+4. `settled` = 每个 entry 已创建 + `loader.await()` 停稳 + 一次全 ACTIVE 扫描。扫描列出每个 import 失败、FAILED 或 PENDING 的 fiber 及其缺失的服务。它存在的理由：cordis 的 inject 等待没有超时——这次扫描就是大声失败的兜底线。
+5. loading 页的启动状态是经 `internal/status` 对真实 fiber 状态的投影。settled 翻转即一次性切换到真实 UI。
+
+### 热重载：一个驱动插件，自行监视的 bundle
+
+热重载是否启用是一项组合决策：dev 图包含 `client-hmr` 行（一个常规的插件包）并开启 bundle 监视；prod 图两者皆无。
+
+重建好的 bundle 怎么变成重载信号？webserver 自己观察——没有构建器来通知它。注册表扫描本就握有每个插件的 bundle 路径（`clientPath`），因此 dev 模式下注册表用 `fs.watchFile` 对每个已扫描的 bundle 文件做 stat 轮询。轮询是刻意选择：inotify 在 weka 网络挂载上不触发，构建侧监视器需要 `--poll` 也是同一原因。mtime/size 一变，注册表就重哈希该行（`rebuilt(id)`）；当 `rev` 真的变了，才在 `GET /plugins/events` 上广播 `rebuilt` 帧——这是一条系统级 SSE（Server-Sent Events）通道，连接即发全量图，变更时发 `rebuilt` 帧，仅供呈现的 wire，永不进会话日志。监视集合的成员随表走：重扫为新行添加监视、为消失的行撤下监视，dispose（资源释放）撤掉全部。轮询间隔是一个经校验的配置字段（默认 500ms），不是常量。重建 bundle 则是任意一个 tsdown watch 进程的事——`scripts/dev-web.ts` 仍作为 watch 构建入口保留，其包清单在启动时扫描 `packages/*/*/package.json` 按 dshClient 发现——构建器与 host 共享零协议。写一半的 bundle 被撕裂读取会自愈：写入完成期间 stat 持续变化，下一个轮询节拍会再次重哈希并广播最终的 rev。
+
+浏览器侧，驱动插件每帧重载一个插件，串行执行：
+
+1. `invalidate`——丢弃陈旧的工厂与记录。工厂还活着会让下一步变成 no-op。
+2. `prefetch`——fetch + 执行 + 登记新工厂，旧 fiber 此刻仍在服役。
+3. `registry.delete`——先于任何 fiber 操作。裸做 fiber dispose 会触发 vendored Loader 的自 dispose 分支，把 entry 永久停用。
+4. 排空旧 fiber 的各 disposer。
+5. 移除名下的 `<style data-plugin>` 标签。
+6. `entry.refresh()`——重新 import，物化新工厂。CSS 在这里重新注入，沿用同一批稳定标签 id。
+7. `fiber.await()`——让失败大声重抛。
+
+九个插件共享这同一套语义；`immediately` 行的重载与 lazy 行分毫不差。依赖级联不花一行 client 代码：fiber 的激活纪元串接着它各服务提供方的 uid，因此换掉提供方的 fiber，每个依赖方都会经 cordis 本身重新装载。重载 connection 或 runtime 会级联整个 UI——正确，虽然重。
+
+支持边界，如实陈述。重载粒度刻意做粗：全新 fiber、全新组件、React 状态丢失、数据层不动——react-refresh 级的状态保留与「重执行 bundle 即重跑工厂」相冲突，属刻意不做。普通包（react 家族、壳内核、尚未升格的库）不是 entry：改它们意味着壳重建加整页刷新。v1 不做回滚：import 失败让 entry 失去 fiber，下一个 rebuilt 帧从头重试；apply 失败留下 FAILED fiber 交给状态投影；两者都大声记录。自我重载可行——在途的重载在旧 bundle 的闭包里跑完，新的 apply 再开一条新 SSE 通道——但空窗期到达的帧会丢失，下次重建会再次通知。一处已知的仅限 dev 竞态：rebuilt 帧与仍在途的 boot 到达重叠时共享那次到达的任务，可能物化重建前的字节；下一帧自愈。
+
+## 包盘点（现状 → 长期）
+
+| 包 | 角色 | 现状 | 长期 |
+|---|---|---|---|
+| react 家族 / cordis | 平台单例 | 打进壳，已播种 | 永为普通包（绝对基座） |
+| vendored `@cordisjs/plugin-loader` | entry 治理（两侧同一份代码） | 编译期浏览器化，内核挂载 | 不动（vendor 政策） |
+| `dsh-client-modules` | client 模块系统 | lazy CJS 模块表；双层 boot | 永为普通包（模块先于模块） |
+| `dsh-client-web` | 壳内核 + AppRoot + app-shell 装配 | 自足（手写状态 store，零插件值 import） | 持续缩小 |
+| `dsh-client-ui-slots` | slot 注册表核心 | 普通包，已播种 | 升格为插件；接收 runtime 的 slots 机件 |
+| `dsh-client-web-react` | ctx↔React 胶水 | 普通包，已播种 | 升格为插件；渲染器安装移入其 apply |
+| `dsh-client-ui-primitives` | 基础组件 | 普通包，已播种 | 升格为插件（组件经 slot/服务供给） |
+| `dsh-client-connection` | wire 层 | 插件（dshClient + bundle），声明 `immediately` | 传输替换（Electron IPC 载体） |
+| `dsh-client-runtime` | 会话对象层 + slots 服务 + store 引擎 | 插件，声明 `immediately` | 持续缩向纯会话对象层 |
+| `dsh-client-ui-theme` | 主题 token/服务 | 插件，声明 `immediately`，外加 `./styles/*` 源码通道 | Theme Registry（另行裁定） |
+| `dsh-client-i18n` | I18nService | 插件，声明 `immediately` | 按部署组合语言包 |
+| `dsh-client-hmr` | 热重载驱动 | 插件，声明 `immediately`；仅进 dev 图 | 回滚；重连握手 |
+| ui-layout / ui-sidebar / ui-conversation / ui-trajectory | UI 功能 | 插件，按需到达 | conversation 域拆分；trajectory 真实现 |
+
+## Consequences
+
+wire 两侧跑着同一份治理实现；浏览器特有的表面只是一套模块系统加一个重载插件。插件包只有一种形态，纯度门禁因此覆盖全部插件。依赖边与启动档位都与其所有者——manifest——同住，负责组合的 app 只握名册与 `--dev` 开关。各漂移缺陷类被结构性关死：共享清单人肉同步、装载顺序耦合、跨插件 import、名册/档位双重记账。
+
+接受的代价：vendored Loader 在浏览器里背着闲置机件（EntryTree 持久化是 no-op，分组/隔离未用）；开发期每次修改插件都要付一次 bundle 重建加 fiber 重挂；图中 `inject` 行仅是信息性说明——激活的真相在服务层——因此不匹配会在 settled 扫描时浮出，而不是在图校验时被拦下；三个尚未升格的库在各自的 DI 转换落地之前保持静态 import 的导出面。
+
+名册的终局：当 `dsh web` 迁到配置树 boot，名册落进 cordis.yml——client 插件包变成普通的配置树 entry 行，`mountWebPlugins` 与 `CLIENT_PACKAGES` 常量消失，重组一次部署等于换 yml/overlay。注册表为这次迁移零改动，因为它的 `internal/plugin` 订阅本就发现配置树挂载的任何 entry。
+
+## Alternatives considered
+
+| Rejected | One-line reason |
+|---|---|
+| 两轴分类体系（entry × 到达），基础设施包不带 dshClient | 抹掉了 manifest 依赖边（inject 泄漏给组合方）、把插件形态拆成两种、让纯度门禁对一半插件失明 |
+| 继续把手写 loader 演化成治理器 | 重新实现 vendored Loader 已拥有的 entry/fiber 生命周期；HMR 将与 host 侧毫无共享骨架 |
+| 在浏览器复用 `@cordisjs/plugin-hmr` | 约 80% 在解决浏览器没有的问题（fs 监听、深度图着色、Node 的双缓存）；只按形状抄用其重载骨架 |
+| 模块联邦（module federation） | 独立构建的远端 bundle 恰是 vite 联邦不支持的形态 |
+| import map | 早已排除；DI require 表是终局机制 |
+| 现在就彻底 ctx 化（react 与库全走服务，不设模块表） | 模块轴上的极端形态；搁置——升级法则改为一次一包走向它 |
+| 冻结表 + 到达即实例化 | 要求按到达时刻排序；lazy CJS 登记让递归 `require` 自行定序，且与朴素拉取器的分层相合 |
+| 构建器推送重建通道（编排器在 `onSuccess` 里 POST `/plugins/rebuilt`） | 把重载耦合到一个钦定的构建器进程和第二套 wire 协议；webserver 本就握有每个 bundle 路径，stat 轮询（每次 stat 变化即重哈希）已兜住当年为推送辩护的撕裂写竞态 |

.agents/notes/implemented/architecture/2026-07-23-unified-session-query-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
+2026-07-23-unified-session-query-service.md: 0a466e1c36ff1796c858666b0eb36bbd0f480bb0
+2026-07-23-unified-session-query-service.zh.md: 448122b8e6951058b9f633cd56112b0391e1912e

.agents/notes/implemented/architecture/2026-07-23-unified-session-query-service.md

@@ -0,0 +1,35 @@
+# Agent Note: Unified session query service
+
+Status: implemented
+
+English | [中文](2026-07-23-unified-session-query-service.zh.md)
+
+## Problem
+
+Exact reads, semantic filters, relationship traces, and full-text search operate on the same live-preferred session corpus. Exposing full-text search under a second context key makes consumers and app compositions treat one capability as two services, even though the SQLite implementation is the only backend-specific part.
+
+The interface package already owns the shared record, filter, trace, search-request, cursor, and error contracts. A provider registry or coordinator would add runtime selection semantics unsupported by any current consumer.
+
+## Decision
+
+`SessionQueryService` is the single abstract service registered as `ctx.sessionQuery`. It concretely implements listing, title and event reads, surface reads, filtering, and relationship tracing through its backend-independent `SessionCorpus`. Its only abstract methods are `searchSessions()` and `searchEvents()`.
+
+`SessionQuerySqlite` extends that service and is the sole concrete backend. One mounted instance therefore exposes every operation through `ctx.sessionQuery`; its inherited exact operations use the shared corpus implementation, while its SQLite-owned lifecycle observes sources, reconciles the derived FTS index, ranks matches, and owns cursor generations. The interface package has no standalone concrete plugin, search-provider registry, or second context key.
+
+Backend configuration includes the inherited `readWindowMax` setting alongside its own index path, journal mode, page limits, and snippet limit. First-party apps that need session queries mount the SQLite backend and place its disposable index beside their configured persistence root.
+
+This service topology supersedes the separate-key portion of the [exact query decision](../feature/2026-07-10-session-query-service.md) and [SQLite search decision](../feature/2026-07-10-sqlite-session-query-provider.md); their corpus, query, tokenizer, reconciliation, and safety decisions remain in force.
+
+## Alternatives considered
+
+- **Keep `ctx.sessionQuery` and `ctx.sessionSearch` separate** — rejected because both expose operations over one logical corpus, force consumers to discover two keys, and let apps accidentally mount only a partial query surface.
+- **Keep a concrete base service and let the SQLite plugin register or mutate two search methods** — rejected because method availability would depend on plugin order and teardown, and the service would need a provider registration protocol for one implementation.
+- **Move every query implementation into the SQLite package** — rejected because exact reads, filters, and traces require no index and are shared behavior that belongs with their provider-independent contracts.
+
+## Consequences
+
+Consumers inject one service and can combine exact and full-text operations without a second capability lookup. A production composition must choose a concrete backend even when one consumer currently calls only inherited exact methods; tests may use a minimal subclass when backend behavior is outside their scope.
+
+The unified object deliberately retains two internal observation strategies: exact operations read authoritative live/persisted sources per call, while full-text operations reconcile a disposable index. Sharing the context key does not make the derived index authoritative or couple exact-read availability to an FTS query.
+
+Unit coverage pins inherited and abstract behavior on one key, SQLite coverage exercises both operation families on the concrete backend, and the real Loader path verifies that one exported plugin registers the combined service.

.agents/notes/implemented/architecture/2026-07-23-unified-session-query-service.zh.md

@@ -0,0 +1,35 @@
+# Agent Note: 统一会话查询服务
+
+Status: implemented
+
+[English](2026-07-23-unified-session-query-service.md) | 中文
+
+## 问题
+
+精确读取、语义过滤、关系追踪与全文搜索都作用于同一个实时源优先的会话语料库。将全文搜索暴露在第二个上下文键下，会让消费方与应用组合把同一项查询功能视为两个服务，尽管只有 SQLite 实现是后端特有的部分。
+
+接口包已经拥有共享的记录、过滤、追踪、搜索请求、游标与错误契约。提供方注册表或协调器会引入运行时选择语义，而目前没有任何消费方支持这种语义。
+
+## 决策
+
+`SessionQueryService` 是注册为 `ctx.sessionQuery` 的唯一抽象服务。它通过后端无关的 `SessionCorpus` 具体实现列表查询、标题与事件读取、表层读取、过滤和关系追踪。仅有 `searchSessions()` 与 `searchEvents()` 两个方法为抽象方法。
+
+`SessionQuerySqlite` 扩展该服务，并且是唯一的具体后端。因此，一个挂载实例便可通过 `ctx.sessionQuery` 暴露全部操作；其继承的精确操作使用共享的语料库实现，而由 SQLite 管理的生命周期负责观察数据源、对齐派生 FTS 索引、对匹配项排序并管理游标代际。接口包不提供独立的具体插件、搜索提供方注册表或第二个上下文键。
+
+后端配置除了自身的索引路径、日志模式、分页限制与文本片段长度上限外，还包含继承的 `readWindowMax` 设置。需要会话查询的第一方应用挂载 SQLite 后端，并将其可丢弃索引放在已配置的持久化根目录旁。
+
+这一服务拓扑取代了[精确查询决策](../feature/2026-07-10-session-query-service.md)和 [SQLite 搜索决策](../feature/2026-07-10-sqlite-session-query-provider.md)中关于分离上下文键的部分；其中关于语料库、查询、分词器、对齐与安全性的决策仍然有效。
+
+## 已考虑的替代方案
+
+- **保留相互独立的 `ctx.sessionQuery` 与 `ctx.sessionSearch`**：不予采纳，因为二者都针对同一逻辑语料库提供操作，迫使消费方识别两个键，还可能让应用误挂载一组不完整的查询接口。
+- **保留具体的基础服务，再由 SQLite 插件注册或修改两个搜索方法**：不予采纳，因为方法是否可用将取决于插件顺序与资源释放时机，而且该服务需要为唯一的实现定义一套提供方注册协议。
+- **将所有查询实现移入 SQLite 包**：不予采纳，因为精确读取、过滤与追踪不需要索引，并且都属于应与提供方无关契约放在一起的共享行为。
+
+## 后果
+
+消费方只需注入一个服务，无需再次查找其他功能，便可组合精确操作与全文操作。生产环境的组合必须选择一个具体后端，即使当前某个消费方只调用继承的精确方法；如果后端行为不在测试范围内，测试可以使用最小子类。
+
+统一后的对象有意保留两种内部观察策略：精确操作在每次调用时读取权威的实时源或持久化源，全文操作则使可丢弃索引与数据源对齐。共用上下文键不会让派生索引成为权威来源，也不会使精确读取的可用性依赖 FTS 查询。
+
+单元测试在同一个键上同时固定继承实现与抽象方法的契约，SQLite 测试在具体后端上覆盖两类操作，真实 Loader 路径则验证单个导出的插件能够注册组合后的服务。

.agents/notes/implemented/bug-fix/2026-07-20-jsonl-storage-identity.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
+2026-07-20-jsonl-storage-identity.md: 1ada16791f411a54fbcf9271c7d7963223bbe683
+2026-07-20-jsonl-storage-identity.zh.md: 8027c51dbf6c7d01463b7851d859a40890bf03e1

.agents/notes/implemented/bug-fix/2026-07-20-jsonl-storage-identity.md

@@ -0,0 +1,29 @@
+# Agent Note: Bind JSONL session identity before mutation
+
+Status: implemented
+
+English | [中文](2026-07-20-jsonl-storage-identity.zh.md)
+
+## Problem
+
+JSONL lookup selects a physical log from the requested session id across cwd buckets, while the parsed `SessionHeader` supplies the metadata used by later repair and append operations. Without binding those two facts, a log selected for session A can declare session B's id or cwd and redirect a repair or later append to B's path. The bucket scan also needs a defined result when the same encoded id exists in more than one bucket. SQLite does not share this ambiguity because its primary-key query binds metadata and events to the requested id.
+
+## Decision
+
+`loadStored(id)` is the coordinator's single stored-prefix lookup. The JSONL backend scans every cwd bucket, requires at most one matching encoded filename, parses that file, then validates both `header.id === id` and `selectedPath === logPath(root, header.cwd, header.id)` before returning metadata. `list()` applies the same path validation and rejects duplicate ids across buckets.
+
+The coordinator independently asserts the returned id and compares the stored cwd with a live session's cwd before repair, state publication, or suffix persistence. It keeps a detached copy of validated metadata; JSONL append and repair derive their path from that copy. The `PersistenceBackend<TornMarker>` interface therefore needs neither a scope-specific live lookup nor a storage-locator type.
+
+An existing configured JSONL root must be a readable directory when the plugin loads. An absent root remains valid and is created on first materialization. The backend supports one live writer per session; another backend instance or process must not mutate that session until the owner finishes disposal and all writes stop.
+
+## Alternatives considered
+
+**Flatten storage by session id.** A flat namespace makes duplicate publication collide on one path, but path validation and duplicate rejection close the identity defect without changing the project-grouped cwd layout or its consumers.
+
+**Carry an opaque storage locator through the coordinator.** A locator binds JSONL mutations directly to a selected path, but JSONL can reproduce that path from metadata it has already validated. Adding another generic and argument to SQLite, test backends, append, and repair makes every implementation carry a concept only the file backend needs.
+
+**Coordinate multiple live writers.** A dedicated coordination service, process-global registry, or cross-process lock would define a new deployment topology rather than repair identity validation. The supported topology has one live writer; no-overwrite hard-link publication still arbitrates an initial same-id creation race.
+
+## Consequences
+
+Mismatched, misplaced, and duplicate JSONL logs fail before repair or coordinator state mutation. The cwd-bucket format stays unchanged and needs no migration. Lookup remains proportional to the number of buckets, and one-live-writer ownership remains an explicit limitation. Coordinator and JSONL tests pin rejection before repair, unchanged bytes for both affected logs, path validation during listing, duplicate-id rejection, cwd collision handling, and load-time root validation.

.agents/notes/implemented/bug-fix/2026-07-20-jsonl-storage-identity.zh.md

@@ -0,0 +1,29 @@
+# Agent Note: 在变更前绑定 JSONL 会话身份
+
+Status: implemented
+
+[English](2026-07-20-jsonl-storage-identity.md) | 中文
+
+## 问题
+
+JSONL 查找会根据请求的会话 id 在各个 cwd 分桶目录中选出物理日志，而解析得到的 `SessionHeader` 会提供后续修复和追加操作使用的元数据。如果这两个事实没有绑定，为会话 A 选中的日志就能声明会话 B 的 id 或 cwd，并将修复或后续追加重定向到 B 的路径。当同一个编码后 id 出现在多个分桶目录中时，分桶扫描也必须给出确定的结果。SQLite 不存在这种歧义，因为主键查询会将元数据和事件绑定到请求的 id。
+
+## 决策
+
+`loadStored(id)` 是协调器唯一的已存前缀查找操作。JSONL 后端扫描所有 cwd 分桶目录，要求匹配编码文件名的日志至多有一个，解析该文件，然后在返回元数据前同时验证 `header.id === id` 和 `selectedPath === logPath(root, header.cwd, header.id)`。`list()` 执行相同的路径验证，并拒绝跨分桶目录重复的 id。
+
+协调器会独立断言返回的 id，并在修复、发布状态或持久化后缀之前比较已存 cwd 和活动会话的 cwd。协调器保留一份已验证元数据的独立副本；JSONL 的追加和修复操作根据该副本派生路径。因此，`PersistenceBackend<TornMarker>` 接口既不需要限定范围的活动会话查找，也不需要存储定位器类型。
+
+如果配置的 JSONL 根目录已存在，插件加载时该路径必须是可读目录。根目录不存在仍然是有效配置，首次物化时会创建该目录。后端对每个会话只支持一个活动写入方；在所有者完成资源释放且所有写入停止之前，另一个后端实例或进程不得变更该会话。
+
+## 考虑过的替代方案
+
+**按会话 id 扁平化存储。** 扁平命名空间会让重复发布在同一路径上冲突，但路径验证和重复项拒绝无需改变按项目分组的 cwd 布局及其消费方，也能消除身份缺陷。
+
+**通过协调器传递不透明存储定位器。** 定位器可以将 JSONL 变更直接绑定到选定路径，但 JSONL 可以根据已经验证的元数据重新得到该路径。为 SQLite、测试后端、追加和修复操作增加一个泛型和参数，会让每个实现都承担只有文件后端需要的概念。
+
+**协调多个活动写入方。** 专用协调服务、进程级全局注册表或跨进程锁会定义新的部署拓扑，而不是修复身份验证。受支持的拓扑只有一个活动写入方；禁止覆盖的硬链接发布仍会裁决初始的同 id 创建竞争。
+
+## 后果
+
+JSONL 日志的身份不匹配、位置错误和重复会在修复或协调器状态变更前失败。cwd 分桶格式保持不变，无需迁移。查找开销仍与分桶目录数量成正比，单一活动写入方的所有权仍是明确限制。协调器和 JSONL 测试固定了修复前拒绝、两个受影响日志的字节均保持不变、列出时的路径验证、重复 id 拒绝、cwd 冲突处理以及加载时的根目录验证。

.agents/notes/implemented/bug-fix/2026-07-22-collapsed-sidebar-control-rail.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
-2026-07-22-collapsed-sidebar-control-rail.md: e959eef37a9e9c0fea79b82ff970daddd9257609
-2026-07-22-collapsed-sidebar-control-rail.zh.md: 7f6d6529a8aa4a655a1d3292e7f41bfb822f05a3
+2026-07-22-collapsed-sidebar-control-rail.md: 940fcabf126941cc0e411b01c337e45831e442aa
+2026-07-22-collapsed-sidebar-control-rail.zh.md: 70ace36fafcb28aa714000262e31c8555d394854

.agents/notes/implemented/bug-fix/2026-07-22-collapsed-sidebar-control-rail.md

@@ -10,11 +10,11 @@ The sidebar close action persisted a zero width preference, and the layout mappe
 
 ## Decision
 
-The layout maps a closed sidebar (persisted width `0`) to the fixed `SIDEBAR_COLLAPSED` width of 56px: a 24px icon column between the sidebar's 16px horizontal paddings. The compact rail participates in the concession solver and retains its right border, while the stored expanded width remains untouched.
+The layout maps a closed sidebar (persisted width `0`) to the fixed `SIDEBAR_COLLAPSED` width of 56px: a 24px icon column between the sidebar's 16px horizontal paddings. The sidebar track is fixed-width in the solver — open or collapsed it never concedes to viewport pressure (only details shrinks, then auto-closes) — and the rail retains its right border while the stored expanded width remains untouched.
 
 `AppFrame` marks the sidebar collapsed from the persisted width preference rather than from the resolved track width, removes the resize handle while collapsed, and passes `collapsed` to the sidebar slot as owner props from the render site. Collapse and expand animate: the frame transitions `grid-template-columns` (and the remaining handle its `left`) on the deepsuite sider curve — `--ds-ease-in-out` over `--ds-transition-duration-slow`, both supplied by ui-theme's base sheet; transitions pause during drags and under `prefers-reduced-motion`.
 
-`SidebarRoot` reads the owner `collapsed` prop and morphs in place rather than swapping renders: the four control rows persist into the rail — expand toggle, new session, new workspace, search, in the same top-down order as their expanded rows — animating their geometry (heights, paddings, margins, capsule borders) on the same curve, each aligned with its expanded counterpart's behavior (the search icon expands the sidebar and focuses the search box). Wide-only content (brand, labels, input, session tree) cross-fades out over 200ms, stays mounted while the collapse animates, and unmounts once the 300ms settle passes — dropping the sessions subscription and leaving the rendered and accessibility trees. The search query lives with the root and survives the round trip.
+`SidebarRoot` reads the owner `collapsed` prop and transitions as a slide + crossfade: the expanded content freezes at its width (inline style) and fades out in place over 150ms while the sliding grid column clips it — nothing reflows mid-slide. At settle the wide-only content (brand, labels, input, session tree) unmounts — dropping the sessions subscription and leaving the rendered and accessibility trees — and the control rows snap to the rail (open toggle, new session, new workspace, search, the same top-down order as their expanded rows) fading in as the slide ends. Each rail control keeps its expanded counterpart's behavior (the search icon expands the sidebar and focuses the search box after the slide), carries a tooltip, and the toggle rests as the whale mark with the panel icon on hover. The search query lives with the root and survives the round trip.
 
 ## Alternatives considered
 

.agents/notes/implemented/bug-fix/2026-07-22-collapsed-sidebar-control-rail.zh.md

@@ -10,11 +10,11 @@ Status: implemented
 
 ## 决策
 
-布局将关闭的侧边栏（持久化宽度为 `0`）映射为固定的 `SIDEBAR_COLLAPSED` 宽度 56px：在侧边栏两侧各 16px 的水平内边距之间放置一列 24px 的图标控件。紧凑控制栏参与空间收缩求解，并保留右侧边框；已存储的展开宽度保持不变。
+布局将关闭的侧边栏（持久化宽度为 `0`）映射为固定的 `SIDEBAR_COLLAPSED` 宽度 56px：在侧边栏两侧各 16px 的水平内边距之间放置一列 24px 的图标控件。侧边栏轨道在求解器中是定宽的——无论展开还是折叠都不向视口压力让步（只有 details 会收缩、继而自动关闭）；控制栏保留右侧边框，已存储的展开宽度保持不变。
 
 `AppFrame` 根据持久化的宽度偏好标记侧边栏是否折叠，而不是根据求解后的轨道宽度来判断；折叠时移除尺寸调整手柄，并在渲染点把 `collapsed` 作为 owner props 传给侧边栏插槽。折叠与展开带动画：frame 对 `grid-template-columns`（以及余下手柄的 `left`）应用 deepsuite 侧栏曲线过渡——`--ds-ease-in-out` 配 `--ds-transition-duration-slow`，两个变量由 ui-theme 的 base 表提供；拖拽期间和 `prefers-reduced-motion` 下过渡暂停。
 
-`SidebarRoot` 读取 owner 的 `collapsed` 属性，原地 morph 而非切换渲染：四个控件行持续存在并演变为控制栏——展开开关、新建会话、新建工作区、搜索，自上而下与展开态各行顺序一致——几何（行高、内边距、外边距、胶囊边框）走同一条曲线动画，行为与展开态对应控件对齐（搜索图标会展开侧边栏并聚焦搜索框）。宽态专属内容（品牌标识、文字标签、输入框、会话树）以 200ms 交叉淡出，折叠动画期间保持挂载，300ms settle 后卸载——随之退订会话列表并离开渲染树与可访问性树。搜索关键词由根组件持有，折叠往返后保留。
+`SidebarRoot` 读取 owner 的 `collapsed` 属性，过渡是滑动 + 交叉淡变：展开内容以内联样式冻结在原宽度、150ms 原地淡出，滑动中的网格列裁切它——滑动途中不发生任何重排。settle 时宽态专属内容（品牌标识、文字标签、输入框、会话树）卸载——随之退订会话列表并离开渲染树与可访问性树——控件行落位到控制栏（打开开关、新建会话、新建工作区、搜索，自上而下与展开态各行顺序一致），随滑动结束淡入。每个控制栏控件保持与展开态对应控件一致的行为（搜索图标展开侧边栏并在滑动结束后聚焦搜索框）并带 tooltip；开关静止时显示鲸鱼标，悬停切换为面板图标。搜索关键词由根组件持有，折叠往返后保留。
 
 ## 曾考虑的替代方案
 

.agents/notes/implemented/feature/2026-06-15-code-mode.md

@@ -38,7 +38,7 @@ This note owns Code Mode's presentation, composition, isolation, and settlement
 
 ### The run_code tool and the dispatch bridge
 
-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)`:
+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` → optional definition-owned `finalizeContent` → 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 snapshots lossless-JSON arguments, 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`. Success returns the tool's final canonical JSON value; failure becomes the program-visible `ToolCallError`. 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.

.agents/notes/implemented/feature/2026-06-25-ask-user-question.md

@@ -14,12 +14,16 @@ Introduce `dsh-user-interaction` as the provider-neutral interface package for `
 
 The model-facing request vocabulary is deliberately aligned with the product-research schema: `ask_user_question({ questions: [{ id, question, header?, options?: [{ label, description? }], multi_select? }] })`. `id` is supplied per question and echoed in the result so a batch can be routed without relying on question text. `label` is both user-facing display text and the selected value returned to the model; there is no separate `value`, no `recommended`, no `allow_custom`, and no `desc` alias.
 
-Providers return `{ answers: [{ id, selected, custom? }] }`. `selected` is always an array of selected option labels, so single-select and `multi_select` answers share one result shape. `custom` carries a free-text "Other" answer; optionless questions collect `custom` directly. When `custom` is present, it overrides any selected choices and `selected` is empty.
+Providers return `{ answers: [{ id, selected, custom? }] }`. `selected` is always an array of selected option labels, so single-select and `multi_select` answers share one result shape. `custom` carries a free-text "Other" answer; optionless questions collect `custom` directly. When `custom` is present, it overrides any selected choices and `selected` is empty. A provider that supports partial completion represents a deliberately skipped item with the existing `{ id, selected: [] }` shape, preserving the other answers without extending the tool result vocabulary.
 
 `UserInteractionError` extends `HarnessError`, so failures such as `NO_PROVIDER`, `ASK_ABORTED`, ACP cancellation, or missing session routing survive `ctx.tools.execute()` as machine-routable `{ name, code }` tool errors. This matches the structured-error taxonomy and lets the model or a wrapping plugin distinguish "user cancelled" from a generic thrown exception.
 
 ## UI mappings
 
+`dsh web` mounts `dsh-client-ui-question`, whose host half opts the Web product into the model-facing tool and whose browser half registers a `question` entry in the conversation-owned keyed composer slot. `createApiProxy` implements the Web provider with a process-memory pending table keyed by a host-minted rpcId. It registers the wait before broadcasting `question/requested`, replays the same id on every mux reopen, validates the session and complete answer batch before claiming it, and broadcasts `question/resolved` after answer, cancellation, abort, or disposal. Claiming deletes the entry synchronously, so the first valid response wins and duplicate or late responses return `not-pending`.
+
+The Web composer shows one question at a time while retaining every request in the session object layer. It supports single-select, multi-select, optionless or explicit custom answers, description text, and a visual recommendation badge without selecting the recommendation automatically. Single-select choices advance to the next item immediately, and Enter submits when every item is answered or explicitly skipped; Enter during IME composition only confirms the input candidate. The footer skips only the current item and preserves earlier drafts; the close control rejects the whole tool call with `ASK_CANCELLED`. The normal composer returns only after the host's resolved frame removes the pending item.
+
 `dsh-tui` renders each question as a keyboard overlay, shows option descriptions, supports single- and multi-select choices plus free-form custom answers, and rejects pending questions on abort, provider disposal, or terminal shutdown. Batched and simultaneous requests are queued so one overlay owns keyboard focus at a time.
 
 `dsh-acp` provides the same seam for ACP sessions. It resolves the calling `Agent` through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, and calls ACP `unstable_createElicitation` with a session-scoped form for each question. Single-select options become a `choice` string enum; `multi_select` options become a `choice` array enum; optionless questions use a required `custom` text field. If the client returns both `choice` and non-empty `custom`, the custom answer wins. ACP `decline`/`cancel`, a missing answer, a missing session, and a client without elicitation support all become structured `UserInteractionError`s.
@@ -42,8 +46,8 @@ ACP elicitation is currently marked unstable in the SDK. The fallback is still s
 
 The feature gives the model a powerful pause primitive, so prompt guidance matters. The tool description tells the model to ask concise questions and use options when possible. Product policy can later wrap `tools/execute` to restrict when the tool is allowed, but the loop should not special-case it.
 
-`dsh-user-interaction` and `dsh-tool-ask-user` both live in `packages/ui` because they form one product-facing human-interaction capability. `agent-core` does not load either the tool or a provider. `dsh-tui-demo` opts into the seam, TUI provider, and model-facing tool. `acp-agent` keeps only the `userInteraction` seam/provider by default: ACP elicitation support is still client-dependent, so an ACP leaf must opt into the model-facing tool deliberately once its client can complete elicitation requests.
+`dsh-user-interaction` and `dsh-tool-ask-user` both live in `packages/ui` because they form one product-facing human-interaction capability. `agent-core` does not load either the tool or a provider. `dsh-tui-demo` opts into the seam, TUI provider, and model-facing tool. `dsh web` boots the seam/provider in the host runtime and exposes the tool through the selected Web question plugin. `acp-agent` keeps only the `userInteraction` seam/provider by default: ACP elicitation support is still client-dependent, so an ACP leaf must opt into the model-facing tool deliberately once its client can complete elicitation requests.
 
 ## Testing
 
-Unit coverage pins provider registration/disposal, duplicate-provider rejection, abort-before-provider, empty-question rejection, structured tool errors through `ctx.tools.execute()`, batched answers, multi-select answers, custom answers, and the model schema including the removal of `value`, `recommended`, `allow_custom`, and `desc`. TUI tests cover option descriptions, queued requests, shutdown/abort cleanup, optionless free-form input, invalid choices, duplicate multi-select selections, and batched question flows. ACP bridge tests drive a real in-memory ACP connection with the real `ask_user_question` tool and verify selected-option, custom-overrides-choice, multi-select, and optionless free-form elicitation paths continue the agent loop.
+Unit coverage pins provider registration/disposal, duplicate-provider rejection, abort-before-provider, empty-question rejection, structured tool errors through `ctx.tools.execute()`, batched answers, multi-select answers, custom answers, explicit per-item skips, and the model schema including the removal of `value`, `recommended`, `allow_custom`, and `desc`. TUI tests cover option descriptions, queued requests, shutdown/abort cleanup, optionless free-form input, invalid choices, duplicate multi-select selections, and batched question flows. ACP bridge tests drive a real in-memory ACP connection with the real `ask_user_question` tool and verify selected-option, custom-overrides-choice, multi-select, and optionless free-form elicitation paths continue the agent loop. Web tests pin stable-id replay, response validation, first-wins settlement, duplicate and late responses, whole-request cancellation versus owner abort, single-select advance, IME-safe Enter submission, per-item skip preservation, composer takeover, structured batch submission, and restoration of the normal composer.

.agents/notes/implemented/feature/2026-06-30-interception-seams.md

@@ -20,15 +20,16 @@ The canonical surface separates transformable policy, around-dispatch control, a
 
 ### The tool pipeline gives each phase one kind of authority
 
-Every call follows `tools/pre-execute` → guards → `tools/execute` → dispatch → `tools/post-execute` → `tools/result`. The registry snapshots caller input, materializes and freezes arguments, and assigns an opaque token. Nested calls carry only the parent token. Identity remains immutable; only `signal` may change around dispatch. The log, UI, and tool body therefore agree on what ran.
+Every call follows `tools/pre-execute` → guards → `tools/execute` → dispatch → `tools/post-execute` → definition-owned `finalizeContent` → `tools/result`. The registry snapshots caller input, materializes and freezes arguments, assigns an opaque token, and snapshots the visible definition's final-content callback before policy begins. Nested calls carry only the parent token. Identity remains immutable; only `signal` may change around dispatch. The log, UI, and tool body therefore agree on what ran.
 
