fix(fleet): report idle agents as available

docs/scratchpads/h1-heartbeat-readiness.md

@@ -0,0 +1,66 @@
+# H1 — heartbeat readiness detection
+
+## Objective
+
+Add runtime-agnostic readiness classification to `mosaic fleet ps` so an agent can be reported as working/idle/stuck/stale/dead/unknown instead of treating pane liveness as progress.
+
+## Scope
+
+- `packages/mosaic/src/commands/fleet.ts`
+  - exported readiness state/types/default thresholds/helpers/classifier
+  - `AgentPsRow.readiness` additive JSON field
+  - table HB column and IDLE/STUCK flags
+- `packages/mosaic/src/commands/fleet.spec.ts`
+  - pure classifier branch/boundary coverage
+  - threshold helper coverage
+  - legitimate render/JSON assertion updates for new HB text
+
+## Acceptance Criteria
+
+- Branches covered: dead, unknown, stale, busy working, null-idle working, stuck boundary, idle boundary, working below idle.
+- Threshold env helpers default to 300s/900s and honor positive integer env values.
+- `fleet ps` rows populate `readiness` for roster and unmanaged socket sessions.
+- Table HB text becomes `<age>s/<readiness>` when heartbeat age exists; remains `unknown` when absent.
+- Flags include `IDLE`/`STUCK` for matching readiness.
+- Local gates green: `pnpm typecheck`, `pnpm lint`, `pnpm format:check`, fleet vitest.
+- Pre-push queue guard passes; PR opened off `origin/main`; no merge by worker.
+
+## Constraints / Assumptions
+
+- Source branch: `origin/main` @ `e3adc6a`.
+- No scope creep beyond readiness detection.
+- `docs/TASKS.md` and `docs/fleet/TASKS.md` are orchestrator-owned; worker will not modify them.
+- PRD alignment source: `docs/fleet/PRD.md` Phase 2 observability; this is a refinement of heartbeat observability, preserving existing unknown/stale behavior.
+
+## Plan
+
+1. Install dependencies with requested PNPM environment.
+2. Add readiness types/helpers/classifier near heartbeat constants.
+3. Add `readiness` to `AgentPsRow` and populate both row paths.
+4. Update table render and flags.
+5. Add unit tests and update affected ps render/JSON assertions.
+6. Run build precheck + required gates.
+7. Run automated independent review, remediate findings.
+8. Queue guard, push, open PR.
+
+## Progress
+
+- 2026-06-24: Branch created from `origin/main` @ `e3adc6a`.
+- 2026-06-24: Implemented readiness thresholds/classifier, JSON row field, HB column label, and IDLE/STUCK flags.
+- 2026-06-24: Added classifier branch/boundary tests, threshold helper tests, JSON shape assertions, and readiness table rendering assertions.
+
+## Verification Evidence
+
+- `pnpm install --store-dir "$HOME/.pnpm-store"` — pass.
+- `npx turbo build --filter=@mosaicstack/mosaic^...` — pass, 12/12 tasks successful.
+- `pnpm typecheck` — pass, 41/41 tasks successful.
+- `pnpm lint` — pass, 23/23 tasks successful.
+- `pnpm format:check` — pass, all matched files use Prettier style.
+- `pnpm --filter @mosaicstack/mosaic exec vitest run src/commands/fleet.spec.ts` — pass, 171 tests.
+- `pnpm --filter @mosaicstack/mosaic test` — pass, 39 files / 547 tests; `fleet.spec.ts` 171 tests.
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — approve, 0 findings (reviewed supplied diff; sandbox file-inspection limitation noted by tool).
+
+## Risks / Blockers
+
+- No current blocker.
+- Review tool could not inspect repo files directly due sandbox wrapper limitation, but it reviewed the supplied diff and approved with no findings.

