feat(cli): self-healing daemon lifecycle

every daemon-routed verb now probes the ipc socket via /v1/version (instead of trusting existsSync), cleans up stale sock/pid files left by a crashed daemon, and auto-spawns a detached `claudemesh daemon up` under a file-lock when the daemon is down. polls for liveness up to a budget (3s for ad-hoc verbs, 10s for launch) before falling through to cold path. includes a per-process result cache (script doing 50 sends pays spawn cost at most once), a 30s recently-failed marker (no thundering-herd retries on crash-loop), a spawn-lock (concurrent invocations share one attempt), and a recursion guard env var (nested cli calls inside the daemon process skip auto-spawn). fixes the stale-socket bug where launch's ensureDaemonRunning returned early on a left-over socket file from a crashed daemon, silently breaking the spawned claude session's mcp shim. deferred to 1.28.0: --strict / --no-daemon flags, lazy-loading of cold-path code, per-session ipc tokens. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 11:17:32 +01:00
parent 8a5469a5df
commit 2b6cf2c14b
6 changed files with 396 additions and 49 deletions
--- a/apps/cli/CHANGELOG.md
+++ b/apps/cli/CHANGELOG.md
@@ -1,5 +1,54 @@
 # Changelog

+## 1.27.3 (2026-05-04) — self-healing daemon lifecycle
+
+The CLI now auto-recovers from a dead daemon on every invocation
+instead of silently mis-routing through a stale socket.
+
+### What changed
+
+- New `services/daemon/lifecycle.ts` — single helper that probes the
+  IPC socket via `/v1/version` (instead of trusting `existsSync`),
+  cleans up stale `daemon.sock` / `daemon.pid` files, and auto-spawns
+  a detached `claudemesh daemon up` under a file-lock when the daemon
+  is missing.
+- Polls for socket liveness up to a budget (3 s for ad-hoc verbs,
+  10 s for `claudemesh launch`) before falling through.
+- Recently-failed marker (`~/.claudemesh/daemon/.spawn-failure`,
+  30 s TTL) prevents thundering-herd retries when the daemon
+  crash-loops at startup.
+- Spawn-lock (`~/.claudemesh/daemon/.spawn.lock`) ensures concurrent
+  CLI invocations share one spawn attempt instead of racing.
+- Per-process result cache — a script doing 50 sends pays the spawn
+  cost at most once, not 50 times.
+- Recursion guard via `CLAUDEMESH_INTERNAL_NO_AUTOSPAWN=1` env (set
+  on the spawned daemon's env) so nested CLI calls inside the daemon
+  process don't re-trigger spawn.
+
+### User-visible behavior
+
+- `peer list`, `send`, `state get`, etc. now restart the daemon
+  automatically when invoked while the daemon is down.
+- One-line stderr info on auto-restart:
+  `[claudemesh] info daemon restarted automatically (took 615ms)`.
+- Cold-path fallback fires only when auto-spawn fails or is
+  suppressed by the recently-failed marker; in those cases a `warn`
+  line points at the daemon log.
+
+### Bug fixed
+
+`claudemesh launch`'s `ensureDaemonRunning` previously checked only
+`existsSync(SOCK_FILE)` and returned early on a stale socket left by
+a crashed daemon — silently breaking new sessions. Now delegates to
+the lifecycle helper which probes the socket and recovers.
+
+### What's not in this patch
+
+- `--strict` and `--no-daemon` flags (deferred to D in 1.28.0).
+- Lazy-loading of cold-path code (deferred to 1.28.0).
+- Per-session IPC tokens (deferred to 1.28.0 alongside D's
+  thin-client conversion).
+
 ## 1.27.2 (2026-05-04) — skill: full-flag launch templates

