@selesai/code 0.13.40 → 0.14.3

package/dist/extensions/pi-subagents/skills/pi-subagents/references/execution-controls.md

@@ -9,7 +9,7 @@ Agent files can live in:
 - `.pi/agents/**/*.md` — canonical project scope
 - legacy `.agents/**/*.md` — still read for compatibility, but `.pi/agents/` wins on conflicts
 
-Saved chain files may still be discovered for management and existing durable run state, but they are not a public execution surface. Author new orchestration with `workflowScript`.
+Saved chain files may still be discovered for management and existing durable run state, but they are not a public execution surface. Author new orchestration as a workflow script.
 
 Precedence is by parsed runtime name:
 1. project scope
@@ -24,7 +24,7 @@ Project settings resolve from the nearest parent directory containing `.selesai`
 
 An agent may set `runner.type: external-cli` with a non-empty `command`, optional string `args`, and `promptDelivery: stdin` (the default). The command runs with `shell: false`, inherits the resolved cwd and environment, and receives the combined agent instructions and task through stdin. It must already be installed; pi-subagents adds no CLI dependency.
 
-External CLI profiles are async-only and one-shot. They support lifecycle artifacts, stdout/stderr logs, timeout, and stop. Full stdout and stderr are retained in their log files, while the final stdout response and stderr error kept in memory are each limited to their last 64 KiB. They do not support native Pi child options such as model override, structured output, acceptance/agent contract, tool budgets, fast mode, fork context, skills, or native Pi tools unless the runner explicitly implements them. Foreground/clarify, steer/resume/interrupt-as-pause, nested subagents, fallbacks, and sessions are also unsupported.
+A command-runner agent with a plain `command` (no adapter) is also how a classifier or scoring script becomes a typed workflow step: the prompt arrives on stdin, stdout is the child's `output`, and the script parses it. Keep `inheritProjectContext`, `inheritGlobalContext`, and `inheritSkills` off unless the command wants that text. External CLI profiles are async-only and one-shot. They support lifecycle artifacts, stdout/stderr logs, timeout, and stop. Full stdout and stderr are retained in their log files, while the final stdout response and stderr error kept in memory are each limited to their last 64 KiB. They do not support native Pi child options such as model override, structured output, acceptance/agent contract, tool budgets, fast mode, fork context, skills, or native Pi tools unless the runner explicitly implements them. Foreground/clarify, steer/resume/interrupt-as-pause, nested subagents, and sessions are also unsupported.
 
 ### External job profiles
 
@@ -32,7 +32,7 @@ An agent may set `runner.type: external-job` with a non-empty `provider` and opt
 
 External job profiles are async-only. The provider owns the remote job and Pi owns the async run record. Status persists provider name, provider job id, prompt digest, provider options, handle/conversation URLs when supplied, result artifact path, last known state, and provider failure code/message. Recovery uses existing provider job metadata to call `reattach` and `result`; it refuses to redispatch a prompt when the persisted provider job does not match the prompt digest.
 
-External job profiles do not support foreground/clarify, steer/resume, Pi models/tools/extensions/skills, tool budgets, structured output, native child permissions, fallbacks, or Pi child sessions. Capacity conflicts fail closed and include the blocking provider job id when the provider supplies it.
+External job profiles do not support foreground/clarify, live steer or native session resume, Pi models/tools/extensions/skills, tool budgets, structured output, native child permissions, or Pi child sessions. Completed external-job runs can use `action: "resume"` for provider follow-up when the registered provider exposes `followUp(input)`; running jobs must finish first, and providers without follow-up support fail closed with an update/reload message. Capacity conflicts fail closed and include the blocking provider job id when the provider supplies it.
 
 ### Single agent
 
@@ -45,16 +45,16 @@ subagent({
 
 Use direct single-agent execution for one bounded task when no stable key,
 branching, retained-child lookup, or aggregate workflow result is needed. Use a
-`workflowScript` when the parent needs JavaScript control flow or data-dependent
+workflow script when the parent needs JavaScript control flow or data-dependent
 branching, or when the run is part of a larger coordinated wave or a later step
 must resume it by key.
 
