fix(web): make continuous handoff self-recovering

tools/web/run-wbv2-supervisor.mjs

@@ -16,10 +16,12 @@ const valueArg = (name, fallback) => {
 };
 const maxIterations = Number(valueArg("--max-iterations", "0"));
 const pollMs = Number(valueArg("--poll-ms", "1000"));
+const pushRetries = Number(valueArg("--push-retries", "6"));
 const commitEnabled = process.argv.includes("--commit");
 const pushEnabled = process.argv.includes("--push");
 if (!Number.isSafeInteger(maxIterations) || maxIterations < 0) throw new Error("--max-iterations must be a non-negative integer; 0 means unlimited");
 if (!Number.isSafeInteger(pollMs) || pollMs < 0) throw new Error("--poll-ms must be a non-negative integer");
+if (!Number.isSafeInteger(pushRetries) || pushRetries < 0) throw new Error("--push-retries must be a non-negative integer");
 if (pushEnabled && !commitEnabled) throw new Error("--push requires --commit");
 
 fs.mkdirSync(abs(supervisorRoot), { recursive: true });
@@ -59,19 +61,34 @@ const releaseLock = () => {
   try { fs.unlinkSync(abs(lockPath)); }
   catch (error) { if (error?.code !== "ENOENT") throw error; }
 };
+let stopRequested = false;
+let stopSignal;
+let iteration = 0;
+let fatalHandled = false;
 const stopFromSignal = (signal) => {
-  try {
-    writeCheckpoint({ state: "stopped", iteration: 0, reason: signal });
-    appendLog(`stopped signal=${signal}`);
-    releaseLock();
-  }
-  finally {
-    process.exitCode = signal === "SIGINT" ? 130 : 143;
-  }
+  stopRequested = true;
+  stopSignal = signal;
+  appendLog(`stop-requested signal=${signal}`);
+  process.exitCode = signal === "SIGINT" ? 130 : 143;
 };
 process.once("SIGINT", () => stopFromSignal("SIGINT"));
 process.once("SIGTERM", () => stopFromSignal("SIGTERM"));
 
+const stopOnFatal = (error, source) => {
+  if (fatalHandled) return;
+  fatalHandled = true;
+  try {
+    writeCheckpoint({ state: "blocked", iteration, reason: source, error: error?.message ?? String(error) });
+    appendLog(`blocked reason=${source} error=${error?.message ?? String(error)}`);
+  }
+  finally {
+    releaseLock();
+    process.exit(1);
+  }
+};
+process.once("uncaughtException", (error) => stopOnFatal(error, "uncaught_exception"));
+process.once("unhandledRejection", (error) => stopOnFatal(error, "unhandled_rejection"));
+
 if (lockHandle === undefined) {
   throw new Error(`unable to acquire supervisor lock=${lockPath}`);
 }
@@ -96,14 +113,18 @@ const currentTask = () => {
 const childArgs = ["tools/web/run-wbv2-continuous.mjs", "--max-iterations", "1"];
 if (commitEnabled) childArgs.push("--commit");
 if (pushEnabled) childArgs.push("--push");
+if (pushEnabled) childArgs.push("--push-retries", String(pushRetries));
 
 appendLog(`started pid=${process.pid} maxIterations=${maxIterations} child=${childArgs.join(" ")}`);
 writeCheckpoint({ state: "started", iteration: 0, current: currentTask(), child: childArgs.join(" ") });
 
-let iteration = 0;
 let exitCode = 0;
 try {
   while (maxIterations === 0 || iteration < maxIterations) {
+    if (stopRequested) {
+      writeCheckpoint({ state: "stopped", iteration, current: currentTask(), reason: stopSignal });
+      break;
+    }
     const before = currentTask();
     const print = run(process.execPath, ["tools/web/print-task-context.mjs"]);
     const check = run(process.execPath, ["tools/web/check-task-context.mjs"]);
@@ -117,6 +138,10 @@ try {
     const child = run(process.execPath, childArgs);
     appendLog(`child task=${before.task} exit=${child.code}\n${child.output}`);
     const after = currentTask();
+    if (stopRequested) {
+      writeCheckpoint({ state: "stopped", iteration, before, after, reason: stopSignal, childExit: child.code });
+      break;
+    }
     if (child.code !== 0) {
       const reason = after.task === before.task ? "child_failed_same_task" : "child_failed_after_queue_advance";
       writeCheckpoint({ state: "blocked", iteration: iteration + 1, before, after, reason, childExit: child.code });
@@ -136,6 +161,9 @@ try {
       Atomics.wait(wait, 0, 0, pollMs);
     }
   }
+  if (stopRequested) {
+    exitCode = stopSignal === "SIGINT" ? 130 : 143;
+  }
   if (exitCode === 0) {
     const current = currentTask();
     writeCheckpoint({ state: maxIterations === 0 ? "running" : "complete", iteration, current });