Merge remote-tracking branch 'origin/master' into codex/rfc-subagent-background-tasks

# Conflicts:
#	docs/architecture.md
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	docs/tool-catalog.md
#	packages/bash/tool-bash/tests/integration.spec.ts
#	packages/bash/tool-bash/tests/tools.spec.ts
#	packages/core/agent-core/tests/agent-core.spec.ts
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/src/index.ts
#	packages/core/agent/README.md
#	packages/core/agent/src/index.ts
#	packages/core/agent/tests/agent.spec.ts
#	packages/subagent/subagent/README.md
#	packages/subagent/subagent/src/index.ts
#	packages/subagent/tool-subagent/README.md
#	packages/subagent/tool-subagent/src/index.ts
#	pnpm-lock.yaml
#	scripts/doc-budgets.manifest.json

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

@@ -4,47 +4,49 @@ Status: implemented
 
 ## Problem
 
-Today the agent loop advertises every registered tool to the model as a native JSON-schema function definition. `ToolRegistry` contributes its schemas to the system-prompt assembly, the assembly's `tools` land on the wire (and in the logged request header), the model invokes one `tool-call` block per step, and the loop dispatches each call through `ctx.tools.execute()` **sequentially** (parallel tool execution is an explicit open TODO in `dsh-tools` and [docs/architecture.md](../../../architecture.md)), with **every** intermediate `tool-result` re-entering the model's context on the next request.
+In the registry's native presentation, the agent loop advertises every visible capability as a JSON-schema function definition. `ToolRegistry` contributes its schemas to the system-prompt assembly, the assembly's `tools` land on the wire (and in the logged request header), the model invokes one `tool-call` block per step, and the loop dispatches each call through `ctx.tools.execute()` **sequentially** (parallel tool execution is an explicit open TODO in `dsh-tools` and [docs/architecture.md](../../../architecture.md)), with **every** intermediate `tool-result` re-entering the model's context on the next request.
 
 For multi-step tool work this is token-heavy and serial. The model cannot compose tools — loop over a result set, branch on an intermediate value, fan out, post-process — without a full model round-trip per call, and each round-trip drags the entire intermediate result back into context whether the model needs it or not.
 
 Cloudflare's [Code Mode](https://blog.cloudflare.com/code-mode/) proposes an alternative grounded in a simple observation: LLMs are better at writing code than at emitting tool calls, because they have seen millions of lines of real code and comparatively few contrived tool-calling traces. Instead of one tool call per step, the model writes a TypeScript program against a generated API over the tools, the program executes in a sandboxed runtime, and the model curates what comes back — only what it prints or returns — instead of every intermediate result.
 
-An earlier draft of this RFC designed Code Mode as an add-on consumer plugin with zero core changes, deferring the execution substrate to a follow-up. Both constraints are dropped here, deliberately. First, the harness is pre-release and optimizes for the correct foundation over blast radius: tool presentation is the registry's own concern, and bolting a second presentation onto it from outside means transforming the registry's contribution after the fact — a waterfall listener whose correctness depends on listener ordering, which fights the [reconstructable-requests](../../implemented/architecture/2026-07-05-reconstructable-requests.md) design instead of riding it (that refactor removed request mutation from `agent/request`, the seam the old draft relied on). Second, the substrate question is answerable now: a Node `worker_threads` runtime gives real containment — separate isolate, empty environment, heap caps, and a `terminate()` that reliably stops a hot synchronous loop — where the old draft's `node:vm` stub had none of those, and it fits the harness's existing trust model (§Trust posture) without a hardening follow-up.
+Tool presentation belongs to the registry that owns tool visibility: implementing a second presentation as an after-the-fact waterfall transform would make correctness depend on listener order and fight [reconstructable requests](../../implemented/architecture/2026-07-05-reconstructable-requests.md). The execution substrate is also part of the foundation rather than a placeholder: Node `worker_threads` provides a separate isolate, an empty environment, heap caps, and termination of a hot synchronous loop, while fitting the harness's existing trust model (§Trust posture).
 
 ## Decision
 
 Three decisions, each elaborated in its own section below:
 
-1. **Code Mode is a first-class presentation mode of `ToolRegistry`** (`dsh-tools`), selected by a validated `mode` config: `'native'` (today's behavior, the default), `'code'` (the wire carries exactly one tool, `run_code`, plus a generated SDK `.d.ts` in the system prompt), or `'both'` (native schemas *and* `run_code` + SDK). The registry's existing tool-schema provider contributes whatever the mode dictates, so the wire tool list is shaped at its source — no interception, no listener-ordering caveats — and the logged request header records it for free.
-2. **Code execution is a capability seam** — a new group `packages/code-runtime/` with the interface package `@deepseek-ai/dsh-code-runtime` owning `ctx.codeRuntime` ([capability seams](../../implemented/architecture/2026-06-13-capability-seams.md); consumer = `dsh-tools`, with core-consumes-a-seam precedent in `agent-loop` → `dsh-llm`). The runtime knows nothing about tools: it is handed a program and named async bindings, runs the program, and reports `{ value, logs, error? }`. Language and substrate are backend properties, so a future Python or container backend is a new implementation package, not a redesign.
+1. **Code Mode is a first-class presentation mode of `ToolRegistry`** (`dsh-tools`), selected by a validated `mode` config: `'native'` (the default, contributing the visible capability schemas), `'code'` (the registry contributes only its reserved `run_code` transport plus a generated SDK `.d.ts` in the system prompt), or `'both'` (native schemas and the transport + SDK). The registry shapes its canonical contribution at the source; the cooperative prompt-assembly result remains authoritative, and the logged request header records exactly that returned presentation.
+2. **Code execution is a capability seam** — `packages/code-runtime/` contains the interface package `@deepseek-ai/dsh-code-runtime`, which owns `ctx.codeRuntime` ([capability seams](../../implemented/architecture/2026-06-13-capability-seams.md); consumer = `dsh-tools`, with core-consumes-a-seam precedent in `agent-loop` → `dsh-llm`). The runtime knows nothing about tools: it is handed a program and named async bindings, runs the program, and reports `{ value, logs, error? }`. Language and substrate are backend properties, so a future Python or container backend is another implementation package, not a redesign.
 3. **The shipped implementation is `@deepseek-ai/dsh-code-runtime-worker`**: one fresh Node worker thread per run, executing the model's TypeScript after type-strip, with bindings bridged over the message port, an empty environment, configurable heap/output/time caps, and hard termination. Its trust posture is bash-equivalent by design — no unsafe-acknowledgement flags — because the harness already ships `dsh-bash-local`, which executes arbitrary model-written shell commands with strictly *more* ambient authority.
 
 ### The registry owns the mode
 
 `ToolRegistry` gains a schemastery-validated config (`static Config`), its first: `mode: 'native' | 'code' | 'both'`, default `'native'`. A deployment flips it from `cordis.yml` (`tools: { mode: code }`) — no code edit, per the no-hardcoded-tunables convention.
 
-**Wire tool list = the registry's contribution.** The registry already feeds the assembly through `ctx.systemPrompt.tools(() => this.schemas())`; the provider becomes mode-aware: `'native'` contributes all schemas (unchanged), `'code'` contributes only `run_code`'s schema, `'both'` contributes all schemas plus `run_code`. Because [`PromptAssembly.tools` is the single source the loop's request header snapshots](../../../../packages/core/system-prompt/src/index.ts), the collapse is automatically logged and reconstructable — model-visible ⟺ logged holds with zero new mechanism. Scope of the guarantee, stated honestly: the mode governs the **registry's** contribution, and the registry is the only shipped schema source — but `systemPrompt.tools()` is a public multi-provider API and the `system-prompt/assemble` waterfall may transform the assembly, so a deployment that wires a second direct provider (or a mutating listener) owns what it adds, exactly as in native mode. Those are deliberate acts; what the design eliminates is the *accidental* leak the old draft worried about — a listener-ordering race around an after-the-fact collapse — and the shipped-configuration invariant (`'code'` ⇒ assembled tools exactly `[run_code]`) is pinned by tests and, like every request, by the logged header.
+**Wire tool list = the registry's contribution before cooperative assembly.** The registry feeds assembly through a mode-aware provider: `'native'` contributes every capability visible to that assembly scope, `'code'` contributes only `run_code`, and `'both'` contributes both. Because [`PromptAssembly.tools` is the single source the loop's request header snapshots](../../../../packages/core/system-prompt/src/index.ts), the final presentation is logged and reconstructable. The reserved transport is not a capability: it lives outside global/scoped registration and restriction layers, cannot be registered or shadowed there, and cannot be named by `ctx.tools.restrict()`. The mode governs this provider's input to assembly; other direct `systemPrompt.tools()` providers own their schemas, and the trusted assembly waterfall owns the returned wire list.
 
-**Interaction with `toolOrder`, stated up front:** a configured `systemPrompt.toolOrder` naming native tools rejects every assembly under `mode: 'code'` (those names are no longer contributed), by the existing fail-loud rule for unlisted names. This is correct behavior, not a bug: a deployment switching modes updates its order config or drops it.
+**Interaction with `toolOrder`, stated up front:** a configured `systemPrompt.toolOrder` naming native capabilities rejects every assembly under `mode: 'code'`, because those names are outside that mode's wire-validation universe. This is correct behavior, not a bug: a deployment using Code Mode updates its order config or drops it.
 
-**The SDK prompt section.** Under `'code'` and `'both'` the registry registers one lazy prompt section (`tools:sdk`, in the 100–199 tool-guidance order band) whose thunk regenerates, at each assembly, a TypeScript declaration of every registered tool except `run_code` itself, plus fixed usage instructions. The thunk reads the live store and emits tools in lexicographic name order, so its output is deterministic and stable across steps — an unchanged tool set produces byte-identical text (prefix-cache-friendly; a mid-session registration surfaces as one logged header delta, exactly like a native-mode tool change).
+**The SDK prompt section.** Under `'code'` and `'both'` the registry registers one lazy prompt section (`tools:sdk`, in the 100–199 tool-guidance order band) whose thunk regenerates, for each assembly scope, a TypeScript declaration of every visible end-capability tool plus fixed usage instructions. It uses the same visibility resolver as lookup and execution, so scoped grants and shadows appear while restricted globals disappear; the reserved `run_code` transport itself is excluded. The thunk emits tools in lexicographic name order, so an unchanged visible set produces byte-identical text.
+
+**Assembly ownership.** `run_code` and `tools:sdk` enter the trusted `system-prompt/assemble` waterfall as normal assembly inputs. A scoped `tools:sdk` section may shadow the global default before dispatch, and a listener may remove or replace either contribution. The waterfall's returned assembly is final, so whoever changes these inputs owns preserving a viable Code Mode protocol when the deployment expects Code Mode to remain usable; no restoration pass overrides deliberate composition.
 
 **Codegen.** A pure `jsonSchemaToTs(schema)` module inside `dsh-tools` (sibling of `json-schema.ts` — `schemas()` and the SDK are two projections of the same store) maps the JSON-Schema subset the `defineTool` DSL emits (object/string/number/boolean/array, `properties`, `required`, string `enum` → literal union, nested objects, array `items`, `description` → JSDoc) to a TS type literal. It is **total**: any construct outside that subset (`$ref`, `oneOf`/`anyOf`, `integer`, future MCP shapes, …) degrades to `unknown` without throwing. Because `ToolSchema.name` is an arbitrary string, the SDK is declared as one object constant — `declare const tools: { "some-mcp-tool"(args: …): Promise<string>; bash(args: …): Promise<string>; … }` — quoted keys make every name reachable with no sanitization or alias-collision logic. Typing is advisory (the runtime executes type-stripped JS); the instructions say so.
 