docs/scratchpads/h1b-pane-idle-signal.md

@@ -0,0 +1,53 @@
+# H1b — tmux pane idle signal wiring
+
+## Objective
+
+Feed `classifyReadiness()` a real idle signal on tmux 3.4 by deriving `idleSeconds` from the first available tmux timestamp source: pane activity, then window activity, then session activity.
+
+## Scope
+
+- `packages/mosaic/src/commands/fleet.ts`
+  - Extend `buildTmuxListPanesCommand()` format to include `#{window_activity}` and `#{session_activity}` after the existing fields.
+  - Update `parseTmuxListPanes()` to choose the first non-empty finite positive timestamp and clamp future idle values to 0.
+- `packages/mosaic/src/commands/fleet.spec.ts`
+  - Cover pane/window/session activity parsing behavior, empty-field index alignment, null idle, future clamping, math correctness, and exact tmux format.
+
+## Out of Scope
+
+- No changes to `classifyReadiness()`, thresholds, `AgentPsRow`, or `fleet ps` rendering.
+- No merge by worker; orchestrator routes review/merge.
+- Workers do not modify `docs/TASKS.md`.
+
+## PRD Alignment
+
+Aligned with `docs/fleet/PRD.md` FR-1 and acceptance criteria for truthful `mosaic fleet ps` pane/pid/idle observability.
+
+## Plan
+
+1. Sync branch from latest `origin/main` and install dependencies with required pnpm env.
+2. Add/confirm reproducer tests for tmux 3.4 empty `pane_activity` and new fallback behavior.
+3. Implement the focused parser/format change only.
+4. Run required build, baseline gates, fleet vitest, and independent review.
+5. Run pre-push queue guard, push branch, and open PR to `main` with Mosaic wrapper.
+
+## Progress
+
+- 2026-06-24: Branch `fix/fleet-pane-idle-activity` created from `origin/main` @ `ec8dd7c` after fetching.
+- 2026-06-24: Session-start generated local `.mosaic/orchestrator/*` changes on the previous release branch; stashed as `coder1 session-start state before H1b` to keep this branch clean.
+- 2026-06-24: Added TDD coverage for the tmux 3.4 production case (`pane_activity` empty, `window_activity` populated), exact new list-panes format, null/future/multiple-source behavior.
+- 2026-06-24: Implemented parser fallback without changing readiness classifier thresholds or render shape.
+
+## Verification Evidence
+
+- `pnpm install --store-dir "$HOME/.pnpm-store"` — pass.
+- Reproducer before implementation: `pnpm --filter @mosaicstack/mosaic exec vitest run src/commands/fleet.spec.ts` — failed as expected (old format, no fallback, negative future idle).
+- `npx turbo build --filter=@mosaicstack/mosaic^...` — pass, 12/12 tasks successful.
+- `pnpm typecheck` — pass, 41/41 tasks successful.
+- `pnpm lint` — pass, 23/23 tasks successful.
+- `pnpm format:check` — pass, all matched files use Prettier style.
+- `pnpm --filter @mosaicstack/mosaic exec vitest run src/commands/fleet.spec.ts` — pass, 176 tests.
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — approve, 0 findings (reviewed supplied diff; sandbox file-inspection limitation noted by tool).
+
+## Risks / Blockers
+
+- No current blocker.

