wip(fleet): F3-m2 native Pi heartbeat + sidecar reconciliation

WIP — not for merge yet. Implements the core of the custom Pi harness (R14/R15):
- runtime/pi/mosaic-extension.ts: native heartbeat — writes the same .hb contract
  (ts/pid/status[/model]) on a MOSAIC_HEARTBEAT_INTERVAL timer; turn_start/turn_end
  flip status busy/ok; model self-report via ctx.model; touches a .hb.native
  precedence marker. Also FIXES a latent bug: session_end -> session_shutdown (the
  old handler never fired) + corrects the import scope to @earendil-works/pi-coding-agent.
- start-agent-session.sh: sidecar DEFERS when the .hb.native marker is fresh
  (< 2x interval), else writes the fallback — native precedence, sidecar fallback,
  same contract so fleet ps is agnostic (per Lead's design). Generated script
  validated (bash -n) + deferral/fallback behavior tested.

REMAINING before PR: surface model in `fleet ps` (parseHeartbeat + row); vitest for
the native-HB writer; "proper tool usage" (registerTool) piece; rebase onto #599's
%q sidecar (overlap on the printf line).

Refs #588

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

packages/mosaic/framework/runtime/pi/mosaic-extension.ts

@@ -9,8 +9,15 @@
  *   4. Memory routing — remind agent to use ~/.config/mosaic/memory/
  */
 
-import type { ExtensionAPI } from '@mariozechner/pi-coding-agent';
-import { existsSync, readFileSync, writeFileSync, unlinkSync, mkdirSync } from 'node:fs';
+import type { ExtensionAPI, ExtensionContext } from '@earendil-works/pi-coding-agent';
+import {
+  existsSync,
+  readFileSync,
+  writeFileSync,
+  unlinkSync,
+  mkdirSync,
+  renameSync,
+} from 'node:fs';
 import { join, basename } from 'node:path';
 import { homedir } from 'node:os';
 import { execSync, spawnSync } from 'node:child_process';
@@ -25,6 +32,57 @@ const MOSAIC_HOME = process.env['MOSAIC_HOME'] ?? join(homedir(), '.config', 'mo
 // Helpers
 // ---------------------------------------------------------------------------
 
+// ---------------------------------------------------------------------------
+// Native heartbeat (fleet R14/R15)
+// ---------------------------------------------------------------------------
+// When this agent runs under the Mosaic fleet (MOSAIC_AGENT_NAME set), the
+// extension writes its OWN heartbeat in the same .hb contract `fleet ps` reads
+// (ts/pid/status[/model]) and touches a `.hb.native` precedence marker so the
+// shell sidecar defers. Native HB knows the real turn state (busy/ok), so it is
+// more accurate than the pane-PID-only sidecar fallback.
+const HB_AGENT_NAME = process.env['MOSAIC_AGENT_NAME'] ?? '';
+const HB_RUN_DIR = process.env['MOSAIC_HEARTBEAT_RUN_DIR'] ?? join(MOSAIC_HOME, 'fleet', 'run');
+const HB_INTERVAL_MS = (() => {
+  const s = Number.parseInt(process.env['MOSAIC_HEARTBEAT_INTERVAL'] ?? '', 10);
+  return Number.isFinite(s) && s > 0 ? s * 1000 : 15_000;
+})();
+
+function nativeHbEnabled(): boolean {
+  return HB_AGENT_NAME.length > 0;
+}
+
+function readModelId(ctx: ExtensionContext): string | null {
+  const m = ctx.model as unknown as { id?: string; name?: string } | undefined;
+  return m?.id ?? m?.name ?? null;
+}
+
+function writeNativeHeartbeat(status: 'ok' | 'busy', model: string | null): void {
+  if (!nativeHbEnabled()) return;
+  try {
+    mkdirSync(HB_RUN_DIR, { recursive: true });
+    const hb = join(HB_RUN_DIR, `${HB_AGENT_NAME}.hb`);
+    const lines = [`ts=${nowIso()}`, `pid=${process.pid}`, `status=${status}`];
+    if (model) lines.push(`model=${model}`);
+    const tmp = `${hb}.tmp.${process.pid}`;
+    writeFileSync(tmp, lines.join('\n') + '\n');
+    renameSync(tmp, hb); // atomic replace — fleet ps never reads a partial file
+    // Precedence marker: tells the shell sidecar that native HB is authoritative.
+    writeFileSync(join(HB_RUN_DIR, `${HB_AGENT_NAME}.hb.native`), nowIso() + '\n');
+  } catch {
+    // Best-effort: never let heartbeat I/O disrupt the Pi session.
+  }
+}
+
+function clearNativeMarker(): void {
+  if (!nativeHbEnabled()) return;
+  try {
+    const m = join(HB_RUN_DIR, `${HB_AGENT_NAME}.hb.native`);
+    if (existsSync(m)) unlinkSync(m); // native stopping — let the sidecar take over
+  } catch {
+    /* ignore */
+  }
+}
+
 function safeRead(filePath: string): string | null {
   try {
     return readFileSync(filePath, 'utf-8');
@@ -187,6 +245,9 @@ function buildMissionSummary(cwd: string, mission: ActiveMission): string {
 
