docs: align runtime-context contracts

2026-07-31 13:49:41 +08:00
parent 49a40bbd8d
commit da541c10a7
15 changed files with 60 additions and 60 deletions
@@ -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 .agents/notes/implemented/feature/2026-07-06-approval-seam.md
-2026-07-06-approval-seam.md: efb4159d736779af28edc1ae6091de4669c92f31
-2026-07-06-approval-seam.zh.md: 9a4656f30a43473fe90cde9c56d45f48943e5d10
+2026-07-06-approval-seam.md: ae143a41302b7bcd6029345fa91ca4eda837c141
+2026-07-06-approval-seam.zh.md: a66ce804167fd4de5c8dbe51d70c9b038d1ebb17
@@ -25,7 +25,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou
  #   policy: never   # deployment default for sessions without an override; 'ask' when omitted
 ```

-The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its [automation-only bridge](../simplification/2026-07-23-acp-automation-only-protocol.md) registers an answerer that sends `session/request_permission` to the owning client with the exact tool-call id and one-shot allow/reject options. `policy: never` is the unattended stance — every ask auto-rejects deterministically and is stated in the system prompt. `policy` is validated against the closed list at plugin load; anything else throws.
+The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its [automation-only bridge](../simplification/2026-07-23-acp-automation-only-protocol.md) registers an answerer that sends `session/request_permission` to the owning client with the exact tool-call id and one-shot allow/reject options. `policy: never` is the unattended stance — every ask auto-rejects deterministically, and the current value joins the runtime-context snapshot. `policy` is validated against the closed list at plugin load; anything else throws.

 What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; a successful in-turn request lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. An idle request or audit append failure rejects instead of returning an unaudited decision.

@@ -63,7 +63,7 @@ Answerers are `approval/request` waterfall listeners. Zero listeners fall throug

 #### The per-session policy tier

-The seam also owns the session-scoped `'ask' | 'never'` policy described by [the sandbox Agent Note](2026-07-06-sandbox.md). Effective policy is folded from logged switches over the deployment default. `'never'` resolves to `rejected` inside `request()` before any answerer can run; `'ask'` dispatches and otherwise falls through to `unavailable`. The prompt states only deterministic `'never'`, switch narration is coalesced, and every request still records the audit pair.
+The seam also owns the session-scoped `'ask' | 'never'` policy described by [the sandbox Agent Note](2026-07-06-sandbox.md). Effective policy is folded from logged switches over the deployment default. `'never'` resolves to `rejected` inside `request()` before any answerer can run; `'ask'` dispatches and otherwise falls through to `unavailable`. Both current values join the atomic runtime-context snapshot before each model request, so a policy switch needs no separate narration; every approval request still records the audit pair.

 #### The ACP answerer

@@ -83,7 +83,7 @@ The answerer routes through the bridge's exact-agent ownership check described b

 Unit tests pin outcomes, first-wins delegation, containment, cancellation, scoped routing, audit pairing, the unbypassable `'never'` policy, tool deny reasons, and ACP ownership/outcome mapping through a real scripted bridge.

-Snapshots record allowed and rejected sandbox escalation through `session/request_permission`, plus the `'never'` prompt and policy-switch notice. Unscripted permission prompts cancel and fail closed.
+Snapshots record allowed and rejected sandbox escalation through `session/request_permission`, plus the complete `'ask'` and `'never'` runtime-context contributions. Unscripted permission prompts cancel and fail closed.

 ## Deferred

@@ -124,7 +124,7 @@ Costs and accepted limits:
 - **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer. When both audit appends commit, either path records one pair, never two.
 - **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant.
 - **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. A `'never'` parent seeds that override into each in-process child's log ([decision](2026-07-25-subagent-policy-inheritance.md)), so the child is told up front instead of asking into the empty waterfall. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent controller is deferred (§ Deferred).
- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; each successful auto-rejection records the audit pair.
+- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the next atomic runtime-context snapshot states the policy; each successful auto-rejection records the audit pair.
 - **What happens across a hot reload, or when an answerer unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state.
 - **Where does a client get approval context?** The request carries the exact `callId` and the asker's human-readable `reason`; channel adapters may correlate richer tool-call state without duplicating arguments in the approval seam.

@@ -25,7 +25,7 @@ Status: implemented
  #   policy: never   # deployment default for sessions without an override; 'ask' when omitted
 ```

-仅有这条条目只提供机制，不提供通道：没有组合应答者时，每次 ask 都解析为 `unavailable`，发起请求的工具调用被拒绝——失败关闭无需配置。组合 ACP 应用（`@deepseek-ai/dsh-acp-demo`，如 [acp-agent 示例的默认树](../../../../examples/acp-agent/README.md)）即可闭环：其[仅面向自动化的桥接层](../simplification/2026-07-23-acp-automation-only-protocol.md)注册一个应答者，向拥有该会话的客户端发送 `session/request_permission`，携带精确的工具调用 id 和一次性 allow/reject 选项。`policy: never` 是无人值守姿态：每次 ask 确定性地自动拒绝，并在系统提示词中声明。`policy` 在插件加载时对照封闭列表校验；非法值直接抛异常。
+仅有这条条目只提供机制，不提供通道：没有组合应答者时，每次 ask 都解析为 `unavailable`，发起请求的工具调用被拒绝——失败关闭无需配置。组合 ACP 应用（`@deepseek-ai/dsh-acp-demo`，如 [acp-agent 示例的默认树](../../../../examples/acp-agent/README.md)）即可闭环：其[仅面向自动化的桥接层](../simplification/2026-07-23-acp-automation-only-protocol.md)注册一个应答者，向拥有该会话的客户端发送 `session/request_permission`，携带精确的工具调用 id 和一次性 allow/reject 选项。`policy: never` 是无人值守姿态：每次 ask 都会被确定性地自动拒绝，当前值也会加入运行时上下文快照。`policy` 在插件加载时对照封闭列表校验；非法值直接抛异常。

 组合部署的可观测行为：`allowed-once` 仅允许该次调用继续；拒绝、关闭和通道缺失以三种不同原因拒绝，模型可以区分；轮次内成功的请求会在发起请求的 agent 的会话日志上落一对持久的 `approval/asked`/`approval/decided` 事件；授权不会在发起请求的调用结束后继续存在。空闲时的请求或审计追加失败会拒绝，而不会返回未经审计的决策。

