Merge origin/master into timeout-design

Resolve conflicts from master's catalog/doc refactors landing alongside the
tool-call timeout work:
- knip.json: keep both new workspace entries (util/timeout + support/acp-snapshot).
- tool-web/src/fetch.ts: keep the timeout_ms removal, adopt master's richer
  JSDoc @param/@returns style on parseFetchArgs/presentFetchCall.
- tools/README.md: keep the tools/execute pipeline wording, adopt master's
  flattened docs/tool-catalog.md path.
- Regenerate every generated doc (cordis-catalog, tool-catalog, config-catalog,
  doc-graphs, module-graph) so they carry both master's changes and the
  tools/execute event + timeout-policy package.
- Add @param/@returns to toolTimeoutResult for master's new verify-export-jsdoc gate.

docs/rfc/implemented/architecture/2026-06-24-web-capability-seam.md

@@ -66,7 +66,7 @@ flowchart LR
 
 `@deepseek-ai/dsh-web` depends only on Cordis and low-level harness support. It declares `ctx.web`, provider interfaces, request/result types, the provider status type, and error codes. It does not import tool, agent, session, LLM, or provider packages.
 
-Provider packages depend on `@deepseek-ai/dsh-web` and Cordis. They own credentials, endpoint config, provider-specific request mapping, provider-specific response parsing, and provider-specific error translation into `WebError`. They issue network requests with the platform-native `fetch` (Node 24), mirroring `@deepseek-ai/dsh-llm-deepseek`'s adapter, NOT a cordis HTTP-client service (`ctx.http`/`@cordisjs/plugin-http`) — even where a Perplexity provider's request is shaped like an OpenAI-compatible chat completion, that wire shape is a provider-private detail and does not make the provider depend on `ctx.llm`. A provider does NOT own the `ctx.web` key (two search providers cannot both own it): like `dsh-llm-deepseek`, each provider package is a function/namespace plugin (`inject: ['web']`) whose `apply` constructs the backend and calls `ctx.web.registerSearchProvider` / `registerFetchProvider`. `@deepseek-ai/dsh-web` is the `export default` service that owns the key.
+Provider packages depend on `@deepseek-ai/dsh-web` and Cordis. They own credentials, endpoint config, provider-specific request mapping, provider-specific response parsing, and provider-specific error translation into `WebError`. They issue network requests with platform-native `fetch` at the repo's Node floor, mirroring `@deepseek-ai/dsh-llm-deepseek`'s adapter, NOT a cordis HTTP-client service (`ctx.http`/`@cordisjs/plugin-http`) — even where a Perplexity provider's request is shaped like an OpenAI-compatible chat completion, that wire shape is a provider-private detail and does not make the provider depend on `ctx.llm`. A provider does NOT own the `ctx.web` key (two search providers cannot both own it): like `dsh-llm-deepseek`, each provider package is a function/namespace plugin (`inject: ['web']`) whose `apply` constructs the backend and calls `ctx.web.registerSearchProvider` / `registerFetchProvider`. `@deepseek-ai/dsh-web` is the `export default` service that owns the key.
 
 `@deepseek-ai/dsh-tool-web` depends on `@deepseek-ai/dsh-web`, `@deepseek-ai/dsh-tools`, `@deepseek-ai/dsh-system-prompt`, and Cordis. It never imports concrete provider packages.
 

docs/rfc/implemented/feature/2026-06-30-session-store-fork-api.md

@@ -0,0 +1,41 @@
+# RFC: SessionStore fork API
+
+Status: implemented
+
+## Problem
+
+The event-sourced session log already has the primitive a fork needs: create a new session with a seed event prefix, then derive model history from that seeded log exactly as replay does. That primitive is intentionally low-level: `ctx.sessions.create(id, { seed, meta })` accepts any valid seed, but ordinary live-session branching needs policy around which prefix can be copied, which metadata is stamped on the child, and how errors are classified.
+
+The semantic hazard is the fork boundary. A valid user-visible fork seed must be contiguous and turn-enclosed. Forking inside an active turn would copy an open `turn/start`, possibly an open `step/start`, and possibly dangling tool calls. That violates turn-enclosure and provider-transcript invariants, and it creates a misleading child history that appears to have participated in an unfinished parent turn. The existing [subagent seam](../../implemented/feature/2026-06-21-subagent-capability-seam.md) deliberately solves a different problem: tool-triggered subagent forks usually happen while the parent turn is open, so `dsh-subagent-fork` clips the seed to the parent's last completed-turn prefix. A general session fork should not silently clip; it should either fork the requested boundary or reject it.
+
+## Decision
+
+`dsh-session` owns ordinary live-session forking directly on `ctx.sessions`. There is no separate `dsh-session-fork` package or `ctx.sessionFork` service: the API has no independent backend, event vocabulary, lifecycle, or persistence behavior, and all durable work delegates to the existing session store and persistence backends.
+
+The store exposes one operation:
+
+```ts ignore-check
+type SessionForkSource = Session | SessionId
+
+class SessionStore extends Service {
+  fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session
+}
+```
+
+`boundary` is the inclusive source event `seq` to copy through. When omitted, it defaults to the source session's current last event; on an empty source, omitted `boundary` creates an empty child. Fork-specific validation only checks that the requested boundary exists and is a `turn/end`. The selected prefix is then deep-cloned into the child seed. The child inherits the source session's `cwd`, stamps `parentSession` to the source id, and sets `seedLength` to the copied prefix length. When `childSessionId` is omitted, `SessionStore` generates one using its existing id policy.
+
+The boundary rule is structural: an empty selected prefix is forkable, and any non-empty selected prefix must end at `turn/end`, regardless of the turn-end reason (`completed`, `aborted`, `error`, `disposed`, `max-tokens`, `interrupted`, or a future merge-extensible reason). A boundary that is not an existing event seq, is not a safe integer, or does not point at `turn/end` is rejected with a typed `SessionForkError` code. Broader session-log sanity remains in the existing invariant/repair layers: `dsh-invariants` checks turn enclosure and richer event ordering in dev, while persistence repair handles the valid crash-tail case of a final interrupted turn. The API also classifies non-live source ids (`SESSION_NOT_FOUND`), stale `Session` object references whose id is live on a different instance (`SESSION_NOT_LIVE`), duplicate requested child ids (`SESSION_ALREADY_EXISTS`), and invalid boundary values (`INVALID_BOUNDARY`).
+
+## Alternatives considered
+
+**Separate `ctx.sessionFork` service.** This was the first implementation, but review showed it overfit the capability-seam pattern. The code had no swappable backend, no extra event surface, no independent ownership lifecycle, and no durable behavior beyond `ctx.sessions.create({ seed, meta })`. Keeping a separate package would make callers discover and install a second service just to perform policy around a session-store primitive.
+
+**Two functions: `snapshot()` plus `fork()`.** This preserved a reusable seed/metadata computation, but the only supported consumer created a session immediately. It also made the surface feel more abstract than the concrete operation users need. A single `fork()` with an explicit `boundary` keeps the API direct while still supporting previous-point forks.
+
+**Silently clip open turns to the last completed boundary.** That is correct for `dsh-subagent-fork`, where delegation often starts while the parent turn is open and the child should inherit only the completed prefix. It is wrong for ordinary user/session branching because it hides that the requested fork point was not actually a valid boundary and silently drops the parent turn tail.
+
+## Consequences
+
+The public surface stays small and discoverable: live session branching is part of `ctx.sessions`, next to `create({ seed })`, rather than a standalone service or a two-step helper pair. Persistence continues to work through existing `session/created` and `session/flush` behavior: a forked child starts life with seeded events, so existing backends persist that seed once and preserve `parentSession` / `seedLength` in the header.
+
+The v1 scope still excludes ACP `session/fork`, unloaded persisted-session forking, model-facing tools, and subagent refactors. If a future ACP method is added, it should advertise the capability only after it has transcript/snapshot coverage; this RFC adds no editor-facing updates, so no ACP snapshot is required now. Fork-child replay remains covered by the existing [seed-boundary testing RFC](../../implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md), while this API gets focused `dsh-session` unit tests plus JSONL persistence coverage.

