@ouro.bot/cli 0.1.0-alpha.60 → 0.1.0-alpha.600

package/dist/heart/daemon/daemon-health.js

@@ -0,0 +1,176 @@
+"use strict";
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.HEALTH_TRACKED_EVENTS = exports.DaemonHealthWriter = void 0;
+exports.isRollupStatus = isRollupStatus;
+exports.isDaemonStatus = isDaemonStatus;
+exports.getDefaultHealthPath = getDefaultHealthPath;
+exports.createHealthNervesSink = createHealthNervesSink;
+exports.readHealth = readHealth;
+const fs = __importStar(require("fs"));
+const os = __importStar(require("os"));
+const path = __importStar(require("path"));
+const runtime_1 = require("../../nerves/runtime");
+/**
+ * Daemon-wide rollup vocabulary — locked layer-1 contract.
+ *
+ * - `RollupStatus` is what `computeDaemonRollup` returns (post-inventory,
+ *   four-state). The function never returns `"down"` because by the time
+ *   the rollup is reachable the daemon has already started, opened its
+ *   socket, and read its agent inventory — pre-inventory failure is the
+ *   caller's domain.
+ * - `DaemonStatus` is what `DaemonHealthState.status` accepts. The caller
+ *   widens the rollup result with `"down"` along the daemon-entry failure
+ *   path (e.g. when the daemon process can't read inventory at all).
+ *
+ * `isRollupStatus` and `isDaemonStatus` are runtime guards used both by
+ * `readHealth` (validating cached health files on disk) and by render-side
+ * consumers that want to narrow `unknown` JSON into the typed union before
+ * branching on it.
+ */
+// Single source of truth — the literal lists below are the runtime
+// projection of the type unions. A future literal added to RollupStatus
+// MUST also be added to ROLLUP_STATUS_LITERALS or `satisfies` blows up
+// at tsc. That tightens the Layer 1 contract: producer + consumer +
+// guard all stay in lockstep.
+const ROLLUP_STATUS_LITERALS = ["healthy", "partial", "degraded", "safe-mode"];
+const DAEMON_STATUS_LITERALS = [...ROLLUP_STATUS_LITERALS, "down"];
+const ROLLUP_STATUS_VALUES = new Set(ROLLUP_STATUS_LITERALS);
+const DAEMON_STATUS_VALUES = new Set(DAEMON_STATUS_LITERALS);
+function isRollupStatus(value) {
+    return typeof value === "string" && ROLLUP_STATUS_VALUES.has(value);
+}
+function isDaemonStatus(value) {
+    return typeof value === "string" && DAEMON_STATUS_VALUES.has(value);
+}
+class DaemonHealthWriter {
+    healthPath;
+    constructor(healthPath) {
+        this.healthPath = healthPath;
+    }
+    writeHealth(state) {
+        try {
+            const dir = path.dirname(this.healthPath);
+            fs.mkdirSync(dir, { recursive: true });
+            const tmpPath = `${this.healthPath}.tmp.${process.pid}`;
+            fs.writeFileSync(tmpPath, JSON.stringify(state, null, 2) + "\n", "utf-8");
+            fs.renameSync(tmpPath, this.healthPath);
+            (0, runtime_1.emitNervesEvent)({
+                component: "daemon",
+                event: "daemon.health_written",
+                message: "daemon health file written",
+                meta: { path: this.healthPath, status: state.status },
+            });
+        }
+        catch {
+            // Best-effort: if we can't write, don't crash the daemon.