 ### The run_code tool and the dispatch bridge
 
-Under `'code'` and `'both'` the registry registers `run_code` in itself as an ordinary tool — one required parameter `{ code: string }` — so the unchanged loop dispatches it through the normal pipeline and `tools/pre-execute` / `tools/post-execute` gate it like any other call (a permission plugin can inspect the program text before it runs). 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` → 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. **Builds the bindings**: the bridge owns a **run-scoped `AbortController`** whose signal follows `exec.signal` (an outer cancel propagates in) and which the bridge itself fires the moment the run settles for any reason — completion, program exception, `computeMs`/`maxWallMs` expiry, worker exit. For every registered tool except `run_code`, the binding is an async function that (a) checks the run signal before and after (throwing stops the program — necessary because `ctx.tools.execute()` converts errors to `isError` data), (b) **JSON-normalizes the argument** — a `JSON.parse(JSON.stringify(args))` round-trip, rejecting that one call with a descriptive `Error` when the value does not survive (`BigInt`, circular structures) — because the seam's structured-clone boundary is wider than JSON while the session log accepts only JSON: normalizing BEFORE dispatch makes the dispatched form and the logged form the same JSON value by construction, so an executed sub-call can never fail at logging time, (c) awaits its turn on the **per-run serialization queue** (below), (d) calls `this.execute({ callId, name, arguments, agent: exec.agent, signal: runSignal })` with a deterministic sub-id `` CallId(`${exec.callId}:code:${n}`) `` — the run signal, not the bare outer one, so a budget expiry aborts an in-flight sub-tool (`bash-local` kills on its spec signal) instead of orphaning it, (e) appends a `tool/code-dispatch` session event, and (f) maps the result: success → the text-block contents joined as a `string` (non-text blocks become placeholders, an MVP limitation), `isError` → **the binding rejects** with an `Error` carrying the result text. Rejection is the deliberate model-facing contract — real code signals failure by throwing, `try/catch` and `Promise.all` short-circuiting behave as every model has seen them behave — where the old draft's `{ output, isError }` envelope made error handling a bespoke convention.
-2. **Runs the program**: `ctx.codeRuntime.run({ program: args.code, bindings: [{ global: 'tools', functions }], signal: exec.signal })`.
-3. **Surfaces the outcome — after reaching quiescence.** When `ctx.codeRuntime.run()` resolves, the bridge fires the run-scoped abort (cancelling any in-flight sub-dispatch and abandoning queued-unstarted ones), then **awaits the dispatch queue's drain before returning**, per the dispose-to-quiescence rule in [defensive patterns](../../../defensive-patterns.md): an aborted in-flight sub-call still settles and logs its `isError` `tool/code-dispatch` event *inside* the open turn, and nothing can append after `run_code` returns. A successful run then returns one text block — the captured console/stdout output followed by the rendered return value (if any) — plus a `meta` payload (capped logs, dispatch count) for presentation. A run with `result.error` throws a `CodeRunFailedError extends HarnessError` (`code: 'CODE_RUN_FAILED'`, message = the error kind and text plus captured logs so the model can self-correct); the registry's existing catch turns it into a structured `isError` result.
+1. **Builds the bindings**: the bridge owns a **run-scoped `AbortController`** whose signal follows `exec.signal` (an outer cancel propagates in) and which the bridge itself fires the moment the run settles for any reason — completion, program exception, `computeMs`/`maxWallMs` expiry, worker exit. For every visible capability tool, the binding is an async function that (a) checks the run signal before and after, (b) **JSON-normalizes the argument** — a `JSON.parse(JSON.stringify(args))` round-trip, rejecting that one call with a descriptive `Error` when the value does not survive (`BigInt`, circular structures) — because the seam's structured-clone boundary is wider than JSON while the session log accepts only JSON, (c) awaits its turn on the **per-run serialization queue** (below), (d) calls `this.execute({ callId, name, arguments, agent: exec.agent, parent: exec.token, signal: runSignal })` with a deterministic sub-id `` CallId(`${exec.callId}:code:${n}`) ``, (e) appends a `tool/code-dispatch` session event, and (f) maps the result: success → the text-block contents joined as a `string` (non-text blocks become placeholders), `isError` → **the binding rejects** with an `Error` carrying the result text. The child's readonly `parent` is only the outer execution's frozen, property-free token, so commit-style observers can correlate outcomes without receiving a mutation path into the live `run_code` wrapper. Every sub-call still traverses the full pipeline under its own immutable identity and registry-assigned token. The run signal, rather than the bare outer one, lets budget expiry abort an in-flight sub-tool instead of orphaning it. Rejection gives programs ordinary `try/catch` and `Promise.all` failure semantics rather than a bespoke result envelope.
+2. **Runs the program**: `ctx.codeRuntime.run({ program: args.code, bindings: [{ global: 'tools', functions }], signal: runController.signal })`. The runtime receives the run-scoped signal, not only the caller's outer signal, so any way the outer run settles also aborts work inside the runtime.
+3. **Surfaces the outcome — after reaching quiescence.** When `ctx.codeRuntime.run()` settles, whether by fulfillment or rejection, the bridge fires the run-scoped abort (cancelling any in-flight sub-dispatch and abandoning queued-unstarted ones), then **awaits the dispatch queue's drain before returning or propagating**, per the dispose-to-quiescence rule in [defensive patterns](../../../defensive-patterns.md): an aborted in-flight sub-call still settles and logs its `isError` `tool/code-dispatch` event *inside* the open turn, and nothing can append after `run_code` settles. A successful result then returns one text block — the captured console/stdout output followed by the rendered return value (if any) — plus a `meta` payload (capped logs, dispatch count) for presentation. A fulfilled run with `result.error` throws a `CodeRunFailedError extends HarnessError` (`code: 'CODE_RUN_FAILED'`, message = the error kind and text plus captured logs so the model can self-correct); a backend rejection propagates through the same registry error boundary. Both become structured `isError` tool results.
 
 **Sub-call `additionalContext` is suppressed, deliberately.** A `tools/post-execute` hook may attach `additionalContext` to a call; for loop-dispatched calls the loop buffers those and appends each as a `context/message` only after the step's `tool/result`s, preserving call/result adjacency. A sub-dispatch result's `additionalContext` has no such safe outlet from inside a running `run_code`: injecting immediately would land a `context/message` between the parent's `tool/call` and its `tool/result` (breaking the adjacency the buffering exists to protect), and `PostToolDecision.additionalContext` is singular where a program may produce many. The MVP therefore drops sub-call `additionalContext`, pinned by a test and stated in the hooks bridge's docs; the follow-up (a plural context channel or loop-level sub-dispatch buffering) is deferred until a real hook needs it through Code Mode.
 
-**Concurrency: serialized, enforced by the binding.** The bindings are async, so a model writing `Promise.all([tools.a(…), tools.b(…)])` starts both immediately — concurrent dispatch would be the *default*, while the tool contract still carries no concurrency-safety metadata (the open parallel-execution TODO). Each `run_code` invocation therefore owns a dispatch queue and every binding call chains onto it, so even `Promise.all` executes the underlying `ctx.tools.execute()` calls one at a time in submission order; when the run settles, queued-but-unstarted dispatches are abandoned. Lifting this per-tool once tools can declare themselves concurrency-safe is deferred work, same as before.
+**Concurrency: serialized, enforced by the binding.** The bindings are async, so a model writing `Promise.all([tools.a(…), tools.b(…)])` starts both immediately — concurrent dispatch would be the default, while the tool contract carries no concurrency-safety metadata (the open parallel-execution TODO). Each `run_code` invocation therefore owns a dispatch queue and every binding call chains onto it, so even `Promise.all` executes the underlying `ctx.tools.execute()` calls one at a time in submission order; when the run settles, queued-but-unstarted dispatches are abandoned. Lifting this per tool remains tied to tools declaring themselves concurrency-safe.
 
-**Presentation.** `run_code`'s render intent is decided here per the [render-intent RFC](../../implemented/architecture/2026-07-02-tool-render-intent-union.md): `presentCall` → a `generic` card, `kind: 'execute'`, title `Run code`, `rawInput` = the program text; `presentResult` → a `generic` card whose content is the captured output (from `meta`). Not a `terminal` card: that card's semantics are "a shell command in a working directory", which a program is not.
+**Presentation.** `run_code`'s render intent is decided here per the [render-intent RFC](../../implemented/architecture/2026-07-02-tool-render-intent-union.md): `presentCall` → a `generic` card, `kind: 'execute'`, title = the program text, `rawInput` = the same program text; `presentResult` → a `generic` card whose content is the captured output (from `meta`). The program is the title because ACP execute cards reliably render that field while some clients omit body and raw-input content. This is not a `terminal` card: that card's semantics are "a shell command in a working directory", which a program is not.
 
 ### Observability: `tool/code-dispatch`
 
@@ -56,12 +58,12 @@ Each sub-dispatch appends one session event, declared by `dsh-tools` via `Sessio
 
 - `CodeRunRequest = { program: string; bindings: CodeBindingNamespace[]; signal?: AbortSignal }`
 - `CodeBindingNamespace = { global: string; functions: Record<string, (args: unknown) => Promise<unknown>> }` — the runtime exposes each namespace as a global object of async functions inside the program; binding arguments and resolutions must be structured-cloneable (a runtime may cross a serialization boundary; ours does).
-- `CodeRunResult = { value?: unknown; logs: CodeLogEntry[]; error?: CodeRunFailure }` — an error is a field on a resolved result, never a rejection of `run()`.
+- `CodeRunResult = { value?: unknown; logs: CodeLogEntry[]; error?: CodeRunFailure }` — program execution outcomes, including exception, timeout, abort, and worker exit, resolve as the `error` field. `run()` may reject only for caller/seam misuse (for example a duplicate binding namespace); consumers still contain a non-conforming backend rejection at their own error boundary.
 - `CodeLogEntry = { source: 'console' | 'stdout' | 'stderr'; level?: 'log' | 'info' | 'warn' | 'error' | 'debug'; text: string }`
 - `CodeRunFailure = { kind: 'exception' | 'timeout' | 'abort' | 'worker-exit'; message: string }` — orthogonal outcomes reported independently per [defensive patterns](../../../defensive-patterns.md); a timed-out run is not an exception, an abort is not a timeout.
 - Two readonly backend descriptors, informational not gating: `language` (what the program must be written in — `'typescript'` for the shipped backend; a Python backend would say so, and pair with its own SDK generator on the presentation side) and `isolation` (`'worker-thread'` for the shipped backend; `'process'`, `'container'`, … for future ones). `dsh-tools` requires `language === 'typescript'` in the MVP — its codegen emits TS — and fails the assembly loudly otherwise, the same misconfiguration idiom as `toolOrder` violations (as when `mode` is non-native with no `ctx.codeRuntime` loaded at all).
 
-Per explicit-over-implicit at seams, the request spells out everything the runtime acts on; defaulting (timeouts, caps) is the implementation's validated config, never a hidden `??` inside `run()`. Consumption uses the loop's established optional-backend idiom: cordis has no optional injection — every `inject` entry gates activation — so a static `inject` on the registry would hold `ctx.tools` (and every tool plugin behind it) hostage to a code runtime existing even under `mode: 'native'`; instead the registry reads `ctx.get('codeRuntime')` at use time, exactly as `agent-loop` consumes `sessionPersistence`, with absence failing loud in the provider thunk as above. The seam split is justified by real planned divergence on both axes — substrate (worker now; container/microVM later) and language (the Python/AssemblyScript direction sketched in the earlier draft survives as future work) — not by speculation: `dsh-tools` consumes the interface today and tests against a trivial in-repo fake, exactly the interface/implementation/consumer shape of the bash template.
+Per explicit-over-implicit at seams, the request spells out everything the runtime acts on; defaulting (timeouts, caps) is the implementation's validated config, never a hidden `??` inside `run()`. Consumption uses the loop's optional-backend idiom: Cordis has no optional injection — every `inject` entry gates activation — so a static `inject` on the registry would hold `ctx.tools` (and every tool plugin behind it) hostage to a code runtime existing even under `mode: 'native'`; instead the registry reads `ctx.get('codeRuntime')` at use time, exactly as `agent-loop` consumes `sessionPersistence`, with absence failing loud in the provider thunk. The seam has concrete divergence on both axes: the worker-thread substrate can be replaced by a container or microVM implementation, and the TypeScript language contract can be paired with a language-specific SDK and runtime. `dsh-tools` consumes only the interface and tests against a trivial in-repo fake, exactly the interface/implementation/consumer shape of the bash template.
 
 ### The worker-thread runtime
 
@@ -76,7 +78,7 @@ Per explicit-over-implicit at seams, the request spells out everything the runti
 
 ### Trust posture
 
-The worker runtime is **containment, not a security boundary**, and the RFC says so without ceremony. Model code in the worker can reach Node globals — `fetch`, `process` (with an empty env), dynamic `import()` of built-ins — so a deliberately adversarial program has ambient authority comparable to what the harness's own `bash` tool already grants every model turn: `dsh-bash-local` runs arbitrary model-written commands with the host filesystem, network, and a scrubbed-but-populated environment. One asymmetry runs the other way and is stated plainly: `worker.terminate()` ends the thread, not OS processes a program may have spawned via `node:child_process` — weaker than `bash-local`'s process-group kill for direct children (equivalent for double-forked daemons, which survive both); the wall-clock ceiling bounds the worker itself, and orphan cleanup is the same deployment-level concern it already is for bash. Code Mode is gated where bash is gated — `tools/pre-execute`, where permission/sandbox plugins veto or approve the program before it runs — and adds containment bash does not have: empty env, heap caps, hard termination of the program itself, a separate isolate. The earlier draft's two-flag unsafe ceremony (`{ unsafe: true }` constructor + `allowUnsafeRuntime`) existed for a `node:vm` stub with *no* containment and is dropped with it; demanding scarier flags for the better-contained executor than for bash would be posture theater. A deployment that needs a hard boundary (untrusted multi-tenant input) needs it for bash too; that is a future `isolation: 'container'` backend, and the `isolation` descriptor exists so such a deployment can tell backends apart.
+The worker runtime is **containment, not a security boundary**. Model code in the worker can reach Node globals — `fetch`, `process` (with an empty env), dynamic `import()` of built-ins — so a deliberately adversarial program has ambient authority comparable to what the harness's own `bash` tool grants every model turn: `dsh-bash-local` runs arbitrary model-written commands with the host filesystem, network, and a scrubbed-but-populated environment. One asymmetry runs the other way: `worker.terminate()` ends the thread, not OS processes a program may have spawned via `node:child_process` — weaker than `bash-local`'s process-group kill for direct children (equivalent for double-forked daemons, which survive both); the wall-clock ceiling bounds the worker itself, and orphan cleanup is the same deployment-level concern it is for bash. Code Mode is gated where bash is gated — `tools/pre-execute`, where permission/sandbox plugins veto or approve the program — and adds containment bash does not have: empty env, heap caps, hard termination of the program itself, and a separate isolate. A `node:vm` executor with no containment would need explicit unsafe acknowledgement; imposing that ceremony on the better-contained worker while bash needs none would be posture theater. A deployment that needs a hard boundary (untrusted multi-tenant input) needs it for bash too; that is a future `isolation: 'container'` backend, and the `isolation` descriptor lets deployments distinguish backends.
 
 ### What the model sees
 
@@ -84,37 +86,37 @@ The `tools:sdk` section carries the `.d.ts` plus fixed instructions: the program
 
 ## Consequences
 
-The design shipped as four stacked changes — this RFC, the `dsh-code-runtime` interface package, the `dsh-code-runtime-worker` backend, and the `dsh-tools` integration — each gates-green with docs in the same change; review fixes landed on the change that introduced them and merged down.
+The design consists of the `dsh-code-runtime` interface package, the `dsh-code-runtime-worker` backend, and the `dsh-tools` presentation and dispatch integration.
 