@@ -63,7 +63,7 @@ tool/result      "escalated" — this one call ran under the wider mode; the gra

 #### 每会话策略层

-seam 还拥有[沙箱 Agent Note](2026-07-06-sandbox.md) 所描述的会话级 `'ask' | 'never'` 策略。生效策略由日志中记录的切换在部署默认值之上折叠而成。`'never'` 会在任何应答者运行之前，于 `request()` 内部解析为 `rejected`；`'ask'` 则派发请求，否则一路委派至 `unavailable`。提示词仅声明确定性的 `'never'`，切换叙述会被合并，每个请求仍记录审计对。
+seam 还拥有[沙箱 Agent Note](2026-07-06-sandbox.md) 所描述的会话级 `'ask' | 'never'` 策略。生效策略由日志中记录的切换在部署默认值之上折叠而成。`'never'` 会在任何应答者运行之前，于 `request()` 内部解析为 `rejected`；`'ask'` 则派发请求，否则一路委派至 `unavailable`。两个当前值都会在每次模型请求前加入原子化的运行时上下文快照，因此策略切换无需单独叙述；每次批准请求仍会记录审计对。

 #### ACP 应答者

@@ -83,7 +83,7 @@ ACP 桥只应答其会话映射所拥有的精确 agent 对象。它携带既有

 单元测试固定结果、先到先得的委派、错误容纳、取消、作用域路由、审计配对、不可绕过的 `'never'` 策略、工具拒绝原因，以及通过真实脚本化桥实现的 ACP 归属/结果映射。

-快照记录通过 `session/request_permission` 批准和拒绝沙箱升级，以及 `'never'` 提示词与策略切换通知。没有脚本化应答的权限提示会取消并失败关闭。
+快照记录通过 `session/request_permission` 批准和拒绝沙箱升级，以及完整的 `'ask'` 与 `'never'` 运行时上下文贡献。没有脚本化应答的权限提示会取消并失败关闭。

 ## 延后

@@ -124,7 +124,7 @@ ACP 桥只应答其会话映射所拥有的精确 agent 对象。它携带既有
 - **用户关闭提示或轮次在 ask 进行中中止时会发生什么？** 关闭映射为 `cancelled` 并携带自己的拒绝文本。已中止的 signal 直接结算为 `cancelled` 而不派发；ask 进行中的中止丢弃迟到的应答。当两个审计追加都提交时，任一路径都记录恰好一对事件，绝不会两对。
 - **如果客户端以 harness 从未提供的选项应答呢？** 除已提供的 `allow_once` 之外的任何选项都映射为 `rejected`——来自不合规客户端的未知 optionId 永远不能授权。
 - **subagent 的审批如何路由？** 没有应答者拥有的 agent 穿过整个 waterfall 委派并失败关闭——进程内 subagent 被刻意设计为不可应答。`'never'` 父级会把该覆盖项预置到每个进程内子 agent 的日志中（[决策](2026-07-25-subagent-policy-inheritance.md)），因此子 agent 一开始就会得知，而不是向空的 waterfall 发出 ask。`subagent-acp` 的子侧自动应答是独立的；将子 agent 的 ask 路由到父控制器已延后（§ 延后）。
- **`policy: 'never'` 在运行时实际改变了什么？** 服务在派发任何应答者之前，将该会话的每次 ask 解析为 `rejected`（在服务内部，因此没有注册顺序能绕过它）；系统提示词声明该策略；切换在边界处被叙述；每次成功的自动拒绝都会记录审计对。
+- **`policy: 'never'` 在运行时实际改变了什么？** 服务在派发任何应答者之前，将该会话的每次 ask 解析为 `rejected`（在服务内部，因此没有注册顺序能绕过它）；下一份原子化的运行时上下文快照会声明该策略；每次成功的自动拒绝都会记录审计对。
 - **热重载或应答者在会话中途卸载时会发生什么？** 应答者随其拥有的 fiber 一起 dispose，因此下一次 ask 降级为 `unavailable` 而非挂在死通道上；重新挂载会重新注册应答者，无需追赶状态。
 - **客户端从哪里获得审批上下文？** 请求携带精确的 `callId` 和发起方的人类可读 `reason`；通道适配器可自行关联更丰富的工具调用状态，而无需在审批 seam 中重复携带参数。

@@ -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 .agents/notes/implemented/feature/2026-07-06-sandbox.md
-2026-07-06-sandbox.md: f29bdf840db8b0f4cbcba9958c20cd0255097f38
-2026-07-06-sandbox.zh.md: 91b3a0acf42585b2e47af2158e03fe7eee198d7d
+2026-07-06-sandbox.md: f53516f97d45426bc4693b43a7135dd565a468a3
+2026-07-06-sandbox.zh.md: 6c92d9d80cf67a5e501f15572cbbe680babb863b
@@ -40,7 +40,7 @@ The swap is invisible to every consumer of `ctx.bash`: the bash tools, hook comm

 Misconfiguration fails loud: `mode` outside the closed vocabulary is rejected at plugin load, and a host with no usable backend throws the structured `SANDBOX_UNAVAILABLE` — at `confine()` before the command ever spawns — rather than degrading to unconfined execution. `runnerCommand` on `dsh-sandbox-local` is the operator's explicit assertion of a bwrap-compatible runner (chain and probes skipped); it doubles as the deterministic fake-runner seam for keyless tests.

-Denied file effects return a `[sandbox: file access denied under <mode> mode]` marker and instructions not to work around the denial. A confining executor adds paired `sandbox_permissions` and `justification` fields for one approved retry that must be strictly wider than the session's effective mode. A grant widens only that retry; rejection executes nothing, returns `the user rejected escalating this command to "<mode>"`, and permits no re-ask. The owner-derived prompt section states the current file policy without replacing those enforcement boundaries. When `dsh-permission` is composed with a UI adapter, one preset selects both knob values; unmatched values fold to `custom`. The [ACP automation composition](../../../../examples/acp-agent/README.md) does not mount that UI service and selects its deployment mode explicitly.
+Denied file effects return a `[sandbox: file access denied under <mode> mode]` marker and instructions not to work around the denial. A confining executor adds paired `sandbox_permissions` and `justification` fields for one approved retry that must be strictly wider than the session's effective mode. A grant widens only that retry; rejection executes nothing, returns `the user rejected escalating this command to "<mode>"`, and permits no re-ask. The owner-derived runtime context states the current file policy without replacing those enforcement boundaries. When `dsh-permission` is composed with a UI adapter, one preset selects both knob values; unmatched values fold to `custom`. The [ACP automation composition](../../../../examples/acp-agent/README.md) does not mount that UI service and selects its deployment mode explicitly.

