@selesai/code 0.8.12 → 0.9.0

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

@@ -186,9 +186,7 @@ const run = subagent({
 // Continue local inspection, then later call status with the returned id.
 ```
 
-While children run, the persistent FleetView and the collapsed foreground tool-result card show live per-child detail: resolved model and thinking level, `[fresh]`/`[fork]` context, tool/token/elapsed counters, and current activity. The collapsed running card also prints the configured expand-key hint ("Press … for live detail"); expanding it shows nested children, recent tools, and recent output. Model badges appear once the child's model resolves at first attempt start. `/subagents-fleet` opens the live fleet inspector, which also has per-child controls (`s` steer, `D` stop with confirmation). When optional Herdr 0.7.5+ is available, `H` opens a raw inspector dashboard for the selected active async child; this mirrors artifacts rather than attaching to the headless child. Use it for confusing or long-running active async work when the human wants a dedicated visual pane or FleetView is insufficient, not for routine headless runs.
-
-Inspect async runs with `subagent({ action: "status", id: "..." })` or `subagent({ action: "status" })` for active runs. Use `subagent({ action: "status", view: "fleet" })` when supervising several active foreground/background runs and `subagent({ action: "status", id: "...", view: "transcript", index: 0 })` when you need the latest child output without digging through artifacts. If a delegated fanout child launches nested runs, the parent status view shows them as a tree and you can target a nested run directly with its nested id.
+Inspect async runs with `subagent({ action: "status", id: "..." })` or `subagent({ action: "status" })` for active runs. Use `subagent({ action: "status", id: "...", view: "transcript", index: 0 })` when you need the latest child output without digging through artifacts. Use `steer` to send guidance to a running child and `stop` to terminate a current-session top-level async run. If a delegated fanout child launches nested runs, the parent status view shows them as a tree and you can target a nested run directly with its nested id.
 
 Stop a current-session top-level async run with `stop` (or `/subagents-stop`). Stopped runs finish as `stopped`/cancelled and are not resumable. For an active foreground single-subagent run, `/subagents-detach [run-id]` leaves the child running without terminating it and returns the eventual result through status/wait. Append one more step to the tail of a still-running durable chain with `append-step` (`step` must contain exactly one step object). Use checkpoint steps for planned human gates; they pause without launching a child and are approved or rejected through current-session control actions:
 
@@ -236,31 +234,6 @@ Use native `subagent` runs for unattended implementation, review, and gate work
 
 A cooperating terminal runtime can register read-only external records through `pi-subagents/external-runs`. Records include the source, session, state, optional report path, and completion reason. They are observations only: pi-subagents does not start, stop, steer, or otherwise own the foreign process. Run unattended raw terminal agents in an explicit isolated cwd or worktree; do not use a live project checkout as disposable review space.
 
-### Scheduled subagent runs
-
-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.
-
-```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.' })" })
-
-// Fixed recurring workflow
-subagent({ action: "schedule.create", id: "backlog", every: "6h", catchUp: "latest", workflowScript: "..." })
-
-subagent({ action: "schedule.list" })
-subagent({ action: "schedule.show", id: "backlog" })
-subagent({ action: "schedule.history", id: "backlog" })
-subagent({ action: "schedule.pause", id: "backlog" })
-subagent({ action: "schedule.resume", id: "backlog" })
-subagent({ action: "schedule.run", id: "backlog" })
-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 Selesai 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.
-
 ### Subagent control
 
 Subagent control is the runtime visibility and intervention layer for delegated runs. It is separate from lifecycle status. Lifecycle status says whether a child is `queued`, `running`, `paused`, `complete`, `stopped`, `failed`, or `rejected`. Activity reporting is factual: it tracks the last observed activity time and the current tool when known. It does not pretend to know that a child is truly stuck. Manual top-level async cancellation uses `stop` / `/subagents-stop`; a live async chain can gain one more tail step via `append-step`, and a paused async chain checkpoint can be decided with `approve-checkpoint` or `reject-checkpoint`.