-- **`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.
+- **`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 resolved decision still reaches post-policy; a throwing listener becomes a final normalized failure.
 - **`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 replace and restore the required `exec.signal` before doing so but cannot remove it, and receives the already-normalized canonical success/failure result of a thrown or unknown tool; a wrapper-authored success short-circuits dispatch and is re-normalized through the resolved output declaration.
-- **`tools/post-execute`** is the inspect/transform waterfall. Its `PostToolDecision` accepts, blocks with feedback, replaces either presentation content or canonical value, or attaches `additionalContexts`. Value replacement revalidates and recomputes presentation; content replacement preserves programmatic value and is not a confidentiality boundary. The returned decision is the supported transform channel; after the waterfall, the registry materializes the complete outcome once before final observation.
+- **`tools/post-execute`** is the inspect/transform waterfall. Its `PostToolDecision` accepts, blocks with feedback, replaces either presentation content or canonical value, or attaches `additionalContexts`. Value replacement revalidates and recomputes presentation; content replacement preserves programmatic value and is not a confidentiality boundary. The returned decision is the supported transform channel.
+- **`ToolDefinition.finalizeContent`** is an optional synchronous, total, content-only boundary snapshotted with the visible definition at call creation. It runs exactly once after the registry has normalized and losslessly snapshotted the candidate outcome, including pre-, around-, or post-listener failures that bypass later waterfalls and errors discovered while snapshotting another result field. It may replace `content` or preserve it with `undefined`, but cannot rewrite `isError`, structured error identity, contexts, or presentation metadata. This is where a tool enforces its own last-mile content invariant without converting policy failures into weaker block decisions.
 - **`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, invalid canonical value, renderer/projector, non-JSON presentation, 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 the execution-local canonical value beside exactly the presentation fields the session log can persist. The [canonical tool-output contract](../architecture/2026-07-20-canonical-tool-output-contract.md) owns the value/projection and durability rules.
+Core dispatch and the tool body sit inside normalization boundaries, so tool, listener, invalid canonical value, renderer/projector, non-JSON presentation, 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; definition-owned final content invariants also cover outer pipeline and candidate-materialization failures; and a final observer sees the execution-local canonical value beside exactly the presentation fields the session log can persist. The [canonical tool-output contract](../architecture/2026-07-20-canonical-tool-output-contract.md) owns the value/projection and durability rules.
 
 **`TurnEndReason.rejected`** (`dsh-session`): a zero-step turn whose claimed prompt was blocked by `prompt-submit`.
 

.agents/notes/implemented/feature/2026-07-10-session-query-service.md

@@ -6,11 +6,11 @@ Status: implemented
 
 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.
+Full-text search is related but materially larger. Putting provider coordination, synchronization, invalidation, ranking, and cursor state into the exact-read service would create a second state machine beside the concrete database owner.
 
 ## Decision
 
-`@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.
+`@deepseek-ai/dsh-session-query` owns the single abstract `ctx.sessionQuery` service over one logical corpus. It concretely implements `listSessions()`, provider-independent `filterSessions(filters)`, `listEvents(sessionId)`, `filterEvents(sessionId, filters)`, bounded `readEvent(request)`, `traceSession(sessionId)`, and `traceEvent(request)`, while concrete backends implement its two full-text methods. The [unified service decision](../architecture/2026-07-23-unified-session-query-service.md) owns that topology, the [SQLite search decision](2026-07-10-sqlite-session-query-provider.md) owns search behavior, and the [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`.
 
@@ -31,10 +31,10 @@ The service is context-wide trusted infrastructure, not an authorization layer.
 - **Put logical-corpus resolution directly in every consumer** — rejected because source precedence, conflicts, optional-service lifecycle, cloning, and surface classification are shared correctness rules.
 - **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.
+- **Put provider registration into the exact-read service** — rejected because the SQLite package owns one reconciliation/transaction lifecycle; a registry would split that state without a second provider to justify it.
 
 ## Consequences
 
-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.
+The inherited exact-read implementation has one source-resolution state variable: the currently mounted persistence service. It has no provider queues, fingerprints, extractor registries, observation generations, or derived index updates; a concrete backend owns its full-text state separately. Exact reads, semantic scans, and event traces remain usable in live-only deployments and deterministic when persistence is present.
 
-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.
+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, while scale-oriented full-text methods use the concrete backend's SQLite derived index.

.agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.md

@@ -0,0 +1,57 @@
+# Agent Note: SQLite FTS5 session search
+
+Status: implemented
+
+## 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.
+
+Splitting those concerns across a provider coordinator and a database implementation would create two coupled reconciliation state machines. The first implementation needs to own source observation, extraction, SQLite transactions, generations, and query execution as one lifecycle while still exposing a small provider-neutral call contract.
+
+## Decision
+
+`@deepseek-ai/dsh-session-query` declares one abstract `ctx.sessionQuery` service whose exact reads, filters, and traces are concrete and whose two full-text methods are abstract. `searchSessions(request, exec?)` returns cursor-paginated `SessionSearchHit`s grouped by each session's strongest matching event; `searchEvents(request, exec?)` returns `SessionEventSearchHit`s within one logical session. Both requests require `query`, accept `limit` and an owned branded `SessionSearchCursor`, and support an optional abort signal. Session search accepts `sessionFilters` plus event metadata filters; event search accepts event metadata filters. Results expose bounded plain-text snippets but no provider identifier or numeric relevance score. The [unified service decision](../architecture/2026-07-23-unified-session-query-service.md) owns the single-key topology.
+
+`@deepseek-ai/dsh-session-query-sqlite` extends the interface service and is the sole concrete owner of `ctx.sessionQuery`. It depends on live `ctx.sessions`, observes optional `ctx.sessionPersistence` dynamically, and owns a dedicated derived SQLite database. There is no search-provider registry, coordinator, persistence event, or agent-loop integration.
+
+The interface package also owns shared first-party semantic extraction and provider-independent filtering. `SessionResultFilter` covers id, nullable cwd, created-at range, nullable parent, and availability; `ctx.sessionQuery.filterSessions()` applies it without an FTS provider. `SessionEventResultFilter` covers seq/time ranges, event type, surface, and literal semantic text. Arrays are ANDed and list values are ORed. The text clause escapes caller input into a Unicode case-insensitive regular expression whose whitespace runs match one or more whitespace characters; it is available through `ctx.sessionQuery.filterEvents()` and is not delegated to an FTS provider.
+
+## Search semantics
+
+Each semantic event is one FTS document carrying session metadata, event metadata, surface classification, and extracted text. All `current`, `shadowed`, and `log-only` documents participate unless a surface filter narrows them. Metadata filters compile to parameterized SQL before ranking. Session results partition matching documents by session and retain the strongest one.
+
+Ordering is deterministic and comparable across the persistent and TEMP FTS tables: actual FTS5 highlighted-match span count descending, indexed document code-point length ascending, event time descending, session id ascending for the cross-session scope, and seq descending. Snippets use those actual highlight positions, strip the reserved markers, normalize whitespace, and bound by Unicode code points. Opaque cursors bind to the service instance, scope, canonical normalized request, offset, and relevant generation. Any corpus change invalidates cross-session cursors; a within-session cursor changes only when its target source/generation changes, so unrelated sessions do not invalidate it. Reopening creates a new service instance and invalidates old cursors.
+
+Queries are trimmed, whitespace-normalized, and quoted as one literal FTS5 phrase. Embedded quotes are doubled before binding, so MATCH operators such as `OR`, `NEAR`, quotes, parentheses, and `*` remain data rather than executable query syntax. NUL is rejected before SQLite execution. Reserved highlight noncharacters and NUL in documents are normalized before indexing, making inserted presentation markers collision-free. Phrase matching follows tokenizer tokens rather than arbitrary substrings.
+
+## Tokenizer choice
+
+Both persistent and live FTS5 tables use `unicode61`. The implementation experiment found that this tokenizer supports the two-character token `AI` and produces an index about 2.1× smaller than the trigram alternative. The accepted limitation is token/phrase recall: `AI` does not match the larger token `BRAID`, and arbitrary substring search uses the provider-independent text scan instead.
+
+## Extraction and reconciliation
+
+The shared extractor includes message text, reasoning, nested tool-call/result content, tool names and arguments, blocked-prompt reasons, todo status/content, and error or terminal status detail. Structural boundaries, stream chunks, request headers, successful completion markers, and unknown declaration-merged event/content variants produce no document. Surface classification reuses `foldSurface()` so search agrees with model-history derivation.
+
+One serialized operation reads the provider-neutral `SessionPersistence` snapshot listing, compares each source-qualified opaque revision with the revision stored beside the indexed session, loads only new or changed logs, reconciles rows in one transaction, and executes the query. It never calls the backend's mutating `load()` for an id currently owned by `ctx.sessions`; the TEMP overlay records persisted availability, and the durable base refreshes after the live owner detaches. A revision identifies its backing persistence store as well as the backend-local log revision, so reopening against the same store reuses indexed rows while switching to an independent store cannot collide on a session id and local counter. Observation repeats when listing changes during a load; this incorporates a mutating load repair's refreshed revision before commit. Repeated queries and unchanged reopen load no full persisted logs. New, changed, and deleted sessions update on the next stable search. A source or extraction failure cannot mark a row current, and a transaction failure rolls back so a later search retries.
+
+Persisted documents survive restarts. Live sessions use connection-local TEMP tables, shadow the persisted base for the same id, and reveal that base on detach. Closing the database drops live rows. Unmounting persistence hides durable rows without treating absence as authoritative deletion; remounting observes and reconciles the backend again. Conflicting immutable live and durable headers fail rather than combining sources.
+
+The derived schema has its own application id and monotonic schema version. A recognized incompatible version resets only this derived database. A database with a foreign application id or unrecognized user tables is refused before journal-mode mutation, which prevents an accidentally configured canonical session database from being changed. On POSIX filesystems, missing directories and database files are created owner-only so new SQLite sidecars inherit that mode; existing modes are preserved. One service in one process exclusively owns a derived-index path; cross-process writers are unsupported because generations and live TEMP shadow state are connection-owned.
+
+Cancellation rejects queued operations and caller waits around asynchronous source observation without committing an aborted observation. Node's synchronous `DatabaseSync` MATCH call cannot be interrupted once it is executing on the JavaScript thread, so the service checks the signal at serialized boundaries but does not promise mid-statement preemption.
+
+## Alternatives considered
+
+- **Add FTS tables to the canonical persistence database** — rejected because a rebuildable index must not share the authoritative log's schema, reset, or failure boundary.
+- **Add a phase-one provider registry and coordinator** — rejected because one implementation provides no evidence for registration semantics and would split one reconciliation lifecycle across two owners.
+- **Persist live overrides immediately** — rejected because live events are not canonical until the existing checkpoint commits.
+- **Use the FTS5 trigram tokenizer** — rejected because it omits useful queries shorter than three characters and measured about 2.1× the index size of `unicode61`; literal substring filtering remains available through the scan path.
+- **Use FTS5 BM25 independently in each table** — rejected because scores from differently populated persistent and TEMP corpora are not comparable; actual matched spans and document length have one shared scale.
+
+## Consequences
+
+Search has a small provider-neutral API while its only backend owns every derived-index state transition. The separate database adds configuration and a lightweight snapshot read before queries, but index corruption, reset, and tokenizer changes cannot endanger canonical logs. Durable revisions avoid full-log reads and rewrites for unchanged sessions; TEMP live overlays preserve current-session truth without making uncheckpointed events durable.
+
+The chosen tokenizer supports short tokens with a smaller index but does not promise substring recall. Literal phrases make query syntax safe and predictable at the cost of excluding boolean/full MATCH expressions. Cancellation is effective while queued or awaiting sources, but synchronous SQLite execution remains a non-preemptible section.
+
+Unit coverage pins extraction, filters, both search scopes, all default surfaces, metadata-before-ranking, snippets, literal escaping, deterministic ties, complete pagination, scoped cursor invalidation, dynamic persistence mount/unmount, restart reconciliation, live shadow/reveal/reopen, schema safety, rollback retry, and queued/in-flight source-wait cancellation. A keyless real-Loader-path test combines the package with the real SQLite persistence backend.

.agents/notes/implemented/feature/2026-07-16-persistent-pty-sessions.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
-2026-07-16-persistent-pty-sessions.md: 76354891f557974b953a1b0b805d94330c9f6e69
-2026-07-16-persistent-pty-sessions.zh.md: 86200d70c6eda815a440c44e8b55457b0424edb6
+2026-07-16-persistent-pty-sessions.md: b33993d36753d3195ec52d3b38dda62746a47bf3
+2026-07-16-persistent-pty-sessions.zh.md: 6ed330d75824a4e6fca9de0d82db61a7c6543322

.agents/notes/implemented/feature/2026-07-16-persistent-pty-sessions.md

@@ -34,14 +34,14 @@ Idle detection is backend behavior, not a second public seam. A remote or contai
 
 There are no plugin-load auto-start sessions. `terminal_open` creates a session only during an agent tool call, when ownership and the owning event-sourced session are known. A future declarative startup feature must compose through unpublished agent setup rather than create shared global terminals.
 
-Agent-scope disposal closes registrations first, then awaits quiescent teardown of every owned PTY. Backend or tool-plugin reload does not orphan sessions: ownership lives in `PtyService` until the agent ends, following the same service-owned-record pattern as [`ctx.tasks`](../../../../packages/tasks/tasks/README.md).
+Agent-scope disposal closes registrations first, then awaits quiescent teardown of every owned PTY. Unpublished backend setup is a tracked lifecycle operation: owner or service disposal aborts its service-owned signal, waits for backend settlement and rollback, and only then returns. Caller cancellation retains its exact `AbortSignal.reason` even when the backend rejects or returns a session whose rollback close fails; that cleanup failure remains tracked for later owner or service disposal instead of replacing the caller reason. A lifecycle-triggered rollback close failure rejects both the spawn and the disposing lifecycle, while `PtyBackendCleanupError` lets a backend preserve its own failed startup cleanup for the disposing lifecycle without replacing a caller cancellation. When caller cancellation settles before disposal, the cleanup failure remains tracked owner activity until later owner or service disposal consumes and reports it, so sandbox-mode policy cannot mistake failed cleanup for quiescence. Backend or tool-plugin reload does not orphan sessions: ownership lives in `PtyService` until the agent ends, following the same service-owned-record pattern as [`ctx.tasks`](../../../../packages/tasks/tasks/README.md). The service reserves the session synchronously for one active send before returning its operation, including before a background task id becomes visible; a second send fails with `SEND_ACTIVE`, so output and cancellation cannot cross operation ownership.
 
 ### Security and process boundary
 
 A registered `shell` backend constrains how a terminal starts; it does not constrain commands typed after startup. `dsh-pty-local` therefore applies two protections before spawning:
 
 - It builds a scrubbed child environment using the same credential-shaped-name policy as `bash-local`, removing ambient `*KEY*`, `*SECRET*`, `*TOKEN*`, and harness-managed variables unless an explicit trusted mapping supplies them.
-- It requires `ctx.sandbox` and the shared `ctx.sandboxPolicy`. At spawn, the backend resolves the owner's effective session mode over the deployment default and wraps the shell argv once; that mode and workspace root remain the process boundary for the PTY lifetime. `danger-full-access` is the existing explicit unconfined choice rather than a PTY-specific bypass.
+- It requires `ctx.sandbox` and the shared `ctx.sandboxPolicy`. At spawn, the backend resolves the owner's effective session mode over the deployment default and wraps the shell argv once; that mode and workspace root remain the process boundary for the PTY lifetime. A write that would change the effective `sandbox/mode` is rejected before commit while the owner has any open PTY or unpublished spawn, with an instruction to wait for creation to settle and close those sessions first; same-effective-mode writes remain valid. The pending reservation spans backend setup through publication, so there is no race in which a wider terminal appears after a downgrade. `danger-full-access` is the existing explicit unconfined choice rather than a PTY-specific bypass.
 
 Sandboxing confines local process effects but does not make arbitrary shell input safe: network calls and other external side effects remain governed by deployment policy. Tool descriptions state that PTY sessions are less auditable than one-shot tools and should be used only when persistence or interactive stdin is necessary.
 
@@ -58,19 +58,21 @@ The implementation uses only public `node-pty` capabilities: child PID, `data` a
 | `terminal_close` | Close one session and await process-tree quiescence | `{ killed }` |
 | `terminal_list` | List the caller's live sessions | owner-scoped session summaries |
 
-`terminal_send({ sessionId, text, submit?, run_in_background? })` treats `text` as UTF-8 bytes and resolves `submit` to `true` in the tool implementation. When `submit` is true it writes the platform Enter sequence after the text; when false it writes only the text, allowing control characters and REPL fragments without hidden content heuristics.
+The ACP render contract is exact and location-free. `terminal_send` uses terminal call/result cards only for foreground sends; its background form is generic `execute`. `terminal_open`, `terminal_read`, `terminal_signal`, `terminal_close`, and `terminal_list` use generic `execute`, `read`, `execute`, `delete`, and `read` cards respectively. No PTY tool emits `locations`.
 
-Foreground sends return a bounded rendered delta and two independent facts: `waitReason` (`stdin_read | inferred_idle | timeout | session_exit`) and `sessionStatus` (`running` or `exited` with exit code or signal). `session_exit` refers to the PTY's top-level shell process, not an arbitrary foreground command whose status the shell consumes. A timeout never implies process exit.
+`terminal_send({ sessionId, text, submit?, run_in_background? })` treats `text` as UTF-8 bytes and resolves `submit` to `true` in the tool implementation. When `submit` is true it writes the platform Enter sequence after the text; when false it writes only the text, allowing control characters and REPL fragments without hidden content heuristics. `enableRunInBackground` defaults to true; false removes `run_in_background` from the schema and rejects the same undeclared argument if a caller forces it through execution.
 
-With `run_in_background: true`, `dsh-tool-pty` registers the in-flight send on `ctx.tasks` and returns immediately with `taskId`. `task_output(wait: true)` waits, reads incremental output, and records the final result; `task_kill` forwards cancellation as `SIGINT` and escalates only through the PTY backend's owned teardown path. If the task surface is absent, background mode fails before writing input. No PTY-specific `sleep` tool or general wake-up seam is added.
+Foreground sends return a bounded rendered delta and two independent facts: `waitReason` (`stdin_read | inferred_idle | timeout | session_exit`) and `sessionStatus` (`running` or `exited` with exit code or signal). `session_exit` refers to the PTY's top-level shell process, not an arbitrary foreground command whose status the shell consumes. A timeout never implies process exit. `dsh-tool-pty.maxResultBytes` defaults to 262144, rejects values below 64 so creation acknowledgements retain registry-issued ids, and caps each single-text UTF-8 result after normalized tool or pipeline errors, wait, session, pagination, truncation, generic task-status wrappers, policy denials or short-circuits, and post-execute replacements or blocks; the terminal definitions' last-mile `finalizeContent` callback leaves deliberately structured multi-block policy content unchanged. The renderer reserves suffix space and preserves code-point boundaries instead of treating the backend payload cap as the final model bound.
 
-`terminal_read` pages backward from the newest retained line. The backend enforces both line and UTF-8 byte caps on retained scrollback and the complete returned value, so one oversized line cannot bypass the bound. `truncated` distinguishes retention loss from an ordinary viewport delta.
+With `run_in_background: true`, `dsh-tool-pty` registers the in-flight send on `ctx.tasks` and returns immediately with `taskId`. The producer places `maxResultBytes` on the task snapshot so `task_output`, terminal kill status, and completion notices enforce the same complete-result cap after generic metadata. `task_output(wait: true)` waits, reads incremental output, and records the final result; `task_kill` resolves the current foreground PGID and delivers a real `SIGINT`, including when the application has disabled terminal `ISIG`, and escalates only through the PTY backend's owned teardown path. If the task surface is absent, background mode fails before writing input. No PTY-specific `sleep` tool or general wake-up seam is added.
+
+`terminal_read` pages backward from the newest retained line. The backend enforces both line and UTF-8 byte caps on retained scrollback and the returned page payload, so one oversized line cannot bypass the backend bound; the tool then caps the fully rendered page including pagination and truncation metadata. `truncated` distinguishes retention loss from an ordinary viewport delta.
 
 `terminal_signal` accepts the closed set `SIGINT | SIGTERM | SIGKILL | SIGTSTP | SIGHUP`. The backend resolves the terminal foreground process group at execution time. `SIGKILL` is rejected when that group is the top-level shell, directing the caller to `terminal_close`; a failed group lookup fails the operation instead of signaling a guessed PID.
 
 ### Local readiness detection
 
-The local backend first recognizes a private OSC prompt marker emitted by its controlled bash startup, then runs three bounded fallback tiers. The marker is removed before output reaches the model and avoids a fixed silence delay for ordinary shell commands on both platforms. Unpublished startup does not accept zero-output silence as readiness; timeout rejects the spawn. All timings are validated config fields: `pollIntervalMs`, `exactProbeAfterMs`, `idleSilenceMs`, and `timeoutMs`.
+The local backend first recognizes a private OSC prompt marker emitted by its controlled bash startup, then requires printable prompt text after that marker before declaring prompt readiness and runs three bounded fallback tiers. Carrying that state across data callbacks covers macOS delivery where the OSC marker and `PS1` arrive separately; the marker alone can no longer publish an empty MOTD. The marker is removed before output reaches the model and avoids a fixed silence delay for ordinary shell commands on both platforms. Unpublished startup does not accept zero-output silence as readiness; timeout rejects the spawn. If caller cancellation wins during startup, the backend closes the private session and propagates the exact `AbortSignal.reason`; a foreground PGID that is not observable yet cannot replace cancellation with a lookup error. All timings are validated config fields: `pollIntervalMs`, `exactProbeAfterMs`, `idleSilenceMs`, and `timeoutMs`.
 
 On Linux, the inspector reads the shell's terminal foreground PGID from `/proc/<shellPid>/stat`, enumerates every process and thread in that process group, and probes their current syscalls. A positive Tier 1 result requires an observed stdin wait: direct `read(0)`, a permitted read of a `select`/`pselect6` or `poll`/`ppoll` argument containing fd 0, or an epoll interest list containing fd 0. Unreadable process memory and unrecognized syscalls are misses, never positive guesses. Architecture tables contain only syscall numbers defined by the corresponding Linux UAPI; unsupported architectures skip Tier 1.
 
@@ -78,7 +80,7 @@ On macOS there is no exact syscall tier. Output silence returns `inferred_idle`
 
 Tier 2 returns `inferred_idle` after `idleSilenceMs` without output. A sleeping or network-blocked command can therefore look ready. Tier 3 returns `timeout` after `timeoutMs` so a foreground tool call cannot hold the agent indefinitely. The result preserves the distinction; callers may wait through `ctx.tasks`, signal the foreground group, or inspect from another session.
 
-`node-pty` data notifications feed one streaming decoder and terminal parser. Parser carry state handles UTF-8 and terminal query sequences split across chunks. The implementation normalizes line-oriented output and detects alternate-screen entry, but it does not promise correct interaction with a full-screen application.
+`node-pty` data notifications feed one terminal parser. Parser carry state handles control sequences and a trailing carriage return split across callbacks, so a divided CRLF produces one newline rather than a pagination-changing blank line. The implementation normalizes line-oriented output, but it does not promise correct interaction with a full-screen application.
 
 ### Model-visible output and durability
 
@@ -88,9 +90,9 @@ Background sends use the existing task completion notice and `task_output` resul
 
 ### Process-tree teardown
 
-The top-level `node-pty` child is the ownership anchor. On close, the backend stops callbacks, snapshots that PID and its transitive descendants by parent PID in children-first order, sends `SIGTERM`, closes the PTY, waits for quiescence, then sends `SIGKILL` to verified survivors after configurable `disposeGraceMs` and waits for them to leave the process table. Every captured PID includes process-start identity so reuse cannot redirect escalation.
+The top-level `node-pty` child is the ownership anchor. On close, the backend stops callbacks, snapshots its transitive descendants by parent PID in children-first order, sends `SIGTERM`, waits, rescans for children forked during shutdown, sends `SIGKILL` to the remaining descendant tree, and verifies that every non-zombie descendant left the process table while the shell is still alive. A matching Linux zombie has no executable work and therefore counts as quiescent, allowing shell shutdown to reap or reparent it. Only then does the backend stop the shell with its own TERM/grace/KILL sequence. Every captured PID includes process-start identity so reuse cannot redirect escalation.
 
-Teardown reports root exit and survivor cleanup independently. It does not claim success merely because the shell exited; disposal resolves only after no captured tree member remains or returns a structured cleanup failure naming the survivors. Service disposal still clears its backend, reservation, and owner-detacher registries when a close fails. It never broadens ownership to every member of the root PID's POSIX session.
+Teardown reports root exit and survivor cleanup independently. It does not claim success merely because the shell exited; disposal resolves only after no captured non-quiescent tree member remains or returns a cleanup failure naming the survivors. A failed close is not cached forever: the registry and local session each clear the fence only when it still names that failed attempt, so a later explicit or lifecycle close retries after the external survivor condition changes without disturbing a newer concurrent attempt. Service disposal still clears its backend, reservation, and owner-detacher registries when a close fails. It never broadens ownership to every member of the root PID's POSIX session.
 
 ### Composition and rollout
 
@@ -115,9 +117,12 @@ plugins:
       timeoutMs: 30000
       disposeGraceMs: 3000
   '@deepseek-ai/dsh-tool-pty':
+    config:
+      enableRunInBackground: true
+      maxResultBytes: 262144
 ```
 
-The package ships concise tool guidance explaining persistent state, owner isolation, uncertain idle results, cleanup, and the preference for existing one-shot tools when interaction is unnecessary. It does not add a global system-prompt recommendation or mount PTY in shipped defaults; dedicated ACP and headless snapshot overlays exercise the opt-in composition.
+The package ships concise tool guidance explaining persistent state, owner isolation, uncertain idle results, cleanup, and the preference for existing one-shot tools when interaction is unnecessary. It does not mount PTY in the base shipped examples: PTY is opt-in through the dedicated composition, while ACP and headless snapshot overlays exercise it. Within an enabled `dsh-tool-pty` instance, the six tools and `run_in_background` are enabled by default; deployments may disable only the background argument with config.
 
 ### Deferred work
 
@@ -147,9 +152,9 @@ The package ships concise tool guidance explaining persistent state, owner isola
 
 ## Verification
 
-- Per-file coverage pins owner fencing, concurrent reservations, lifecycle cleanup, readiness tiers, sanitizer carry state, UTF-8 bounds, task integration, schemas, and render intents.
-- Linux process fixtures cover non-leader and non-main-thread stdin waits, unreadable process state, supported syscall tables, unsupported architectures, and false-positive rejection; macOS inspector logic is injected into the same unit suite.
-- Real `node-pty` tests exercise shell state, shared sandbox policy, environment scrubbing, signals, a TERM-ignoring descendant, and immediate post-disposal quiescence on supported hosts.
+- Per-file coverage pins owner fencing, concurrent reservations, unpublished-spawn cancellation and awaited teardown, sandbox-mode change rejection, retriable lifecycle cleanup, readiness tiers, sanitizer carry state, complete UTF-8 bounds, task integration, schemas, and exact render intents.
+- Linux process fixtures cover non-leader and non-main-thread stdin waits, zombie quiescence, unreadable process state, supported syscall tables, unsupported architectures, and false-positive rejection; macOS inspector logic is injected into the same unit suite.
+- Real `node-pty` tests exercise shell state, shared sandbox policy, environment scrubbing, raw-mode foreground `SIGINT`, a TERM-ignoring descendant, and immediate post-disposal quiescence on supported hosts.
 - A Loader-driven `cordis.yml` test mounts the real three-package composition, while ACP and headless snapshots pin the six schemas, bounded results, error rendering, and terminal/generic cards through opt-in overlays.
 - Package contracts, the architecture map, core data structures, generated catalogs, and the website API describe the same shipped surface.
 - The repository CI-equivalent sequence owns type, lint, coverage, snapshot, documentation, build, hygiene, demo, and built-entry verification.

.agents/notes/implemented/feature/2026-07-16-persistent-pty-sessions.zh.md

@@ -34,14 +34,14 @@ idle 检测属于后端行为，不是第二条公共 seam。远程或容器后
 
 实现不提供插件加载期 auto-start 会话。`terminal_open` 只在 agent 工具调用期间创建会话，此时所有权和所属的事件溯源会话都已确定。未来的声明式启动功能必须通过尚未发布的 agent setup 组合，而不能创建全局共享终端。
 
-agent scope dispose 时先关闭注册，再等待全部所属 PTY 静默退出。后端或工具插件 reload 不会遗留会话：所有权持续存放在 `PtyService` 中，直到 agent 结束，与 [`ctx.tasks`](../../../../packages/tasks/tasks/README.md) 的服务持有记录模式一致。
+agent scope dispose 时先关闭注册，再等待全部所属 PTY 静默退出。未发布的后端 setup 同样是受追踪的生命周期操作：owner 或服务 dispose 会中止服务自有的 signal，等待后端结算与回滚完成后才返回。即使后端 reject，或返回的会话在回滚 close 时失败，调用方取消仍会原样保留其 `AbortSignal.reason`；该清理失败不会替换调用方原因，而会继续受追踪，留待后续 owner 或服务 dispose 处理。由 lifecycle dispose 触发的回滚 close 失败会使 spawn 与该 lifecycle dispose 都 reject，而 `PtyBackendCleanupError` 让后端在不替换调用方取消的前提下，为该 lifecycle dispose 保留自身的启动清理失败。若调用方取消先于 dispose 完成结算，该清理失败会继续作为受追踪的 owner activity 保留，直到后续 owner 或服务 dispose 消费并报告它，因此沙箱模式策略不会把清理失败误判为静默。后端或工具插件 reload 不会遗留会话：所有权持续存放在 `PtyService` 中，直到 agent 结束，与 [`ctx.tasks`](../../../../packages/tasks/tasks/README.md) 的服务持有记录模式一致。服务会先同步把会话预留给一次活跃发送，再返回该操作；后台发送同样会在 task id 对外可见前完成预留。第二次发送会以 `SEND_ACTIVE` 失败，因此输出与取消无法跨越操作所有权。
 
 ### 安全与进程边界
 
 注册的 `shell` 后端只约束终端如何启动，不约束启动后输入的命令。因此 `dsh-pty-local` 在 spawn 前应用两层保护：
 
 - 它使用与 `bash-local` 相同的凭证形态名称策略构建清洗后的子进程环境，移除环境中的 `*KEY*`、`*SECRET*`、`*TOKEN*` 和 harness 管理的变量，除非显式的可信映射提供这些值。
-- 它要求 `ctx.sandbox` 和共享的 `ctx.sandboxPolicy`。后端在 spawn 时，以部署默认值为底折叠 owner 的有效 session mode，并只包装一次 shell argv；该 mode 与 workspace root 在 PTY 的整个生命周期中充当进程边界。`danger-full-access` 是现有的显式无约束选择，不另设 PTY 私有 bypass。
+- 它要求 `ctx.sandbox` 和共享的 `ctx.sandboxPolicy`。后端在 spawn 时，以部署默认值为底折叠 owner 的有效 session mode，并只包装一次 shell argv；该 mode 与 workspace root 在 PTY 的整个生命周期中充当进程边界。只要 owner 有任何已打开的 PTY 或尚未发布的 spawn，任何会改变生效 `sandbox/mode` 的写入都会在提交前被拒绝，并提示先等待创建操作结算，再关闭这些会话；不会改变生效模式的写入仍然有效。这项进行中的预留从后端 setup 持续到发布完成，因此不存在降级后又出现权限更宽的终端这一竞态。`danger-full-access` 是现有的显式无约束选择，不另设 PTY 私有 bypass。
 
 沙箱限制本地进程副作用，但不会让任意 shell 输入自动安全：网络调用和其他外部副作用仍由部署策略治理。工具描述会说明 PTY 会话比一次性工具更难审计，只应在确实需要持久状态或交互式 stdin 时使用。
 
@@ -58,19 +58,21 @@ agent scope dispose 时先关闭注册，再等待全部所属 PTY 静默退出
 | `terminal_close` | 关闭一个会话并等待进程树静默退出 | `{ killed }` |
 | `terminal_list` | 列出调用方的活会话 | 按 owner 隔离的会话摘要 |
 
-`terminal_send({ sessionId, text, submit?, run_in_background? })` 将 `text` 视为 UTF-8 字节，并由工具实现在解析阶段把 `submit` 默认成 `true`。`submit` 为 true 时先写入文本，再写入平台 Enter 序列；为 false 时只写文本，使控制字符和 REPL 片段无需隐藏的内容启发式即可发送。
+ACP 渲染契约精确且不携带位置信息。`terminal_send` 只为前台发送使用 terminal 调用卡片和结果卡片；后台形式使用通用 `execute` 卡片。`terminal_open`、`terminal_read`、`terminal_signal`、`terminal_close` 和 `terminal_list` 分别使用通用 `execute`、`read`、`execute`、`delete` 和 `read` 卡片。所有 PTY 工具都不发出 `locations`。
 
-前台发送返回有界的渲染增量和两个独立事实：`waitReason`（`stdin_read | inferred_idle | timeout | session_exit`）与 `sessionStatus`（`running`，或携带退出码或信号的 `exited`）。`session_exit` 指 PTY 顶层 shell 进程退出，不指由 shell 消费状态的任意前台命令。timeout 从不意味着进程已经退出。
+`terminal_send({ sessionId, text, submit?, run_in_background? })` 将 `text` 视为 UTF-8 字节，并由工具实现在解析阶段把 `submit` 默认成 `true`。`submit` 为 true 时先写入文本，再写入平台 Enter 序列；为 false 时只写文本，使控制字符和 REPL 片段无需隐藏的内容启发式即可发送。`enableRunInBackground` 默认为 true；设为 false 时，schema 中会移除 `run_in_background`，调用方即使强行把这个未声明参数传入执行流程，也会被拒绝。
 
-当 `run_in_background: true` 时，`dsh-tool-pty` 在 `ctx.tasks` 上注册进行中的发送，并立即返回 `taskId`。`task_output(wait: true)` 负责等待、读取增量输出并记录最终结果；`task_kill` 将取消转发为 `SIGINT`，只有 PTY 后端拥有的 teardown 路径可以升级信号。若 task 对外接口不存在，后台模式必须在写入输入前失败。设计不新增 PTY 专用的 `sleep` 工具或通用唤醒 seam。
+前台发送返回有界的渲染增量和两个独立事实：`waitReason`（`stdin_read | inferred_idle | timeout | session_exit`）与 `sessionStatus`（`running`，或携带退出码或信号的 `exited`）。`session_exit` 指 PTY 顶层 shell 进程退出，不指由 shell 消费状态的任意前台命令。timeout 从不意味着进程已经退出。`dsh-tool-pty.maxResultBytes` 默认为 262144；低于 64 的值会被拒绝，以确保创建确认保留 registry 签发的 id；每个单文本 UTF-8 结果在加入规范化的工具或流水线错误、等待、会话、分页、截断、通用 task 状态包装、策略拒绝或短路以及 post-execute 替换或阻断后，仍受该值限制；终端定义自有的末端 `finalizeContent` callback 会原样保留策略刻意返回的结构化多 block 内容。渲染器会为后缀预留空间并保持代码点边界，而不会把后端载荷上限当作面向模型结果的最终上限。
 
-`terminal_read` 从最新保留行向后分页。后端同时对保留的 scrollback 和完整返回值执行行数与 UTF-8 字节上限，因此单个超长行无法绕过限制。`truncated` 用于区分保留数据丢失与普通 viewport 增量。
+当 `run_in_background: true` 时，`dsh-tool-pty` 在 `ctx.tasks` 上注册进行中的发送，并立即返回 `taskId`。生产方把 `maxResultBytes` 写入 task 快照，使 `task_output`、kill 返回的终态状态和完成通知在加上通用元数据后，仍对完整结果执行同一上限。`task_output(wait: true)` 负责等待、读取增量输出并记录最终结果；`task_kill` 会解析当前前台 PGID 并发送真正的 `SIGINT`，即使应用已禁用终端 `ISIG` 也同样如此，且后续升级仍只通过 PTY 后端拥有的 teardown 路径进行。若 task 对外接口不存在，后台模式必须在写入输入前失败。设计不新增 PTY 专用的 `sleep` 工具或通用唤醒 seam。
+
+`terminal_read` 从最新保留行向后分页。后端同时对保留的 scrollback 和返回页载荷执行行数与 UTF-8 字节上限，因此单个超长行无法绕过后端上限；工具随后再限制包含分页与截断元数据的完整渲染页。`truncated` 用于区分保留数据丢失与普通 viewport 增量。
 
 `terminal_signal` 接受闭合集 `SIGINT | SIGTERM | SIGKILL | SIGTSTP | SIGHUP`。后端在执行时解析终端前台进程组。当目标组是顶层 shell 时拒绝 `SIGKILL`，并指引调用方使用 `terminal_close`；进程组解析失败时操作直接失败，而不是向猜测的 PID 发送信号。
 
 ### 本地就绪检测
 
-本地后端先识别受控 bash 启动时发出的私有 OSC prompt marker，再执行 3 个有界 fallback 层级。marker 在输出到达模型前被移除，使两个平台上的普通 shell 命令都无需固定等待静默阈值。尚未发布的 startup 不会把零输出静默视为就绪；timeout 会拒绝 spawn。所有时间参数都是经校验的配置字段：`pollIntervalMs`、`exactProbeAfterMs`、`idleSilenceMs` 和 `timeoutMs`。
+本地后端先识别受控 bash 启动时发出的私有 OSC prompt marker，并且只有在该 marker 后出现可打印的 prompt 文本时才据此声明 prompt 就绪；除此之外，它还运行 3 个有界 fallback 层级。在 data callback 之间保留这项状态，可以适配 macOS 分开交付 OSC marker 与 `PS1` 的情况；单独的 marker 不会发布空 MOTD。marker 在输出到达模型前被移除，使两个平台上的普通 shell 命令都无需固定等待静默阈值。尚未发布的 startup 不会把零输出静默视为就绪；timeout 会拒绝 spawn。若调用方取消在 startup 期间胜出，后端会关闭私有会话并原样抛出 `AbortSignal.reason`；尚不可观察的前台 PGID 不会再用查找错误覆盖取消原因。所有时间参数都是经校验的配置字段：`pollIntervalMs`、`exactProbeAfterMs`、`idleSilenceMs` 和 `timeoutMs`。
 
 在 Linux 上，检查器从 `/proc/<shellPid>/stat` 读取 shell 的终端前台 PGID，枚举该进程组中的每个进程与线程，并检查它们当前的 syscall。Tier 1 只有观察到 stdin 等待才返回正结果：直接 `read(0)`、获准读取且含 fd 0 的 `select`/`pselect6` 或 `poll`/`ppoll` 参数，或者含 fd 0 的 epoll interest list。无法读取的进程内存和未识别的 syscall 都是 miss，绝不作为正向猜测。架构表只包含对应 Linux UAPI 定义的 syscall number；不支持的架构跳过 Tier 1。
 
@@ -78,7 +80,7 @@ macOS 没有精确 syscall 层。任何前台进程组输出静默都会返回 `
 
 Tier 2 在持续 `idleSilenceMs` 没有输出后返回 `inferred_idle`，因此 sleep 或网络阻塞的命令可能看似 ready。Tier 3 在 `timeoutMs` 后返回 `timeout`，避免前台工具调用无限占住 agent。结果保留这些区别；调用方可以通过 `ctx.tasks` 等待、向前台组发信号，或从另一个会话排查。
 
-`node-pty` data 通知进入同一个流式 decoder 和终端 parser。parser 的 carry 状态处理跨 chunk 的 UTF-8 与终端查询序列。当前实现只规范化行式输出并检测 alternate-screen 进入，不承诺正确操作全屏应用。
+`node-pty` data 通知进入同一个终端 parser。parser 的 carry state 会处理跨 callback 的控制序列和位于 callback 末尾的回车；因此，即使 CRLF 被拆开，也只会生成一个换行，而不会产生改变分页的空行。实现会规范化行式输出，但不承诺正确操作全屏应用。
 
 ### 模型可见输出与持久性
 
@@ -88,9 +90,9 @@ Tier 2 在持续 `idleSilenceMs` 没有输出后返回 `inferred_idle`，因此
 
 ### 进程树 teardown
 
-顶层 `node-pty` 子进程是所有权锚点。关闭时，后端先停止 callback，再按父 PID 以子进程优先顺序捕获该 PID 及其传递子进程、发送 `SIGTERM`、关闭 PTY 并等待静默，然后在可配置的 `disposeGraceMs` 后向已验证的存活者发送 `SIGKILL`，并等待它们离开进程表。每个捕获的 PID 都包含进程启动身份，避免 PID 复用把升级信号发给无关进程。
+顶层 `node-pty` 子进程是所有权锚点。关闭时，后端先停止 callback，再按父 PID 以子进程优先顺序捕获其传递子进程、发送 `SIGTERM` 并等待，然后重新扫描关停期间 fork 出的子进程，向剩余子孙进程树发送 `SIGKILL`，并在 shell 仍存活时验证每个非僵尸子孙进程都已离开进程表。身份匹配的 Linux 僵尸进程已无可执行工作，因此视为静止；shell 关闭时会回收它或将其重新挂接给负责回收的父进程。完成这些步骤后，后端才用 shell 自身的 TERM、宽限等待、KILL 序列停止 shell。每个捕获的 PID 都包含进程启动身份，避免 PID 复用把升级信号发给无关进程。
 
-teardown 独立报告根进程退出与存活进程清理。它不会只因 shell 退出就声称成功；dispose 只有在已捕获的进程树成员全部消失后才完成，否则返回结构化清理失败并列出存活者。即使某个 close 失败，服务 dispose 仍会清空其后端、预留与 owner detacher 注册表。所有权绝不会扩大到根 PID 所属 POSIX 会话的全部成员。
+teardown 独立报告根进程退出与存活进程清理。它不会只因 shell 退出就声称成功；dispose 只有在已捕获的进程树中不再存在非静止成员后才完成，否则返回清理失败并列出存活者。失败的 close 不会永久缓存：注册表与本地会话各自仅在关闭围栏仍指向该次失败尝试时才将其清除，因此外部存活进程状态改变后，后续的显式 close 或生命周期 close 会重试，且不会干扰较新的并发尝试。即使某个 close 失败，服务 dispose 仍会清空其后端、预留与 owner detacher 注册表。所有权绝不会扩大到根 PID 所属 POSIX 会话的全部成员。
 
 ### 组合与推行
 
@@ -115,9 +117,12 @@ plugins:
       timeoutMs: 30000
       disposeGraceMs: 3000
   '@deepseek-ai/dsh-tool-pty':
+    config:
+      enableRunInBackground: true
+      maxResultBytes: 262144
 ```
 