-What exists now:
+Shipped surface:
 
 - **The seam**: `packages/code-runtime/` — `@deepseek-ai/dsh-code-runtime` (abstract `CodeRuntime`, the vocabulary above, `ctx.codeRuntime`) and `@deepseek-ai/dsh-code-runtime-worker` (the worker-thread backend, every cap a validated config field). Rows in the service map, capability-seams graph, config catalog, and cordis catalog.
-- **The registry surface**: `ToolRegistry`'s first config (`mode`), the mode-aware wire contribution, the `tools:sdk` section, `jsonSchemaToTs`/`renderToolsSdk` (exported), `run_code` + the dispatch bridge + `CodeRunFailedError`, and the `tool/code-dispatch` log event (declaration-merged into `SessionEventMap`, regenerated into the persistence catalog; `run_code` in the tool catalog).
-- **The composed surface**: the `tools` config forwards through `agent-core` and both app packages (`stdio-agent`, `acp-agent`); `demo:code-mode` boots each UI example's `code-mode.cordis.yml` overlay (the worker runtime + `mode: 'code'` over the base tree); the adding-a-tool cookbook states that a registered tool is reachable from programs for free, and the tool-pipeline doc shows sub-dispatches re-entering both waterfalls.
-- **Interactions inherited by deployments**: a `toolOrder` naming native tools rejects every assembly under `'code'` (update or drop the order config when switching modes); sub-call `additionalContext` is dropped by the bridge (a plural context channel is deferred until a real hook needs it through Code Mode); sub-dispatch stays serialized until tools can declare concurrency safety — the same metadata the native parallel-dispatch TODO waits on.
+- **The registry surface**: `ToolRegistry`'s `mode` config, mode-aware wire contribution, lazy `tools:sdk` section and reserved `run_code` transport, `jsonSchemaToTs`/`renderToolsSdk` (exported), the dispatch bridge and `CodeRunFailedError`, and the `tool/code-dispatch` log event (declaration-merged into `SessionEventMap`, regenerated into the persistence catalog; `run_code` in the tool catalog).
+- **The composed surface**: the `tools` config forwards through `agent-core` and both app packages (`stdio-agent`, `acp-agent`); `demo:code-mode` boots each UI example's `code-mode.cordis.yml` overlay (the worker runtime + `mode: 'code'` over the base tree); every program sub-dispatch resolves the same scoped capability view and re-enters the complete tool pipeline with an immutable link to its enclosing transport execution.
+- **Interactions inherited by deployments**: a `toolOrder` naming native tools rejects every assembly under `'code'` (update or drop the order config when switching modes); restrictions can hide end capabilities but cannot remove the registry-owned presentation transport, while assembly listeners may rewrite the final model-visible surface and own its protocol integrity; sub-call `additionalContext` is dropped by the bridge (a plural context channel is deferred until a real hook needs it through Code Mode); sub-dispatch stays serialized until tools can declare concurrency safety — the same metadata the native parallel-dispatch TODO waits on.
 
 ## Testing
 
 What the suites pin, per tier:
 
 - **Unit — worker runtime** (real workers, no mocks): output/value capture and log-source attribution; error kinds (exception incl. non-erasable syntax, abort, worker-exit under OOM); the two budgets from both sides (a hot loop behind an un-awaited pending dispatch dies at `computeMs` busy time; a program idling on a slow binding outlives `computeMs` and dies only at `maxWallMs`); binding-bridge hostility (junk/forged port traffic incl. non-object messages and forged `log`/`done` cap bypass attempts, unknown names, duplicate ids, post-settlement replies, `__proto__`/`constructor`/`toString` binding names); structured-clone fallback and cap truncation; `env` emptiness verified from inside a program; dispose-awaits-exit. A real-load-path e2e runs the BUILT package under plain `node` so the worker entry resolves both unbuilt (tsx) and built — the published-artifact guard from [docs/testing.md](../../../testing.md).
-- **Unit — registry integration**: the codegen table (DSL subset, quoted names, `unknown` degradation, byte-identical determinism); provider contribution per mode (`'native'` unchanged, `'code'` exactly `[run_code]`, `'both'` all + `run_code`); `toolOrder × mode` rejection; missing-runtime / wrong-language loud failures; serialization non-overlap (a probe tool records enter/exit under `Promise.all`); abort aborting the in-flight sub-dispatch and abandoning queued ones; binding rejection on `isError` and on JSON-unrepresentable arguments; `CodeRunFailedError` → structured `isError` carrying kind + logs; `tool/code-dispatch` payloads (JSON-normalized arguments identical to what dispatched); `deriveMessages()` ignoring the event; sub-call `additionalContext` suppression; HMR safety (disposing the registry removes the tool and the section).
+- **Unit — registry integration**: the codegen table (DSL subset, quoted names, `unknown` degradation, byte-identical determinism); provider contribution per mode (`'native'` capabilities, `'code'` exactly `[run_code]`, `'both'` capabilities + `run_code`); reserved-name, restriction, scoped shadowing, authoritative assembly transformation, and `toolOrder × mode` invariants; missing-runtime / wrong-language loud failures; full-pipeline and opaque parent-token behavior for sub-dispatches; serialization non-overlap (a probe tool records enter/exit under `Promise.all`); abort aborting the in-flight sub-dispatch and abandoning queued ones; binding rejection on `isError` and on JSON-unrepresentable arguments; `CodeRunFailedError` → structured `isError` carrying kind + logs; `tool/code-dispatch` payloads (JSON-normalized arguments identical to what dispatched); `deriveMessages()` ignoring the event; sub-call `additionalContext` suppression; HMR safety.
 - **e2e (with-key, self-skips)**: a real model under `mode: 'code'` composes two bash calls in one program (`examples/coding-agent/tests/code-mode.e2e.ts`) — every logged `request/header` carries exactly `[run_code]`, the dispatch events land under the parent call, the file the program wrote exists, and the final answer is the curated output.
 - **Snapshot (keyless replay)**: goldens for a `run_code` turn under `'code'` and `'both'` (`code-mode-turn`, `both-mode-turn`), each its own header-pinning class — the SDK section text, the collapsed header tool list, the dispatch events, and the result card are committed and replayed.
 
 ## Alternatives considered
 
-**An add-on consumer plugin, zero core changes (the previous draft of this RFC).** Rejected on both halves. The wire-collapse half aged out from under it: it targeted the `agent/request` waterfall, which [reconstructable requests](../../implemented/architecture/2026-07-05-reconstructable-requests.md) has since re-typed to call-config-only, and the surviving alternative — transforming the assembly a waterfall listener receives — is strictly worse than contributing the right list in the first place (transformation must undo `toolOrder` canonicalization it cannot see the config for, and its correctness depends on where it sits in a listener chain). The deeper reason is ownership: which tools the model is offered, in which representation, is the registry's single concern — `schemas()` for function calling and the SDK for Code Mode are two projections of one store, and splitting the second projection into a satellite package would preserve a boundary the domain does not have.
+**An add-on consumer plugin with zero core changes.** Rejected because `agent/request` is call-config-only under [reconstructable requests](../../implemented/architecture/2026-07-05-reconstructable-requests.md), while transforming an assembled tool list would have to undo `toolOrder` canonicalization without owning its config and would depend on listener order. Which tools the model is offered, and in which representation, is the registry's single concern: native schemas and the SDK are two projections of one visible store.
 
-**`node:vm` as the reference runtime, hardening deferred (also the previous draft).** Rejected: `node:vm` is not isolation (prototype-chain escapes reach the host realm), cannot interrupt a hot loop, and forced the draft into a two-flag unsafe ceremony plus a mandatory follow-up RFC. The worker thread delivers the missing properties now — separate isolate, empty env, `resourceLimits`, reliable `terminate()` (all verified by probe before this revision) — at bash-equivalent trust, so the reference implementation and the production one are the same package and the ceremony dissolves.
+**`node:vm` as the reference runtime, with hardening deferred.** Rejected: `node:vm` is not isolation (prototype-chain escapes reach the host realm) and cannot interrupt a hot loop. A worker thread provides a separate isolate, empty environment, `resourceLimits`, and reliable `terminate()` at bash-equivalent trust, so the reference and production implementation are one package without an unsafe-acknowledgement ceremony.
 
-**Result elision / summarization over native tool-calling.** Addresses only the context-bloat half of the problem: trimming old `tool-result`s (now cheap to add as a logged surface replace, per the reconstructable-requests consequences) still pays one model round-trip per call and cannot express loops, branches, or joins. Complementary, not competing; it can layer under Code Mode for residual native calls.
+**Result elision / summarization over native tool-calling.** Addresses only the context-bloat half of the problem: trimming old `tool-result`s is cheap to add as a logged surface replacement under reconstructable requests, but still pays one model round-trip per call and cannot express loops, branches, or joins. Complementary, not competing; it can layer under Code Mode for residual native calls.
 
 **Parallel native dispatch in the loop.** The other answer to round-trip cost; still valid future work (the open TODO), still blocked on concurrency-safety metadata, and still no composition — it parallelizes calls the model already decided on in one step. Code Mode's serialized-queue decision keeps the two compatible: when the metadata lands, both native parallel dispatch and per-tool binding parallelism unlock together.
 
 **Always-exclusive (Cloudflare-faithful, no mode).** Rejected for this SDK's primary consumer: a coding agent's bread-and-butter single calls (`bash`, `read`, `edit`) are already ideal as native calls, and forcing every edit through a program taxes the common case. The mode config keeps the faithful form (`'code'`) one line away without imposing it.
 
-**Per-tool visibility tiers (this tool native, that tool code-only).** Deferred again, knowingly: it needs per-tool metadata and a presentation split that `'native' | 'code' | 'both'` does not, and every learning it depends on (how models actually split usage under `'both'`) arrives only after this ships.
+**Per-tool visibility tiers (this tool native, that tool code-only).** Deferred: it needs per-tool metadata and a presentation split that `'native' | 'code' | 'both'` does not, and its design depends on evidence about how models split usage under `'both'`.
 
 **Sanitized identifier aliases in the SDK** (`my-tool` → `my_tool`, Cloudflare's approach). Rejected: quoted keys on a `declare const` make every name reachable with zero alias-collision logic; models handle `tools["my-tool"](…)` fine.
 

docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md

@@ -35,18 +35,18 @@ A new package group `packages/subagent/`:
 | `@deepseek-ai/dsh-subagent-mock` | support: a scripted provider for testing the seam through the real load path |
 | `@deepseek-ai/dsh-tool-subagent` | consumer: the model-facing `subagent` tool over `ctx.subagents` |
 
-### The primitive: `start → SubagentRun`
+### The primitive: async `start → SubagentRun`
 
-A provider exposes `start(request) → SubagentRun`. The run carries a `result` promise (the terminal `SubagentResult`), `cancel()`, and `dispose()`. The transport-neutral verb is **`start`**; "spawn" is reserved for the in-process `dsh-subagent-spawn` backend's identity, not the service verb. The service's `start(name, request)` resolves the named provider, validates capabilities, delegates, and emits `subagent/start` / `subagent/end` around the run.
+A provider exposes `start(request) → Promise<SubagentRun>`. Promise fulfillment is the publication/readiness and provider-to-caller ownership boundary: for an in-process backend the child is already published in `ctx.agents`, and for ACP the remote session already exists. `SubagentStartRequest.signal` is the single cancellation channel before and after readiness; `SubagentRun` carries the terminal `result` and a `dispose()` method that cancels remaining work and awaits quiescence. The transport-neutral verb is **`start`**; "spawn" is reserved for the in-process `dsh-subagent-spawn` backend's identity, not the service verb. A rejected start cleans provider-owned partial resources and emits neither subagent lifecycle event.
 
 ### Two kinds of optional capability, discovered two ways
 
-- **Start-time features** (`outputSchema`, `depthLimit`, `toolFilter`) ride on a static `provider.capabilities` descriptor. The service checks every requested one BEFORE delegating and **rejects loud** (`SubagentError('UNSUPPORTED_CAPABILITY')`) if the provider lacks it — never accepted-then-ignored. They must be checked before a run exists, which is why they cannot be runtime methods.
+- **Start-time features** (`outputSchema`, `depthLimit`, `toolFilter`, `persona`) ride on a static `provider.capabilities` descriptor. The service checks every requested one BEFORE delegating and **rejects loud** (`SubagentError('UNSUPPORTED_CAPABILITY')`) if the provider lacks it — never accepted-then-ignored. They must be checked before a run exists, which is why they cannot be runtime methods.
 - **Runtime features** (steering via `sendMessage`, follow-up via `resume`) are **optional methods** on `SubagentRun`. The method's presence IS the capability, and TypeScript narrowing is the discovery mechanism: a consumer cannot call an absent method without narrowing first, so there is no silent-degradation path and no separate flags object to keep in sync.
 
 ### Fork vs. fresh are separate backends, not a flag
 
-Rather than a `context: 'fresh' | 'fork'` request field, the distinction is the provider's identity: `dsh-subagent-spawn` (fresh, isolated, own system prompt) and `dsh-subagent-fork` (seeded from the parent's log) are two registered providers. You pick behavior by picking a provider — consistent with the registry being the selection mechanism. The fork backend seeds only a **balanced, completed-turn prefix** of the parent log: at tool-execute time the parent's turn is open (it holds the `assistant/message` and the dangling spawn `tool/call` with no `tool/result`), and seeding that raw prefix would give the child an unbalanced turn the [invariants](../../../../packages/support/invariants/src/index.ts) freeze-check rejects.
+Rather than a `context: 'fresh' | 'fork'` request field, the distinction is the provider's identity: `dsh-subagent-spawn` (fresh, isolated, own system prompt) and `dsh-subagent-fork` (seeded from the parent's log) are two registered providers. You pick behavior by picking a provider — consistent with the registry being the selection mechanism. The fork backend seeds only a **balanced, completed-turn prefix** of the parent log: at tool-execute time the parent's turn is open (it holds the `assistant/message` and the dangling spawn `tool/call` with no `tool/result`), and seeding that raw prefix would give the child an unbalanced turn that the [invariants](../../../../packages/support/invariants/src/index.ts) trace replay rejects.
 
 ### Child isolation and the parent log
 
@@ -54,7 +54,7 @@ Each subagent runs in its **own `Session`** (own id, `parentSession` lineage), p
 
 ### Synchronous collect (first cut)
 
-The `dsh-tool-subagent` consumer awaits `run.result` and returns the child's final output as the tool result, blocking the parent's turn until the child finishes. It does so inside a `try/finally` that always `dispose()`s the run (no leaked idle child/session on any path), bridges `exec.signal` to `run.cancel()`, and maps a non-`completed` stop reason to an `isError` result rather than returning partial output as success. Steering (`sendMessage`) is part of the contract but **intentionally unused** this cut.
+The `dsh-tool-subagent` consumer passes its execution signal into the start request, awaits the ready run's `result`, and returns the child's final output as the tool result, blocking the parent's turn until the child finishes. A `try/finally` always `dispose()`s the run, so no success, failure, or cancellation path leaks an idle child/session. A non-`completed` stop reason maps to an `isError` result rather than returning partial output as success. Steering (`sendMessage`) is part of the contract but intentionally unused in this consumer.
 