 Documentation-only ship. `skills/claudemesh/SKILL.md` gains a canonical
--- a/apps/cli/package.json
+++ b/apps/cli/package.json
@@ -1,6 +1,6 @@
 {
  "name": "claudemesh-cli",
-  "version": "1.27.2",
+  "version": "1.27.3",
  "description": "Peer mesh for Claude Code sessions — CLI + MCP server.",
  "keywords": [
    "claude-code",
--- a/apps/cli/src/commands/launch.ts
+++ b/apps/cli/src/commands/launch.ts
@@ -49,46 +49,28 @@ export interface LaunchFlags {
 *
 * As of 1.24.0 the daemon owns the broker WS and feeds the MCP push-pipe
 * over IPC SSE. If the socket is absent when Claude boots its MCP shim,
- * the shim bails (no fallback). So we probe for the socket here and, if
- * missing, spawn `claudemesh daemon up --mesh <slug>` in the background,
- * waiting briefly for the socket to appear.
- *
- * Best-effort: if the daemon spawn fails, we surface the error and let
- * the launch proceed — Claude Code will print the same "daemon not
- * running" message and the user can fix it manually.
+ * the shim bails (no fallback). Delegates to the shared lifecycle helper
+ * (services/daemon/lifecycle.ts) which probes the socket properly
+ * (avoiding the stale-socket bug where existsSync was a false positive
+ * after a daemon crash), spawns under a file-lock, and polls for liveness.
 */
 async function ensureDaemonRunning(meshSlug: string, quiet: boolean): Promise<void> {
-  const { DAEMON_PATHS } = await import("~/daemon/paths.js");
-  if (existsSync(DAEMON_PATHS.SOCK_FILE)) return;
-
-  if (!quiet) render.info("starting claudemesh daemon…");
-  const { spawn } = await import("node:child_process");
-  const argv0 = process.argv[1] ?? "claudemesh";
-  let binary = argv0;
-  if (/\.ts$/.test(binary) || /node_modules|src\/entrypoints/.test(binary)) {
-    try {
-      const { execSync } = await import("node:child_process");
-      binary = execSync("which claudemesh", { encoding: "utf8" }).trim();
-    } catch { binary = "claudemesh"; }
+  const { ensureDaemonReady } = await import("~/services/daemon/lifecycle.js");
+  if (!quiet) render.info("ensuring claudemesh daemon is running…");
+  // Larger budget for `launch` — it's a one-shot flow where the user
+  // is actively waiting; cold node start + broker hello can take
+  // longer than the default 3s budget for ad-hoc verbs.
+  const res = await ensureDaemonReady({ budgetMs: 10_000, mesh: meshSlug });
+  if (res.state === "up") {
+    if (!quiet) render.ok("daemon already running");
+    return;
  }
-  const child = spawn(binary, ["daemon", "up", "--mesh", meshSlug], {
-    detached: true,
-    stdio: "ignore",
-  });
-  child.unref();
-
-  // Wait for the socket to appear. 10 s budget — covers cold node start +
-  // broker hello round-trip on slow links.
-  const start = Date.now();
-  while (Date.now() - start < 10_000) {
-    if (existsSync(DAEMON_PATHS.SOCK_FILE)) {
-      if (!quiet) render.ok("daemon ready");
-      return;
-    }
-    await new Promise((r) => setTimeout(r, 200));
+  if (res.state === "started") {
+    if (!quiet) render.ok(`daemon ready (${res.durationMs}ms)`);
+    return;
  }
  render.warn(
-    "daemon failed to start within 10s",
+    `daemon ${res.state}${res.reason ? `: ${res.reason}` : ""}`,
    "Run `claudemesh daemon up --mesh " + meshSlug + "` manually, then re-launch.",
  );
 }
--- a/apps/cli/src/services/bridge/daemon-route.ts
+++ b/apps/cli/src/services/bridge/daemon-route.ts
@@ -1,21 +1,40 @@
 // Try forwarding a send through the local daemon's IPC. Returns null if
 // the daemon isn't running or the daemon's mesh doesn't match the target
 // mesh — the caller falls back to the bridge or cold path.
-
-import { existsSync } from "node:fs";
+//
+// Auto-recovery: when the daemon socket is missing or stale, every
+// helper here calls into the lifecycle module which probes, spawns
+// (under a lock), polls, and retries — so cold-path fallback only
+// fires if auto-spawn failed. The lifecycle module caches its
+// per-process result, so a script doing 50 sends pays the spawn cost
+// at most once.

