Merge branch 'codex/invariant-package-registration-gate' into codex/package-invariant-checks

# Conflicts:
#	.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.i18n.yaml
#	.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.md
#	.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.zh.md
#	.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.i18n.yaml
#	docs/rfc/INDEX.md
#	packages/AGENTS.md

packages/hooks/README.md

@@ -1,6 +1,6 @@
 # hooks/ — hook bridges + shared protocol
 
-The hooks subsystem lets users extend the agent at lifecycle points the way Claude Code and Codex do — by pointing a bridge plugin at an existing `hooks.json` (or settings) so those external shell hooks run faithfully. The canonical extension surface itself is the harness's typed interception seams ([the interception-seams RFC](../../docs/rfc/implemented/feature/2026-06-30-interception-seams.md)); a "native hook" is just an ordinary cordis plugin on those seams. These packages are the **bridges** that translate the external shell-hook protocol onto that same surface, plus the shared wire-protocol library they build on.
+The hooks subsystem lets users extend the agent at lifecycle points the way Claude Code and Codex do — by pointing a bridge plugin at an existing `hooks.json` (or settings) so those external shell hooks run faithfully. The canonical extension surface itself is the harness's typed interception seams ([the interception-seams Agent Note](../../.agents/notes/implemented/feature/2026-06-30-interception-seams.md)); a "native hook" is just an ordinary cordis plugin on those seams. These packages are the **bridges** that translate the external shell-hook protocol onto that same surface, plus the shared wire-protocol library they build on.
 
 | Package | Role | Shape |
 |---|---|---|

packages/hooks/hook-protocol/README.md

@@ -27,13 +27,17 @@ Why a shared lib at all: Codex deliberately reimplements a *subset* of the Claud
 
 Declaration-merged into `SessionEventMap` (log-only, like `compact/*` — NOT a `SurfaceEventType`, no `surfaceOp`): `hook/invoked` (a hook command ran) and `hook/result` (its outcome, paired by `handlerId`, with `appendHookResult` owning the decision rule). Payloads and per-event JSDoc are in the generated [persistence log event catalog](../../../docs/persistence-catalog.md); `stderrSummary` is truncated to the record's `stderrSummaryMaxChars` (the bridge's config, reference default `DEFAULT_STDERR_SUMMARY_MAX_CHARS` = 500; omitted when empty).
 
-Like every event they must sit inside an open turn. The mid-turn points (`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`) fire inside the loop's open turn by construction; `SessionStart` gets no `hook/*` record (its injected `context/message` is the durable evidence) — see the hooks RFC.
+Like every event they must sit inside an open turn. The mid-turn points (`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`) fire inside the loop's open turn by construction; `SessionStart` gets no `hook/*` record (its injected `context/message` is the durable evidence) — see the hooks Agent Note.
 
 ## Model Experience
 
 Indirectly, through `dsh-hooks-claude` and `dsh-hooks-codex`, which can turn parsed hook output into prompt context, blocked outcomes, or continuation feedback.
 
+#### KV Cache effect
+
+No direct invalidation; the named consumer owns any request-prefix changes.
+
 ## Known Limitations and Deferred Work
 
-- **`HookOutput.updatedInput` is parsed but not honored** — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite RFC](../../../docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md)); a bridge logs + warns when a hook sets it. See `src/types.ts` for the full contracts.
+- **`HookOutput.updatedInput` is parsed but not honored** — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite Agent Note](../../../.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md)); a bridge logs + warns when a hook sets it. See `src/types.ts` for the full contracts.
 - **An invalid matcher regex matches nothing, silently** — `matchesMatcher` never throws; surfacing the error needs a diagnostic-returning variant or parse-time validation (`TODO(matcher-diagnostics)`).

packages/hooks/hook-protocol/src/types.ts

@@ -43,7 +43,7 @@ declare module '@deepseek-ai/dsh-session' {
 /**
  * The bridge that ran a hook — the CC bridge stamps `'claude'`, the Codex
  * bridge `'codex'`. A native plugin on the interception seams is not a bridge
- * and writes no `hook/*` provenance (see the interception-seams RFC).
+ * and writes no `hook/*` provenance (see the interception-seams Agent Note).
  */
 export type HookDialect = 'claude' | 'codex'
 