 ### Provider selection is config, not model-facing
 
@@ -66,8 +66,8 @@ The seam is tested through the real cordis Loader / export path, not a hand-buil
 
 ## Consequences
 
-- **Recursion.** Without a guard, an in-process child inherits the spawn tool and can spawn unboundedly. Depth-limit is an optional capability (the in-process backends enforce it; ACP advertises it off and rejects a `maxDepth` request); tool-filtering is likewise optional. Tool-filtering, when implemented, needs a `tools/pre-execute` deny in the child context — schema filtering alone is insufficient because a model can hallucinate a denied tool name.
-- **Blocking the parent turn.** Synchronous collect holds the parent's `runStep` open for the child's full duration. This is acceptable for the first cut; **background / poll / spill semantics are deferred to a future redesign that unifies long-running-tool handling across subagents AND bash** (a sub-agent and a long `bash` background task pose the same "the model started something slow, how does it collect later" problem, and should share one mechanism rather than each inventing its own).
+- **Recursion.** Without a bound, an in-process child can see the delegation tool and recurse. The in-process backends implement the optional absolute depth limit and scoped live-global `toolFilter`; ACP advertises both capabilities off and rejects such a request. The [subagent composition-controls RFC](2026-07-12-subagent-persona-tool-filter-and-depth.md) owns their exact semantics and security limits.
+- **Blocking the parent turn.** Foreground collection holds the parent's step open for the child's full duration. Background delegation uses the shared `ctx.tasks` runtime and generic `task_*` tools, the same collection mechanism as background bash; the subagent seam itself remains task-agnostic.
 - **Live progress.** This cut surfaces only lifecycle + final result; a per-chunk child→parent update stream is deferred with the background redesign.
 - **ACP client surface.** Proxying `fs`/`terminal` from the ACP child back to the parent (a shared-workspace mode) is future work; the first cut advertises neither, so the child self-serves in its own process.
 - **Snapshot coverage of nested agents.** The snapshot tier (`pnpm run test:snapshot`) replays a recorded session through `dsh-llm-replay`. It was built single-session: a single GLOBAL positional cursor (the Nth `llm/stream` call serves the Nth recorded entry) and a harness that harvested a single session log file. A subagent runs as a *second* agent with its own session log, so a parent→child scenario needed per-session-keyed replay plus harvest-all-logs and plural-session-id plumbing — self-contained infrastructure orthogonal to the backends, scheduled as a dedicated stacked follow-up rather than folded into the in-process-backends PR. That follow-up has **landed**: see [Per-session snapshot replay for nested agents](../../implemented/testing/2026-06-22-subagent-snapshot-replay.md). Replay now keys each call by its calling session (`GenerateOptions.sessionId`) and binds live sessions to recorded scripts by first-call order; the harness harvests every log; and two nested scenarios (`subagent-spawn`, `subagent-multi`) replay keyless in the default gate. In-process subagents remain covered by real-loop unit tests and a with-key e2e in addition to the snapshot tier.

docs/rfc/implemented/feature/2026-06-22-acp-subagent-backend.md

@@ -34,7 +34,7 @@ The child is a separate process, so it inherits an environment. Credential-shape
 
 Designed at every tier the backend touches, per the root AGENTS.md rule that a new capability shape names its coverage at every tier at plan time:
 
-- **Keyless unit/integration** (`subagent-acp.spec.ts`): spawns a scripted mock ACP server subprocess (`tests/mock-acp-server.ts`) and drives it through the real backend over real ACP stdio. Covers: the prompt round-trip + output accumulation; every StopReason mapping; cancellation via `run.cancel()` and via the request signal; the already-aborted-before-start case; the cancel-races-ahead-of-newSession case; a torn-pipe-after-cancel (child crashes on cancel) settling `aborted`; permission auto-answer under both policies (including the allow-policy-no-allow-option fallback); a non-message update consumed but not accumulated; a nonexistent-command spawn failure settling `error`; HMR provider cleanup; and the namespace export shape. 100% per-file coverage.
+- **Keyless unit/integration** (`subagent-acp.spec.ts`): spawns a scripted mock ACP server subprocess (`tests/mock-acp-server.ts`) and drives it through the real backend over real ACP stdio. Coverage includes the prompt round-trip and output accumulation; every StopReason mapping; cancellation through the required request signal and through disposal; already-aborted and cancel-races-ahead-of-newSession starts; a torn pipe after cancellation settling `aborted`; permission auto-answer under both policies; non-message updates; nonexistent-command startup failure with process reaping; provider HMR; and the namespace export shape.
 - **With-key e2e** (`subagent-acp.e2e.ts`): the harness drives ITSELF — the backend spawns the real `acp-agent` example process and a real model in that child answers a prompt (PONG) and does real file work (writes `proof.txt`, verified on disk). Self-skips without `DEEPSEEK_API_KEY`. This is the "talk to our own process" smoke and the out-of-process analogue of the in-process spawn e2e.
 - **Snapshot**: deferred as `TODO(acp-subagent-replay)`. An ACP child is a distinct replay shape — each child is its own PROCESS with its own single-agent replay (booted under `DSH_SNAPSHOT=replay` with its own sessions-root + fixture), unlike the in-process per-session keying that [the per-session replay RFC](../testing/2026-06-22-subagent-snapshot-replay.md) added. The keyless mock-server tests give deterministic coverage of the backend in the meantime; the snapshot follow-up would record the parent driving a real-but-replayed ACP child.
 

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

@@ -26,9 +26,11 @@ Each bridge maps the neutral `MergedHookOutcome` from the shared lib onto the se
 | `tools/pre-execute` | `deny`→`deny`; `ask`→`ask` | `block`→`deny` (no allow/ask) |
 | `tools/post-execute` | `deny`→`block`+feedback; context-only→delegate+fold | same |
 | `agent/turn-continuation` | blocking Stop → `continue` (reason = next-step steering) | same |
-| `subagent/start` (emit) | additionalContext → inject into the live child | — (not a Codex event) |
+| `subagent/start` (emit) | additionalContext → inject into a live in-process child; a remote child has no local injection target | — (not a Codex event) |
 | `subagent/end` (emit) | observe-only | — |
 
+The CC bridge's `ask` result is a real permission path, not a terminal bridge decision: `dsh-tools` resolves it through the optional [approval seam](2026-07-06-approval-seam.md). A composed ACP answerer prompts the owning editor session and `allowed-once` proceeds; without an ApprovalService or answerer, the call fails closed to `deny`.
+
 ### Context source is always the plugin (the mislabel guard)
 
 `agent.inject()` defaults a missing `MessageSource` to `{ kind: 'user' }` — which would record plugin-injected context as if the user had typed it. So every bridge `inject()` and every `HookContext` passes an explicit `{ kind: 'plugin', plugin: 'hooks-claude' | 'hooks-codex' }` source. A test asserts the resulting `context/message.source` is the plugin, never `user`.
@@ -52,11 +54,10 @@ Two different cwds, kept distinct on purpose. The hooks **themselves** run in th
 ## Deferred (faithful-but-degraded)
 
 - **Tool-input rewrite.** A CC/Codex `updatedInput` is logged + warned, not honored — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite RFC](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)), because the pre-execution args are read by `tool/call` audit + `assistant/message` history + ACP/tool-bash presentation, so an honest rewrite is a design unit, not a field.
-- **Stop loop-guard** (`TODO(stop-loop-guard)`). CC/Codex break an infinite force-continue with `stop_hook_active` (true once a Stop hook fired this run) plus a max-consecutive cap; both are deferred. Today `stop_hook_active` is always `false`, so a Stop hook that unconditionally blocks would force-continue every step — a hook author must self-limit until the guard lands.
-- **Permission `ask`** — deferred at landing, since serviced: the [approval seam](2026-07-06-approval-seam.md) resolves `ask` through `ctx.approval` (ACP prompts over `session/request_permission`), degrading to `deny` only where no approval service is composed.
+- **Stop loop-guard** (`TODO(stop-loop-guard)`). CC/Codex break an infinite force-continue with `stop_hook_active` (true once a Stop hook fired this run) plus a max-consecutive cap; both are deferred. `stop_hook_active` is always `false`, so a Stop hook that unconditionally blocks would force-continue every step — a hook author must self-limit until the guard lands.
 - **Hook `continue:false` (hard halt).** A hook can ask to halt the whole run (CC/Codex `continue:false`); the shared merge folds it into `MergedHookOutcome.stop`/`stopReason`, but no bridge acts on it (`TODO(hook-continue-false)`) — the interception seams have no "hard-halt the agent" primitive yet (a Decision blocks/steers a single point, not the run). Deferred with the loop-guard work; the halt request is recorded in the `hook/result` log, and the hook keeps its per-point effect (decision/context) meanwhile.
 - **Config discovery.** The path is explicit in `cordis.yml` and process-level (see above); the full multi-layer CC/Codex precedence walk, per-session project-local discovery, and the trust/hash model are not reimplemented (`TODO(per-session-hook-config)`).
-- **Session-start / subagent-start context is best-effort, not gated (`TODO(session-start-gating)`).** `agent/session-start` is a synchronous emit and the bridge runs its hook on a detached `.then`, so the injected `additionalContext` is not guaranteed to land before the first turn reaches the model — a slow hook can miss the first request (the context then arrives as a later injection). `subagent/start` is sharper: an in-process provider may have already queued the child's prompt before the listener runs, and a short-lived child can finish before the detached inject fires. Making startup context a gated/awaited primitive is a loop-level change deferred to the interception seams; today the contract is "injected as soon as the hook resolves", not "before the first request". The bridge tests do NOT wait on the injection where they assert the guaranteed-timing behavior, so they document the real (best-effort) timing rather than masking it.
+- **Session-start / subagent-start context is best-effort, not gated (`TODO(session-start-gating)`).** `agent/session-start` is a synchronous emit and the bridge runs its hook on a detached `.then`, so the injected `additionalContext` is not guaranteed to land before the first turn reaches the model — a slow hook can miss the first request (the context then arrives as a later injection). `subagent/start` is emitted only after child publication, so the bridge can capture the live in-process child synchronously, but the result driver may queue the prompt as that same readiness boundary resolves and a short-lived child can finish before the detached hook injects. Making startup context a gated/awaited primitive is a loop-level change deferred to the interception seams; the contract is "injected as soon as the hook resolves", not "before the first request". The bridge tests do NOT wait on the injection where they assert the guaranteed-timing behavior, so they document the real (best-effort) timing rather than masking it.
 
 ## Alternatives considered
 

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

@@ -6,21 +6,31 @@ Status: implemented
 
 The harness needs a hooks subsystem: users extend or gate the agent at lifecycle points the way Claude Code (CC) and Codex do. The key reframe driving this design is that **"native hooks" are not a package** — a native hook is just an ordinary Cordis plugin subscribing to the canonical lifecycle events. So the real product is a *powerful, well-typed canonical event surface*; the CC/Codex bridges (the `dsh-hooks-claude` / `dsh-hooks-codex` packages) are merely translators that map an external shell-hook protocol onto that same surface. Anything a bridge can do, a plain plugin can do directly — more powerfully (no serialization boundary, full `ctx`, typed returns).
 
-Before this change the interception surface was incomplete and inconsistent for that goal: there was no per-prompt seam (CC's `UserPromptSubmit`), no session-start signal (CC's `SessionStart`), the single `tools/execute` waterfall conflated the pre-gate and post-inspect phases (CC splits `PreToolUse`/`PostToolUse`), and `agent/turn-continuation` returned a bare `boolean` with no room for a force-continue *reason*. The [event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md) pinned down the three-domain rule and the typed-Decision idiom as the interception convention; this RFC builds the actual seams on top of it.
+The surface needs distinct contracts for per-prompt policy (CC's `UserPromptSubmit`), session-start observation (CC's `SessionStart`), pre-tool policy, around-dispatch control, post-tool transformation, final-result observation, and continuation with a model-facing reason. Conflating those phases gives plugins mutation channels they do not need and makes finality depend on listener ordering. The [event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md) supplies the three-domain rule and the typed-Decision idiom; this RFC applies them to the lifecycle seams.
 
 ## Decision
 
-Add/​reshape the interception seams so every one returns a small, seam-specific **typed Decision union**, and the set covers the hook points in scope (`session-start`, `prompt-submit`, `pre-tool`, `post-tool`, `stop`-via-continuation).
+The canonical surface separates transformable policy, around-dispatch control, and observe-only notification. Policy waterfalls return small seam-specific **typed Decision unions**; wrappers return normalized results; notifications receive immutable snapshots and cannot affect the outcome. The set covers the hook points in scope (`session-start`, `prompt-submit`, `pre-tool`, `post-tool`, `stop`-via-continuation) while leaving non-hook execution policy independently composable.
 
-**New `agent/*` events** (`dsh-agent`):
+**Agent events** (`dsh-agent`):
 - `agent/session-start(agent, source)` — emit, once before turn 1, carrying a `SessionStartSource` (`startup` for a fresh/forked create, `resume` for a reloaded persisted session; `clear`/`compact` reserved). A pure notification — it CANNOT block startup (a deliberate gap: a bridge logs/injects, it does not gate startup). A listener seeds context via `agent.inject()`.
 - `agent/prompt-submit(agent, content, source, next) → PromptDecision` — waterfall, fired per drained queued message inside the open turn, before the `user/message` append. `allow` (optionally rewriting the prompt `content` or attaching `additionalContext`) or `block` (dropping the prompt; the loop appends a durable `prompt/blocked` in its place — see the dispatch note below).
 
-**Reshaped** `agent/turn-continuation` from `(…, defaultDecision: boolean) → boolean` to `(…, defaultDecision: ContinuationDecision) → ContinuationDecision`. A `{action:'continue', reason?}` may carry model-facing context recorded as next-step steering in the same turn — the typed twin of the existing `/goal` step-end-steer pattern.
+**`agent/turn-continuation`** receives and returns a `ContinuationDecision`. A `{action:'continue', reason?}` may carry model-facing context recorded as next-step steering in the same turn — the typed twin of the `/goal` step-end-steer pattern.
 