docs/scratchpads/h2-readiness-available.md

@@ -0,0 +1,70 @@
+# H2 — readiness semantics: available, not stuck
+
+## Objective
+
+Correct fleet readiness semantics so a healthy long-idle agent is reported as `available` (good/assignable) instead of `stuck` (fault). Reserve `stuck` in the type/JSON value space for future positive block evidence.
+
+## Scope
+
+- `packages/mosaic/src/commands/fleet.ts`
+  - replace `idle` readiness state with `available`
+  - keep `stuck` in the union but stop emitting it from idle-only heuristics
+  - remove stuck threshold helper/env handling
+  - remove IDLE/STUCK alarm flags from table rendering
+- `packages/mosaic/src/commands/fleet.spec.ts`
+  - update classifier branch/boundary tests
+  - assert very long idle maps to `available`, not `stuck`
+  - update table/JSON assertions for available with no alarm flags
+  - remove stuck threshold helper tests
+
+## Acceptance Criteria
+
+- `classifyReadiness()` remains pure/total/never-throw and maps:
+  - dead/stale/unknown unchanged
+  - busy/null/undefined/non-finite idle to `working`
+  - idle >= activity threshold to `available`
+  - idle < activity threshold to `working`
+- No idle-derived path emits `stuck`.
+- `MOSAIC_HEARTBEAT_IDLE_THRESHOLD` remains backward compatible as the working→available activity threshold.
+- `MOSAIC_HEARTBEAT_STUCK_THRESHOLD` and helper/default are removed.
+- `fleet ps` keeps the idle-seconds column header `IDLE`, renders `available` in HB label, and does not add IDLE/STUCK warning flags.
+- Local gates green: build precheck, typecheck, lint, format:check, fleet vitest.
+- PR opened against `main`; no merge by worker.
+
+## Constraints / Assumptions
+
+- Source branch: `origin/main` @ `1020cfa`.
+- `docs/TASKS.md` is orchestrator-owned; worker will not modify it.
+- Documentation impact is captured in this scratchpad and PR description; no user/admin guide behavior beyond CLI readiness label semantics.
+
+## Plan
+
+1. Install dependencies with requested PNPM environment.
+2. Inspect current H1/H1b readiness implementation and tests.
+3. Update classifier types/helpers/rendering.
+4. Update focused tests.
+5. Run build precheck + required gates.
+6. Run automated code review, remediate any findings.
+7. Queue guard, push, open PR.
+
+## Progress
+
+- 2026-06-24: Branch created from `origin/main` @ `1020cfa`.
+- 2026-06-24: Replaced idle-derived `idle`/`stuck` outputs with `available`; retained `stuck` in type union for future positive block evidence.
+- 2026-06-24: Removed stuck threshold env/helper plumbing and IDLE/STUCK alarm flags.
+- 2026-06-24: Updated classifier and table-render tests for available semantics.
+
+## Verification Evidence
+
+- `pnpm install --store-dir "$HOME/.pnpm-store"` — pass.
+- `npx turbo build --filter=@mosaicstack/mosaic^...` — pass, 12/12 tasks successful.
+- `pnpm typecheck` — pass, 41/41 tasks successful.
+- `pnpm lint` — pass, 23/23 tasks successful.
+- `pnpm format:check` — pass, all matched files use Prettier style.
+- `pnpm --filter @mosaicstack/mosaic exec vitest run src/commands/fleet.spec.ts` — pass, 177 tests.
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — approve, 0 findings (reviewed supplied diff; sandbox file-inspection limitation noted by tool).
+
+## Risks / Blockers
+
+- No current blocker.
+- Review tool could not inspect repo files directly due sandbox wrapper limitation, but it reviewed the supplied diff and approved with no findings.

packages/mosaic/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mosaicstack/mosaic",
-  "version": "0.0.42",
+  "version": "0.0.44",
   "repository": {
     "type": "git",
     "url": "https://git.mosaicstack.dev/mosaicstack/stack.git",

packages/mosaic/src/commands/fleet.spec.ts

@@ -19,17 +19,20 @@ import {
   buildSystemdShowCommand,
   buildTmuxListPanesCommand,
   buildTmuxListSessionsCommand,
+  classifyReadiness,
   classifySendResult,
   countOrchestrators,
   countEnhancers,
   detectDrift,
   enableFleetUnits,
   FLEET_PROFILES,
+  HEARTBEAT_IDLE_THRESHOLD_SECONDS,
   generateAgentEnv,
   getDefaultOperatorSourceLabel,
   getDefaultTenantAndHost,
   getRosterAgent,
   heartbeatPath,
+  idleThresholdSeconds,
   isSendAccepted,
   loadFleetRoster,
   mergeAgentEnv,
@@ -850,7 +853,7 @@ describe('fleet ps — command construction', () => {
       '-t',
       '=canary-pi:0.0',
       '-F',
-      '#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}',
+      '#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}',
     ]);
   });
 
@@ -933,6 +936,125 @@ describe('fleet ps — heartbeat parsing', () => {
   });
 });
 