-包提供简洁的工具指引，说明持久状态、owner 隔离、不确定的 idle 结果、清理，以及无需交互时优先使用现有一次性工具。它不增加全局 system prompt 推荐，也不在已发布的默认配置中挂载 PTY；专用 ACP 与 headless 快照 overlay 覆盖 opt-in 组合。
+包提供简洁的工具指引，说明持久状态、owner 隔离、不确定的 idle 结果、清理，以及无需交互时优先使用现有一次性工具。已发布的基础示例不挂载 PTY：PTY 仅通过专用组合 opt-in，ACP 与 headless 快照 overlay 覆盖该组合。`dsh-tool-pty` 实例一旦启用，6 个工具和 `run_in_background` 就会默认启用；部署可通过配置仅禁用后台参数。
 
 ### 推迟的工作
 
@@ -147,9 +152,9 @@ plugins:
 
 ## 验证
 
-- 每文件覆盖率固定 owner 隔离、并发预留、生命周期清理、就绪层级、sanitizer carry state、UTF-8 上限、task 集成、schema 和 render intent。
-- Linux 进程 fixture 覆盖非 leader 与非主线程的 stdin 等待、不可读进程状态、受支持的 syscall 表、不支持的架构和误报拒绝；同一单元测试套件通过注入覆盖 macOS 检查器逻辑。
-- 真实 `node-pty` 测试在受支持宿主上覆盖 shell 状态、共享沙箱策略、环境清洗、信号、忽略 `SIGTERM` 的子进程，以及 dispose 返回后立即静默。
+- 每文件覆盖率固定 owner 隔离、并发预留、未发布 spawn 的取消与等待式 teardown、沙箱模式变更拒绝、可重试的生命周期清理、就绪层级、sanitizer carry state、完整 UTF-8 结果上限、task 集成、schema 和精确 render intent。
+- Linux 进程 fixture 覆盖非 leader 与非主线程的 stdin 等待、僵尸进程静止性、不可读进程状态、受支持的 syscall 表、不支持的架构和误报拒绝；同一单元测试套件通过注入覆盖 macOS 检查器逻辑。
+- 真实 `node-pty` 测试在受支持宿主上覆盖 shell 状态、共享沙箱策略、环境清洗、raw mode 下的前台 `SIGINT`、忽略 `SIGTERM` 的子进程，以及 dispose 返回后立即静默。
 - Loader 驱动的 `cordis.yml` 测试挂载真实三包组合；ACP 与 headless 快照通过 opt-in overlay 固定 6 个 schema、有界结果、错误渲染和 terminal/generic card。
 - 包契约、架构图、核心数据结构、生成目录和 website API 描述同一个已发布接口。
 - 仓库 CI 等价序列负责类型、lint、覆盖率、快照、文档、构建、hygiene、demo 和 built-entry 验证。

.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.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
-2026-07-20-dsh-cli-personal-config.md: 514bb5b12a3e04c7deaad1e8616472eed1c920e1
-2026-07-20-dsh-cli-personal-config.zh.md: 16fada82c59c8a356e6df112234e6b7565aae1bf
+2026-07-20-dsh-cli-personal-config.md: 9525aa811d792a918f03a52c21bc273e92fb8be7
+2026-07-20-dsh-cli-personal-config.zh.md: f21d4b1f22b3a3807b6b4155969282343f6048f5

.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md

@@ -12,7 +12,7 @@ A developer's own preferences — which provider and model the TUI uses, persona
 
 Two coupled pieces, aligned with the `apps/` assembly tier proposed by the `dsh web` PR (#443):
 
-**The `dsh` CLI (`apps/cli`, npm name `@deepseek-ai/dsh`).** `apps/*` joins the workspaces as the product-assembly tier over `packages/*` libraries. The bin's dispatch reserves `web` and `-p`/`--prompt` for PR #443 (they exit with a pointer) so the two branches merge as a near-union; everything else runs the default surface: the interactive TUI, booting the shipped `examples/tui-agent/cordis.yml` (or an explicit config argument) with the invoking directory as the workspace. The committed `bin/dsh` launcher resolves the checkout through its own real path and runs the bin **from source** via the repo's tsx (with `--expose-internals` for the config's HMR entry), so `ln -sf "$(pwd)/bin/dsh" ~/.local/bin/dsh` installs a command that always executes the current working tree. `pnpm run demo:tui` runs the same entry.
+**The `dsh` CLI (`apps/cli`, npm name `@deepseek-ai/dsh`).** `apps/*` joins the workspaces as the product-assembly tier over `packages/*` libraries. The bin's dispatch reserves `web` and `-p`/`--prompt` for PR #443 (they exit with a pointer) so the two branches merge as a near-union; everything else runs the default surface: the interactive TUI, booting the shipped `examples/tui-agent/cordis.yml` (or an explicit config argument) with the invoking directory as the workspace. The committed `bin/dsh` launcher resolves the checkout through its own real path and runs the bin **from source** via the repo's tsx, so `ln -sf "$(pwd)/bin/dsh" ~/.local/bin/dsh` installs a command that always executes the current working tree. `pnpm run demo:tui` runs the same entry.
 
 **Personal config (`dsh-app-boot`).** The personal overlay lives in the Harness home — `$DSH_HOME`, else `~/.dsh` — resolved by the shared [`resolveDshHome`](../architecture/2026-07-24-single-harness-home-resolver.md) (`@deepseek-ai/dsh-paths`), the same single root skills and AGENTS.md resolve against. The dsh TUI surface consumes its two optional files; the demo bins boot their committed trees verbatim:
 

.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.zh.md

@@ -12,7 +12,7 @@ Status: implemented
 
 两个耦合的部分，与 `dsh web` PR（#443）提出的 `apps/` 装配层对齐：
 
-**`dsh` CLI（`apps/cli`，npm 名 `@deepseek-ai/dsh`）。** `apps/*` 作为 `packages/*` 库之上的产品装配层加入 workspaces。bin 的分发把 `web` 和 `-p`/`--prompt` 保留给 PR #443（它们以指引退出），使两个分支能以接近并集的方式合并；其余一切都运行默认表面：交互式 TUI，加载随仓库提供的 `examples/tui-agent/cordis.yml`（或显式的配置参数），并以调用目录为工作区。已提交的 `bin/dsh` 启动器通过自身真实路径解析 checkout，用仓库的 tsx **从源码**运行该 bin（带 `--expose-internals`，供配置里的 HMR 配置项使用），因此 `ln -sf "$(pwd)/bin/dsh" ~/.local/bin/dsh` 安装的命令永远执行当前工作树。`pnpm run demo:tui` 运行同一入口。
+**`dsh` CLI（`apps/cli`，npm 名 `@deepseek-ai/dsh`）。** `apps/*` 作为 `packages/*` 库之上的产品装配层加入 workspaces。bin 的分发把 `web` 和 `-p`/`--prompt` 保留给 PR #443（它们以指引退出），使两个分支能以接近并集的方式合并；其余一切都运行默认表面：交互式 TUI，加载随仓库提供的 `examples/tui-agent/cordis.yml`（或显式的配置参数），并以调用目录为工作区。已提交的 `bin/dsh` 启动器通过自身真实路径解析 checkout，用仓库的 tsx **从源码**运行该 bin，因此 `ln -sf "$(pwd)/bin/dsh" ~/.local/bin/dsh` 安装的命令永远执行当前工作树。`pnpm run demo:tui` 运行同一入口。
 
 **个人配置（`dsh-app-boot`）。** 个人 overlay 存放在 Harness home——`$DSH_HOME`，否则 `~/.dsh`——由共享的 [`resolveDshHome`](../architecture/2026-07-24-single-harness-home-resolver.md)（`@deepseek-ai/dsh-paths`）解析，与 skills、AGENTS.md 解析所依据的单一根目录相同。dsh 的 TUI 表面消费其中两个可选文件；各示例 bin 仍然逐字节按已提交的配置树启动：
 

.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.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
-2026-07-21-log-backed-session-titles.md: cd0d2a4bab9b6504c65e942c0e03bce79488364e
-2026-07-21-log-backed-session-titles.zh.md: b90ac6c59677e6542733210b91de38ef1169c760
+2026-07-21-log-backed-session-titles.md: 183aa6909fecffdaf18c77c2a66fbc38c67c2d2c
+2026-07-21-log-backed-session-titles.zh.md: c6a0c2ce2ad4b2cddec2ada36f655fe55adb143b

.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md

@@ -12,7 +12,7 @@ Session identity metadata is immutable, the event log is the replay and fork bou
 
 ## Decision
 
-The [`session-title` capability family](../../../../packages/session-title/README.md) owns title state and generation policy. `@deepseek-ai/dsh-session-title` provides `ctx.sessionTitle`, a deterministic first-message fallback, and a registry for at most one optional asynchronous provider. `@deepseek-ai/dsh-session-title-llm` owns the common auxiliary-model request policy; separate first-message and all-user-messages plugins choose input cadence. The shared agent spine mounts only the fallback service with overridable explicit example limits, leaving both model providers opt-in.
+The [`session-title` capability family](../../../../packages/session-title/README.md) owns title state and generation policy. `@deepseek-ai/dsh-session-title` provides `ctx.sessionTitle`, a deterministic first-message fallback, and a registry for at most one optional asynchronous provider. `@deepseek-ai/dsh-session-title-llm` owns the common auxiliary-model request policy; separate first-message and all-user-messages plugins choose input cadence. The shared agent spine mounts only the fallback service. The Web host mounts that service plus the first-message model provider with explicit overridable limits, so a fresh Web session gains an immediate fallback and then a non-blocking model summary. Other compositions choose either model provider explicitly.
 
 ### Event ownership and folding
 
@@ -32,7 +32,7 @@ The first-message provider schedules once when a fresh session first creates its
 
 `register(provider)` validates one branded stable id, cadence, and generation function, then returns an awaitable effect disposer. A second live registration throws immediately. Provider disposal marks the registration closing, aborts its pending and active work, and waits for every call to settle before removing the registration, so replacement cannot overlap a provider that ignores cancellation. Session disposal aborts its active work. Service teardown prevents queued fallback and provider microtasks from starting, aborts active work, and drains tracked promises before unloading completes. Every session-local generation has a monotonic revision and exact registration identity; acceptance rechecks revision, registration, session liveness, service liveness, and cancellation, so stale output cannot commit.
 
-Model providers require explicit word, CJK-character, input-byte, output-token, and timeout limits. Optional `provider` and `model` overrides are a pair; without them the helper uses the exact route from the logged main request header. Selected messages are framed as JSON under one fixed language-aware instruction. The input limit measures that final user prompt, including wrappers, seq fields, and JSON escaping, before the request is logged or dispatched. Oversized input is rejected rather than truncated because truncation would make the recorded source seqs falsely imply complete use. The fused deadline is checked while consuming each stream chunk and after completion, so a successful result returned after timeout cannot be accepted even when an interceptor or adapter ignores abort.
+Model providers require explicit word, CJK-character, input-byte, output-token, and timeout limits. Optional `provider` and `model` overrides are a pair; without them the helper uses the exact route from the logged main request header. Selected messages are framed as JSON under one fixed language-aware instruction. The dispatched `GenerateOptions` carries `purpose: 'session-title'`; the DeepSeek adapter maps that purpose to thinking-disabled and omits reasoning effort so the bounded output is visible title text, while the main conversation keeps its configured thinking mode. The input limit measures the final user prompt, including wrappers, seq fields, and JSON escaping, before the request is logged or dispatched. Oversized input is rejected rather than truncated because truncation would make the recorded source seqs falsely imply complete use. The fused deadline is checked while consuming each stream chunk and after completion, so a successful result returned after timeout cannot be accepted even when an interceptor or adapter ignores abort.
 
 Automatic provider failures are nonfatal warnings and retain the latest title. Explicit refresh failures reject to the caller. Output must be non-empty text with unique ordered seqs drawn from the fixed request; the service normalizes and byte-limits it before durable acceptance.
 
@@ -40,7 +40,7 @@ Automatic provider failures are nonfatal warnings and retain the latest title. E
 
 A fork inherits seed title events unchanged, like the rest of its source log. The first-message provider does not automatically retitle a fork. The all-messages provider may append a child-owned revision after a later child prompt, using inherited and new eligible messages.
 
-`ctx.sessionQuery.readTitle()` folds one live-preferred or persisted log without loading titles during `listSessions()`. ACP maps the event to `session_info_update` during both live streaming and load replay, using the event timestamp for `updatedAt`. The TUI uses the latest title as its header subtitle and sets the terminal window title to `<session title> — <configured product title>` after terminal-safe rendering. A synthetic title turn remains a completed durability boundary for the metadata write; consumers reporting agent completion use the core `findLastMessageTurnEnd()` fold so a later title, injection, or other plugin-owned turn cannot replace the preceding message-triggered outcome.
+`ctx.sessionQuery.readTitle()` folds one live-preferred or persisted log without loading titles during `listSessions()`. ACP maps the event to `session_info_update` during both live streaming and load replay, using the event timestamp for `updatedAt`. The TUI uses the latest title as its header subtitle and sets the terminal window title to `<session title> — <configured product title>` after terminal-safe rendering. The Web host folds the same log state into a validated mux control frame after each attached-session subscription baseline and immediately after forwarding a live raw title event. The browser retains only newer title event seqs even when the control frame precedes list or session-instance creation; sidebar labels, search, breadcrumbs, and the browser title then react to the projected revision. `session.list` remains metadata-only, so a cold persisted session uses the cwd basename or id until opening or resuming it attaches the log. The browser title uses `<session title> — <existing HTML title>` only for a selected titled session and otherwise preserves the product title. A synthetic title turn remains a completed durability boundary for the metadata write; consumers reporting agent completion use the core `findLastMessageTurnEnd()` fold so a later title, injection, or other plugin-owned turn cannot replace the preceding message-triggered outcome.
 
 ## Alternatives considered
 
@@ -50,11 +50,13 @@ A fork inherits seed title events unchanged, like the rest of its source log. Th
 - **Permit multiple registered providers and resolve precedence after completion** — rejected because completion order is not product precedence and would make retries, HMR, and provenance nondeterministic. A deployment that needs a composite policy can register one provider that owns that policy.
 - **Silently truncate oversized auxiliary input** — rejected because the provider result would claim exact source-message provenance while receiving only partial text. Keeping the prior title and warning preserves truthful attribution.
 - **Index titles in `listSessions()` immediately** — rejected because the existing lightweight metadata list would need per-backend derived-index synchronization. Exact `readTitle()` establishes the read contract without precommitting search or indexing policy.
+- **Keep the Web host fallback-only** — rejected because the UI would expose durable titles but never improve them beyond the first-prompt prefix. The first-message provider keeps its latency off the main response path while making model summaries the default Web outcome.
 
 ## Consequences
 
 - Titles survive JSONL and SQLite persistence, replay through ACP, and follow fork inheritance without a separate mutable record.
-- A fallback appears without an auxiliary call; deployments choose whether better titles justify model cost and whether later prompts should retitle a session.
+- Web title delivery stays incremental and log-backed without a title index or persisted-list scan; cold list rows improve after attach.
+- A fallback appears immediately. Each fresh Web session adds one first-message auxiliary call; other compositions choose whether better titles justify model cost and whether later prompts should retitle a session.
 - Auxiliary request records and late accepted titles consume event seqs and may create balanced zero-step turns, so persistence exposes both attempted dispatches and accepted updates even though model history and KV-cache identity do not change.
 - One provider and monotonic per-session revisions make disposal, supersession, and stale-result rejection explicit, at the cost of leaving multi-strategy precedence to a composite provider.
 - Manual rename, deletion, generated-versus-user precedence, search, and list indexing remain outside the capability.

.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.zh.md

@@ -12,7 +12,7 @@ Status: implemented
 
 ## 决策
 
-[`session-title` 功能包族](../../../../packages/session-title/README.md)负责标题状态和生成策略。`@deepseek-ai/dsh-session-title` 提供 `ctx.sessionTitle`、确定性的首消息回退方案，以及一个至多接受单个可选异步提供方的注册表。`@deepseek-ai/dsh-session-title-llm` 负责通用的辅助模型请求策略；首消息插件和全部用户消息插件分别选择输入调度方式。共享 agent 主干只挂载回退服务，并为其显式设置可覆盖的示例限制；两种模型提供方均需按需启用。
+[`session-title` 功能包族](../../../../packages/session-title/README.md)负责标题状态和生成策略。`@deepseek-ai/dsh-session-title` 提供 `ctx.sessionTitle`、确定性的首消息回退方案，以及一个至多接受单个可选异步提供方的注册表。`@deepseek-ai/dsh-session-title-llm` 负责通用的辅助模型请求策略；首消息插件和全部用户消息插件分别选择输入调度方式。共享 agent 主干只挂载回退服务。Web host 会挂载该服务和首消息模型提供方，并显式设置可覆盖的限制，因此新建的 Web 会话会立即获得回退标题，随后在不阻塞主响应的情况下获得模型摘要。其他组合需显式选择任一模型提供方。
 
 ### 事件归属与折叠
 
@@ -32,7 +32,7 @@ Status: implemented
 
 `register(provider)` 会验证一个带品牌类型的稳定 id、执行时机和生成函数，然后返回一个可等待完成的 effect 资源释放函数。第二个活跃注册会立即抛出错误。提供方执行资源释放时，会将注册标记为正在关闭，中止其待执行和活跃工作，并等待所有调用结束后才移除注册，因此替代提供方不会与忽略取消的旧提供方重叠运行。会话资源释放会中止其活跃工作。服务卸载时，会阻止排队中的回退和提供方微任务启动，中止活跃工作，并且卸载完成前会等待所有已跟踪的 promise 结算。每项会话本地生成都有单调递增的修订号和对应的注册身份；接受结果时会重新检查修订号、注册、会话活跃状态、服务活跃状态和取消状态，因此陈旧输出无法提交。
 
-模型提供方必须显式配置单词数、CJK 字符数、输入字节数、输出 token 数和超时限制。可选的 `provider` 和 `model` 覆盖项必须成对提供；两者均未提供时，辅助组件会使用主请求已记录请求头中的准确路由。系统在一条固定且能区分语言的指令下，将选中的消息封装为 JSON。输入字节数按最终形成的用户提示词计算，其中包括包装文本、seq 字段和 JSON 转义；系统会在记录请求或发起调用前完成这项检查。过大输入会被拒绝而不是截断，因为截断会让记录的源消息 seq 错误地表示这些消息已被完整使用。系统在消费每个流分片时以及流完成后都会检查融合后的截止时间，因此即使拦截器或适配器忽略中止信号，超时后返回的成功结果也不会被接受。
+模型提供方必须显式配置单词数、CJK 字符数、输入字节数、输出 token 数和超时限制。可选的 `provider` 和 `model` 覆盖项必须成对提供；两者均未提供时，辅助组件会使用主请求已记录请求头中的准确路由。系统在一条固定且能区分语言的指令下，将选中的消息封装为 JSON。发出的 `GenerateOptions` 携带 `purpose: 'session-title'`；DeepSeek 适配器将该用途映射为禁用思考且省略推理强度设置的请求，使受限输出成为可见的标题文本，而主对话仍沿用已配置的思考模式。输入字节数按最终形成的用户提示词计算，其中包括包装文本、seq 字段和 JSON 转义；系统会在记录请求或发起调用前完成这项检查。过大输入会被拒绝而不是截断，因为截断会让记录的源消息 seq 错误地表示这些消息已被完整使用。系统在消费每个流分片时以及流完成后都会检查融合后的截止时间，因此即使拦截器或适配器忽略中止信号，超时后返回的成功结果也不会被接受。
 
 自动提供方故障只会发出非致命警告，并保留最新标题。显式刷新失败则会向调用方返回拒绝。输出必须是非空文本，并包含来自固定请求、唯一且有序的 seq；服务会在持久接受前对其进行规范化并施加字节限制。
 
@@ -40,7 +40,7 @@ Status: implemented
 
 与源日志的其他部分相同，fork 会原样继承作为种子的标题事件。首消息提供方不会自动为 fork 重新生成标题。全部消息提供方可以在子会话出现后续提示词后追加一项归子会话所有的修订，并使用继承的合格消息和新增的合格消息。
 
-`ctx.sessionQuery.readTitle()` 会折叠一份实时优先或已持久化的日志，而不会在 `listSessions()` 期间加载标题。ACP（Agent Client Protocol）会在实时流式输出和加载回放期间把该事件映射到 `session_info_update`，并使用事件时间戳作为 `updatedAt`。TUI 使用最新标题作为其标题栏副标题，并在完成终端安全渲染后，将终端窗口标题设置为 `<session title> — <configured product title>`。合成标题轮次本身仍会完成，并作为元数据写入的持久性边界；报告 agent 完成情况的消费方使用核心的 `findLastMessageTurnEnd()` 折叠逻辑，因此后续的标题轮次、注入轮次或其他归插件所有的轮次无法取代此前由消息触发的结果。
+`ctx.sessionQuery.readTitle()` 会折叠一份实时优先或已持久化的日志，而不会在 `listSessions()` 期间加载标题。ACP（Agent Client Protocol）会在实时流式输出和加载回放期间把该事件映射到 `session_info_update`，并使用事件时间戳作为 `updatedAt`。TUI 使用最新标题作为其标题栏副标题，并在完成终端安全渲染后，将终端窗口标题设置为 `<session title> — <configured product title>`。Web host 会在每个已附加会话的订阅基线之后，以及转发实时原始标题事件后立即，将同一份日志状态折叠为经过校验的 mux 控制帧。即使控制帧先于列表或会话实例创建抵达，浏览器也只保留标题事件 seq 较新的版本；侧边栏标签、搜索、面包屑和浏览器标题会随投影后的修订更新。`session.list` 仍只包含元数据，因此尚未打开的持久化会话会继续以 cwd 基名或 id 作为回退，直至打开或恢复会话时附加其日志。浏览器仅在选中已有标题的会话时将标题设置为 `<session title> — <existing HTML title>`，否则保留产品标题。合成标题轮次本身仍会完成，并作为元数据写入的持久性边界；报告 agent 完成情况的消费方使用核心的 `findLastMessageTurnEnd()` 折叠逻辑，因此后续的标题轮次、注入轮次或其他归插件所有的轮次无法取代此前由消息触发的结果。
 
 ## 考虑过的替代方案
 
@@ -50,11 +50,13 @@ Status: implemented
 - **允许注册多个提供方，并在完成后解析优先级**：不予采纳，因为完成顺序并不等于产品优先级，而且会让重试、HMR 和来源信息变得不确定。需要组合策略的部署可以注册一个自行负责该策略的提供方。
 - **静默截断过大的辅助输入**：不予采纳，因为提供方结果会声明准确的源消息来源信息，实际却只接收了部分文本。保留原有标题并发出警告，可以保持归因真实。
 - **立即在 `listSessions()` 中索引标题**：不予采纳，因为现有的轻量元数据列表将需要逐后端同步派生索引。精确的 `readTitle()` 建立了读取契约，而没有提前锁定搜索或索引策略。
+- **让 Web host 只使用回退标题**：不予采纳，因为 UI 虽会显示持久标题，却始终无法将第一条提示词的前缀改进为更好的标题。首消息提供方在主响应路径之外运行，并让模型摘要成为 Web 的默认结果。
 
 ## 后果
 
 - 标题可以在 JSONL 和 SQLite 持久化中存续，通过 ACP 回放，并遵循 fork 继承语义，而无需单独的可变记录。
-- 回退标题无需辅助调用即可出现；部署方可以自行决定更优标题是否值得模型成本，以及后续提示词是否需要重新生成会话标题。
+- Web 标题仍以增量方式从日志交付，无需标题索引或扫描持久化列表；冷启动列表项会在会话附加后改用标题。
+- 回退标题会立即出现。每个新建的 Web 会话都会增加一次针对首消息的辅助调用；其他组合可以自行决定更优标题是否值得模型成本，以及后续提示词是否需要重新生成会话标题。
 - 辅助请求记录和延迟接受的标题会占用事件 seq，并可能创建平衡的零步骤轮次，因此持久化会同时呈现尝试发起的调用与已接受的更新，尽管模型历史和 KV 缓存标识保持不变。
 - 单个提供方和每会话单调递增的修订号让释放、取代和陈旧结果拒绝行为明确可见，但多策略优先级必须由复合提供方负责。
 - 手动重命名、删除、生成标题与用户标题的优先级、搜索和列表索引不在此功能范围内。

.agents/notes/implemented/feature/2026-07-21-tui-reload-command.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
-2026-07-21-tui-reload-command.md: e5600f0ab5cd82dc556df76006fcf532d8c7d302
-2026-07-21-tui-reload-command.zh.md: 3798b0518df1c379cca808bd4af38490016567cb
+2026-07-21-tui-reload-command.md: 89bf2f7bb482d7f3889136c1a6ac9918ba0c4919
+2026-07-21-tui-reload-command.zh.md: cfea10690af49f2cf484938a3f9f12d954766a71

.agents/notes/implemented/feature/2026-07-21-tui-reload-command.md

@@ -6,7 +6,7 @@ English | [中文](2026-07-21-tui-reload-command.zh.md)
 
 ## Problem
 
-HMR's file watcher only reacts to in-place `change` events under its configured roots (the config leaf's directory in the shipped demos). Editors that replace files by rename (BSD `sed -i`, `git checkout`) produce no event, and runtimes without the HMR entry (or without `--expose-internals`) have no config reload path at all. During development that means restarting the TUI to apply a config edit the watcher missed. Widening the watch roots to the whole repo was considered and rejected in discussion: dense package sharing makes module-level HMR a remount-most-of-the-tree operation with unpredictable externals boundaries.
+HMR's file watcher only reacts to in-place `change` events under its configured roots (the config leaf's directory in the shipped demos). Editors that replace files by rename (BSD `sed -i`, `git checkout`) produce no event, and runtimes without the HMR entry have no config reload path at all. During development that means restarting the TUI to apply a config edit the watcher missed. Widening the watch roots to the whole repo was considered and rejected in discussion: dense package sharing makes module-level HMR a remount-most-of-the-tree operation with unpredictable externals boundaries.
 
 ## Decision
 

.agents/notes/implemented/feature/2026-07-21-tui-reload-command.zh.md

@@ -6,7 +6,7 @@ Status: implemented
 
 ## Problem
 
-HMR 的文件监听器只对其配置根目录（示例中即配置叶子所在目录）下的就地 `change` 事件起反应。以重命名方式替换文件的编辑器（BSD `sed -i`、`git checkout`）不产生事件，而没有挂载 HMR 配置项（或没有 `--expose-internals`）的运行时则完全没有配置重载路径。开发时这意味着监听器漏掉一次配置编辑就得重启 TUI。曾考虑把监听根目录扩大到整个仓库，讨论后否决：包之间的密集共享使模块级 HMR 变成「重挂大半棵树」的操作，externals 边界也不可预测。
+HMR 的文件监听器只对其配置根目录（示例中即配置叶子所在目录）下的就地 `change` 事件起反应。以重命名方式替换文件的编辑器（BSD `sed -i`、`git checkout`）不产生事件，而没有挂载 HMR 配置项的运行时则完全没有配置重载路径。开发时这意味着监听器漏掉一次配置编辑就得重启 TUI。曾考虑把监听根目录扩大到整个仓库，讨论后否决：包之间的密集共享使模块级 HMR 变成「重挂大半棵树」的操作，externals 边界也不可预测。
 
 ## Decision
 

.agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.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
+2026-07-23-tui-file-reference-autocomplete.md: 1a136009213c845af28f4ac47a8b31d426ac8cf5
+2026-07-23-tui-file-reference-autocomplete.zh.md: 410f0d49dbd20a2dcf704892a192406020aaa86e

.agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.md

@@ -0,0 +1,33 @@
+# Agent Note: TUI file-reference autocomplete
+
+Status: implemented
+
+English | [中文](2026-07-23-tui-file-reference-autocomplete.zh.md)
+
+## Problem
+
+The TUI offered structured `@session` references but no dependable way to discover workspace paths while composing a prompt. Requiring users to remember exact paths made file-oriented requests unnecessarily awkward, while eagerly attaching every selected file would spend context before the model knew whether its contents were relevant and would hide the normal `read` observation from the tool transcript.
+
+## Decision
+
+The TUI owns a bounded, cancellable host-workspace path index rooted at the active session's working directory. Typing `@` at a token boundary fuzzy-matches files and directories; queries containing `/` list the named directory directly, accepting a directory continues completion, and paths containing whitespace use the `@"path with spaces"` form. Configuration controls result count, index size, and excluded directory basenames. The default exclusions are `.git` and `node_modules`; traversal does not follow directory symlinks or interpret ignore files.
+
+Selecting a file changes only the editor text. The submitted user message retains the natural `@path` spelling and carries no injected contents, hidden context, or reference object. When the model-facing `read` tool is registered, the TUI contributes a stable system-prompt section that identifies `@` paths as explicit user references, directs the model to call `read` when contents are needed, and forbids claiming inspection before that call. Tool results invalidate the reusable fuzzy index so subsequent interactions observe likely workspace mutations.
+
+Structured session mentions keep their existing snapshot preparation. Unlike files, a referenced session has no general model-facing retrieval tool, so reducing `@session` to a path-like label would make its content unreachable.
+
+## Alternatives considered
+
+**Eagerly inject selected file contents.** This spends tokens before relevance is known, can capture stale content before execution reaches the reference, and bypasses the auditable `read` call/result sequence.
+
+**Require an external file finder.** Depending on `fd`, `rg --files`, or another executable would make baseline completion vary by host installation and complicate cancellation and cross-platform behavior.
+
+**Use the filesystem service's ordinary directory-list operation for discovery.** That seam is optimized for exact model-facing filesystem operations and may represent a remote namespace; recursive fuzzy indexing would multiply provider round trips and couple editor latency to tool policy. Host-side discovery keeps the terminal interaction local, while the documented namespace-alignment limitation remains explicit for non-local deployments.
+
+**Add a new cross-package file-search capability.** The TUI is the only current consumer and the behavior is editor presentation rather than a model capability, so a new interface, implementation, and consumer package set would split the seam prematurely.
+
+## Consequences
+
+Users can discover and insert paths without making selection itself expensive or model-visible beyond the path. The model preserves agency over whether to inspect a file, and any inspection remains reconstructable through the logged tool transcript. The fixed instruction slightly enlarges TUI system prompts when `read` is present, and content-requiring requests take an additional tool round trip.
+
+Completion is deliberately bounded and advisory: very large workspaces may omit paths beyond the configured index cap, ignored files may still appear, and remote or virtual filesystem deployments must align the TUI host working directory with the `read` namespace or supply a different completion surface. Package tests pin token grammar, ranking, bounds, cancellation, invalidation, and path-only submission; terminal snapshots and the real Loader PTY smoke pin the visible menu and keyboard completion.

.agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.zh.md

@@ -0,0 +1,33 @@
+# Agent Note: TUI 文件引用自动补全
+
+Status: implemented
+
+[English](2026-07-23-tui-file-reference-autocomplete.md) | 中文
+
+## 问题
+
+TUI 提供结构化的 `@session` 引用，但用户在编辑提示词时无法可靠地发现工作区路径。要求用户记住准确路径会给面向文件的请求带来不必要的麻烦；如果直接附加每个选中文件，则会在模型判断其内容是否相关之前占用上下文，并在工具 transcript（文本记录）中隐藏常规的 `read` 观察结果。
+
+## 决策
+
+TUI 维护一个有容量上限且可取消的主机工作区路径索引，以活跃会话的工作目录为根。在 token 边界输入 `@` 会对文件和目录进行模糊匹配；查询包含 `/` 时会直接列出指定目录，接受目录后会继续补全，包含空白的路径采用 `@"path with spaces"` 形式。配置项控制结果数量、索引大小以及排除的目录基名。默认排除 `.git` 和 `node_modules`；遍历既不跟随目录符号链接，也不解析忽略文件。
+
+选择文件只会改变编辑器文本。提交的用户消息保留自然的 `@path` 写法，不携带注入的内容、隐藏上下文或引用对象。注册面向模型的 `read` 工具时，TUI 会加入一个稳定的系统提示词段，说明 `@` 路径是用户的显式引用，指示模型在需要内容时调用 `read`，并禁止模型在调用前声称已检查文件。工具结果会使可复用的模糊索引失效，后续交互因而能看到工作区中可能发生的变更。
+
+结构化会话提及保留现有的快照准备方式。与文件不同，被引用的会话没有通用的模型侧检索工具；如果把 `@session` 简化为类似路径的标签，模型将无法获取其内容。
+
+## 备选方案
+
+**直接注入选中文件的内容。** 这种方式会在确定相关性前消耗 token，可能在执行到该引用前捕获到陈旧内容，并绕过可审计的 `read` 调用与结果序列。
+
+**要求使用外部文件查找器。** 依赖 `fd`、`rg --files` 或其他可执行文件，会使基础补全行为随主机安装情况而变化，也会增加取消处理和跨平台支持的复杂度。
+
+**使用文件系统服务的常规目录列表操作进行发现。** 该 seam 针对面向模型的准确文件系统操作进行了优化，并且可能表示远程命名空间；递归模糊索引会增加提供方往返次数，并使编辑器延迟与工具策略耦合。主机侧发现让终端交互保留在本地，同时文档仍明确说明非本地部署中的命名空间对齐限制。
+
+**新增跨包的文件搜索功能。** TUI 是目前唯一的消费方，而且该行为属于编辑器呈现而非模型功能；新增一组接口、实现和消费方包会过早拆分这条 seam。
+
+## 影响
+
+用户可以发现并插入路径，而选择操作本身不会带来高开销，对模型可见的内容也仅限路径。模型仍可自行决定是否检查文件，任何检查都能通过已记录的工具 transcript 重建。存在 `read` 时，固定指令会略微增大 TUI 系统提示词；需要文件内容的请求还会增加一次工具往返。
+
+补全有意采用有界的提示性设计：超大型工作区可能省略超过配置索引上限的路径，被忽略的文件仍可能出现，远程或虚拟文件系统部署必须让 TUI 的主机工作目录与 `read` 命名空间对齐，否则需要提供不同的补全接口。包（package）测试固定 token 语法、排序、边界、取消、失效和仅提交路径的行为；终端快照与真实 Loader PTY 冒烟测试固定可见菜单和键盘补全。

.agents/notes/implemented/feature/2026-07-23-web-assistant-markdown.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
+2026-07-23-web-assistant-markdown.md: ce98a16fa43e2743c18826ee7f2344c38e7c70e7
+2026-07-23-web-assistant-markdown.zh.md: 0d6fd2f9e6b91f76830586ecf4c29774e5d6978a

.agents/notes/implemented/feature/2026-07-23-web-assistant-markdown.md

@@ -0,0 +1,35 @@
+# Agent Note: Safe assistant Markdown in the Web conversation
+
+Status: implemented
+
+English | [中文](2026-07-23-web-assistant-markdown.zh.md)
+
+## Problem
+
+The Web conversation preserves assistant Markdown source through session events, history replay, and streaming accumulation, but its terminal text primitive renders that source literally. Changing the shared primitive would also format user and steering messages, while parsing in the runtime would mix presentation state into the React-free session projection.
+
+## Decision
+
+`@deepseek-ai/dsh-client-ui-primitives` exports `MarkdownText` as the untrusted assistant-text renderer, and `ui-conversation` selects it only for assistant `text` blocks. Finalized history, the streaming tail, and interrupted partials already share `AssistantMarkdown`, so they receive the same renderer without changing events or snapshots. User and steering messages keep `MessageText` and remain literal.
+
+`MarkdownText` uses `react-markdown` with `remark-gfm` to build React elements from an AST. It covers CommonMark blocks plus GFM tables, task lists, strikethrough, and autolinks without `dangerouslySetInnerHTML`, raw-HTML parsing, or syntax highlighting. The dependency is explicit in `ui-primitives`; because that pure library is seeded by the Web shell, the parser is part of the initial browser bundle.
+
+## Untrusted output policy
+
+Assistant-authored destinations are restricted to absolute HTTP, HTTPS, and mailto URLs. HTTP(S) links open in a new tab with `rel="noopener noreferrer"`; relative destinations and other protocols render as non-navigable text. Markdown images render only their alt text, so model output cannot initiate a remote image request. Raw HTML remains inert source text because no HTML parser enters the pipeline.
+
+The renderer uses existing `--dsw-*` typography and color tokens. Fenced code and GFM tables own horizontal overflow so long content cannot widen the conversation column.
+
+## Alternatives considered
+
+**Promote the existing mdast and micromark development dependencies and maintain a custom React walker.** This avoids a new parser family but makes the product own every node mapping, GFM extension, and security-sensitive rendering branch. The dedicated React renderer keeps that traversal upstream while preserving an AST-to-React path.
+
+**Replace `MessageText` with Markdown rendering.** This formats user prompts and steering as a side effect. Those authored surfaces remain literal until the product chooses that behavior explicitly.
+
+**Parse Markdown into session snapshots.** This would make React nodes or presentation ASTs durable runtime state and reintroduce a final-versus-streaming mode boundary. Parsing stays at the presentation leaf instead.
+
+**Enable raw HTML or remote images with sanitization.** Neither capability has a current product need, while both enlarge the executable or network privacy boundary. They remain disabled rather than adding sanitizer and image-policy dependencies.
+
+## Consequences
+
+Assistant replies render semantic Markdown consistently during streaming and replay, while tool cards, reasoning rows, interactions, user bubbles, and the host protocol remain unchanged. Streaming reparses the current text after each accumulated update; incomplete Markdown can temporarily change structure, but the isolated tail bounds React invalidation and the final event does not switch renderers. The initial Web shell grows by the Markdown parser and GFM runtime, and future extensions such as syntax highlighting or remote media require a separate bundle and security decision.

.agents/notes/implemented/feature/2026-07-23-web-assistant-markdown.zh.md

@@ -0,0 +1,35 @@
+# Agent Note: Web 对话中安全的 assistant Markdown
+
+Status: implemented
+
+[English](2026-07-23-web-assistant-markdown.md) | 中文
+
+## 问题
+
+Web 对话通过会话事件、历史回放与流式累积保留 assistant Markdown 源文本，但其最末端的文本原语会按字面渲染源文本。若修改共享原语，用户消息与 steering（中途引导）消息也会被格式化；若在运行时中解析，则会把呈现状态混入不依赖 React 的会话投影。
+
+## 决策
+
+`@deepseek-ai/dsh-client-ui-primitives` 导出 `MarkdownText`，用作不受信任的 assistant 文本渲染器；`ui-conversation` 仅为 assistant `text` 块选择该渲染器。已完成的历史消息、流式输出尾部与被中断的部分输出已经共用 `AssistantMarkdown`，因此无需更改事件或快照，它们便会采用同一渲染器。用户消息与 steering 消息继续使用 `MessageText`，并保持按字面渲染。
+
+`MarkdownText` 使用 `react-markdown` 与 `remark-gfm`，从 AST 构建 React 元素。它支持 CommonMark 块，以及 GFM 表格、任务列表、删除线与自动链接，但不使用 `dangerouslySetInnerHTML`，不解析原始 HTML，也不进行语法高亮。`ui-primitives` 显式声明该依赖；由于这一纯库由 Web shell 预置，解析器会成为初始浏览器 bundle 的一部分。
+
+## 不受信任输出策略
+
+assistant 生成的目标地址仅限绝对 HTTP、HTTPS 与 mailto URL。HTTP(S) 链接会在新标签页中打开，并带有 `rel="noopener noreferrer"`；相对目标地址与其他协议会渲染为不可导航的文本。Markdown 图片仅渲染替代文本，因此模型输出无法发起远程图片请求。由于管线中未引入 HTML 解析器，原始 HTML 仍是不会生效的源文本。
+
+渲染器使用现有的 `--dsw-*` 排版与颜色 token。围栏代码块与 GFM 表格各自处理横向溢出，因此较长内容无法撑宽对话栏。
+
+## 考虑过的替代方案
+
+**将现有的 mdast 与 micromark 开发依赖提升为正式依赖，并维护自定义 React walker。**此方案避免引入新的解析器体系，但产品需要自行负责每种节点映射、GFM 扩展和安全敏感的渲染分支。专用 React 渲染器将这套遍历交由上游维护，同时保留 AST 到 React 的处理路径。
+
+**将 `MessageText` 替换为 Markdown 渲染。**这会产生格式化用户提示词与 steering 的副作用。在产品明确选择此行为之前，这两类输入内容仍按字面渲染。
+
+**将 Markdown 解析为会话快照。**这会让 React 节点或呈现层 AST 成为持久的运行时状态，并重新引入最终输出与流式输出之间的模式边界。解析仍留在呈现层的叶节点中。
+
+**通过净化启用原始 HTML 或远程图片。**当前产品并不需要这两项功能，但二者都会扩大可执行行为或网络隐私边界。因此它们保持禁用，无需增加净化器与图片策略依赖。
+
+## 后果
+
+assistant 回复在流式输出与回放期间都会一致地渲染为语义化 Markdown，而工具卡片、推理行、交互、用户气泡和宿主协议保持不变。每次累积更新后，流式输出都会重新解析当前文本；未完成的 Markdown 可能暂时改变结构，但独立的尾部会限定 React 失效范围，最终事件也不会切换渲染器。初始 Web shell 的体积会因加入 Markdown 解析器与 GFM 运行时而增大；语法高亮或远程媒体等后续扩展需要另行作出 bundle 与安全决策。

.agents/notes/implemented/process/2026-07-20-gui-testing-system.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
-2026-07-20-gui-testing-system.md: fdd5c7f9d33f9a90ea4afe145265be5fe93e0fc2
-2026-07-20-gui-testing-system.zh.md: 0ae08133742711b87e9155ddc6f3104b757c1b55
+2026-07-20-gui-testing-system.md: e42dafcdf37e48475e7d420eaad9600e6c20891c
+2026-07-20-gui-testing-system.zh.md: e4ef6246e59e0ad6c0a3070a38c546f964e347fa

.agents/notes/implemented/process/2026-07-20-gui-testing-system.md

@@ -19,24 +19,24 @@ Cut along the architecture's natural test seams into three tiers, bottom-up:
 | Tier | Under test | Key technique | File location |
 |---|---|---|---|
 | 1 Protocol isomorphism | `AbstractApiClient` + `toFetchHandler` (bidirectional data / rpcId / zod types / SSE streams / batching / timeouts) | **The full chain at the isomorphic point**: `InProcessApiClient(toFetchHandler(脚本化 impl))` skips the network but genuinely runs the wire serialization — zero browser, pure node env | `packages/host/apiproxy/tests/client-handler.spec.ts` |
-| 2 Object-layer orchestration | `Session`/`SessionManager`/`ConnectionController` (state machines and timing: stitching / dedup / paging / optimistic draft clearing / pendingBuffers / reconnect / backoff) | **The "event sequence in → snapshot out" golden path**: programmable fakes + deferreds controlling timing + fake timers controlling backoff | `packages/client/web-runtime/tests/{session,manager,connection,…}.spec.ts` |
-| 3 Browser smoke | Build artifacts × a real browser (the page boots, one conversation round-trips) | Bare playwright library (chromium headless, no @playwright/test framework), minimal pass-through; fixture level + real-host level (self-skips without a key) | `apps/web/tests/smoke-{fixture,real}.e2e.ts` |
+| 2 Object-layer orchestration | `Session`/`SessionManager`/`ConnectionController` (state machines and timing: stitching / dedup / paging / optimistic draft clearing / pendingBuffers / reconnect / backoff) | **The "event sequence in → snapshot out" golden path**: programmable fakes + deferreds controlling timing + fake timers controlling backoff | `packages/client/{runtime,connection}/tests/` |
+| 3 Assembled presentation | Built artifacts × the real client loader and plugin composition | App-owned semantic snapshots boot all eight built client plugins under jsdom for deterministic cross-plugin state changes; bare Playwright smoke separately proves the real browser/carrier boundary, with real-host cases self-skipping without a key | `apps/web/tests/*.snapshot.ts`, `apps/web/tests/smoke-{fixture,real}.e2e.ts` |
 
-Inter-tier discipline: **each tier tests its own layer, upper tiers never re-test lower ones** — smoke only proves the wiring is alive (the fixture level asserts zero `/api` requests and zero pageerror), interaction detail belongs to the verify scripts (see the lane map), wire semantics to tier 1, data semantics to tier 2. Pure-function layers (lineage/partial/notifier/fold-adapter) are tested directly with zero fakes in the same package's tests/ alongside tier 2.
+Inter-tier discipline: **each tier tests its own layer, upper tiers never re-test lower ones** — an app semantic snapshot pins only user-visible projection across the assembled plugin boundary, while Playwright smoke proves browser and carrier liveness; wire semantics belong to tier 1 and data semantics to tier 2. Pure-function layers (lineage/partial/notifier/fold-adapter) are tested directly with zero fakes in the same package's tests/ alongside tier 2.
 
-- **Host side** (apiproxy/runtime/webserver): under the repo-wide `test:coverage` gate, per-file 100%.
-- **Client side**: web-runtime **is already under the per-file 100% gate** (12 defensive unreachable arms carry reasoned `/* v8 ignore */` comments); the `vitest.config.ts` coverage.exclude is down to `packages/client/web-ui/src/**` (temporary — lifted progressively as component specs fill in after the component redo); tests still run, the exclusion only keeps web-ui src out of the thresholds. web-ui takes the **jsdom route (landed)**: jsdom + @testing-library/react entered root devDependencies (dev-only), first spec `web-ui/tests/utils.spec.tsx` (utils pure functions + component RTL render + hook uSES probe); the environment uses the per-file `// @vitest-environment jsdom` pragma, zero impact on the other node-env packages.
-- The exclusion is an **explicitly annotated ruling**, not a silent waiver; the lift path = delete the exclude line + add a justified exclusion or the missing tests.
+- **Host and client source** are under the repo-wide per-file 100% coverage gate except the narrow browser-grade exclusions annotated in `vitest.config.ts`; component suites use per-file jsdom pragmas and Testing Library without changing Node suites.
+- **App-owned semantic snapshots** read built client bundles, execute them through the real loader, and drive only deterministic fixture hooks. They own stable visible state such as sidebar labels, breadcrumbs, and `document.title`, not CSS pixels or lower-layer state-machine details.
 
 ## Lane map
 
 | Scenario | Command | Content | When to run |
 |---|---|---|---|
 | Baseline | `pnpm run test:gui` | Tier 1+2 vitest (`packages/client packages/host`), seconds-fast, no browser, no server | Casually, after touching any GUI source |
+| Semantic snapshot | `DSH_EXAMPLE_MODE=lib pnpm run test:snapshot` | Keyless assembled-application semantics plus the repo's transport-specific expected outputs | After a human-visible GUI change; before delivery |
 | Browser end-to-end | `pnpm run test:web` | Rebuilds the front-end dist first, then runs the tier-3 two-level smoke (fixture level + real-host level self-skip) | After touching the build surface/boot/carriage; before delivery |
-| Gate | `pnpm run test:coverage` | The repo-wide gate (host-side GUI packages included, client side excluded) | The PR window |
+| Gate | `pnpm run test:coverage` | The repo-wide gate (host and client GUI packages included, except annotated browser-grade exclusions) | The PR window |
 
-**Division of labor between the verify scripts and vitest**: verify owns browser black-box regression (sequential steps = a user-operation script, one shared browser session, streaming PASS/FAIL output for the agent to locate the break), vitest owns first-class data-layer semantic assertions (reference stability `toBe`, state-machine timing, wire shapes). The two lanes complement each other, neither absorbs the other — scripts do not migrate to vitest (tearing apart an ordered script is a net loss); promoting one means wrapping a spawn shell hooked into the e2e lane, never rewriting the script body.
+**Division of labor between the browser scripts and vitest**: Playwright owns browser/carrier black-box regression and long sequential user journeys; ordinary vitest owns data-layer semantics such as reference stability, timing, and wire shapes; snapshot vitest owns stable app-level semantic output through the built composition. These lanes complement each other rather than duplicating assertions.
 
 ## Anti-regression discipline
 
@@ -46,7 +46,7 @@ Inter-tier discipline: **each tier tests its own layer, upper tiers never re-tes
 
 ## Consequences
 
-Each lane tests its own tier: touching any GUI source gets seconds-fast `test:gui` feedback, wire/object-layer semantics assert in milliseconds in node env, and the browser carries only wiring-liveness smoke. On the gate surface, the host side is fully under per-file 100%; on the client side web-runtime is under the gate while web-ui waits behind the explicitly annotated exclude. The accepted cost: the inter-tier discipline (upper tiers never re-test lower ones) is upheld by review rather than a machine gate, and web-ui's coverage gap persists until component specs fill in after the component redo.
+Each lane tests its own tier: touching any GUI source gets seconds-fast `test:gui` feedback, wire/object-layer semantics assert in milliseconds in Node, built-composition snapshots pin deterministic user-visible projection, and the browser carries wiring and carrier acceptance. The accepted cost is that inter-tier discipline is upheld by review rather than a machine gate and every new app snapshot must avoid unstable layout or clock output.
 
 ## Alternatives considered
 

.agents/notes/implemented/process/2026-07-20-gui-testing-system.zh.md

@@ -19,24 +19,24 @@ GUI 栈需要考虑多种应用形态，同应用形态内的不同运行环境
 | 层 | 被测物 | 关键手段 | 文件落点 |
 |---|---|---|---|
 | 1 协议同构层 | `AbstractApiClient` + `toFetchHandler`（双向数据/rpcId/ZOD类型/SSE 流/合批/超时） | **同构点全链**：`InProcessApiClient(toFetchHandler(脚本化 impl))` 不过网络但真跑 wire 序列化——零浏览器、纯 node env | `packages/host/apiproxy/tests/client-handler.spec.ts` |
-| 2 对象层编排 | `Session`/`SessionManager`/`ConnectionController`（状态机与时序：缝合/去重/翻页/乐观清稿/pendingBuffers/重连/退避） | **「事件序列进→快照出」黄金路径**：可编程假体 + deferred 控时序 + fake timers 控退避 | `packages/client/web-runtime/tests/{session,manager,connection,…}.spec.ts` |
-| 3 浏览器 smoke | 构建产物 × 真浏览器（页面起得来、一轮对话跑得通） | playwright 裸库（chromium headless，无 @playwright/test 框架）最简跑通；fixture 级 + 真 host 级（无 key self-skip） | `apps/web/tests/smoke-{fixture,real}.e2e.ts` |
+| 2 对象层编排 | `Session`/`SessionManager`/`ConnectionController`（状态机与时序：缝合/去重/翻页/乐观清稿/pendingBuffers/重连/退避） | **「事件序列进→快照出」黄金路径**：可编程假体 + deferred 控时序 + fake timers 控退避 | `packages/client/{runtime,connection}/tests/` |
+| 3 组装呈现层 | 构建产物 × 真实 client loader 与插件组合 | 归应用所有的语义快照会在 jsdom 下启动全部 8 个已构建的 client 插件，以固定确定性的跨插件状态变化；独立使用 Playwright 裸库的冒烟测试负责验证真实浏览器/承载层边界，真 host 用例在无密钥时自行跳过 | `apps/web/tests/*.snapshot.ts`、`apps/web/tests/smoke-{fixture,real}.e2e.ts` |
 
-层间纪律：**下层各测各的，上层不重测下层**——smoke 只证接线活着（fixture 级断零 `/api` 请求、零 pageerror），交互细节归 verify 脚本（见车道地图），wire 语义归 1 层，数据语义归 2 层。纯函数层（lineage/partial/notifier/fold-adapter）随 2 层同包 tests/ 零假体直测。
+层间纪律：**下层各测各的，上层不重测下层**：应用语义快照只固定组装后插件边界上的用户可见投影，Playwright 冒烟测试负责验证浏览器与承载层是否存活；wire 语义归 1 层，数据语义归 2 层。纯函数层（lineage/partial/notifier/fold-adapter）随 2 层同包 tests/ 零假体直测。
 
-- **host 侧**（apiproxy/runtime/webserver）：进全仓 `test:coverage` 门禁，per-file 100%。
-- **client 侧**：web-runtime **已进 per-file 100% 门禁**（12 处防御性不可达臂带理由 `/* v8 ignore */` 注释）；`vitest.config.ts` coverage.exclude 只剩 `packages/client/web-ui/src/**`（暂时——组件重做后随组件 specs 铺满逐步解除），测试照跑，只是不拉 web-ui src 进阈值。web-ui 走 **jsdom 路线（已落地）**：jsdom + @testing-library/react 入 root devDeps（dev-only），首个 spec `web-ui/tests/utils.spec.tsx`（utils 纯函数 + 组件 RTL render + hook uSES 探针）；环境用 per-file `// @vitest-environment jsdom` pragma，node env 的其他包零影响。
-- 排除是**显式注释的裁决**不是静默豁免；解除路径=删 exclude 行 + 补 justified 排除或补测。
+- **host 与 client 源码**均纳入全仓 per-file 100% 覆盖率门禁，仅排除 `vitest.config.ts` 中带注释的少量浏览器级例外；组件套件通过逐文件 jsdom pragma 和 Testing Library 运行，不会改变 Node 套件。
+- **归应用所有的语义快照**读取已构建的 client bundle，通过真实 loader 执行它们，并且只驱动确定性的 fixture 钩子。它们负责固定侧边栏标签、面包屑和 `document.title` 等稳定可见状态，而不固定 CSS 像素或下层状态机细节。
 
 ## 车道地图
 
 | 场景 | 命令 | 内容 | 何时跑 |
 |---|---|---|---|
 | 基础 | `pnpm run test:gui` | 1+2 层 vitest（`packages/client packages/host`），秒级、无浏览器无 server | 改 GUI 任意源码后随手跑 |
+| 语义快照 | `DSH_EXAMPLE_MODE=lib pnpm run test:snapshot` | 无需密钥的组装应用语义，以及仓库按传输形态划分的预期输出 | 用户可见的 GUI 变更后；交付前 |
 | 浏览器端到端 | `pnpm run test:web` | 先重建前端 dist，再跑 3 层双级 smoke（fixture 级 + 真 host 级 self-skip） | 改构建面/boot/承载后；交付前 |
-| 门禁 | `pnpm run test:coverage` | 全仓 gate（host 侧 GUI 包在内，client 侧 excluded） | PR 窗口 |
+| 门禁 | `pnpm run test:coverage` | 全仓 gate（host 与 client GUI 包均纳入，仅排除带注释的浏览器级例外） | PR 窗口 |
 
-**verify 脚本与 vitest 的分工**：verify 管浏览器黑盒回归（顺序步骤=用户操作剧本，共享一次浏览器会话，PASS/FAIL 流式输出供 agent 定位断点），vitest 管数据层语义一等断言（引用稳定性 `toBe`、状态机时序、wire 形）。两车道互补不收编——脚本不迁 vitest（拆散有序剧本是负收益），转正时包一层 spawn 壳挂 e2e 车道即可，脚本本体不改写。
+**浏览器脚本与 vitest 的分工**：Playwright 负责浏览器/承载层黑盒回归和较长的连续用户操作流程；普通 vitest 负责引用稳定性、时序和 wire 结构等数据层语义；快照 vitest 通过构建后的组合负责稳定的应用层语义输出。这些车道彼此互补，而不重复断言。
 
 ## 防回归纪律
 
@@ -46,7 +46,7 @@ GUI 栈需要考虑多种应用形态，同应用形态内的不同运行环境
 
 ## Consequences
 
-各车道各测各层：改任意 GUI 源码有秒级 `test:gui` 反馈，wire/对象层语义在 node env 毫秒级断言，浏览器只承担接线存活冒烟。门禁面上 host 侧全量进 per-file 100%；client 侧 web-runtime 已进门，web-ui 暂留显式注释的 exclude 之后。接受的代价：层间纪律（上层不重测下层）靠 review 而非机器门禁维持；web-ui 的覆盖缺口持续到组件重做后组件 specs 铺满为止。
+各车道各测各层：改动任意 GUI 源码后都能获得秒级 `test:gui` 反馈，wire/对象层语义在 Node 环境中进行毫秒级断言，基于构建后组合的快照固定确定性的用户可见投影，浏览器负责接线与承载层验收。接受的代价是层间纪律由评审而非机器门禁维持，而且每个新的应用快照都必须避开不稳定的布局或时钟输出。
 
 ## Alternatives considered
 

.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.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
-2026-07-22-evidence-based-larger-hosted-runners.md: 13ecbd5c74bb08d84c8fdf1140a9970235aab826
-2026-07-22-evidence-based-larger-hosted-runners.zh.md: 93d6818fdf5af826980b6f4b938fadc122722b68
+2026-07-22-evidence-based-larger-hosted-runners.md: aaeab4ed9ae9687598f9f1d4a862120405697672
+2026-07-22-evidence-based-larger-hosted-runners.zh.md: 72b69c85908990a9f35b60f4c0a2ce213f9c8134

.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md

@@ -18,7 +18,7 @@ The required primary path depends on those enterprise pools. Standard GitHub-hos
 
 The former gate-level and coarse primary shard jobs are absent from the workflow. Their static, lint, coverage, snapshot, and scenario shard selectors are also absent from the repository, so an unused diagnostic path cannot preserve a second CI architecture.
 
-Linux primary work uses two independent 32-core jobs. Coverage runs alone with its own worker bound. The other job starts the static scheduler alone; once it reports a successful build, lint, Node 24 runtime compatibility, build-backed snapshots, and all artifact consumers start against that completed tree. Generated NodeNext consumer directories are excluded from ESLint discovery because the artifact check removes them while these processes overlap. The pnpm store and ESLint cache are restored without putting cache uploads on the pull-request critical path. Performance reports use each job's `startedAt` to `completedAt` interval; runner queue delay is capacity evidence, not repository execution time.
+Linux primary work uses three independent 32-core jobs. Coverage runs alone with its own worker bound, and the static scheduler runs alone so its result has no post-build consumer tail. After static gates finish, that job publishes its emitted `apps/*/lib`, `packages/*/*/lib`, and `vendor/*/lib` tree as a run-scoped artifact. The third job restores that exact tree, then starts lint, Node 24 runtime compatibility, build-backed snapshots, and all artifact consumers without repeating the build. Generated NodeNext consumer directories are excluded from ESLint discovery because the artifact check removes them while these processes overlap. The pnpm store and ESLint cache are restored without putting cache uploads on the pull-request critical path. Performance reports use each job's `startedAt` to `completedAt` interval; runner queue delay is capacity evidence, not repository execution time.
 
 Windows shares one 32-core setup across the blocking build and production site plus observational built-artifact contracts. Linux owns the duplicate lint, coverage, and snapshot inventories because running those observational copies on Windows extends the paid critical path without adding a blocking platform claim.
 
@@ -58,6 +58,8 @@ Complete serial Linux, macOS, and Windows references run only when `master` move
 
 **Keep build behind typecheck.** This orders independent compiler invocations and turns snapshot replay into a three-stage critical chain. Build output has its own success dependency, so only snapshot and publication consumers wait for it.
 
+**Keep static gates and post-build consumers on one runner.** Reusing one workspace avoids a setup wave and artifact transfer, but build-duration variance delays every consumer and leaves their lint and snapshot tails after the static result. A run-scoped built tree preserves one exact build while independent jobs keep both complete paths within the observed target.
+
 **Keep the complete required path on standard GitHub-hosted capacity.** This avoids repository-external runner configuration, but exact-head standard-runner runs remain materially slower and can spend longer queued behind shared capacity. Standard-hosted compatibility and serial references preserve portable evidence without making that slower topology the ordinary primary path.
 
 **Keep required and observational Windows checks in separate jobs.** The split preserves status semantics at the workflow level but pays setup twice. `run-gates` preserves the same required versus non-blocking distinction inside one process.
@@ -68,7 +70,7 @@ Complete serial Linux, macOS, and Windows references run only when `master` move
 
 The required topology pays one setup wave per 32-core lane and retains no shard selectors. Every ordinary pull request consumes paid enterprise Linux and Windows minutes; manual benchmarks add other sizes only when remeasurement is useful.
 
-GitHub rounds each larger-runner execution up to a whole minute, so complete-job measurement exposes both billed time and workflow complexity. Splitting Linux repeats setup once, but isolates coverage from build, lint, and snapshot contention; consolidating Windows avoids repeating its slower setup.
+GitHub rounds each larger-runner execution up to a whole minute, so complete-job measurement exposes both billed time and workflow complexity. Splitting Linux repeats setup twice and transfers one built tree, but isolates coverage, static gates, and post-build consumers from each other's critical paths without repeating the build; consolidating Windows avoids repeating its slower setup.
 
 Performance targets are observations, not cancellation deadlines or correctness requirements. Manual all-size and serial suites remain available when image, dependency, scheduler, or pricing changes need remeasurement.
 

.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md

@@ -18,7 +18,7 @@ Status: implemented
 
 原有的门禁级和粗粒度主流程分片作业已从工作流中移除。相应的静态、lint、覆盖率、快照和场景分片选择器也已从仓库中移除，因此未使用的诊断路径无法继续维系第二套 CI 架构。
 
-Linux 主流程使用两个相互独立的 32 核作业。覆盖率单独运行，并设有自己的工作线程上限。另一个作业先单独启动静态调度器；静态调度器报告构建成功后，lint、Node 24 运行时兼容性、依赖构建产物的快照和所有产物消费方才基于构建完成后的工作树启动。生成的 NodeNext 消费方目录不会纳入 ESLint 的文件发现范围，因为这些进程重叠执行时，产物检查会删除这些目录。pnpm store 和 ESLint 缓存会得到恢复，但缓存上传不会进入拉取请求关键路径。性能报告采用每个作业从 `startedAt` 到 `completedAt` 的区间；运行器排队延迟是容量证据，而非仓库执行时间。
+Linux 主流程使用 3 个相互独立的 32 核作业。覆盖率单独运行，并设有自己的工作线程上限；静态调度器也单独运行，因此构建后的消费方不会拖延其结果。静态门禁完成后，该作业将其生成的 `apps/*/lib`、`packages/*/*/lib` 和 `vendor/*/lib` 目录树作为仅供本次运行使用的产物发布。第三个作业恢复完全相同的目录树，再让 lint、Node 24 运行时兼容性、依赖构建产物的快照和所有产物消费方基于构建完成后的工作树启动，而不重复构建。生成的 NodeNext 消费方目录不会纳入 ESLint 的文件发现范围，因为这些进程重叠执行时，产物检查会删除这些目录。pnpm store 和 ESLint 缓存会得到恢复，但缓存上传不会进入拉取请求关键路径。性能报告采用每个作业从 `startedAt` 到 `completedAt` 的区间；运行器排队延迟是容量证据，而非仓库执行时间。
 
 Windows 以一次 32 核环境设置同时承载阻塞性构建、生产网站和观测性的构建产物契约。重复的 lint、覆盖率和快照清单由 Linux 承担，因为在 Windows 上运行这些观测性副本会延长付费关键路径，却不会新增任何阻塞性平台契约。
 
@@ -58,6 +58,8 @@ Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完
 
 **让构建继续等待类型检查。** 此方案会给相互独立的编译器调用排定先后顺序，并把快照回放变成 3 阶段关键链。构建输出本身有独立的成功依赖关系，因此只有快照和发布消费方需要等待它。
 
+**将静态门禁和构建后消费方保留在同一台运行器上。** 复用同一个工作区可以省去一轮设置和一次产物传输，但构建耗时的波动会延迟每个消费方，并使消费方的 lint 和快照尾段延续到静态结果之后。仅供本次运行使用的已构建目录树可以保留同一份构建结果，而相互独立的作业能让两条完整路径都保持在实测目标内。
+
 **将完整必需路径保留在 GitHub 标准托管容量上。** 此方案可以避免依赖仓库外部的运行器配置，但标准运行器上的分支头精确运行仍明显更慢，也可能因共享容量而排队更久。标准托管兼容性作业和串行参考流程保留可移植证据，无需让这套较慢的拓扑成为普通主路径。
 
 **将必需的 Windows 检查和观测性 Windows 检查保留在不同作业中。** 这种拆分在工作流层保留状态语义，却需要支付两次设置开销。`run-gates` 在一个进程内保留了相同的必需与非阻塞区别。
@@ -68,7 +70,7 @@ Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完
 
 必需拓扑中的每个 32 核通道只承担 1 轮设置开销，且不保留分片选择器。每个普通拉取请求都会消耗付费的企业级 Linux 和 Windows 运行器分钟数；只有在重新测量有价值时，手动基准测试才会加入其他规格。
 
-GitHub 会把每次大型运行器执行向上取整到整分钟计费，因此完整作业测量能同时呈现计费时长与工作流复杂度。拆分 Linux 会重复一次设置，但可将覆盖率同构建、lint 和快照的争用隔离；合并 Windows 则避免重复其耗时更长的设置。
+GitHub 会把每次大型运行器执行向上取整到整分钟计费，因此完整作业测量能同时呈现计费时长与工作流复杂度。拆分 Linux 会重复两轮设置并传输一份已构建目录树，但能使覆盖率、静态门禁与构建后消费方不再相互进入关键路径，且无需重复构建；合并 Windows 则避免重复其耗时更长的设置。
 
 性能目标是观测结果，而非取消截止时间或正确性要求。当映像、依赖、调度器或定价发生变化而需要重新测量时，仍可使用手动全规格和串行套件。
 

.agents/notes/implemented/process/2026-07-23-translation-prompt-v4-contract.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
+2026-07-23-translation-prompt-v4-contract.md: 3e1e51797aa3463c8db24d8657120434e6822789
+2026-07-23-translation-prompt-v4-contract.zh.md: 161d2b6cf3bd3499e3c505a178da40ce577ca797

.agents/notes/implemented/process/2026-07-23-translation-prompt-v4-contract.md

@@ -0,0 +1,33 @@
+# Agent Note: Calibrated translation prompt v4 contract
+
+Status: implemented
+
+English | [中文](2026-07-23-translation-prompt-v4-contract.zh.md)
+
+## Problem
+
+Automated counterpart generation needs a stable prompt that reproduces the register and corrections established by human-reviewed translations. Injecting a general-purpose instruction document changes that calibrated model input whenever human or agent guidance changes, while an unframed response cannot carry a draft, its self-review, and the corrected document separately. Plain XML-like section tags also collide with valid Markdown that documents those same tags.
+
+## Decision
+
+The committed [translation prompt](../../../../docs/i18n/translation-prompt.md) is the calibrated pipeline asset. Its renderer injects only the source language, target language, and current [terminology table](../../../../docs/i18n/terminology.md), and rejects unknown, missing, or malformed placeholder syntax before assembling a request. The request assembler retains the source basename outside the model-visible prompt and places each reviewed whole-document pair into one bare-text user/assistant example turn before the real source document. The template may carry model-specific calibration rules, but those rules remain subordinate to the repository's binding pairing, terminology, structure, and emphasis contracts.
+
+The response has three ordered top-level sections: `translation`, `review`, and `final`. The response consumer derives the target basename from the retained source context, preserves optional leading YAML frontmatter, and mechanically inserts or corrects the language switcher after the first H1 in `final`. The parser requires each section exactly once, rejects content outside the envelope, and tolerates one outer `xml` Markdown fence because models sometimes echo the prompt's example fence.
+
+## Response framing
+
+Section delimiter lines are reserved by the wire format. When a Markdown body line consists of a delimiter tag, possibly preceded by backslashes, the serializer and model add one leading backslash; the parser removes exactly one. This count-preserving escape round-trips both a literal delimiter and an already escaped delimiter without changing inline tag mentions.
+
+The executable contract lives in [the renderer, request assembler, parser, and response consumer](../../../../scripts/translation-prompt.ts). Unit tests cover both directions, request order, placeholder validation, target-path validation, strict section order and cardinality, fenced responses, inline tag mentions, delimiter lines inside Markdown bodies, and frontmatter-preserving new-pair switcher correction. A keyless subprocess snapshot pins the assembled prompt and five reviewed example turns together with a frontmatter-bearing recorded response consumed through the target-path correction.
+
+## Alternatives considered
+
+**Inject `translation-rules.md` into every request.** That document governs humans and agents as well as the automated pipeline. Injecting it couples each editorial clarification to model behavior and displaces the manually calibrated prompt constraints; the pipeline instead injects the binding terminology table and verifies its own asset directly.
+
+**Use a strict CDATA XML document.** CDATA provides general XML framing but adds a nested protocol, an additional `]]>` escape, and XML-parser behavior that the three-section contract does not otherwise need. Reserving and escaping six delimiter lines keeps the calibrated response shape while preserving arbitrary Markdown.
+
+**Return only the final translation.** A single body is simpler to parse but discards the explicit correction pass used to catch tone, structure, terminology, and punctuation defects before publication.
+
+## Consequences
+
+Prompt wording is executable behavior and receives code review, a translation-prompt verifier, and a runnable request/response snapshot. The calibrated asset and the general translation rules can evolve for their different audiences, but review must reject contradictions with binding repository contracts. The line escape is visible only when source documentation contains a wrapper tag on its own line, and parser tests pin its lossless behavior.

