chore(session): re-record the pairing and catalog fixture after the master merge

examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl

@@ -11,7 +11,7 @@
 {"type":"assistant/chunk","seq":9,"time":1783951000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":10,"time":1784449176722,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"1ac37046-d1c0-4ef6-9ea9-963e4b46d1cf"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}
 {"type":"tool/call","seq":11,"time":1784449176722,"data":{"turn":1,"step":1,"callId":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}}
-{"type":"tool/result","seq":12,"time":1784449176732,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"inspect-tools-api"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n    /**\n     * Register globally or in the calling agent scope. Scoped tools shadow\n     * globals; duplicates within one layer and the reserved `run_code` name fail.\n     * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n     * @returns the exact disposer that unregisters the tool.\n     */\n    register(definition: ToolDefinition): () => void\n    /**\n     * Restrict global tools for the calling agent scope. Empty filters, unknown\n     * names, scope-local names, and reserved transport names fail. Restrictions\n     * intersect; scoped registrations remain visible.\n     * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n     * @returns the exact disposer that lifts this restriction.\n     */\n    restrict(filter: ToolRestriction): () => void\n    /**\n     * Register a monotonic guard after the extensible `tools/pre-execute`\n     * waterfall. A plain-context guard applies globally; one registered through\n     * `agent.ctx` applies only to that agent. Any matching guard may deny by\n     * returning a reason, while no guard can force-allow a call another guard\n     * denied. The exact effect disposer is returned for ordered ownership and\n     * HMR cleanup.\n     * @param guard - synchronous check; a returned string denies the execution.\n     * @returns the exact disposer that unregisters the guard.\n     */\n    guard(guard: ToolGuard): () => void\n    /**\n     * Look up a tool as one scope sees it (scoped\n     * shadows global; a restricted-away global reads as absent). Presenters pass\n     * the calling agent so the rendered card matches the definition that\n     * actually executed.\n     * @param name - the tool name as registered.\n     * @param scope - the viewing scope (the agent); omitted = the global view.\n     * @returns the definition the scope resolves, or undefined when none is visible.\n     */\n    get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n    /**\n     * Project visible definitions onto the allowlisted model-facing schema fields,\n     * excluding execution and presentation callbacks.\n     * @param scope - the viewing scope (the agent); omitted = the global view.\n     * @returns one deep-cloned schema per visible tool.\n     */\n    schemas(scope?: ScopeKey): ToolSchema[]\n    /**\n     * Classify a pending call through the caller's visible tool definition. Only\n     * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n     * throwing classifiers are exclusive.\n     * @param exec - call name, parsed arguments, and optional agent scope.\n     * @returns the fail-closed scheduling mode.\n     */\n    executionMode(exec: ToolExecutionInput): ToolExecutionMode\n    /**\n     * Execute through pre-policy, guards, around-dispatch, post-policy,\n     * definition-owned content finalization, and final notification. Tool and\n     * listener failures resolve as materialized error results; an invisible tool\n     * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n     * snapshot final observers receive. Cancellation\n     * arriving after entry and before final result materialization skips a\n     * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n     * successful started outcome with `ABORTED`; already-started work is still\n     * drained and may retain a tool-owned structured error.\n     * @param exec - the typed same-process call input. The registry assigns its\n     *   correlation token before policy begins.\n     * @returns the materialized final result.\n     */\n    async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n    export interface Agent {\n        readonly id: SessionId;\n        readonly options: AgentOptions;\n        readonly session: Session;\n        readonly status: AgentStatus;\n        readonly acceptsNextStep: boolean;\n        readonly ctx: Context;\n        send(message: UserMessage, options: SendOptions): void;\n        updateInbox(id: InboxItemId, action: InboxAction): InboxActionResult;\n        cancel(cause: AgentCancelCause, options?: CancelOptions): void;\n        whenIdle(): Promise<void>;\n        followup(message: UserMessage): void;\n        steer(message: UserMessage): void;\n        inject(message: UserMessage): void;\n    }\n    export type AgentCancelCause = {\n        readonly kind: 'user';\n    } | {\n        readonly kind: 'parent';\n    };\n    export interface AgentOptions {\n        provider?: string;\n        model?: string;\n        maxTokens?: numberLine truncated