@@ -325,27 +298,9 @@ and can optionally run non-blocking Scopey-style cadence reviews every N tool re
 are always transcript-visible; choose the watchdog model that matches the desired
 cheap-monitor vs strong-reviewer policy.
 
-Prefer a strong complementary model (for example Opus 4.8 high paired against a
-GPT 5.5 main session, or the reverse). Recommendation and configuration:
-
-```text
-/subagents-watchdog recommend-model
-/subagents-watchdog session model recommended
-/subagents-watchdog on
-/subagents-watchdog status
-/subagents-watchdog check
-```
-
-```typescript
-subagent({ action: "watchdog.status" })
-subagent({ action: "watchdog.recommend-model" })
-subagent({ action: "watchdog.configure", model: "recommended", scope: "session" })
-subagent({ action: "watchdog.check" })
-```
-
-`session` scope is temporary. Persistent `user`/`project` scopes write settings only
-when the user asked. Use ordinary fresh-context `reviewer` fanout for planned review
-waves; enable the watchdog when you want an automatic second pass on real edits.
+Enable the watchdog with `/subagents-watchdog on`; inspect it with `status` or `check`.
+Use ordinary fresh-context `reviewer` fanout for planned review waves; enable the
+watchdog when you want an automatic second pass on real edits.
 
 ## Clarify TUI
 

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

@@ -161,4 +161,4 @@ Native chain and parallel steps are also launchable directly from the command li
 
 Other Selesai 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 Selesai processes and child subagents need lifecycle artifact files or `pi-intercom` instead.
+Methods: `ping`, `status`, `spawn`, `steer`, `interrupt`, `resume`, and `stop`. `ping` capability metadata advertises optional projections: `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 Selesai processes and child subagents need lifecycle artifact files or `pi-intercom` instead.

package/dist/extensions/pi-subagents/skills/pi-subagents/references/prompting-and-roles.md

@@ -31,8 +31,7 @@ Agents use the `subagent(...)` tool directly for execution, management, status,
 - `/subagents-stop [run-id]` — stop a current-session top-level async run; opens a selector when no id is given
 - `/subagents-detach [run-id]` — detach an active foreground single-subagent run without terminating its child
 - `/subagent-cost` — show parent plus child token usage and cost for the session
-- `/subagents-fleet` — open the live fleet inspector with per-child controls; `Ctrl+Alt+F` opens it during an active foreground turn, `↑↓`/`jk` selects children, `PgUp`/`PgDn` scrolls transcript detail, `s` steers the selected live async child, and `D` stops its top-level async run after confirmation
-- `/subagents-watchdog` — inspect or configure the opt-in adversarial change watchdog (model, on/off, recommend-model, check)
+- `/subagents-watchdog` — inspect or configure the opt-in adversarial change watchdog (on/off, model, check)
 - `/subagents-doctor` — diagnose setup, discovery, async paths, and intercom bridge state
 - `/subagents-models [agent]` — show the live runtime-loaded builtin model mapping
 - `/subagents-profiles`, `/subagents-load-profile`, `/subagents-refresh-provider-models`, `/subagents-generate-profiles`, `/subagents-check-profile` — manage model profiles and provider catalogs

package/dist/extensions/pi-subagents/src/extension/config.ts

@@ -1,5 +1,4 @@
 import * as fs from "node:fs";
-import * as os from "node:os";
 import * as path from "node:path";