-**Split** the single `tools/execute` waterfall into `tools/pre-execute` (→ `PreToolDecision` allow/deny/ask gate) and `tools/post-execute` (→ `PostToolDecision` accept/block, optionally replacing content or attaching `additionalContext`). Core dispatch sits between them as plain code inside `ToolRegistry.execute`'s outer try/catch, and the tool body keeps its own inner try/catch so a thrown tool still becomes an `isError` result that `post-execute` listeners can inspect.
+### The tool pipeline gives each phase one kind of authority
 
-**New `TurnEndReason` variant** `rejected` (`dsh-session`): a turn whose entire prompt batch was blocked by `prompt-submit`.
+Every call follows one ordered pipeline: `tools/pre-execute` → monotonic guards → `tools/execute` → core dispatch → `tools/post-execute` → `tools/result`. The registry reads each caller-owned input field once, materializes `arguments` as detached lossless JSON in one recursive pass, and snapshots `ToolExecutionInput` into a pipeline execution with its own opaque token. Identity fields and deeply frozen arguments are immutable for the whole pipeline, and a nested call's `parent` contains only the enclosing execution's token rather than its live object. Optional `signal` is the only operational field an around-dispatch wrapper may add, replace, or remove, and the complete object freezes before final observers run. This identity contract prevents a policy listener from silently changing what the log, UI, and tool body believe 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.
+- **`ctx.tools.guard()`** installs synchronous scope-aware policy after the whole pre-execute waterfall. A guard may deny or abstain, never force-allow, so listener ordering cannot resurrect an operation that a final invariant forbids.
+- **`tools/execute`** is the around-dispatch waterfall for timeout, retry, and metrics plugins. A wrapper delegates to core dispatch with `next()`, may add, replace, or remove only `exec.signal` before doing so, and receives the already-normalized result of a thrown or unknown tool; returning its own valid result short-circuits dispatch.
+- **`tools/post-execute`** is the inspect/transform waterfall. Its `PostToolDecision` accepts, blocks with feedback, optionally replaces content, or attaches `additionalContext`; in-place mutation of the result is not a transform channel, because the registry rebuilds the outcome from a protected snapshot plus the returned decision.
+- **`tools/result`** is the synchronous contained notification after every transform, lossless-JSON materialization, and the outer error boundary. It receives the same frozen execution identity and an immutable snapshot of the authoritative result; observer failures are contained per listener and cannot change or reject `ToolRegistry.execute()`'s returned outcome.
+
+Core dispatch and the tool body sit inside normalization boundaries, so tool, listener, malformed-result, non-JSON result, and identity-shape failures resolve as JSON-safe `isError` results rather than escaping the turn. A post-execute listener can therefore inspect a thrown tool, and a final observer sees exactly what the caller receives and the session log can persist.
+
+**`TurnEndReason.rejected`** (`dsh-session`): a turn whose entire prompt batch was blocked by `prompt-submit`.
 
 ### Three load-bearing loop decisions
 
@@ -30,13 +40,13 @@ Add/​reshape the interception seams so every one returns a small, seam-specifi
 
 3. **A forced `continue` `reason` is enqueued through the steering channel**, so the next step's top-of-loop drain records it as steering for the continued turn — next-*step* steering within the SAME turn, not a next-*turn* prompt (matching the existing `hasSteering` force-continue override).
 
-### Pre-tool INPUT rewrite is DEFERRED (the over-reach signal)
+### Pre-tool input rewrite is a separate consistency decision
 
-`PreToolDecision` is allow/deny/ask only — **no `arguments` rewrite**. Output replacement (`PostToolDecision.accept.content`) is safe because `tool/result` is logged AFTER execution (one source of truth). Input rewrite is NOT safe today: `assistant/message` (the model-history source) and `tool/call` (the audit record) are both logged BEFORE execution, and live consumers READ `tool/call.arguments` for presentation (the ACP bridge remembers them for `presentResult`; `dsh-tool-bash` derives the title/cwd/terminal-vs-background from them). A rewrite that changed only execution would make the UI show one command while another RAN. Designing that consistently (rewriting the audit + history + presentation as one unit) is a real consistency-design problem CC itself warns is racy — so it gets its own [proposed RFC](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md), and `TODO(pre-tool-input-rewrite)` anchors it at the loop's pre-execute call site. This does not regress any production consumer (no production `tools/execute` listener mutated `exec.arguments`). The low-level capability to mutate `exec` in a `pre-execute` listener still exists (unadvertised — a test shim uses it to thread a generated id), but it is not a first-class advertised contract.
+`PreToolDecision` is allow/deny/ask only — **no `arguments` rewrite**. Output replacement is safe because `tool/result` is logged after execution from the final result. Input rewrite is different: `assistant/message` (model history) and `tool/call` (the audit record) are logged before `ToolRegistry.execute()`, while ACP and tool presentation read those arguments. The registry therefore seals the materialized arguments before `tools/pre-execute`; no listener or test shim can mutate them in place. An honest rewrite must update history, audit, presentation, and execution as one unit before that identity is created, which belongs to the separate [pre-tool input-rewrite proposal](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md) and its loop-side `TODO(pre-tool-input-rewrite)`.
 
-### What this PR does NOT do
+### Boundaries
 
-It does **not** declare `hook/*` SessionEvents (the durable hook-invocation log) — those belong to the `dsh-hook-protocol` library, because a native plugin can already use the typed Decisions without a durable hook log. A worked native-plugin example/test in this PR (`packages/core/agent-loop/tests/interception.spec.ts`) proves all the seams compose end-to-end through the REAL loop with NO `hook/*` involved — the concrete proof that "native hooks are just a plugin". Compaction (`PreCompact`/`PostCompact`), the Notification hook, Codex `PermissionRequest`, and the Stop loop-guard remain deferred; the permission/`ask` system has since landed as the [approval seam](2026-07-06-approval-seam.md), whose `ctx.approval` services the `ask` this PR shipped degraded to deny.
+The seam package does **not** declare `hook/*` session events (the durable hook-invocation log); those belong to `dsh-hook-protocol`, because a native plugin uses typed decisions without an external hook log. The native-plugin integration test (`packages/core/agent-loop/tests/interception.spec.ts`) composes the seams through the real loop with no `hook/*` protocol. Compaction (`PreCompact`/`PostCompact`), Notification, and Codex `PermissionRequest` remain outside this decision. The [approval seam](2026-07-06-approval-seam.md) resolves `ask` decisions through `ctx.approval`, while terminal monotonic stopping is owned separately by `agent/turn-stop`.
 
 ## Alternatives considered
 
@@ -45,4 +55,4 @@ It does **not** declare `hook/*` SessionEvents (the durable hook-invocation log)
 
 ## Consequences
 
-The canonical interception surface is now complete and uniformly typed: a native plugin returns typed decisions directly, and a CC/Codex bridge maps its protocol fields onto the same unions. The loop gained four firing points (session-start emit, prompt-submit waterfall, the post-tool context buffer, the continuation reshape) and the `dsh-tools` registry runs a two-waterfall pipeline; both are documented in [architecture.md](../../../architecture.md) and the package READMEs, and the decision types in [core-data-structures](../../../core-data-structures/core.md#interception-decisions) + [tools.md](../../../core-data-structures/tools.md). All existing `tools/execute` and `turn-continuation` listeners (tests, docs) migrated to the new seams. The ACP bridge maps the new `rejected` reason to `cancelled` (its codec). A pure internal change with no editor-visible transcript shift for the existing scenarios — the new behavior only fires when a hook is registered — so the snapshot goldens are unchanged; a hook-driven snapshot scenario lands with the `dsh-hooks-claude` bridge, which is what makes a hook observable end-to-end through ACP.
+The canonical interception surface is uniformly typed without giving every extension the same power: hooks return decisions, execution wrappers wrap, terminal guards only deny, and final observers only observe. The loop owns session-start, prompt-submit, post-tool context buffering, and continuation; `dsh-tools` owns identity sealing and the five-phase execution pipeline. Their contracts are documented in [architecture.md](../../../architecture.md), package READMEs, [core interception decisions](../../../core-data-structures/core.md#interception-decisions), and [tool structures](../../../core-data-structures/tools.md). The ACP bridge maps `rejected` turns to its `cancelled` codec value, while hook-driven snapshots verify the observable bridge behavior end to end.

docs/rfc/implemented/feature/2026-06-30-subagent-observe-enrich.md

@@ -6,13 +6,13 @@ Status: implemented
 
 The hooks subsystem ([interception seams RFC](2026-06-30-interception-seams.md)) lets a plugin observe and gate the agent at lifecycle points. Claude Code and Codex both expose **SubagentStart / SubagentStop** hooks, and CC's carry the subagent's final message. The harness already emits `subagent/start` and `subagent/end` lifecycle events ([the subagent capability-seam](2026-06-21-subagent-capability-seam.md)), but their payloads were minimal (`provider`, `id`, and on end `stopReason`) — not enough for a hooks bridge to report WHAT a subagent produced without separately reaching for the live run.
 
-This RFC enriches the end payload. It is deliberately **observe-only**: no control-flow change, no waterfall, no `start()` restructure. A run-affecting subagent-stop decision (continuation, injection that changes the run) is a separate, larger redesign and stays out of scope.
+This RFC enriches the end payload. It is deliberately **observe-only**: no control-flow change and no waterfall. A run-affecting subagent-stop decision (continuation, injection that changes the run) is a separate, larger redesign and stays out of scope.
 
 ## Decision
 
-**Add `lastAssistantMessage` — the child's final output — to `SubagentRunEndInfo`.** On the settle path it is a DEEP CLONE of `SubagentResult.output` (so an observer sees WHAT the subagent produced without holding the run). On the REJECT path (an infrastructure fault where no `SubagentResult` was produced — the seam only knows `stopReason: 'error'`) it is absent. The clone is load-bearing for observe-only: the `subagent/end` emit fires from a detached `.then` registered *before* `start()` returns, i.e. before the caller's own `await run.result` continuation — handing listeners the same array reference would let a mutating listener corrupt the caller's `SubagentResult.output`. `structuredClone` makes the event a read-only view (a regression test mutates the event's array and asserts the caller's result is untouched); a clone failure is contained (logged, the event still fires without `lastAssistantMessage`) rather than becoming an unhandled rejection on the detached `.then`.
+**Add `lastAssistantMessage` — the child's final output — to `SubagentRunEndInfo`.** On the settle path it is the readonly typed `SubagentResult.output`, so an observer sees what the child produced without holding the run. On an infrastructure rejection where no `SubagentResult` exists, it is absent and the event reports `stopReason: 'error'`. Providers and listeners are trusted same-process collaborators and honor the borrowed immutable payload contract.
 
-Both events stay plain **`emit`s**. `subagent/end` fires from a detached `.then` on `run.result` and awaits no listener, so it is genuinely observe-only by construction — a `subagent/start` listener can still reach the live child via `ctx.agents.get(info.id)` and `inject()` into it; a `subagent/end` listener can only observe (the run has settled). Per-listener containment (already in place) keeps one bad subscriber from stranding a live run or surfacing as an unhandled rejection on the detached settle hook.
+Both events stay plain **`emit`s**. Async `SubagentService.start()` attaches result observation to the ready provider run, emits `subagent/start`, and then returns the run; an in-process listener can therefore reach the published child via `ctx.agents.get(info.id)`, while a remote provider need not have a local registry entry. A rejected provider start emits neither event. The callbacks remain observe-only and per-listener containment keeps one bad subscriber from stranding a live run or starving later listeners.
 
 ## Alternatives considered
 

docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md

@@ -24,7 +24,9 @@ One deliberate strictness DIVERGENCE from CC: hook misuse — unknown or deferre
 
 **Trust premise (governs every engine decision below)**: workflow scripts are MODEL-WRITTEN — the same trust level as the model's existing bash access — so the engine defends against BUGGY scripts, never hostile ones. In scope: `result` never rejects, no unhandled rejections from dropped hook promises, loud rejection of values JSON cannot carry, fatal-vs-null hook discipline, cancellation that always frees the caller. Out of scope, deliberately: adversarial values (throwing/spinning accessors, proxies with hostile traps, prototype forgery, `prepareStackTrace` hijack) AND Node-API escape from the script's context — the vm context shares object machinery with its surrounding realm, so a script can reach the `Function` constructor (`globalThis.constructor.constructor`) and from it `process` and every Node builtin; the absent globals are API surface, not containment, and a worker thread is NOT a security boundary (an escapee holds process-wide privileges — Node's permission model is per-process). Worker-side code MAY run script code while reading script values, and that is accepted: a synchronous spin costs the script its OWN thread (terminated at the post-cancel grace), never the host loop, so containing error VALUES would be cost without a threat model. Genuine sandboxing (isolated-vm, a separate process) remains an engine swap behind the seam, not incremental defenses here.
 
-**Why node:worker_threads**: one run = one worker thread, no pooling — a run is heavyweight (many children), so thread spin-up (~tens of ms) is noise. The script runs in a vm context INSIDE the worker, keeping the script-visible surface exactly the hook contract above (a bare worker realm would leak `setTimeout`/`fetch`/`process` as accidental API), and every `agent()` bridges to `ctx.subagents` by message-port RPC — children are I/O-bound LLM loops and stay on the host loop; the thread isolates the SCRIPT, the only part that can spin. What the thread buys: `start()` never blocks the host (an in-process engine runs the initial synchronous slice inline and cannot kill a spin past the first await — it could only ABANDON such a script, leaving the spin on the host loop), the post-cancel grace ends in a REAL `worker.terminate()`, and the value boundary is serialization by construction. isolated-vm was rejected for actual sandboxing: maintenance mode, `--no-node-snapshot` on EVERY consumer process (including published bins) on Node ≥ 20, node-gyp source-build fallback. Key mechanics (details in the package README): meta shape-validation and a body pre-parse stay HOST-side (preserving the seam's synchronous throws), a ready→go handshake keeps a run cancelled before start from ever executing the body, `cancel()` drives both child-cancel channels host-side (the shared request signal AND each child's explicit `cancel()` — a wedged worker cannot relay its own cancel RPCs), a host-side child registry backs worker-death reaping and `dispose()` quiescence, the wire protocol is enum-keyed payload maps private to the package, and on a termination path `agentsStarted` degrades to the host-observed count. Coverage puts the worker-side session on an in-process `MessageChannel` (real-Worker code is invisible to main-process v8) and proves the built `lib/worker.js` — a second tsdown entry, sanctioned in the workspace-constraints gate by the `"./worker"` subpath export — under plain node in the built-bin smoke gate.
+**Why node:worker_threads**: one run uses one unpooled worker because a workflow run is already heavyweight relative to thread startup. The script runs in a vm context inside the worker, keeping the script-visible surface to the hook contract instead of exposing a bare worker realm, while `agent()` bridges by message-port RPC to I/O-bound child loops on the host. This keeps `start()` from blocking the host on the script's synchronous slice, makes the post-cancel deadline end in a real `worker.terminate()`, and gives cross-thread values a serialization boundary by construction. isolated-vm was rejected for its maintenance state, required `--no-node-snapshot` consumer flag on Node ≥ 20, and node-gyp fallback.
+
+Host-side meta validation and body pre-parsing preserve the seam's synchronous errors, and private enum-keyed payload maps define the wire protocol. Pending async starts, published child records, one host cancellation signal, worker-death reaping, result precedence, and disposal quiescence preserve the subagent run contract across that wire; the [agent-scope runtime-design RFC](../architecture/2026-07-12-agent-scope-runtime-design.md#workflow-children-are-pending-starts-or-published-records) owns those race algorithms. Coverage uses an in-process `MessageChannel` for worker-side logic that main-process V8 coverage cannot see and separately proves the built `lib/worker.js`—a second tsdown entry sanctioned by the `"./worker"` subpath export—under plain Node in the built-bin smoke gate.
 