 import { ipc } from "~/daemon/ipc/client.js";
-import { DAEMON_PATHS } from "~/daemon/paths.js";
+import { ensureDaemonReady } from "~/services/daemon/lifecycle.js";
+import { warnDaemonState } from "~/ui/warnings.ts";

 function meshQuery(mesh?: string): string {
  return mesh ? `?mesh=${encodeURIComponent(mesh)}` : "";
 }

+/** Common entry: ensure the daemon is reachable, emitting a one-shot
+ *  stderr warning describing what we did. Returns true when the daemon
+ *  is now reachable, false when the caller should fall back. */
+async function daemonReachable(): Promise<boolean> {
+  const res = await ensureDaemonReady();
+  // Suppress the warning under JSON / quiet at the call site —
+  // helpers here can't see those flags. JSON callers should switch
+  // to lifecycle directly. For now we always print; --quiet at the
+  // top of each verb already redirects stderr where needed.
+  warnDaemonState(res, {});
+  return res.state === "up" || res.state === "started";
+}
+
 /** Try fetching the peer list through the daemon (~1ms warm IPC).
 *  Returns null when the daemon socket isn't present so the caller can
 *  fall back to bridge / cold paths. */
 export async function tryListPeersViaDaemon(mesh?: string): Promise<unknown[] | null> {
-  if (!existsSync(DAEMON_PATHS.SOCK_FILE)) return null;
+  if (!(await daemonReachable())) return null;
  try {
    const res = await ipc<{ peers?: unknown[] }>({ path: `/v1/peers${meshQuery(mesh)}`, timeoutMs: 3_000 });
    if (res.status !== 200) return null;
@@ -29,7 +48,7 @@ export async function tryListPeersViaDaemon(mesh?: string): Promise<unknown[] |

 /** Try fetching mesh-published skills through the daemon. */
 export async function tryListSkillsViaDaemon(mesh?: string): Promise<unknown[] | null> {
-  if (!existsSync(DAEMON_PATHS.SOCK_FILE)) return null;
+  if (!(await daemonReachable())) return null;
  try {
    const res = await ipc<{ skills?: unknown[] }>({ path: `/v1/skills${meshQuery(mesh)}`, timeoutMs: 3_000 });
    if (res.status !== 200) return null;
@@ -43,7 +62,7 @@ export async function tryListSkillsViaDaemon(mesh?: string): Promise<unknown[] |

 /** Try fetching one skill body through the daemon. */
 export async function tryGetSkillViaDaemon(name: string, mesh?: string): Promise<unknown | null> {
-  if (!existsSync(DAEMON_PATHS.SOCK_FILE)) return null;
+  if (!(await daemonReachable())) return null;
  try {
    const res = await ipc<{ skill?: unknown }>({
      path: `/v1/skills/${encodeURIComponent(name)}${meshQuery(mesh)}`,
@@ -70,7 +89,7 @@ export type StateEntry = {
 *   - undefined when the daemon ran but the key is unset (404)
 *   - null when the daemon socket isn't present (caller falls back) */
 export async function tryGetStateViaDaemon(key: string, mesh?: string): Promise<StateEntry | undefined | null> {
-  if (!existsSync(DAEMON_PATHS.SOCK_FILE)) return null;
+  if (!(await daemonReachable())) return null;
  try {
    const path = `/v1/state?key=${encodeURIComponent(key)}${mesh ? `&mesh=${encodeURIComponent(mesh)}` : ""}`;
    const res = await ipc<{ state?: StateEntry; error?: string }>({ path, timeoutMs: 3_000 });
@@ -85,7 +104,7 @@ export async function tryGetStateViaDaemon(key: string, mesh?: string): Promise<
 }