 import { Key } from "@earendil-works/pi-tui";
 import { FLEET_KEYBINDING_ACTIONS, type ArtifactDirPreference, type ExtensionConfig } from "../shared/types.ts";
@@ -26,19 +25,8 @@ function isValidKeyId(value: string): boolean {
 		&& parts.every((modifier) => KEY_MODIFIERS.has(modifier));
 }
 
-export function resolveScheduledStoreRoot(value: string): string {
-	const expanded = value.startsWith("~/") ? path.join(os.homedir(), value.slice(2)) : value;
-	if (!path.isAbsolute(expanded)) throw new Error(`config.scheduledRuns.storeRoot must be an absolute path or "~/...", got ${JSON.stringify(value)}`);
-	return path.normalize(expanded);
-}
-
-function validateScheduledRunsConfig(value: unknown): void {
-	if (value === undefined) return;
-	if (!value || typeof value !== "object" || Array.isArray(value)) throw new Error("config.scheduledRuns must be a JSON object");
-	const storeRoot = (value as Record<string, unknown>).storeRoot;
-	if (storeRoot === undefined) return;
-	if (typeof storeRoot !== "string" || !storeRoot.trim()) throw new Error("config.scheduledRuns.storeRoot must be a non-empty string");
-	resolveScheduledStoreRoot(storeRoot);
+function validateRemovedScheduledRunsConfig(value: unknown): void {
+	if (value !== undefined) throw new Error("config.scheduledRuns is no longer supported");
 }
 
 function validateFleetKeybindingsConfig(value: unknown): void {
@@ -119,7 +107,7 @@ function validateConfig(config: Record<string, unknown>): void {
 	validateMissionStoreConfig(config.missions);
 	validateAuthorityPolicy(config.authorityPolicy);
 	validatePermissionConfig(config.permissions);
-	validateScheduledRunsConfig(config.scheduledRuns);
+	validateRemovedScheduledRunsConfig(config.scheduledRuns);
 	validateFleetKeybindingsConfig(config.fleetKeybindings);
 	validateArtifactConfig(config.artifactConfig);
 	validateMainWindowRendererConfig(config.mainWindowRenderer);

package/dist/extensions/pi-subagents/src/extension/index.ts

@@ -27,8 +27,6 @@ import { resolveCurrentSessionId } from "../shared/session-identity.ts";
 import { resolveSessionLineage } from "../shared/session-lineage.ts";
 import { cleanupOldChainDirs } from "../shared/settings.ts";
 import { clearLegacyResultAnimationTimer, renderSubagentResult, renderSubagentSummary } from "../tui/render.ts";
-import { openSubagentFleet } from "../tui/fleet.ts";
-import { SubagentFleetStatus, resolveFleetViewPlacement } from "../tui/fleet-status.ts";
 import { createSubagentParamsSchema } from "./schemas.ts";
 import { validateChainInput } from "./chain-validation.ts";
 import { createSubagentExecutor, type SubagentParamsLike } from "../runs/foreground/subagent-executor.ts";
@@ -36,10 +34,8 @@ import { createAsyncJobTracker } from "../runs/background/async-job-tracker.ts";
 import { getActiveAsyncCapacitySnapshot, resolveMaxActiveAsyncRunsPerSession } from "../runs/background/active-async-capacity.ts";
 import { cleanupResultIndexes } from "../runs/background/result-files.ts";
 import { createResultWatcher } from "../runs/background/result-watcher.ts";
-import { createScheduledRunManager } from "../runs/background/scheduled-runs.ts";
 import { registerSlashCommands } from "../slash/slash-commands.ts";
 import { registerPromptTemplateDelegationBridge } from "../slash/prompt-template-bridge.ts";
-import { registerMainWatchdog } from "../watchdog/register-main.ts";
 import { registerSlashSubagentBridge } from "../slash/slash-bridge.ts";
 import { createNativeSupervisorChannel } from "../intercom/native-supervisor-channel.ts";