+describe('fleet ps — readiness thresholds', () => {
+  const savedIdle = process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
+
+  afterEach(() => {
+    if (savedIdle === undefined) delete process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
+    else process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = savedIdle;
+  });
+
+  it('uses the default activity threshold when env is unset', () => {
+    delete process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
+
+    expect(idleThresholdSeconds()).toBe(HEARTBEAT_IDLE_THRESHOLD_SECONDS);
+  });
+
+  it('honors a positive integer activity threshold from env', () => {
+    process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = '120';
+
+    expect(idleThresholdSeconds()).toBe(120);
+  });
+
+  it('falls back to the default for invalid activity thresholds', () => {
+    process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = '0';
+
+    expect(idleThresholdSeconds()).toBe(HEARTBEAT_IDLE_THRESHOLD_SECONDS);
+  });
+});
+
+describe('fleet ps — readiness classification', () => {
+  const thresholds = { idleThresholdSeconds: 300 };
+
+  it('reports dead when the pane is not alive', () => {
+    expect(
+      classifyReadiness(
+        { paneAlive: false, hbHealth: 'healthy', hbStatus: 'busy', idleSeconds: 0 },
+        thresholds,
+      ),
+    ).toBe('dead');
+  });
+
+  it('reports unknown when heartbeat health is unknown', () => {
+    expect(
+      classifyReadiness(
+        { paneAlive: true, hbHealth: 'unknown', hbStatus: null, idleSeconds: 0 },
+        thresholds,
+      ),
+    ).toBe('unknown');
+  });
+
+  it('reports stale when heartbeat health is stale', () => {
+    expect(
+      classifyReadiness(
+        { paneAlive: true, hbHealth: 'stale', hbStatus: 'busy', idleSeconds: 1_000 },
+        thresholds,
+      ),
+    ).toBe('stale');
+  });
+
+  it('reports working when heartbeat status is busy, even after the activity threshold', () => {
+    expect(
+      classifyReadiness(
+        { paneAlive: true, hbHealth: 'healthy', hbStatus: 'busy', idleSeconds: 2_000 },
+        thresholds,
+      ),
+    ).toBe('working');
+  });
+
+  it('reports working when pane idle seconds are null', () => {
+    expect(
+      classifyReadiness(
+        { paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: null },
+        thresholds,
+      ),
+    ).toBe('working');
+  });
+
+  it('reports working when pane idle seconds are undefined', () => {
+    expect(
+      classifyReadiness({ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok' }, thresholds),
+    ).toBe('working');
+  });
+
+  it('reports working when pane idle seconds are non-finite', () => {
+    expect(
+      classifyReadiness(
+        { paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: Number.NaN },
+        thresholds,
+      ),
+    ).toBe('working');
+  });
+
+  it('reports available at the activity threshold boundary', () => {
+    expect(
+      classifyReadiness(
+        { paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: 300 },
+        thresholds,
+      ),
+    ).toBe('available');
+  });
+
+  it('reports working below the activity threshold', () => {
+    expect(
+      classifyReadiness(
+        { paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: 299 },
+        thresholds,
+      ),
+    ).toBe('working');
+  });
+
+  it('reports very long idle as available, not stuck', () => {
+    const readiness = classifyReadiness(
+      { paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: 100_000 },
+      thresholds,
+    );
+
+    expect(readiness).toBe('available');
+    expect(readiness).not.toBe('stuck');
+  });
+});
+
 describe('fleet ps — systemd show parsing', () => {
   it('parses ActiveState, SubState, UnitFileState from systemctl show output', () => {
     const output = 'ActiveState=active\nSubState=running\nUnitFileState=enabled\n';
@@ -953,9 +1075,11 @@ describe('fleet ps — systemd show parsing', () => {
 describe('fleet ps — tmux list-panes parsing', () => {
   const NOW_MS = 1_700_000_000_000;
 