 export async function tryListStateViaDaemon(mesh?: string): Promise<StateEntry[] | null> {
-  if (!existsSync(DAEMON_PATHS.SOCK_FILE)) return null;
+  if (!(await daemonReachable())) return null;
  try {
    const res = await ipc<{ entries?: StateEntry[] }>({ path: `/v1/state${meshQuery(mesh)}`, timeoutMs: 3_000 });
    if (res.status !== 200) return null;
@@ -98,7 +117,7 @@ export async function tryListStateViaDaemon(mesh?: string): Promise<StateEntry[]
 }

 export async function trySetStateViaDaemon(key: string, value: unknown, mesh?: string): Promise<boolean> {
-  if (!existsSync(DAEMON_PATHS.SOCK_FILE)) return false;
+  if (!(await daemonReachable())) return false;
  try {
    const res = await ipc<{ ok?: boolean; error?: string }>({
      method: "POST",
@@ -122,7 +141,7 @@ export type MemoryEntry = {
 };

 export async function tryRememberViaDaemon(content: string, tags?: string[], mesh?: string): Promise<{ id: string; mesh?: string } | null> {
-  if (!existsSync(DAEMON_PATHS.SOCK_FILE)) return null;
+  if (!(await daemonReachable())) return null;
  try {
    const res = await ipc<{ id?: string; mesh?: string; error?: string }>({
      method: "POST",
@@ -136,7 +155,7 @@ export async function tryRememberViaDaemon(content: string, tags?: string[], mes
 }

 export async function tryRecallViaDaemon(query: string, mesh?: string): Promise<MemoryEntry[] | null> {
-  if (!existsSync(DAEMON_PATHS.SOCK_FILE)) return null;
+  if (!(await daemonReachable())) return null;
  try {
    const path = `/v1/memory?q=${encodeURIComponent(query)}${mesh ? `&mesh=${encodeURIComponent(mesh)}` : ""}`;
    const res = await ipc<{ matches?: MemoryEntry[] }>({ path, timeoutMs: 5_000 });
@@ -150,7 +169,7 @@ export async function tryRecallViaDaemon(query: string, mesh?: string): Promise<
 }

 export async function tryForgetViaDaemon(id: string, mesh?: string): Promise<boolean> {
-  if (!existsSync(DAEMON_PATHS.SOCK_FILE)) return false;
+  if (!(await daemonReachable())) return false;
  try {
    const path = `/v1/memory/${encodeURIComponent(id)}${meshQuery(mesh)}`;
    const res = await ipc<{ ok?: boolean }>({ method: "DELETE", path, timeoutMs: 3_000 });
@@ -179,7 +198,7 @@ export async function trySendViaDaemon(args: {
   *  right mesh by either flag or single-mesh-default. */
  expectedMesh?: string;
 }): Promise<DaemonSendResult | null> {
-  if (!existsSync(DAEMON_PATHS.SOCK_FILE)) return null;
+  if (!(await daemonReachable())) return null;