 import { registerHerdrStatusBridge, type HerdrStatusRun } from "../integrations/herdr-status.ts";
@@ -55,7 +51,7 @@ import { formatSteeringNotice, handleSubagentSteeringNotice, SUBAGENT_STEERING_M
 import { SUBAGENT_CHILD_ENV, SUBAGENT_PARENT_SESSION_ENV } from "../runs/shared/pi-args.ts";
 import { resolveCurrentSubagentCapabilityCeiling } from "../runs/shared/capability-ceiling.ts";
 import { formatDuration, shortenPath } from "../shared/formatters.ts";
-import { loadConfig, resolveAsyncByDefault, resolveScheduledStoreRoot } from "./config.ts";
+import { loadConfig, resolveAsyncByDefault } from "./config.ts";
 import { buildSubagentToolDescription } from "./tool-description.ts";
 import { collectGoalContinuationNotices } from "../missions/goal-driver.ts";
 import { restoreForegroundRunHistory } from "../runs/foreground/foreground-history.ts";
@@ -383,8 +379,6 @@ export default function registerSubagentExtension(pi: ExtensionAPI): void {
 	const config = loadConfig();
 	const waitToolConfig = resolveWaitToolConfig(config.waitTool);
 	const asyncByDefault = resolveAsyncByDefault(config);
-	const fleetViewEnabled = config.fleetView !== false;
-	const fleetViewPlacement = resolveFleetViewPlacement(config.fleetViewPlacement);
 	const asyncWidgetEnabled = config.asyncWidget !== false;
 	const summaryInlineToolDisplay = config.inlineToolDisplay === "summary";
 	const tempArtifactsDir = getArtifactsDir(null);
@@ -442,33 +436,8 @@ export default function registerSubagentExtension(pi: ExtensionAPI): void {
 
 	const supervisorChannel = createNativeSupervisorChannel(pi, state);
 	const waitSubscriptionManager = createWaitSubscriptionManager(pi, state);
-	const mainWatchdog = registerMainWatchdog(pi);
 	const completionNotifier = registerSubagentNotify(pi, state, { batchConfig: config.completionBatch });
-	const fleetStatus = fleetViewEnabled
-		? new SubagentFleetStatus(state, async (itemKey) => {
-			const ctx = state.lastUiContext;
-			if (!ctx?.hasUI) return;
-			await openSubagentFleet(ctx, state, { initialKey: itemKey, asyncDirRoot: DIRS.async, resultsDir: DIRS.results, fleetKeybindings: config.fleetKeybindings });
-		}, { placement: fleetViewPlacement })
-		: undefined;
-	let executorScheduled: ((id: string, params: SubagentParamsLike, signal: AbortSignal, ctx: ExtensionContext) => Promise<AgentToolResult<Details>>) | undefined;
 	let goalTurnId = 0;
-	const scheduledStoreRoot = config.scheduledRuns?.storeRoot === undefined ? undefined : resolveScheduledStoreRoot(config.scheduledRuns.storeRoot);
-	const scheduledRunManager = createScheduledRunManager({
-		config,
-		storeRoot: scheduledStoreRoot,
-		launch: (params, ctx, signal) => {
-			if (!executorScheduled) {
-				return Promise.resolve({
-					content: [{ type: "text", text: "Scheduled subagent launch is unavailable (executor not ready)." }],
-					isError: true,
-					details: { mode: "management" as const, results: [] },
-				});
-			}
-			return executorScheduled(randomUUID(), params, signal, ctx);
-		},
-		resolveCapabilityCeiling: (sessionId) => resolveCurrentSubagentCapabilityCeiling(sessionId),
-	});
 	const { ensurePoller, refreshWidget, handleStarted, handleComplete, resetJobs, restoreActiveJobs, dispose: disposeAsyncJobTracker } = createAsyncJobTracker(pi, state, DIRS.async, {
 		widgetEnabled: asyncWidgetEnabled,
 	});
@@ -479,8 +448,6 @@ export default function registerSubagentExtension(pi: ExtensionAPI): void {
 		10 * 60 * 1000,
 		{
 			notifier: completionNotifier,