 **Meta as data, never evaluated**: the meta block reaches the seam as a plain JSON request field (the tool's schema-validated `meta` parameter) and the engine only shape-validates it, every violation named. This is a host-isolation invariant, not a convenience: evaluating a meta literal host-side — even one contractually "pure", in an empty timed vm context — hands script-controlled getters a host stack with no timeout the moment the result is READ, defeating the exact spin isolation the worker thread buys.
 
@@ -36,7 +38,11 @@ A `workflow` tool mirroring `dsh-tool-subagent`'s synchronous shape: start, awai
 
 ### The foundation: structured output on the subagent seam
 
-`agent({schema})` needs `SubagentStartRequest.outputSchema` to actually work; it was vocabulary without an implementation (`outputSchema: false` everywhere). Implemented in `dsh-subagent-inprocess` for both in-process backends: a globally registered `structured_output` capture tool whose per-child schema is enforced by a `prepend: true` `system-prompt/assemble` listener doing FINAL-ASSEMBLY enforcement (post-processing `await next()` — cooperative mutation would not survive a downstream listener returning a replacement assembly; the calling instruction rides as a trailing prompt section, since `AgentOptions` carries no per-agent prompt field, and the loop logs the result as the step's `request/header`, keeping the injection reconstructable), a `prepend: true` `agent/turn-continuation` veto after capture (no wasted extra model step) plus a `tools/pre-execute` deny for calls arriving after the capture (terminal within the step, not only at its end), and validation-retry in-turn via `ToolArgsError`. The schema is `structuredClone`d at `start()` (caller mutation cannot drift enforcement). Deliberately NO re-prompt: a child that finishes cleanly without calling the tool settles `error` to the parent. Lifetime is refcounted by backends (plugin lifetime) AND live runs (start → settle). The seam's `outputSchema` type became the raw JSON-Schema SUBSET (`StructuredOutputSchema` in dsh-tools: single-string `type`, `properties`/`required`/`additionalProperties`, `items`, scalar `enum`/`const`; anything unenforced is rejected loud) — the schema travels verbatim to the model as the forced tool's parameters, so the wire format, not the author DSL, is the right vocabulary.
+`SubagentStartRequest.outputSchema` is implemented by `dsh-subagent-inprocess` for both in-process backends. Each structured child receives its own scoped capture tool, instruction, and enforcement registrations on `child.ctx`; concurrent children can use different schemas without sharing mutable policy, and disposing the child removes the entire attachment.
+
+An output schema makes a schema-valid committed capture mandatory for successful child completion. The scoped runtime presents the capture tool and instruction, commits only a successful final outcome—including the enclosing `run_code` outcome for an SDK call—denies later side effects after capture becomes pending, and stops the child without another model step after commit. A validation failure remains a retryable tool error; clean completion without a committed capture settles as an error.
+
+`StructuredOutputSchema` is the raw enforceable JSON-Schema subset in `dsh-tools` (single-string `type`, `properties`/`required`/`additionalProperties`, `items`, scalar `enum`/`const`), and unsupported keywords fail loudly because that wire data becomes the capture tool's parameters verbatim. The [agent-scope runtime-design RFC](../architecture/2026-07-12-agent-scope-runtime-design.md#structured-output-commits-only-authoritative-outcomes) owns the assembly, commit, guard, and terminal-stop correctness algorithms.
 
 ## Deferred (documented non-goals of this cut)
 
@@ -51,11 +57,11 @@ A `workflow` tool mirroring `dsh-tool-subagent`'s synchronous shape: start, awai
 
 ## Alternatives considered
 
-- **Hostile-value containment in the host** (trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition): an earlier revision built all of it, and review showed the cost was real while the threat model was not — every one of those defenses guards against an author the premise already trusts. Removed in favor of the plain boundary above; the thread boundary makes such machinery redundant anyway (serialization by construction).
-- **In-process `node:vm` execution** (the first cut of this RFC shipped it): mechanically simplest — no RPC, no thread — but `start()` blocks the caller for the script's initial synchronous slice, a synchronous spin past the first await cannot be killed in-process (the vm `timeout` covers only that first slice), and `dispose()` could only ABANDON an unsettling script, leaving the spin on the host loop. Superseded by the worker-thread engine, which keeps the same vm-context script surface while unblocking the host and making termination real.
+- **Hostile-value containment in the host** (trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition): rejected because every defense targets an author the trust premise accepts, while the thread's serialization boundary already makes cross-realm values total by construction.
+- **In-process `node:vm` execution**: mechanically simplest — no RPC, no thread — but `start()` blocks the caller for the script's initial synchronous slice, a synchronous spin past the first await cannot be killed in-process (the vm `timeout` covers only that first slice), and `dispose()` could only abandon an unsettling script on the host loop. The worker-thread engine keeps the same vm-context script surface while unblocking the host and making termination real.
 - **Background execution as the default** (CC's shape): deferred; foreground-synchronous matches `dsh-tool-subagent`'s cut, and background semantics should be designed ONCE across bash/subagent/workflow rather than per-tool.
 - **Workflow-layer JSON parsing for `agent({schema})`**: duplicating a seam concern at one consumer while the seam's capability flag stayed dishonestly `false`.
-- **Meta embedded in the script as `export const meta = {...}`** (CC's exact format; the first cut shipped it): keeps scripts self-contained and CC scripts drop-in, but obtaining meta means evaluating model-written text on the HOST — the shipped extractor ran the literal in an empty timed vm context, yet reading the RESULT still executed script-controlled getters on the host stack outside any timeout, re-opening the host-spin hole the worker thread exists to close. A JSON parameter deletes the scanner, the evaluation, and the hole outright; the cost is that a CC script's meta header must move into the parameter (the body stays drop-in).
+- **Meta embedded in the script as `export const meta = {...}`** (CC's exact format): keeps scripts self-contained and CC scripts drop-in, but obtaining meta requires evaluating model-written text on the host. Even an empty timed vm context cannot bound script-controlled getters when the host reads the resulting object. A JSON parameter removes the scanner, evaluation, and host-spin hole; the cost is that a CC script's meta header must move into the parameter (the body stays drop-in).
 - **`SchemaSpec` as the outputSchema type**: the author-facing DSL cannot express what arrives as data and cannot be validated against without conversion loss.
 - **A schema-object library (zod, or the repo's schemastery) for the structured-output subset**: the schema is wire data — plain JSON that crosses the vm realm boundary in `agent({schema})` and lands verbatim in the forced tool's parameters — exactly where live schema objects cannot sit; consuming raw JSON Schema at runtime would need a third-party converter on top (zod core only emits JSON Schema, not the reverse), and it would put a second schema language beside schemastery's config role.
 - **ajv for value validation**: it validates FULL JSON Schema, so the subset gate — the module's actual point, since every accepted keyword must be one the harness enforces — would remain hand-written regardless; it compiles validators through `new Function`; and it would be dsh-tools' first runtime dependency, all to replace the ~70-line value walker while the path-qualified, every-violation error reporting stays custom either way.
@@ -63,4 +69,4 @@ A `workflow` tool mirroring `dsh-tool-subagent`'s synchronous shape: start, awai
 
 ## Consequences
 
-The harness gains CC-compatible script orchestration: fan-out plans live in a rerunnable artifact instead of the parent context, and the structured-output half of the subagent seam is now real (the vocabulary stopped lying about `outputSchema`). What it cost, all bounded by the trust premise: a worker thread per run (~tens-of-ms spin-up), every hook crossing a message port as RPC, and a termination-path `agentsStarted` that degrades to the host-observed count; in exchange `start()` never blocks the host, a post-cancel grace ends in a real `worker.terminate()`, and the value boundary is serialization by construction. A worker thread is still NOT a security boundary — scripts share the model's trust level, and actual sandboxing names its exit (the isolated-vm/separate-process engine swap behind the seam). The fatal-vs-null strictness divergence from CC means a CC-authored script that RELIES on option typos dissolving to `null` behaves differently here — judged worth it to keep the repo's no-accepted-then-ignored rule. Consumers must hold the run handle for control (`cancel`/`dispose`); observers get data snapshots only, so no listener can extend a run's lifetime or corrupt another's view.
+The harness gains CC-compatible script orchestration: fan-out plans live in a rerunnable artifact instead of the parent context, and `outputSchema` yields an authoritative structured child result across native and Code Mode presentation. The cost, bounded by the trust premise, is a worker thread per run (~tens-of-ms spin-up), every hook crossing a message port as RPC, and a termination-path `agentsStarted` that degrades to the host-observed count; in exchange `start()` never blocks the host, a post-cancel grace ends in a real `worker.terminate()`, and the value boundary is serialization by construction. A worker thread is still not a security boundary — scripts share the model's trust level, and actual sandboxing requires an isolated-vm/separate-process engine behind the seam. The fatal-vs-null strictness divergence from CC means a CC-authored script that relies on option typos dissolving to `null` behaves differently, preserving the repo's no-accepted-then-ignored rule. Consumers must hold the run handle for control (`cancel`/`dispose`); observers get data snapshots only, so no listener can extend a run's lifetime or corrupt another's view.

docs/rfc/implemented/feature/2026-07-06-approval-seam.md

@@ -4,7 +4,7 @@ Status: implemented
 
 ## Problem
 
-Two callers need to put one question — "may this specific action proceed?" — to a human, and neither has a channel. `tools/pre-execute`'s `ask` decision (produced today by the Claude-Code hook bridge's `permissionDecision: ask`) degrades to deny because nothing services it. The [sandbox RFC](2026-07-06-sandbox.md)'s escalation phase needs the same channel for its post-denial one-shot retry. Without a shared seam, each would invent its own outcome vocabulary, UI routing, cancellation, and audit trail — and a deployment with no UI at all needs a guarantee that an unanswerable question can never grant anything.
+Two callers need to put one question — "may this specific action proceed?" — to a human: `tools/pre-execute`'s `ask` decision (including the Claude-Code hook bridge's `permissionDecision: ask`) and the [sandbox RFC](2026-07-06-sandbox.md)'s post-denial one-shot escalation retry. A shared seam keeps them from inventing separate outcome vocabularies, UI routing, cancellation, and audit trails, while guaranteeing that a deployment with no UI can never grant an unanswerable request.
 
 The routing problem is ownership: an approval prompt must reach the editor session that owns the asking agent (the ACP bridge multiplexes N sessions over one connection), fail closed for agents nobody owns (in-process subagents, tests), and stay out of deployments that compose no UI (headless, CI).
 
@@ -14,7 +14,7 @@ One package, `dsh-user-approval` (`packages/ui/user-approval`), owning the vocab
 