-  it('parses alive pane with pid, command, and idle time', () => {
+  it('uses pane_activity when present', () => {
-    const activityEpoch = Math.floor((NOW_MS - 30_000) / 1000); // 30s ago
+    const paneActivityEpoch = Math.floor((NOW_MS - 30_000) / 1000); // 30s ago
-    const output = `12345 claude 0 ${activityEpoch}\n`;
+    const windowActivityEpoch = Math.floor((NOW_MS - 60_000) / 1000); // 60s ago
+    const sessionActivityEpoch = Math.floor((NOW_MS - 90_000) / 1000); // 90s ago
+    const output = `12345 claude 0 ${paneActivityEpoch} ${windowActivityEpoch} ${sessionActivityEpoch}\n`;
     const result = parseTmuxListPanes(output, NOW_MS);
     expect(result.pid).toBe(12345);
     expect(result.command).toBe('claude');
@@ -963,8 +1087,45 @@ describe('fleet ps — tmux list-panes parsing', () => {
     expect(result.idleSeconds).toBe(30);
   });
 
+  it('uses window_activity when pane_activity is empty', () => {
+    const windowActivityEpoch = Math.floor((NOW_MS - 45_000) / 1000); // 45s ago
+    const sessionActivityEpoch = Math.floor((NOW_MS - 90_000) / 1000); // 90s ago
+    const output = `12345 node 0  ${windowActivityEpoch} ${sessionActivityEpoch}\n`;
+    expect(output).toContain('0  '); // empty pane_activity preserves index alignment
+    const result = parseTmuxListPanes(output, NOW_MS);
+    expect(result.pid).toBe(12345);
+    expect(result.command).toBe('node');
+    expect(result.dead).toBe(false);
+    expect(result.idleSeconds).toBe(45);
+  });
+
+  it('uses session_activity when pane_activity and window_activity are empty', () => {
+    const sessionActivityEpoch = Math.floor((NOW_MS - 75_000) / 1000); // 75s ago
+    const output = `12345 node 0   ${sessionActivityEpoch}\n`;
+    const result = parseTmuxListPanes(output, NOW_MS);
+    expect(result.idleSeconds).toBe(75);
+  });
+
+  it('reports null idleSeconds when all activity sources are empty', () => {
+    const output = '12345 node 0   \n';
+    const result = parseTmuxListPanes(output, NOW_MS);
+    expect(result.idleSeconds).toBeNull();
+  });
+
+  it('computes exact idle seconds from now minus epoch seconds', () => {
+    const activityEpoch = 1_699_999_877;
+    const result = parseTmuxListPanes(`12345 claude 0 ${activityEpoch} 0 0\n`, NOW_MS);
+    expect(result.idleSeconds).toBe(123);
+  });
+
+  it('clamps future activity epochs to 0 idle seconds', () => {
+    const futureActivityEpoch = Math.floor((NOW_MS + 30_000) / 1000);
+    const result = parseTmuxListPanes(`12345 claude 0 ${futureActivityEpoch} 0 0\n`, NOW_MS);
+    expect(result.idleSeconds).toBe(0);
+  });
+
   it('reports dead pane when pane_dead=1', () => {
-    const output = `0 bash 1 0\n`;
+    const output = `0 bash 1 0 0 0\n`;
     const result = parseTmuxListPanes(output, NOW_MS);
     expect(result.dead).toBe(true);
   });
@@ -1324,8 +1485,9 @@ describe('fleet ps — JSON output shape (FR-6)', () => {
     // boot-enable warning: active + disabled
     expect(row.bootEnableWarning).toBe(true);
 
-    // heartbeat missing → unknown
+    // heartbeat missing → unknown readiness preserves existing display semantics
     expect(row.heartbeat.health).toBe('unknown');
+    expect(row.readiness).toBe('unknown');
 
     expect(row.name).toBe('canary-pi');
     expect(row.runtime).toBe('pi');
@@ -1387,6 +1549,88 @@ describe('fleet ps — command sequences issued', () => {
   });
 });
 