-			observeCompletion: (result) => scheduledRunManager.handleAsyncCompletion(result),
-			observedCompletionRunIds: () => scheduledRunManager.observedCompletionRunIds(),
 			deliverIntercomResults: config.intercomBridge?.resultDelivery === true,
 		},
 	);
@@ -490,11 +457,8 @@ export default function registerSubagentExtension(pi: ExtensionAPI): void {
 		stopResultWatcher();
 		state.currentSessionId = null;
 		completionNotifier.dispose();
-		mainWatchdog.dispose();
-		scheduledRunManager.stop();
 		supervisorChannel.dispose();
 		waitSubscriptionManager.dispose();
-		fleetStatus?.dispose();
 		disposeAsyncJobTracker();
 	};
 	globalStore[runtimeCleanupStoreKey] = runtimeCleanup;
@@ -505,14 +469,11 @@ export default function registerSubagentExtension(pi: ExtensionAPI): void {
 		config,
 		asyncByDefault,
 		waitToolEnabled: waitToolConfig.enabled,
-		handleScheduledRunAction: (params, ctx) => scheduledRunManager.handleToolCall(params, ctx),
-		watchdog: mainWatchdog,
 		tempArtifactsDir,
 		getSubagentSessionRoot,
 		expandTilde,
 		discoverAgents,
 	});
-	executorScheduled = executor.executeScheduled;
 
 	pi.registerMessageRenderer<SlashMessageDetails>(SLASH_RESULT_TYPE, (message, options, theme) => {
 		const details = resolveSlashMessageDetails(message.details);
@@ -737,20 +698,16 @@ export default function registerSubagentExtension(pi: ExtensionAPI): void {
 	};
 	const asyncStartedHandler = (payload: unknown) => {
 		handleStarted(payload);
-		fleetStatus?.refresh();
 	};
 	const asyncCompleteHandler = (payload: unknown) => {
 		handleComplete(payload);
 		refreshActiveAsyncCapacity();
-		scheduledRunManager.handleAsyncCompletion(payload);
-		fleetStatus?.refresh();
 	};
 	const eventUnsubscribes = [
 		pi.events.on(SUBAGENT_ASYNC_STARTED_EVENT, asyncStartedHandler),
 		pi.events.on(SUBAGENT_ASYNC_COMPLETE_EVENT, asyncCompleteHandler),
 		pi.events.on(SUBAGENT_PROCESS_TERMINAL_EVENT, () => {
 			refreshActiveAsyncCapacity();
-			fleetStatus?.refresh();
 		}),
 		pi.events.on(SUBAGENT_CONTROL_EVENT, controlEventHandler),
 		pi.events.on(SUBAGENT_STEERING_NOTICE_EVENT, steeringNoticeHandler),
@@ -764,8 +721,6 @@ export default function registerSubagentExtension(pi: ExtensionAPI): void {
 		if (!ctx.hasUI) return;
 		state.lastUiContext = ctx;
 		restoreActiveJobs(ctx);
-		fleetStatus?.setContext(ctx);
-		fleetStatus?.refresh();
 		if (state.asyncJobs.size > 0) {
 			refreshWidget(ctx);
 			ensurePoller();
@@ -787,14 +742,12 @@ export default function registerSubagentExtension(pi: ExtensionAPI): void {
 		if (state.widgetsSuspended) return;
 		state.widgetsSuspended = true;
 		if (state.lastUiContext?.hasUI) state.lastUiContext.ui.setWidget(WIDGET_KEY, undefined);
-		fleetStatus?.refresh();
 	};
 	const resumeWidgetsAfterCompaction = () => {
 		if (!state.widgetsSuspended) return;
 		state.widgetsSuspended = false;
 		const ctx = state.lastUiContext;
 		if (ctx?.hasUI) refreshWidget(ctx);
-		fleetStatus?.refresh();
 	};
 
 	const refreshActiveAsyncCapacity = () => {
@@ -890,8 +843,6 @@ export default function registerSubagentExtension(pi: ExtensionAPI): void {
 		logSlowPhase("active-job-restore", phaseStartedAt);
 		state.handoffResumePending = adoptedJobs > 0 && state.lastUiContext?.hasUI === true;
 		phaseStartedAt = Date.now();
-		scheduledRunManager.bindSession(ctx);
-		logSlowPhase("scheduled-runs", phaseStartedAt);
 		phaseStartedAt = Date.now();
 		restoreSlashFinalSnapshots(ctx.sessionManager.getEntries());
 		logSlowPhase("slash-snapshots", phaseStartedAt);