 ### Forked context
 
-```typescript
-subagent({
-  workflowScript: `return runs.run("oracle-check", { agent: "oracle", task: "Review my current direction and challenge assumptions.", context: "fork" })`
-})
+Write this block in the reply, then call `subagent({ workflow: true })` (see [Scripted workflows](#scripted-workflows)):
+
+```js workflow
+return runs.run("oracle-check", { agent: "oracle", task: "Review my current direction and challenge assumptions.", context: "fork" });
 ```
 
 `context: "fork"` creates a branched child session from the current persisted
@@ -68,7 +68,7 @@ its resolved launch context as `[fresh]` or `[fork]`. Aggregate headers show
 
 ### Scripted workflows
 
-`workflowScript` is the public composition surface when the parent needs
+A workflow script is the public composition surface when the parent needs
 JavaScript control flow or data-dependent branching. Use
 `runs.run(key, { agent, task, ... })` for keyed children, `runs.all([...])` for
 parallel children, and ordinary JavaScript for sequence, filtering, retries,
@@ -80,17 +80,25 @@ workflow whenever the parent is starting a coordinated wave, such as multiple
 reviews, review plus gate monitor, worker then monitor setup, cross-repo prep
 lanes, or a fanout that the parent will consume together.
 
+Write the script as one ```` ```js workflow ```` fenced block in the reply, then
+call `subagent({ workflow: true, ... })` in the same reply. The block is plain
+text, so it needs no JSON string escaping; a line containing only ```` ``` ````
+(three or more backticks) ends it. A reply carries one block and one
+`workflow: true` call. Use `workflow: "./path/to/script.js"` for a script file.
+Later examples that show only a ```` ```js workflow ```` block run with
+`subagent({ workflow: true })`.
+
+```js workflow
+const scan = await runs.run("scan", { label: "Map target behavior", agent: "scout", task: "Map the target" });
+const reviews = await runs.all([
+  { key: "correctness", label: "Review target correctness", agent: "reviewer", task: "Review correctness: " + scan.output },
+  { key: "tests", label: "Review target test coverage", agent: "reviewer", task: "Review tests: " + scan.output }
+]);
+return reviews.map(result => result.output);
+```
+
 ```js
-subagent({
-  workflowScript: `
-    const scan = await runs.run("scan", { agent: "scout", task: "Map the target" });
-    const reviews = await runs.all([
-      { key: "correctness", agent: "reviewer", task: "Review correctness: " + scan.output },
-      { key: "tests", agent: "reviewer", task: "Review tests: " + scan.output }
-    ]);
-    return reviews.map(result => result.output);
-  `
-})
+subagent({ workflow: true, async: true })
 ```
 
 Scripts run in a timed worker with only `runs.run`, `runs.all`, `runs.status`, `runs.ref/refs`, `emit`, captured `console`, and standard JavaScript. Pass explicit task text to `runs.run`. Mission-attached workflows also get `await state.get(key)` and `await state.set(key, value)` for durable JSON state shared across workflows on the same mission; `mission: false` workflows have no `state` global. Stable keys are required. Child launches follow ordinary single-agent execution controls. Give each child a distinct decision and output path when reports must outlive the workflow, then consume the aggregate workflow result before opening individual reports. Do not ask children to write `reports/...` or other repo-root scratch paths in task text.
@@ -99,9 +107,11 @@ If `runs.all` is missing in a running session, reload or update `pi-subagents` b
 
 For one host-run verification command, pass `gate: "npm test"` on a `runs.run`/`runs.all` item (or at the top level as a workflow default). It is shorthand for verified acceptance with that single command: the runtime executes it on the host, records the result as evidence, and memoizes it per tracked workspace state and effective environment. `gate` cannot be combined with `acceptance`; use explicit `acceptance.verify` for multiple commands or custom criteria.
 
+For a typed post-run check, pass the object form `gate: { command, output: "json", schema?, timeoutMs? }`. A passing command must print one JSON document (under 12,000 characters); the parsed value, validated against `schema` when given, becomes the child's `structuredOutput`, so a script can branch on `result.structuredOutput` and `runs.lanes` blocks on `verdict === "blocked"` without the parent reading the child's output. Pair it with `output` + `outputMode: "file-only"` so the command reads the saved file. Empty, non-JSON, or schema-invalid stdout fails the gate and rejects the run. Typed gates are never memoized. A typed gate cannot be combined with an `outputSchema` from the launch or the agent; the launch is rejected before any child starts. See the `tool-reference` guide, "Typed gates".
+
 If omitted, acceptance is inferred from role, mode, and risk. Use `level: "checked"` for ordinary writer evidence and `level: "verified"` when the runtime should run explicit validation commands. Independent review is orthogonal: use `review: { required: true, agent: "reviewer" }`; reviewer/read-only calls omit `acceptance`. `review-required` means evidence passed but review is pending; `reviewed` means an independent review found no blockers. Never request `level: "reviewed"`; it is recognized only so preflight can return an actionable correction. Disable gates with `{ level: "none", reason: "..." }`; bare `"none"` is rejected and `false` is only a deprecated shorthand. Child-reported command success is evidence, not runtime verification.
 
-Completed workflow children from this parent session stay addressable as retained children. `subagent({ action: "children.list" })` lists up to the last 10 with run ids and reports each row as `resumable` or `not resumable` with a reason. Resume only rows reported `resumable`. For a retained-child challenge, use `resume` instead of `steer` when the child is complete. If no retained child is resumable, launch a same-role fallback challenge and label it as fallback. A later workflow continues a resumable child with `runs.run(key, { resume: "<run-id>", task: "follow-up" })`. Inside `workflowScript`, awaiting that call waits for the revived child to finish and returns its completed output and new `runId`; top-level `{ action: "resume" }` remains detached. Pass explicit follow-up task text. Assign each returned child result back to the loop variable because every resume can return a new retained `runId`; always resume the latest returned id. `resume` and `agent` are mutually exclusive, the revived child keeps its stored agent/model/tool contract, and `gate` is rejected on retained resume items.
+Completed workflow children from this parent session stay addressable as retained children. `subagent({ action: "children.list" })` lists up to the last 10 with run ids and reports each row as `resumable` or `not resumable` with a reason. This workflow-only roster is not an exhaustive list of direct native children. Resume only rows reported `resumable`. When the exact run id of an intended direct child is known, inspect it with `subagent({ action: "status", id: "<run-id>" })`; if status identifies the candidate, attempt `subagent({ action: "resume", id: "<run-id>", message: "..." })`. Resume performs the authoritative eligibility check and may reject the attempt. For a retained-child challenge, use `resume` instead of `steer` when the child is complete. Launch a same-role fallback challenge, labeled as fallback, only when no known candidate exists or resume rejects eligibility. A later workflow continues a resumable child with `runs.run(key, { resume: "<run-id>", task: "follow-up" })`. Inside a workflow script, awaiting that call waits for the revived child to finish and returns its completed output and new `runId`; top-level `{ action: "resume" }` remains detached. Pass explicit follow-up task text. Assign each returned child result back to the loop variable because every resume can return a new retained `runId`; always resume the latest returned id. `resume` and `agent` are mutually exclusive, the revived child keeps its stored agent/model/tool contract, and `gate` is rejected on retained resume items.
 
 Each workflow key identifies one result lane: use a new stable workflow key for every distinct retained resume pass; same-key calls are reused only when launch parameters are identical, and incompatible parameters are rejected.
 
@@ -109,6 +119,7 @@ Terminal async workflows also persist `workflow-receipt.json` beside `status.jso
 