.agents/notes/implemented/process/2026-07-23-translation-prompt-v4-contract.zh.md

@@ -0,0 +1,33 @@
+# Agent Note: 经校准的翻译提示词 v4 契约
+
+Status: implemented
+
+[English](2026-07-23-translation-prompt-v4-contract.md) | 中文
+
+## 问题
+
+自动生成对侧文件需要一份稳定的提示词，能够复现经人工评审的译文所确立的语体和修正方式。注入通用说明文档，会让这份经校准的模型输入随着面向人类或 agent（智能体）的指导发生变化，而未经封装的响应无法分别承载草稿、自检内容和修正后的文档。普通的类 XML 分段标签还会与用于说明这些标签的合法 Markdown 内容发生冲突。
+
+## 决策
+
+提交入库的[翻译提示词](../../../../docs/i18n/translation-prompt.md)是经过校准的流水线资源。其渲染器仅注入源语言、目标语言和当前[术语表](../../../../docs/i18n/terminology.md)，并在组装请求前拒绝未知、缺失或语法格式错误的占位符。请求组装器在模型可见的提示词之外保留源文件基本名，并在真正的源文档之前，将每组经评审的整篇文档对编排为一个纯文本 user/assistant 示例轮次。模板可以包含针对特定模型的校准规则，但这些规则必须服从仓库中具约束力的配对、术语、结构与强调格式契约。
+
+响应包含三个有序的顶层分段：`translation`、`review` 和 `final`。响应消费方根据保留的源文件上下文推导目标文件基本名，保留文件开头可选的 YAML frontmatter，并以机械方式在 `final` 中第一个 H1 之后插入或校正语言切换行。解析器要求每个分段恰好出现一次，拒绝封套之外的内容，并允许响应最外层有一层 `xml` Markdown 围栏，因为模型有时会照抄提示词中的示例围栏。
+
+## 响应封装格式
+
+分段定界行由协议格式（wire format）保留。当 Markdown 正文中的某一行仅包含定界标签（前面可以带反斜杠）时，序列化器和模型会在行首再添加一个反斜杠；解析器则只移除一个。这种保留计数的转义方式让字面量定界标签与已转义的定界标签都能无损往返，同时不会改动行内提及的标签。
+
+可执行契约由[渲染器、请求组装器、解析器和响应消费方](../../../../scripts/translation-prompt.ts)实现。单元测试覆盖两个翻译方向、请求顺序、占位符校验、目标路径校验、严格的分段顺序与数量约束、带围栏的响应、行内提及标签、Markdown 正文中的定界行，以及保留 YAML frontmatter 的新配对语言切换行校正。一个无密钥子进程快照锁定组装后的提示词、五个经评审的示例轮次，以及带 YAML frontmatter 的录制响应经目标路径校正后的消费结果。
+
+## 考虑过的替代方案
+
+**在每个请求中注入 `translation-rules.md`。** 该文档既约束人类与 agent，也约束自动翻译流水线。注入它会让编辑规范的每次澄清都与模型行为耦合，并挤占经过人工校准的提示词约束；因此流水线仅注入具约束力的术语表，并直接校验自身资源。
+
+**使用严格的 CDATA XML 文档。** CDATA 提供通用的 XML 封装，但会引入一层嵌套协议、额外的 `]]>` 转义规则，以及三段式契约原本不需要的 XML 解析器行为。预留并转义六种定界行，既能维持经校准的响应形态，也能保留任意 Markdown 内容不变。
+
+**只返回最终译文。** 单一正文更易解析，却会丢弃显式修正步骤；这个步骤用于在发布前发现语气、结构、术语和标点缺陷。
+
+## 影响
+
+提示词措辞属于可执行行为，因此需要经过代码评审、翻译提示词校验器校验及可运行的请求/响应快照验证。经校准的资源与通用翻译规则可以针对各自的受众分别演进，但评审必须拒绝任何与仓库约束性契约冲突的改动。只有当源文档中的封装标签独占一行时，行转义才会显现；解析器测试锁定这一无损行为。

.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.md

@@ -12,7 +12,7 @@ A capability seam ([interface / implementation / consumer](../architecture/2026-
 
 The abstract service declared its operations beyond create/append: `load`, `list`, `has`, `delete`. Production consumers of `ctx.sessionPersistence` use only two: the agent-loop resume path calls `load()` ([packages/core/agent-loop/src/index.ts:176](../../../../packages/core/agent-loop/src/index.ts)), and the ACP bridge calls `list()` for `session/list` ([packages/ui/acp/src/index.ts:494](../../../../packages/ui/acp/src/index.ts)). Grepping every `sessionPersistence.*` / `persistence.*` use across `packages/*/src` and `examples/` finds no `has(` and no `delete(` on the service. The `.has(`/`.delete(` calls in `packages/ui/acp/src/index.ts` are on the in-memory `SessionStore` and a local `Set` of loading ids, not persistence. The only callers of `has`/`delete` were the contract suites and per-backend specs.
 
-`has()` was not just unused — it was the most intricate branch in the shared coordinator: a tracked-vs-untracked dual-probe (`loadLive(id, cwd)` for a live-tracked session vs `loadStored(id)` for an untracked one) with a multi-line rationale. `delete()` dragged the `deleteStored` backend hook that every backend had to implement. This is the [drop-mutable-session-summary](2026-06-19-drop-mutable-session-summary.md) pattern: a contract test exercised both, but no shipping code asks "is this session persisted?" or removes one.
+`has()` was not just unused: it added a tracked-vs-untracked coordinator probe and a contract branch even though `loadStored(id)` already owns durable existence checks. `delete()` dragged the `deleteStored` backend hook that every backend had to implement. This is the [drop-mutable-session-summary](2026-06-19-drop-mutable-session-summary.md) pattern: a contract test exercised both, but no shipping code asks "is this session persisted?" or removes one.
 
 ## Decision
 

.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.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
-2026-07-22-plan-specific-collaboration-state.md: 8a7caf9b1150cb6d3ea2c8ed52e42751f30c773c
-2026-07-22-plan-specific-collaboration-state.zh.md: c4d2528cc06a74ce8c152199bc2503daff315dbf
+2026-07-22-plan-specific-collaboration-state.md: 2fc163213ca0ee1de5633e4d7db14a814b2f7bb2
+2026-07-22-plan-specific-collaboration-state.zh.md: 811f657bf31c96dde88e400fc25fe2fe6df1f157

.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.md

@@ -14,7 +14,7 @@ The word “mode” also spans unrelated domains. Sandbox mode is an enforcing p
 
 Plan mode owns a plan-specific product package: `@deepseek-ai/dsh-plan-mode` at `packages/plan/plan-mode/`. The durable fact is `plan/mode: { active: boolean }`, folded by `foldPlanMode(events)` with `false` as the empty-log value. `ctx.planMode.get(agent)` returns `{ active, pending? }`, and `set(agent, active)` records the boundary-applied selection. The existing prompt-submit, continuation, retry, append-failure, and disposal fences remain unchanged in meaning.
 
-Configuration is exactly `{ section: string }`. The package registers the fixed `plan:policy` section, `/plan [message]`, and `exit_plan_mode` itself. Bare `/plan` selects the state; a non-empty argument selects it first and then sends the trimmed text through `agent.steer()`, making the text an ordinary logged user message in the affected step. The exit tool remains registered while plan mode is inactive so the request tool catalog stays stable.
+Configuration is exactly `{ section: string }`. The package registers the fixed `plan:policy` section, `/plan [message]`, the exact `/plan off` direct-exit form, and `exit_plan_mode` itself. Bare `/plan` selects active; another non-empty argument selects it first and then sends the trimmed text through `agent.steer()`, making the text an ordinary logged user message in the affected step. `/plan off` selects inactive without model input and can cancel an entry that is still pending at the boundary. The exit tool remains registered while plan mode is inactive so the request tool catalog stays stable.
 
 ACP keeps its protocol-level `default` and `plan` ids. The bridge maps those two ids to the boolean service, advertises only that fixed pair, rejects every other id at the adapter boundary, and maps committed `plan/mode` events back to `current_mode_update`. The protocol remains generic without forcing genericity into the product domain.
 
@@ -38,9 +38,9 @@ Sandbox mode and approval policy remain separate enforcement axes. Plan mode nei
 ## Verification
 
 - Package tests retain boundary ordering, retry, append-failure, HMR disposal, prompt assembly, stable native and Code Mode schemas, review outcomes, and invariant coverage through the boolean service.
-- Command tests cover bare `/plan`, `/plan <message>`, absence of `/mode` and `/review`, and effect-scoped removal.
+- Command tests cover bare `/plan`, `/plan <message>`, active `/plan off`, pending-entry cancellation, inactive idempotence, absence of `/mode` and `/review`, and effect-scoped removal.
 - ACP tests cover fixed advertisement, both ids, unknown-id rejection, optimistic updates, committed exits, and load replay.
-- The keyless TUI scenario enters through `/plan <message>` and proves `plan/mode` precedes the first request header and that the message is logged under plan guidance.
+- The keyless TUI scenarios enter through `/plan <message>`, leave through `/plan off`, and prove that each committed `plan/mode` precedes the request header it changes, the entry message is logged under plan guidance, and the post-exit request omits that guidance.
 
 ## Consequences
 

.agents/notes/implemented/simplification/2026-07-22-plan-specific-collaboration-state.zh.md

@@ -14,7 +14,7 @@ Status: implemented
 
 Plan mode 拥有一个 plan 专用产品包：位于 `packages/plan/plan-mode/` 的 `@deepseek-ai/dsh-plan-mode`。持久化事实为 `plan/mode: { active: boolean }`，由 `foldPlanMode(events)` 折叠，空日志值为 `false`。`ctx.planMode.get(agent)` 返回 `{ active, pending? }`，`set(agent, active)` 则记录在边界生效的选择。现有的提示词提交、continuation、重试、追加失败和 dispose（资源释放）栅栏在语义上保持不变。
 
-配置严格为 `{ section: string }`。该包自行注册固定的 `plan:policy` 段、`/plan [message]` 和 `exit_plan_mode`。不带参数的 `/plan` 选择该状态；非空参数则先选择该状态，再通过 `agent.steer()` 发送去除首尾空白后的文本，使该文本在受影响的步骤中成为一条记录到日志的普通用户消息。即使 plan mode 未激活，退出工具仍保持注册，以确保请求工具目录稳定。
+配置严格为 `{ section: string }`。该包自行注册固定的 `plan:policy` 段、`/plan [message]`、精确匹配的 `/plan off` 主动退出形式，以及 `exit_plan_mode`。不带参数的 `/plan` 选择激活；其他非空参数则先选择激活，再通过 `agent.steer()` 发送去除首尾空白后的文本，使该文本在受影响的步骤中成为一条记录到日志的普通用户消息。`/plan off` 选择未激活，不产生模型输入，并可取消仍待在边界生效的进入选择。即使 plan mode 未激活，退出工具仍保持注册，以确保请求工具目录稳定。
 
 ACP 保留协议层的 `default` 和 `plan` id。桥接层把这两个 id 映射到布尔服务，只公布这组固定选项，在适配器边界拒绝其他所有 id，并把已提交的 `plan/mode` 事件映射回 `current_mode_update`。协议仍保持通用性，但不会迫使产品领域也采用通用抽象。
 
@@ -38,9 +38,9 @@ ACP 保留协议层的 `default` 和 `plan` id。桥接层把这两个 id 映射
 ## 验证
 
 - 包测试通过布尔服务继续覆盖边界顺序、重试、追加失败、HMR（热模块替换）资源释放、提示词组装、稳定的原生 schema 与 Code Mode schema、评审结果和不变式。
-- 命令测试覆盖不带参数的 `/plan`、`/plan <message>`、不存在 `/mode` 和 `/review`，以及随 effect 作用域移除。
+- 命令测试覆盖不带参数的 `/plan`、`/plan <message>`、激活状态下的 `/plan off`、取消待生效的进入选择、未激活状态下的幂等性、不存在 `/mode` 和 `/review`，以及随 effect 作用域移除。
 - ACP 测试覆盖固定模式列表公布、两个 id、未知 id 拒绝、乐观更新、已提交退出和加载回放。
-- 无密钥 TUI 场景通过 `/plan <message>` 进入，证明 `plan/mode` 先于首个请求头，且消息在 plan 引导下记录到日志。
+- 无密钥 TUI 场景通过 `/plan <message>` 进入、通过 `/plan off` 退出，并证明每个已提交的 `plan/mode` 都先于其所改变的请求头，进入消息在 plan 引导下记录到日志，且退出后的请求不含该引导。
 
 ## 后果
 

.agents/notes/implemented/simplification/2026-07-23-collapse-persistence-flush-state.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
+2026-07-23-collapse-persistence-flush-state.md: a9b0f6847712f47d46adb6b01c57563033738964
+2026-07-23-collapse-persistence-flush-state.zh.md: acb9f798d86b4ec41d975d9de23f36080d3d7848

.agents/notes/implemented/simplification/2026-07-23-collapse-persistence-flush-state.md

@@ -0,0 +1,47 @@
+# Agent Note: Collapse live persistence into one flush controller
+
+Status: implemented
+
+English | [中文](2026-07-23-collapse-persistence-flush-state.zh.md)
+
+## Problem
+
+The persistence coordinator represented one live session's write lifecycle with separate buffer, initialization, and retirement containers plus the per-id operation chain. Those structures mirrored the same fact: whether that exact `Session` still had initialization or events that must settle before its state could be released. The checkpoint-only drain also kept every event volatile until another plugin requested `session/flush`, even though the backend could begin durability work without blocking the synchronous producer.
+
+## Decision
+
+Each live `Session` has one controller containing `pending`, `init`, and the optional current `flush` promise. A `session/event` listener copies the frozen event into `pending` and immediately schedules `ensureFlush()`. Calls during an active write reuse the same promise. The drain snapshots one stable pending prefix and removes it only after `appendBatch` commits; events admitted during the write remain after that prefix and schedule one follow-up batch.
+
+`session/flush` is an observation barrier. It waits for initialization and repeatedly awaits or starts the controller's flush until neither a current promise nor pending events remain. An eager failure is logged without rejecting the synchronous event producer, retains the complete batch, and is retried by the next explicit flush, retirement attempt, or backend teardown. Explicit flush and teardown still surface the failure if that retry rejects.
+
+Initialization now enters the existing per-id operation chain once and calls the unserialized core operations while it owns that turn. The chain remains separate from the live controller because detached public `create`/`append`/`load` calls can race without a `Session` object and still require identity-level serialization.
+
+Crash repair is cold-only. For a live identity, `load(id)` snapshots the authoritative in-memory events before awaiting their flush, then returns them with `SessionState.meta`, the header actually used for durable writes; it rejects an open turn without reading or repairing storage. A cold load reserves its identity synchronously inside the per-id chain before awaiting stored-prefix reads or repair writes; the `session/created` publication boundary rejects and rolls back a same-id live session until the reservation clears. HMR adoption remains separate through `loadStored` plus the coordinator's cwd check and truncates torn storage without closing the authoritative live turn.
+
+The live-controller map is also the retirement registry. Successful retirement drains and removes its controller; failed retirement leaves it in the map. Backend teardown stops event admission, flushes every controller still present, awaits remaining per-id operations, and closes the backend. No separate retirement set is needed to rediscover unfinished work.
+
+## Alternatives considered
+
+**Keep checkpoint-only write-behind.** This can form larger batches, but makes durability depend on a separately mounted checkpoint policy and maximizes the crash-loss window between checkpoints. Eager scheduling still coalesces synchronous bursts and events arriving during an active write.
+
+**Use one coordinator-wide flush promise.** The attachment pattern works for one file, but a global promise would serialize unrelated sessions. One controller per live session preserves independent backend progress while the per-id chain protects same-identity operations.
+
+**Latch the first eager error permanently.** This makes every later flush deterministic, but prevents the existing teardown retry from recovering a transient storage failure. Retaining the batch without latching the error preserves both observability and retry.
+
+**Reject every live load.** This is safe but removes established balanced live snapshots used by persistence consumers and tests. Snapshot-before-flush gives the call a stable linearization point: successful flush proves exactly that snapshot is durable, while the live path never invokes crash repair.
+
+## Verification
+
+- A focused coordinator test gates the first append, admits another event during that write, and observes an automatic second durable batch without calling `session/flush`.
+- The shared coordinator contract still covers live adoption, collisions, crash repair, and session/backend disposal over the in-memory, JSONL, and SQLite backends.
+- Failure and teardown tests keep rejected batches pending, retry them before close, and prove an in-flight controller delays backend close.
+- The shared backend contract persists an open live turn, proves `load` rejects without writing synthetic closers, completes and retires the owner, then reloads the exact completed turn.
+- An AgentLoop regression races `resume()` against a live open turn and proves the original agent can still durably complete it without an injected `interrupted` boundary.
+- A controlled backend blocks `loadStored`, attempts same-id session publication while repair owns the reservation, and proves rollback leaves no ghost controller before a balanced resume succeeds.
+- The ownerless-claim contract gives the live `Session` a different `createdAt`, then proves live and later cold loads both return the original stored header.
+
+## Consequences
+
+The coordinator has three long-lived containers: persisted identity state, live-session controllers, and per-id operation chains. Eager writes reduce the ordinary crash-loss window and remove separate buffer, initialization, and retirement registries. They can produce more backend batches than checkpoint-only draining; same-tick bursts and events admitted during one write still coalesce.
+
+`session/flush` no longer chooses when ordinary persistence begins. It remains the ordering and error-observation boundary used by the loop and checkpoint policy, so a successful checkpoint still means every event admitted before its completion is durable.

.agents/notes/implemented/simplification/2026-07-23-collapse-persistence-flush-state.zh.md

@@ -0,0 +1,47 @@
+# Agent Note: 将实时持久化归并到单个刷新控制器
+
+Status: implemented
+
+[English](2026-07-23-collapse-persistence-flush-state.md) | 中文
+
+## 问题
+
+持久化协调器使用彼此独立的缓冲区、初始化容器和退役容器，以及按 id 划分的操作链，表示一个活跃会话的写入生命周期。这些结构反映的是同一个事实：该 `Session` 是否仍有初始化操作或事件必须完成，之后才能释放其状态。仅由检查点触发的排空还会让每个事件都停留在易失状态，直至另一个插件请求 `session/flush`，尽管后端可以在不阻塞同步生产方的情况下开始持久化工作。
+
+## 决策
+
+每个活跃的 `Session` 都有一个控制器，其中包含 `pending`、`init` 和可选的当前 `flush` promise。`session/event` 监听器将冻结的事件复制到 `pending`，并立即调度 `ensureFlush()`。活跃写入期间的调用复用同一个 promise。排空操作会对待处理事件中一个稳定的前缀生成快照，并且只在 `appendBatch` 提交后移除该前缀；写入期间接纳的事件保留在该前缀之后，并调度一个后续批次。
+
+`session/flush` 是观测屏障。它等待初始化完成，并反复等待或启动控制器的刷新，直至当前 promise 和待处理事件均不存在。即时写入失败会被记录，但不会拒绝同步事件生产方；完整批次会保留下来，由下一次显式刷新、退役尝试或后端资源销毁重试。若该次重试仍失败，显式刷新和资源销毁仍会向调用方暴露失败。
+
+初始化只进入现有的按 id 操作链一次，并在占有该轮执行权时调用未串行化的核心操作。该操作链与活跃控制器保持分离，因为公共 `create`、`append`、`load` 调用即使没有 `Session` 对象仍可能发生竞态，依然需要按标识串行执行。
+
+崩溃修复仅适用于冷态标识。对于活跃标识，`load(id)` 会在等待刷新完成前，先对内存中的权威事件生成快照，再将这些事件与 `SessionState.meta`（即持久化写入实际使用的标头）一同返回；若轮次仍打开，则在不读取或修复存储的情况下拒绝该次加载。冷态加载会先在按 id 操作链内同步占用对应标识，再等待读取已存储前缀或执行修复写入；在这项占用解除前，`session/created` 发布边界会拒绝同 id 活跃会话的发布并将其回滚。HMR 接管仍由 `loadStored` 与协调器的 cwd 检查独立处理，会截断撕裂的存储，但不会闭合权威的活跃轮次。
+
+活跃控制器映射同时也是退役注册表。退役成功时，系统排空并移除其控制器；退役失败时，控制器保留在映射中。后端资源销毁会停止接纳事件，刷新所有仍存在的控制器，等待其余按 id 操作完成，然后关闭后端。无需另设退役集合来重新发现未完成的工作。
+
+## 备选方案
+
+**保留仅由检查点触发的延后写入。** 这种方式可以形成更大的批次，但会让持久性依赖另行挂载的检查点策略，并使检查点之间因崩溃而丢失数据的窗口达到最大。即时调度仍会合并同步突发事件，以及活跃写入期间到达的事件。
+
+**在整个协调器范围内使用一个刷新 promise。** 这种挂接方式适用于单个文件，但全局 promise 会串行化互不相关的会话。每个活跃会话各有一个控制器，既能让不同会话的后端操作独立推进，又由按 id 操作链保护同一标识的操作。
+
+**永久锁存首次即时写入错误。** 这会让后续每次刷新都得到确定的结果，却会阻止现有的资源销毁重试从暂时性存储故障中恢复。保留批次但不锁存错误，可以同时保留可观测性和重试能力。
+
+**拒绝对所有活跃会话的加载。** 这样做很安全，但会让持久化消费方和测试无法再使用既有的闭合活跃会话快照。先生成快照再刷新，为调用提供了稳定的线性化点：刷新成功即可证明正是该快照已持久化，而活跃路径绝不调用崩溃修复。
+
+## 验证
+
+- 一个针对协调器的测试会阻塞第一次追加，在该次写入期间接纳另一个事件，并在不调用 `session/flush` 的情况下观测到自动执行的第二个持久批次。
+- 共享协调器契约仍覆盖内存、JSONL 和 SQLite 后端上的活跃会话接管、冲突、崩溃修复，以及会话和后端的资源释放。
+- 失败和资源销毁测试会让写入失败的批次保持待处理，在关闭前重试这些批次，并证明尚在执行的控制器会延迟后端关闭。
+- 共享后端契约会持久化一个仍打开的活跃轮次，证明 `load` 会拒绝且不会写入合成闭合事件，随后完成该轮次并让其所有者退役，最后重新加载完全相同的已完成轮次。
+- AgentLoop 回归测试让 `resume()` 与一个仍打开的活跃轮次发生竞态，并证明原有的 agent（智能体）仍能完成该轮次并将其持久化，其间不会注入 `interrupted` 边界。
+- 一个受控后端会阻塞 `loadStored`，在修复操作持有标识占用期间尝试发布同 id 会话，并证明回滚不会留下残留控制器，之后可以成功恢复一个闭合会话。
+- 无所有者声明契约会为活跃 `Session` 设置不同的 `createdAt`，并证明活跃加载和之后的冷态加载均返回最初存储的标头。
+
+## 后果
+
+协调器有三个长生命周期容器：持久化的标识状态、活跃会话控制器和按 id 操作链。即时写入缩短了通常情况下因崩溃而丢失数据的窗口，并移除了彼此独立的缓冲区、初始化注册表和退役注册表。与仅由检查点触发的排空相比，这种方式可能产生更多后端批次；同一轮事件循环内的突发事件和一次写入期间接纳的事件仍会合并。
+
+`session/flush` 不再决定普通持久化何时开始。它仍是循环和检查点策略使用的顺序与错误观测边界，因此检查点成功仍表示在其完成前接纳的每个事件都已持久化。

.agents/notes/proposed/feature/2026-07-10-sqlite-session-query-provider.md

@@ -1,51 +0,0 @@
-# Agent Note: SQLite FTS5 session search
-
-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, 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.
-
-## Proposal
-
-Add `@deepseek-ai/dsh-session-query-sqlite` beside the exact-read package. The package will expose a search service or extend the family with the smallest API required by its actual consumers; phase one does not pre-commit a provider-registration protocol. It will depend on `ctx.sessions` and optional `ctx.sessionPersistence`, own a separate derived SQLite database, and reuse the canonical `foldSurface()` classification.
-
-The implementation owns one serialized reconciliation/DB transaction state machine. A transaction observes authoritative persisted metadata and live snapshots, extracts semantic documents, updates derived tables, advances relevant cursor generations, and executes or enables the corresponding query. No second service maintains parallel fingerprints, dirty flags, live-id sets, or invalidation generations.
-
-Persisted documents survive restarts. Live overrides are connection-local and shadow the persisted rows for the same session, then disappear when the live owner or database closes. The derived database remains separate from canonical persistence so index reset, corruption, tokenizer changes, and schema churn cannot endanger durable conversation logs.
-
-## Search semantics to decide with implementation
-
-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.
-
-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.
-
-## Extraction and reconciliation
-
-The package starts with first-party semantic extraction for messages, reasoning, tool calls/results, blocked prompts, context, steering, todos, and error/status detail. Structural events and stream chunks contribute no document. Unknown declaration-merged event/content types remain non-searchable unless a real extension consumer demonstrates the need for a public extractor registry.
-
-Reconciliation may use stable fingerprints to avoid rewriting unchanged persisted sessions, but the database package owns their calculation and storage. It must never report a row current when source observation or extraction failed. Provider-schema mismatch may reset only the derived database; ordinary source changes use transactional upsert/delete. Mounted but unreadable persistence fails affected searches without affecting canonical writes or known live exact reads.
-
-## Alternatives considered
-
-- **Add FTS tables to the canonical persistence database** — rejected because a rebuildable index must not share the authoritative log's schema/reset/failure boundary.
-- **Reintroduce phase-one provider coordination** — rejected because there is one planned implementation and no evidence for a stable multi-provider seam.
-- **Persist live overrides immediately** — rejected because live events are not canonical until the existing checkpoint commits.
-- **Return BM25 scores** — rejected because provider-specific numeric scales are unstable across corpus changes.
-
-## Acceptance criteria
-
-- 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, 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 Agent Note is amended to the measured tokenizer and public API actually implemented before moving to `implemented/`.
-
-## Risks
-
-A single owner is simpler but initially less reusable than a provider-neutral seam. That is intentional: a second real backend can reveal what to extract. SQLite runtime differences can affect FTS ranking and snippets, so tests must pin only contract-controlled ordering and presentation. The separate database adds configuration and lifecycle work, but preserves the canonical store's safety boundary.

.agents/skills/dsh-translate-docs/SKILL.md

@@ -20,7 +20,7 @@ These are authoritative; read them at the source so this skill never drifts out
 - **[docs/i18n/README.md](../../../docs/i18n/README.md)** — the pairing contract: the three-file pair (`foo.md`, `foo.zh.md`, `foo.i18n.yaml`), the consistency record's both-side blob hashes, the language-switcher lines, scope/exclusions, and the rollout manifest.
 - **[docs/i18n/translation-rules.md](../../../docs/i18n/translation-rules.md)** — how to translate: faithfulness, structure preservation, terminology discipline, typography (MUST/SHOULD levels).
 - **[docs/i18n/terminology.md](../../../docs/i18n/terminology.md)** — the terminology table, binding in both directions. Load it BEFORE translating, not when a term feels uncertain; the terms you don't notice are the ones that drift.
-- **[docs/i18n/translation-prompt.md](../../../docs/i18n/translation-prompt.md)** — the automated pipeline's machine-consumed template. Agents using this skill do not render it; the renderer injects `translation-rules.md` so rules have only one home.
+- **[docs/i18n/translation-prompt.md](../../../docs/i18n/translation-prompt.md)** — the automated pipeline's calibrated machine-consumed template. Agents using this skill do not render it; the terminology table is the only repository file the automated renderer injects, while this skill and `translation-rules.md` remain binding for agent-authored translations.
 - **[dsh-prose-standard](../dsh-prose-standard/SKILL.md)** — required prose coverage and editorial judgment. Apply it to both sides without adding or dropping source propositions.
 
 ## Find the work

.github/workflows/ci.yml

@@ -27,38 +27,119 @@ env:
 
 jobs:
 
-  # Two enterprise runners split the two longest primary Node paths. The
-  # static lane starts snapshot and artifact validation as soon as its build
-  # completes, while exhaustive coverage runs alone on the other runner.
+  # Three enterprise jobs isolate coverage, static analysis, and the
+  # build-backed consumer tail. The static job publishes its exact build so
+  # consumers do not repeat the longest part of their critical path.
   node-24:
     if: github.event_name == 'pull_request'
-    runs-on: ${{ matrix.runner }}
-    name: ${{ matrix.name }}
+    runs-on: dsh-enterprise-ubuntu-latest-32core-test
+    name: node 24 / static
+    env:
+      DSH_GATE_CONCURRENCY: '8'
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          persist-credentials: false
+
+      # Pull requests consume the default-branch cache but do not put cache
+      # compression and upload on the paid latency-critical path.
+      - uses: actions/cache/restore@v4
+        with:
+          path: /home/runner/.local/share/pnpm/store/v11
+          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }}
+          restore-keys: |
+            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-
+
+      - uses: actions/setup-node@v6
+        with:
+          node-version: ${{ env.PRIMARY_NODE_VERSION }}
+
+      - name: Enable corepack and install dependencies
+        run: |
+          corepack enable
+          pnpm install --frozen-lockfile
+
+      - name: Run static gates
+        run: pnpm run check:ci:static
+
+      - name: Pack built tree
+        run: >-
+          tar -czf "$RUNNER_TEMP/node-24-built-tree.tar.gz"
+          apps/*/lib packages/*/*/lib vendor/*/lib
+
+      - uses: actions/upload-artifact@v6
+        with:
+          name: node-24-built-tree
+          path: ${{ runner.temp }}/node-24-built-tree.tar.gz
+          if-no-files-found: error
+          retention-days: 1
+          compression-level: 0
+
+  node-24-coverage:
+    if: github.event_name == 'pull_request'
+    runs-on: dsh-enterprise-ubuntu-24-04-32core-test
+    name: node 24 / coverage
     env:
       DSH_COVERAGE_MAX_WORKERS: '24'
+      DSH_GATE_CONCURRENCY: '8'
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          persist-credentials: false
+
+      - uses: actions/cache/restore@v4
+        with:
+          path: /home/runner/.local/share/pnpm/store/v11
+          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }}
+          restore-keys: |
+            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-
+
+      - uses: actions/setup-node@v6
+        with:
+          node-version: ${{ env.PRIMARY_NODE_VERSION }}
+
+      - name: Enable corepack, install dependencies, and prepare bubblewrap
+        run: |
+          corepack enable
+          pnpm install --frozen-lockfile &
+          install_pid=$!
+          bash scripts/prepare-ci-bubblewrap.sh &
+          sandbox_pid=$!
+          install_status=0
+          wait "$install_pid" || install_status=$?
+          sandbox_status=0
+          wait "$sandbox_pid" || sandbox_status=$?
+          if (( install_status != 0 )); then exit "$install_status"; fi
+          exit "$sandbox_status"
+
+      - name: Run exhaustive coverage
+        run: pnpm run check:ci:coverage
+
+  node-24-consumers:
+    needs: node-24
+    if: github.event_name == 'pull_request'
+    runs-on: dsh-enterprise-ubuntu-latest-32core-test
+    name: node 24 / snapshots and artifacts
+    env:
       DSH_ESLINT_CACHE: '1'
       DSH_ESLINT_CONCURRENCY: '8'
       DSH_GATE_CONCURRENCY: '8'
       DSH_NODE_COMPAT_SKIP_TYPECHECK: '1'
       DSH_PUBLINT_CONCURRENCY: '8'
       DSH_SNAPSHOT_MAX_CONCURRENCY: '32'
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - lane: static-snapshots-artifacts
-            name: node 24 / static, snapshots, and artifacts
-            runner: dsh-enterprise-ubuntu-latest-32core-test
-          - lane: coverage
-            name: node 24 / coverage
-            runner: dsh-enterprise-ubuntu-24-04-32core-test
     steps:
       - uses: actions/checkout@v6
         with:
           persist-credentials: false
 
-      # Pull requests consume the default-branch cache but do not put cache
-      # compression and upload on the paid latency-critical path.
+      - uses: actions/download-artifact@v8
+        with:
+          name: node-24-built-tree
+          path: ${{ runner.temp }}
+
+      - name: Restore built tree
+        run: tar -xzf "$RUNNER_TEMP/node-24-built-tree.tar.gz"
+
       - uses: actions/cache/restore@v4
         with:
           path: /home/runner/.local/share/pnpm/store/v11
@@ -67,7 +148,6 @@ jobs:
             ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-
 
       - uses: actions/cache/restore@v4
-        if: matrix.lane == 'static-snapshots-artifacts'
         with:
           path: .cache/eslint
           key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-eslint-full-${{ hashFiles('pnpm-lock.yaml', 'eslint.config.mjs', 'tsconfig.json', 'tsconfig.base.json', 'tsconfig.base.client.json', 'tsconfig.host.json', 'tsconfig.client.json', 'packages/*/*/tsconfig.json', 'examples/*/tsconfig.json') }}
@@ -92,26 +172,8 @@ jobs:
           if (( install_status != 0 )); then exit "$install_status"; fi
           exit "$sandbox_status"
 
-      - name: Run static, compatibility, snapshot, and artifact gates
-        if: matrix.lane == 'static-snapshots-artifacts'
+      - name: Run compatibility, snapshot, and artifact gates
         run: |
-          static_log="$RUNNER_TEMP/static-gates.log"
-          : > "$static_log"
-          pnpm run check:ci:static > >(tee "$static_log") 2>&1 &
-          static_pid=$!
-
-          until grep -Fq 'run-gates: PASS build ' "$static_log"; do
-            if ! kill -0 "$static_pid" 2>/dev/null; then
-              static_status=0
-              wait "$static_pid" || static_status=$?
-              if grep -Fq 'run-gates: PASS build ' "$static_log"; then break; fi
-              if (( static_status != 0 )); then exit "$static_status"; fi
-              echo '::error::Static gates exited without completing the build.'
-              exit 1
-            fi
-            sleep 0.2
-          done
-
           pnpm run check:ci:lint &
           lint_pid=$!
           pnpm run check:node-compat &
@@ -143,17 +205,13 @@ jobs:
             fi
           }
           for child_pid in \
-            "$static_pid" "$lint_pid" "$compat_pid" "$snapshot_pid" \
+            "$lint_pid" "$compat_pid" "$snapshot_pid" \
             "$publint_pid" "$node_next_pid" "$built_invariants_pid" "$built_bin_pid"
           do
             capture_status "$child_pid"
           done
           exit "$final_status"
 
-      - name: Run exhaustive coverage
-        if: matrix.lane == 'coverage'
-        run: pnpm run check:ci:coverage
-
 
   node-compat:
     if: github.event_name == 'pull_request'
@@ -629,7 +687,7 @@ jobs:
   all-checks-passed:
     name: all checks passed
     runs-on: ubuntu-latest
-    needs: [node-24, node-compat, python-sdk, windows]
+    needs: [node-24, node-24-coverage, node-24-consumers, node-compat, python-sdk, windows]
     if: always() && github.event_name == 'pull_request'
     steps:
       - name: Fail if any needed job did not succeed

apps/cli/README.md

@@ -10,7 +10,7 @@ The TUI surface:
 - tells the agent where its own source lives: after boot it adds a prompt section naming this harness checkout, resolved from the launcher's real path so it holds under a PATH symlink and an arbitrary cwd, so the self-referential `cordis` toolset can read and modify it;
 - applies the personal overlay from `~/.dsh` (see [app-boot's Personal config](../../packages/ui/app-boot/README.md#personal-config)): `.env` fills environment gaps (ambient > project `.env` > personal `.env`), `config.yaml` patches the booted tree.
 
