@ouro.bot/cli 0.1.0-alpha.494 → 0.1.0-alpha.496

package/changelog.json

@@ -1,6 +1,18 @@
 {
   "_note": "This changelog is maintained as part of the PR/version-bump workflow. Agent-curated, not auto-generated. Agents read this file directly via read_file to understand what changed between versions.",
   "versions": [
+    {
+      "version": "0.1.0-alpha.496",
+      "changes": [
+        "New `Lifecycle` category in `ouro doctor` (`src/heart/daemon/doctor.ts:checkLifecycle`). Reads daemon.ndjson from the first available agent bundle and surfaces operator-relevant signal: last activity timestamp + age (warns if older than 5 minutes — daemon may be silent or stopped), daemon restart count in the last hour (warns if >3 — high churn), recent version-install events with installed versions, and any agent_process_error events with reason. Designed to answer the operator's question after the daemon goes silent: 'did it crash? when did it last do anything? did it just upgrade?' This session's daemon went silent at 04:30 UTC with no easy way to diagnose; the new check would have surfaced 'last event 18m ago — daemon may be silent or stopped' immediately. Tail-reads only the last 5000 log lines so doctor stays snappy on chatty daemons. 13 new tests covering recent activity, restart counts, install events, agent_process_error, age formatting, log truncation, and edge cases (malformed JSON, missing meta fields, missing log file, read failure)."
+      ]
+    },
+    {
+      "version": "0.1.0-alpha.495",
+      "changes": [
+        "New regression bundle at `src/__tests__/heart/provider-replay-regressions.test.ts` that captures provider replay-rejection bug shapes in one place — documentation-as-test. Each entry cites the PR that fixed the shape and the runbook entry; future debuggers seeing a 4xx from a provider on what looks like a valid turn can grep this file first to see if the shape was already encountered. Currently bundles the MiniMax-M2.7 inline-`<think>`-plus-tool_calls case (#612), the reused-tool_call_id-misordered-after-pruning case (#613), and a cross-reference stub for the event-id collision class (covered separately in session-events.test.ts). Also documents the contribution pattern: capture the failing shape, write the test BEFORE the fix, land the fix, verify the test passes, cite the PR. Linked from `docs/known-issues-and-recovery.md` so operators triaging a similar bug land on the test bundle by default."
+      ]
+    },
     {
       "version": "0.1.0-alpha.494",
       "changes": [
@@ -2616,13 +2628,6 @@
         "auth verify and auth switch now use pingProvider for real API verification instead of format-only checks. auth switch verifies credentials work before switching."
       ]
     },
-    {
-      "version": "0.1.0-alpha.125",
-      "changes": [
-        "Fix: Default runtime logger is now silent (no stderr sink) so nerves events emitted before logger configuration no longer interleave with the CLI spinner animation.",
-        "Fix: MCP server connect failures now include the command name, args, and a hint to check agent.json mcpServers configuration."
-      ]
-    },
     {
       "version": "0.1.0-alpha.124",
       "changes": [