@@ -130,7 +130,7 @@ export interface HookOutput {
   systemMessage?: string
   /**
    * A tool-input rewrite a hook requested (CC `updatedInput`). PARSED but NOT
-   * honored — input rewrite is deferred (see the interception-seams RFC); a
+   * honored — input rewrite is deferred (see the interception-seams Agent Note); a
    * bridge logs + warns when this is present.
    */
   updatedInput?: Record<string, unknown>

packages/hooks/hooks-claude/README.md

@@ -2,7 +2,7 @@
 
 A cordis plugin that runs the supported command-hook subset of a user's existing **Claude Code** hook config (a `hooks.json`, or a settings file's `hooks` key) on the harness's canonical interception seams. It is the **CC dialect** half of the hooks subsystem: it owns the bridge's CC-shaped per-event stdin payloads, CC's env + `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` substitution, and the mapping from a hook's neutral outcome onto the harness's typed Decisions. The dialect-agnostic primitives (matcher, exit-code/stdout codec, `ctx.bash` execution, most-restrictive merge, the `hook/*` events) come from [`@deepseek-ai/dsh-hook-protocol`](../hook-protocol/README.md).
 
-A native cordis plugin could do everything this bridge does — more powerfully, with typed returns and no serialization boundary. **The bridge exists only as a compatibility path for the mapped CC command-hook subset**; anything bespoke should be a native plugin on the same seams (see [the interception-seams RFC](../../../docs/rfc/implemented/feature/2026-06-30-interception-seams.md)).
+A native cordis plugin could do everything this bridge does — more powerfully, with typed returns and no serialization boundary. **The bridge exists only as a compatibility path for the mapped CC command-hook subset**; anything bespoke should be a native plugin on the same seams (see [the interception-seams Agent Note](../../../.agents/notes/implemented/feature/2026-06-30-interception-seams.md)).
 
 ## Config
 
@@ -44,7 +44,7 @@ The hooks **themselves** run in the agent's session workspace: for the agent-sco
 
 The three emit points run detached — no seam awaits a `SessionStart`/`SubagentStart`/`SubagentStop` hook. Each run chain is tracked, and disposing the bridge aborts still-running hook processes, then drains the continuations before the dispose resolves (`createDetachedRuns` in `dsh-hook-protocol`).
 
-The matcher subject is the tool name (`PreToolUse`/`PostToolUse`), the session source (`SessionStart`), or a constant `agent_type` of `general-purpose` (`SubagentStart`/`SubagentStop` — the harness subagent seam carries no per-kind label, so the bridge reports Claude Code's own Task-tool default; a default/`*`/empty `agent_type` matcher fires, a specific-kind matcher does not); `UserPromptSubmit`/`Stop` ignore matchers. Multiple file-configured hooks on one point run **serially, in config order**, and fold most-restrictively (`deny > ask > allow`, see `dsh-hook-protocol`); serial keeps each hook's `hook/invoked`/`hook/result` pair adjacent in the log, and the fold is order-independent for the decision (see the RFC's "run serially, not concurrently" note).
+The matcher subject is the tool name (`PreToolUse`/`PostToolUse`), the session source (`SessionStart`), or a constant `agent_type` of `general-purpose` (`SubagentStart`/`SubagentStop` — the harness subagent seam carries no per-kind label, so the bridge reports Claude Code's own Task-tool default; a default/`*`/empty `agent_type` matcher fires, a specific-kind matcher does not); `UserPromptSubmit`/`Stop` ignore matchers. Multiple file-configured hooks on one point run **serially, in config order**, and fold most-restrictively (`deny > ask > allow`, see `dsh-hook-protocol`); serial keeps each hook's `hook/invoked`/`hook/result` pair adjacent in the log, and the fold is order-independent for the decision (see the Agent Note's "run serially, not concurrently" note).
 
 Every agent-scoped stdin payload carries `session_id` and string-shaped `transcript_path`. The bridge resolves the latter through `ctx.sessionPersistence.locate(session.header)` when available and otherwise sends `''`. Lookup does not create or flush the artifact, so a path can be absent before the first turn-end checkpoint or omit the current open turn.
 
@@ -56,22 +56,38 @@ Injected context carries an explicit `{ kind: 'plugin', plugin: 'hooks-claude' }
 
 ### Hook-provided context
 
-**What the model sees**: `SessionStart`, accepted prompt, post-tool, and live in-process subagent-start hooks can add source-attributed context messages; a blocking `Stop` hook adds its reason as next-step steering. Remote-child injection has no local target.
+#### What the model sees
 
-**Token effect**: No cost when hooks return no context. Hook text is data-dependent, logged, and resent in later conversation requests until compaction.
+`SessionStart`, accepted prompt, post-tool, and live in-process subagent-start hooks can add source-attributed context messages; a blocking `Stop` hook adds its reason as next-step steering. Remote-child injection has no local target.
+
+#### Token effect
+
+No cost when hooks return no context. Hook text is data-dependent, logged, and resent in later conversation requests until compaction.
+
+#### KV Cache effect
+
+Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries.
 