@@ -904,7 +855,6 @@ export default function registerSubagentExtension(pi: ExtensionAPI): void {
 		phaseStartedAt = Date.now();
 		primeExistingResults({ triggerTurn: !recovering });
 		logSlowPhase("result-prime", phaseStartedAt);
-		fleetStatus?.setContext(ctx);
 	};
 
 	pi.on("agent_start", () => {
@@ -977,7 +927,6 @@ export default function registerSubagentExtension(pi: ExtensionAPI): void {
 		if (globalStore[eventUnsubscribeStoreKey] === eventUnsubscribes) {
 			delete globalStore[eventUnsubscribeStoreKey];
 		}
-		scheduledRunManager.stop();
 		disposeAsyncJobTracker();
 		for (const timer of state.cleanupTimers.values()) {
 			clearTimeout(timer);
@@ -990,7 +939,6 @@ export default function registerSubagentExtension(pi: ExtensionAPI): void {
 		promptTemplateBridge.cancelAll();
 		promptTemplateBridge.dispose();
 		supervisorChannel.dispose();
-		fleetStatus?.dispose();
 		if (globalStore[runtimeCleanupStoreKey] === runtimeCleanup) {
 			delete globalStore[runtimeCleanupStoreKey];
 		}

package/dist/extensions/pi-subagents/src/extension/public-execution.ts

@@ -37,6 +37,9 @@ export function normalizePublicSubagentExecution<T extends PublicSubagentExecuti
 		return { ok: false, error: "action must be a non-empty management/control action, or omit action and use workflowScript.", mode: "management" };
 	}
 	const normalizedAction = typeof action === "string" ? action.trim() : undefined;
+	if (normalizedAction?.toLowerCase().startsWith("schedule.") || normalizedAction === "watchdog.configure" || normalizedAction === "watchdog.recommend-model") {
+		return { ok: false, error: `Removed action '${normalizedAction}' is no longer supported.`, mode: "management" };
+	}
 	if (params.clarify === true && params.workflowScript !== undefined) {
 		return { ok: false, error: "Public workflowScript execution does not support clarify UI.", mode: "workflow" };
 	}
@@ -48,17 +51,8 @@ export function normalizePublicSubagentExecution<T extends PublicSubagentExecuti
 		if (legacyAction === "single" || legacyAction === "parallel" || legacyAction === "tasks" || legacyAction === "chain") {
 			return { ok: false, error: `action '${normalizedAction}' is not a management action; use the direct execution fields ({ agent, task }, { chain: [...] }, { tasks: [...] }).`, mode: "workflow" };
 		}
-		if (normalizedAction === "schedule.create") {
-			if (typeof params.workflowScript === "string" && params.workflowScript.trim()) {
-				return { ok: true, params: { ...params, action: normalizedAction } };
-			}
-			if (params.agent === undefined && params.task === undefined && params.step === undefined && params.tasks === undefined && params.chain === undefined) {
-				return { ok: false, error: "schedule.create requires a non-empty workflowScript or direct execution fields (agent, task, tasks, or chain).", mode: "management" };
-			}
-			return { ok: true, params: { ...params, action: normalizedAction } };
-		}
 		if (params.workflowScript !== undefined) {
-			return { ok: false, error: "workflowScript execution must omit action; only schedule.create accepts action with workflowScript.", mode: "management" };
+			return { ok: false, error: "workflowScript execution must omit action; use management actions without workflowScript.", mode: "management" };
 		}
 		if (params.task !== undefined) {
 			return { ok: false, error: "Structured single-child task cannot be combined with a management/control action.", mode: "management" };

package/dist/extensions/pi-subagents/src/extension/rpc.ts

