@ddtcorex/dsh-maestro-supervisor 0.6.0 → 0.6.1

package/README.md

@@ -31,7 +31,7 @@ The package declares `dsh.client` (`platform: web`, `inject: ["@deepseek-ai/dsh-
 dsh plugin --profile web add @ddtcorex/dsh-maestro-supervisor
 # or manually:
 # edit ~/.dsh/profiles/web/package.json:
-# "@ddtcorex/dsh-maestro-supervisor": "link:/home/kai/Work/htdocs/maestro-harness/packages/dsh-maestro-supervisor"
+# "@ddtcorex/dsh-maestro-supervisor": "link:<workspace-root>/packages/dsh-maestro-supervisor"
 pnpm --dir ~/.dsh/profiles/web install
 ls -l ~/.dsh/profiles/web/node_modules/@ddtcorex/dsh-maestro-supervisor  # → .../packages/dsh-maestro-supervisor
 ```
@@ -113,8 +113,8 @@ curl -s http://127.0.0.1:3080/dsh-maestro-supervisor-resume/scan -X POST \
 # Resume (re-attaches agent + followup continue, recovers provider/model)
 curl -s http://127.0.0.1:3080/dsh-maestro-supervisor-resume/resume -X POST \
   -H 'content-type: application/json' \
-  -d '{"type":"client-request","rpcId":"r2","method":"resume","payload":{"ids":["--home-kai-Work-htdocs-maestro-harness--/session-abc"]}}'
-# → {"type":"server-response","rpcId":"r2","result":{"ok":true,"value":{"resumed":["--home-kai-Work-htdocs-maestro-harness--/session-abc"]}}}
+  -d '{"type":"client-request","rpcId":"r2","method":"resume","payload":{"ids":["--example-project--/session-abc"]}}'
+# → {"type":"server-response","rpcId":"r2","result":{"ok":true,"value":{"resumed":["--example-project--/session-abc"]}}}
 # or {"ok":false,"error":{"code":"bad-request","message":"resume requires at least one session id"}}
 ```
 
@@ -191,6 +191,6 @@ Hard mode (optional): `package.json` add `"@ddtcorex/dsh-maestro-notifier": "wor
 
 ## See Also
 
-- Spec: `docs/specs/2026-08-27-dsh-web-resilience-design.md`
+- Spec: `<workspace-root>/docs/specs/2026-08-27-dsh-web-resilience-design.md`
 - Skill: `maestro-skills/skills/dsh-safe-web-update/` (`restart-dsh-web.sh` with `dry_boot_and_verify()` and `--auto`)
 - Client bundling: `dsh-maestro-mobile` (`scripts/build-client.mjs` pattern)

package/lib/cli.js

@@ -122,6 +122,12 @@ Commands:
             },
             restartWeb: async () => {
                 const { execSync } = await import('node:child_process');
+                // Kill stale MainThread holding 3080/3000 before any restart attempt
+                // (EADDRINUSE crash leaves old pid alive with http 200; new start would fail)
+                try {
+                    execSync(`pids=$(ss -tlnp 2>/dev/null | sed -n 's/.*pid=\\([0-9]*\\).*/\\1/p' | sort -u); if [ -n "$pids" ]; then echo "[supervisor] killing stale pids $pids"; kill $pids 2>/dev/null || true; sleep 2; fi`, { timeout: 5000, stdio: 'pipe' });
+                }
+                catch { }
                 // Prefer systemd — if dsh-web.service is installed, restart/start it
                 try {
                     execSync('systemctl --user is-active --quiet dsh-web.service && systemctl --user restart dsh-web.service || systemctl --user start dsh-web.service', { timeout: 15000, stdio: 'pipe' });

package/lib/health-poller.js

@@ -39,14 +39,36 @@ export async function pollHealth(opts = {}) {
         // ignore log read errors
     }
     let logError;
-    const lowerLog = logContent.toLowerCase();
-    for (const pat of ERROR_PATTERNS) {
-        if (lowerLog.includes(pat.toLowerCase())) {
-            // extract line containing pattern (case-insensitive)
-            const line = logContent.split('\n').find(l => l.toLowerCase().includes(pat.toLowerCase())) ?? pat;
-            logError = line.trim().slice(0, 500);
+    // Find most recent error line (not first) and ignore stale errors that are
+    // followed by a successful boot (log tail is append-only, old EADDRINUSE stays forever).
+    // We check last occurrence and ensure no "dsh web: http" success after it.
+    const lines = logContent.split('\n');
+    const lowerLines = lines.map(l => l.toLowerCase());
+    let lastErrorIdx = -1;
+    let matchedLine = '';
+    for (let i = lines.length - 1; i >= 0; i--) {
+        const lower = lowerLines[i];
+        for (const pat of ERROR_PATTERNS) {
+            if (lower.includes(pat.toLowerCase())) {
+                lastErrorIdx = i;
+                matchedLine = lines[i].trim().slice(0, 500);
+                break;
+            }
+        }
+        if (lastErrorIdx !== -1)
             break;
+    }
+    if (lastErrorIdx !== -1) {
+        // If a successful boot line appears after the last error, error is stale (already recovered)
+        let hasSuccessAfter = false;
+        for (let i = lastErrorIdx + 1; i < lines.length; i++) {
+            if (lowerLines[i].includes('dsh web: http')) {
+                hasSuccessAfter = true;
+                break;
+            }
         }
+        if (!hasSuccessAfter)
+            logError = matchedLine;
     }
     // Distinguish FULL (http !=200) vs DEGRADED (http 200 but log has plugin error)
     if (fetchError) {
@@ -59,6 +81,19 @@ export async function pollHealth(opts = {}) {
         };
     }
     if (logError) {
+        // EADDRINUSE is fatal even with http 200 — old process still holds 3080/3000
+        // and new start failed; treat as FULL down so supervisor kills + restarts.
+        const lowerErr = logError.toLowerCase();
+        const isFatalPortError = lowerErr.includes('eaddrinuse') || lowerErr.includes('address already in use');
+        if (isFatalPortError) {
+            return {
+                up: false,
+                httpCode,
+                error: logError,
+                degraded: false,
+                logTail: logContent.slice(-5000),
+            };
+        }
         // http 200 but log error → DEGRADED (isolatable), not FULL
         if (httpCode === 200) {
             return {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ddtcorex/dsh-maestro-supervisor",
-  "version": "0.6.0",
+  "version": "0.6.1",
   "description": "Supervisor daemon for DSH Web resilience — auto-detect crashes, rollback to LKG, report",
   "type": "module",
   "main": "./lib/index.js",