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

@@ -0,0 +1,49 @@
+# RFC: Explicit model-facing tool order
+
+Status: implemented
+
+## Problem
+
+The order of the tool list a model call carries — `request/header.tools` on the session log and `GenerateOptions.tools` on the wire — was an emergent artifact: the tool registry returns schemas in registration order, the system-prompt assembly concatenates providers in registration order, and the loop logged and dispatched the result verbatim. Registration order is plugin load order, and plugin load order is a race: the cordis loader imports every `cordis.yml` entry concurrently, so which tool plugin registers first depends on module-import completion timing. The plugin dependency relation cannot rescue this — it is a partial order under which independent tool plugins (e.g. `tool-subagent` vs `tool-todo`) are incomparable, so both interleavings are legal linearizations. This stopped being theoretical when a CI runner resolved the race differently from every recording machine: snapshot goldens pinned one permutation of `request/header.tools`, the `node 22.18` CI leg produced the other, and 5/5 snapshot tests failed on a diff that was pure array reordering. Tool order is part of the request bytes (prompt-cache stability, potentially model behavior) and, since the reconstructability contract, part of the durable session log — it must be a decision, not a residue.
+
+## Decision
+
+The system-prompt assembly owns the canonical model-facing tool order, exactly where it already owns section order. `toolOrder?: string[]` on `dsh-system-prompt` is the optional explicit policy:
+
+- A listed tool that is registered takes its listed position.
+- A listed name with no registered tool is a configuration error. Shape errors (rest entry missing or duplicate names) fail from the service constructor; an unregistered name rejects every `assemble()` — the earliest moment the registered tool set exists to check against (tool plugins register after the service constructs), and the only universal one (registrations can change at any time; cordis has no "all plugins loaded" event). Under the shipped loop the first turn fails before any model request — see the consequences below for the exact blast radius.
+- A registered tool absent from the list is inserted at the `'<unlisted-tools>'` rest entry (`TOOL_ORDER_REST`), in lexicographic name order among the other unlisted tools.
+- No collected tool may use `TOOL_ORDER_REST` as its `ToolSchema.name`; the assembly rejects that reserved name before ordering.
+- 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.
+
+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).
+
+Config plumbing follows the `persona` precedent, and `toolOrder` sits beside it: the app configs (`dsh-stdio-agent`, `dsh-acp-agent`) accept the key and forward it through `dsh-agent-core` (whose schema is the intersection of the owners' schemas) to the `SystemPrompt` child. One schemastery footnote is load-bearing: a schemastery array defaults to `[]`, but an omitted `toolOrder` must stay ABSENT (= lexicographic) rather than become an explicitly-configured empty list (invalid — it lacks the rest entry), so every schema on the chain forces the default to `undefined`.
+
+## Alternatives considered
+
+- **Registration order (the status quo)** — a concurrent-import race, host-dependent (the CI flake above), invisible in review.
+- **A linearization of the plugin dependency graph** — the relation is partial and independent tool plugins are incomparable; the flake happened with the partial order fully satisfied.
+- **Per-plugin `weight` on each tool contribution** — scatters the order across plugins yet still needs a global numbering convention nobody owns (the section `order` bands show that coordination cost being paid by hand).
+- **Sorting in `ToolRegistry.schemas()` (the registry layer)** — equally deterministic, but the registry is a membership store consumed by more than the assembly; ordering is a prompt-composition concern, and the assembly already owns the composition policy for sections.
+- **A `LlmService` config + `orderTools()` method the loop calls before logging the header** — works, but adds a public service method and a loop edit solely to apply a policy at a distance; every future request composer must remember the call. Canonicalizing where the list is born makes an unordered list unrepresentable, with zero new surface.
+- **Normalizing inside `llm.stream()`** — runs after the header event is logged (the flake survives) and rebuilds the deep-frozen envelope, silently disarming the reconstruction invariant.
+- **An exhaustive list (no rest entry)** — every newly loaded tool plugin would break boot; the mandatory rest entry keeps unlisted tools deterministic and their position explicit.
+- **A boot-time validation pass (a `SystemPrompt.assertToolOrderSatisfied()` called by `dsh-app-boot` after `loader.await()`)** — would turn the misconfiguration into a startup death instead of a first-turn failure, but costs a public service method plus a structural coupling from the generic boot glue to one service, and cannot replace the assembly-time check anyway (embedded callers never run app boot; registrations change after boot). No existing event can host the check either: cordis v4 has no ready-like event, `loader/entry-init`/`internal/status` fire mid-load (racy against tool registration, the very entropy this RFC kills), and the agent lifecycle events are no earlier than the assembly. One enforcement point at `assemble()` was judged worth the later failure moment.
+
+## 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.
+- 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.
+- A misspelled or unloaded tool name in `toolOrder` fails the turn at prompt assembly, not the boot: the loop assembles inside the turn (after `turn/start`, before `step/start`), so the rejection reaches the turn's outer catch — the turn closes balanced with an `error` reason carrying the message, `agent/error` mirrors it, no step opens, no `request/header` is logged, no request reaches the adapter, and the agent returns to idle. Every turn fails identically until the config is fixed; the process itself stays up (matching the repo rule that explicit config references must not be silently ignored — the enforcement point is the assembly because no earlier universal moment exists).
+- A tool provider that returns the reserved rest-entry name has the same prompt-assembly failure shape as an unknown listed name. This keeps the sentinel from becoming an ambiguous real tool and preserves the "never drops a tool" ordering contract.
+
+## Testing
+
+Unit tests on `dsh-system-prompt` pin the ordering semantics (lexicographic default, listed/rest placement, unknown-name rejection at assembly, reserved tool-name rejection, stable handling of shared names, provider-order independence), the pre-waterfall contract (listeners observe the canonical list; a listener-appended tool is not re-sorted), and each invalid-list rejection at load. Loop-level tests assert the `request/header` fold carries the canonical order for scrambled registration orders (identical across permutations), that a configured `toolOrder` reaches both the logged header and the dispatched deep-frozen request, that the frozen loop-built envelope survives to the adapter, and that an unregistered `toolOrder` name fails the turn with a balanced `error` `turn/end`, an `agent/error`, no step, no logged header, and no dispatched request. Forwarding is asserted at every level that exposes the key (`dsh-agent-core`, `dsh-stdio-agent`, `dsh-acp-agent`). The snapshot tier replays all scenarios while only the pinned `text-turn` header carries the full canonical tool list; non-pinning fixtures continue to compare through `{{tools}}`.

docs/rfc/implemented/process/2026-06-11-quality-gates.md

@@ -14,7 +14,7 @@ Every AGENTS.md promise gets a command that exits non-zero, wired into git hooks
 - ESLint strict-type-checked + @stylistic (the house style, enforced); vendored code excluded.
 - Per-file 100% coverage on `packages/*/src` (v8); unreachable defensive guards carry `/* v8 ignore */ ` with stated reasons instead of deletion.
 - knip (dead code/deps), publint (package correctness), workspace constraints (workspace rules: private, cordis peer+dev, uniform version, ESM), and a NodeNext consumer typecheck for built package declarations.
-- lefthook pre-commit (lint staged, typecheck, vendor-manifest guard) and pre-push (tests, hygiene); CI runs the full matrix on node 24/26 plus a demo smoke test driving the echo-agent end to end.
+- lefthook pre-commit (lint staged, typecheck, vendor-manifest guard) and pre-push (tests, hygiene); CI runs the full matrix on node 22.19/24/26 plus a demo smoke test driving the echo-agent end to end.
 
 ## Consequences
 

docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md

@@ -4,7 +4,7 @@ Status: implemented
 
 ## Problem
 
-A reader — a plugin author, a prompt engineer, someone auditing what the agent can do — has no single place that lists the model-facing tools the harness ships. The `name` / `description` / JSON-Schema `parameters` a tool contributes are what the model actually receives (via `ctx.systemPrompt.tools()` off `ctx.tools.schemas()`), but they are scattered across each `defineTool` call in each `packages/*/tool-*` package, buried in string concatenation and runtime spreads. The cordis [events](../../../cordis-catalog/events.md) & [services](../../../cordis-catalog/services.md) catalogs ([their RFC](2026-06-20-generated-cordis-catalog.md)) document the *wiring* a plugin works against and the [core-data-structures catalog](../../../core-data-structures/core.md) documents the *vocabulary* those signatures move — but neither documents the *tools* the agent is offered. This RFC adds that third reference surface, `docs/tool-catalog/tools.md`, and a freshness gate so it cannot drift.
+A reader — a plugin author, a prompt engineer, someone auditing what the agent can do — has no single place that lists the model-facing tools the harness ships. The `name` / `description` / JSON-Schema `parameters` a tool contributes are what the model actually receives (via `ctx.systemPrompt.tools()` off `ctx.tools.schemas()`), but they are scattered across each `defineTool` call in each `packages/*/tool-*` package, buried in string concatenation and runtime spreads. The cordis [events](../../../cordis-catalog/events.md) & [services](../../../cordis-catalog/services.md) catalogs ([their RFC](2026-06-20-generated-cordis-catalog.md)) document the *wiring* a plugin works against and the [core-data-structures catalog](../../../core-data-structures/core.md) documents the *vocabulary* those signatures move — but neither documents the *tools* the agent is offered. This RFC adds that third reference surface, `docs/tool-catalog.md`, and a freshness gate so it cannot drift.
 