@@ -284,7 +284,7 @@ interface RegisterSubagentRpcBridgeOptions {
 	resultsDir?: string;
 	kill?: (pid: number, signal?: NodeJS.Signals | 0) => boolean;
 	now?: () => number;
-	/** Native live state, projected into the optional public fleet-status capability. */
+	/** Native live state for status consumers. */
 	state?: SubagentState;
 }
 
@@ -381,7 +381,6 @@ function pingData(ctx: ExtensionContext | null) {
 		methods: [...SUBAGENT_RPC_METHODS],
 		capabilities: {
 			status: true,
-			fleetStatus: { version: 1 },
 			asyncStatusSnapshot: { kind: ASYNC_STATUS_SNAPSHOT_KIND, version: ASYNC_STATUS_SNAPSHOT_VERSION },
 			asyncSpawn: true,
 			steer: true,

package/dist/extensions/pi-subagents/src/extension/schemas.ts

@@ -262,7 +262,6 @@ const SubagentParamProperties = {
 	action: Type.Optional(Type.String({ minLength: 1,
 		description: "Optional management/control action. Omit this field for structured single-child or workflowScript execution; use it only for management/control actions."
 	})),
-	name: Type.Optional(Type.String({ description: "Human-readable name for action='schedule.create'." })),
 	id: Type.Optional(Type.String({
 		description: "Run id/prefix for status/debug.run, interrupt, steer, append-step, approve-checkpoint, reject-checkpoint, or mission."
 	})),
@@ -284,18 +283,8 @@ const SubagentParamProperties = {
 	mode: Type.Optional(Type.String({ enum: ["steer", "follow_up", "auto"], description: "Delivery mode for action='steer': steer interrupts at the next safe point (default), follow_up waits for the next turn boundary, auto follows up mid-turn." })),
 	steeringRecovery: Type.Optional(Type.Boolean({ description: "For action='steer', allow pause-and-revive recovery after a missed acknowledgment. Defaults true for direct tool calls; false for extension RPC steering." })),
 	additional: Type.Optional(Type.Integer({ minimum: 1, description: "Positive launches to add with action='grant-spawn-budget'. Root interactive parent with native user confirmation only." })),
-	scope: Type.Optional(Type.String({ enum: ["session", "user", "project"], description: "Scope for action='watchdog.configure'. Defaults to session." })),
-	target: Type.Optional(Type.String({ enum: ["main", "children", "child"], description: "Target for watchdog actions." })),
 	focus: Type.Optional(Type.Boolean({ description: "Focus the new Herdr pane for inspector.open or project.open." })),
-	thinking: Type.Optional(Type.Unsafe({ anyOf: [{ type: "string" }, { type: "boolean", enum: [false] }], description: "Thinking level for action='watchdog.configure' (off/minimal/low/medium/high/xhigh/max, inherit, or false for off)." })),
-	schedule: Type.Optional(Type.String({ deprecated: true, description: "Deprecated. Use action='schedule.create' with at." })),
-	scheduleName: Type.Optional(Type.String({ deprecated: true, description: "Deprecated. Use name." })),
-	at: Type.Optional(Type.String({ description: "One-shot trigger for action='schedule.create': a relative delay such as '+10m' or an ISO timestamp with timezone." })),
-	every: Type.Optional(Type.String({ description: "Fixed recurring interval for action='schedule.create', such as '30m', '6h', '2d', or '2w'." })),
-	on: Type.Optional(Type.Unsafe({ anyOf: [{ type: "string" }, { type: "integer" }], description: "Reserved for a later calendar schedule slice." })),
-	timezone: Type.Optional(Type.String({ description: "Reserved for a later calendar schedule slice." })),