 ```js
 return runs.run("cross-oracle", {
+  label: "Challenge proposed direction",
   resume: { workflowRunId: "<pass-1-workflow-id>", key: "advisor-oracle", latest: true },
   task: "Review the focused challenge packet."
 });
@@ -119,8 +130,9 @@ Keyed resume reads that one exact receipt and revalidates the retained run at la
 ### Parallel sequential lanes
 
 For a broad plan with a known set of narrow, visible stages per lane, use
-`runs.lanes(...)` inside a `workflowScript`; it is a nested helper, not a
-top-level `subagent` mode. Give each lane and stage a stable key. The first
+`runs.lanes(...)` inside a workflow script; it is a nested helper, not a
+top-level `subagent` mode. Give each lane and stage a stable key; give stage
+items a short verb + behavior `label`, preserving explicit user labels. The first
 stage from every lane is launched together, then later stages sequence per lane.
 `resume: "previous"` requires the retained predecessor, and a failed or blocked
 stage blocks only that lane. The returned board exposes lane/stage results for
@@ -180,25 +192,26 @@ fleet. If `SELESAI_SUBAGENT_WAIT_TOOL_ENABLED` disables blocking, direct waits r
 immediately, but headless `agent_end` auto-drain still surfaces provider,
 reconciliation, or timeout failures.
 
+```js workflow
+return runs.run("main", { agent: "worker", task: "Run the full test suite" });
+```
+
 ```typescript
-subagent({
-  workflowScript: `return runs.run("main", { agent: "worker", task: "Run the full test suite" })`,
-  async: true
-})
+subagent({ workflow: true, async: true })
 ```
 
-File-only output mode works for workflowScript child launches. Use relative child output paths for scratch reports so the runtime stores them under the run artifact directory and age-based cleanup can remove them. Use absolute paths only for user-approved durable destinations, such as session memory, a docs folder outside the repo, or a known handoff path. For cross-codebase waves, include the repo slug or lane key in each output path so reports from different repositories cannot collide.
+File-only output mode works for workflow script child launches. Use relative child output paths for scratch reports so the runtime stores them under the run artifact directory and age-based cleanup can remove them. Use absolute paths only for user-approved durable destinations, such as session memory, a docs folder outside the repo, or a known handoff path. For cross-codebase waves, include the repo slug or lane key in each output path so reports from different repositories cannot collide.
 
 The `output` field is the API binding; a filename mentioned in task text is only instruction and does not override runtime routing. When a later workflow step or parent needs a durable file, set `output` on `runs.run`/`runs.all` and return the child’s `outputReference`, `outputPathMapping`, or `artifactPaths`; arbitrary literal strings returned by workflow JavaScript are not rewritten. Omitted child output may use a managed aggregate-derived sibling path.
 
 For review fanout where the parent continues a local audit:
 
+```js workflow
+return runs.run("correctness", { agent: "reviewer", task: "Review the current diff for correctness issues. Do not edit files." });
+```
+
 ```typescript
-const run = subagent({
-  workflowScript: `return runs.run("correctness", { agent: "reviewer", task: "Review the current diff for correctness issues. Do not edit files." })`,
-  async: true,
-  context: "fresh"
-})
+const run = subagent({ workflow: true, async: true, context: "fresh" })
 // Continue local inspection, then later call status with the returned id.
 ```
 