 ## Decision
 

docs/rfc/implemented/process/2026-07-03-documentation-graph-atlas.md

@@ -4,7 +4,7 @@ Status: implemented
 
 ## Problem
 
-The repo already had several high-trust documentation surfaces, each on a different axis: [module-graph.md](../../../module-graph.md) is generated from package `peerDependencies`, the generated [Cordis events](../../../cordis-catalog/events.md) and [services](../../../cordis-catalog/services.md) catalogs are generated from Cordis `Events` and `Context` declarations, [tool-catalog/tools.md](../../../tool-catalog/tools.md) is generated by booting shipped tool plugins, and [core-data-structures/](../../../core-data-structures/core.md) uses `ts type-equiv` blocks to keep pasted type definitions synchronized with source.
+The repo already had several high-trust documentation surfaces, each on a different axis: [module-graph.md](../../../module-graph.md) is generated from package `peerDependencies`, the generated [Cordis events](../../../cordis-catalog/events.md) and [services](../../../cordis-catalog/services.md) catalogs are generated from Cordis `Events` and `Context` declarations, [tool-catalog.md](../../../tool-catalog.md) is generated by booting shipped tool plugins, and [core-data-structures/](../../../core-data-structures/core.md) uses `ts type-equiv` blocks to keep pasted type definitions synchronized with source.
 
 Those references are accurate, but they are mostly catalogs. A maintainer still has to synthesize the relationships: which packages form a capability seam, which app bundles a concrete spine, which event is durable vs live, where a hook or policy plugin can intercept work, and which model-facing tool depends on which service. An SDK user has the same problem from another angle: "Which package do I install or load for the behavior I want, and which event/service/tool do I extend?"
 
@@ -31,7 +31,7 @@ The first index links ten relationship surfaces. Package topology and tool-packa
 | Graph | Maintenance mode | Source of truth |
 |---|---|---|
 | [module dependency graph](../../../module-graph.md) | generated | `packages/*/*/package.json` peer dependencies plus package group paths |
-| [tool schema catalog and package map](../../../tool-catalog/tools.md) | generated | boot-harvested tool schemas plus tool-package service/effect metadata |
+| [tool schema catalog and package map](../../../tool-catalog.md) | generated | boot-harvested tool schemas plus tool-package service/effect metadata |
 | [capability seams and core services](../../../capability-seams.md) | hybrid generated | Cordis service declarations plus a role manifest in `gen-doc-graphs.ts` |
 | [echo-agent app composition](../../../../examples/echo-agent/composition.md) | hybrid generated | `examples/echo-agent/cordis.yml` plugin list plus curated app/bundle expansion |
 | [coding-agent app composition](../../../../examples/coding-agent/composition.md) | hybrid generated | `examples/coding-agent/cordis.yml` plugin list plus curated app/bundle expansion |

docs/rfc/implemented/process/2026-07-04-persistence-log-catalog.md

@@ -8,7 +8,7 @@ The session event log is the harness's on-disk contract: every `SessionEventMap`
 
 ## Decision
 
-Generate `docs/persistence-catalog/log-events.md` from source, with a freshness gate, as the fourth reference surface: the *records* a persisted session log can contain, complementing the cordis catalog (wiring), core-data-structures (vocabulary), and the tool catalog (tools).
+Generate `docs/persistence-catalog.md` from source, with a freshness gate, as the fourth reference surface: the *records* a persisted session log can contain, complementing the cordis catalog (wiring), core-data-structures (vocabulary), and the tool catalog (tools).
 
 `scripts/gen-persistence-catalog.ts` is a pure TypeScript-AST pass, like `gen-cordis-catalog.ts` — log events ARE statically knowable: every member is a string-literal-named property with a static type annotation, so the AST is the whole truth. The walk collects every `interface SessionEventMap` declaration under `packages/*/*/src` — the owning top-level interface and every `declare module '@deepseek-ai/dsh-session'` merge — so a brand-new event, core or merged, appears in the next regenerate and an un-regenerated file fails `--check` (`verify-persistence-catalog`, a `doc-sync` member, so pre-push and CI both run it). Each entry renders the member's JSDoc prose, its payload (printed through the TypeScript printer, so a newline-separated multi-line type literal still yields a valid one-line fragment), a surface badge, cross-links into core-data-structures, and the declaration's source pointer, grouped by scope.
 

docs/rfc/implemented/process/2026-07-06-export-surface-jsdoc-gate.md

@@ -0,0 +1,43 @@
+# RFC: Export-surface JSDoc gate
+
+Status: implemented
+
+## Problem
+
+The [cordis JSDoc completeness gate](2026-07-04-cordis-jsdoc-completeness-gate.md) made undocumented parameters and results impossible on the cordis surface — `interface Events` members and `ctx.<key>` service classes — but that surface is a fraction of what a plugin author imports. The AGENTS.md rule "every export (and non-obvious method) has a JSDoc explaining semantics" stayed prose-checkable only by review everywhere else, and nothing at all asked for `@param`/`@returns` on ordinary exported functions. A survey at adoption found 203 under-documented module-level exports across 34 packages: seam-adjacent helpers (`runBash`, `readForEdit`, `htmlToMarkdown`), format codecs, whole undocumented interfaces and type aliases — exactly the names an IDE consumer hovers.
+
+## Decision
+
+A new gate, `scripts/verify-export-jsdoc.ts` (`pnpm run verify-export-jsdoc`, wired into `doc-sync` beside `verify-cordis-catalog`), walks every module-level exported name under each `packages/<group>/<pkg>/src/` tree. The parsing and check helpers moved from `gen-cordis-catalog.ts` into a shared `scripts/jsdoc.ts`, so "documented" means the same thing on both surfaces: description prose ends at the first block tag, every checkable parameter needs a non-empty `@param`, a non-void ANNOTATED return needs a non-empty `@returns`, a stale `@param` errors, and violations aggregate into one report.
+
+The contract by declaration kind:
+
+- Every exported name needs JSDoc with non-empty description prose.
+- Function-like exports (function declarations; consts with function initializers or an INLINE callable annotation; non-identifier function default exports) follow the full function contract, with wrapper expressions (parentheses, `as`/`satisfies` casts, non-null assertions) peeled before classifying. A const whose declarator is annotated with a NAMED type (`export const f: Handler = …`) defers the signature contract to that type's own declaration and `@returns` stays optional; an inline `(x: T) => U` annotation or single-call-signature literal is the surface signature itself and gets the full contract, and a literal mixing call/construct signatures with anything else is refused outright (no single signature to hold the tags against — extract a named type).
+- Exported classes need class-level prose; public methods (statics included — reachable on the exported name) follow the function contract; public properties and accessors need prose (a get/set pair is covered by the getter). Overload implementations are exempt — the signatures carry the docs.
+- Exported interfaces, type aliases, and enums need prose on the declaration; member-level enforcement is deliberately deferred (the highest-value member surface — seam service classes — is already under the cordis gate).
+- Exported namespaces recurse (inside an ambient `declare` namespace every member exports implicitly); the namespace itself needs prose only when it does not merge with a documented same-name declaration (the Config-namespace idiom documents the plugin once).
+- `declare module` / `declare global` bodies and `export … from` re-export statements are skipped: an augmentation is not an export of the package, and a re-exported definition is checked where it is defined. An `export import X = N.member` alias documents ITSELF — its target may be a non-exported namespace member no walk visits — and only prose-only target kinds are gate-supported: a callable, class, or namespace target carries signature/member contracts the alias prose cannot hold, so the gate refuses it and demands the declaration be exported directly.
+- Everything else fails CLOSED: `export =` is refused outright, parameters the base never names keep their `@param` duty even as binding patterns, and an exported statement kind the dispatch does not recognize is itself a violation — no export form can pass unchecked by omission.
+
+Three exemption families keep the gate from demanding boilerplate, in the spirit of the cordis gate's `this`/`next` exemptions (documenting an exempt name anyway is allowed; only absence goes unchecked):
+
+- **Heritage members.** A class member whose name exists on an `extends`/`implements` heritage type is exempt: the seam declaration is the doc's one home, and the IDE inherits it on hover — re-documenting every `LocalBashExecutor.run` invites drift. The exemption stops where the override grows surface the base never documented: a protected-only base member does not exempt a public override, parameters the base never names keep their `@param` duty (an underscore-prefixed rename of a base parameter — the deliberately-unused marker — is the same parameter), and a concrete result above a void base return keeps its `@returns` duty (an unannotated override's inferred return is classified by the checker, so a faithful void override needs no boilerplate annotation). Heritage lookups and that one return classification are the walk's only TYPE CHECKER questions (heritage types live across package boundaries, resolved through the repo `paths` map); everything else stays pure AST, and the annotated-return requirement is kept for symmetry with the cordis gate (it bound nothing at adoption — every exported function was already annotated).
+- **Plugin-protocol slots.** Top-level `name` / `inject` / `reusable` / `Config` consts and the `apply` entry, plus the same slots as statics on a plugin class, are framework protocol: their shape is fixed by cordis, and the module doc comment plus the `interface Config` carry the plugin's real semantics.
+- **Constructors**, mirroring the cordis gate: plugin classes are framework-constructed, and the class doc owns the story.
+
+`collectExportJsdocViolations()` returns the violation list (the CLI exits 1 on non-empty) so the negative-path tests in `packages/core/agent/tests/verify-export-jsdoc.spec.ts` assert on findings directly, driving fixture packages through every rejection and every exemption.
+
+## Alternatives considered
+
+- **eslint-plugin-jsdoc** (`require-jsdoc`/`require-param`/`require-returns`) — covers the mechanical core but cannot express the repo's contract: the heritage-member exemption needs cross-package type resolution, the protocol-slot and namespace-merge idioms are cordis-specific, and the completeness semantics (prose-above-tags, stale-tag errors, aggregate reporting) already have one home in `scripts/jsdoc.ts` shared with the catalog generator. Two subtly different definitions of "documented" is the failure mode this repo's one-home rule exists to prevent.
+- **Extending `gen-cordis-catalog.ts`** — the catalog generator renders a curated surface and gates its freshness; a repo-wide walk has no catalog to render. Sharing the helpers while keeping the walks separate keeps each gate's scope legible.
+- **Enforcing interface/type-alias member docs** — deferred: it would multiply the checked surface for members that are largely self-describing fields, while the seam classes carrying the load-bearing member contracts are already gated. Revisit if member-doc drift shows up in review.
+
+## Consequences
+
+- A new export cannot land undocumented: `verify-export-jsdoc` fails `doc-sync`, which pre-push and CI already run. The 203 gaps found at adoption were filled in the same change, so the gate landed green.
+- Exported functions must annotate return types (universal at adoption, now load-bearing) and use identifier parameters where `@param` must name them.
+- Seam docs are canonical: an implementation inherits its heritage docs, and behavior notes worth keeping on the implementation are additions, not requirements.
+- The gate builds a `ts.Program` (~6s) — the one doc gate that pays for type resolution; acceptable inside `doc-sync`, which already compiles doc snippets.
+- The protocol-slot names are reserved by convention at module top level; a non-protocol export coincidentally named `apply` or `Config` would go unchecked — accepted, documented here.