package/dist/heart/daemon/doctor.js

@@ -14,6 +14,7 @@ exports.checkSenses = checkSenses;
 exports.checkHabits = checkHabits;
 exports.checkSecurity = checkSecurity;
 exports.checkDisk = checkDisk;
+exports.checkLifecycle = checkLifecycle;
 exports.runDoctorChecks = runDoctorChecks;
 const runtime_1 = require("../../nerves/runtime");
 const bluebubbles_health_diagnostics_1 = require("./bluebubbles-health-diagnostics");
@@ -448,9 +449,137 @@ function computeSummary(categories) {
     }
     return { passed, warnings, failed };
 }
+/**
+ * Recent daemon lifecycle: surfaces last activity timestamp, recent restarts,
+ * version-install events, and process errors from the last hour. Designed
+ * to answer the operator's question after the daemon has gone silent: "did
+ * it crash? when did it last do anything? did it just upgrade?"
+ *
+ * Reads daemon.ndjson from the first available agent bundle (one daemon
+ * serves all agents, so any agent's bundle has the shared log).
+ */
+function checkLifecycle(deps) {
+    const checks = [];
+    const HOUR_MS = 60 * 60 * 1000;
+    const STALE_THRESHOLD_MS = 5 * 60 * 1000;
+    const cutoff = Date.now() - HOUR_MS;
+    const agents = discoverAgents(deps);
+    let logPath = null;
+    for (const agentDir of agents) {
+        const candidate = `${deps.bundlesRoot}/${agentDir}/state/daemon/logs/daemon.ndjson`;
+        if (deps.existsSync(candidate)) {
+            logPath = candidate;
+            break;
+        }
+    }
+    if (!logPath) {
+        checks.push({ label: "daemon log readable", status: "warn", detail: "no daemon.ndjson found in any agent bundle" });
+        return { name: "Lifecycle", checks };
+    }
+    let lastTs = null;
+    let lastEvent = null;
+    let startCount = 0;
+    let installCount = 0;
+    let installVersions = [];
+    let processErrors = [];
+    let lastEntryAgeMs = Number.POSITIVE_INFINITY;
+    try {
+        // Read the whole log via deps.readFileSync, then take the tail. For a
+        // chatty daemon this can be a few MB; we only inspect the last 5000
+        // lines which is enough for the last hour of activity. If the file is
+        // small (typical case), reading it all is cheap.
+        const raw = deps.readFileSync(logPath);
+        const allLines = raw.split("\n").filter((l) => l.trim());
+        const usable = allLines.length > 5000 ? allLines.slice(-5000) : allLines;
+        for (const line of usable) {
+            let parsed;
+            try {
+                parsed = JSON.parse(line);
+            }
+            catch {
+                continue;
+            }
+            const ts = typeof parsed.ts === "string" ? parsed.ts : null;
+            const event = typeof parsed.event === "string" ? parsed.event : null;
+            if (!ts || !event)
+                continue;
+            const tsMs = Date.parse(ts);
+            if (Number.isNaN(tsMs))
+                continue;
+            lastTs = ts;
+            lastEvent = event;
+            lastEntryAgeMs = Math.min(lastEntryAgeMs, Date.now() - tsMs);
+            if (tsMs < cutoff)
+                continue;
+            if (event === "daemon.daemon_started")
+                startCount++;
+            if (event === "daemon.cli_version_install_end") {
+                installCount++;
+                const meta = parsed.meta;
+                const ver = typeof meta?.version === "string" ? meta.version : null;
+                if (ver)
+                    installVersions.push(ver);
+            }
+            if (event === "daemon.agent_process_error") {
+                const meta = parsed.meta;
+                const reason = typeof meta?.reason === "string" ? meta.reason : "unknown";
+                const agent = typeof meta?.agent === "string" ? meta.agent : "unknown";
+                processErrors.push(`${agent}: ${reason}`);
+            }
+        }
+    }
+    catch (error) {
+        checks.push({ label: "daemon log readable", status: "fail", detail: `read failed: ${error instanceof Error ? error.message : /* v8 ignore next -- non-Error throw is unreachable from deps.readFileSync (always Error) @preserve */ String(error)}` });
+        return { name: "Lifecycle", checks };
+    }
+    if (lastTs === null) {
+        checks.push({ label: "recent daemon activity", status: "warn", detail: "no parseable events in tail of daemon.ndjson" });
+    }
+    else {
+        const ageSec = Math.round(lastEntryAgeMs / 1000);
+        const ageDetail = ageSec < 60 ? `${ageSec}s ago` : `${Math.round(ageSec / 60)}m ago`;
+        if (lastEntryAgeMs > STALE_THRESHOLD_MS) {
+            checks.push({
+                label: "recent daemon activity",
+                status: "warn",
+                detail: `last event ${ageDetail} (${lastEvent}) — daemon may be silent or stopped`,
+            });
+        }
+        else {
+            checks.push({
+                label: "recent daemon activity",
+                status: "pass",
+                detail: `last event ${ageDetail} (${lastEvent})`,
+            });
+        }
+    }
+    if (startCount > 0) {
+        checks.push({
+            label: "daemon restarts (last hour)",
+            status: startCount > 3 ? "warn" : "pass",
+            detail: `${startCount} restart${startCount === 1 ? "" : "s"}${startCount > 3 ? " — high churn, investigate" : ""}`,
+        });
+    }
+    if (installCount > 0) {
+        checks.push({
+            label: "version installs (last hour)",
+            status: "pass",
+            detail: `installed: ${installVersions.join(", ")}`,
+        });
+    }
+    if (processErrors.length > 0) {
+        checks.push({
+            label: "agent process errors (last hour)",
+            status: "warn",
+            detail: `${processErrors.length} error${processErrors.length === 1 ? "" : "s"}: ${processErrors.slice(0, 3).join("; ")}${processErrors.length > 3 ? "..." : ""}`,
+        });
+    }
+    return { name: "Lifecycle", checks };
+}
 const CATEGORY_CHECKERS = [
     { name: "CLI", fn: checkCliPath },
     { name: "Daemon", fn: checkDaemon },
+    { name: "Lifecycle", fn: checkLifecycle },
     { name: "Agents", fn: checkAgents },
     { name: "Senses", fn: checkSenses },
     { name: "Habits", fn: checkHabits },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ouro.bot/cli",
-  "version": "0.1.0-alpha.494",
+  "version": "0.1.0-alpha.496",
   "main": "dist/heart/daemon/ouro-entry.js",
   "bin": {
     "cli": "dist/heart/daemon/ouro-bot-entry.js",