+describe('fleet ps — readiness table output', () => {
+  it('renders available in HB column without idle/stuck alarm flags', async () => {
+    const home = await mkdtemp(join(tmpdir(), 'mosaic-fleet-'));
+    const rosterPath = join(home, 'fleet', 'roster.yaml');
+    const runDir = join(home, 'fleet', 'run');
+    await mkdir(runDir, { recursive: true });
+    await writeFile(
+      rosterPath,
+      [
+        'version: 1',
+        'transport: tmux',
+        'agents:',
+        '  - name: working-agent',
+        '    runtime: pi',
+        '  - name: available-agent',
+        '    runtime: pi',
+      ].join('\n'),
+    );
+
+    const nowMs = 1_700_000_000_000;
+    const workingActivityEpoch = Math.floor((nowMs - 2_000) / 1000);
+    const availableActivityEpoch = Math.floor((nowMs - 40_000) / 1000);
+    const hbTs = new Date(nowMs - 1_000).toISOString();
+    await writeFile(join(runDir, 'working-agent.hb'), `ts=${hbTs}\npid=111\nstatus=ok\n`);
+    await writeFile(join(runDir, 'available-agent.hb'), `ts=${hbTs}\npid=222\nstatus=ok\n`);
+
+    const savedIdle = process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
+    process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = '5';
+
+    const dateNow = vi.spyOn(Date, 'now').mockReturnValue(nowMs);
+    const runner: CommandRunner = async (command, args) => {
+      const full = [command, ...args].join(' ');
+      if (full.includes('list-sessions')) {
+        return { stdout: 'working-agent\navailable-agent\n', stderr: '', exitCode: 0 };
+      }
+      if (full.includes('=working-agent:0.0')) {
+        return { stdout: `111 pi 0 ${workingActivityEpoch}\n`, stderr: '', exitCode: 0 };
+      }
+      if (full.includes('=available-agent:0.0')) {
+        return { stdout: `222 pi 0 ${availableActivityEpoch}\n`, stderr: '', exitCode: 0 };
+      }
+      if (full.includes('systemctl') && full.includes('show')) {
+        return {
+          stdout: 'ActiveState=active\nSubState=running\nUnitFileState=enabled\n',
+          stderr: '',
+          exitCode: 0,
+        };
+      }
+      return { stdout: '', stderr: '', exitCode: 0 };
+    };
+
+    const lines: string[] = [];
+    const origLog = console.log;
+    console.log = (msg: string) => {
+      lines.push(msg);
+    };
+
+    const program = new Command();
+    program.exitOverride();
+    registerFleetCommand(program, { runner, mosaicHome: home });
+
+    try {
+      await program.parseAsync(['node', 'mosaic', 'fleet', 'ps']);
+    } finally {
+      console.log = origLog;
+      dateNow.mockRestore();
+      if (savedIdle === undefined) delete process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
+      else process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = savedIdle;
+      await rm(home, { recursive: true, force: true });
+    }
+
+    const workingLine = lines.find((line) => line.includes('working-agent'));
+    const availableLine = lines.find((line) => line.includes('available-agent'));
+    expect(workingLine).toBeDefined();
+    expect(workingLine).toContain('1s/working');
+    expect(availableLine).toBeDefined();
+    expect(availableLine).toContain('1s/available');
+    expect(availableLine).not.toMatch(/\bIDLE\b/);
+    expect(availableLine).not.toMatch(/\bSTUCK\b/);
+  });
+});
+
 describe('buildTmuxListSessionsCommand', () => {
   it('builds exact list-sessions command with session_name format', () => {
     expect(buildTmuxListSessionsCommand('mosaic-fleet')).toEqual([
@@ -1514,6 +1758,7 @@ describe('fleet ps — unmanaged socket sessions', () => {
 
     // driftFlag must be false for unmanaged (no roster runtime to compare)
     expect(unmanagedRow.driftFlag).toBe(false);
+    expect(unmanagedRow.readiness).toBe('unknown');
   });
 
   it('shows UNMANAGED flag in table output for unmanaged sessions', async () => {

packages/mosaic/src/commands/fleet.ts

@@ -394,6 +394,7 @@ export function buildAgentTailCommand(agentName: string, lines: number, socketNa
 // ---------------------------------------------------------------------------
 
 export const HEARTBEAT_INTERVAL_MS = 15_000;
+export const HEARTBEAT_IDLE_THRESHOLD_SECONDS = 300;
 