docs/rfc/implemented/process/2026-07-06-generated-config-catalog.md

@@ -0,0 +1,38 @@
+# RFC: Generated plugin config catalog
+
+Status: implemented
+
+## Problem
+
+The config surface — the exact set of fields a `cordis.yml` entry's `config:` block can set for each plugin, with types, defaults, and semantics — had no reference page. A deployment author assembling a config tree had to open every plugin's source (or trust its README) to learn what is settable. The per-package README `## Config` sections cover parts of it by hand, in formats that diverged package-by-package (a key/default table here, an annotated YAML snippet there) and with no gate tying them to source. Nothing enumerated which packages are loadable at all — plugin vs abstract seam vs plain library — and nothing verified that the runtime schemastery schema and the documented `Config` interface agree, so a schema-validated field could exist with no documentation anywhere.
+
+## Decision
+
+Generate the catalog from source: `scripts/gen-config-catalog.ts` emits [docs/config-catalog.md](../../../config-catalog.md), one section per configurable package containing the VERBATIM config declaration — the `export interface Config` (or equivalently named type) with its JSDoc, pasted as-is in a ` ```ts config-catalog ` fence — plus a `Requires:` line (the plugin's `inject`), a `Depends on:` line resolving every type name the paste references, and a source pointer. The paste is the plugin's full declared config type: a field the runtime schema deliberately excludes is a runtime-only seam, marked as such by its own JSDoc, not a `cordis.yml`-settable knob. Package-local referenced types are pasted transitively into the same fence; another plugin's config type links to that plugin's section; names in the cordis catalog's shared `LINK_MAP` link to core-data-structures; any other workspace type links to its source; an external type is named with its module. It mirrors the `gen-cordis-catalog` pattern exactly: `--write` regenerates, `--check` (`verify-config-catalog`, inside `doc-sync`) fails if the committed file is stale, output is deterministic, the file is a build artifact never hand-edited.
+
+Pure AST generation is correct here for the same reason it is for the events/services catalog and NOT for the tool catalog: a config type is a static declaration and every schemastery schema in the repo is a static `z.object`/`z.intersect` literal, so the source is the whole truth — nothing about the config surface is runtime-composed.
+
+Specific choices:
+
+- **The config type is the second-parameter type.** What the catalog documents is the declared type of `apply(ctx, config)` / the service constructor's `(ctx, config)` — the value cordis actually passes — not a `Config` export located by naming convention. This is what makes the walk total: it works for interfaces named `AcpConfig` or `BasicCompactConfig`, for types declared in a sibling file, and for plugins with no validating schema at all.
+- **Classification is total.** Every `packages/<group>/<pkg>` entry resolves, mirroring the Loader's `unwrapExports` (`exports.default ?? exports`), to a configurable plugin, a config-free plugin, an abstract seam class, or a library — each rendered in its own section — and an unclassifiable entry hard-errors. A new package cannot be silently undocumented.
+- **Per-field JSDoc is enforced.** Every property of a pasted declaration (nested type literals included) needs non-empty JSDoc prose, or generation fails. The paste IS the documentation, so this is the same forcing function the events catalog applies via `@mode`: thin source docs fail the gate rather than yielding a thin catalog.
+- **The schema is cross-checked, one-directionally, nested keys included.** When a plugin declares a schemastery schema (`export const Config` / `static Config`), the generator walks it statically — object-literal keys and their nested object/array compositions as key paths (`agents[].id`), chained refinements, and `z.intersect` composition across workspace packages — and every schema-validated key path must be locatable on the declared config type, resolving package-local and workspace-imported types (re-export chains included), intersections, unions, utility wrappers, and indexed access. So the paste cannot hide a loader-accepted field, top-level or nested. The check is presence-only and fails loud only on a definite miss: a path crossing a type the walk cannot enumerate (an external package's type) is skipped rather than mis-reported, and dynamic-key shapes (`z.dict`) or union alternatives contribute no nested paths. The reverse direction is deliberately unchecked: a declared field may be a runtime-only seam the schema excludes (the ACP bridge's test-injected `stream`).
+- **A dedicated fence.** Pasted declarations use a ` ```ts config-catalog ` info string that `doc-typecheck` skips (a lone declaration referencing imported types is not standalone-compilable), excluded from the opt-out ratio — the same treatment the `cordis-catalog` and `persistence-catalog` fences get.
+- **A single file at `docs/config-catalog.md`**, not a one-file directory: the page serves one audience (the `cordis.yml` author) with one axis, unlike `cordis-catalog/`, which holds two sibling pages.
+
+The package README `## Config` sections stay. The overlap is accepted deliberately: the README is the curated per-package contract (config semantics in deployment context, alongside limitations and extension points), the catalog is the exhaustive generated enumeration. Because the catalog is generated, a disagreement between the two indicts the README, and the fix is a README edit — the catalog cannot drift.
+
+## Alternatives considered
+
+- **Synthesized per-field rendering** — a bullet list, table, or annotated-YAML snippet per field, assembled from parsed JSDoc plus schema metadata. Rejected for the verbatim paste: the interface with its JSDoc is already the authored contract in its authored form, and a synthesizing renderer re-formats prose it does not own, adding a rendering layer that can misrepresent it.
+- **Runtime boot + schema introspection, as the tool catalog does** — rejected: nothing here is runtime-composed, and the schema alone under-documents the surface (prose-documented defaults, runtime-only fields, plugins with no schema at all). Booting would add fragility without adding truth.
+- **Two-directional schema/interface equality** — rejected for the subset check: the declared type legitimately carries members the schema refuses to accept from config (runtime-only seams).
+- **Retiring the README `## Config` sections in the same change** — rejected: the accepted duplication keeps the per-package contract readable in place, and a sweep would have to fold each README's extra facts into field JSDoc first — separable work the catalog does not depend on.
+
+## Consequences
+
+- The catalog cannot drift: a source change the committed file does not reflect fails `verify-config-catalog` in pre-push and CI. An undocumented config field, an unresolvable referenced type name, or a schema key missing from the config type fails the generator outright.
+- Config prose now has a forcing function at the declaration: writing a new config field means writing its JSDoc, which becomes the catalog entry verbatim.
+- The generator hard-errors on shapes it cannot walk statically — an aliased package-local config import, a schema built by anything other than `object`/`intersect` composition, an unlisted global type name. Introducing such a shape includes teaching the generator (or the shape stays out of the repo), which is the point: the catalog stays the whole truth.
+- `gen-cordis-catalog.ts` exports its JSDoc/pointer helpers and `LINK_MAP` for reuse, so the two catalogs cross-link types identically and a link-map addition serves both.