  try {
    const res = await ipc<{
--- a/apps/cli/src/services/daemon/lifecycle.ts
+++ b/apps/cli/src/services/daemon/lifecycle.ts
@@ -0,0 +1,243 @@
+/**
+ * Daemon lifecycle helper — probe, auto-spawn, retry, fall-through.
+ *
+ * Every daemon-routed CLI verb passes through `ensureDaemonReady()` before
+ * its IPC call. The helper:
+ *
+ *   1. Probes the socket via a fast `/v1/version` IPC (~5-10 ms).
+ *   2. If the socket is missing OR present-but-stale, attempts a detached
+ *      `claudemesh daemon up` spawn under a file-lock.
+ *   3. Polls for the new socket up to a budget (default 3s).
+ *   4. Returns a state describing what happened, so the caller can either
+ *      proceed warm or fall back to the cold path with a clear warning.
+ *
+ * State machine:
+ *   - "up"               daemon was already running
+ *   - "started"          daemon was down; we spawned it; it came up
+ *   - "down"             daemon was down; auto-spawn skipped (e.g., recursion guard)
+ *   - "spawn-failed"     spawn attempted but socket never appeared within budget
+ *   - "spawn-suppressed" recently-failed marker is fresh; skipped retry
+ *
+ * Stale-socket handling: if the socket file exists but the IPC probe
+ * fails (ECONNREFUSED / timeout), we treat the file as stale, remove
+ * it, and proceed as if the daemon were down. This fixes the prior bug
+ * where `existsSync(SOCK_FILE)` was a false positive after a daemon
+ * crash.
+ *
+ * Recursion guard: when we spawn the daemon we set
+ * `CLAUDEMESH_INTERNAL_NO_AUTOSPAWN=1` in its env so any nested CLI
+ * calls inside the daemon skip the auto-spawn check and avoid a loop.
+ */
+
+import { existsSync, readFileSync, statSync, unlinkSync, writeFileSync } from "node:fs";
+import { join } from "node:path";
+
+import { ipc, IpcError } from "~/daemon/ipc/client.js";
+import { DAEMON_PATHS } from "~/daemon/paths.js";
+
+export type DaemonReadyState =
+  | "up"
+  | "started"
+  | "down"
+  | "spawn-failed"
+  | "spawn-suppressed";
+
+export interface EnsureDaemonResult {
+  state: DaemonReadyState;
+  /** Total ms spent in this call (probe ± spawn ± poll). */
+  durationMs: number;
+  /** When state is `spawn-failed` or `spawn-suppressed`, a one-line reason. */
+  reason?: string;
+}
+
+export interface EnsureDaemonOpts {
+  /** Total budget for socket-appearance polling after spawn. Default 3000ms. */
+  budgetMs?: number;
+  /** Skip auto-spawn entirely. Used by `--no-daemon` and the recursion guard. */
+  noAutoSpawn?: boolean;
+  /** When auto-spawning a legacy single-mesh daemon, pin a slug. Omit for multi-mesh (default). */
+  mesh?: string;
+}
+
+const SPAWN_LOCK_FILE  = () => join(DAEMON_PATHS.DAEMON_DIR, ".spawn.lock");
+const SPAWN_FAIL_FILE  = () => join(DAEMON_PATHS.DAEMON_DIR, ".spawn-failure");
+const SPAWN_FAIL_TTL_MS = 30_000;
+const PROBE_TIMEOUT_MS  = 800;
+
+let lastResultThisProcess: EnsureDaemonResult | null = null;
+
+/** Probe daemon and return what we know. Cached per-process so a script
+ *  with 50 sends doesn't re-spawn 50 times. */
+export async function ensureDaemonReady(opts: EnsureDaemonOpts = {}): Promise<EnsureDaemonResult> {
+  if (lastResultThisProcess && (lastResultThisProcess.state === "up" || lastResultThisProcess.state === "started")) {
+    return lastResultThisProcess;
+  }
+  if (process.env.CLAUDEMESH_INTERNAL_NO_AUTOSPAWN === "1") {
+    opts = { ...opts, noAutoSpawn: true };
+  }
+  const result = await runEnsureDaemon(opts);
+  lastResultThisProcess = result;
+  return result;
+}
+
+/** Reset the per-process cache. Test helper. */
+export function _resetDaemonReadyCache(): void {
+  lastResultThisProcess = null;
+}
+