@@ -246,9 +259,9 @@ Use diagnostics when setup or child startup looks wrong:
 subagent({ action: "doctor" })
 ```
 
-### Failed lane recovery and execution-mode fallback
+### Failed lane recovery and execution-mode changes
 
-A failure in the subagent workflow, child launch, prompt runtime, extension loading, or child tooling setup is a lane infrastructure blocker, not permission to silently change execution mode. Stop and report the exact failure, run/status, and repo/cwd/worktree/branch/ref state. Retry or fix the `subagent` path only through a clear same-protocol retry; before retrying or asking the owner, verify the worktree is clean or capture the partial diff. For backlog lanes and other subagent-governed workflows, switching to `interactive_shell`, `pi -ne`, Codex/Claude/Cursor CLI, a foreground agent, or another external mode requires explicit owner approval. Pi core may print a generic `pi -ne` extension-load hint; that hint is outside this package and is not protocol-approved fallback. This execution-mode boundary does not prohibit configured native model/provider fallback.
+A failure in the subagent workflow, child launch, prompt runtime, extension loading, or child tooling setup is a lane infrastructure blocker, not permission to silently change execution mode. Stop and report the exact failure, run/status, and repo/cwd/worktree/branch/ref state. Retry or fix the `subagent` path only through a clear same-protocol retry; before retrying or asking the owner, verify the worktree is clean or capture the partial diff. For backlog lanes and other subagent-governed workflows, switching to `interactive_shell`, `pi -ne`, Codex/Claude/Cursor CLI, a foreground agent, or another external mode requires explicit owner approval. Pi core may print a generic `pi -ne` extension-load hint; that hint is outside this package and is not protocol-approved. A verified compaction abort may continue the retained child session once on the same resolved model; provider failures never select another model automatically.
 
 ### External terminal work
 
@@ -261,11 +274,11 @@ A cooperating terminal runtime can register read-only external records through `
 Schedules are durable project records under `.pi-subagents/schedules/`. They are enabled by default; set `{ "scheduledRuns": { "enabled": false } }` in `~/.selesai/agent/extensions/subagent/config.json` to disable them. Only schedule explicit work the user asked for. To keep schedules outside the project repository, set `{ "scheduledRuns": { "storeRoot": "~/.selesai/subagent-schedules" } }` in the same config: `storeRoot` accepts an absolute path or a `~/`-prefixed path, and records land under `<storeRoot>/<sha256(path.resolve(cwd)) first 20 hex>/<scheduleId>/`.
 
 ```typescript
-// One-shot reviewer
-subagent({ action: "schedule.create", id: "evening-review", name: "Evening review", at: "+30m", workflowScript: "return runs.run('main', { agent: 'reviewer', task: 'Review the diff.' })" })
+// One-shot reviewer, after a ```js workflow block with the script
+subagent({ action: "schedule.create", id: "evening-review", name: "Evening review", at: "+30m", workflow: true })
 
-// Fixed recurring workflow
-subagent({ action: "schedule.create", id: "backlog", every: "6h", catchUp: "latest", workflowScript: "..." })
+// Fixed recurring workflow from a script file
+subagent({ action: "schedule.create", id: "backlog", every: "6h", catchUp: "latest", workflow: "./.selesai/workflows/backlog.js" })
 
 subagent({ action: "schedule.list" })
 subagent({ action: "schedule.show", id: "backlog" })
@@ -277,7 +290,7 @@ subagent({ action: "schedule.run-due" })
 subagent({ action: "schedule.delete", id: "backlog" })
 ```
 
-`schedule.create` accepts exactly one target, `workflowScript`, and exactly one trigger (`at`, or a fixed `every` interval using `m`, `h`, `d`, or `w`). Runs always launch async with fresh context and no automatic mission; mission attachment is deferred from this first slice. `overlap` is currently `skip`; `catchUp` supports `latest` and `none`. `schedule.run-due` is the headless external-launcher seam. Calendar recurrence, cron, and the schedule inspector are deferred from this first safe slice. Definitions, bounded history, append-only events, and per-run receipts remain project-scoped across Pi sessions.
+`schedule.create` accepts exactly one target, a workflow script (`workflow: true` or a script path; the script text is stored at creation), and exactly one trigger (`at`, or a fixed `every` interval using `m`, `h`, `d`, or `w`). Runs always launch async with fresh context and no automatic mission; mission attachment is deferred from this first slice. `overlap` is currently `skip`; `catchUp` supports `latest` and `none`. `schedule.run-due` is the headless external-launcher seam. Calendar recurrence, cron, and the schedule inspector are deferred from this first safe slice. Definitions, bounded history, append-only events, and per-run receipts remain project-scoped across Pi sessions.
 
 Humans can use `/subagents-doctor` for the same read-only report. It checks runtime paths, discovery counts, async support, current session context, and intercom bridge state.
 
@@ -304,17 +317,15 @@ A soft interrupt cancels the current child turn and leaves the run paused. It do
 
 Per-run control thresholds can be overridden when a task legitimately runs without observable output for longer than usual:
 
-```typescript
-subagent({
-  workflowScript: `return runs.run("slow-tests", {
-    agent: "worker",
-    task: "Run the slow migration test suite",
-    control: {
-      needsAttentionAfterMs: 300000,
-      notifyOn: ["needs_attention"]
-    }
-  })`
-})
+```js workflow
+return runs.run("slow-tests", {
+  agent: "worker",
+  task: "Run the slow migration test suite",
+  control: {
+    needsAttentionAfterMs: 300000,
+    notifyOn: ["needs_attention"]
+  }
+});
 ```
 