docs/rfc/implemented/process/2026-07-06-node-engine-floor.md

@@ -0,0 +1,37 @@
+# RFC: Raise the Node LTS engine floor to 22.19
+
+Status: implemented
+
+## Problem
+
+The Node 22 branch of the root `engines.node` range is a contract for the installed workspace, not only for the runtime APIs the harness source calls directly. It must be no lower than package `engines.node` declarations for dependencies the workspace installs on that branch; otherwise `pnpm install --engine-strict` fails at an advertised LTS version, and non-strict installs run outside a dependency's supported runtime.
+
+## Decision
+
+Set `engines.node` to `^22.19.0 || >=24.0.0` and test the keyless CI compatibility matrix on `['22.19', 24, 26]`. The real-API e2e workflow stays on Node 24 because it exercises API integration rather than the runtime floor.
+
+Two Node features gate the source runtime:
+
+- **`node:sqlite`** — `packages/session-persistence/session-persistence-sqlite` does a top-level `import { DatabaseSync } from 'node:sqlite'`. The module dropped its `--experimental-sqlite` flag requirement at **22.13** (LTS) and **23.4** (Current); before those, importing it throws at load.
+- **Native TypeScript type-stripping** — the `packages/ui/stdio-agent/tests/built-bin.e2e.ts` smoke boots the published `lib/bin.js` under plain `node` (no tsx) and loads the example's `.ts` plugins (`mock-llm.ts`, `echo-tool.ts`). Type-stripping is the default from **22.18** (LTS) and **23.6** (Current); before those it needs `--experimental-strip-types`.
+
+Those source features clear on the 22.x line at **22.18**, but the installed Pi adapter dependency raises the advertised LTS floor. `@deepseek-ai/dsh-llm-pi-ai` depends on `@earendil-works/pi-ai@0.79.3`, whose package declares `engines.node >=22.19.0`, so the LTS floor is **22.19**. The 24.x branch remains `>=24.0.0`. The disjoint range excludes Node 23 entirely: Node 23.0–23.5 still has at least one flagged source feature, and the 23 line is non-LTS/EOL, so advertising `>=23.6` would add a dead release line and a CI leg no deployment should use.
+
+`@types/node` remains pinned to the 22.x line (`^22.20.0`) to match the LTS support line: reaching for a Node 23+/24+/25+ API fails `tsc` on every machine and in the typecheck gate, rather than compiling clean and surviving to a runtime failure only a floor matrix leg could catch. The whole tree typechecks clean against the Node 22 type surface today, so the pin costs nothing.
+
+## Consequences
+
+- The advertised LTS branch no longer undercuts the Pi adapter dependency floor.
+- CI proves the Node 22 LTS floor directly with Node 22.19, keeps the Node 24 branch on `node: 24`, and keeps Node 26 for the next even line.
+- The built-bin smoke needs no version-conditional flag: at 22.19 type-stripping is already the default, so the test stays the plain `node lib/bin.js` path it documents.
+- A future dependency or source API that raises the runtime floor must move `engines.node`, the compatibility matrix, and this RFC in the same change.
+
+## Alternatives considered
+
+- **Keep `^22.18.0 || >=24.0.0`.** Rejected: it advertises an LTS version lower than the Pi adapter dependency floor. `@earendil-works/pi-ai@0.79.3` requires `>=22.19.0`.
+- **Downgrade or pin `@earendil-works/pi-ai` to preserve the 22.18 advertised range.** Rejected: the current Pi adapter dependency is part of the intended workspace, and 22.19 is still inside the Node 22 LTS line.
+- **Floor `>=22.13` (the `node:sqlite` boundary) plus `--experimental-strip-types` in the built-bin smoke on 22.13–22.17.** Rejected: it adds a version-conditional test flag for one narrow range and dresses up an experimental-flag dependency as first-class support. The Pi adapter dependency already requires a higher LTS floor.
+- **Open-ended `>=22.19`.** Rejected: it advertises support for Node 23.0–23.5, where `node:sqlite` (until 23.4) or type-stripping (until 23.6) is still flagged.
+- **Include Node 23.6+ (`^22.19.0 || >=23.6.0`).** Rejected: 23.6+ does run both source features unflagged, but Node 23 is end-of-life; advertising a dead release line adds a range term and a CI leg for a runtime no deployment should use.
+- **Matrix `[22, 24, 26]` instead of pinning `22.19`.** Rejected: floating major-version entries drift upward over time and silently stop exercising the declared LTS floor.
+- **Keep `@types/node` ahead of the floor (`^25`).** Rejected: types ahead of the runtime floor let a Node 24/25-only API compile clean and fail only at runtime on 22.x. Pinning `@types/node` to the 22.x line turns that into a compile error everywhere.

docs/rfc/implemented/process/2026-07-06-parallel-github-ci-gates.md

@@ -0,0 +1,39 @@
+# RFC: Parallel GitHub CI gates
+
+Status: implemented
+
+## Problem
+
+The keyless GitHub CI gates are mostly orthogonal: typecheck, lint, documentation freshness, coverage, snapshot replay, build, package-publication hygiene, demo smoke, and built-bin smoke fail for different reasons and do not need each other's runtime state. Running them as one ordered command chain makes the workflow wall clock equal the sum of those gates, while splitting every leaf gate into its own GitHub job repeats checkout, Node setup, pnpm restore, and install work until orchestration overhead becomes the bottleneck.
+
+The hard part is the artifact boundary. `publint`, `verify-node-next-types`, and built-bin smoke tests need the built `lib/` outputs, while most gates only need source and dependencies. A blind fan-out either races those artifact consumers before `pnpm run build` has emitted declarations and bundles, or repeats the build in every artifact-dependent job.
+
+## Decision
+
+[CI](../../../../.github/workflows/ci.yml) keeps the keyless workflow to a few broad jobs instead of one job per gate. The Node 24 matrix has five lanes: static gates (`pnpm run check:ci:static`), lint (`pnpm run check:ci:lint`), coverage (`pnpm run check:ci:coverage`), snapshot replay (`pnpm run check:ci:snapshot`), and artifact gates (`pnpm run check:ci:artifacts`). The Node 26 compatibility job installs once and runs `pnpm run check:node-compat`.
+
+Each lane delegates to [scripts/run-gates.ts](../../../../scripts/run-gates.ts), an in-process scheduler with bounded concurrency (`DSH_GATE_CONCURRENCY`). The static lane fans out constraints, the echo-agent demo smoke, `doc-sync` leaf gates, module-graph freshness, and `knip`; the lint lane runs ESLint with its own Node heap cap and a content-strategy ESLint cache; the coverage lane runs Vitest coverage with bounded file workers (`DSH_COVERAGE_MAX_WORKERS`); the snapshot lane isolates replay; the artifact lane builds once and then fans out the artifact consumers; the Node 26 compatibility job owns the TypeScript typecheck. The scheduler buffers each gate's output and prints a named result block with duration, so independent failures stay attributable inside each broad job log.
+
+Generated `.sessions/` logs and `.doc-typecheck-*` temp directories are ignored by lint. The aggregate local CI mode still runs demo smoke after lint, while the split GitHub static lane can run demo smoke directly because lint is isolated in its own lane.
+
+Build output is produced once inside the Node 24 artifact lane. The artifact consumers (`publint`, `verify-node-next-types`, and built-bin smoke) declare a dependency on `build`, so there is no upload/download handoff and no consumer can race ahead of declarations or bundles. The CI coverage reporter is text-only while local coverage keeps the HTML report.
+
+Both CI workflows cache the pnpm store after enabling Corepack. The real-API e2e workflow also uses the shared `vitest.e2e.config.ts` bounded file pool (`DSH_E2E_MAX_WORKERS=14` in CI), so its speedup comes from dependency-cache reuse plus lower-level test-file fan-out instead of a separate GitHub job split.
+
+## Alternatives considered
+
+- **Keep the full serial chain in a Node matrix** - simplest to reason about, but it duplicates repo-wide gates that do not produce Node-version-specific signal and leaves every PR waiting for the sum of all gates.
+- **Run every gate as a separate GitHub job** - maximizes GitHub-visible fan-out, but it creates too many checks and pays repeated setup/install overhead for gates whose runtime is shorter than the runner preparation.
+- **Upload build artifacts to artifact-dependent jobs** - preserves correctness across many jobs, but it adds artifact upload/download time and keeps the workflow wide when the artifact consumers can run behind a local dependency in the primary job.
+- **Run `typecheck` and `build` concurrently** - exposes more work to the scheduler, but both commands invoke `tsc -b`; sharing incremental build state between them is a needless race for a small wall-clock gain.
+- **Use unbounded real-API e2e parallelism** - rejected because the suite includes many live model/tool scenarios; the worker pool needs an explicit `DSH_E2E_MAX_WORKERS` cap so CI and local runs can fan out without hiding quota or resource problems behind flaky rate-limit failures.
+
+## Consequences
+
+PR feedback arrives as a few GitHub checks with structured per-gate log blocks inside each broad job. That keeps runner setup overhead bounded and the Actions UI compact, at the cost of losing one status check per leaf gate.
+
+The broad-lane split repeats checkout, setup, and install more often than a single primary job. That setup cost is intentional: on GitHub's hosted runner, running lint, coverage, and snapshot replay in one process pool oversubscribes CPU badly enough that the single-job critical path is longer than the repeated setup.
+
+The split introduces a maintenance obligation: when `package.json` adds or removes a gate that belongs in CI, [scripts/run-gates.ts](../../../../scripts/run-gates.ts) needs the matching leaf. That obligation is intentional because the runner is the parallel execution plan for the same gate vocabulary, not a separate quality policy.
+
+The Node 26 signal is narrower than the primary Node 24 signal. It proves the source graph on the newer runtime without doubling documentation, coverage, publication, snapshot, and smoke checks whose failures are not expected to vary by Node minor version.