 ### Design detail

@@ -105,7 +105,7 @@ interface SessionEventMap {

 Each owner exports the same three-piece kit: the event declaration, a pure fold (`effectiveSandboxMode(events)` / `effectiveApprovalPolicy(events)` — a `findLast`, typed to the domain's closed union), and THE write path (`setSandboxMode(session, mode)` / `setApprovalPolicy(session, policy)` — a switch IS its event; nothing mutates state out of band). No shared owner service, no generic facts map, no registry: a third knob copies the ~40-line pattern into its own package. Execution follows the fold on both sides — the bash tool's per-call stamp reads it as the middle rung of the § Escalation precedence chain, and the approval seam's `'never'` gate is [the approval Agent Note](2026-07-06-approval-seam.md)'s side of the same pattern.

-Sandbox policy is rendered from the current mode and workspace root before every request; the existing `request/header` records the exact section, so no switch narrator or last-told state is needed. Approval policy stays separate: only `'never'` is stated because automatic rejection otherwise looks like a user decision, and its owner retains its own switch narration.
+Sandbox and approval policy are rendered as ordered contributions to one runtime-context snapshot before every request. The loop records the complete snapshot as a sourced `user/message`; both `'ask'` and `'never'` are explicit, so neither owner needs switch narration or last-told state.

 **The optional UI surface** is `PermissionService`: a deployment-defined preset table whose entries bundle one sandbox mode with one approval policy. The shipped `workspace-write` and `danger-full-access` presets write through to both domain setters; a knob combination outside the table is reported as `custom`. UI adapters may expose that table as a selector. The automation-only ACP transport advertises no configuration selector and mounts no permission-preset service.

@@ -117,10 +117,10 @@ fs/web/todo execute in-process, so their sandbox semantics are policy at their s

 ### Testing

- **Unit:** pin platform selection and profiles, fail-closed runner classification, per-call mode/root resolution, per-process facts, escalation validation and outcomes, permission preset folding and write-through, and narrator coalescing.
+- **Unit:** pin platform selection and profiles, fail-closed runner classification, per-call mode/root resolution, per-process facts, escalation validation and outcomes, permission preset folding and write-through, and runtime-context ordering and materialization.
 - **Keyless real-runner:** exercise bwrap, Landlock, and Seatbelt against real filesystem effects at provider and bash-consumer layers; one real Cordis context concurrently drives two project sessions through shipped bash and fs tools, proving own-root success and sibling-root denial. Packed-install coverage proves the registry launcher remains executable. CI rejects a silent all-skip.
 - **With-key:** start the real ACP composition in read-only mode, let a model-driven bash write hit the runner's denial marker, then drive the bridge answerer and disk effect through granted and rejected workspace-write retries; unavailable credentials or runners self-skip.
- **Snapshot:** pin the current policy section and both scripted approval branches. A real ACP example scenario places its session under the user home while the deployment fallback points at `/tmp`, then pins both the workspace-write request header and a successful deployment-selected mutation; this distinguishes session-root resolution from the process fallback without depending on runner-specific denial text. Other snapshots start unconfined so unrelated fixtures remain platform-independent.
+- **Snapshot:** pin the atomic current-policy context and both scripted approval branches. A real ACP example scenario places its session under the user home while the deployment fallback points at `/tmp`, then pins both the workspace-write runtime-context message and a successful deployment-selected mutation; this distinguishes session-root resolution from the process fallback without depending on runner-specific denial text. Other snapshots start unconfined so unrelated fixtures remain platform-independent.

 ## Deferred phases

@@ -149,9 +149,9 @@ Each phase gets its full design when picked up, validated against the code at th
 - **Per-session dynamic tool schemas** — rejected: schemas are registry-global by design (one assembly vocabulary, the pinned-header snapshot contract), and re-registering per session would buy only what the execution-time strict-wider check already guarantees, at the cost of a per-session schema surface and header churn on every switch.
 - **Hard-match the retry to a prior denial** — rejected: command-string identity is fragile (quoting, `workdir`, env prefixes, a pipeline retried as its failing stage) — false-rejects honest retries or is trivially satisfied; the real boundary is the human seeing command + justification. Revisit only if `allow_always` grant storage ever needs machine-checkable scopes.
 - **A generic `env/state` facts map with an owner service** — rejected: approval and sandbox compose independently, so neither's state may drag in a third package; single-key folds are one `findLast` each, dissolving the owner service; no invariant spans the knobs, so atomic multi-key patches bought nothing.
- **Narrate via `agent/user-message` + a bus event** — rejected: it presupposes a turn-entry seam that does not exist (the real seam is `agent/prompt-submit`), and pre-step's position serves both the coalesced turn-entry notice and the mid-turn immediacy bound with one listener.
- **A standing prompt statement of the sandbox mode (+ a switch narrator)** — shipped first, then removed on live evidence: with `Bash commands run under the "read-only" file sandbox.` in every request, the model refused to ATTEMPT denied-then-escalatable work (five of twelve turns in the first manual session ended with zero tool calls), turning the sandbox into a soft lockout. The denial marker names the mode at the moment it matters and the escalation fields carry the recovery; the approval knob keeps its statement because an auto-rejection is behaviorally indistinguishable from a human "no". The absence decision is superseded by [the current-policy decision](2026-07-30-current-sandbox-policy-context.md); this measurement and causal observation remain the evidence that any replacement must counter-test.
- **Track "last told" with its own bookkeeping events** — rejected: the `request/header` fold already records the exact prompt the model saw; parsing the closed candidate sentences back replaces a second bookkeeping stream — events are needed only where they ARE the store.
+- **Narrate each switch through `agent.inject()` plus a bus event** — rejected: independent notices expose owner ordering and intermediate combinations, while one assembly pass can materialize the complete current state atomically at the request boundary.
+- **State sandbox mode in the stable system prompt** — shipped first, then removed on live evidence: with `Bash commands run under the "read-only" file sandbox.` in every request, the model refused to ATTEMPT denied-then-escalatable work (five of twelve turns in the first manual session ended with zero tool calls), turning the sandbox into a soft lockout. The denial marker names the mode at the moment it matters and the escalation fields carry the recovery. The absence decision is superseded by [the current-policy decision](2026-07-30-current-sandbox-policy-context.md); this measurement and causal observation remain the evidence that any replacement must counter-test.
+- **Track "last told" with its own bookkeeping events** — rejected: the latest sourced runtime-context `user/message` records the exact full snapshot the model saw. Materializing that snapshot from current owner contributions replaces a second bookkeeping stream — events are needed only where they ARE the store.
 - **Independent sandbox and approval selectors** — rejected: one deployment-defined permission preset keeps the two policy knobs coherent for UI clients that expose runtime switching.