 If the run already has an active intercom bridge target, needs-attention notifications can also prepare a compact intercom ping for the orchestrator. When a child route is available, the ping tells the orchestrator which agent needs attention and includes the exact `intercom({ action: "send", to: "..." })` target for a nudge. Do not invent a target or ask the child to self-report when no bridge exists.
@@ -338,7 +349,7 @@ subagent({ action: "steer", id: "abc123", mode: "follow_up", message: "After thi
 subagent({ action: "steer", id: "abc123", mode: "auto", message: "Switch to the failing test now." })
 ```
 
-Direct input acceptance returns `delivered`, not proof of model compliance. A live follow-up acknowledgment reports `queued`, meaning Pi accepted it into its follow-up queue, not that it was delivered. The runtime does not provide a later correlated live queued-to-delivered receipt.
+For async runs, `delivered` records that the child consumed the correlated user input; foreground `delivered` records in-process transport acceptance. Neither is proof of model compliance. A live foreground follow-up acknowledgment reports `queued`, meaning Pi accepted it into its follow-up queue, not that it was delivered. The foreground transport does not provide a later correlated queued-to-delivered receipt.
 
 ## Watchdog
 
@@ -396,7 +407,7 @@ Use `mission.update` while work runs to record decisions, artifacts, labels, sum
 
 ### Mission use policy
 
-- **Keep the default.** Every ordinary `workflowScript` launch with a task creates one enclosing mission automatically. All workflow children share it and never get their own. Do not add `mission: {...}` boilerplate. Pass it only to set the title, objective, labels, or to enable `goal` with `budget`.
+- **Keep the default.** Every ordinary workflow script launch with a task creates one enclosing mission automatically. All workflow children share it and never get their own. Do not add `mission: {...}` boilerplate. Pass it only to set the title, objective, labels, or to enable `goal` with `budget`.
 - **Use `mission: false` for noise.** Use it for trivial one-shot lookups, scouts, disposable probes, and quick validation where a recovery record is noise. It removes the mission and the `state` global for the whole workflow, so do not use it for monitors or multi-workflow loops that coordinate through `state`. Scheduled runs already launch without automatic missions.
 - **Use `missionId` for follow-up work.** Attach later work to an existing objective with `missionId`; attachment re-marks the mission active. `missionId` and `mission` are mutually exclusive. Explicit attachment fails before launch if the mission is missing, while automatic missions degrade to `details.missionWarning` without blocking the run.
 - **Keep `state` small.** Mission `state` is JSON coordination across workflows on the same mission. Keys use the same format as run keys, values must be JSON, and the whole state file is capped at 256 KiB. Each `set` merges one key under a file lock. Put large content in artifact files and store paths in state. In goal missions, write `state.set("nextReadyAction", "...")` so the next idle-turn notice names the exact ready step.
@@ -409,15 +420,15 @@ After compaction, restart, or confusing history, recover from durable state firs
 Routing rule:
 - Same project: ordinary mission-backed subagents.
 - Different project, small/bounded task: ordinary async subagent with explicit `cwd`, an authority boundary, and durable output.
-- Several projects with independent work: one async `workflowScript` whose child keys include repo slugs and whose child calls set explicit `cwd`; keep publication and merge decisions serial per repo.
+- Several projects with independent work: one async workflow script whose child keys include repo slugs and whose child calls set explicit `cwd`; keep publication and merge decisions serial per repo.
 - Different project, substantial or long-running work: open a project-owned Herdr pane rooted there when a separate visible project session is useful, then give that project Pi session a narrow mission/result contract. Do not model it as ordinary child nesting, and do not expect existing headless runs to move into the pane.
 
 Project panes run a separate Pi session from the target directory. Subagents launched inside that pane use that project's config, agents, skills, files, git state, and mission records. The pane binding lives under `<projectRoot>/.pi-subagents/project-panes/herdr.json`. When Pi runs inside Herdr, the owning pane reports compact active-work status and title suffixes, and the parent inline status counts opened project panes. Use Herdr itself or `project.status` / `project.close` for pane-level follow-up. For ordinary headless delegation to another repo, prefer explicit `cwd` first; reserve project panes for visible or persistent project ownership.
 
 ```typescript
 subagent({ action: "mission.create", mission: { title: "Ship auth refresh", objective: "Implement and validate refresh handling" } })
-subagent({ workflowScript: `return runs.run("main", { agent: "worker", task: "Implement the approved plan" })`, missionId: "<mission-id>" })
-subagent({ workflowScript: `return runs.run("main", { agent: "scout", task: "Quickly answer whether this file exists" })`, mission: false })
+subagent({ workflow: true, missionId: "<mission-id>" }) // after a ```js workflow block
+subagent({ workflow: true, mission: false }) // after a ```js workflow block
 subagent({ action: "mission.list", missionScope: "global" })
 subagent({ action: "mission.resolve-decision", missionId: "<mission-id>", id: "<decision-id>", summary: "Settled: ship the v2 API; no schema freeze needed." })
 subagent({ action: "project.open", cwd: "/path/to/other-repo", message: "Own this mission for the project and report back with receipts." })
@@ -431,16 +442,12 @@ subagent({ action: "mission.close", missionId: "<mission-id>", missionStatus: "c
 When multiple agents might write concurrently, use worktrees instead of letting
 them share one filesystem view.
 