+        }
+    }
+}
+exports.DaemonHealthWriter = DaemonHealthWriter;
+function getDefaultHealthPath() {
+    return path.join(os.homedir(), ".ouro-cli", "daemon-health.json");
+}
+/** Events that trigger a debounced health file write */
+exports.HEALTH_TRACKED_EVENTS = new Set([
+    "daemon.habit_cron_verification_failed",
+    "daemon.habit_fire",
+    "daemon.agent_exit",
+    "daemon.agent_started",
+    "daemon.agent_config_invalid",
+    "daemon.agent_config_failure",
+    "daemon.agent_entry_missing",
+    "daemon.agent_spawn_failed",
+    "daemon.agent_startup_stale_recovered",
+    "daemon.agent_restart_exhausted",
+    "daemon.agent_permanent_failure",
+    "daemon.agent_cooldown_recovery",
+    "daemon.bootstrap_degraded",
+    "daemon.safe_mode_entered",
+    "daemon.habit_scheduler_start",
+]);
+/**
+ * Creates a nerves LogSink that triggers debounced health writes on relevant events.
+ * Components don't know about the health writer — they just emit events.
+ */
+function createHealthNervesSink(writer, getState) {
+    let debounceTimer = null;
+    return (entry) => {
+        if (!exports.HEALTH_TRACKED_EVENTS.has(entry.event)) {
+            return;
+        }
+        // Debounce: max once per second
+        if (debounceTimer !== null) {
+            clearTimeout(debounceTimer);
+        }
+        debounceTimer = setTimeout(() => {
+            debounceTimer = null;
+            const state = getState();
+            writer.writeHealth(state);
+        }, 1000);
+    };
+}
+function readHealth(healthPath) {
+    try {
+        const raw = fs.readFileSync(healthPath, "utf-8");
+        const parsed = JSON.parse(raw);
+        if (!isDaemonStatus(parsed.status) ||
+            typeof parsed.mode !== "string" ||
+            typeof parsed.pid !== "number" ||
+            typeof parsed.startedAt !== "string" ||
+            typeof parsed.uptimeSeconds !== "number" ||
+            !Array.isArray(parsed.degraded) ||
+            typeof parsed.agents !== "object" ||
+            parsed.agents === null ||
+            typeof parsed.habits !== "object" ||
+            parsed.habits === null) {
+            return null;
+        }
+        return {
+            status: parsed.status,
+            mode: parsed.mode,
+            pid: parsed.pid,
+            startedAt: parsed.startedAt,
+            uptimeSeconds: parsed.uptimeSeconds,
+            safeMode: parsed.safeMode,
+            degraded: parsed.degraded,
+            agents: parsed.agents,
+            habits: parsed.habits,
+        };
+    }
+    catch {
+        return null;
+    }
+}

package/dist/heart/daemon/daemon-rollup.js

@@ -0,0 +1,57 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.computeDaemonRollup = computeDaemonRollup;
+/**
+ * Pure rollup decision function — given the post-inventory daemon
+ * surface, returns the daemon-wide rollup state per the locked Layer 1
+ * vocabulary table:
+ *
+ *   | rollup     | when                                                      |
+ *   | ---------- | --------------------------------------------------------- |
+ *   | healthy    | every enabled agent serving + no bootstrap-degraded + no safe-mode |
+ *   | partial    | (≥1 serving + ≥1 not serving) OR (all serving + ≥1 bootstrap-degraded) |
+ *   | degraded   | zero enabled agents serving (fresh install OR all unhealthy)        |
+ *   | safe-mode  | `safeMode === true` overrides everything else                       |
+ *
+ * The function NEVER returns `"down"`. By the time `computeDaemonRollup`
+ * is reachable, the daemon process has started, opened its socket, and
+ * read its agent inventory — pre-inventory failure is the caller's
+ * domain. `daemon-entry.ts`'s startup-failure path assigns `"down"` to
+ * `DaemonHealthState.status` directly without consulting this function.
+ */
+function computeDaemonRollup(input) {
+    // Safe mode wins, period. Crash-loop detection trumps everything —
+    // we want the human to see SAFE MODE, not a noisy partial/degraded.
+    if (input.safeMode) {
+        return "safe-mode";
+    }
+    // Count serving agents. "Serving" = "running" worker status.
+    // Anything else (crashed/stopped/starting/etc) is not serving.