 export default function register(pi: ExtensionAPI) {
   let sessionCwd = process.cwd();
+  let hbStatus: 'ok' | 'busy' = 'ok';
+  let hbModel: string | null = null;
+  let hbTimer: ReturnType<typeof setInterval> | null = null;
 
   // ── Session Start ─────────────────────────────────────────────────────
   pi.on('session_start', async (_event, ctx) => {
@@ -207,10 +268,39 @@ export default function register(pi: ExtensionAPI) {
     } else {
       ctx.ui.notify('Mosaic framework loaded', 'info');
     }
+
+    // Native heartbeat: write immediately, then on an interval. Idle = 'ok';
+    // turn_start/turn_end flip the status so `fleet ps` reflects real activity.
+    if (nativeHbEnabled()) {
+      hbModel = readModelId(ctx);
+      writeNativeHeartbeat('ok', hbModel);
+      hbTimer = setInterval(() => writeNativeHeartbeat(hbStatus, hbModel), HB_INTERVAL_MS);
+      if (typeof hbTimer.unref === 'function') hbTimer.unref();
+    }
   });
 
-  // ── Session End ───────────────────────────────────────────────────────
-  pi.on('session_end', async (_event, _ctx) => {
+  // ── Turn lifecycle → accurate busy/ok heartbeat ───────────────────────
+  pi.on('turn_start', async (_event, ctx) => {
+    hbStatus = 'busy';
+    hbModel = readModelId(ctx) ?? hbModel;
+    writeNativeHeartbeat('busy', hbModel);
+  });
+  pi.on('turn_end', async (_event, ctx) => {
+    hbStatus = 'ok';
+    hbModel = readModelId(ctx) ?? hbModel;
+    writeNativeHeartbeat('ok', hbModel);
+  });
+
+  // ── Session Shutdown ──────────────────────────────────────────────────
+  // (The pi API event is 'session_shutdown'; the prior 'session_end' handler
+  // never fired — fixed here so repo hooks + lock cleanup actually run.)
+  pi.on('session_shutdown', async (_event, _ctx) => {
+    if (hbTimer) {
+      clearInterval(hbTimer);
+      hbTimer = null;
+    }
+    clearNativeMarker();
+
     // Run repo session-end hook
     runRepoHook(sessionCwd, 'session-end');
 

packages/mosaic/framework/tools/fleet/start-agent-session.sh

@@ -129,7 +129,7 @@ _start_heartbeat_sidecar() {
   # references to any variables from this script's environment.
   local sidecar_script
   sidecar_script=$(printf \
-    'hb=%s; pid=%s; iv=%s; mkdir -p "$(dirname "$hb")"; while kill -0 "$pid" 2>/dev/null; do tmp="$hb.tmp.$$"; printf "ts=%%s\npid=%%s\nstatus=ok\n" "$(date +%%Y-%%m-%%dT%%H:%%M:%%S%%z)" "$pid" > "$tmp" && mv "$tmp" "$hb"; sleep "$iv"; done' \
+    'hb=%s; pid=%s; iv=%s; mkdir -p "$(dirname "$hb")"; while kill -0 "$pid" 2>/dev/null; do nat="$hb.native"; if [ -f "$nat" ] && [ "$(( $(date +%%s) - $(stat -c %%Y "$nat" 2>/dev/null || echo 0) ))" -lt "$(( iv * 2 ))" ]; then sleep "$iv"; continue; fi; tmp="$hb.tmp.$$"; printf "ts=%%s\npid=%%s\nstatus=ok\n" "$(date +%%Y-%%m-%%dT%%H:%%M:%%S%%z)" "$pid" > "$tmp" && mv "$tmp" "$hb"; sleep "$iv"; done' \
     "$hb_file" "$pane_pid" "$interval")
 
   # setsid + disown ensures the sidecar survives this script exiting.