-```typescript
-subagent({
-  workflowScript: `
-    const results = await runs.all([
-      { key: "feature-a", agent: "worker", task: "Implement feature A", worktree: true },
-      { key: "feature-b", agent: "worker", task: "Implement feature B", worktree: true }
-    ]);
-    return results.map(({ key, artifactPaths }) => ({ key, artifactPaths }));
-  `
-})
+```js workflow
+const results = await runs.all([
+  { key: "feature-a", agent: "worker", task: "Implement feature A", worktree: true },
+  { key: "feature-b", agent: "worker", task: "Implement feature B", worktree: true }
+]);
+return results.map(({ key, artifactPaths }) => ({ key, artifactPaths }));
 ```
 
 `worktree: true` on a `runs.run` / `runs.all` item gives that child its own git
@@ -483,16 +490,14 @@ The intended oracle loop is:
 4. the main agent decides what direction to approve
 5. only then should `worker` implement
 
-```typescript
+```js workflow
 // Advisory review in a branched thread. Oracle defaults to forked context.
-subagent({
-  workflowScript: `return runs.run("oracle-check", { agent: "oracle", task: "Review my current direction, challenge assumptions, and propose the best next move." })`
-})
+return runs.run("oracle-check", { agent: "oracle", task: "Review my current direction, challenge assumptions, and propose the best next move." });
+```
 
-// Implementation only after explicit approval. Worker defaults to forked context.
-subagent({
-  workflowScript: `return runs.run("implementation", { agent: "worker", task: "Implement the approved approach: ..." })`
-})
+```js workflow
+// Implementation only after explicit approval, in a later reply. Worker defaults to fresh context.
+return runs.run("implementation", { agent: "worker", task: "Implement the approved approach: ..." });
 ```
 
 `oracle` is not a fresh-context reviewer in the Cognition article sense. It is

package/dist/extensions/pi-subagents/skills/pi-subagents/references/management-authoring-rpc.md