+    let serving = 0;
+    let notServing = 0;
+    for (const agent of input.enabledAgents) {
+        if (agent.status === "running") {
+            serving++;
+        }
+        else {
+            notServing++;
+        }
+    }
+    // Zero-serving wins over bootstrap-degraded — we have no working
+    // agents to surface a "partially working" story about. This covers
+    // both fresh-install (`enabledAgents.length === 0`) and
+    // all-failed-live-check (`serving === 0` with `notServing > 0`).
+    // Render layer (cli-render.ts) splits the UX copy by inspecting the
+    // agents map; the rollup itself doesn't carry the distinction.
+    if (serving === 0) {
+        return "degraded";
+    }
+    // From here we have ≥1 serving agent. The remaining choice is
+    // healthy vs partial.
+    const hasUnhealthyAgent = notServing > 0;
+    const hasBootstrapDegraded = input.bootstrapDegraded.length > 0;
+    if (hasUnhealthyAgent || hasBootstrapDegraded) {
+        return "partial";
+    }
+    return "healthy";
+}

package/dist/heart/daemon/daemon-runtime-sync.js

@@ -2,6 +2,22 @@
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.ensureCurrentDaemonRuntime = ensureCurrentDaemonRuntime;
 const runtime_1 = require("../../nerves/runtime");
+/* v8 ignore start -- daemon liveness poll: real socket timing untestable in vitest @preserve */
+async function verifyDaemonStarted(deps) {
+    if (!deps.checkSocketAlive)
+        return true;
+    const maxWaitMs = 10_000;
+    const pollIntervalMs = 500;
+    const deadline = Date.now() + maxWaitMs;
+    deps.onProgress?.("waiting for the replacement background service to answer");
+    while (Date.now() < deadline) {
+        await new Promise((r) => setTimeout(r, pollIntervalMs));
+        if (await deps.checkSocketAlive(deps.socketPath))
+            return true;
+    }
+    return false;
+}
+/* v8 ignore stop */
 function isKnownVersion(version) {
     return version !== "unknown" && version.trim().length > 0;
 }
@@ -17,6 +33,7 @@ function normalizeRuntimeIdentity(value) {
         lastUpdated: typeof value.lastUpdated === "string" ? value.lastUpdated : "unknown",
         repoRoot: typeof value.repoRoot === "string" ? value.repoRoot : "unknown",
         configFingerprint: typeof value.configFingerprint === "string" ? value.configFingerprint : "unknown",
+        managedAgents: typeof value.managedAgents === "string" ? value.managedAgents : "unknown",
     };
 }
 async function readRunningRuntimeIdentity(deps) {
@@ -55,23 +72,29 @@ function collectRuntimeDriftReasons(local, running) {
             running: running.configFingerprint,
         });
     }
-    return reasons;
-}
-function formatRuntimeValue(reason) {
-    if (reason.key === "configFingerprint") {
-        return `${reason.running.slice(0, 12)} -> ${reason.local.slice(0, 12)}`;
+    if (isKnownRuntimeValue(local.managedAgents)
+        && isKnownRuntimeValue(running.managedAgents)
+        && local.managedAgents !== running.managedAgents) {
+        reasons.push({
+            key: "managedAgents",
+            label: "managed agents",
+            local: local.managedAgents,
+            running: running.managedAgents,
+        });
     }
-    return `${reason.running} -> ${reason.local}`;
+    return reasons;
 }
-function formatRuntimeDriftSummary(reasons) {
-    return reasons.map((reason) => `${reason.label} ${formatRuntimeValue(reason)}`).join("; ");
+function formatRuntimeDriftPublicSummary(reasons) {
+    return reasons.map((reason) => reason.label).join(", ");
 }
 async function ensureCurrentDaemonRuntime(deps) {
+    deps.onProgress?.("checking whether an older background service is already running");
     const localRuntime = normalizeRuntimeIdentity({
         version: deps.localVersion,
         lastUpdated: deps.localLastUpdated,
         repoRoot: deps.localRepoRoot,
         configFingerprint: deps.localConfigFingerprint,
+        managedAgents: deps.localManagedAgents,
     });
     try {
         const runningRuntime = await readRunningRuntimeIdentity(deps);
@@ -80,17 +103,40 @@ async function ensureCurrentDaemonRuntime(deps) {
         let result;
         if (driftReasons.length > 0) {
             const includesVersionDrift = driftReasons.some((entry) => entry.key === "version");
-            const driftSummary = formatRuntimeDriftSummary(driftReasons);