 ### Blocked prompt or tool outcome
 
-**What the model sees**: Provider-supplied reasons pass through verbatim. When absent, a blocked prompt uses exactly `blocked by UserPromptSubmit hook`, a denied tool becomes `Error: blocked by PreToolUse hook`, blocked post-tool feedback is exactly `blocked by PostToolUse hook`, and a blocking stop adds steering exactly `continue: blocked by Stop hook`. `systemMessage` and `updatedInput` are logged or warned but are not model-visible in this implementation.
+#### What the model sees
 
-**Token effect**: Blocking a prompt removes that prompt's request tokens; denial or feedback adds the retained fallback or provider text; forced continuation pays another full request.
+Provider-supplied reasons pass through verbatim. When absent, a blocked prompt uses exactly `blocked by UserPromptSubmit hook`, a denied tool becomes `Error: blocked by PreToolUse hook`, blocked post-tool feedback is exactly `blocked by PostToolUse hook`, and a blocking stop adds steering exactly `continue: blocked by Stop hook`. `systemMessage` and `updatedInput` are logged or warned but are not model-visible in this implementation.
+
+#### Token effect
+
+Blocking a prompt removes that prompt's request tokens; denial or feedback adds the retained fallback or provider text; forced continuation pays another full request.
+
+#### KV Cache effect
+
+A blocked prompt sends no request and invalidates nothing. Denial, feedback, and forced-continuation context append after the reusable prefix without rewriting it.
 
 ## Known Limitations and Deferred Work
 
 - **Unsupported hook events (23 of Claude Code's current 30):** `Setup`, `InstructionsLoaded`, `UserPromptExpansion`, `MessageDisplay`, `PermissionRequest`, `PostToolUseFailure`, `PostToolBatch`, `PermissionDenied`, `Notification`, `TaskCreated`, `TaskCompleted`, `StopFailure`, `TeammateIdle`, `ConfigChange`, `CwdChanged`, `FileChanged`, `WorktreeCreate`, `WorktreeRemove`, `PreCompact`, `PostCompact`, `SessionEnd`, `Elicitation`, and `ElicitationResult`. Config for these events is parsed but never dispatched. The comparison baseline is Claude Code's [official hook-event reference](https://code.claude.com/docs/en/hooks#hook-events).
 - **`SessionStart` is partial:** JSON `additionalContext` is consumed, but plain stdout context, `initialUserMessage`, `sessionTitle`, `watchPaths`, `reloadSkills`, and `CLAUDE_ENV_FILE` are unsupported. The hook runs detached, so context can miss the first request (`TODO(session-start-gating)`), and the payload omits current optional fields such as `model`, `agent_type`, and `session_title`.
 - **`UserPromptSubmit` is partial:** blocking and JSON `additionalContext` work, but plain stdout context, `sessionTitle`, and `suppressOriginalPrompt` are unsupported. Unless overridden, the bridge also uses its 600-second default instead of Claude Code's event-specific 30-second command timeout.
-- **`PreToolUse` is partial:** `deny` and `ask` decisions work; `allow` does not pre-approve, `defer` is unsupported, `additionalContext` is ignored, and `updatedInput` is logged + warned but not honored ([the pre-tool-input-rewrite RFC](../../../docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md)).
+- **`PreToolUse` is partial:** `deny` and `ask` decisions work; `allow` does not pre-approve, `defer` is unsupported, `additionalContext` is ignored, and `updatedInput` is logged + warned but not honored ([the pre-tool-input-rewrite Agent Note](../../../.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md)).
 - **`PostToolUse` is partial:** blocking feedback and JSON `additionalContext` work, but `updatedToolOutput` and `updatedMCPToolOutput` are unsupported and `tool_response` is flattened to text.
 - **`SubagentStart` and `SubagentStop` are partial:** both report a constant `agent_type` of `general-purpose` and use the child session id where Claude Code reports the parent session. Start context is best-effort and can only reach a live in-process child, while stop is observe-only and cannot block the subagent or feed it context. Start omits `transcript_path`; stop also omits `agent_transcript_path`, `last_assistant_message`, `background_tasks`, and `session_crons` and always reports `stop_hook_active: false`.
 - **`Stop` is partial:** blocking forces another model turn, but `stop_hook_active` is always `false`, `last_assistant_message`, `background_tasks`, and `session_crons` are omitted, and the consecutive-block cap is not implemented (`TODO(stop-loop-guard)`). An unconditionally blocking hook therefore force-continues every step unless it self-limits.