 ## Consequences
@@ -160,12 +160,12 @@ What shipped pins — the tiers in Testing hold each:

 - A denied command retried with `sandbox_permissions` + `justification` prompts the user through the composed answerer chain; a grant runs THAT call under the wider mode (result facts say so) while every other call keeps its own effective mode; every non-grant outcome produces its distinct error text and executes nothing.
 - The escalation fields exist exactly when the mounted executor confines; a request that is not strictly wider than the call's effective mode fails closed with its own text and prompts no one; a deployment with no ApprovalService fails escalating calls closed and leaves plain calls untouched.
- The system prompt states sandbox policy and approval policy in separate owner-derived sections; the whole exchange — headers, knob events, approval notices, approvals, and results — reconstructs from the session log alone, with no event types beyond the two knob events.
- One preset selection records only changed knob values, while a no-op selection records nothing; an approval-policy switch is narrated in at most one coalesced notice, and a committed sandbox switch is honored by the next call's stamp.
- A resumed session's overrides apply with no catch-up state; a default changed while the process was down is narrated before the session's first new request, attributed to the operator.
+- One sourced runtime-context message states the complete current sandbox and approval policies atomically; the whole exchange — context snapshots, headers, knob events, approval notices, approvals, and results — reconstructs from the session log alone, with no policy bookkeeping events beyond the two knob events.
+- One preset selection records only changed knob values, while a no-op selection records nothing; the next request snapshots both current values atomically, and a committed sandbox switch is honored by the next call's stamp.
+- A resumed session's overrides enter its first new runtime-context snapshot with no catch-up state; a composition default changed while the process was down likewise appears in that snapshot.
 - Two concurrent sessions never see each other's state or notices.
 - Two concurrent project sessions in one Cordis context resolve independent workspace roots; bash and fs writes succeed inside the calling session's cwd and fail against its neighbor's cwd.
- `agent-loop` is untouched — everything rides `systemPrompt.section`, `SessionEventMap` merging, `agent.inject()`, `agent/step`, `agent/prompt-submit`, and capability-owned policy resolution.
+- Policy ownership stays in plugins through `systemPrompt.context`, `SessionEventMap` merging, and capability-owned resolution; the generic loop change materializes every owner's ordered context as one sourced message.

 Costs and accepted limits:

@@ -178,9 +178,8 @@ Costs and accepted limits:
 - **The model may over-ask.** Escalating without denial grounding, or picking `danger-full-access` where `workspace-write` suffices: the description steers and the enum forces the ladder, but the human prompt is the actual gate; the `approval/asked` reasons make over-asking auditable, and a `prepend` policy answerer can auto-reject patterns a deployment never wants.
 - **The advertised target set is static while the effective mode is per-session** (schemas are registry-global) — a session already at the widest mode is still offered the fields. Harmless by construction: the strict-wider check at execution, not the enum, is the safety boundary — a non-widening request fails with its own text and never prompts anyone.
 - **A granted escalation is not a working sandbox.** An unavailable backend still fails closed even for a granted escalation to a confining mode — at `confine()` when the platform has no chain or every probe fails, at execution when an unprobed sole runner refuses (classified as a sandbox failure, not a command failure) — while a granted `danger-full-access` run never touches the provider at all: there the grant, not the probe, is the authority.
- **The approval narrator's restart baseline parses prompt prose.** The closed candidate sentence is owned by the writing module itself, so a wording change is a coordinated writer+parser edit in one file; a session whose headers predate the section silently adopts the current policy without a notice.
- **The approval and sandbox sections are dynamic prompt surfaces.** A policy switch breaks provider prompt-prefix caching for that session; unchanged state remains byte-stable, and a model acting on stale authority is worse than the bounded invalidation.
- **The model may hold a stale belief about the sandbox mode** (nothing announces a switch). Accepted deliberately in the original design: the next attempt's marker or success corrects it, and the observed failure mode of announcing — preemptive refusal — is worse than one wasted retry. [The current-policy decision](2026-07-30-current-sandbox-policy-context.md) supersedes this accepted limit with a family-aware request section while retaining the preemptive-refusal evidence as its counter-test.
+- **Runtime-context history is append-only.** A policy switch appends a complete superseding snapshot after retained history, preserving the stable system-and-conversation prefix; unchanged state adds no message.
+- **Older policy snapshots remain in history.** Each full snapshot explicitly supersedes earlier runtime-context snapshots, so replay and compaction need only retain the latest materialized message.

 ## FAQ

@@ -191,8 +190,8 @@ Costs and accepted limits:
 - **Does the sandbox restrict network or process visibility?** No — `SandboxMode` claims FILE effects only; the bwrap profile deliberately does not unshare pid, and no backend claims network. Whether network restriction becomes its own knob is left open in § The seam.
 - **Which tools actually run confined?** OS subprocesses through `ctx.bash` — the bash tools, and hook commands transitively — plus the filesystem tools (`read`/`write`/`edit`) through the sandboxed `ctx.fs` provider (the [cross-family fs sandbox RFC](2026-07-14-cross-family-fs-sandbox.md)): bash confines via the OS runner, fs via an in-process path fence, both keying off the same `ctx.sandboxPolicy` mode. web/todo stay in-process and unfenced (web's only effect is network, outside the file-effect mode vocabulary).
 - **Does a granted escalation persist?** No. The grant is consumed by the exact foreground or background call that asked; every neighboring call keeps its own effective mode. A later background denial surfaces through `task_output` and may ground a new exact-command retry.
- **When does a runtime mode switch take effect?** Once its session event commits, the next request section and the next capability resolution fold the new mode. The request header records what the model was told, and any later denial names the same policy at the point of use.
- **What survives a restart — and what if the operator changed the config default while the process was down?** Overrides replay from the session log (`effective = fold ?? config`), so a resumed session keeps its modes with zero catch-up machinery; a default that drifted offline changes behavior the same way a switch does (the approval policy, being stated, is additionally narrated with operator/config attribution).
+- **When does a runtime mode switch take effect?** Once its session event commits, the next runtime-context snapshot and the next capability resolution fold the new mode. The sourced context message records what the model was told, and any later denial names the same policy at the point of use.
+- **What survives a restart — and what if the operator changed the config default while the process was down?** Overrides replay from the session log (`effective = fold ?? config`), so a resumed session keeps its modes with zero catch-up machinery; a default that drifted offline enters the next full runtime-context snapshot.
 - **What does `enforcement: 'partial'` on a result mean?** The selected backend enforces the subset its kernel ABI governs — e.g. Landlock before ABI v3 does not govern path truncate — and says so structurally instead of refusing the host; the probe's report line distinguishes the cases. The bwrap and Seatbelt profiles govern every promised file effect by construction, so they always report `full`.