+            const publicDriftSummary = formatRuntimeDriftPublicSummary(driftReasons);
             try {
+                deps.onProgress?.("stopping the older background service");
                 await deps.stopDaemon();
+                if (deps.prepareDaemonRuntimeReplacement) {
+                    deps.onProgress?.("disabling daemon auto-restart during replacement");
+                    try {
+                        await Promise.resolve(deps.prepareDaemonRuntimeReplacement());
+                    }
+                    catch (error) {
+                        (0, runtime_1.emitNervesEvent)({
+                            level: "warn",
+                            component: "daemon",
+                            event: "daemon.runtime_sync_replacement_prepare_error",
+                            message: "daemon runtime replacement preparation failed",
+                            meta: {
+                                socketPath: deps.socketPath,
+                                reason: formatErrorReason(error),
+                            },
+                        });
+                    }
+                }
             }
             catch (error) {
                 const reason = formatErrorReason(error);
                 result = {
+                    ok: false,
                     alreadyRunning: true,
                     message: includesVersionDrift
-                        ? `daemon already running (${deps.socketPath}; could not replace stale daemon ${runningVersion} -> ${deps.localVersion}: ${reason})`
-                        : `daemon already running (${deps.socketPath}; could not replace drifted daemon ${driftSummary}: ${reason})`,
+                        ? `daemon already running (${deps.socketPath}; could not replace the older background service ${runningVersion} -> ${deps.localVersion}: ${reason})`
+                        : `daemon already running (${deps.socketPath}; could not replace the older background service after runtime drift ${publicDriftSummary}: ${reason})`,
+                    startupFailureReason: includesVersionDrift
+                        ? "could not replace the older background service"
+                        : "could not replace the older background service after runtime drift",
                 };
                 (0, runtime_1.emitNervesEvent)({
                     level: "warn",
@@ -103,10 +149,12 @@ async function ensureCurrentDaemonRuntime(deps) {
                         localLastUpdated: localRuntime.lastUpdated,
                         localRepoRoot: localRuntime.repoRoot,
                         localConfigFingerprint: localRuntime.configFingerprint,
+                        localManagedAgents: localRuntime.managedAgents,
                         runningVersion,
                         runningLastUpdated: runningRuntime.lastUpdated,
                         runningRepoRoot: runningRuntime.repoRoot,
                         runningConfigFingerprint: runningRuntime.configFingerprint,
+                        runningManagedAgents: runningRuntime.managedAgents,
                         action: "stale_replace_failed",
                         driftKeys: driftReasons.map((entry) => entry.key),
                         reason,
@@ -115,12 +163,27 @@ async function ensureCurrentDaemonRuntime(deps) {
                 return result;
             }
             deps.cleanupStaleSocket(deps.socketPath);
+            deps.onProgress?.("starting the replacement background service");
+            const bootStartedAtMs = (deps.now ?? Date.now)();
             const started = await deps.startDaemonProcess(deps.socketPath);
+            const pid = started.pid ?? "unknown";
+            const startupCheck = deps.waitForDaemonStartup
+                ? await deps.waitForDaemonStartup({ pid: started.pid ?? null, bootStartedAtMs })
+                : { ok: await verifyDaemonStarted(deps) };
+            const verified = startupCheck.ok;
+            /* v8 ignore next -- daemon liveness failure: requires real daemon crash timing @preserve */
+            const suffix = verified
+                ? ""
+                : `\n${startupCheck.reason ?? "replacement background service did not answer in time"}; check logs with \`ouro logs\` or run \`ouro doctor\`.`;
             result = {
+                ok: verified,
                 alreadyRunning: false,