@@ -18,7 +18,7 @@ subagent({ action: "list" })
 subagent({ action: "children.list" })
 ```
 
-Lists up to the last 10 retained workflow children from this parent session with explicit `resumable` or `not resumable` rows. Resume only rows reported `resumable`. Send a simple follow-up or implementation challenge with `subagent({ action: "resume", id: "<run-id>", message: "..." })`. Continue one inside a workflow with `runs.run(key, { resume: "<run-id>", task: "follow-up" })`; each workflow key identifies one result lane, so use a new stable workflow key for every distinct retained resume pass. Same-key calls are reused only when launch parameters are identical, and incompatible parameters are rejected. The revived child keeps its stored agent, model, and tool contract. If no resumable child is listed, start a same-role fallback challenge and label it as fallback. `steer` with `mode: "follow_up"` only queues text for the next `resume` when the child has already completed.
+Lists up to the last 10 retained workflow children from this parent session with explicit `resumable` or `not resumable` rows. This workflow-only roster is not an exhaustive list of direct native children. Resume only rows reported `resumable`. When the exact run id of an intended direct child is known, inspect it with `subagent({ action: "status", id: "<run-id>" })`; if status identifies the candidate, attempt `subagent({ action: "resume", id: "<run-id>", message: "..." })`. Resume performs the authoritative eligibility check and may reject the attempt. Continue one inside a workflow with `runs.run(key, { resume: "<run-id>", task: "follow-up" })`; each workflow key identifies one result lane, so use a new stable workflow key for every distinct retained resume pass. Same-key calls are reused only when launch parameters are identical, and incompatible parameters are rejected. The revived child keeps its stored agent, model, and tool contract. Start a same-role fallback challenge, labeled as fallback, only when no known candidate exists or resume rejects eligibility. `steer` with `mode: "follow_up"` only queues text for the next `resume` when the child has already completed.
 
 ### Refinement overlays
 
@@ -85,7 +85,7 @@ subagent({ action: "reset", agent: "reviewer" })
 Use management actions when the system needs to create or edit subagents on
 demand without dropping into raw file editing.
 
-Management actions create or update user/project agent files. `config.name` is the local frontmatter name; optional `config.package` registers and looks up the runtime name as `{package}.{name}`. Use the dotted runtime name for `get`, `update`, `delete`, slash commands, and scripted workflow steps. For small agent changes such as a model swap, prefer `subagents.agentOverrides` in settings. Durable `.chain.md` definitions are legacy records, not a current authoring target; use `workflowScript` or `/prompt-workflow` for repeatable orchestration.
+Management actions create or update user/project agent files. `config.name` is the local frontmatter name; optional `config.package` registers and looks up the runtime name as `{package}.{name}`. Use the dotted runtime name for `get`, `update`, `delete`, slash commands, and scripted workflow steps. For small agent changes such as a model swap, prefer `subagents.agentOverrides` in settings. Durable `.chain.md` definitions are legacy records, not a current authoring target; use a workflow script file (`workflow: "./path.js"`) or `/prompt-workflow` for repeatable orchestration.
 
 ## Creating and Editing Agents by File
 
@@ -117,7 +117,6 @@ That is only a starting point. Omit `package` for the traditional unqualified ru
 - `defaultReads`
 - `output`
 - `aliases`
-- `fallbackModels`
 - `subagentOnlyExtensions`
 - `skills`
 - `skillPath`
@@ -132,7 +131,7 @@ That is only a starting point. Omit `package` for the traditional unqualified ru
 
 `acceptance` is a single-agent launch default. Use a scalar level such as `checked` or an inline/block YAML map such as `{ level: "none", reason: "lightweight lookup" }`. An explicit tool-call value wins; scripted workflow child acceptance remains configured on the `runs.run` or `runs.all` item. Management create/update accepts the same policy object, and `acceptance: ""` clears the frontmatter default (`false` remains the deprecated disabled-policy shorthand).
 
-`acceptanceRole` is `read-only` or `writer` and controls automatic acceptance inference only. Explicit task mutation or no-edit intent wins; otherwise the role replaces agent-name guessing. Omission preserves the current name heuristics. The field does not grant or revoke tools. Management accepts `false` or an empty string to clear it.
+`acceptanceRole` is `read-only` or `writer` and controls automatic acceptance inference only. The structured role is authoritative; task wording and agent names do not escalate acceptance. Omission uses lightweight attestation. The field does not grant or revoke tools. Management accepts `false` or an empty string to clear it.
 
 `tools` is a strict child allowlist, not an extension loader. For a named extension tool, keep its registered name in `tools` and load its provider through normal Pi discovery, `extensions`, a path-like `tools` entry, or `subagentOnlyExtensions`. For example, pair `tools: read, fixture_search` with `subagentOnlyExtensions: ./tools/fixture-search.ts` when the provider should exist only in that agent's child sessions. The child now fails with the unavailable names and provider-loading guidance instead of silently continuing when a requested tool is absent; internal `structured_output` is allowed automatically when an output schema requires it.
 
@@ -159,4 +158,4 @@ Additional user prompt templates can delegate into `pi-subagents` through the na
 
 Other Pi extensions can call `pi-subagents` through the in-process event bus. The RPC channels are `subagents:rpc:v1:ready`, `subagents:rpc:v1:request`, and per-request replies at `subagents:rpc:v1:reply:<requestId>`. Envelopes use `{ version: 1, requestId, method, params }`, and replies use `{ version: 1, requestId, success, data | error }`. `ping` advertises the exact process-local async completion event as `events.asyncComplete` for RPC-spawn consumers.
 
-Methods: `ping`, `status`, `spawn`, `steer`, `interrupt`, `resume`, and `stop`. `ping` capability metadata advertises optional projections: `capabilities.fleetStatus: { version: 1 }` adds bounded current-session `data.fleet` records (opaque reconciliation `key`, resolved `agent`, optional `role`, `model`, `effort`, caller-facing `goal`, `startedAt`, split `{ input, output, total }` tokens, plus `totalActive`/`omitted` overflow counts) to successful `status` replies; `capabilities.launchResolvedExtensions` advertises parent-resolved opaque launch-extension identifiers in status details; `capabilities.runtimeAcknowledgedExtensions` advertises the best-effort child-runtime acknowledgement projection fed by cooperating extensions emitting `subagent:acknowledge-extension`. Foreground `details.results[]` rows carry a stable numeric `index`; correlate children by `(runId, index)` rather than row position. Consumers should read status/result artifacts and RPC projections instead of scraping terminal output and must ignore unknown fields. `spawn` requires `workflowScript`, is async-only, and rejects management actions, `async: false`, or `clarify: true`; it reuses the normal executor, so discovery, validation, session attribution, configured spawn caps, child-safety depth, artifacts, and async status are shared with the `subagent` tool. `status`, acknowledged async `steer`, and `interrupt` map to the normal control actions. RPC steer disables pause-and-revive recovery and advertises `capabilities.nonRecoveringSteer`, preserving the caller's authority over the exact spawned child. `resume` requires a target plus non-empty message and delegates to the package-owned revival path; it may set a caller-owned `file-only` output path but cannot override the persisted child model, tools, budgets, session ownership, or exclusive session lease. For retained-child workflows, list children first and resume only rows reported `resumable`; otherwise start a same-role fallback challenge and label it as fallback. `stop` targets running async runs through the existing timeout control channel. `pi.events` is process-local, so separate Pi processes and child subagents need lifecycle artifact files or `pi-intercom` instead.