+async function runEnsureDaemon(opts: EnsureDaemonOpts): Promise<EnsureDaemonResult> {
+  const t0 = Date.now();
+
+  // Step 1 — probe.
+  const probe = await probeDaemon();
+  if (probe === "up") return { state: "up", durationMs: Date.now() - t0 };
+  if (probe === "stale") cleanupStaleFiles();
+
+  // Step 2 — auto-spawn unless forbidden.
+  if (opts.noAutoSpawn) {
+    return { state: "down", durationMs: Date.now() - t0, reason: "auto-spawn disabled" };
+  }
+  if (recentSpawnFailureFresh()) {
+    return {
+      state: "spawn-suppressed",
+      durationMs: Date.now() - t0,
+      reason: `daemon failed to start within last ${Math.round(SPAWN_FAIL_TTL_MS / 1000)}s`,
+    };
+  }
+
+  // Step 3 — spawn detached.
+  const spawnRes = await spawnDaemon(opts);
+  if (spawnRes.ok) {
+    return { state: "started", durationMs: Date.now() - t0 };
+  }
+
+  // Step 4 — record failure for backoff and report.
+  markSpawnFailure();
+  return { state: "spawn-failed", durationMs: Date.now() - t0, reason: spawnRes.reason };
+}
+
+async function probeDaemon(): Promise<"up" | "absent" | "stale"> {
+  if (!existsSync(DAEMON_PATHS.SOCK_FILE)) return "absent";
+  try {
+    const res = await ipc<{ version?: string }>({ path: "/v1/version", timeoutMs: PROBE_TIMEOUT_MS });
+    if (res.status === 200) return "up";
+    return "stale";
+  } catch (err) {
+    if (err instanceof IpcError) return "stale";
+    const msg = String(err);
+    if (/ENOENT|ECONNREFUSED|ipc_timeout|EPIPE|ECONNRESET/.test(msg)) return "stale";
+    return "stale";
+  }
+}
+
+function cleanupStaleFiles(): void {
+  for (const p of [DAEMON_PATHS.SOCK_FILE, DAEMON_PATHS.PID_FILE]) {
+    try { unlinkSync(p); } catch { /* best-effort */ }
+  }
+}
+
+function recentSpawnFailureFresh(): boolean {
+  try {
+    const st = statSync(SPAWN_FAIL_FILE());
+    return Date.now() - st.mtimeMs < SPAWN_FAIL_TTL_MS;
+  } catch {
+    return false;
+  }
+}
+
+function markSpawnFailure(): void {
+  try { writeFileSync(SPAWN_FAIL_FILE(), String(Date.now()), { mode: 0o600 }); } catch { /* best-effort */ }
+}
+
+function clearSpawnFailure(): void {
+  try { unlinkSync(SPAWN_FAIL_FILE()); } catch { /* best-effort */ }
+}
+
+interface SpawnResult { ok: boolean; reason?: string; }
+
+async function spawnDaemon(opts: EnsureDaemonOpts): Promise<SpawnResult> {
+  const lockResult = await acquireOrShareLock(opts);
+  if (lockResult === "wait-existing") {
+    // Another process is spawning; just wait for the socket to appear.
+    return await pollForSocket(opts.budgetMs ?? 3_000);
+  }
+
+  try {
+    const { spawn } = await import("node:child_process");
+    const binary = await resolveCliBinary();
+    const args = ["daemon", "up"];
+    if (opts.mesh) args.push("--mesh", opts.mesh);
+
+    const child = spawn(binary, args, {
+      detached: true,
+      stdio: "ignore",
+      env: { ...process.env, CLAUDEMESH_INTERNAL_NO_AUTOSPAWN: "1" },
+    });
+    child.unref();
+
+    const polled = await pollForSocket(opts.budgetMs ?? 3_000);
+    if (polled.ok) clearSpawnFailure();
+    return polled;
+  } catch (err) {
+    return { ok: false, reason: err instanceof Error ? err.message : String(err) };
+  } finally {
+    releaseLock();
+  }
+}
+
+/** Acquire spawn lock. If another process holds it AND its pid is alive,
+ *  return "wait-existing" so we share that spawn attempt. If the pid is
+ *  dead, take over the lock. */
+async function acquireOrShareLock(_opts: EnsureDaemonOpts): Promise<"acquired" | "wait-existing"> {
+  const lockPath = SPAWN_LOCK_FILE();
+  if (existsSync(lockPath)) {
+    try {
+      const pidStr = readFileSync(lockPath, "utf8").trim();
+      const pid = Number.parseInt(pidStr, 10);
+      if (Number.isFinite(pid) && pid > 0) {