 ### How a deployment uses it
 
-One `cordis.yml` entry mounts the seam; not loading it is the opt-out — consumers degrade to their historical fail-closed behavior with zero approval code registered:
+One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-out: consumers deny unanswerable requests with zero approval code registered.
 
 ```yaml
 - id: approval
@@ -49,29 +49,29 @@ The `escalation-rejected` twin ends in `{"outcome": "rejected"}` instead: nothin
 
 #### The seam: mechanism and policy split
 
-`ApprovalService.request(req)` always resolves to a closed `ApprovalOutcome` — `allowed-once` / `rejected` / `cancelled` / `unavailable` — and never rejects. The service is the mechanism: it dispatches the `approval/request` waterfall, races the request's `AbortSignal` (abort settles `cancelled`; a late answer is discarded, never double-audited), contains a throwing answerer as `unavailable`, normalizes a rogue non-vocabulary return to `unavailable`, and lands the log-only audit pair `approval/asked`/`approval/decided` (paired by the branded `ApprovalRequestId`) on the requesting agent's session log. Grants are one-shot by definition: `allowed-once` authorizes the single asked-about action, never a class of future ones, and the service stores nothing between requests. The one precondition: `request()` throws (before appending anything) when the agent's session has no open turn — the audit pair must be turn-enclosed, the turn being the durable log's commit/replay boundary (a bare event between turns is dropped as crash tail on reload); every shipped ask path runs mid-turn already, and idle asks are a deferred design.
+After request validation and a successful `approval/asked` append, the answerer phase always resolves to a closed `ApprovalOutcome` — `allowed-once` / `rejected` / `cancelled` / `unavailable`. `ApprovalRequest` is a readonly same-process contract, so the service borrows its routing identity and cancellation signal instead of copying the record or capturing a parallel callback bundle. It dispatches the `approval/request` waterfall, races the request signal (abort settles `cancelled`; a late answer is discarded, never double-audited), contains a throwing answerer as `unavailable`, normalizes a rogue non-vocabulary return to `unavailable`, and lands the log-only audit pair `approval/asked`/`approval/decided` (paired by the branded `ApprovalRequestId`) on the request agent's session log. Request acceptance and either pre-commit audit append may still reject; returning a decision that could not be logged would violate the pair. Session owns post-commit observer containment, so a callback failure cannot turn an authoritative audit append into a rejected request or suppress the matching event. Grants are one-shot by definition: `allowed-once` authorizes the single asked-about action, never a class of future ones, and the service stores nothing between requests. `request()` also throws before appending anything when the agent's session has no open turn — the audit pair must be turn-enclosed, the turn being the durable log's commit/replay boundary (a bare event between turns is dropped as crash tail on reload); every ask path runs mid-turn already, and idle asks are a deferred design.
 
 Answerers are the policy, and they are `approval/request` waterfall listeners. The waterfall buys exactly what the seam needs: with zero listeners the dispatch falls through to the caller-supplied default — `unavailable`, so fail-closed needs no configuration and no code in any deployment; a listener that recognizes the request's agent answers by returning an outcome without calling `next()` (the decision slot is single-occupancy, first answer wins — the same documented semantics as the `fs/write-intent` gate); a listener that does not recognize the agent MUST delegate via `next()` so another answerer or the default gets the question; and listeners dispose with their owning fiber, so an unloaded UI plugin degrades the next ask to `unavailable` instead of leaving a dangling channel. Registration order across sibling plugins is not load-order deterministic (the loader starts siblings concurrently), so a deployment composes ONE terminal answerer and reserves `prepend` listeners for decide-or-delegate gates.
 
-`ApprovalRequest` carries the asking `agent` (routes the question; receives the audit events), the `toolName`, the optional exact `callId`, the asker's human-readable `reason`, and the optional `signal`. The vocabulary is deliberately self-contained — it names the tool-call by the `CallId` brand from `dsh-llm` and never imports `dsh-tools` — because `dsh-tools` depends on `dsh-user-approval` (the ask routing) and a `ToolCallView` import would close a package cycle. It deliberately does NOT carry tool arguments: a UI answerer attaches the prompt to the already-streamed tool call via `callId` instead of re-rendering the call.
+`ApprovalRequest` carries the asking `agent` (routes the question; receives the audit events), the `toolName`, the optional exact `callId`, the asker's human-readable `reason`, and the optional `signal`. The caller retains ownership and honors the readonly contract for the duration of `request()`. The vocabulary is deliberately self-contained — it names the tool-call by the `CallId` brand from `dsh-llm` and never imports `dsh-tools` — because `dsh-tools` depends on `dsh-user-approval` (the ask routing) and a `ToolCallView` import would close a package cycle. It deliberately does NOT carry tool arguments: a UI answerer attaches the prompt to the already-streamed tool call via `callId` instead of re-rendering the call.
 
 #### Ask routing in dsh-tools
 
-`ToolRegistry.execute()` resolves an `ask` decision through the seam before the shared deny path: `allowed-once` proceeds to dispatch, and the three non-grants deny with distinct reasons — "the user rejected…", "…was cancelled", "…no approval channel is available" — so the model can tell a human "no" from an absent channel. The seam is consumed opportunistically (`ctx.get('approval')`, the `tool-bash`/`agent-loop` pattern), not statically injected: a deployment that composes no ApprovalService keeps the historical ask→deny degrade verbatim, an unmount mid-session degrades the same way on the next ask, and the registry's fiber never gates on the seam's presence. An agent-less execution also degrades — without an agent there is no session to audit to and no UI to route to.
+`ToolRegistry.execute()` resolves an `ask` decision through the seam before the shared deny path: `allowed-once` proceeds to guards and dispatch, and the three non-grants deny with distinct reasons — "the user rejected…", "…was cancelled", "…no approval channel is available" — so the model can tell a human "no" from an absent channel. The seam is consumed opportunistically (`ctx.get('approval')`, the `tool-bash`/`agent-loop` pattern), not statically injected: with no ApprovalService, or after one unmounts, the next ask fails closed without gating the registry's fiber. An agent-less execution also fails closed — without an agent there is no session to audit to and no UI to route to.
 
 #### The per-session policy tier
 
-The seam also owns the session-scoped approval policy — the approval knob of the two-knob per-session switching design ([the sandbox RFC](2026-07-06-sandbox.md) § Per-session modes is the pattern's home: one log-only event per knob, a pure fold, THE write path, ACP config-option advertisement, and turn-anchoring). `ApprovalPolicy` is `'ask' | 'never'`, and `effectiveApprovalPolicy(events) ?? Config.policy` (default `'ask'`) decides every request BEFORE any interactive answerer: the service resolves a `'never'` session to `'rejected'` INSIDE `request()`, before dispatching the waterfall at all — no listener registration, including a later `prepend`, can sit ahead of it — while `'ask'` dispatches unchanged (fail-closed `'unavailable'` with nobody composed, exactly the prior behavior). Visibility follows the switching design's two layers with one asymmetry: the prompt section states ONLY `'never'` (deterministic, availability-independent — "you will be prompted" would overclaim in a composition with no answerer, and absence under a logged header is exactly how the narrator reads `'ask'` back), the narrator injects at most one coalesced notice per switch, and the audit pair still lands on every ask, including the policy's auto-rejections.
+The seam also owns the session-scoped approval policy — the approval knob of the two-knob per-session switching design ([the sandbox RFC](2026-07-06-sandbox.md) § Per-session modes is the pattern's home: one log-only event per knob, a pure fold, THE write path, ACP config-option advertisement, and turn-anchoring). `ApprovalPolicy` is `'ask' | 'never'`, and `effectiveApprovalPolicy(events) ?? Config.policy` (default `'ask'`) decides every request BEFORE any interactive answerer: the service resolves a `'never'` session to `'rejected'` INSIDE `request()`, before dispatching the waterfall at all — no listener registration, including a later `prepend`, can sit ahead of it — while `'ask'` dispatches unchanged and falls through to fail-closed `'unavailable'` when nobody answers. Visibility follows the switching design's two layers with one asymmetry: the prompt section states ONLY `'never'` (deterministic, availability-independent — "you will be prompted" would overclaim in a composition with no answerer, and absence under a logged header is exactly how the narrator reads `'ask'` back), the narrator injects at most one coalesced notice per switch, and the audit pair still lands on every ask, including the policy's auto-rejections.
 
 #### The ACP answerer
 
 The bridge registers the first real answerer: it resolves the owning session through its existing `WeakMap<Agent, sessionId>` reverse map, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment.
 
-The reverse-map ownership seam [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) laid down is exactly what the answerer routes through, and per-session permission ownership (the blocker recorded in [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md)) is what it implements.
+The answerer routes through the bridge's reverse-map ownership seam described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md).
 
 #### Audit, and what the model sees
 
-`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching) and a contained answerer failure.
+`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` lands per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended.
 
 #### Entities and dependencies
 
@@ -79,35 +79,35 @@ One package, no cycles: `dsh-user-approval` peers on `cordis`, `dsh-session` (ev
 
 ### Testing
 
-Unit tier: the service's outcome branches (fail-closed default, first-wins slot, delegation, containment, rogue-value normalization, abort-before and abort-during with late-answer discard, fresh ids, fiber-disposal degradation) and the policy tier (both values × dispatch/decide, a `'never'` decision unbypassable even by an answerer prepended AFTER the service, audit pair intact) in `dsh-user-approval`; the ask routing matrix (grant dispatches; three non-grant reasons pinned verbatim; unmounted and agent-less degrades; the registry's own exhaustiveness backstop against a non-conforming stand-in) in `dsh-tools`; the answerer (wire shape of the prompt, outcome mapping, unknown-option conservatism, foreign-agent and call-less delegation) driven through a real bridge + scripted client in `dsh-acp`.
+Unit tier: the service's outcome branches (fail-closed default, first-wins slot, delegation, containment, rogue-value normalization, abort-before and abort-during with late-answer discard, fresh ids, fiber-disposal degradation), scoped routing, post-append observer throws on both audit events, and the policy tier (both values × dispatch/decide, a `'never'` decision unbypassable even by an answerer prepended AFTER the service, audit pair intact) in `dsh-user-approval`; the ask routing matrix (grant dispatches; three non-grant reasons pinned verbatim; unmounted and agent-less degrades; the registry's own exhaustiveness backstop against a non-conforming stand-in) in `dsh-tools`; the answerer (wire shape of the prompt, outcome mapping, unknown-option conservatism, foreign-agent and call-less delegation) driven through a real bridge + scripted client in `dsh-acp`.
 
 Snapshot tier: the harness accepts scripted permission answers (`permissionAnswers` in a scenario's `input.json`, consumed FIFO; an unscripted prompt answers `cancelled`, fail closed). The seam's wire is recorded end to end in the sandbox example's suite: both escalation branches drive `session/request_permission` through this seam over scripted answers (grant and rejection), and the recorded `mode-switching` scenario pins the `'never'` prompt sentence and the policy-switch notice ([the sandbox RFC](2026-07-06-sandbox.md) § Testing).
 
 ## Deferred
 
 - **`allow_always` grant storage** — honoring a persistent grant means designing storage, scope identity (call? path? prefix? session? time window?), and revocation; until designed, only the one-shot options are advertised ([the sandbox RFC](2026-07-06-sandbox.md) § Escalation records the open scope question).
-- **A recorded hook-driven `ask` scenario** — the wire is recorded via the sandbox example's escalation branches; the hook-producer variant stays on the unit tier and the hook matrix's `hook-cc-pretool-ask`, with its deny texts pinned verbatim there.
-- **Routing a child agent's approvals to the parent session** — `subagent-acp`'s child today auto-answers its own `permission` requests; surfacing them to the parent's editor is its own design.
+- **A recorded hook-driven `ask` through a composed answerer** — the human-prompt wire is recorded through the sandbox example's escalation branches. The hook matrix's `hook-cc-pretool-ask` pins the no-ApprovalService fallback denial, while the hook-producer-plus-answerer composition remains on the unit tier.
+- **Routing a child agent's approvals to the parent session** — `subagent-acp`'s child auto-answers its own `permission` requests; surfacing them to the parent's editor is its own design.
 
 ## Alternatives considered
 
 - **A single registered provider instead of waterfall listeners** — rejected: a `registerProvider()` surface forces every composition question — allowlist pre-filters, external hook deciders, scripted test answers, a policy gate in front of a human — inside one provider implementation. The waterfall gets composition, fail-closed absence, and HMR disposal from machinery the runtime already has; the seam's JSDoc pins the single-decision-slot convention instead of inventing a provider registry.
-- **[The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md)'s inline `tools/pre-execute` permission gate** — rejected, and superseded by this seam: prompting for every bridge-owned call hardwires the asking POLICY into the UI plugin, cannot serve a second asker (sandbox escalation happens after execution starts, with no pre-execute moment), and leaves hooks' `ask` — the vocabulary the interception seams already ship — unserviced.
-- **A generic user-interaction seam (`ctx.userInteraction`) instead** — rejected: the two share a skeleton (route by agent, block for a human, handle absence), but approval's contract is narrower in every dimension that matters: a closed outcome vocabulary instead of free text, a protocol-native prompt attached to a tool call instead of a generic form, mandatory fail-closed absence, and audit events. The generic seam has since shipped (`packages/ui/user-interaction`, the `ask_user_question` tool over ACP elicitation) and approval deliberately still does not ride it — an elicitation form is not a permission prompt, and a free-text answer is not a closed outcome; sharing provider plumbing stays open if the two ever converge.
+- **An inline `tools/pre-execute` permission gate in the ACP bridge** — rejected: prompting for every bridge-owned call hardwires the asking POLICY into the UI plugin, cannot serve a second asker (sandbox escalation happens after execution starts, with no pre-execute moment), and leaves hook-produced `ask` decisions without a shared mechanism.
+- **The generic user-interaction seam (`ctx.userInteraction`)** — rejected as the approval mechanism: the two share a skeleton (route by agent, block for a human, handle absence), but approval's contract is narrower in every dimension that matters: a closed outcome vocabulary instead of free text, a protocol-native prompt attached to a tool call instead of a generic form, mandatory fail-closed absence, and audit events. Approval therefore does not ride the shipped `packages/ui/user-interaction` / `ask_user_question` elicitation path — an elicitation form is not a permission prompt, and a free-text answer is not a closed outcome; sharing provider plumbing stays open if the two ever converge.
 - **Static optional injection in `dsh-tools`** — rejected: the vendored cordis `Inject` type has no optional flag — the object form maps service names to intercept config, and a declared inject gates the fiber. `ctx.get('approval')` is the documented opportunistic-consumption pattern (the `tool-bash` owner-token lookup, the loop's persistence probe), reads presence per call, and degrades correctly across HMR without extra machinery.
 - **The capability-seam three-package split** — rejected: interface/implementation/consumer fits a seam whose implementation is swappable (bash-local vs bash-sandbox). Here the service body is fixed mechanism and the variable part is listeners that live with their owners — splitting would manufacture an implementation package with nothing in it ("don't split preemptively").
 - **Offering `allow_always` now** — rejected: the protocol can express it, but honoring it means designing grant storage, scope identity, and revocation (§ Deferred). Advertising an option the harness cannot honor manufactures doomed grants.
 
 ## Consequences
 
-What shipped pins — the suites in Testing hold each:
+The implemented contract is pinned by the suites in Testing:
 
 - With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason.
 - A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)).
-- Every unanswerable path fails closed to `unavailable`: no service (degrade, verbatim historical text), no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, a dead client connection.
-- Every `request()` lands exactly one `approval/asked`/`approval/decided` pair on the asking agent's log, replayable, invisible to the model transcript.
+- Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection.
+- Every `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; post-append observer failures cannot split the pair.
 - Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor.
-- A deployment that composes nothing new behaves byte-identically (the snapshot suite's goldens are unchanged).
+- A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request.
 
 Costs and accepted limits:
 