-The Web surface treats its invoking directory as the default project and loads applicable `AGENTS.md`/`CLAUDE.md` instructions into each agent-loop request prefix with a 65,536-byte render budget.
+The Web surface treats its invoking directory as the default project, loads applicable `AGENTS.md`/`CLAUDE.md` instructions into each agent-loop request prefix with a 65,536-byte render budget, and opts into first-message model titles. The headless surface retains deterministic fallback titles without making the auxiliary title-model request.
 
 ## Install (developer machine)
 
@@ -20,4 +20,4 @@ Symlink the source-running launcher onto your PATH; it resolves the checkout thr
 ln -sf "$(pwd)/bin/dsh" ~/.local/bin/dsh
 ```
 
-`pnpm run demo:tui` runs the same entry from the repo root. The built form (`lib/bin.js`, via `pnpm run build`) needs `node --expose-internals` for the shipped config's HMR entry, exactly like the demo bins.
+`pnpm run demo:tui` runs the same entry from the repo root. The built form (`lib/bin.js`, via `pnpm run build`) boots the same config under plain Node.

apps/cli/package.json

@@ -14,6 +14,16 @@
   "license": "BSD-3-Clause",
   "dependencies": {
     "@deepseek-ai/dsh-app-boot": "workspace:^",
+    "@deepseek-ai/dsh-client-connection": "workspace:^",
+    "@deepseek-ai/dsh-client-hmr": "workspace:^",
+    "@deepseek-ai/dsh-client-i18n": "workspace:^",
+    "@deepseek-ai/dsh-client-runtime": "workspace:^",
+    "@deepseek-ai/dsh-client-ui-conversation": "workspace:^",
+    "@deepseek-ai/dsh-client-ui-layout": "workspace:^",
+    "@deepseek-ai/dsh-client-ui-question": "workspace:^",
+    "@deepseek-ai/dsh-client-ui-sidebar": "workspace:^",
+    "@deepseek-ai/dsh-client-ui-theme": "workspace:^",
+    "@deepseek-ai/dsh-client-ui-trajectory": "workspace:^",
     "@deepseek-ai/dsh-frontend": "workspace:^",
     "@deepseek-ai/dsh-host-apiproxy": "workspace:^",
     "@deepseek-ai/dsh-host-runtime": "workspace:^",

apps/cli/src/web.ts

@@ -14,6 +14,34 @@ const LOOPBACK_HOST = '127.0.0.1'
 const ALL_INTERFACES_HOST = '0.0.0.0'
 const REQUEST_ENVELOPE_HEADROOM_BYTES = 1024 * 1024
 
+// --- Client composition (composition decisions live in the composing app) ---
+// The composition layer owns one decision: which plugin packages mount (the
+// roster). Dependency edges and the boot prefetch tier live in each package's
+// dshClient declaration.
+
+/**
+ * Dev-only plugin: the client HMR driver. Whether it composes in is a
+ * deployment decision — the dev graph includes its row, the prod graph does
+ * not mount it at all.
+ */
+const CLIENT_HMR_ID = '@deepseek-ai/dsh-client-hmr'
+
+/** Bundle stat-poll interval for --dev (held here so the startup log states the real value). */
+const CLIENT_BUNDLE_POLL_MS = 500
+
+/** The client plugin roster (flat; per-row boot behavior comes from manifests). */
+const CLIENT_PACKAGES = [
+  '@deepseek-ai/dsh-client-connection',
+  '@deepseek-ai/dsh-client-runtime',
+  '@deepseek-ai/dsh-client-ui-theme',
+  '@deepseek-ai/dsh-client-i18n',
+  '@deepseek-ai/dsh-client-ui-layout',
+  '@deepseek-ai/dsh-client-ui-sidebar',
+  '@deepseek-ai/dsh-client-ui-conversation',
+  '@deepseek-ai/dsh-client-ui-question',
+  '@deepseek-ai/dsh-client-ui-trajectory',
+] as const
+
 export async function runWeb(argv: string[]): Promise<void> {
   const { values } = parseArgs({
     args: argv,
@@ -21,6 +49,7 @@ export async function runWeb(argv: string[]): Promise<void> {
       host: { type: 'string', default: LOOPBACK_HOST },
       port: { type: 'string', default: '3080' },
       'max-request-body-bytes': { type: 'string' },
+      dev: { type: 'boolean', default: false },
     },
     allowPositionals: false,
   })
@@ -40,8 +69,11 @@ export async function runWeb(argv: string[]): Promise<void> {
     ? undefined
     : Number(values['max-request-body-bytes'])
   if (configuredMaxRequestBodyBytes !== undefined
-    && (!Number.isInteger(configuredMaxRequestBodyBytes) || configuredMaxRequestBodyBytes < 1)) {
-    process.stderr.write(`dsh web: invalid --max-request-body-bytes ${values['max-request-body-bytes']}\n`)
+    && (!Number.isInteger(configuredMaxRequestBodyBytes)
+      || configuredMaxRequestBodyBytes < 1)) {
+    process.stderr.write(
+      `dsh web: invalid --max-request-body-bytes ${values['max-request-body-bytes']}\n`,
+    )
     process.exit(1)
   }
 
@@ -50,22 +82,46 @@ export async function runWeb(argv: string[]): Promise<void> {
     boot: {
       persistenceRoot: './.sessions',
       workspaceContext: { maxBytes: 65_536 },
+      sessionTitleLlm: true,
     },
   })
   const attachments = host.ctx.get('attachments')
   if (attachments === undefined) throw new Error('dsh web: attachment service unavailable')
   const maxRequestBodyBytes = configuredMaxRequestBodyBytes
-    ?? Math.ceil(attachments.imageLimits.maxMessageImageBytes * 4 / 3) + REQUEST_ENVELOPE_HEADROOM_BYTES
+    ?? Math.ceil(attachments.imageLimits.maxMessageImageBytes * 4 / 3)
+      + REQUEST_ENVELOPE_HEADROOM_BYTES
 
-  // Web UI plugin chain: in-memory Loader tree over the eight UI packages,
-  // then the registry that feeds __DSH_BOOT__ and /plugins/<id>/client.js.
-  const mounted = await mountWebPlugins(host.ctx)
+  // Client plugin chain: in-memory Loader tree over the composed roster, then
+  // the registry that feeds the __DSH_BOOT__ entry graph and
+  // /plugins/<id>/client.js. All row content comes from dshClient discovery
+  // over the mounted roster (dev adds the HMR driver row and turns on the
+  // bundle watch that drives rebuilt frames).
+  const roster = [...CLIENT_PACKAGES, ...values.dev ? [CLIENT_HMR_ID] : []]
+  const mounted = await mountWebPlugins(host.ctx, roster, import.meta.url)
   const webPlugins = createHostWebPluginRegistry({
     ctx: host.ctx,
     loader: mounted.loader,
     resolvePkgJson: mounted.resolvePkgJson,
     onError: (err: Error) => { process.stderr.write(`dsh web: plugin rescan: ${String(err)}\n`) },
+    ...values.dev ? { watch: { intervalMs: CLIENT_BUNDLE_POLL_MS } } : {},
   })
+  if (values.dev) {
+    // Dev visibility (the registry is a library and never prints): list what
+    // the bundle watch covers, then log every observed rebuild. This is a
+    // second onRebuilt subscription — the SSE relay inside the webserver is
+    // unaffected (multicast).
+    const revs = new Map(webPlugins.graph().entries.map(row => [row.id, row.rev]))
+    const bundlePaths = [...revs.keys()]
+      .map(id => webPlugins.clientPath(id))
+      .filter((path): path is string => path !== undefined)
+    console.log(
+      `dsh web: watching ${String(bundlePaths.length)} plugin bundles (${String(CLIENT_BUNDLE_POLL_MS)}ms poll):\n  ${bundlePaths.join('\n  ')}`,
+    )
+    webPlugins.onRebuilt((id, rev) => {
+      console.log(`dsh web: plugin rebuilt: ${id} rev ${revs.get(id) ?? '?'} -> ${rev}`)
+      revs.set(id, rev)
+    })
+  }
   // Published so the webserver invariant companion can audit manifest/bundle
   // consistency; nothing else reads this key.
   host.ctx.reflect.provide('webPlugins', webPlugins)
@@ -97,7 +153,14 @@ export async function runWeb(argv: string[]): Promise<void> {
   let server: Awaited<ReturnType<typeof startWebServer>>
   try {
     server = await startWebServer(
-      { host: hostAddress, port, distIndex, apiHandler: host.handler, maxRequestBodyBytes, webPlugins },
+      {
+        host: hostAddress,
+        port,
+        distIndex,
+        apiHandler: host.handler,
+        maxRequestBodyBytes,
+        webPlugins,
+      },
       (err: Error) => {
         process.stderr.write(`dsh web: ${String(err)}\n`)
         void shutdown(1)

apps/cli/tsconfig.json

@@ -8,12 +8,56 @@
     "src"
   ],
   "references": [
-    { "path": "../../vendor/cordis" },
-    { "path": "../../packages/host/apiproxy" },
-    { "path": "../../packages/host/runtime" },
-    { "path": "../../packages/host/webserver" },
-    { "path": "../../packages/core/session" },
-    { "path": "../../packages/ui/app-boot" },
-    { "path": "../../packages/util/paths" }
+    {
+      "path": "../../vendor/cordis"
+    },
+    {
+      "path": "../../packages/host/apiproxy"
+    },
+    {
+      "path": "../../packages/host/runtime"
+    },
+    {
+      "path": "../../packages/host/webserver"
+    },
+    {
+      "path": "../../packages/core/session"
+    },
+    {
+      "path": "../../packages/ui/app-boot"
+    },
+    {
+      "path": "../../packages/util/paths"
+    },
+    {
+      "path": "../../packages/client/connection"
+    },
+    {
+      "path": "../../packages/client/hmr"
+    },
+    {
+      "path": "../../packages/client/runtime"
+    },
+    {
+      "path": "../../packages/client/ui-theme"
+    },
+    {
+      "path": "../../packages/client/i18n"
+    },
+    {
+      "path": "../../packages/client/ui-layout"
+    },
+    {
+      "path": "../../packages/client/ui-sidebar"
+    },
+    {
+      "path": "../../packages/client/ui-conversation"
+    },
+    {
+      "path": "../../packages/client/ui-trajectory"
+    },
+    {
+      "path": "../../packages/client/ui-question"
+    }
   ]
 }

apps/web/package.json

@@ -20,7 +20,7 @@
     "react-dom": "^18.2.0"
   },
   "devDependencies": {
-    "@deepseek-ai/dsh-client-runtime": "workspace:^",
+    "@deepseek-ai/dsh-client-modules": "workspace:^",
     "@deepseek-ai/dsh-client-ui-primitives": "workspace:^",
     "@deepseek-ai/dsh-client-ui-slots": "workspace:^",
     "@deepseek-ai/dsh-client-web-react": "workspace:^",

apps/web/src/node-module-stub.ts

@@ -0,0 +1,16 @@
+/**
+ * Browser stand-in for `node:module`, mapped by the vite alias in
+ * vite.config.ts (design §2.4). The vendored Loader's internal.ts imports
+ * `createRequire` at module scope but only calls it inside
+ * `ModuleLoader.fromInternal()`, whose version probe is compiled to the
+ * `"0.0.0"` define in the browser build — so this throw is a fail-loud
+ * tripwire for any path that would genuinely need Node's module machinery.
+ */
+
+/** Throwing stand-in for node:module's createRequire (never reached in the browser boot). */
+export const createRequire = (): never => {
+  throw new Error('node:module is not available in the browser')
+}
+
+/** Erased type peer for the vendored loader's type-only LoadHookContext import. */
+export type LoadHookContext = never

apps/web/tests/session-title.snapshot.ts

@@ -0,0 +1,114 @@
+// @vitest-environment jsdom
+import { readFileSync } from 'node:fs'
+import { join } from 'node:path'
+import { act, cleanup, fireEvent, screen, waitFor, within } from '@testing-library/react'
+import { afterEach, beforeEach, expect, it, vi } from 'vitest'
+import type { WebBootEntry } from '@deepseek-ai/dsh-client-modules'
+import { bootWebShell } from '@deepseek-ai/dsh-client-web'
+
+const PLUGINS: readonly (WebBootEntry & { dir: string })[] = [
+  { id: '@deepseek-ai/dsh-client-connection', dir: 'connection', url: '/plugins/connection.js', rev: 'fx', inject: [], immediately: true },
+  { id: '@deepseek-ai/dsh-client-runtime', dir: 'runtime', url: '/plugins/runtime.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-connection'], immediately: true },
+  { id: '@deepseek-ai/dsh-client-ui-theme', dir: 'ui-theme', url: '/plugins/ui-theme.js', rev: 'fx', inject: [], immediately: true },
+  { id: '@deepseek-ai/dsh-client-i18n', dir: 'i18n', url: '/plugins/i18n.js', rev: 'fx', inject: [], immediately: true },
+  { id: '@deepseek-ai/dsh-client-ui-layout', dir: 'ui-layout', url: '/plugins/ui-layout.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-runtime'] },
+  { id: '@deepseek-ai/dsh-client-ui-sidebar', dir: 'ui-sidebar', url: '/plugins/ui-sidebar.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
+  { id: '@deepseek-ai/dsh-client-ui-conversation', dir: 'ui-conversation', url: '/plugins/ui-conversation.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
+  { id: '@deepseek-ai/dsh-client-ui-trajectory', dir: 'ui-trajectory', url: '/plugins/ui-trajectory.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-conversation'] },
+]
+
+const bundles = new Map(PLUGINS.map(plugin => [
+  plugin.url,
+  readFileSync(join(process.cwd(), 'packages/client', plugin.dir, 'lib/client.js'), 'utf8'),
+]))
+
+interface FixtureTiming {
+  appendTitle(id: string, title: string): void
+}
+
+interface FixtureWindow extends Window {
+  __DSH_BOOT__?: { rev: string; entries: WebBootEntry[] }
+  __ModuleLoader__?: unknown
+}
+
+class ResizeObserverStub {
+  observe(): void {}
+  disconnect(): void {}
+  unobserve(): void {}
+}
+
+const win = window as FixtureWindow
+let unmount: (() => void) | undefined
+
+beforeEach(() => {
+  localStorage.clear()
+  history.replaceState(null, '', '/?fixture')
+  document.title = 'DeepSeek Harness'
+  const root = document.createElement('div')
+  root.id = 'root'
+  document.body.appendChild(root)
+  vi.stubGlobal('ResizeObserver', ResizeObserverStub)
+  vi.stubGlobal('requestAnimationFrame', (callback: FrameRequestCallback) =>
+    setTimeout(() => { callback(0) }, 0) as unknown as number)
+  vi.stubGlobal('cancelAnimationFrame', (id: number) => { clearTimeout(id) })
+  win.__DSH_BOOT__ = { rev: 'fx', entries: PLUGINS.map(({ dir: _dir, ...plugin }) => plugin) }
+})
+
+afterEach(() => {
+  act(() => { unmount?.() })
+  unmount = undefined
+  cleanup()
+  delete win.__DSH_BOOT__
+  delete win.__ModuleLoader__
+  delete (globalThis as Record<string, unknown>).__fxTiming
+  document.body.innerHTML = ''
+  document.head.querySelectorAll('style[data-plugin]').forEach((style) => { style.remove() })
+  document.title = ''
+  history.replaceState(null, '', '/')
+  vi.unstubAllGlobals()
+})
+
+/** Read only the stable, user-facing title surfaces from the assembled app. */
+function titleSurfaces(label: string): { sidebar: string; breadcrumb: string; documentTitle: string } {
+  const tree = screen.getByRole('tree', { name: 'Sessions' })
+  const sidebar = within(tree).getByText(label).textContent ?? ''
+  const breadcrumb = within(screen.getByRole('navigation', { name: '会话层级' }))
+    .getByRole('button', { name: label }).textContent ?? ''
+  return { sidebar, breadcrumb, documentTitle: document.title }
+}
+
+it('projects initial and revised durable titles through the built eight-plugin fixture app', async () => {
+  const root = document.querySelector<HTMLElement>('#root')
+  if (root === null) throw new Error('snapshot root missing')
+  act(() => {
+    unmount = bootWebShell(root, {
+      fetchBundle: (url) => {
+        const code = bundles.get(url)
+        return code === undefined ? Promise.reject(new Error(`missing built bundle ${url}`)) : Promise.resolve(code)
+      },
+      executeBundle: (code) => { (0, eval)(code) },
+    })
+  })
+
+  const projectLabel = await screen.findByText('fixture', {}, { timeout: 10_000 })
+  const projectRow = projectLabel.closest<HTMLElement>('[role="treeitem"]')
+  if (projectRow === null) throw new Error('fixture project row missing')
+  fireEvent.click(projectRow)
+
+  const initialLabel = 'Fixture 历史会话'
+  const initialRowLabel = await screen.findByText(initialLabel)
+  const initialRow = initialRowLabel.closest<HTMLElement>('[role="treeitem"]')
+  if (initialRow === null) throw new Error('fixture session row missing')
+  fireEvent.click(initialRow)
+  await waitFor(() => { expect(document.title).toBe(`${initialLabel} — DeepSeek Harness`) })
+  const initial = titleSurfaces(initialLabel)
+
+  const revisedLabel = 'Fixture 修订标题'
+  const timing = (globalThis as Record<string, unknown>).__fxTiming as FixtureTiming
+  act(() => { timing.appendTitle('fx-alpha', revisedLabel) })
+  await waitFor(() => { expect(document.title).toBe(`${revisedLabel} — DeepSeek Harness`) })
+  const revised = titleSurfaces(revisedLabel)
+
+  await expect(`${JSON.stringify({ initial, revised }, null, 2)}\n`)
+    .toMatchFileSnapshot('./snapshots/session-title.json')
+})

apps/web/tests/smoke-fixture.e2e.ts

@@ -1,39 +1,68 @@
-// Keyless boot-chain smoke over the REAL carrier: startWebServer + web-plugins
-// registry surface + __DSH_BOOT__ injection + built shell dist in a real
-// chromium. First describe: manifest injection + static serving. Second
-// describe: the full eight-plugin production chain loads through the DI chain
-// in ?fixture mode, exercises the sidebar rail, and covers durable history,
-// pasted, and dropped images without a model key.
+// Keyless boot-chain smoke over the REAL carrier: startWebServer + entry
+// graph (__DSH_BOOT__ web2 shape) injection + built shell dist in a real
+// chromium. First describe: graph injection + the fail-loud half. Second
+// describe: the settled success pass — all nine REAL tsdown bundles load
+// through the module system + vendored Loader chain in ?fixture mode (the
+// infrastructure four ride the immediately prefetch tier, the UI rows fetch
+// on demand), the three-column frame appears in one flip, and the resident
+// question completes through the real UI stack. The full model round lands
+// in smoke-real under the W5 real-host standard.
 import { existsSync } from 'node:fs'
 import { fileURLToPath } from 'node:url'
 import type { Browser, Page } from 'playwright'
 import { chromium } from 'playwright'
 import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
 import { startWebServer } from '@deepseek-ai/dsh-host-webserver'
-import type { WebPluginBootEntry } from '@deepseek-ai/dsh-host-webserver'
+import type { WebBootEntry, WebBootGraph } from '@deepseek-ai/dsh-host-webserver'
 import { DIST_INDEX, probeFreePort, requireDist, saveFailureShot } from './support.ts'
 
 const bundlePath = (dir: string): string =>
   fileURLToPath(new URL(`../../../packages/client/${dir}/lib/client.js`, import.meta.url))
 
-/** id ↔ bundle table for the success pass (the production Web plugin chain). */
-const REAL_PLUGINS: { id: string; dir: string; inject: string[]; immediately?: boolean }[] = [
-  { id: '@deepseek-ai/dsh-client-connection', dir: 'connection', inject: [], immediately: true },
+const LAYOUT_ID = '@deepseek-ai/dsh-client-ui-layout'
+const SIDEBAR_ID = '@deepseek-ai/dsh-client-ui-sidebar'
+const FIXTURE_PNG = 'iVBORw0KGgoAAAANSUhEUgAAAKAAAABaCAYAAAA/xl1SAAAAvklEQVR42u3SMQ0AAAjAMIyhELM4AAe8PD1qYFlk9cCXEAEDYkAwIAYEA2JAMCAGBANiQDAgBgQDYkAwIAYEA2JAMCAGBANiQDAgBgQDYkAwIAYEA2JAMCAGxIBCYEAMCAbEgGBADAgGxIBgQAwIBsSAYEAMCAbEgGBADAgGxIBgQAwIBsSAYEAMCAbEgGBADAgGxIAYEAyIAcGAGBAMiAHBgBgQDIgBwYAYEAyIAcGAGBAMiAHBgBgQDIgB4bYWLb6pnOb1xAAAAABJRU5ErkJggg=='
+
+/** id ↔ bundle table for the success pass (the complete Web UI assembly). */
+const REAL_PLUGINS: { id: string; dir: string; inject?: string[]; immediately?: boolean }[] = [
+  { id: '@deepseek-ai/dsh-client-connection', dir: 'connection', immediately: true },
   { id: '@deepseek-ai/dsh-client-runtime', dir: 'runtime', inject: ['@deepseek-ai/dsh-client-connection'], immediately: true },
-  { id: '@deepseek-ai/dsh-client-ui-theme', dir: 'ui-theme', inject: [], immediately: true },
-  { id: '@deepseek-ai/dsh-client-i18n', dir: 'i18n', inject: [], immediately: true },
-  { id: '@deepseek-ai/dsh-client-ui-layout', dir: 'ui-layout', inject: ['@deepseek-ai/dsh-client-runtime'] },
-  { id: '@deepseek-ai/dsh-client-ui-sidebar', dir: 'ui-sidebar', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
-  { id: '@deepseek-ai/dsh-client-ui-conversation', dir: 'ui-conversation', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
+  { id: '@deepseek-ai/dsh-client-ui-theme', dir: 'ui-theme', immediately: true },
+  { id: '@deepseek-ai/dsh-client-i18n', dir: 'i18n', immediately: true },
+  { id: LAYOUT_ID, dir: 'ui-layout', inject: ['@deepseek-ai/dsh-client-runtime'] },
+  { id: SIDEBAR_ID, dir: 'ui-sidebar', inject: [LAYOUT_ID] },
+  { id: '@deepseek-ai/dsh-client-ui-conversation', dir: 'ui-conversation', inject: [LAYOUT_ID] },
+  { id: '@deepseek-ai/dsh-client-ui-question', dir: 'ui-question', inject: ['@deepseek-ai/dsh-client-ui-conversation'] },
   { id: '@deepseek-ai/dsh-client-ui-trajectory', dir: 'ui-trajectory', inject: ['@deepseek-ai/dsh-client-ui-conversation'] },
 ]
 
-/** Manifest served by the fake registry: one live bundle row, one missing row. */
-const ROWS: WebPluginBootEntry[] = [
-  { id: '@deepseek-ai/dsh-client-ui-layout', url: '/plugins/@deepseek-ai/dsh-client-ui-layout/client.js', inject: [] },
-  { id: '@probe/absent', url: '/plugins/@probe/absent/client.js', inject: [] },
-]
-const LAYOUT_BUNDLE = bundlePath('ui-layout')
+const BUNDLE_PATHS = new Map(REAL_PLUGINS.map(p => [p.id, bundlePath(p.dir)]))
+
+const row = (id: string, extra?: Partial<WebBootEntry>): WebBootEntry =>
+  ({ id, url: `/plugins/${id}/client.js?rev=e2e`, rev: 'e2e', ...extra })
+
+const graphRows: WebBootEntry[] = REAL_PLUGINS.map(p => row(p.id, {
+  ...(p.inject !== undefined ? { inject: p.inject } : {}),
+  ...(p.immediately === true ? { immediately: true } : {}),
+}))
+
+/** Graph for the fail-loud half: the immediately tier, one live UI row, one missing row. */
+const FAIL_GRAPH: WebBootGraph = {
+  rev: 'e2e-fail',
+  entries: [...graphRows.filter(r => r.immediately === true), row(LAYOUT_ID), row('@probe/absent')],
+}
+
+/** Graph for the success pass: the complete assembly. */
+const OK_GRAPH: WebBootGraph = { rev: 'e2e-ok', entries: graphRows }
+
+/** Registry stub over a fixed graph (the real HostWebPluginRegistry is webserver-side production code). */
+function fixedRegistry(graph: WebBootGraph, byId: ReadonlyMap<string, string>) {
+  return {
+    graph: () => graph,
+    clientPath: (id: string) => byId.get(id),
+    onRebuilt: () => () => undefined,
+  }
+}
 
 describe('web boot chain (keyless, real carrier)', () => {
   let server: Awaited<ReturnType<typeof startWebServer>>
@@ -51,10 +80,7 @@ describe('web boot chain (keyless, real carrier)', () => {
       distIndex: DIST_INDEX,
       apiHandler,
       maxRequestBodyBytes: 32 * 1024 * 1024,
-      webPlugins: {
-        snapshot: () => ROWS,
-        clientPath: id => (id === ROWS[0]!.id ? LAYOUT_BUNDLE : undefined),
-      },
+      webPlugins: fixedRegistry(FAIL_GRAPH, BUNDLE_PATHS),
     }, (err) => { pageErrors.push(`server: ${String(err)}`) })
     browser = await chromium.launch()
     page = await browser.newPage()
@@ -67,16 +93,25 @@ describe('web boot chain (keyless, real carrier)', () => {
     await server?.close()
   })
 
-  it('GET / injects the manifest verbatim', async () => {
+  it('GET / injects the entry graph verbatim', async () => {
     onTestFailed(() => saveFailureShot(page, 'smoke-boot-manifest'))
     const boot = await page.evaluate(() => (window as { __DSH_BOOT__?: unknown }).__DSH_BOOT__)
-    expect(boot).toEqual({ plugins: ROWS })
+    expect(boot).toEqual(FAIL_GRAPH)
   })
 
   it('serves a real bundle through the plugins endpoint', async () => {
-    const res = await page.request.get(`${new URL(page.url()).origin}${ROWS[0]!.url}`)
+    const res = await page.request.get(`${new URL(page.url()).origin}/plugins/${LAYOUT_ID}/client.js`)
     expect(res.status()).toBe(200)
-    expect(await res.text()).toContain('window.DSHClientProxy.loadPlugin')
+    expect(await res.text()).toContain('window.__ModuleLoader__.load')
+  })
+
+  it('boots to the loading page and fail-louds the absent entry', async () => {
+    onTestFailed(() => saveFailureShot(page, 'smoke-boot-fail-loud'))
+    await page.waitForSelector('text=HARNESS', { timeout: 10_000 })
+    await page.waitForSelector('text=Failed to load plugins', { timeout: 10_000 })
+    await page.waitForSelector('text=@probe/absent', { timeout: 2000 })
+    // The real UI must not have flipped in: the gate opens only on settled.
+    expect(await page.locator('[class*="frame"]').count()).toBe(0)
   })
 
   it('applies the token sheets before any plugin CSS', async () => {
@@ -85,8 +120,7 @@ describe('web boot chain (keyless, real carrier)', () => {
   })
 })
 
-describe('web boot chain success pass (keyless, production plugin chain, ?fixture)', () => {
-  const missing = REAL_PLUGINS.filter(p => !existsSync(bundlePath(p.dir)))
+describe('web boot chain success pass (keyless, nine real bundles, ?fixture)', () => {
   let server: Awaited<ReturnType<typeof startWebServer>>
   let browser: Browser
   let page: Page
@@ -94,14 +128,9 @@ describe('web boot chain success pass (keyless, production plugin chain, ?fixtur
 
   beforeAll(async () => {
     requireDist()
+    const missing = REAL_PLUGINS.filter(p => !existsSync(bundlePath(p.dir)))
     if (missing.length > 0) throw new Error(`client bundles not built (pnpm --filter <pkg> bundle): ${missing.map(m => m.dir).join(', ')}`)
     const port = await probeFreePort()
-    const rows: WebPluginBootEntry[] = REAL_PLUGINS.map((p) => {
-      const row: WebPluginBootEntry = { id: p.id, url: `/plugins/${p.id}/client.js`, inject: p.inject }
-      if (p.immediately === true) row.immediately = true
-      return row
-    })
-    const byId = new Map(REAL_PLUGINS.map(p => [p.id, bundlePath(p.dir)]))
     // ?fixture never opens HTTP streams; /api is a tripwire like the first describe.
     const apiHandler = { fetch: () => Promise.resolve(new Response('fixture mode must not call /api', { status: 500 })) }
     server = await startWebServer({
@@ -110,7 +139,7 @@ describe('web boot chain success pass (keyless, production plugin chain, ?fixtur
       distIndex: DIST_INDEX,
       apiHandler,
       maxRequestBodyBytes: 32 * 1024 * 1024,
-      webPlugins: { snapshot: () => rows, clientPath: id => byId.get(id) },
+      webPlugins: fixedRegistry(OK_GRAPH, BUNDLE_PATHS),
     }, (err) => { pageErrors.push(`server: ${String(err)}`) })
     browser = await chromium.launch()
     page = await browser.newPage()
@@ -135,8 +164,8 @@ describe('web boot chain success pass (keyless, production plugin chain, ?fixtur
   it('every plugin CSS landed with its ownership tag', async () => {
     const owners = await page.evaluate(() =>
       [...document.querySelectorAll('style[data-plugin]')].map(s => (s as HTMLElement).dataset['plugin']))
-    expect(owners).toContain('@deepseek-ai/dsh-client-ui-layout')
-    expect(owners).toContain('@deepseek-ai/dsh-client-ui-sidebar')
+    expect(owners).toContain(LAYOUT_ID)
+    expect(owners).toContain(SIDEBAR_ID)
   })
 
   it('collapsed sidebar animates to a 56px rail with the four controls', async () => {
@@ -149,25 +178,27 @@ describe('web boot chain success pass (keyless, production plugin chain, ?fixtur
     const settledTrack = async (px: string): Promise<void> => {
       await expect.poll(firstTrack, { timeout: 2000 }).toBe(px)
     }
+    // The brand wordmark is decorative svg (aria-hidden) — presence tracks the wide chrome.
+    const brand = () => page.locator('[class*="brand"]').count()
     await page.getByRole('button', { name: 'Collapse sidebar' }).click()
     // Mid-collapse the wide chrome is still mounted, fading — not swapped out.
-    expect(await page.locator('text=HARNESS').count()).toBe(1)
+    expect(await brand()).toBe(1)
     await settledTrack('56px')
-    await expect.poll(() => page.locator('text=HARNESS').count(), { timeout: 2000 }).toBe(0)
-    for (const name of ['Expand sidebar', 'New session', 'New workspace', 'Search sessions', 'Settings']) {
+    await expect.poll(brand, { timeout: 2000 }).toBe(0)
+    for (const name of ['Open sidebar', 'New session', 'New workspace', 'Search sessions', 'Settings']) {
       await expect(page.getByRole('button', { name }).isVisible(), name).resolves.toBe(true)
     }
-    await page.getByRole('button', { name: 'Expand sidebar' }).click()
-    await settledTrack('300px')
+    await page.getByRole('button', { name: 'Open sidebar' }).click()
+    await settledTrack('280px')
     await expect(page.getByRole('button', { name: 'Collapse sidebar' }).isVisible()).resolves.toBe(true)
     // Rail search: collapse again, the search control expands and lands in the box.
     await page.getByRole('button', { name: 'Collapse sidebar' }).click()
     await settledTrack('56px')
     await page.getByRole('button', { name: 'Search sessions' }).click()
-    await settledTrack('300px')
-    const focused = await page.evaluate(() =>
-      (document.activeElement as HTMLInputElement | null)?.placeholder ?? '')
-    expect(focused).toContain('Search')
+    await settledTrack('280px')
+    // Focus is deferred past the slide (EXPAND_SLIDE_MS) — poll for it.
+    await expect.poll(() => page.evaluate(() =>
+      (document.activeElement as HTMLInputElement | null)?.placeholder ?? ''), { timeout: 2000 }).toContain('Search')
   })
 
   it('renders file tool rows and expands fixture reasoning from either click target', async () => {
@@ -218,15 +249,36 @@ describe('web boot chain success pass (keyless, production plugin chain, ?fixtur
     await preview.waitFor({ state: 'detached' })
   })
 
+  it('keeps Markdown semantic while a fixture reply streams and finalizes', async () => {
+    onTestFailed(() => saveFailureShot(page, 'smoke-markdown-stream'))
+    await page.getByRole('button', { name: 'New session', exact: true }).click()
+    const input = page.locator('textarea[placeholder]')
+    await input.waitFor({ timeout: 15_000 })
+    await input.fill('render markdown')
+    await page.getByRole('button', { name: '发送' }).click()
+
+    const streaming = page.locator('[data-streaming="true"]')
+    await streaming.getByRole('heading', { name: 'Markdown fixture' }).waitFor({ timeout: 15_000 })
+    await streaming.waitFor({ state: 'detached', timeout: 15_000 })
+
+    const finalHeading = page.getByRole('heading', { name: 'Markdown fixture' })
+    expect(await finalHeading.evaluate(element => element.tagName)).toBe('H1')
+    expect(await page.locator('pre code').filter({ hasText: 'const markdown = true' }).count()).toBe(1)
+    const external = page.getByRole('link', { name: 'DeepSeek' })
+    expect(await external.getAttribute('target')).toBe('_blank')
+    expect(await external.getAttribute('rel')).toBe('noopener noreferrer')
+  })
+
   it('pastes and drops images into the composer, then sends them as durable history', async () => {
     onTestFailed(() => saveFailureShot(page, 'smoke-fixture-image-paste'))
-    await page.getByRole('button', { name: '停止' }).click()
     const textarea = page.locator('textarea')
     await textarea.waitFor({ state: 'visible' })
+    if (await page.getByRole('button', { name: '停止' }).count() > 0) {
+      await page.getByRole('button', { name: '停止' }).click()
+    }
     await expect.poll(() => textarea.isEnabled()).toBe(true)
-    await textarea.evaluate((element) => {
-      const binary = atob('iVBORw0KGgoAAAANSUhEUgAAAKAAAABaCAYAAAA/xl1SAAAAvklEQVR42u3SMQ0AAAjAMIyhELM4AAe8PD1qYFlk9cCXEAEDYkAwIAYEA2JAMCAGBANiQDAgBgQDYkAwIAYEA2JAMCAGBANiQDAgBgQDYkAwIAYEA2JAMCAGxIBCYEAMCAbEgGBADAgGxIBgQAwIBsSAYEAMCAbEgGBADAgGxIBgQAwIBsSAYEAMCAbEgGBADAgGxIAYEAyIAcGAGBAMiAHBgBgQDIgBwYAYEAyIAcGAGBAMiAHBgBgQDIgB4bYWLb6pnOb1xAAAAABJRU5ErkJggg==')
-      const bytes = Uint8Array.from(binary, character => character.charCodeAt(0))
+    await textarea.evaluate((element, png) => {
+      const bytes = Uint8Array.from(atob(png), character => character.charCodeAt(0))
       const transfer = new DataTransfer()
       transfer.items.add(new File([bytes], 'clipboard.png', { type: 'image/png' }))
       element.dispatchEvent(new ClipboardEvent('paste', {
@@ -234,12 +286,11 @@ describe('web boot chain success pass (keyless, production plugin chain, ?fixtur
         cancelable: true,
         clipboardData: transfer,
       }))
-    })
+    }, FIXTURE_PNG)
 
     const rail = page.getByLabel('待发送图片')
     await rail.waitFor({ state: 'visible' })
-    const draftImage = rail.getByTitle('双击查看原图')
-    await draftImage.dblclick()
+    await rail.getByTitle('双击查看原图').dblclick()
     const preview = page.getByRole('dialog', { name: '原图预览' })
     await preview.waitFor({ state: 'visible' })
     await page.keyboard.press('Escape')
@@ -247,38 +298,70 @@ describe('web boot chain success pass (keyless, production plugin chain, ?fixtur
 
     await page.getByRole('button', { name: '发送' }).click()
     await rail.waitFor({ state: 'detached' })
-    await expect.poll(() => page.getByTitle('双击查看原图').count()).toBeGreaterThanOrEqual(3)
+    await expect.poll(() => page.getByTitle('双击查看原图').count()).toBeGreaterThanOrEqual(1)
 
     await page.getByRole('button', { name: '停止' }).click()
     await expect.poll(() => textarea.isEnabled()).toBe(true)
-    await textarea.evaluate((element) => {
-      const binary = atob('iVBORw0KGgoAAAANSUhEUgAAAKAAAABaCAYAAAA/xl1SAAAAvklEQVR42u3SMQ0AAAjAMIyhELM4AAe8PD1qYFlk9cCXEAEDYkAwIAYEA2JAMCAGBANiQDAgBgQDYkAwIAYEA2JAMCAGBANiQDAgBgQDYkAwIAYEA2JAMCAGxIBCYEAMCAbEgGBADAgGxIBgQAwIBsSAYEAMCAbEgGBADAgGxIBgQAwIBsSAYEAMCAbEgGBADAgGxIAYEAyIAcGAGBAMiAHBgBgQDIgBwYAYEAyIAcGAGBAMiAHBgBgQDIgB4bYWLb6pnOb1xAAAAABJRU5ErkJggg==')
-      const bytes = Uint8Array.from(binary, character => character.charCodeAt(0))
+    await textarea.evaluate((element, png) => {
+      const bytes = Uint8Array.from(atob(png), character => character.charCodeAt(0))
       const transfer = new DataTransfer()
       transfer.items.add(new File([bytes], 'dropped.png', { type: 'image/png' }))
-      element.closest('[class*="card"]')?.dispatchEvent(new DragEvent('dragenter', {
+      const card = element.closest('[class*="card"]')
+      card?.dispatchEvent(new DragEvent('dragenter', {
         bubbles: true,
         cancelable: true,
         dataTransfer: transfer,
       }))
-    })
-    await page.getByRole('status').filter({ hasText: '松开以添加图片' }).waitFor({ state: 'visible' })
-    await textarea.evaluate((element) => {
-      const binary = atob('iVBORw0KGgoAAAANSUhEUgAAAKAAAABaCAYAAAA/xl1SAAAAvklEQVR42u3SMQ0AAAjAMIyhELM4AAe8PD1qYFlk9cCXEAEDYkAwIAYEA2JAMCAGBANiQDAgBgQDYkAwIAYEA2JAMCAGBANiQDAgBgQDYkAwIAYEA2JAMCAGxIBCYEAMCAbEgGBADAgGxIBgQAwIBsSAYEAMCAbEgGBADAgGxIBgQAwIBsSAYEAMCAbEgGBADAgGxIAYEAyIAcGAGBAMiAHBgBgQDIgBwYAYEAyIAcGAGBAMiAHBgBgQDIgB4bYWLb6pnOb1xAAAAABJRU5ErkJggg==')
-      const bytes = Uint8Array.from(binary, character => character.charCodeAt(0))
-      const transfer = new DataTransfer()
-      transfer.items.add(new File([bytes], 'dropped.png', { type: 'image/png' }))
-      element.closest('[class*="card"]')?.dispatchEvent(new DragEvent('drop', {
+      card?.dispatchEvent(new DragEvent('drop', {
         bubbles: true,
         cancelable: true,
         dataTransfer: transfer,
       }))
-    })
+    }, FIXTURE_PNG)
     await rail.waitFor({ state: 'visible' })
     await rail.getByAltText('dropped.png').waitFor({ state: 'visible' })
     await page.getByRole('button', { name: '发送' }).click()
     await rail.waitFor({ state: 'detached' })
-    await expect.poll(() => page.getByTitle('双击查看原图').count()).toBeGreaterThanOrEqual(4)
+    await expect.poll(() => page.getByTitle('双击查看原图').count()).toBeGreaterThanOrEqual(2)
+  })
+
+  it('renders and completes the resident question through the composer slot', async () => {
+    onTestFailed(() => saveFailureShot(page, 'smoke-question-composer'))
+    const sessionTree = page.getByRole('tree', { name: 'Sessions' })
+    const projectRow = sessionTree.getByRole('treeitem').filter({ hasText: '3 sessions' })
+    if (await projectRow.getAttribute('aria-expanded') === 'false') await projectRow.click()
+    await sessionTree.getByText('Fixture 历史会话', { exact: true }).click()
+    const composer = page.locator('[data-question-key]')
+    await composer.waitFor({ timeout: 15_000 })
+    expect({
+      question: await composer.getByRole('heading').innerText(),
+      progress: await composer.getByText('1 / 3', { exact: true }).innerText(),
+      options: await composer.getByRole('radio').allTextContents(),
+      custom: await composer.getByRole('button', { name: '其他，请填写自定义答案' }).innerText(),
+    }).toMatchInlineSnapshot(`
+      {
+        "custom": "其他，请填写自定义答案",
+        "options": [
+          "1工程落地型推荐更看重能直接做 runtime、tool executor、sandbox、trace 和线上问题排查。",
+          "2研究潜力型更看重 Agent 理解、训练评测思路和长期成长空间。",
+          "3均衡型同时要求工程能力和 Agent 认知，但可能筛选门槛更高。",
+        ],
+        "progress": "1 / 3",
+        "question": "你现在更想招哪类 Agent/Harness 候选人？",
+      }
+    `)
+
+    await composer.getByRole('radio', { name: '工程落地型' }).click()
+    await composer.getByText('2 / 3', { exact: true }).waitFor()
+    await composer.getByRole('button', { name: '跳过本题', exact: true }).click()
+    await composer.getByRole('checkbox', { name: '系统设计' }).click()
+    await composer.getByRole('checkbox', { name: 'Agent 产品判断' }).click()
+    await composer.getByRole('checkbox', { name: 'Agent 产品判断' }).press('Enter')
+
+    await composer.waitFor({ state: 'detached' })
+    const restoredInput = page.locator('textarea[placeholder]')
+    await restoredInput.waitFor()
+    expect(await restoredInput.getAttribute('placeholder')).toBe('回复生成中，可停止后再输入')
   })
 
   it('stayed clean: no page errors across the whole load chain', () => {

apps/web/tests/smoke-real.e2e.ts

@@ -77,6 +77,55 @@ async function rpc<T>(baseUrl: string, method: string, payload: unknown): Promis
   return body.result.value
 }
 
+interface HistoryPage {
+  events: { event: { type: string; data: unknown } }[]
+  hasMore: boolean
+}
+
+function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === 'object' && value !== null
+}
+
+function providerTitle(page: HistoryPage): string | undefined {
+  for (let index = page.events.length - 1; index >= 0; index--) {
+    const event = page.events[index]!.event
+    if (event.type !== 'session/title' || !isRecord(event.data)) continue
+    const source = event.data.source
+    if (typeof event.data.title === 'string' && isRecord(source) && source.kind === 'provider') {
+      return event.data.title
+    }
+  }
+  return undefined
+}
+
+function hasAssistantMarker(page: HistoryPage, marker: string): boolean {
+  return page.events.some(({ event }) => {
+    if (event.type !== 'assistant/message' || !isRecord(event.data) || !Array.isArray(event.data.content)) return false
+    return event.data.content.some(block =>
+      isRecord(block) && block.type === 'text' && typeof block.text === 'string' && block.text.includes(marker))
+  })
+}
+
+async function history(baseUrl: string, sessionId: string): Promise<HistoryPage> {
+  return rpc<HistoryPage>(baseUrl, 'session.history', { sessionId, maxMessages: 10 })
+}
+
+async function waitForProviderTitle(baseUrl: string, sessionId: string): Promise<string> {
+  let observed: string | undefined
+  await expect.poll(async () => {
+    observed = providerTitle(await history(baseUrl, sessionId))
+    return observed
+  }, { timeout: 90_000 }).toEqual(expect.any(String))
+  if (observed === undefined) throw new Error('provider-backed session title was not observed')
+  return observed
+}
+
+async function waitForAssistantMarker(baseUrl: string, sessionId: string, marker: string): Promise<void> {
+  await expect.poll(async () => hasAssistantMarker(await history(baseUrl, sessionId), marker), {
+    timeout: 120_000,
+  }).toBe(true)
+}
+
 /** W5 screenshot: evidence for the figma comparison, not a failure artifact. */
 async function screen(page: Page, name: string): Promise<void> {
   await page.screenshot({ path: join(REPO_ROOT, '.artifacts', `w5-${name}.png`) })
@@ -95,10 +144,11 @@ async function detailsTrack(page: Page): Promise<number> {
   return Number(cols.split(' ').pop()!.replace('px', ''))
 }
 
-// Readiness gate: `dsh web` serves ALL eight manifest plugins; until every UI
+// Readiness gate: `dsh web` serves ALL nine manifest plugins; until every UI
 // plugin's client bundle exists and exports apply, the loader fail-louds and
 // the frame never appears.
-const UI_PLUGIN_DIRS = ['connection', 'runtime', 'ui-theme', 'i18n', 'ui-layout', 'ui-sidebar', 'ui-conversation', 'ui-trajectory']
+const UI_PLUGIN_DIRS = ['connection', 'runtime', 'ui-theme', 'i18n', 'ui-layout', 'ui-sidebar', 'ui-conversation', 'ui-question', 'ui-trajectory']
+const ROUND_DONE_MARKER = 'WEB_ROUND_DONE'
 const notReady = UI_PLUGIN_DIRS.filter((dir) => {
   const bundle = join(REPO_ROOT, 'packages/client', dir, 'lib/client.js')
   return !existsSync(bundle) || !readFileSync(bundle, 'utf8').includes('exports.apply')
@@ -280,7 +330,8 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke
     const input = page.locator('textarea').first()
     await input.waitFor({ timeout: 10_000 })
     await screen(page, '02-empty-state')
-    await input.fill('请简单介绍事件溯源，两句话即可，最后以「介绍完毕」结尾')
+    const prompt = `Please answer this request carefully: explain event sourcing in two sentences, ending with exactly ${ROUND_DONE_MARKER}.`
+    await input.fill(prompt)
     await input.press('Enter')
     // startSession chain: session mounts, composer moves to the bottom.
     // Regression pin (P0, 585671106): this send used to white-screen the tree
@@ -288,7 +339,32 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke
     // near-empty here means that class of bug is back.
     await page.waitForFunction(() => document.body.innerText.length > 50, undefined, { timeout: 15_000 })
     expect(pageErrors).toEqual([])
-    await page.waitForFunction(() => document.body.innerText.includes('介绍完毕'), undefined, { timeout: 120_000 })
+    await page.waitForFunction(
+      () => document.title !== 'DeepSeek Harness' && document.title.endsWith(' — DeepSeek Harness'),
+      undefined,
+      { timeout: 15_000 },
+    )
+    await expect.poll(async () => (await rpc<{ items: { sessionId: string }[] }>(baseUrl, 'session.list', {})).items.length, {
+      timeout: 15_000,
+    }).toBe(1)
+    const sessions = await rpc<{ items: { sessionId: string }[] }>(baseUrl, 'session.list', {})
+    const sessionId = sessions.items[0]?.sessionId
+    if (sessionId === undefined) throw new Error('created Web session was not listed')
+    const durableTitle = await waitForProviderTitle(baseUrl, sessionId)
+    await page.waitForFunction(
+      expected => document.title === `${expected} — DeepSeek Harness`,
+      durableTitle,
+      { timeout: 15_000 },
+    )
+    const sessionTree = page.getByRole('tree', { name: 'Sessions' })
+    const projectRow = sessionTree.getByRole('treeitem').first()
+    if (await projectRow.getAttribute('aria-expanded') === 'false') await projectRow.click()
+    await Promise.all([
+      sessionTree.getByText(durableTitle, { exact: true }).waitFor({ timeout: 10_000 }),
+      page.getByRole('navigation').getByText(durableTitle, { exact: true }).waitFor({ timeout: 10_000 }),
+    ])
+    await waitForAssistantMarker(baseUrl, sessionId, ROUND_DONE_MARKER)
+    await page.locator('p').filter({ hasText: ROUND_DONE_MARKER }).waitFor({ timeout: 10_000 })
     await screen(page, '04-round-complete')
   }, 150_000)
 
@@ -308,10 +384,10 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke
     await input.fill('请用 bash 工具运行命令 echo w5marker 然后告诉我结果')
     await input.press('Enter')
     // Wait for the tool ROW, not response text (the reply echoes any marker).
-    // bash renders through the third-party sample registration (data-sample) —
-    // that IS the differential-rendering acceptance; the generic path renders
-    // data-variant rows with the handler on the data-clickable inner row.
-    const toolRow = page.locator('[data-sample], [data-variant] [data-clickable]').first()
+    // Bash renders through the third-party sample registration. Match that
+    // exact row: other clickable variants (for example Think disclosure)
+    // may precede the tool call in document order.
+    const toolRow = page.locator('[data-sample="bash-global"]')
     await toolRow.waitFor({ timeout: 120_000 })
     await screen(page, '08-bash-round')
     expect(await detailsTrack(page)).toBe(0)
@@ -363,7 +439,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke
     onTestFailed(() => saveFailureShot(page, 'w5-reload'))
     await page.reload({ waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
-    await page.waitForFunction(() => document.body.innerText.includes('介绍完毕'), undefined, { timeout: 30_000 })
+    await page.locator('p').filter({ hasText: ROUND_DONE_MARKER }).waitFor({ timeout: 30_000 })
     await screen(page, '12-reload-recovery')
   })
 

apps/web/tests/snapshots/session-title.json

@@ -0,0 +1,12 @@
+{
+  "initial": {
+    "sidebar": "Fixture 历史会话",
+    "breadcrumb": "Fixture 历史会话",
+    "documentTitle": "Fixture 历史会话 — DeepSeek Harness"
+  },
+  "revised": {
+    "sidebar": "Fixture 修订标题",
+    "breadcrumb": "Fixture 修订标题",
+    "documentTitle": "Fixture 修订标题 — DeepSeek Harness"
+  }
+}

apps/web/tsconfig.json

@@ -9,14 +9,23 @@
       "DOM",
       "DOM.Iterable"
     ],
-    "types": ["node"]
+    "types": [
+      "node"
+    ]
   },
   "include": [
     "src",
     "tests"
   ],
   "references": [
-    { "path": "../../packages/client/web" },
-    { "path": "../../packages/host/webserver" }
+    {
+      "path": "../../packages/client/web"
+    },
+    {
+      "path": "../../packages/host/webserver"
+    },
+    {
+      "path": "../../packages/client/modules"
+    }
   ]
 }

apps/web/vite.config.ts

@@ -10,17 +10,28 @@ export default defineConfig({
     // Workspace packages resolve to SOURCE: package.json exports point at lib
     // for Node/type consumers, but the browser bundle must compile src directly
     // so CSS rides vite's pipeline instead of the CSS-externalized lib bundle.
-    // Only the shell's static surface is aliased — UI plugin packages are NOT
-    // bundled here; they arrive as dynamic bundles through the client loader.
-    // Order matters — subpath aliases must win over bare-name prefixes.
+    // Only the shell's normal-package surface is aliased — plugin packages are
+    // NEVER bundled here (web2 shell self-sufficiency); they arrive as runtime
+    // bundles through the client module system. Order matters — subpath
+    // aliases must win over bare-name prefixes.
     alias: [
+      // Browserization of the vendored cordis Loader: its only node-only
+      // import; the two process probes are mapped by `define` below.
+      { find: /^node:module$/, replacement: src('./src/node-module-stub.ts') },
       { find: /^@deepseek-ai\/dsh-client-web$/, replacement: src('../../packages/client/web/src/boot.tsx') },
-      { find: /^@deepseek-ai\/dsh-client-web-react\/store$/, replacement: src('../../packages/client/web-react/src/store/index.ts') },
       { find: /^@deepseek-ai\/dsh-client-web-react$/, replacement: src('../../packages/client/web-react/src/index.ts') },
       { find: /^@deepseek-ai\/dsh-client-ui-slots$/, replacement: src('../../packages/client/ui-slots/src/index.ts') },
       { find: /^@deepseek-ai\/dsh-client-ui-primitives$/, replacement: src('../../packages/client/ui-primitives/src/index.ts') },
-      { find: /^@deepseek-ai\/dsh-client-runtime\/loader$/, replacement: src('../../packages/client/runtime/src/client/loader/index.ts') },
-      { find: /^@deepseek-ai\/dsh-client-runtime$/, replacement: src('../../packages/client/runtime/src/index.ts') },
+      { find: /^@deepseek-ai\/dsh-client-modules$/, replacement: src('../../packages/client/modules/src/index.ts') },
     ],
   },
+  define: {
+    // vendored loader internal.ts: fromInternal() probes the Node major —
+    // "0.0.0" takes neither branch, returning undefined (exactly the empty
+    // internal slot the shell boot fills with the client module loader).
+    'process.versions.node': '"0.0.0"',
+    'process.execArgv': '[]',
+    // vendored loader index.ts: envData falls to its default branch.
+    'process.env.CORDIS_SHARED': 'undefined',
+  },
 })

bin/dsh

@@ -2,7 +2,6 @@
 # dsh launcher: runs the apps/cli `dsh` bin FROM SOURCE with this checkout's
 # tsx, so a symlink from anywhere (e.g. ~/.local/bin/dsh) always executes the
 # current working tree — code changes apply on the next launch, no build step.
-# --expose-internals: the shipped config mounts HMR, which needs Loader internals.
 set -eu
 
 # Resolve symlink chains without readlink -f (not on every macOS).
@@ -19,4 +18,4 @@ root=$(CDPATH='' cd -- "$(dirname -- "$script")/.." && pwd)
 # tsx is imported by absolute path because bare `--import tsx` resolves from
 # the invoking cwd, which is usually outside this repository.
 export TSX_TSCONFIG_PATH="$root/tsconfig.json"
-exec node --expose-internals --import "$root/node_modules/tsx/dist/loader.mjs" "$root/apps/cli/src/bin.ts" "$@"
+exec node --import "$root/node_modules/tsx/dist/loader.mjs" "$root/apps/cli/src/bin.ts" "$@"

docs/architecture.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
-architecture.md: 5e10d39f0b3b0236a0a7e58dfd928d9bfba59e46
-architecture.zh.md: 6f4a9b37da693f3b65d4868719b3b468c8eeb330
+architecture.md: 94b8fe18ccb326cf1f60fca03fafe913d5148995
+architecture.zh.md: 800612ae5edbc205e3d6377a4c3ec1ee5c41c40a

docs/architecture.md

@@ -42,10 +42,10 @@ Harnesses are [Cordis](cordis-primer.md) contexts whose packages contribute serv
 | `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.goals` | [`goal/`](../packages/goal/README.md) | persisted same-session goals |
-| `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 exact reads and relationship traces |
-| `ctx.sessionTitle` | [`session-title/`](../packages/session-title/README.md) | log-backed fallback titles and one optional asynchronous provider |
-| `ctx.invariants` | [`support/invariants`](../packages/support/invariants/README.md) | registry and package-name selection for package-owned runtime checks |
+| `ctx.sessionPersistence` | [`session-persistence/`](../packages/session-persistence/README.md) | durable session-log storage |
+| `ctx.sessionQuery` | [`session-query/`](../packages/session-query/README.md) | `session-query` interface: concrete live-preferred exact/filter/trace; exactly two abstract FTS methods via `session-query-sqlite` |
+| `ctx.sessionTitle` | [`session-title/`](../packages/session-title/README.md) | log-backed fallbacks plus one optional asynchronous provider |
+| `ctx.invariants` | [`support/invariants`](../packages/support/invariants/README.md) | package-name-selected registry for package-owned runtime checks |
 
 ## Event
 

docs/architecture.zh.md

@@ -42,10 +42,10 @@
 | `ctx.tasks` | [`tasks/`](../packages/tasks/README.md) | 后台任务注册表和通用 `task_*` 控制工具 |
 | `ctx.workflows` | [`workflow/`](../packages/workflow/README.md) | 脚本驱动的多 agent 编排 |
 | `ctx.goals` | [`goal/`](../packages/goal/README.md) | 持久化的同会话目标 |
-| `ctx.sessionPersistence` | [`session-persistence/`](../packages/session-persistence/README.md) | 会话日志的持久存储 |
-| `ctx.sessionQuery` | [`session-query/`](../packages/session-query/README.md) | 实时优先的逻辑语料精确读取和关系追踪 |
-| `ctx.sessionTitle` | [`session-title/`](../packages/session-title/README.md) | 基于日志的回退标题和单个可选异步提供方 |
-| `ctx.invariants` | [`support/invariants`](../packages/support/invariants/README.md) | 按包名选择包自有运行时检查的注册表 |
+| `ctx.sessionPersistence` | [`session-persistence/`](../packages/session-persistence/README.md) | 会话日志的持久化存储 |
+| `ctx.sessionQuery` | [`session-query/`](../packages/session-query/README.md) | `session-query` 接口：精确检索、过滤与追踪采用实时优先的具体实现；恰有两个全文搜索方法为抽象方法，由 `session-query-sqlite` 实现 |
+| `ctx.sessionTitle` | [`session-title/`](../packages/session-title/README.md) | 基于日志的回退标题，以及单个可选的异步提供方 |
+| `ctx.invariants` | [`support/invariants`](../packages/support/invariants/README.md) | 按包名筛选包自有运行时检查的注册表 |
 
 ## 事件
 

docs/capability-seams.md

@@ -28,6 +28,7 @@ flowchart LR
   pkg_cli_demo["cli-demo"]
   pkg_session_persistence["session-persistence"]
   pkg_session_query["session-query"]
+  pkg_session_query_sqlite["session-query-sqlite"]
   pkg_subagent_inprocess["subagent-inprocess"]
   pkg_invariants["invariants"]
   svc_invariants["ctx.invariants<br/>Package-owned invariant registry"]
@@ -39,7 +40,7 @@ flowchart LR
   pkg_hooks_claude["hooks-claude"]
   pkg_hooks_codex["hooks-codex"]
   pkg_acp["acp"]
-  svc_sessionQuery["ctx.sessionQuery<br/>Exact session-history reads and traces"]
+  svc_sessionQuery["ctx.sessionQuery<br/>Session reads, traces, filters, and search"]
   pkg_session_reference["session-reference"]
   svc_sessionReferences["ctx.sessionReferences<br/>Cross-session snapshot preparation"]
   pkg_tui["tui"]
@@ -162,6 +163,7 @@ flowchart LR
   pkg_session_persistence_jsonl --> svc_sessionPersistence
   pkg_session_persistence_sqlite --> svc_sessionPersistence
   pkg_session_query --> svc_sessionQuery
+  pkg_session_query_sqlite --> svc_sessionQuery
   pkg_session_reference --> svc_sessionReferences
   pkg_session_title --> svc_sessionTitle
   pkg_session_title_all_messages_llm --> svc_sessionTitle
@@ -226,6 +228,7 @@ flowchart LR
   svc_sessionPersistence --> pkg_hooks_claude
   svc_sessionPersistence --> pkg_hooks_codex
   svc_sessionPersistence --> pkg_session_query
+  svc_sessionPersistence --> pkg_session_query_sqlite
   svc_sessionPersistence --> pkg_tool_bash
   svc_sessionQuery --> pkg_session_reference
   svc_sessionReferences --> pkg_acp
@@ -233,8 +236,10 @@ flowchart LR
   svc_sessions --> pkg_agent
   svc_sessions --> pkg_agent_loop
   svc_sessions --> pkg_cli_demo
+  svc_sessions --> pkg_invariants
   svc_sessions --> pkg_session_persistence
   svc_sessions --> pkg_session_query
+  svc_sessions --> pkg_session_query_sqlite
   svc_sessions --> pkg_subagent_inprocess
   svc_skills --> pkg_tool_skill
   svc_spillStore --> pkg_spill_policy
@@ -277,10 +282,10 @@ flowchart LR
 | `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.toolResultPrune` | `core` | [`compact-tool-result-prune`](../packages/compact/compact-tool-result-prune) | - | [`compact-basic`](../packages/compact/compact-basic) | - | Rewrites oversized current tool results through replayable single-node surface replacements before summary compaction. |
-| `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`cli-demo`](../packages/examples/cli-demo), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | - | Owns append-only Session instances and emits the durable session event feed. |
+| `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`cli-demo`](../packages/examples/cli-demo), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`session-query-sqlite`](../packages/session-query/session-query-sqlite), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. |
 | `ctx.invariants` | `core` | [`invariants`](../packages/support/invariants) | - | [`session`](../packages/core/session), [`agent`](../packages/core/agent), [`scope`](../packages/core/scope), [`agent-loop`](../packages/core/agent-loop) | - | Companion subpaths register owner-local checks; the service owns selection, uniqueness, child fibers, and package-attributed failures. |
-| `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) | - | [`session-reference`](../packages/context/session-reference) | - | Resolves live and optional persisted logs into one logical corpus for exact reads and relationship traces. |
+| `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), [`session-query-sqlite`](../packages/session-query/session-query-sqlite) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. |
+| `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | [`session-query-sqlite`](../packages/session-query/session-query-sqlite) | [`session-reference`](../packages/context/session-reference) | - | The interface supplies exact reads, filters, and traces; its concrete backend adds full-text reconciliation, ranking, snippets, and cursor generations on the same service. |
 | `ctx.sessionReferences` | `core` | [`session-reference`](../packages/context/session-reference) | - | [`tui`](../packages/ui/tui), [`acp`](../packages/ui/acp) | - | Projects bounded current-surface conversation snapshots into durable untrusted message context; host adapters own mention syntax. |
 | `ctx.sessionTitle` | `seam` | [`session-title`](../packages/session-title/session-title) | [`session-title-first-message-llm`](../packages/session-title/session-title-first-message-llm), [`session-title-all-messages-llm`](../packages/session-title/session-title-all-messages-llm) | - | - | Owns the deterministic fallback, latest-title fold, and sole optional asynchronous provider registration. |
 | `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-pty`](../packages/pty/tool-pty), [`tool-web`](../packages/web/tool-web) | - | Collects prompt sections and model-facing tool schemas for each step. |

docs/config-catalog.md

@@ -58,7 +58,7 @@ export interface Config {
   dshHome?: string
   /** Fallback session-title limits forwarded through agent-spine-demo. */
   sessionTitle?: NonNullable<agentCore.Config['sessionTitle']>
-  /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */
+  /** Directory for JSONL sessions and the derived query index. Defaults to `./.sessions`. */
   persistenceRoot?: string
   /** Write delta-chunk runs as packed storage rows (the JSONL backend's `packChunks`). Defaults to `false`. */
   packChunks?: boolean
@@ -83,7 +83,7 @@ export interface Config {
 
 Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`JsonlCompression`](../packages/session-persistence/session-persistence-jsonl/src/index.ts) · [`SessionReferenceConfig`](#deepseek-aidsh-session-reference) · [`ToolsConfig`](#deepseek-aidsh-tools)
 
-Source: [`packages/examples/acp-demo/src/index.ts:43`](../packages/examples/acp-demo/src/index.ts)
+Source: [`packages/examples/acp-demo/src/index.ts:44`](../packages/examples/acp-demo/src/index.ts)
 
 ## `@deepseek-ai/dsh-agent-loop`
 
@@ -552,6 +552,8 @@ export interface Config {
   thinking?: 'enabled' | 'disabled'
   /** Thinking effort (only meaningful with thinking enabled). */
   reasoningEffort?: 'high' | 'max'
+  /** Positive context capacity used when the selected model has no exact value. */
+  defaultContextWindow?: number
   /** Advisory models shown by discovery consumers; defaults to V4 Flash and V4 Pro. */
   models?: DeepSeekCatalogModel[]
   /** Maximum provider idle time while one stream read is outstanding (default five minutes). */
@@ -818,7 +820,7 @@ export interface PlanModeConfig {
 }
 ```
 