+{"type":"tool/result","seq":12,"time":1784449176732,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"inspect-tools-api"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n    /**\n     * Register globally or in the calling agent scope. Scoped tools shadow\n     * globals; duplicates within one layer and the reserved `run_code` name fail.\n     * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n     * @returns the exact disposer that unregisters the tool.\n     */\n    register(definition: ToolDefinition): () => void\n    /**\n     * Restrict global tools for the calling agent scope. Empty filters, unknown\n     * names, scope-local names, and reserved transport names fail. Restrictions\n     * intersect; scoped registrations remain visible.\n     * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n     * @returns the exact disposer that lifts this restriction.\n     */\n    restrict(filter: ToolRestriction): () => void\n    /**\n     * Register a monotonic guard after the extensible `tools/pre-execute`\n     * waterfall. A plain-context guard applies globally; one registered through\n     * `agent.ctx` applies only to that agent. Any matching guard may deny by\n     * returning a reason, while no guard can force-allow a call another guard\n     * denied. The exact effect disposer is returned for ordered ownership and\n     * HMR cleanup.\n     * @param guard - synchronous check; a returned string denies the execution.\n     * @returns the exact disposer that unregisters the guard.\n     */\n    guard(guard: ToolGuard): () => void\n    /**\n     * Look up a tool as one scope sees it (scoped\n     * shadows global; a restricted-away global reads as absent). Presenters pass\n     * the calling agent so the rendered card matches the definition that\n     * actually executed.\n     * @param name - the tool name as registered.\n     * @param scope - the viewing scope (the agent); omitted = the global view.\n     * @returns the definition the scope resolves, or undefined when none is visible.\n     */\n    get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n    /**\n     * Project visible definitions onto the allowlisted model-facing schema fields,\n     * excluding execution and presentation callbacks.\n     * @param scope - the viewing scope (the agent); omitted = the global view.\n     * @returns one deep-cloned schema per visible tool.\n     */\n    schemas(scope?: ScopeKey): ToolSchema[]\n    /**\n     * Classify a pending call through the caller's visible tool definition. Only\n     * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n     * throwing classifiers are exclusive.\n     * @param exec - call name, parsed arguments, and optional agent scope.\n     * @returns the fail-closed scheduling mode.\n     */\n    executionMode(exec: ToolExecutionInput): ToolExecutionMode\n    /**\n     * Execute through pre-policy, guards, around-dispatch, post-policy,\n     * definition-owned content finalization, and final notification. Tool and\n     * listener failures resolve as materialized error results; an invisible tool\n     * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n     * snapshot final observers receive. Cancellation\n     * arriving after entry and before final result materialization skips a\n     * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n     * successful started outcome with `ABORTED`; already-started work is still\n     * drained and may retain a tool-owned structured error.\n     * @param exec - the typed same-process call input. The registry assigns its\n     *   correlation token before policy begins.\n     * @returns the materialized final result.\n     */\n    async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n    export interface Agent {\n        readonly id: SessionId;\n        readonly options: AgentOptions;\n        readonly session: Session;\n        readonly status: AgentStatus;\n        readonly acceptsNextStep: boolean;\n        readonly ctx: Context;\n        send(message: UserMessage, options: SendOptions): void;\n        updateInbox(id: InboxItemId, action: InboxAction): InboxActionResult;\n        cancel(cause: AgentCancelCause, options?: CancelOptions): void;\n        whenIdle(): Promise<void>;\n        followup(message: UserMessage): void;\n        steer(message: UserMessage): void;\n        inject(message: UserMessage): void;\n    }\n    export type AgentCancelCause = {\n        readonly kind: 'user';\n    } | {\n        readonly kind: 'parent';\n    };\n    export interface AgentOptions {\n        provider?: string;\n        model?: string;\n        maxTokens?: numberLine truncated
 {"type":"step/end","seq":13,"time":1784449176732,"data":{"turn":1,"step":1}}
 {"type":"step/start","seq":14,"time":1784449176733,"data":{"turn":1,"step":2}}
 {"type":"assistant/chunk","seq":15,"time":1783951000015,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}

packages/host/apiproxy/README.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 packages/host/apiproxy/README.md
-README.md: 7129842a0cc89f5fa10c0bceec7cf0997ac71a99
-README.zh.md: 8765627236ea7af9e5cd3b7029133181ef499905
+README.md: c745dd6fb142b5b5a50b4593e3ce0223e2be6728
+README.zh.md: 7ddd7a37f7dd45f683a93601637c75b3f1bd8fd2