+        try {
+          process.kill(pid, 0); // signal 0 = liveness probe
+          return "wait-existing";
+        } catch {
+          // Holder is dead — fall through to take over.
+        }
+      }
+    } catch { /* unreadable lock — take over */ }
+  }
+  try {
+    writeFileSync(lockPath, String(process.pid), { mode: 0o600 });
+  } catch { /* best-effort; lock is advisory */ }
+  return "acquired";
+}
+
+function releaseLock(): void {
+  try { unlinkSync(SPAWN_LOCK_FILE()); } catch { /* best-effort */ }
+}
+
+async function pollForSocket(budgetMs: number): Promise<SpawnResult> {
+  const start = Date.now();
+  while (Date.now() - start < budgetMs) {
+    if (existsSync(DAEMON_PATHS.SOCK_FILE)) {
+      // Don't just trust file presence — confirm it answers.
+      const probe = await probeDaemon();
+      if (probe === "up") return { ok: true };
+    }
+    await new Promise((r) => setTimeout(r, 150));
+  }
+  return { ok: false, reason: `socket did not appear within ${budgetMs}ms` };
+}
+
+/** Resolve the absolute path to the `claudemesh` binary the user is running.
+ *  When invoked via tsx/bun in dev, fall back to the system `claudemesh`. */
+async function resolveCliBinary(): Promise<string> {
+  const argv1 = process.argv[1] ?? "claudemesh";
+  if (/\.ts$/.test(argv1) || /node_modules|src\/entrypoints/.test(argv1)) {
+    try {
+      const { execSync } = await import("node:child_process");
+      return execSync("which claudemesh", { encoding: "utf8" }).trim() || "claudemesh";
+    } catch {
+      return "claudemesh";
+    }
+  }
+  return argv1;
+}
--- a/apps/cli/src/ui/warnings.ts
+++ b/apps/cli/src/ui/warnings.ts
@@ -0,0 +1,54 @@
+/**
+ * Once-per-process daemon-state warnings, routed to stderr.
+ *
+ * Suppressed under --quiet (caller responsibility — we never inspect
+ * argv). JSON callers should consult the result's `state` field
+ * directly and skip calling this helper.
+ */
+
+import type { EnsureDaemonResult } from "~/services/daemon/lifecycle.js";
+import { dim } from "./styles.js";
+
+let alreadyWarned = false;
+
+export interface WarnDaemonOpts {
+  quiet?: boolean;
+  /** When true, emit nothing — the caller will surface the state in JSON. */
+  json?: boolean;
+}
+
+/** Print a single, severity-appropriate line to stderr describing the
+ *  result of `ensureDaemonReady`. Returns whether anything was printed. */
+export function warnDaemonState(
+  res: EnsureDaemonResult,
+  opts: WarnDaemonOpts = {},
+): boolean {
+  if (alreadyWarned) return false;
+  if (opts.quiet || opts.json) return false;
+  if (res.state === "up") return false;
+
+  alreadyWarned = true;
+  const tag = (label: string) => `[claudemesh] ${label}`;
+  const hint = (s: string) => dim(s);
+
+  switch (res.state) {
+    case "started":
+      process.stderr.write(`${tag("info")} daemon restarted automatically ${hint(`(took ${res.durationMs}ms)`)}\n`);
+      return true;
+    case "down":
+      process.stderr.write(`${tag("info")} daemon not running — using cold path ${hint("(slower; run `claudemesh daemon up` for warm path)")}\n`);
+      return true;
+    case "spawn-suppressed":
+      process.stderr.write(`${tag("warn")} ${res.reason ?? "daemon failed to start recently"} — using cold path ${hint("(run `claudemesh doctor`)")}\n`);
+      return true;
+    case "spawn-failed":
+      process.stderr.write(`${tag("warn")} daemon spawn failed${res.reason ? `: ${res.reason}` : ""} — using cold path ${hint("(check ~/.claudemesh/daemon/daemon.log)")}\n`);
+      return true;
+  }
+  return false;
+}
+
+/** Reset the once-per-process latch. Test helper. */
+export function _resetDaemonWarningLatch(): void {
+  alreadyWarned = false;
+}