-Source: [`packages/plan/plan-mode/src/index.ts:57`](../packages/plan/plan-mode/src/index.ts)
+Source: [`packages/plan/plan-mode/src/index.ts:58`](../packages/plan/plan-mode/src/index.ts)
 
 ## `@deepseek-ai/dsh-pty-local`
 
@@ -953,7 +955,9 @@ export interface Config {
   /**
    * Root directory for all session files. Required (no default): a default of
    * `process.cwd()` would scatter session files as the process's cwd changes
-   * (bash calls, subprocesses). Sessions group under per-cwd subdirectories.
+   * (bash calls, subprocesses). Sessions group under per-cwd subdirectories. An
+   * existing root must be a readable directory; an absent root is created on
+   * first materialization.
    */
   root: string
   /**
@@ -973,7 +977,7 @@ export interface Config {
 export type JsonlCompression = 'zstd' | 'none'
 ```
 
-Source: [`packages/session-persistence/session-persistence-jsonl/src/index.ts:37`](../packages/session-persistence/session-persistence-jsonl/src/index.ts)
+Source: [`packages/session-persistence/session-persistence-jsonl/src/index.ts:39`](../packages/session-persistence/session-persistence-jsonl/src/index.ts)
 
 ## `@deepseek-ai/dsh-session-persistence-sqlite`
 
@@ -1012,21 +1016,38 @@ export interface Config {
 export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist'
 ```
 
-Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:55`](../packages/session-persistence/session-persistence-sqlite/src/index.ts)
+Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:58`](../packages/session-persistence/session-persistence-sqlite/src/index.ts)
 
-## `@deepseek-ai/dsh-session-query`
+## `@deepseek-ai/dsh-session-query-sqlite`
 
 Requires: `sessions`
 
 ```ts config-catalog
-/** Configuration for exact session-query reads and traces. */
-export interface Config {
-  /** Maximum accepted raw read context on either side. Defaults to 50. */
-  readWindowMax?: number
+/** Combined session-query configuration backed by SQLite full-text search. */
+export interface Config extends SessionQueryConfig {
+  /**
+   * Dedicated derived-index path; `:memory:` is supported for tests. Missing
+   * directories and database files are created owner-only on POSIX filesystems;
+   * existing modes are preserved.
+   */
+  path: string
+  /** SQLite journal mode. Defaults to `wal`. */
+  journalMode?: JournalMode
+  /** Page size when a request omits `limit`. At most `Number.MAX_SAFE_INTEGER - 1`; defaults to 20. */
+  defaultLimit?: number
+  /** Largest accepted page size. At most `Number.MAX_SAFE_INTEGER - 1`; defaults to 100. */
+  maxLimit?: number
+  /** Maximum snippet length in Unicode code points. Defaults to 240. */
+  snippetChars?: number
 }
+
+/** Supported SQLite journal modes. */
+export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist'
 ```
 
-Source: [`packages/session-query/session-query/src/config.ts:9`](../packages/session-query/session-query/src/config.ts)
+Depends on: [`SessionQueryConfig`](../packages/session-query/session-query/src/index.ts)
+
+Source: [`packages/session-query/session-query-sqlite/src/index.ts:74`](../packages/session-query/session-query-sqlite/src/index.ts)
 
 ## `@deepseek-ai/dsh-session-reference`
 
@@ -1386,6 +1407,22 @@ export interface Config {
 
 Source: [`packages/lsp/tool-lsp/src/index.ts:58`](../packages/lsp/tool-lsp/src/index.ts)
 
+## `@deepseek-ai/dsh-tool-pty`
+
+Requires: `pty` · `tools` · `systemPrompt`
+
+```ts config-catalog
+/** Model-facing terminal tool configuration. */
+export interface Config {
+  /** Expose `run_in_background` and accept background sends (default true). */
+  enableRunInBackground?: boolean
+  /** Maximum UTF-8 bytes in one complete terminal or task-output result. */
+  maxResultBytes?: number
+}
+```
+
+Source: [`packages/pty/tool-pty/src/index.ts:35`](../packages/pty/tool-pty/src/index.ts)
+
 ## `@deepseek-ai/dsh-tool-ralph`
 
 Requires: `tools` · `workflows` · `subagents` · `systemPrompt`
@@ -1490,7 +1527,7 @@ export interface Config {
 }
 ```
 
-Source: [`packages/tasks/tool-tasks/src/index.ts:21`](../packages/tasks/tool-tasks/src/index.ts)
+Source: [`packages/tasks/tool-tasks/src/index.ts:23`](../packages/tasks/tool-tasks/src/index.ts)
 
 ## `@deepseek-ai/dsh-tool-web`
 
@@ -1550,7 +1587,7 @@ export interface Config {
 export type ToolPresentationMode = 'native' | 'code' | 'both'
 ```
 
-Source: [`packages/core/tools/src/index.ts:517`](../packages/core/tools/src/index.ts)
+Source: [`packages/core/tools/src/index.ts:529`](../packages/core/tools/src/index.ts)
 
 ## `@deepseek-ai/dsh-tui`
 
@@ -1573,7 +1610,7 @@ export interface Config extends TuiConfig {
   resumeCommand?: string
 }
 