 ## Prior art
@@ -40,7 +40,7 @@ harness 是一个 SDK，因此约束必须是开发者可组合的能力：是

 配置错误大声失败：`mode` 不在封闭词汇中时在插件加载时被拒绝；主机上没有可用后端时在 `confine()` 阶段（命令 spawn 之前）抛出结构化的 `SANDBOX_UNAVAILABLE`，而非降级为无约束执行。`dsh-sandbox-local` 上的 `runnerCommand` 是运维人员对一个 bwrap 兼容 runner 的显式断言（跳过链和探测）；它同时充当 keyless 测试的确定性 fake-runner seam。

-被拒绝的文件操作返回 `[sandbox: file access denied under <mode> mode]` 标记，并附带不要绕过拒绝的指令。约束执行器添加配对的 `sandbox_permissions` 和 `justification` 字段，用于一次经批准的重试，该重试必须严格宽于会话的有效模式。授权仅放宽该次重试；拒绝则不执行任何内容，返回 `the user rejected escalating this command to "<mode>"`，且不允许再次请求。由归属方派生的提示词段落会说明当前文件策略，但不会取代这些强制执行边界。当 `dsh-permission` 与某个 UI 适配器一起组合时，一个 preset 同时选定两个旋钮值；不匹配的组合折叠为 `custom`。[ACP 自动化组合](../../../../examples/acp-agent/README.md)不挂载该 UI 服务，而是显式选定其部署模式。
+被拒绝的文件操作返回 `[sandbox: file access denied under <mode> mode]` 标记，并附带不要绕过拒绝的指令。约束执行器添加配对的 `sandbox_permissions` 和 `justification` 字段，用于一次经批准的重试，该重试必须严格宽于会话的有效模式。授权仅放宽该次重试；拒绝则不执行任何内容，返回 `the user rejected escalating this command to "<mode>"`，且不允许再次请求。由归属方派生的运行时上下文会说明当前文件策略，但不会取代这些强制执行边界。当 `dsh-permission` 与某个 UI 适配器一起组合时，一个 preset 同时选定两个旋钮值；不匹配的组合折叠为 `custom`。[ACP 自动化组合](../../../../examples/acp-agent/README.md)不挂载该 UI 服务，而是显式选定其部署模式。

 ### 设计细节

@@ -105,7 +105,7 @@ interface SessionEventMap {

 每个拥有者导出相同的三件套：事件声明、纯 fold（`effectiveSandboxMode(events)` / `effectiveApprovalPolicy(events)`——一个 `findLast`，类型化到领域的封闭联合），以及唯一的写入路径（`setSandboxMode(session, mode)` / `setApprovalPolicy(session, policy)`——切换即其事件；没有任何东西在带外修改状态）。无共享拥有者服务、无通用 facts map、无注册表：第三个旋钮只需将约 40 行模式复制到自己的包中。执行在两侧都遵循 fold——bash 工具的按调用盖章将其作为 § 升级机制优先级链的中间层读取，approval seam 的 `'never'` 门控是[批准 Agent Note](2026-07-06-approval-seam.md) 同一模式的另一侧。

-每次请求前都会根据当前模式与工作区根目录渲染沙箱策略；现有 `request/header` 会记录确切段落，因此无需切换叙述器或「上次告知」状态。批准策略保持独立：只有 `'never'` 被声明，因为自动拒绝在行为上与用户的「不」无法区分，其归属方继续保留自己的切换叙述。
+沙箱策略与批准策略会在每次请求前渲染为同一份运行时上下文快照中的有序贡献。循环会将完整快照记录为一条带来源的 `user/message`；`'ask'` 与 `'never'` 都会明确写入，因此两个归属方都无需切换叙述或「上次告知」状态。

 **可选的 UI 界面**是 `PermissionService`：一张部署定义的 preset 表，每个条目捆绑一个沙箱模式与一个批准策略。随附的 `workspace-write` 和 `danger-full-access` preset 写入两个领域 setter；preset 表之外的旋钮组合报告为 `custom`。UI 适配器可以把该表暴露为选择器。仅面向自动化的 ACP 传输层不公布任何配置选择器，也不挂载权限 preset 服务。

@@ -117,10 +117,10 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层

 ### 测试

- **单元测试：** 固定平台选择和 profile、失败关闭的 runner 分类、按调用的模式/根目录解析、按进程事实、升级验证和结果、权限 preset fold 和写入透传、以及叙述器合并。
+- **单元测试：** 固定平台选择和 profile、失败关闭的 runner 分类、按调用的模式/根目录解析、按进程事实、升级验证和结果、权限 preset fold 和写入透传、以及运行时上下文排序与具体化。
 - **Keyless 真实 runner：** 在提供方和 bash 消费方层面对 bwrap、Landlock 和 Seatbelt 执行真实文件系统效果测试；一个真实 Cordis 上下文通过已交付的 bash 和 fs 工具并发驱动两个项目会话，证明在自身根目录写入成功、在兄弟根目录写入被拒绝。Packed-install 覆盖率证明注册表 launcher 保持可执行。CI 拒绝静默全跳过。
 - **With-key：** 以只读模式启动真实 ACP 组合，让模型驱动的 bash 写入命中 runner 的拒绝标记，再通过已授权与被拒绝的 workspace-write 重试驱动 bridge 应答器和磁盘效果；不可用的凭证或 runner 自动跳过。
- **快照：** 固定当前策略段落和两个脚本化的 approval 分支。一个真实 ACP 示例场景把会话放在用户主目录下，同时让部署后备根目录指向 `/tmp`，然后固定 workspace-write 请求 header 与一次成功的、由部署选定的变更；这能区分会话根目录解析与进程后备值，而不依赖 runner 特定的拒绝文本。其他快照以无约束启动，使无关 fixture（测试前置数据）保持平台无关。
+- **快照：** 固定原子化的当前策略上下文和两个脚本化的 approval 分支。一个真实 ACP 示例场景把会话放在用户主目录下，同时让部署后备根目录指向 `/tmp`，然后固定 workspace-write 运行时上下文消息与一次成功的、由部署选定的变更；这能区分会话根目录解析与进程后备值，而不依赖 runner 特定的拒绝文本。其他快照以无约束启动，使无关 fixture（测试前置数据）保持平台无关。