-	overlap: Type.Optional(Type.String({ enum: ["skip"], description: "Overlap policy. This slice supports skip only." })),
-	catchUp: Type.Optional(Type.String({ enum: ["none", "latest"], description: "Missed occurrence policy for recurring schedules. Defaults to latest." })),
+	thinking: Type.Optional(Type.Unsafe({ anyOf: [{ type: "string" }, { type: "boolean", enum: [false] }], description: "Thinking level override." })),
 	missionId: Type.Optional(Type.String({ description: "Mission id." })),
 	mission: Type.Optional(Type.Unsafe({ ...MissionLaunchOverride, description: "Mission object, or false for no mission. Requires exactly one non-empty title or summary; goal may only be true and then requires budget.tokens." })),
 	missionUpdate: Type.Optional(Type.Unsafe({ ...MissionUpdateOverride, description: "Mission update: objective, goal false or {paused:boolean}, budget, summary, labels, decisions, artifacts, or delivery receipts." })),

package/dist/extensions/pi-subagents/src/extension/tool-description.ts

@@ -33,7 +33,6 @@ MANAGEMENT / CONTROL (use action; omit execution fields):
 • status, interrupt, stop, resume, and steer manage live or persisted runs. Use status view:"fleet" for an overview or view:"transcript" with id and optional index to tail output.
 • { action: "append-step", id: "...", step: {agent:"agent-c", task:"Use {previous}"} } appends one step to an already-running durable chain. step is control-only, not an execution mode; use { chain: [...] } for new chains.
 • approve-checkpoint and reject-checkpoint decide a paused chain checkpoint.
-• Create durable project schedules with { action:"schedule.create", id?, name?, at:"+10m" | ISO, workflowScript:"return runs.run('main', {agent:'worker', task:'...'})" } or { every:"6h", workflowScript:"..." }. Manage them with schedule.list/show/history/pause/resume/run/run-due/delete. This first slice supports fixed intervals; calendar schedules and schedule mission attachment are deferred.
 
 ${SUBAGENT_SAFETY_GUIDANCE}`;
 
@@ -47,7 +46,7 @@ EXECUTE:
 • context can be fresh or fork. timeoutMs/maxRuntimeMs apply to foreground and async runs; foreground defaults to 30 minutes absent call/agent. Omit acceptance for read-only calls.
 
 MANAGE / CONTROL:
-• Use action without execution fields for list/get/models/guide/authoring, refine/refine.show/refine.rollback, mission, watchdog, status, interrupt, stop, resume, steer, script-only scheduling, diagnostics, and other management actions. guide reads shipped current-version docs by topic.
+• Use action without execution fields for list/get/models/guide/authoring, refine/refine.show/refine.rollback, mission, watchdog, status, interrupt, stop, resume, steer, diagnostics, and other management actions. guide reads shipped current-version docs by topic.
 • append-step uses step:{...} only for an already-running durable chain; step is not an execution mode.
 • A mission object needs exactly one non-empty title or summary; objective and labels are optional. goal may only be true and requires budget:{tokens}.
 

package/dist/extensions/pi-subagents/src/policy/authority.ts

@@ -2,7 +2,6 @@ export const AUTHORITY_ACTIONS = [
 	"discardWorktree",
 	"destructiveCleanup",
 	"spawnBudgetGrant",
-	"scheduleCreate",
 	"stopRun",
 	"steerRun",
 ] as const;
@@ -15,7 +14,6 @@ const DEFAULT_AUTHORITY_POLICY: Record<AuthorityAction, AuthorityDecision> = {
 	discardWorktree: "confirm",
 	destructiveCleanup: "confirm",
 	spawnBudgetGrant: "confirm",
-	scheduleCreate: "auto",
 	stopRun: "auto",
 	steerRun: "auto",
 };