 /**
  * Heartbeat interval in ms, honoring MOSAIC_HEARTBEAT_INTERVAL (seconds) so the
@@ -404,8 +405,57 @@ export function heartbeatIntervalMs(): number {
   const sec = Number.parseInt(process.env.MOSAIC_HEARTBEAT_INTERVAL ?? '', 10);
   return Number.isFinite(sec) && sec > 0 ? sec * 1000 : HEARTBEAT_INTERVAL_MS;
 }
+
+/** Activity threshold in seconds, honoring MOSAIC_HEARTBEAT_IDLE_THRESHOLD. */
+export function idleThresholdSeconds(): number {
+  const sec = Number.parseInt(process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD ?? '', 10);
+  return Number.isFinite(sec) && sec > 0 ? sec : HEARTBEAT_IDLE_THRESHOLD_SECONDS;
+}
 export const HEARTBEAT_HEALTHY_MULTIPLIER = 3;
 
+export type ReadinessState = 'working' | 'available' | 'stuck' | 'stale' | 'dead' | 'unknown';
+
+export interface ReadinessSignals {
+  paneAlive: boolean;
+  hbHealth: 'healthy' | 'stale' | 'unknown';
+  hbStatus: 'ok' | 'busy' | null;
+  idleSeconds: number | null;
+}
+
+export interface ReadinessThresholds {
+  idleThresholdSeconds: number;
+}
+
+/**
+ * Classify whether an agent is progressing based on already-parsed heartbeat/tmux signals.
+ * Best-effort and runtime-agnostic: it never probes, never throws, and preserves existing
+ * unknown/stale behavior when heartbeat data is absent or old.
+ */
+export function classifyReadiness(
+  signals: Partial<ReadinessSignals> | null | undefined,
+  thresholds: Partial<ReadinessThresholds> | null | undefined = {},
+): ReadinessState {
+  try {
+    if (signals?.paneAlive !== true) return 'dead';
+    if (signals.hbHealth === 'unknown' || signals.hbHealth === undefined) return 'unknown';
+    if (signals.hbHealth === 'stale') return 'stale';
+    if (signals.hbStatus === 'busy') return 'working';
+    if (signals.idleSeconds === null || signals.idleSeconds === undefined) return 'working';
+
+    const idleSeconds = Number.isFinite(signals.idleSeconds) ? signals.idleSeconds : null;
+    if (idleSeconds === null) return 'working';
+
+    const idleThreshold = Number.isFinite(thresholds?.idleThresholdSeconds)
+      ? Number(thresholds?.idleThresholdSeconds)
+      : idleThresholdSeconds();
+    // Follow-up: stuck pending per-agent assignment awareness: assigned task + idle past threshold => stuck.
+    if (idleSeconds >= idleThreshold) return 'available';
+    return 'working';
+  } catch {
+    return 'unknown';
+  }
+}
+
 export interface HeartbeatInfo {
   ts: Date | null;
   pid: number | null;
@@ -429,6 +479,7 @@ export interface AgentPsRow {
   paneCommand: string | null;
   idleSeconds: number | null;
   heartbeat: HeartbeatInfo;
+  readiness: ReadinessState;
   /** roster runtime !== actual pane command */
   driftFlag: boolean;
   /** active but UnitFileState=disabled */
@@ -461,7 +512,7 @@ export function buildSystemdShowCommand(agentName: string): string[] {
 
 /**
  * Returns the tmux list-panes command for an agent pane.
- * Format: `#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}`
+ * Format: `#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}`
  */
 export function buildTmuxListPanesCommand(agentName: string, socketName = ''): string[] {
   return [
@@ -471,7 +522,7 @@ export function buildTmuxListPanesCommand(agentName: string, socketName = ''): s
     '-t',
     `=${agentName}:0.0`,
     '-F',
-    '#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}',
+    '#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}',
   ];
 }
 