 ## 延迟阶段

@@ -149,9 +149,9 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层
 - **按会话动态工具 schema**：否决。schema 设计上是注册表全局的（一套 assembly 词汇、固定 header 快照契约），按会话重新注册只能买到执行时严格放宽检查已保证的东西，代价是按会话的 schema 表面和每次切换的 header 变动。
 - **将重试硬匹配到先前的拒绝**：否决。命令字符串同一性脆弱（引号、`workdir`、env 前缀、作为失败阶段重试的管道）——要么误拒诚实的重试，要么被轻易满足；真正的边界是人看到命令 + 理由。仅在 `allow_always` 授权存储需要机器可检查的范围时才重新考虑。
 - **通用 `env/state` facts map 加拥有者服务**：否决。approval 和沙箱独立组合，因此任何一方的状态都不应拖入第三个包；单键 fold 各自是一个 `findLast`，拥有者服务自然消解；没有跨旋钮的不变式，因此原子多键补丁无收益。
- **通过 `agent/user-message` + 总线事件叙述**：否决。它预设了一个不存在的轮次入口 seam（真正的 seam 是 `agent/prompt-submit`），而步骤前检查点的位置使一个监听器能够同时服务合并的轮次入口通知和轮中即时性约束。
- **在提示词中常驻声明沙箱模式（并加切换叙述器）**：先行交付，随后根据线上证据移除：每次请求都带有 `Bash commands run under the "read-only" file sandbox.` 时，模型会拒绝尝试本可在被拒后升级的工作（首次人工会话的十二个轮次中有五个以零工具调用结束），使沙箱变成软锁死。拒绝标记会在相关时刻指出模式，升级字段则承载恢复路径；批准旋钮之所以保留声明，是因为自动拒绝在行为上与人类回答「否」无法区分。[当前策略决策](2026-07-30-current-sandbox-policy-context.md)取代了省略策略的决策；这项测量和因果观察仍是任何替代方案必须进行反证测试的依据。
- **用专门的簿记事件追踪「上次告知」**：否决。`request/header` fold 已记录模型看到的确切提示词；将封闭的候选句子解析回来替代了第二条簿记流——事件仅在它们本身即为存储时才需要。
+- **通过 `agent.inject()` 加总线事件逐次叙述切换**：否决。独立通知会暴露归属方顺序和中间组合，而一次组装过程可以在请求边界以原子方式具体化完整的当前状态。
+- **在稳定系统提示词中声明沙箱模式**：先行交付，随后根据线上证据移除：每次请求都带有 `Bash commands run under the "read-only" file sandbox.` 时，模型会拒绝尝试本可在被拒后升级的工作（首次人工会话的十二个轮次中有五个以零工具调用结束），使沙箱变成软锁死。拒绝标记会在相关时刻指出模式，升级字段则承载恢复路径。[当前策略决策](2026-07-30-current-sandbox-policy-context.md)取代了省略策略的决策；这项测量和因果观察仍是任何替代方案必须进行反证测试的依据。
+- **用专门的簿记事件追踪「上次告知」**：否决。最新一条带来源的运行时上下文 `user/message` 会记录模型看到的确切完整快照。根据当前归属方贡献具体化该快照，取代了第二条簿记流——事件仅在它们本身即为存储时才需要。
 - **相互独立的沙箱与批准选择器**：否决。一个部署定义的权限 preset 让两个策略旋钮对暴露运行时切换的 UI 客户端保持一致。

 ## 后果
@@ -160,12 +160,12 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层

 - 被拒绝的命令以 `sandbox_permissions` + `justification` 重试时，通过组合的应答器链提示用户；授权使该次调用在更宽模式下运行（结果事实如此报告），而其他所有调用保持各自的有效模式；每种非授权结果产生各自不同的错误文本且不执行任何内容。
 - 升级字段恰好在已挂载的执行器约束时存在；不严格宽于调用有效模式的请求以自身文本失败关闭且不提示任何人；没有 ApprovalService 的部署对升级调用失败关闭，对普通调用不影响。
- 系统提示词在由各自归属方派生的独立段落中分别声明沙箱策略与批准策略；整个交互——header、旋钮事件、批准通知、批准与结果——仅从会话日志即可重建，除两个旋钮事件外无额外事件类型。
- 一次 preset 选择只记录发生变化的旋钮值，而无操作的选择不记录任何内容；批准策略切换最多以一条合并通知叙述，已提交的沙箱切换由下一次调用的盖章兑现。
- 恢复的会话的覆盖直接生效，无需追赶状态；进程停止期间变更的默认值在会话的首个新请求前被叙述，归因于运维人员。
+- 一条带来源的运行时上下文消息会以原子方式声明完整的当前沙箱策略与批准策略；整个交互——上下文快照、header、旋钮事件、批准通知、批准与结果——仅从会话日志即可重建，除两个旋钮事件外没有策略簿记事件。
+- 一次 preset 选择只记录发生变化的旋钮值，而无操作的选择不记录任何内容；下一个请求会把两个当前值共同纳入一份原子快照，已提交的沙箱切换由下一次调用的盖章兑现。
+- 恢复会话的覆盖项会进入其首个新运行时上下文快照，无需追赶状态；进程停止期间变更的组合默认值也会出现在该快照中。
 - 两个并发会话永远看不到彼此的状态或通知。
 - 同一个 Cordis 上下文中的两个并发项目会话解析各自独立的工作区根目录；bash 和 fs 写入在调用方会话的 cwd 内成功，对其相邻会话的 cwd 则失败。
- `agent-loop` 未被触及——一切搭载 `systemPrompt.section`、`SessionEventMap` 合并、`agent.inject()`、`agent/step`、`agent/prompt-submit` 和由能力拥有的策略解析。
+- 策略归属仍通过 `systemPrompt.context`、`SessionEventMap` 合并和由能力归属方拥有的解析留在插件中；通用循环变更会将每个归属方的有序上下文具体化为一条带来源的消息。