+Methods: `ping`, `status`, `manage`, `spawn`, `steer`, `interrupt`, `resume`, `stop`, and `cost`. `ping` capability metadata advertises optional projections: `capabilities.fleetStatus: { version: 1 }` adds bounded current-session `data.fleet` records (opaque reconciliation `key`, resolved `agent`, optional `role`, `model`, `effort`, caller-facing `goal`, `startedAt`, split `{ input, output, total }` tokens, plus `totalActive`/`omitted` overflow counts) to successful `status` replies; `capabilities.launchResolvedExtensions` advertises parent-resolved opaque launch-extension identifiers in status details; `capabilities.runtimeAcknowledgedExtensions` advertises the best-effort child-runtime acknowledgement projection fed by cooperating extensions emitting `subagent:acknowledge-extension`; `capabilities.cost: { version: 1 }` advertises parent-plus-child accounting as data. Foreground `details.results[]` rows carry a stable numeric `index`; correlate children by `(runId, index)` rather than row position. Consumers should read status/result artifacts and RPC projections instead of scraping terminal output and must ignore unknown fields. `spawn` accepts either `{ agent, task? }`, inline script text as `script`, or `workflow` with a script path (containing `/`) or a named workflow resource; `workflow: true` is rejected because RPC has no assistant reply to read. It is async-only and rejects management actions, `async: false`, or `clarify: true`. It reuses the normal executor, so discovery, validation, session attribution, configured spawn caps, child-safety depth, artifacts, and async status are shared with the `subagent` tool. `manage` accepts only the schedule actions advertised by `ping.capabilities.managementActions`. `status`, acknowledged async `steer`, and `interrupt` map to the normal control actions. RPC steer disables pause-and-revive recovery and advertises `capabilities.nonRecoveringSteer`, preserving the caller's authority over the exact spawned child. `resume` requires a target plus non-empty message and delegates to the package-owned revival path; it may set a caller-owned `file-only` output path but cannot override the persisted child model, tools, budgets, session ownership, or exclusive session lease. For retained-child workflows, resume only roster rows reported `resumable`; because that workflow-only roster is not exhaustive, inspect the exact status of a known direct-run candidate and attempt the authoritative resume when status identifies it. Start a labeled same-role fallback only when there is no known candidate or resume rejects eligibility. `stop` targets running async runs through the existing timeout control channel. `pi.events` is process-local, so separate Pi processes and child subagents need lifecycle artifact files or `pi-intercom` instead.

package/dist/extensions/pi-subagents/skills/pi-subagents/references/multi-lane-orchestration.md

@@ -2,7 +2,15 @@
 
 Use this reference when several independent tasks need coordinated workers, worktrees, or repositories. It defines lane ownership; use the other pi-subagents references for run controls, prompts, and mission details. The parent remains the final decision-maker.
 
-Create lanes only when delegation materially improves evidence, independent review, or isolated execution. Do not manufacture parallelism: keep dependent work serial, and only split work when each lane has a distinct decision and useful output.
+Create lanes only after delegation is operator-authorized and each lane materially improves evidence, independent review, specialization, useful parallelism, or isolated execution. Do not manufacture parallelism: keep dependent work serial, and only split work when each lane has a distinct decision and useful output.
+
+## Mandatory implementation-topology preflight
+
+Before launching a writer for substantial mutation work, classify the implementation as **single-seam** or **multi-seam**. Two or more independently testable contracts or source boundaries make it multi-seam. One PR does not imply one writer, and the one-writer-per-worktree rule prevents concurrent ownership conflicts; it does not authorize an issue-wide commission.
+
+Record the classification and evidence on a lane board before writer launch. For multi-seam work, give each isolated component writer exclusive file or contract ownership and focused validation gates. Require every component to produce a committed or otherwise durable handoff, then start a separate integration-only owner after the component handoffs are ready. Mechanically reject and repartition a writer prompt if it owns all major outcomes across multiple independent boundaries.
+
+A single complete writer remains valid only when the board records evidence that the work is genuinely one seam or that splitting it would create overlapping ownership or artificial handoffs. This preflight must not manufacture parallelism: do not split tightly coupled work merely to increase the lane count.
 
 ## Lane board and authority
 
@@ -26,7 +34,7 @@ Partition fanout by repository, source seam, decision, or review angle. Each run
 
 Every child packet must stand alone: include the goal, exact repository/cwd/ref, authority and edit boundary, relevant context/evidence, success criteria, validation, expected output, and stop/escalation rules. Do not rely on parent history, an issue number, or a broad glob alone. An orchestration audit by a top-reasoning critic model is read-only and returns at most three cited omissions; use high thinking only as an explicit parent/user escalation, never as an autonomous root or a parallel placeholder.
 
-Use one async `workflowScript` for a coordinated wave. Use `runs.all` for independent lanes and `runs.run` for dependent lane stages. Give cross-repository runs explicit `cwd` values and lane-qualified outputs. Use `outputMode: "file-only"` when a report must survive the run or feed a later stage. Keep scratch outputs relative so they live under subagent artifacts; use absolute paths only for durable memory, approved docs paths, or final handoff files.
+Use one async workflow script (`subagent({ workflow: true, async: true })` after a ```` ```js workflow ```` block) for a coordinated wave. Use `runs.all` for independent lanes and `runs.run` for dependent lane stages. Give cross-repository runs explicit `cwd` values and lane-qualified outputs. Use `outputMode: "file-only"` when a report must survive the run or feed a later stage. Keep scratch outputs relative so they live under subagent artifacts; use absolute paths only for durable memory, approved docs paths, or final handoff files.
 
 ## Keep independent work moving