@@ -571,8 +622,8 @@ export function parseSystemdShow(output: string): {
 }
 
 /**
- * Parse the output of `tmux list-panes -F '#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}'`
+ * Parse the output of `tmux list-panes -F '#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}'`
- * pane_activity is a Unix epoch timestamp (seconds).
+ * Activity fields are Unix epoch timestamps (seconds), ordered most precise to coarsest.
  */
 export function parseTmuxListPanes(
   output: string,
@@ -582,15 +633,17 @@ export function parseTmuxListPanes(
   if (!line) {
     return { pid: null, command: null, dead: true, idleSeconds: null };
   }
-  // format: <pid> <command> <dead(0|1)> <activity_epoch>
+  // format: <pid> <command> <dead(0|1)> <pane_activity> <window_activity> <session_activity>
   const parts = line.split(' ');
   const pid = parts[0] ? (Number.isFinite(Number(parts[0])) ? Number(parts[0]) : null) : null;
   const command = parts[1] ?? null;
   const dead = parts[2] === '1';
-  const activityEpoch = parts[3] ? Number(parts[3]) : NaN;
+  const activityEpoch = parts
-  const idleSeconds =
+    .slice(3, 6)
-    Number.isFinite(activityEpoch) && activityEpoch > 0
+    .map((part) => (part ? Number(part) : NaN))
-      ? Math.floor((nowMs - activityEpoch * 1000) / 1000)
+    .find((epoch) => Number.isFinite(epoch) && epoch > 0);
+  const idleSeconds = activityEpoch
+    ? Math.max(0, Math.floor((nowMs - activityEpoch * 1000) / 1000))
     : null;
   return { pid, command, dead, idleSeconds };
 }
@@ -1022,6 +1075,9 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
       const nowMs = Date.now();
 
       const rows: AgentPsRow[] = [];
+      const readinessThresholds = {
+        idleThresholdSeconds: idleThresholdSeconds(),
+      };
 
       // Build the set of roster agent names for quick lookup when filtering socket sessions.
       const rosterAgentNames = new Set(roster.agents.map((a) => a.name));
@@ -1052,6 +1108,17 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
         const bootEnableWarning =
           sysInfo.ActiveState === 'active' && sysInfo.UnitFileState === 'disabled';
 
+        const paneAlive = !paneInfo.dead;
+        const readiness = classifyReadiness(
+          {
+            paneAlive,
+            hbHealth: hb.health,
+            hbStatus: hb.status,
+            idleSeconds: paneInfo.idleSeconds,
+          },
+          readinessThresholds,
+        );
+
         rows.push({
           name: agent.name,
           tenant_id,
@@ -1059,11 +1126,12 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
           runtime: agent.runtime,
           systemdActive: sysInfo.ActiveState,
           systemdEnabled: sysInfo.UnitFileState,
-          paneAlive: !paneInfo.dead,
+          paneAlive,
           panePid: paneInfo.pid,
           paneCommand: paneInfo.command,
           idleSeconds: paneInfo.idleSeconds,
           heartbeat: hb,
+          readiness,
           driftFlag,
           bootEnableWarning,
           managed: true,
@@ -1110,6 +1178,17 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
             const bootEnableWarning =
               sysInfo.ActiveState === 'active' && sysInfo.UnitFileState === 'disabled';
 
+            const paneAlive = !paneInfo.dead;
+            const readiness = classifyReadiness(
+              {
+                paneAlive,
+                hbHealth: hb.health,
+                hbStatus: hb.status,
+                idleSeconds: paneInfo.idleSeconds,
+              },
+              readinessThresholds,
+            );
+
             rows.push({
               name: sessionName,
               tenant_id,
@@ -1118,11 +1197,12 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
               runtime: 'unknown',
               systemdActive: sysInfo.ActiveState,
               systemdEnabled: sysInfo.UnitFileState,
-              paneAlive: !paneInfo.dead,
+              paneAlive,
               panePid: paneInfo.pid,
               paneCommand: paneInfo.command,
               idleSeconds: paneInfo.idleSeconds,
               heartbeat: hb,
+              readiness,
               // No roster runtime to compare — drift is not meaningful for unmanaged sessions
               driftFlag: false,
               bootEnableWarning,
@@ -1164,7 +1244,7 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
         const idle = row.idleSeconds !== null ? `${row.idleSeconds}s` : '-';
         const hbAge =
           row.heartbeat.ageMs !== null
-            ? `${Math.round(row.heartbeat.ageMs / 1000)}s/${row.heartbeat.health}`
+            ? `${Math.round(row.heartbeat.ageMs / 1000)}s/${row.readiness}`
             : `unknown`;
         const model = row.heartbeat.model ?? '-';
         const flags: string[] = [];