-/** Presentation settings for the pi-tui terminal mode. */
+/** Interaction and presentation settings for the pi-tui terminal mode. */
 export interface TuiConfig {
   /** Render model reasoning blocks. */
   showReasoning?: boolean
@@ -1591,6 +1628,12 @@ export interface TuiConfig {
   modelDialogWidth?: number
   /** Model-selector maximum height in terminal rows. */
   modelDialogMaxHeight?: number
+  /** Maximum fuzzy file candidates displayed for one `@` query. */
+  fileSearchMaxResults?: number
+  /** Maximum paths retained in one `@` workspace index. */
+  fileSearchMaxEntries?: number
+  /** Directory basenames excluded from `@` traversal and completion. */
+  fileSearchExcludedDirectories?: string[]
   /** Show the terminal's hardware cursor at the pi editor's IME marker. */
   showHardwareCursor?: boolean
   /** Apply the built-in ANSI color palette. */
@@ -1607,7 +1650,7 @@ export interface TuiConfig {
 }
 ```
 
-Source: [`packages/ui/tui/src/index.ts:217`](../packages/ui/tui/src/index.ts)
+Source: [`packages/ui/tui/src/index.ts:248`](../packages/ui/tui/src/index.ts)
 
 ## `@deepseek-ai/dsh-tui-demo`
 
@@ -1630,7 +1673,7 @@ export interface Config {
   dshHome?: string
   /** Fallback session-title limits forwarded through agent-spine-demo. */
   sessionTitle?: NonNullable<agentCore.Config['sessionTitle']>
-  /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */
+  /** Directory for JSONL sessions and the derived query index. Defaults to `./.sessions`. */
   persistenceRoot?: string
   /** JSONL artifact encoding; defaults to checksummed Zstandard frames. */
   persistenceCompression?: JsonlCompression
@@ -1664,7 +1707,7 @@ export interface Config {
 
 Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`JsonlCompression`](../packages/session-persistence/session-persistence-jsonl/src/index.ts) · [`SessionReferenceConfig`](#deepseek-aidsh-session-reference) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`uiTui`](../packages/ui/tui/src/index.ts)
 
-Source: [`packages/examples/tui-demo/src/index.ts:38`](../packages/examples/tui-demo/src/index.ts)
+Source: [`packages/examples/tui-demo/src/index.ts:39`](../packages/examples/tui-demo/src/index.ts)
 
 ## `@deepseek-ai/dsh-user-approval`
 
@@ -1870,10 +1913,12 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co
 
 - `@deepseek-ai/dsh-agent` ([`packages/core/agent/src/index.ts`](../packages/core/agent/src/index.ts))
 - `@deepseek-ai/dsh-client-connection` ([`packages/client/connection/src/index.ts`](../packages/client/connection/src/index.ts))
+- `@deepseek-ai/dsh-client-hmr` ([`packages/client/hmr/src/index.ts`](../packages/client/hmr/src/index.ts))
 - `@deepseek-ai/dsh-client-i18n` ([`packages/client/i18n/src/index.ts`](../packages/client/i18n/src/index.ts))
 - `@deepseek-ai/dsh-client-runtime` ([`packages/client/runtime/src/index.ts`](../packages/client/runtime/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-conversation` ([`packages/client/ui-conversation/src/index.ts`](../packages/client/ui-conversation/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-layout` ([`packages/client/ui-layout/src/index.ts`](../packages/client/ui-layout/src/index.ts))
+- `@deepseek-ai/dsh-client-ui-question` — requires `tools` · `userInteraction` ([`packages/client/ui-question/src/index.ts`](../packages/client/ui-question/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-sidebar` ([`packages/client/ui-sidebar/src/index.ts`](../packages/client/ui-sidebar/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-theme` ([`packages/client/ui-theme/src/index.ts`](../packages/client/ui-theme/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-trajectory` ([`packages/client/ui-trajectory/src/index.ts`](../packages/client/ui-trajectory/src/index.ts))
@@ -1890,7 +1935,6 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co
 - `@deepseek-ai/dsh-tasks` ([`packages/tasks/tasks/src/index.ts`](../packages/tasks/tasks/src/index.ts))
 - `@deepseek-ai/dsh-timeout-policy` — requires `tools` ([`packages/timeout/timeout-policy/src/index.ts`](../packages/timeout/timeout-policy/src/index.ts))
 - `@deepseek-ai/dsh-tool-ask-user` — requires `tools` · `userInteraction` ([`packages/ui/tool-ask-user/src/index.ts`](../packages/ui/tool-ask-user/src/index.ts))
-- `@deepseek-ai/dsh-tool-pty` — requires `pty` · `tools` · `systemPrompt` ([`packages/pty/tool-pty/src/index.ts`](../packages/pty/tool-pty/src/index.ts))
 - `@deepseek-ai/dsh-tool-todo` — requires `tools` ([`packages/todo/tool-todo/src/index.ts`](../packages/todo/tool-todo/src/index.ts))
 - `@deepseek-ai/dsh-user-interaction` ([`packages/ui/user-interaction/src/index.ts`](../packages/ui/user-interaction/src/index.ts))
 
@@ -1905,6 +1949,7 @@ 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-session-query` — abstract `SessionQueryService` ([`packages/session-query/session-query/src/index.ts`](../packages/session-query/session-query/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))
 
@@ -1917,6 +1962,7 @@ Imported as libraries by other packages; a `cordis.yml` cannot load them.
 - `@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-client-modules` ([`packages/client/modules/src/index.ts`](../packages/client/modules/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-primitives` ([`packages/client/ui-primitives/src/index.ts`](../packages/client/ui-primitives/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-slots` ([`packages/client/ui-slots/src/index.ts`](../packages/client/ui-slots/src/index.ts))
 - `@deepseek-ai/dsh-client-web` ([`packages/client/web/src/index.ts`](../packages/client/web/src/index.ts))

docs/cookbook/extension-cookbook.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
-extension-cookbook.md: 8873cac21960e2e2efe0e8c6c5868c3a8e7ee75c
-extension-cookbook.zh.md: f34e9f2fa707be69b13ac408cc1ede1a86310fae
+extension-cookbook.md: 056be4298ed2bec2b78ed777d58f1f8a60a34b78
+extension-cookbook.zh.md: 41cdd4a7d14f32494d1dd5ae4a63c098d5640bdc

docs/cookbook/extension-cookbook.md

@@ -113,7 +113,7 @@ Every product feature maps to a listener on a documented extension seam — the
 | Monotonic terminal turn policy | return `{ action: 'stop' }` from serial `agent/turn-stop`, after continuation and steering have already been folded |
 | Subprocess sandbox (landlock / sandbox-exec) | use a `ctx.sandbox` backend through `dsh-bash-sandbox`; use `tools/pre-execute` for capability-level denial |
 | Permission system / AskUserQuestion | return `ask` from `tools/pre-execute` and answer through `ctx.approval`; register a separate model-facing ask tool for ordinary user questions |
-| Plan mode | Shipped: [`@deepseek-ai/dsh-plan-mode`](../../packages/plan/plan-mode/README.md) — logged `plan/mode` state, the `plan:policy` guidance section, `/plan [message]`, and the user-reviewed `exit_plan_mode` exit; enforcement stays on the independent sandbox/approval axes |
+| Plan mode | Shipped: [`@deepseek-ai/dsh-plan-mode`](../../packages/plan/plan-mode/README.md) — logged `plan/mode` state, the `plan:policy` guidance section, `/plan [message]` entry, `/plan off` direct exit, and the user-reviewed `exit_plan_mode` exit; enforcement stays on the independent sandbox/approval axes |
 | Sub-agent delegation | the `ctx.subagents` provider registry (`dsh-subagent-spawn`/`-fork`/`-acp`) + `dsh-tool-subagent` exposing one configured provider to the model |
 | MCP | one plugin per server: discover tools → `ctx.tools.register()` |
 | Skills | section + tool registration; `inject()` skill content on invocation |

docs/cookbook/extension-cookbook.zh.md

@@ -113,7 +113,7 @@ export function apply(ctx: Context) {
 | 单调终端轮次策略 | 从串行 `agent/turn-stop` 返回 `{ action: 'stop' }`，此时 continuation 和 steering 已折叠完毕 |
 | 子进程沙箱（landlock / sandbox-exec） | 通过 `dsh-bash-sandbox` 使用 `ctx.sandbox` 后端；能力级别的拒绝使用 `tools/pre-execute` |
 | 权限系统 / AskUserQuestion | 从 `tools/pre-execute` 返回 `ask` 并通过 `ctx.approval` 应答；为普通用户提问注册一个独立的面向模型的 ask 工具 |
-| Plan mode | 已交付：[`@deepseek-ai/dsh-plan-mode`](../../packages/plan/plan-mode/README.md) — 落日志的 `plan/mode` 状态、`plan:policy` 引导段、`/plan [message]`，以及经用户评审的 `exit_plan_mode` 出口；强制约束留在独立的沙箱/审批轴上 |
+| Plan mode | 已交付：[`@deepseek-ai/dsh-plan-mode`](../../packages/plan/plan-mode/README.md) — 落日志的 `plan/mode` 状态、`plan:policy` 引导段、`/plan [message]` 入口、`/plan off` 直接退出，以及经用户评审的 `exit_plan_mode` 出口；强制约束留在独立的沙箱/审批轴上 |
 | 子 agent 委派 | `ctx.subagents` 提供方注册表（`dsh-subagent-spawn`/`-fork`/`-acp`）+ `dsh-tool-subagent` 向模型暴露一个已配置的提供方 |
 | MCP | 每个服务器一个插件：发现工具 → `ctx.tools.register()` |
 | Skill（技能） | section + 工具注册；调用时通过 `inject()` 注入 skill 内容 |

docs/cordis-catalog/services.md

@@ -783,7 +783,7 @@ set(agent: Agent, active: boolean): void
 
 Types: [Agent](../core-data-structures/core.md)
 
-Source: [`packages/plan/plan-mode/src/index.ts:141`](../../packages/plan/plan-mode/src/index.ts)
+Source: [`packages/plan/plan-mode/src/index.ts:142`](../../packages/plan/plan-mode/src/index.ts)
 
 ## `ctx.pty` — `PtyService`
 
@@ -812,6 +812,13 @@ listBackends(): string[]
  */
 async spawn(owner: Agent, request: PtySpawnRequest, signal?: AbortSignal): Promise<PtySpawnResult>
 
+/**
+ * Test whether an exact owner has a published session or unpublished spawn.
+ * @param owner - exact live owner to inspect.
+ * @returns true across the entire spawn-to-close interval, with no publication gap.
+ */
+hasOwnerActivity(owner: Agent): boolean
+
 /**
  * Start one exclusive interactive send.
  * @param owner - exact session owner.
@@ -858,7 +865,7 @@ list(owner: Agent): PtySessionSnapshot[]
 
 Types: [Agent](../core-data-structures/core.md) · [PtyBackend](../core-data-structures/pty.md) · [PtyReadRequest](../core-data-structures/pty.md) · [PtyReadResult](../core-data-structures/pty.md) · [PtySendOperation](../core-data-structures/pty.md) · [PtySendRequest](../core-data-structures/pty.md) · [PtySessionId](../core-data-structures/pty.md) · [PtySessionSnapshot](../core-data-structures/pty.md) · [PtySignal](../core-data-structures/pty.md) · [PtySignalResult](../core-data-structures/pty.md) · [PtySpawnRequest](../core-data-structures/pty.md) · [PtySpawnResult](../core-data-structures/pty.md)
 
-Source: [`packages/pty/pty/src/index.ts:95`](../../packages/pty/pty/src/index.ts)
+Source: [`packages/pty/pty/src/index.ts:105`](../../packages/pty/pty/src/index.ts)
 
 ## `ctx.sandbox` — `SandboxProvider` (abstract seam)
 
@@ -928,10 +935,9 @@ abstract locate(meta: SessionHeader): SessionLocation | undefined
 abstract create(meta: SessionHeader): Promise<void>
 
 /**
- * Durably persist a batch of events (called from the write-behind drain at
- * the `session/flush` checkpoint). Honors the append-only and contiguous-seq
- * contracts: the first event's `seq` MUST equal the stored next-seq (after
- * `load` has durably closed any interrupted turn). Rejects non-JSON-
+ * Durably persist a batch of events. Honors the append-only and contiguous-
+ * seq contracts: the first event's `seq` MUST equal the stored next-seq
+ * (after `load` has durably closed any interrupted turn). Rejects non-JSON-
  * serializable `event.data` with an error naming the offending event type.
  * @param id - the session the batch belongs to.
  * @param events - the contiguous batch to persist, in seq order.
@@ -942,34 +948,85 @@ abstract append(id: SessionId, events: readonly SessionEvent[]): Promise<void>
  * Load a header and balanced contiguous log. A complete interrupted final
  * turn is preserved and durably closed with missing tool errors plus any open
  * step and turn boundaries; only a torn final record is discarded. Unknown
- * versions and corruption in the committed prefix reject.
+ * versions and corruption in the committed prefix reject. Implementations
+ * MUST NOT crash-repair an identity still bound to a live Session: a balanced
+ * live log may return with its stored header as a durable snapshot, while an
+ * open live turn rejects.
+ * A coordinator-backed cold load reserves the identity across storage awaits,
+ * so concurrent publication of a same-id live Session rejects.
  * @param id - the persisted session to reload.
  * @returns the header and a log ending on a balanced `turn/end`.
  */
 abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }>
 
+/**
+ * Inspect a header and its valid contiguous stored prefix without repairing
+ * a torn tail, closing an interrupted turn, or publishing coordinator state.
+ * This read is serialized with writes for the same id and returns detached
+ * values, so observers cannot mutate backend-owned state.
+ * @param id - the persisted session to inspect.
+ * @returns the header and valid stored event prefix exactly as observed.
+ */
+abstract inspect(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }>
+
 /**
  * Lightweight listing from metadata, without a full-log parse.
  * @returns one header per materialized session.
  */
 abstract list(): Promise<SessionHeader[]>
+
+/**
+ * List materialized sessions with cheap per-log change tokens.
+ *
+ * Repeated observations of an unchanged log return the same revision. A
+ * successful mutating {@link load} repair changes the next listed revision.
+ * Revisions also distinguish independently backed stores so backend-local
+ * counters cannot compare equal across different persistence sources.
+ * @returns one header and opaque revision per materialized session without loading full logs.
+ */
+abstract listSnapshots(): Promise<SessionPersistenceSnapshot[]>
 ```
 
-Types: [SessionEvent](../core-data-structures/core.md) · [SessionHeader](../core-data-structures/persistence.md) · [SessionId](../core-data-structures/core.md) · [SessionLocation](../core-data-structures/persistence.md)
+Types: [SessionEvent](../core-data-structures/core.md) · [SessionHeader](../core-data-structures/persistence.md) · [SessionId](../core-data-structures/core.md) · [SessionLocation](../core-data-structures/persistence.md) · [SessionPersistenceSnapshot](../core-data-structures/persistence.md)
+
+Source: [`packages/session-persistence/session-persistence/src/index.ts:52`](../../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` (abstract seam)
 
-## `ctx.sessionQuery` — `SessionQueryService`
+Unified live-preferred session query service.
 
-Live-preferred logical-corpus exact-read and relationship-tracing service.
+Exact reads, filters, and traces are backend-independent concrete behavior. A backend implements full-text observation, reconciliation, ranking, cursor generations, and query execution on the same `ctx.sessionQuery` service.
 
 ```ts cordis-catalog
+/**
+ * Search the live-preferred logical corpus and group by session.
+ * @param request - query text, metadata filters, page size, and cursor.
+ * @param exec - optional cancellation control.
+ * @returns session hits ranked by their strongest matching event.
+ */
+abstract searchSessions( request: SessionSearchRequest, exec?: SessionSearchExecContext, ): Promise<SessionSearchPage<SessionSearchHit>>
+
+/**
+ * Search events within one live-preferred logical session.
+ * @param request - target session, query text, filters, page size, and cursor.
+ * @param exec - optional cancellation control.
+ * @returns matching event hits in deterministic relevance order.
+ */
+abstract searchEvents( request: SessionEventSearchRequest, exec?: SessionSearchExecContext, ): Promise<SessionSearchPage<SessionEventSearchHit>>
+
 /**
  * List the complete logical corpus using live-preferred records.
  * @returns deterministic newest-first cloned session records.
  */
 listSessions(): Promise<SessionRecord[]>
 
+/**
+ * Filter the complete logical corpus with provider-independent predicates.
+ * @param filters - ANDed session metadata and availability clauses.
+ * @returns matching cloned records in deterministic newest-first order.
+ */
+async filterSessions(filters: readonly SessionResultFilter[]): Promise<SessionRecord[]>
+
 /**
  * Fold the latest log-backed title from one live-preferred logical session.
  * @param sessionId - live or persisted session id to read.
@@ -984,6 +1041,14 @@ async readTitle(sessionId: SessionId): Promise<SessionTitleSnapshot | undefined>
  */
 async listEvents(sessionId: SessionId): Promise<SessionEventRecord[]>
 
+/**
+ * Scan first-party semantic event documents with provider-independent filters.
+ * @param sessionId - live-preferred session id to scan.
+ * @param filters - ANDed metadata and literal-text predicates.
+ * @returns matching semantic documents in ascending seq order.
+ */
+async filterEvents( sessionId: SessionId, filters: readonly SessionEventResultFilter[], ): Promise<SessionEventSearchDocument[]>
+
 /**
  * Read one session's complete current model surface from one corpus observation.
  * @param sessionId - live-preferred session id to read.
@@ -1016,9 +1081,9 @@ async traceEvent(request: SessionEventTraceRequest): Promise<SessionEventTrace>
 async readEvent(request: SessionEventReadRequest): Promise<SessionEventWindow>
 ```
 
-Types: [SessionEventReadRequest](../core-data-structures/session-query.md) · [SessionEventRecord](../core-data-structures/session-query.md) · [SessionEventTrace](../core-data-structures/session-query.md) · [SessionEventTraceRequest](../core-data-structures/session-query.md) · [SessionEventWindow](../core-data-structures/session-query.md) · [SessionId](../core-data-structures/core.md) · [SessionLineageTrace](../core-data-structures/session-query.md) · [SessionRecord](../core-data-structures/session-query.md) · [SessionSurfaceSnapshot](../core-data-structures/session-query.md) · [SessionTitleSnapshot](../core-data-structures/session-title.md)
+Types: [SessionEventReadRequest](../core-data-structures/session-query.md) · [SessionEventRecord](../core-data-structures/session-query.md) · [SessionEventResultFilter](../core-data-structures/session-query.md) · [SessionEventSearchDocument](../core-data-structures/session-query.md) · [SessionEventSearchHit](../core-data-structures/session-query.md) · [SessionEventSearchRequest](../core-data-structures/session-query.md) · [SessionEventTrace](../core-data-structures/session-query.md) · [SessionEventTraceRequest](../core-data-structures/session-query.md) · [SessionEventWindow](../core-data-structures/session-query.md) · [SessionId](../core-data-structures/core.md) · [SessionLineageTrace](../core-data-structures/session-query.md) · [SessionRecord](../core-data-structures/session-query.md) · [SessionResultFilter](../core-data-structures/session-query.md) · [SessionSearchExecContext](../core-data-structures/session-query.md) · [SessionSearchHit](../core-data-structures/session-query.md) · [SessionSearchPage](../core-data-structures/session-query.md) · [SessionSearchRequest](../core-data-structures/session-query.md) · [SessionSurfaceSnapshot](../core-data-structures/session-query.md) · [SessionTitleSnapshot](../core-data-structures/session-title.md)
 
-Source: [`packages/session-query/session-query/src/index.ts:41`](../../packages/session-query/session-query/src/index.ts)
+Source: [`packages/session-query/session-query/src/index.ts:73`](../../packages/session-query/session-query/src/index.ts)
 
 ## `ctx.sessionReferences` — `SessionReferenceService`
 
@@ -1482,7 +1547,7 @@ attachSurface(name: string): () => void
 
 Types: [Agent](../core-data-structures/core.md) · [TaskDoneListener](../core-data-structures/tasks.md) · [TaskId](../core-data-structures/tasks.md) · [TaskRead](../core-data-structures/tasks.md) · [TaskSnapshot](../core-data-structures/tasks.md) · [TaskStart](../core-data-structures/tasks.md)
 
-Source: [`packages/tasks/tasks/src/index.ts:76`](../../packages/tasks/tasks/src/index.ts)
+Source: [`packages/tasks/tasks/src/index.ts:77`](../../packages/tasks/tasks/src/index.ts)
 
 ## `ctx.tokenMeter` — `TokenMeterService`
 
@@ -1564,7 +1629,7 @@ Tool registry and execution pipeline. Scoped registrations shadow globals; one v
 /**
  * Register globally or in the calling agent scope. Scoped tools shadow
  * globals; duplicates within one layer and the reserved `run_code` name fail.
- * @param definition - the tool schema, execution, and optional presentation functions.
+ * @param definition - tool schema, execution, and optional finalization/presentation callbacks.
  * @returns the exact disposer that unregisters the tool.
  */
 register(definition: ToolDefinition): () => void
@@ -1619,10 +1684,11 @@ schemas(scope?: ScopeKey): ToolSchema[]
 executionMode(exec: ToolExecutionInput): ToolExecutionMode
 
 /**
- * Execute through pre-policy, guards, around-dispatch, post-policy, and final
- * notification. Tool and listener failures resolve as materialized error
- * results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is
- * the same lossless, frozen snapshot final observers receive. Cancellation
+ * Execute through pre-policy, guards, around-dispatch, post-policy,
+ * definition-owned content finalization, and final notification. Tool and
+ * listener failures resolve as materialized error results; an invisible tool
+ * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen
+ * snapshot final observers receive. Cancellation
  * arriving after entry and before final result materialization skips a
  * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a
  * successful started outcome with `ABORTED`; already-started work is still
@@ -1636,7 +1702,7 @@ async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>
 
 Types: [ScopeKey](../core-data-structures/scope.md) · [ToolDefinition](../core-data-structures/tools.md) · [ToolExecutionInput](../core-data-structures/tools.md) · [ToolExecutionMode](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) · [ToolGuard](../core-data-structures/tools.md) · [ToolRestriction](../core-data-structures/tools.md) · [ToolSchema](../core-data-structures/tools.md)
 
-Source: [`packages/core/tools/src/index.ts:622`](../../packages/core/tools/src/index.ts)
+Source: [`packages/core/tools/src/index.ts:634`](../../packages/core/tools/src/index.ts)
 
 ## `ctx.tui` — `TuiExtensionService` (abstract seam)
 

docs/cordis-tutorial/06-composition-and-hmr.md

@@ -39,10 +39,10 @@ In `tmp/cordis-tutorial`, write `cordis.yml`:
 
 Two support plugins joined the list: HMR logs through the Cordis logger service, so without a console exporter you would not see its messages, and it `inject`s the `timer` service for debouncing — without `@cordisjs/plugin-timer` it sits in PENDING forever, silently. That silence is the subject of the next section.
 
-HMR also needs Node's loader internals:
+HMR reads Node's loader internals through the Loader's native helper. Run Cordis under tsx:
 
 ```sh
-node --expose-internals --import tsx ../../vendor/cordis/bin.js
+node --import tsx ../../vendor/cordis/bin.js
 ```
 
 Now edit `hello.ts` — change the log message — and save:

docs/core-data-structures/core.md

@@ -22,7 +22,7 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t
 | [commands.md](commands.md) | the human-command seam: definitions, adapter discovery, direct invocation, results, and parsing views |
 | [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 records, bounded exact-event reads, and relationship traces |
+| [session-query.md](session-query.md) | logical records, bounded exact-event reads, relationship traces, semantic filters/documents, and full-text result pages |
 | [session-title.md](session-title.md) | durable title snapshots, source provenance, and the asynchronous provider contract |
 | [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 |
@@ -244,10 +244,10 @@ interface GenerateOptions {
   sessionId?: Branded<'SessionId'>
   /**
    * Provider-neutral classification for an auxiliary model call. Adapters may
-   * map the purpose to model-hidden transport metadata. Ordinary conversation
-   * requests leave it unset.
+   * map the purpose to model-hidden transport metadata or purpose-specific
+   * generation policy. Ordinary conversation requests leave it unset.
    */
-  purpose?: 'compaction'
+  purpose?: 'compaction' | 'session-title'
 }
 ```
 
@@ -550,6 +550,6 @@ type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact'
 
 ## `ToolDefinition`
 
-The one pipeline-authoring type that is core: what every registered tool *is* — a model-facing `ToolSchema` plus an `execute` function and optional UI presenters. A tool author rarely constructs it by hand (the `defineTool` DSL builds it with typed args), but it is the contract the registry holds and the loop dispatches through.
+The one pipeline-authoring type that is core: what every registered tool *is* — a model-facing `ToolSchema` plus an `execute` function and optional final-content and UI callbacks. A tool author rarely constructs it by hand (the `defineTool` DSL builds it with typed args), but it is the contract the registry holds and the loop dispatches through.
 
 Its full fields, the `defineTool`/`ValueSchemaSpec`/`ParameterSchemaSpec` typed schema DSL, the `ToolExecution`/`ToolExecutionResult` waterfall shapes, and the tool-presentation UI vocabulary are on **[tools.md](tools.md)**.

docs/core-data-structures/persistence.md

@@ -2,16 +2,20 @@
 
 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](../../.agents/notes/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 Agent Note](../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md).
+The seam is a textbook [capability seam](../../.agents/notes/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, crash-repairing load, non-mutating inspect, and lightweight list/snapshot observation over the existing `SessionEvent` — **no parallel persisted type** — and two interchangeable backends that pass the same `runPersistenceContract` suite. See the [session-persistence Agent Note](../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md).
 
 ## The flush checkpoint
 
-`session/event` is a *synchronous* notification; persistence plugins buffer it (write-behind) until `session/flush`. The loop awaits an ordinary turn's checkpoint before claiming the next queue item; synchronous idle `inject()` schedules its checkpoint without blocking `send()`, and disposal still drains it. A successful flush durably commits the closed turn as one unit; a rejecting flush is reported through `agent/error` and the logger — never as a session event past the closed turn — while the backend keeps its buffered events for the next flush.
+`session/event` is a *synchronous* notification; persistence plugins copy the event into a per-session controller and start an eager write without blocking the producer. Concurrent events share the current batch, and events admitted during that write trigger a follow-up batch. `session/flush` waits until no current or pending batch remains, so the loop still uses it as the ordering and error-observation checkpoint before claiming the next ordinary turn. A rejected eager write retains its events; an explicit flush retries them and reports failure through `agent/error` and the logger, never as a session event past the closed turn. Disposal performs the same final drain.
 
 ## Crash recovery preserves an interrupted turn
 
 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)).
 
+Repair applies only to cold sessions. For a live id, `SessionPersistence.load(id)` snapshots the in-memory log, waits until that snapshot is durable, and returns it with the stored header only when balanced; an open live turn rejects rather than receiving synthetic interruption boundaries. A coordinator-backed cold load reserves the id across backend reads and repair writes, so concurrent publication of a same-id live session rejects and rolls back. HMR also adopts a live prefix without closing its active turn.
+
+`SessionPersistence.inspect(id)` is the observer counterpart to recovery: it returns a detached valid stored prefix without truncating a torn record, adding interruption closers, or publishing write state. Same-id serialization keeps it coherent with backend writes. Derived read models use `inspect`, never `load`, so observing a checkpointed open turn cannot mutate the log if live ownership begins concurrently.
+
 ## `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.
@@ -98,11 +102,31 @@ interface CreateSessionOptions {
 
 Replay/fork is therefore `ctx.sessions.create(id, { seed: seedEvents })`; resuming a *persisted* session into a live agent is `ctx.agents.resume({ resumeSessionId })`.
 
+## Lightweight source revisions
+
+Consumers of derived state compare a cheap opaque revision before loading a full event log. The persistence backend owns its representation and changes it transactionally with append or mutating load repair; callers compare it only for equality.
+
+```ts type-equiv
+/**
+ * Backend-owned token that identifies both one storage source and one revision
+ * of a persisted session log.
+ */
+type SessionPersistenceRevision = Branded<'SessionPersistenceRevision'>
+```
+
+```ts type-equiv
+/** Lightweight immutable source identity returned without loading a full log. */
+interface SessionPersistenceSnapshot {
+  /** Detached metadata for one materialized session. */
+  header: SessionHeader
+  /** Opaque source-qualified token that changes whenever this stored log changes. */
+  revision: SessionPersistenceRevision
+}
+```
+
 ## The backends
 
-Both implement the same abstract `SessionPersistence` (locate/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/inspect/list/listSnapshots 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 logical JSONL log per session, stored as checksummed concatenated Zstandard frames by default or raw lines by configuration, with crash-safe atomic writes, interrupted-turn recovery, 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.
-
-Multiple backends sharing one on-disk session coordinate writes through the [shared persistence write-coordinator](../../.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md).

docs/core-data-structures/pty.md

@@ -22,14 +22,14 @@ type PtySessionStatus =
 
 ## Backend and live session
 
-A backend owns how one registered type starts and detects readiness. `PtyService` publishes the returned session only after setup succeeds, then owns id authorization and cleanup. A backend session owns terminal state and captured-resource quiescence.
+A backend owns how one registered type starts and detects readiness. `PtyService` publishes the returned session only after setup succeeds, then owns id authorization and cleanup. A backend that cannot clean partial startup resources rejects with `PtyBackendCleanupError`, allowing disposal to retain the cleanup failure without replacing the caller's cancellation reason. A backend session owns terminal state and captured-resource quiescence.
 
 ```ts type-equiv
 /** Replaceable provider for one PTY session type. */
 interface PtyBackend {
   /** Stable type selected by {@link PtySpawnRequest.type}. */
   readonly type: string
-  /** Create an unpublished session or reject after cleaning partial resources. */
+  /** Create an unpublished session or reject after cleaning partial resources; cleanup failure uses {@link PtyBackendCleanupError}. */
   spawn(spec: PtyBackendSpawnSpec): Promise<PtyBackendSession>
 }
 ```

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

@@ -1,6 +1,6 @@
 # Session Query
 
-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.
+Query vocabulary over the live-preferred logical session corpus. The [interface package](../../packages/session-query/session-query) owns exact reads, source precedence, relationship tracing, semantic extraction, and provider-independent filters, while the [SQLite package](../../packages/session-query/session-query-sqlite) owns the concrete full-text index lifecycle.
 
 Source: [`packages/session-query/session-query/src/types.ts`](../../packages/session-query/session-query/src/types.ts)
 
@@ -55,6 +55,113 @@ interface SessionEventRecord {
 }
 ```
 
+## Provider-independent filters and documents
+
+Session and event filter arrays are ANDed; values inside one list clause are ORed. Ranges are inclusive. The event `text` clause is a literal Unicode case-insensitive, whitespace-flexible regular-expression scan over extracted semantic text, independent of full-text providers.
+
+```ts type-equiv
+/**
+ * One logical-session predicate. A filter array is ANDed; `values` within a
+ * clause are ORed.
+ */
+type SessionResultFilter =
+  | { kind: 'id'; values: readonly SessionId[] }
+  | { kind: 'cwd'; values: readonly (string | null)[] }
+  | ({ kind: 'created-at' } & SessionResultRange)
+  | { kind: 'parent'; values: readonly (SessionId | null)[] }
+  | { kind: 'availability'; values: readonly SessionAvailability[] }
+```
+
+```ts type-equiv
+/**
+ * One event predicate. A filter array is ANDed; list-valued clauses are ORed.
+ * Text is a literal, case-insensitive, whitespace-flexible semantic-text scan.
+ */
+type SessionEventResultFilter =
+  | ({ kind: 'seq' } & SessionResultRange)
+  | ({ kind: 'time' } & SessionResultRange)
+  | { kind: 'type'; values: readonly SessionEventType[] }
+  | { kind: 'surface'; values: readonly SessionEventSurface[] }
+  | { kind: 'text'; text: string }
+```
+
+```ts type-equiv
+/** Searchable semantic document derived from one session event. */
+interface SessionEventSearchDocument extends SessionEventRecord {
+  /** First-party semantic text used by scan filters and full-text indexes. */
+  text: string
+}
+```
+
+`ctx.sessionQuery.filterSessions(filters)` applies `SessionResultFilter` to the complete logical corpus; `ctx.sessionQuery.filterEvents(sessionId, filters)` returns matching documents in ascending seq order. Messages, reasoning, tool calls/results, blocked prompts, todos, and failure/status detail contribute semantic text; structural events and stream chunks do not.
+
+## Full-text search pages
+
+The combined `ctx.sessionQuery` seam has two full-text scopes. `searchSessions()` groups the corpus by strongest matching event; `searchEvents()` searches one session. Requests bind an opaque cursor to the normalized query, metadata filters, and limit. The event text scan is intentionally absent from provider metadata filters.
+
+```ts type-equiv
+/** Provider-owned opaque continuation token returned by session search. */
+type SessionSearchCursor = Branded<'SessionSearchCursor'>
+```
+
+```ts type-equiv
+/** Cross-session full-text search request. */
+interface SessionSearchRequest {
+  /** Full-text query interpreted as data, never executable FTS syntax. */
+  query: string
+  /** Logical-session predicates applied before event ranking. */
+  sessionFilters?: readonly SessionResultFilter[]
+  /** Event predicates applied before event ranking. */
+  eventFilters?: readonly SessionEventMetadataFilter[]
+  /** Maximum sessions in this page. */
+  limit?: number
+  /** Opaque cursor returned for the identical normalized request. */
+  cursor?: SessionSearchCursor
+}
+```
+
+```ts type-equiv
+/** Within-session full-text search request. */
+interface SessionEventSearchRequest {
+  /** Session whose live-preferred logical log is searched. */
+  sessionId: SessionId
+  /** Full-text query interpreted as data, never executable FTS syntax. */
+  query: string
+  /** Event predicates applied before ranking. */
+  filters?: readonly SessionEventMetadataFilter[]
+  /** Maximum events in this page. */
+  limit?: number
+  /** Opaque cursor returned for the identical normalized request. */
+  cursor?: SessionSearchCursor
+}
+```
+
+```ts type-equiv
+/** One cursor-paginated result page. */
+interface SessionSearchPage<T> {
+  /** Results for this page in contract-defined order. */
+  items: readonly T[]
+  /** Opaque continuation cursor, absent on the final page. */
+  nextCursor?: SessionSearchCursor
+}
+```
+
+```ts type-equiv
+/** One event full-text search hit with a bounded plain-text excerpt. */
+interface SessionEventSearchHit extends SessionEventRecord {
+  /** Plain text excerpt selected around the match. */
+  snippet: string
+}
+```
+
+```ts type-equiv
+/** One grouped cross-session hit, ranked by its strongest matching event. */
+interface SessionSearchHit extends SessionRecord {
+  /** Strongest matching event for this session. */
+  bestMatch: SessionEventSearchHit
+}
+```
+
 ## 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.
@@ -165,14 +272,21 @@ interface SessionEventTrace {
 The closed code union distinguishes request validation, missing targets, malformed surface logs, optional-backend failure, and contradictory source metadata.
 
 ```ts type-equiv
-/** Stable machine-routable failure taxonomy for exact session reads and traces. */
+/** Stable machine-routable failure taxonomy for session reads, traces, and search. */
 type SessionQueryErrorCode =
+  | 'SESSION_QUERY_ABORTED'
   | 'SESSION_QUERY_EVENT_NOT_FOUND'
+  | 'SESSION_QUERY_INDEX_FAILED'
   | 'SESSION_QUERY_INVALID_CONFIG'
+  | 'SESSION_QUERY_INVALID_CURSOR'
+  | 'SESSION_QUERY_INVALID_FILTER'
+  | 'SESSION_QUERY_INVALID_LIMIT'
+  | 'SESSION_QUERY_INVALID_QUERY'
   | 'SESSION_QUERY_INVALID_LINEAGE'
   | 'SESSION_QUERY_INVALID_SURFACE'
   | 'SESSION_QUERY_INVALID_WINDOW'
   | 'SESSION_QUERY_PERSISTENCE_FAILED'
   | 'SESSION_QUERY_SESSION_NOT_FOUND'
+  | 'SESSION_QUERY_STALE_CURSOR'
   | 'SESSION_QUERY_SOURCE_CONFLICT'
 ```