                 message: includesVersionDrift
-                    ? `restarted stale daemon from ${runningVersion} to ${deps.localVersion} (pid ${started.pid ?? "unknown"})`
-                    : `restarted drifted daemon (${driftSummary}) (pid ${started.pid ?? "unknown"})`,
+                    ? `replaced an older background service ${runningVersion} -> ${deps.localVersion} (pid ${pid})${suffix}`
+                    : `replaced an older background service after runtime drift: ${publicDriftSummary} (pid ${pid})${suffix}`,
+                verifyStartupStatus: verified,
+                startedPid: started.pid ?? null,
+                startupFailureReason: verified ? null : (startupCheck.reason ?? "replacement background service did not answer in time"),
             };
             (0, runtime_1.emitNervesEvent)({
                 component: "daemon",
@@ -132,10 +195,12 @@ async function ensureCurrentDaemonRuntime(deps) {
                     localLastUpdated: localRuntime.lastUpdated,
                     localRepoRoot: localRuntime.repoRoot,
                     localConfigFingerprint: localRuntime.configFingerprint,
+                    localManagedAgents: localRuntime.managedAgents,
                     runningVersion,
                     runningLastUpdated: runningRuntime.lastUpdated,
                     runningRepoRoot: runningRuntime.repoRoot,
                     runningConfigFingerprint: runningRuntime.configFingerprint,
+                    runningManagedAgents: runningRuntime.managedAgents,
                     action: "stale_restarted",
                     driftKeys: driftReasons.map((entry) => entry.key),
                     pid: started.pid ?? null,
@@ -145,6 +210,7 @@ async function ensureCurrentDaemonRuntime(deps) {
         }
         if (!isKnownVersion(localRuntime.version) || !isKnownVersion(runningVersion)) {
             result = {
+                ok: true,
                 alreadyRunning: true,
                 message: `daemon already running (${deps.socketPath}; unable to verify version)`,
             };
@@ -158,10 +224,12 @@ async function ensureCurrentDaemonRuntime(deps) {
                     localLastUpdated: localRuntime.lastUpdated,
                     localRepoRoot: localRuntime.repoRoot,
                     localConfigFingerprint: localRuntime.configFingerprint,
+                    localManagedAgents: localRuntime.managedAgents,
                     runningVersion,
                     runningLastUpdated: runningRuntime.lastUpdated,
                     runningRepoRoot: runningRuntime.repoRoot,
                     runningConfigFingerprint: runningRuntime.configFingerprint,
+                    runningManagedAgents: runningRuntime.managedAgents,
                     action: "unknown_version",
                 },
             });
@@ -171,6 +239,7 @@ async function ensureCurrentDaemonRuntime(deps) {
     catch (error) {
         const reason = formatErrorReason(error);
         const result = {
+            ok: true,
             alreadyRunning: true,
             message: `daemon already running (${deps.socketPath}; unable to verify version: ${reason})`,
         };
@@ -185,6 +254,7 @@ async function ensureCurrentDaemonRuntime(deps) {
                 localLastUpdated: localRuntime.lastUpdated,
                 localRepoRoot: localRuntime.repoRoot,
                 localConfigFingerprint: localRuntime.configFingerprint,
+                localManagedAgents: localRuntime.managedAgents,
                 action: "status_lookup_failed",
                 reason,
             },
@@ -192,8 +262,12 @@ async function ensureCurrentDaemonRuntime(deps) {
         return result;
     }
     const result = {
+        ok: true,
         alreadyRunning: true,
         message: `daemon already running (${deps.socketPath})`,
+        verifyStartupStatus: true,
+        startedPid: null,
+        startupFailureReason: null,
     };
     (0, runtime_1.emitNervesEvent)({
         component: "daemon",
@@ -205,6 +279,7 @@ async function ensureCurrentDaemonRuntime(deps) {
             localLastUpdated: localRuntime.lastUpdated,
             localRepoRoot: localRuntime.repoRoot,
             localConfigFingerprint: localRuntime.configFingerprint,
+            localManagedAgents: localRuntime.managedAgents,
             action: "already_current",
         },
     });