Merge pull request #748 from jeremymcs/fix/739-epipe-stale-research-state

fix(auto): prevent runaway execute-task when task plan missing after failed research (#739)

src/resources/extensions/gsd/auto-dispatch.ts

@@ -14,7 +14,7 @@ import type { GSDPreferences } from "./preferences.js";
 import type { UatType } from "./files.js";
 import { loadFile, extractUatType, loadActiveOverrides } from "./files.js";
 import {
-  resolveMilestoneFile, resolveMilestonePath, resolveSliceFile,
+  resolveMilestoneFile, resolveMilestonePath, resolveSliceFile, resolveTaskFile,
   relSliceFile, buildMilestoneFileName,
 } from "./paths.js";
 import { existsSync, mkdirSync, writeFileSync } from "node:fs";
@@ -249,6 +249,20 @@ const DISPATCH_RULES: DispatchRule[] = [
       const sTitle = state.activeSlice!.title;
       const tid = state.activeTask.id;
       const tTitle = state.activeTask.title;
+
+      // Guard: refuse to dispatch execute-task when the task plan file is missing.
+      // This prevents the agent from running blind after a failed plan-slice that
+      // wrote S{sid}-PLAN.md but omitted the individual T{tid}-PLAN.md files.
+      // (See issue #739 — missing task plan caused runaway execution and EPIPE crash.)
+      const taskPlanPath = resolveTaskFile(basePath, mid, sid, tid, "PLAN");
+      if (!taskPlanPath || !existsSync(taskPlanPath)) {
+        return {
+          action: "stop",
+          reason: `Task plan ${tid}-PLAN.md is missing for ${mid}/${sid}/${tid}. Re-run plan-slice to regenerate task plans, or create the file manually and resume.`,
+          level: "error",
+        };
+      }
+
       return {
         action: "dispatch",
         unitType: "execute-task",

src/resources/extensions/gsd/auto-recovery.ts

@@ -11,7 +11,7 @@ import type { ExtensionContext } from "@gsd/pi-coding-agent";
 import {
   clearUnitRuntimeRecord,
 } from "./unit-runtime.js";
-import { clearParseCache } from "./files.js";
+import { clearParseCache, parseRoadmap, parsePlan } from "./files.js";
 import {
   nativeConflictFiles,
   nativeCommit,
@@ -36,7 +36,6 @@ import {
   clearPathCache,
   resolveGsdRootFile,
 } from "./paths.js";
-import { parseRoadmap } from "./files.js";
 import { existsSync, mkdirSync, readFileSync, writeFileSync, unlinkSync, renameSync } from "node:fs";
 import { dirname, join } from "node:path";
 
@@ -161,6 +160,31 @@ export function verifyExpectedArtifact(unitType: string, unitId: string, base: s
     }
   }
 
+  // plan-slice must also produce individual task plan files for every task listed
+  // in the slice plan. Without this check, a plan-slice that wrote S{sid}-PLAN.md
+  // but omitted T{tid}-PLAN.md files would be marked complete, causing execute-task
+  // to dispatch with a missing task plan (see issue #739).
+  if (unitType === "plan-slice") {
+    const parts = unitId.split("/");
+    const mid = parts[0];
+    const sid = parts[1];
+    if (mid && sid) {
+      try {
+        const planContent = readFileSync(absPath, "utf-8");
+        const plan = parsePlan(planContent);
+        const tasksDir = resolveTasksDir(base, mid, sid);
+        if (plan.tasks.length > 0 && tasksDir) {
+          for (const task of plan.tasks) {
+            const taskPlanFile = join(tasksDir, `${task.id}-PLAN.md`);
+            if (!existsSync(taskPlanFile)) return false;
+          }
+        }
+      } catch {
+        // Parse failure — don't block; slice plan may have non-standard format
+      }
+    }
+  }
+
   // complete-slice must also produce a UAT file AND mark the slice [x] in the roadmap.
   // Without the roadmap check, a crash after writing SUMMARY+UAT but before updating
   // the roadmap causes an infinite skip loop: the idempotency key says "done" but the

src/resources/extensions/gsd/index.ts

@@ -129,6 +129,23 @@ export default function (pi: ExtensionAPI) {
   registerWorktreeCommand(pi);
   registerExitCommand(pi);
 