 代价与已接受的限制：

@@ -178,9 +178,8 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层
 - **模型可能过度请求。** 在没有拒绝依据的情况下升级，或在 `workspace-write` 足够时选择 `danger-full-access`：描述引导且枚举强制阶梯，但人的提示词是实际门控；`approval/asked` 原因使过度请求可审计，且 `prepend` 策略应答器可以自动拒绝部署永远不想要的模式。
 - **公布的目标集是静态的，而有效模式是按会话的**（schema 是注册表全局的）——已处于最宽模式的会话仍被提供这些字段。构造上无害：执行时的严格放宽检查（而非枚举）是安全边界——非放宽请求以自身文本失败且不提示任何人。
 - **授权的升级不等于可工作的沙箱。** 不可用的后端即使对授权升级到约束模式也仍然失败关闭——在平台没有链或所有探测失败时于 `confine()` 阶段，在未探测的唯一 runner 拒绝时于执行阶段（归类为沙箱失败而非命令失败）——而授权的 `danger-full-access` 运行根本不触及提供方：此时授权（而非探测）是权威。
- **批准叙述器的重启基线解析提示词文本。** 封闭的候选句子由写入模块本身拥有，因此措辞变更是同一文件中写入器+解析器的协调编辑；header 早于该段落的会话静默采用当前策略而不发通知。
- **批准段落与沙箱段落都是动态提示词表面。** 策略切换会破坏该会话的提供方提示词前缀缓存；状态不变时仍保持字节稳定，且模型基于过时权限行动的风险高于这种有限的缓存失效。
- **模型可能持有过时的沙箱模式认知**（没有任何内容会宣布切换）。原始设计有意接受这一点：下一次尝试的标记或成功结果会纠正认知，而观察到的宣布失败模式——预防性拒绝——比一次浪费的重试更糟。[当前策略决策](2026-07-30-current-sandbox-policy-context.md)通过感知家族的请求段落取代了这项已接受限制，同时保留预防性拒绝证据作为其反证测试。
+- **运行时上下文历史仅追加。** 策略切换会在保留的历史之后追加一份用于取代先前快照的完整快照，从而保留稳定的系统与对话前缀；状态不变时不添加消息。
+- **旧策略快照仍保留在历史中。** 每份完整快照都会明确取代更早的运行时上下文快照，因此回放与压缩（compaction）只需保留最新具体化的消息。

 ## FAQ

@@ -191,8 +190,8 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层
 - **沙箱限制网络或进程可见性吗？** 不——`SandboxMode` 仅声称文件操作；bwrap profile 刻意不 unshare pid，没有后端声称网络。网络限制是否成为自己的旋钮留在 § seam 中开放。
 - **哪些工具实际在约束下运行？** 通过 `ctx.bash` 的 OS 子进程——bash 工具及传递性的钩子命令——再加上通过沙箱化 `ctx.fs` 提供方运行的文件系统工具（`read`/`write`/`edit`，见[跨工具族 fs 沙箱 Agent Note](2026-07-14-cross-family-fs-sandbox.md)）：bash 通过 OS runner 约束，fs 通过进程内路径围栏约束，二者都以同一个 `ctx.sandboxPolicy` 模式为键。web/todo 仍在进程内且不受限制（web 的唯一效果是网络，不在文件效果模式词汇内）。
 - **授权的升级会持久化吗？** 不会。授权由发起请求的确切前台或后台调用消费；每个相邻调用保留自己的有效模式。后续的后台拒绝通过 `task_output` 呈现，并且可以作为一次新的精确命令重试的依据。
- **运行时模式切换何时生效？** 一旦其会话事件提交，下一个请求段落与下一次能力解析都会折叠新模式。请求 header 会记录模型收到的内容，之后的任何拒绝都会在使用点命名同一策略。
- **重启后什么存活——如果运维人员在进程停止期间改了配置默认值呢？** 覆盖从会话日志回放（`effective = fold ?? config`），因此恢复的会话以零追赶机制保持其模式；离线漂移的默认值以与切换相同的方式改变行为（批准策略因被声明，还额外以运维人员/配置归因叙述）。
+- **运行时模式切换何时生效？** 一旦其会话事件提交，下一个运行时上下文快照与下一次能力解析都会折叠新模式。带来源的上下文消息会记录模型收到的内容，之后的任何拒绝都会在使用点命名同一策略。
+- **重启后什么存活——如果运维人员在进程停止期间改了配置默认值呢？** 覆盖从会话日志回放（`effective = fold ?? config`），因此恢复的会话以零追赶机制保持其模式；离线漂移的默认值会进入下一份完整运行时上下文快照。
 - **结果上的 `enforcement: 'partial'` 是什么意思？** 所选后端强制其内核 ABI 管控的子集——例如 ABI v3 之前的 Landlock 不管控路径 truncate——并以结构化方式如此声明而非拒绝主机；探测的报告行区分各种情况。bwrap 和 Seatbelt profile 构造上管控所有承诺的文件操作，因此始终报告 `full`。

 ## 先例
@@ -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 docs/architecture.md
-architecture.md: c6e14fac6436b2401509aaf8bb20ccaf29aeeafc
-architecture.zh.md: 2e85f25eb3f40f58c8ffbfa7691bb793638c8b37
+architecture.md: 461a1eee94be28ced65e320286bab98773f78337
+architecture.zh.md: 9dd3b4aed1b3bb0af14f7c53b7c8d51dfd75cd99
@@ -93,7 +93,8 @@ forever:
    STEP loop:
      agent/step
      drain injected context and steering (steering bypasses prompt-submit)
-      assemble system prompt and tool schemas
+      assemble system prompt and tools
+      materialize changed runtime context as sourced 'user/message'
      snapshot the derived messages (the reconstruction boundary)
      'step/start'
      agent/request (config only) -> prepare adapter defaults/provenance under turn signal -> log request/header -> llm/stream (frozen, registration-bound)
@@ -145,7 +146,7 @@ Each agent owns scoped `agent.ctx`; shared storage overlays its tool, prompt, an

 The session log is authoritative. `deriveMessages()` projects model history; raw `assistant/chunk` events preserve replay and UI fidelity. Fork, resume, transcript rendering, telemetry, and persistence derive from this stream.