@@ -125,7 +125,7 @@ Behavioral and usage questions only — every "why not X?" design question lives
 - **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt.
 - **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 — one audit pair either way, 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 unanswerable today by design. `subagent-acp`'s child-side auto-answer is untouched; routing a child's asks to the parent's editor is deferred (§ Deferred).
+- **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent's editor 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; the audit pair still lands for every auto-rejection.
 - **What happens across a hot reload, or when the UI plugin 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 the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own.

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

@@ -17,7 +17,7 @@ The system-prompt assembly owns the canonical model-facing tool order, exactly w
 - The list must contain the rest entry exactly once and no duplicate names.
 - When `toolOrder` is unset, the canonical order is plain lexicographic name order (code-unit comparison, locale-independent), so determinism requires no configuration.
 
-The policy is applied where the list is born: `assemble()`, before the `system-prompt/assemble` waterfall. The assembly canonicalizes the tools it collects from providers the same way it sorts sections by their `order` field — on the initial assembly, killing the registration-order entropy at its source. Everything downstream inherits the order untouched: the waterfall, the loop's `EpochHeader`, the `request/header` event, the deep-frozen request, and the dev invariant's cross-check all see one deterministic list, with no new loop change.
+The policy is applied where the list is born: `assemble()`, before the `system-prompt/assemble` waterfall. The assembly canonicalizes the tools it collects from providers the same way it sorts sections by their `order` field — on the initial assembly, killing the registration-order entropy at its source. The waterfall therefore starts from one deterministic list; when a listener leaves that order intact, the loop's `EpochHeader`, the `request/header` event, the deep-frozen request, and the dev invariant's cross-check inherit it with no new loop change.
 
 Scope is deliberately narrow: this fixes the REGISTRATION-ORDER race, not plugin behavior. A `system-prompt/assemble` listener may still add, remove, or rearrange tools — same as it may edit sections after their sort — and owns the determinism of what it emits; the waterfall contract already demands deterministic listeners (the reconstructability invariant would catch a listener that diverges between build and replay).
 
@@ -36,8 +36,8 @@ Config plumbing follows the `persona` precedent, and `toolOrder` sits beside it:
 
 ## Consequences
 
-- Every assembly — and therefore every `request/header` event and model request — has a deterministic tool order on every host; the CI-vs-local golden flip is structurally gone. The default order is lexicographic, no longer registration order.
-- `PromptAssembly.tools` itself is canonical, so every assembly consumer (the loop, waterfall listeners, any future prompt inspector) sees the model-facing order; provider registration order is observable nowhere downstream of the registry.
+- Every registry-built assembly starts with a deterministic tool order on every host; absent an expert listener that deliberately changes it, every `request/header` event and model request inherits that order. The CI-vs-local registration-order flip is structurally gone, and the default is lexicographic.
+- The initial `PromptAssembly.tools` is canonical, so waterfall listeners start from the model-facing order; provider registration order is observable nowhere before that cooperative seam.
 - The snapshot suite's single pinned request-header fixture (`text-turn`) carries the new canonical tool order; every other ACP snapshot keeps the header bulk scrubbed as `{{system}}`/`{{tools}}`, per the pinned-header design.
 - A pure tool reordering between steps is representable only as a `request/header` `'fallback'` snapshot (the name-keyed `ToolsDelta` cannot express it); with a stable canonical order such reorders no longer occur in practice, so the fallback path stays a safety valve.
 - The `toolOrder` key rides the app → `agent-core` → `SystemPrompt` forwarding chain, so deployments set it next to `persona` in the app config; `dsh-llm` and the agent loop are untouched.

docs/rfc/implemented/feature/2026-07-08-background-subagent-tasks.md

@@ -16,18 +16,18 @@ Each `dsh-tool-subagent` instance may expose `run_in_background?: boolean`, gate
 
 A foreground call keeps the synchronous semantics: it waits for `run.result`, returns final text on `completed`, maps non-clean terminal stop reasons to an errored tool result, and disposes the run in `finally`.
 
-A background call validates that a parent agent exists, checks an already-aborted tool signal, and hands the delegation to `ctx.tasks.start()` — the runtime preflights the control-surface fence and the owner cleanup BEFORE its `run()` starter creates the child through `ctx.subagents`, so a child that started without a collectable id is structurally impossible — then returns `started background subagent task <task_id>`. After the id is returned the tool-call signal is NOT connected to `run.cancel()` — the parent step may finish while the child continues; cancellation belongs to `task_kill` and the owner-cleanup path. `ctx.tasks.start()` supplies the runtime guarantees this feature needs and this RFC does not implement: kind-prefixed branded task ids, owner-scoped access (the parent agent is the owner; another session's agent cannot read or kill the task), the loud no-control-surface failure, completion-notice injection, and the generic prompt guidance.
+A background call validates that a parent agent exists, checks an already-aborted tool signal, and hands the delegation to `ctx.tasks.start()`. The runtime preflights the control-surface fence and owner-scope cleanup before its synchronous `run()` starter creates an independent `AbortController` and begins async `ctx.subagents.start()`; commit after that starter cannot fail, so provider work cannot become uncollectable. The task-owned signal, not the tool-call signal, then covers pending readiness and the live child. `ctx.tasks.start()` supplies kind-prefixed branded ids, owner-scoped access, loud no-control-surface failure, completion notices, and generic prompt guidance.
 
 The registration maps the seam vocabulary onto the runtime's:
 
 - `kind: 'subagent'`, `label`: the model's `description` argument, `owner`: the parent agent.
-- `cancel`: `run.cancel(reason)` — the runtime forwards `task_kill`'s optional logged `reason`; the task shows as `stopping` until settlement.
-- `done` (`settleRun`): awaits `run.result`, then awaits `run.dispose()` (child quiescence — `done` must not settle before the child agent/session is released), then maps the stop reason (`runOutcome`): `completed` → `completed` with the final text as `output`; `aborted` → `killed`; `error`, `max-tokens`, `refusal`, and unknown merge-extensible reasons → `failed` with the reason as `detail`. A rejected `run.result` (infrastructure fault) still disposes and settles `failed`.
+- `cancel`: abort the task-owned controller with `task_kill`'s optional logged reason; the same signal cancels provider-owned partial startup or a published child, and the task shows as `stopping` until settlement.
+- `done`: await `ctx.subagents.start()`. A cancellation rejection after startup rollback maps to `killed`; another startup rejection maps to `failed`. A ready run flows through `settleRun`, which awaits `run.result`, then `run.dispose()` (child quiescence), and maps `completed` to final `output`, `aborted` to `killed`, and other stop reasons to `failed`. Infrastructure and disposal failures settle `failed` rather than rejecting the task contract.
 - No `readOutput`: a subagent task is final-output-only. While it runs, `task_output` returns only the status line; once terminal it returns the final text (or failure detail) idempotently. The child session remains the detailed trace; v1 deliberately exposes no incremental transcript cursor.
 
 ## Lifecycle
 
-The background task is scoped to the owner session, not durable across session closure. The runtime's awaited owner-cleanup path (the `AgentRegistry.onCleanup` seam, owned by [the runtime RFC](../architecture/2026-06-20-generic-long-running-tool-runtime.md)) cancels the owner's running tasks on agent disposal and awaits each task's `done` before `AgentHandle.dispose()` resolves; because this registration's `done` settles only after `run.dispose()`, owner disposal reaches child quiescence without leaking child agents or sessions. `agent/disposed` alone is not the mechanism — the registry emits it synchronously without awaiting listener work, which is exactly why the awaited seam exists. Completion notices are best-effort by the runtime's rule: a live owner gets the injected notice; a disposed owner drops it without throwing.
+The background task is scoped to the owner session, not durable across session closure. The runtime registers one async cleanup through the exact owner's `agent.ctx`; agent-scope disposal cancels running tasks and awaits each `done` before `AgentHandle.dispose()` resolves. Since subagent `done` settles only after startup rollback or `run.dispose()`, owner disposal reaches child quiescence without leaking child agents or sessions. Completion notices are best-effort: a live owner gets the injection, while teardown that already detached or disposed the owner drops it.
 
 ## Model guidance
 

docs/rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md

@@ -0,0 +1,92 @@
+# RFC: Configure subagent persona, tool visibility, and depth
+
+Status: implemented
+
+## Problem
+
+A reusable subagent provider answers how to run a child, but different delegation tools need different child behavior. One deployment may want a reviewer persona, a research-only tool set, or a hard recursion bound without creating a new provider for every combination.
+
+These controls affect the child's first model request and therefore cannot be installed after the child is visible. They also need honest provider support: an ACP backend cannot silently accept an in-process-only tool filter, and a filter must not be described as a security boundary when every plugin runs in the same trusted process.
+
+## Decision
+
+Subagent starts have three independent composition controls: `persona`, `toolFilter`, and `maxDepth`. A provider advertises support for each control, the service rejects unsupported requests before starting a run, and an in-process provider installs the requested composition while the child is still unpublished.
+
+The controls answer different questions:
+
+| Control | Question | Result |
+|---|---|---|
+| `persona` | What role instructions replace the deployment persona for this child? | A child-local prompt section shadows `deployment:persona` |
+| `toolFilter` | Which deployment-global tools enter this child's visible tool view? | A scoped restriction filters globals before child-local tools are added |
+| `maxDepth` | How deep may this delegation tree grow? | A start whose child depth exceeds the absolute cap is rejected |
+
+`dsh-tool-subagent` exposes the controls as plugin configuration and copies them into each request it creates. Direct `SubagentService` callers may choose them per request. The provider capability descriptor remains the source of truth for whether a backend can honor each field.
+
+### Persona is a scoped shadow
+
+The persona control changes one child without changing deployment-wide prompt assembly. During unpublished setup, an in-process provider registers a child-scoped section named `deployment:persona`; ordinary most-specific-wins resolution replaces the global section only in that child's assemblies.
+
+The value has the same strict template semantics as the deployment persona. Omitting it inherits the deployment section through the global layer; an explicit empty string shadows the global persona with an empty section. Parent and sibling personas never enter the child's flat scope.
+
+This uses the normal system-prompt registration mechanism rather than a second persona channel. The first prompt therefore sees the same named contribution that later prompts and prompt-inspection tools see.
+
+### Tool filtering is one live global-view rule
+
+The tool filter controls visibility and executable lookup together. An in-process provider installs `ToolRegistry.restrict()` in the child's scope before publication, and the registry's single resolver applies the same result to prompt schemas, lookup, execution, and Code Mode SDK generation.
+
+Resolution follows these rules:
+
+1. Each restriction applies `allow` before `deny` to the live deployment-global tool registry.
+2. Multiple restrictions intersect, so every installed restriction must admit a global tool.
+3. Child-scoped tools are added after global filtering and may shadow an admitted global tool.
+4. Reserved `run_code` presentation and other scope-local protocol contributions are outside the global filter.
+
+Configuration fails loudly when a filter supplies neither `allow` nor `deny`, or names something outside the current global restrictable set, including a scope-local-only or reserved name. `allow: []` is valid and deliberately hides every global tool. These checks catch misspellings and prevent configuration from appearing effective when it cannot affect the named entry.
+
+The global registry remains live. A deny-only filter admits a later global name unless it explicitly denies that name; an allow-list excludes a later global name unless it explicitly allows that name. Removing a global tool removes it from every resolved view. These semantics preserve hot registration while making the difference between allow and deny explicit.
+
+### Depth is an absolute tree cap
+
+The depth limit bounds recursive delegation independently of tool visibility. A top-level agent has depth zero; an in-process child has its parent's validated depth plus one. `maxDepth` is an absolute non-negative safe integer, and a start rejects before child ownership begins when the derived child depth is greater than the cap.
+
+Every public entry validates the domain rather than relying on one model-facing configuration path. Negative values, fractions, negative zero, non-finite values, unsafe integers, malformed stored parent depth, and derived overflow all reject. Omitting the cap leaves depth unbounded by this mechanism.
+
+A deployment can combine depth and filtering. For example, it may keep the delegation tool visible at depth one but set `maxDepth: 1`, or deny the delegation tool entirely in children. Neither choice changes the provider's conversation-history behavior.
+
+### Capability gating keeps providers honest
+
+Capabilities separate a requested feature from a provider implementation. `SubagentCapabilities` advertises `persona`, `toolFilter`, and `depthLimit`; `SubagentService.start()` checks every present request field against those flags before calling the provider.
+
+This lets spawn and fork providers share the in-process implementation while external providers advertise only what they can enforce. A request never degrades silently: selecting an unsupported control produces `UNSUPPORTED_CAPABILITY`, and no run or lifecycle event exists.
+
+### Unpublished setup makes the first request correct
+
+All child-local composition is complete before the child becomes observable. The in-process provider supplies one setup callback to agent creation; that callback installs persona, tool restriction, and structured-output contributions in the child's scope. Only after setup succeeds does creation publish the session and agent and allow the driver to start.
+
+A setup failure rolls back the private child. No observer can acquire a child whose first prompt used the deployment persona or unfiltered tool set and whose later prompts use the requested configuration.
+
+## Visibility is not authority
+
+These controls compose trusted same-process behavior; they do not authorize it. `toolFilter` changes the child view resolved by the tool registry, but it does not create a parent-to-child grant lattice, require a child to be a subset of its parent, sandbox plugins, or prevent code with another Cordis context from calling services directly.
+
+In particular, a child-local tool is added after the global filter and may be absent from the parent's view. A deny-only child also sees later global tools not named by the deny-list. Those are deliberate live-composition semantics, not non-escalation guarantees.
+
+A security design would need a separate authority representation, propagation rule, and execution-time enforcement point. Creation-time grant snapshots, parent-subset grants, explicit future-grant APIs, and generic capability/output/termination tags are outside this feature.
+
+## Alternatives considered
+
+**Create one provider per persona or tool set.** This multiplies providers that share the same transport and lifecycle implementation, makes dynamic deployment configuration awkward, and still needs a recursion mechanism. Providers remain about execution transport; requests carry per-child composition.
+
+**Copy the parent's complete tool view.** Registration scope is flat by design, and lifetime ownership does not imply visibility inheritance. Copying a resolved view would also freeze dynamic global registrations and conflate composition with authority without defining either contract fully.
+
+**Snapshot allowed global tools at child creation.** A frozen allow-set makes future registration uniformly unavailable, but it changes hot-registration semantics and starts an authorization design. The implemented filter stays a live registry predicate and documents allow-versus-deny behavior directly.
+
+**Hide only tool schemas.** Presentation-only filtering lets the model execute a tool that the prompt says does not exist through Code Mode or a forged call. One resolver governs both presentation and execution instead.
+
+**Use only tool filtering to stop recursion.** Removing the delegation tool is useful but provider-specific and does not protect direct service callers or alternate delegation tools. Absolute depth is an independent structural bound.
+
+## Consequences
+
+Contributors can configure child role, visible global tools, and recursion without defining new providers. Capability checks fail before ownership starts, unpublished setup makes the first request consistent, and one tool resolver prevents presentation/execution drift.
+
+The cost is that deployments must understand live allow/deny behavior and the distinction between visibility and authority. Provider authors must advertise each supported control accurately, and in-process providers must install every requested contribution before publication. The controls deliberately do not solve security confinement or parent-to-child non-escalation.