docs/rfc/implemented/process/2026-07-06-parallel-pre-push-gates.md

@@ -0,0 +1,40 @@
+# RFC: Parallel pre-push gates
+
+Status: implemented
+
+## Problem
+
+The pre-push hook is the last local checkpoint before a branch leaves the machine, so its wall clock directly shapes whether contributors keep it enabled and trust its signal. Lefthook already runs top-level jobs in parallel, but aggregate jobs such as `pnpm run hygiene` and `pnpm run doc-sync` hide long sequential chains inside one job. The hook can therefore be configured as parallel while still waiting on serial subcommands whose members are independent.
+
+Flattening those members directly into `lefthook.yml` solves the local hook only. CI has the same scheduling problem, and duplicating a long leaf list in YAML gives future script changes two places to drift.
+
+`publint` has the same shape one level lower. Each package is linted independently against its own manifest and built output, but the runner loops through every package in order. On this repo that makes one package-publication gate consume time proportional to the number of packages even though the checks do not share mutable state.
+
+## Decision
+
+[lefthook.yml](../../../../lefthook.yml) keeps one pre-push job named `full check` and runs `pnpm run check:pre-push`. That package script delegates to [scripts/run-gates.ts](../../../../scripts/run-gates.ts), the same bounded scheduler CI uses.
+
+The `pre-push` mode expands into leaf gates for the unit suite, snapshot suite, build, `hygiene` members, `doc-sync` members, and module-graph freshness. The leaf list keeps the same gate vocabulary as the package scripts, including RFC classification and RFC format, while the runner schedules independent checks concurrently and prints one timing/output block per gate.
+
+The build gate makes the hook self-contained from a clean worktree. `publint` and `verify-node-next-types` wait for that build output, while source-only gates continue in parallel.
+
+[scripts/publint-all.ts](../../../../scripts/publint-all.ts) discovers the package list from `packages/<group>/<pkg>` and runs `publint` with a worker pool sized from `availableParallelism()`. `DSH_PUBLINT_CONCURRENCY` can cap or raise the worker count for local machines and CI runners with different resource profiles. Results are buffered per package and printed in deterministic package order, so parallel execution does not scramble each package's log block.
+
+The aggregate package scripts remain the source of truth for ad hoc local runs. The scheduler is a parallel execution plan over their member gates, not a replacement vocabulary.
+
+## Alternatives considered
+
+- **Keep aggregate `hygiene` and `doc-sync` jobs in the hook** - simpler config, but it leaves most of the pre-push wall clock inside serial command chains that lefthook cannot see or schedule.
+- **Declare one lefthook job per leaf gate** - exposes parallelism through lefthook's native job model, but it makes the hook file carry a long member list that CI cannot reuse.
+- **Require developers to build before pushing** - avoids one hook gate, but it makes `publint` fail in a clean worktree and turns the final local checkpoint into a convention instead of a runnable check.
+- **Background subcommands inside shell scripts** - can parallelize work, but it loses lefthook's job names, per-job timing, and failure grouping, and makes signal handling harder to reason about.
+- **Declare one publint lefthook job per package** - exposes maximum parallelism, but it turns the hook into a hand-maintained package inventory that drifts exactly when new packages are added.
+- **Run publint with unbounded concurrency** - minimizes elapsed time on small machines only by gambling with process count, memory pressure, package tarball creation, and readable logs.
+
+## Consequences
+
+The hook's critical path becomes the slowest real gate instead of the sum of hidden gate chains. Lefthook reports one `full check` job, and the runner reports per-gate timing inside that job, so a slow local checkpoint still points at the gate that dominates the run.
+
+The hook file stays short, and the duplicated member list lives in [scripts/run-gates.ts](../../../../scripts/run-gates.ts), where CI and pre-push can share it. The cost is a custom scheduler script instead of pure lefthook configuration, plus a build in the local pre-push path.
+
+`publint-all.ts` becomes asynchronous code and buffers command output instead of inheriting stdio live. The payoff is package-level parallelism with stable output order and one environment variable for resource tuning.

docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md

@@ -51,7 +51,7 @@ The ACP server app loads `@deepseek-ai/dsh-llm-deepseek`, whose `apply` throws w
 A snapshot run asserts **two** normalized surfaces, because the harness's external surfaces are distinct:
 
 1. The **stdout transcript** — the framed `session/update` JSON-RPC the editor sees. Catches regressions in the ACP bridge's event→update translation (`streamSessionEventUpdate`). Compared against a committed `stdout.golden.jsonl`.
-2. The **re-persisted session JSONL** — the log the replay run itself persists, compared against the scenario's `session.jsonl`. Catches regressions in the loop, tool dispatch, and turn/step structure that never surface on stdout. There is no separate session golden: `session.jsonl` is BOTH the replay source (recorded scenarios) and the expected produced log. Both sides pass through `normalizeSessionLog` before comparing — the fixture is raw-harvested (its own real session id / cwd / timestamps) and the replay output has fresh ones, so each is scrubbed against ITS OWN volatile values (the fixture's read from its header line) and the comparison is on normalized form. For an authored override scenario the same `session.jsonl` holds the expected produced log; `replay.override.json` drives the model, and `llm-replay` ignores the fixture for model chunks when an override exists, so committing the expected log there does not affect replay.
+2. The **re-persisted session JSONL** — the log the replay run itself persists, compared against the scenario's `session.jsonl`. Catches regressions in the loop, tool dispatch, and turn/step structure that never surface on stdout. There is no separate session golden: `session.jsonl` is BOTH the replay source (recorded scenarios) and the expected produced log. Both sides pass through `normalizeSessionLog` before comparing — the fixture is raw-harvested (its own real session id / cwd / timestamps) and the replay output has fresh ones, so each is scrubbed against ITS OWN volatile values (the fixture's read from its header line) and the comparison is on normalized form. Request-header CONTENT (the composed system prompt + tool schemas) is additionally scrubbed to `{{system}}`/`{{tools}}` tokens on both sides — in the stored fixtures too — for every scenario except the one that pins it ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)). For an authored override scenario the same `session.jsonl` holds the expected produced log; `replay.override.json` drives the model, and `llm-replay` ignores the fixture for model chunks when an override exists, so committing the expected log there does not affect replay.
 
 The two are genuinely additive: stdout is the bridge's *lossy projection* of the log (it drops `assistant/message.usage`, `step/*`, exact `seq`/`time`, and renders tool I/O differently), so a loop/tool/turn-structure regression can change the JSONL while leaving the stdout projection identical, and a bridge-translation regression can change stdout while the JSONL is untouched. Asserting the JSONL equality also echoes the proposed [universal replay fixture](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md) idea.
 

docs/rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md

@@ -12,7 +12,7 @@ This RFC records the decision to add a **second, secret-consuming workflow** tha
 
 ## Decision
 
-Add a dedicated workflow, [.github/workflows/e2e.yml](../../../../.github/workflows/e2e.yml), separate from ci.yml. It runs only `pnpm run test:e2e` against the external API using a repo secret, on trusted events, with a preflight that converts a missing secret into a loud failure instead of a false green. ci.yml is left untouched.
+Add a dedicated workflow, [.github/workflows/e2e.yml](../../../../.github/workflows/e2e.yml), separate from ci.yml. It runs only `pnpm run test:e2e` against the external API using a repo secret, on trusted events, with a preflight that converts a missing secret into a loud failure instead of a false green. The keyless workflow remains separate so forkable quality gates and secret-consuming real-API gates keep different trigger and credential policies.
 