-**Model-visible ⟺ logged**: messages at `step/start` plus the folded `request/header` reconstruct every request; the header also marks adapter-materialized defaults so the next proposal can discard them and resolve the selected route without losing explicit conversation settings. Package-owned `dsh-agent-loop/invariant` can assert reconstructability through `ctx.invariants` ([reconstructability](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)).
+**Model-visible ⟺ logged**: before `step/start`, the loop appends the full current runtime-context snapshot as a sourced `user/message`, then snapshots derived messages. Those messages and the folded `request/header` reconstruct each request. The header marks adapter defaults so later proposals discard them and re-resolve the route without losing explicit settings. `dsh-agent-loop/invariant` asserts this through `ctx.invariants` ([reconstructability](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)).

 Durability is a plugin concern. Backends eagerly drain synchronous `session/event` notifications. `session/flush` barriers precede each request and top-level tool dispatch, then follow `turn/end` before another queued turn or idle observation. `SessionPersistence` stores `SessionEvent` directly and metadata in `SessionHeader`; JSONL defaults to checksummed Zstandard, while SQLite shares the contract ([decision](../.agents/notes/implemented/bug-fix/2026-07-21-semantic-session-checkpoints.md)).

@@ -93,7 +93,8 @@ forever:
    STEP loop:
      agent/step
      drain injected context and steering (steering bypasses prompt-submit)
-      assemble system prompt and tool schemas
+      assemble system prompt and tools
+      materialize changed runtime context as sourced 'user/message'
      snapshot the derived messages (the reconstruction boundary)
      'step/start'
      agent/request (config only) -> prepare adapter defaults/provenance under turn signal -> log request/header -> llm/stream (frozen, registration-bound)
@@ -145,7 +146,7 @@ idle inject:

 会话日志是权威依据。`deriveMessages()` 投影出模型历史；原始 `assistant/chunk` 事件保证回放和 UI 保真。fork、恢复、transcript（文本记录）渲染、遥测和持久化均派生自该事件流。

-**模型可见 ⟺ 已记录**：`step/start` 时的消息与折叠后的 `request/header` 可以重建每个请求；该 header 还会标记适配器填入的默认值，使下一次提议可以丢弃这些值并解析所选路由，同时不丢失显式对话设置。该包的 `dsh-agent-loop/invariant` 可通过 `ctx.invariants` 断言可重建性（[可重建性](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)）。
+**模型可见 ⟺ 已记录**：在 `step/start` 之前，循环会将完整的当前运行时上下文快照作为一条带来源的 `user/message` 追加，随后对派生消息制作快照。这些消息与折叠后的 `request/header` 可以重建每个请求。该 header 会标记适配器默认值，使后续提议丢弃这些值并重新解析路由，同时不丢失显式设置。`dsh-agent-loop/invariant` 通过 `ctx.invariants` 断言这一点（[可重建性](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)）。

 持久性由插件负责。后端会尽快排空同步的 `session/event` 通知。`session/flush` 屏障位于每次请求与顶层工具分发之前，并在 `turn/end` 之后、处理另一个已排队轮次或观察到空闲状态之前执行。`SessionPersistence` 直接存储 `SessionEvent`，并将元数据存入 `SessionHeader`；JSONL 默认采用带校验和的 Zstandard，SQLite 遵循同一契约（[决策](../.agents/notes/implemented/bug-fix/2026-07-21-semantic-session-checkpoints.md)）。

@@ -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 packages/fs/fs-sandbox/README.md
-README.md: bce22feac8b6b4a31abc0cbfddd39681ad437062
-README.zh.md: 0bb0190f5a0506f2d10f82a5f03370b977472aee
+README.md: d6070f4971e7531e929e659b6b5ed476a672dc5d
+README.zh.md: c051b240163f229f7fbc583939c9f4da5095e9aa
@@ -30,11 +30,11 @@ The policy owner contributes capability-neutral `sandbox:policy` context. Indire

 #### Token effect

-The current-policy clause adds a small fixed prefix while this backend is mounted; a denial adds the bounded marker and escalation hint to conversation history.
+The current-policy clause adds a small runtime-context message while this backend is mounted; a denial adds the bounded marker and escalation hint to conversation history.

 #### KV Cache effect

-A standing-policy change updates the owner-rendered request prefix; operation results remain append-only.
+A standing-policy change appends an owner-rendered superseding runtime-context snapshot after retained history; operation results remain append-only.

 ## Known Limitations and Deferred Work

@@ -30,11 +30,11 @@

 #### Token 影响

-该后端挂载期间，当前策略条款会在前缀中增加少量固定内容；拒绝则会把有界标记和升级提示追加到对话历史。
+该后端挂载期间，当前策略条款会增加一条简短的运行时上下文消息；拒绝则会把有界标记和升级提示追加到对话历史。

 #### KV Cache 影响

-常驻策略发生变化时，归属方渲染的请求前缀会更新；操作结果保持仅追加。
+常驻策略发生变化时，会在保留的历史之后追加一份由归属方渲染、取代先前状态的运行时上下文快照；操作结果保持仅追加。

 ## 已知限制与暂缓事项

@@ -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 packages/pty/pty-local/README.md
-README.md: 4c200743732e62d8e76afd1a055943dac5f141b0
-README.zh.md: 0fbcc0eb8c0b5ddb89e62b4e748d1bd280b50b36
+README.md: ba05495318127b63b3d2a6a60ec743e1ff1c5821
+README.zh.md: 81987ea0685d761507b535b7ed6eefa0888fbd54
@@ -26,7 +26,7 @@ The current-policy clause is present while this backend is mounted. Retained PTY

 #### KV Cache effect

-A standing-policy change updates the owner-rendered request prefix; consumer results remain append-only.
+A standing-policy change appends an owner-rendered superseding runtime-context snapshot after retained history; consumer results remain append-only.

 ## Known Limitations and Deferred Work

@@ -26,7 +26,7 @@ Linux 的就绪检测结合以下机制：由前台状态验证的私有 bash

 #### KV Cache 影响

-常驻策略发生变化时，归属方渲染的请求前缀会更新；消费方结果保持仅追加。
+常驻策略发生变化时，会在保留的历史之后追加一份由归属方渲染、取代先前状态的运行时上下文快照；消费方结果保持仅追加。

 ## 已知限制与暂缓事项