packages/hooks/hooks-claude/src/index.ts

@@ -5,7 +5,7 @@
  * mapping; shared execution and parsing live in `dsh-hook-protocol`.
  * `updatedInput` is logged and warned but not honored. Bespoke behavior should
  * use typed native plugins on the same seams; see the
- * [hook-bridges RFC](../../../../docs/rfc/implemented/feature/2026-06-30-hook-bridges.md).
+ * [hook-bridges Agent Note](../../../../.agents/notes/implemented/feature/2026-06-30-hook-bridges.md).
  * @module @deepseek-ai/dsh-hooks-claude
  */
 

packages/hooks/hooks-codex/README.md

@@ -10,7 +10,7 @@ This bridge implements a deliberate subset of Codex's current hook protocol:
 - **No Codex plugin env injection and no config-time placeholder substitution** (the command still receives the executor's environment and runs through its shell).
 - **No pre-tool approval or rewrite path** — a hook can block, but the bridge does not pre-approve or replace tool input.
 
-A native cordis plugin could do everything this bridge does, more powerfully; the bridge exists only as a compatibility path for the mapped Codex subset (see [the interception-seams RFC](../../../docs/rfc/implemented/feature/2026-06-30-interception-seams.md)).
+A native cordis plugin could do everything this bridge does, more powerfully; the bridge exists only as a compatibility path for the mapped Codex subset (see [the interception-seams Agent Note](../../../.agents/notes/implemented/feature/2026-06-30-interception-seams.md)).
 
 ## Config
 
@@ -60,15 +60,31 @@ Injected context carries an explicit `{ kind: 'plugin', plugin: 'hooks-codex' }`
 
 ### Hook-provided context
 
-**What the model sees**: `SessionStart`, accepted prompt, and post-tool hooks can add source-attributed context messages; a blocking `Stop` hook adds its reason as next-step steering.
+#### What the model sees
 
-**Token effect**: No cost when hooks return no context. Hook text is data-dependent, logged, and resent until compaction.
+`SessionStart`, accepted prompt, and post-tool hooks can add source-attributed context messages; a blocking `Stop` hook adds its reason as next-step steering.
+
+#### Token effect
+
+No cost when hooks return no context. Hook text is data-dependent, logged, and resent until compaction.
+
+#### KV Cache effect
+
+Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries.
 
 ### Blocked prompt or tool outcome
 
-**What the model sees**: Provider-supplied reasons pass through verbatim. When absent, a blocked prompt uses exactly `blocked by UserPromptSubmit hook`, a denied tool becomes `Error: blocked by PreToolUse hook`, blocked post-tool feedback is exactly `blocked by PostToolUse hook`, and a blocking stop adds steering exactly `continue: blocked by Stop hook`. Codex `systemMessage` is not surfaced.
+#### What the model sees
 
-**Token effect**: Blocking a prompt removes its request tokens; denial or feedback adds the retained fallback or provider text; forced continuation pays another full request.
+Provider-supplied reasons pass through verbatim. When absent, a blocked prompt uses exactly `blocked by UserPromptSubmit hook`, a denied tool becomes `Error: blocked by PreToolUse hook`, blocked post-tool feedback is exactly `blocked by PostToolUse hook`, and a blocking stop adds steering exactly `continue: blocked by Stop hook`. Codex `systemMessage` is not surfaced.
+
+#### Token effect
+
+Blocking a prompt removes its request tokens; denial or feedback adds the retained fallback or provider text; forced continuation pays another full request.
+
+#### KV Cache effect
+
+A blocked prompt sends no request and invalidates nothing. Denial, feedback, and forced-continuation context append after the reusable prefix without rewriting it.
 
 ## Known Limitations and Deferred Work
 

packages/hooks/hooks-codex/src/index.ts

@@ -5,7 +5,7 @@
  * or command substitution, and no pre-tool approval or rewrite path; only
  * blocking decisions are honored. Shared execution and parsing live in
  * `dsh-hook-protocol`; see the
- * [hook-bridges RFC](../../../../docs/rfc/implemented/feature/2026-06-30-hook-bridges.md).
+ * [hook-bridges Agent Note](../../../../.agents/notes/implemented/feature/2026-06-30-hook-bridges.md).
  * @module @deepseek-ai/dsh-hooks-codex
  */