 ### A separate workflow, not a job in ci.yml
 
@@ -20,7 +20,7 @@ ci.yml's value is that it is keyless, forkable, and always-green: any contributo
 
 ### Cost is not the constraint; reliability is
 
-The usual reason to ration real-API CI — token cost — does not apply here: we are DeepSeek and internal inference is effectively free. So the design optimizes for *coverage and signal*, not for minimizing calls. The suite runs in full (all six `*.e2e.ts` files), on multiple triggers, on every trusted PR. This is the CI embodiment of the [docs/testing.md](../../../testing.md) with-key policy.
+The usual reason to ration real-API CI — token cost — does not apply here: we are DeepSeek and internal inference is effectively free. So the design optimizes for *coverage and signal*, not for minimizing calls. The suite runs in full (all matching `*.e2e.ts` files), on multiple triggers, on every trusted PR. This is the CI embodiment of the [docs/testing.md](../../../testing.md) with-key policy.
 
 ### Triggers: trusted events only
 
@@ -54,7 +54,7 @@ The repo secret is named `DEEPSEEK_API_KEY_EXTERNAL`; it is mapped to the `DEEPS
 
 ### Scope, runtime shape
 
-Run **only** `test:e2e`. The keyless gates (typecheck/lint/coverage/snapshot/build/hygiene) already run in ci.yml on every push and PR; repeating them here would duplicate signal and slow the real-API job. No build step — e2e tests run unbuilt via tsx + the tsconfig paths map. Single Node 24 (the `engines` floor): these tests exercise *API integration*, not node-version compat, which ci.yml's `[24, 26]` matrix already owns; a second Node version would double real-API calls for no added signal. `timeout-minutes: 45` bounds a wedged run given serial files (`fileParallelism: false`), 120s/test, and `retry: 2`. `cancel-in-progress` is enabled only for `pull_request` runs — a superseded PR run is on a stale commit and worth cancelling, whereas a push/schedule run is already producing the post-merge/nightly signal and is never cancelled.
+Run **only** `test:e2e`. The keyless gates (typecheck/lint/coverage/snapshot/build/hygiene) already run in ci.yml on every push and PR; repeating them here would duplicate signal and slow the real-API job. No build step — e2e tests run unbuilt via tsx + the tsconfig paths map. Single Node 24 (the primary line): these tests exercise API integration, not node-version compatibility, which ci.yml's Node 22.19/24/26 matrix owns. `vitest.e2e.config.ts` runs files through a bounded worker pool (`DSH_E2E_MAX_WORKERS`, default `4`, CI value `14`) so CI and local with-key runs parallelize independent files while retaining a one-line serial escape hatch for quota investigations. `timeout-minutes: 45` bounds a wedged run given 120s/test and `retry: 2`. `cancel-in-progress` is enabled only for `pull_request` runs — a superseded PR run is on a stale commit and worth cancelling, whereas a push/schedule run is already producing the post-merge/nightly signal and is never cancelled.
 
 ## Security
 

docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md

@@ -32,4 +32,4 @@ Reviewers lose one artifact name that made the expected persisted log visually s
 
 ## Implementation note
 
-The comparison normalizes BOTH sides, but each against its OWN volatile values, not a shared context. A raw harvested `session.jsonl` bakes in the recording run's session id, cwd, and timestamps; the replay run produces fresh ones. `normalizeSessionLog` scrubs cwd by exact string match, so normalizing the fixture against the *replay* run's cwd would leave the recorded cwd in the header unscrubbed and the compare would fail. The harness therefore derives the fixture's normalize context from its OWN header line (`{ type:'session', id, cwd }`) — `fixtureContext()` in `acp.snapshot.ts` — so both sides scrub to the same `{{sessionId}}`/`{{cwd}}` tokens. An authored fixture copied from the old golden already carries the normalized header (`id:'{{sessionId}}'`, `cwd:'{{cwd}}'`), which yields those tokens as the volatile values and scrubs idempotently. The session-log side uses a plain normalized-string `toEqual`, NOT `toMatchFileSnapshot`, so a run never overwrites the fixture.
+The comparison normalizes BOTH sides, but each against its OWN volatile values, not a shared context. A raw harvested `session.jsonl` bakes in the recording run's session id, cwd, and timestamps; the replay run produces fresh ones. `normalizeSessionLog` scrubs cwd by exact string match, so normalizing the fixture against the *replay* run's cwd would leave the recorded cwd in the header unscrubbed and the compare would fail. The harness therefore derives the fixture's normalize context from its OWN header line (`{ type:'session', id, cwd }`) — `fixtureContext()` in `dsh-acp-snapshot`'s suite module — so both sides scrub to the same `{{sessionId}}`/`{{cwd}}` tokens. An authored fixture copied from the old golden already carries the normalized header (`id:'{{sessionId}}'`, `cwd:'{{cwd}}'`), which yields those tokens as the volatile values and scrubs idempotently. The session-log side uses a plain normalized-string `toEqual`, NOT `toMatchFileSnapshot`, so a run never overwrites the fixture.

docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md

@@ -0,0 +1,32 @@
+# RFC: Pin request-header content in one snapshot scenario
+
+Status: implemented
+
+## Problem
+
+Every model-driving ACP snapshot fixture (`session.jsonl`) embedded the full composed system prompt and the complete tool-schema list in its `request/header` event — roughly 8 KB on one line, per fixture. That content is identical across the suite (byte-identical tool list everywhere, including subagent children; identical prompt modulo each recording's temp cwd), so any change touching a tool description or a system-prompt line had to update every fixture: re-record everything against the live API (churning model responses and stdout goldens along the way) or hand-edit ~35 giant header lines. Introducing the dynamic-workflows feature — one new tool plus one prompt paragraph — rewrote every snapshot fixture in the repo, burying the behavioral diff a reviewer should be reading.
+
+## Decision
+
+Exactly one scenario — `text-turn`, flagged `pinsHeader` in the `acp.snapshot.ts` scenario table — commits and compares the full request-header content; the pin mechanics live in [`dsh-acp-snapshot`](../../../../packages/support/acp-snapshot/README.md), whose suite factory enforces one pin per consuming suite. Every other fixture stores and compares that content as stable tokens via the pure normalizer `scrubRequestHeaders` in that package's `normalize.ts`: a `request/header` event's `header.system` becomes `"{{system}}"` and `header.tools` becomes `"{{tools}}"`; a `request/header-delta` keeps its structural facts — the system delta's `keepStart`/`keepEnd` line positions with one `{{system}}` token per inserted line, the tools delta's added/removed/changed tool names — and tokenizes only the bulk (prompt text, schema bodies), so two different deltas still compare different. The scrub is composed in front of `normalizeSessionLog` on BOTH sides of a non-pinning scenario's log compare and applied to the harvested logs record mode writes, so a re-record cannot smuggle the content back. Absent fields stay absent — WHETHER a header carried a prompt or tools is behavior and stays visible — and `config`/`reason` stay verbatim: a model swap churns every fixture by design (it invalidates the recorded responses), while a prompt or schema edit churns none of them (replay derives model behavior exclusively from `assistant/chunk` events and never reads header content — see `dsh-llm-replay`).
+
+A system-prompt or tool-schema change therefore lands as exactly one committed-fixture diff — the pinned `text-turn` header line — updated by hand or by re-recording that one scenario (`pnpm run test:snapshot:record` with `-t text-turn`).
+
+Guards make the split self-enforcing. On disk (fixture meta-tests): every non-pinning `session*.jsonl` must be a fixed point of `scrubRequestHeaders` (unscrubbed content crept in — apply the scrub), the pinning scenario's fixture must NOT be one (the pin lost its content), and exactly one scenario must pin. Live (every non-pinning scenario run): each `request/header` the run produces — parent, spawn child, fork child, initial or resume — must equal the pinned fixture's header after both sides normalize their own volatile values, and no `request/header-delta` may appear at all (a mid-run header change diverges from the pin by construction, and its content would be invisible under the scrub), so the single-pin premise is asserted rather than assumed.
+
+One pin covers the whole suite because every session — parent, spawn child, fork child — composes the identical tool list and the identical prompt modulo cwd, and the uniformity guard fails the suite the moment that stops holding. If header composition ever becomes session-dependent by design (a restricted subagent toolset, say), the divergent shape gets its own pinning scenario.
+
+## Alternatives considered
+
+- **Re-record or hand-edit every fixture per change** — the status quo; the churn this RFC removes.
+- **Scrub at compare time only, keeping fixtures raw** — the compares go green without fixture edits, but every committed fixture then carries a permanently stale copy of the prompt and schemas: dead weight that misleads readers and still rewrites wholesale on the next re-record. Storing the tokens keeps the fixture honest about what it does and does not pin.
+- **Scrub everywhere, pin nowhere** — loses the only end-to-end record of the composed header as actually sent (prompt assembly, registered-tool order, full schemas). The generated tool catalog documents each tool in isolation; only a real fixture pins the composed set.
+- **Slim the session log itself (log a content digest, store the header elsewhere)** — violates the reconstructability contract: the product log must reproduce each request bit-for-bit ([reconstructable-requests RFC](../architecture/2026-07-05-reconstructable-requests.md)). Header bulk is a test-artifact concern, solved in test normalization; the live log is untouched.
+
+## Verification
+
+All 37 snapshot scenarios replay green with the scrubbed fixtures (the committed fixtures were rewritten once through `scrubRequestHeaders` itself; `text-turn` untouched). The fixed-point, pin-retains-content, exactly-one-pin, live header-uniformity, and no-unpinned-delta guards run inside the suite, and `scrubRequestHeaders` has unit coverage for both header event types, delta structure preservation (line positions, insert arity, tool names), absent-field preservation, config/reason retention, byte-for-byte pass-through of other lines, and idempotence.
+
+## Consequences
+
+A tool-description or system-prompt change churns one committed fixture line instead of every fixture in the suite, so snapshot diffs read as behavior again, and ~270 KB of duplicated header bytes leave the repo. The cost: non-pinning fixtures no longer display header content, so reading one shows tokens where the prompt and schemas were — the pinned `text-turn` fixture is the place to look, and the live uniformity guard guarantees it speaks for every session in the suite. A header change surfaces as a suite-wide test failure whose fix is the one pinned line, rather than as ~35 fixture rewrites.

docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md

@@ -0,0 +1,36 @@
+# RFC: Extract the ACP snapshot suite into a support package
+
+Status: implemented
+
+## Problem
+
+The ACP snapshot tier ([snapshot RFC](2026-06-19-acp-snapshot-tests.md)) was built from three modules living inside one example's test directory: `snapshot-harness.ts` (boot the real bin subprocess, drive it over ACP JSON-RPC, harvest the persisted logs), `snapshot-normalize.ts` (the pure golden normalizers), and the ~150-line scenario body plus fixture guards in `acp.snapshot.ts` (record/replay modes, the stdout-golden and log compares, the pinned-header uniformity guard, the orphan/required-file/single-pin meta-tests).
+
+A second ACP example wanting snapshot coverage — the sandbox/approval composition is the immediate consumer — could only copy those modules, forking exactly the logic that must not drift: record write-back, header scrubbing, child-session harvest ordering. The spawn/client glue was already triplicated across `acp.e2e.ts`, `hooks.e2e.ts`, and the harness (`TODO(acp-test-harness)`). Location also decided test rigor: the per-file 100% coverage gate measures `packages/*/*/src` only, so none of this machinery was measured — the same gap that had moved `dsh-llm-replay` out of `examples/` into [packages/support](../../../../packages/support/README.md). And the harness's ACP client hardcoded `requestPermission → cancelled`, so an approval round-trip — the headline behavior of the sandbox composition — could not be expressed at the snapshot tier at all.
+
+## Decision
+
+The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/support/acp-snapshot/README.md) (`@deepseek-ai/dsh-acp-snapshot`); an example's `*.snapshot.ts` is its scenario table, its agent paths, and one factory call, over its own `snapshots/` fixtures and `cordis.snapshot.yml` overlay ([single-source replay config](2026-07-04-single-source-acp-replay-config.md)). Reading `DSH_SNAPSHOT` stays at that edge — the library takes a resolved `mode`.
+
+**`src/harness.ts`** — `runScenario` and the input-script/result types, parameterized by an `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath`; absolute paths the consuming suite resolves from its own `import.meta.url`). The client's `session/request_permission` handler consumes an optional `InputScript.permissionAnswers` FIFO queue, each entry selecting by option **kind** (ids are agent-issued randoms a committed script cannot know; kinds are the ACP-stable vocabulary, mapped to the offered `optionId` at answer time); an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run — the agent itself is answered `cancelled`, so the scenario bug fails the harness rather than being absorbed as an agent-side denial. This is what lets an approval suite drive allow/reject round-trips deterministically from `input.json`.
+
+**`src/normalize.ts`** — the pure normalizers, hook-free by policy: when a future event carries a new volatile field (an approval duration, say), the shared normalizer learns it in the same change, keeping one home for what "normalized" means rather than per-suite scrub extensions.
+
+**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record-mode fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin, non-pinning fixtures are `scrubRequestHeaders` fixed points). The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each suite flags exactly one `pinsHeader` scenario (the factory throws on zero, a meta-test rejects more than one; WHICH scenario pins is the table's reviewable choice), and the uniformity guard compares only that suite's sessions. The pure helpers (`childFixturePaths`, `fixtureContext`, `normalizedHeaders`, `headerDeltaCount`) are exported for direct unit coverage.
+
+## Alternatives considered
+
+- **Copy the modules into each example** — the fork this RFC exists to prevent: the record/guard logic is exactly the code that must stay byte-identical across suites, and examples are outside the coverage gate, so each copy is also unmeasured.
+- **A shared module directory under `examples/`** — keeps the code outside the coverage gate and forces relative imports across example boundaries, against the package-name import convention; `examples/` leaves stay thin by design.
+- **A `/testing` subpath export of `dsh-acp-agent`** — couples test infrastructure into a product package's surface and dependency set; `packages/support/` exists precisely for real-but-lower-compatibility dev/test packages, with `dsh-llm-replay` as the precedent this package completes.
+- **Export raw test-body functions instead of a suite factory** — each example would re-own the `describe`/`it` skeleton (~80 lines of registration boilerplate per suite) for no flexibility gain; the factory keeps consumers to a scenario table plus one call, and the exported pure helpers preserve unit-testability inside the factory design.
+- **An injectable ACP `Client` factory instead of declarative `permissionAnswers`** — maximally flexible, but it leaks SDK client construction to every consumer and reopens per-example drift in exactly the layer being unified; a declarative queue keeps `input.json` the single scripting surface and stays golden-normalizable.
+- **Generalize beyond ACP (a transport-agnostic snapshot harness)** — no second transport exists; the harness is ACP-shaped end to end (SDK client, JSON-RPC frames, `session/update` waiters), and a speculative abstraction would be a seam split ahead of any consumer.
+
+## Testing
+
+Extraction parity was proven mechanically: after the move, `pnpm run test:snapshot` matched the base commit's result with zero byte changes under `examples/acp-agent/tests/snapshots/`. The package's `src/` holds per-file 100% statements/branches/functions/lines under the gating unit run, driven through the REAL spawn path by a scripted fake ACP bin (`tests/fixtures/fake-acp-agent.ts`, behavior scripted per scenario via a `behavior.json` beside the fixture): `harness.spec.ts` covers every step op, both expect-error arms, the permission queue (selection, fallback, impossible-click), env forwarding, workspace seeding, and the harvest ordering/noise/fallback branches; `suite.spec.ts` runs the factory for real at collection time — a replay suite over committed synthetic fixtures and a record suite over a temp copy (write-back never touches the committed tree; `ACP_SNAPSHOT_SPEC_BOOTSTRAP=1` re-bootstraps it) — plus direct cases for the pure helpers. Two structurally unreachable guards carry reasoned `v8 ignore` comments. The fake bin substitutes the `session/new` cwd, not `process.cwd()`, into scripted logs, matching what the real bin's header carries (darwin realpaths `/var/folders/…` to `/private/var/folders/…`).
+
+## Consequences
+
+A new example gets the whole snapshot tier from a scenario table plus fixtures — the sandbox branch merges master down and adds its own suite (own pin scenario, own overlay, fixtures via `test:snapshot:record`, approvals via `permissionAnswers`). The costs: `suite.ts` imports vitest, so the package is importable only inside a vitest run — a shape no other package has, stated in its README; each suite pins its own ~8 KB header fixture (a genuinely distinct composition deserves its own pin; an identical one would be caught by that suite's uniformity guard); and the e2e launcher duplication remains (`TODO(acp-test-harness)`) — the harness is the extraction target when that migration lands.