+  // ── EPIPE guard — prevent crash when stdout/stderr pipe closes unexpectedly ──
+  // Node.js throws a fatal `Error: write EPIPE` when the parent process closes
+  // its end of the stdio pipe (e.g. during shell/IPC teardown) while auto-mode
+  // is still writing diagnostics. Catching this here gives auto-mode a clean
+  // chance to persist state and pause instead of crashing (see issue #739).
+  if (!process.listeners("uncaughtException").some(l => l.name === "_gsdEpipeGuard")) {
+    const _gsdEpipeGuard = (err: Error): void => {
+      if ((err as NodeJS.ErrnoException).code === "EPIPE") {
+        // Pipe closed — nothing we can write; just exit cleanly
+        process.exit(0);
+      }
+      // Re-throw anything that isn't EPIPE so real crashes still surface
+      throw err;
+    };
+    process.on("uncaughtException", _gsdEpipeGuard);
+  }
+
   // ── /kill — immediate exit (bypass cleanup) ─────────────────────────────
   pi.registerCommand("kill", {
     description: "Exit GSD immediately (no cleanup)",

src/resources/extensions/gsd/prompts/research-slice.md

@@ -46,7 +46,7 @@ Research what this slice needs. Narrate key findings and surprises as you go —
 2. **Skill Discovery ({{skillDiscoveryMode}}):**{{skillDiscoveryInstructions}}
 3. Explore relevant code for this slice's scope. For targeted exploration, use `rg`, `find`, and reads. For broad or unfamiliar subsystems, use `scout` to map the relevant area first.
 4. Use `resolve_library` / `get_library_docs` for unfamiliar libraries — skip this for libraries already used in the codebase
-5. Use the **Research** output template from the inlined context above — include only sections that have real content
+5. Use the **Research** output template from the inlined context above — include only sections that have real content. The template is already inlined above; do NOT attempt to read any template file from disk (there is no `templates/SLICE-RESEARCH.md` — the correct template is already present in this prompt).
 6. Write `{{outputPath}}`
 
 The slice directory already exists at `{{slicePath}}/`. Do NOT mkdir — just write the file.

src/resources/extensions/gsd/tests/auto-recovery.test.ts

@@ -343,7 +343,8 @@ test("verifyExpectedArtifact accepts plan-slice with actual tasks", () => {
   const base = makeTmpBase();
   try {
     const sliceDir = join(base, ".gsd", "milestones", "M001", "slices", "S01");
-    mkdirSync(sliceDir, { recursive: true });
+    const tasksDir = join(sliceDir, "tasks");
+    mkdirSync(tasksDir, { recursive: true });
     writeFileSync(join(sliceDir, "S01-PLAN.md"), [
       "# S01: Test Slice",
       "",
@@ -352,6 +353,8 @@ test("verifyExpectedArtifact accepts plan-slice with actual tasks", () => {
       "- [ ] **T01: Implement feature** `est:2h`",
       "- [ ] **T02: Write tests** `est:1h`",
     ].join("\n"));
+    writeFileSync(join(tasksDir, "T01-PLAN.md"), "# T01 Plan");
+    writeFileSync(join(tasksDir, "T02-PLAN.md"), "# T02 Plan");
     assert.strictEqual(
       verifyExpectedArtifact("plan-slice", "M001/S01", base),
       true,
@@ -366,7 +369,8 @@ test("verifyExpectedArtifact accepts plan-slice with completed tasks", () => {
   const base = makeTmpBase();
   try {
     const sliceDir = join(base, ".gsd", "milestones", "M001", "slices", "S01");
-    mkdirSync(sliceDir, { recursive: true });
+    const tasksDir = join(sliceDir, "tasks");
+    mkdirSync(tasksDir, { recursive: true });
     writeFileSync(join(sliceDir, "S01-PLAN.md"), [
       "# S01: Test Slice",
       "",
@@ -375,6 +379,8 @@ test("verifyExpectedArtifact accepts plan-slice with completed tasks", () => {
       "- [x] **T01: Implement feature** `est:2h`",
       "- [ ] **T02: Write tests** `est:1h`",
     ].join("\n"));
+    writeFileSync(join(tasksDir, "T01-PLAN.md"), "# T01 Plan");
+    writeFileSync(join(tasksDir, "T02-PLAN.md"), "# T02 Plan");
     assert.strictEqual(
       verifyExpectedArtifact("plan-slice", "M001/S01", base),
       true,
@@ -384,3 +390,73 @@ test("verifyExpectedArtifact accepts plan-slice with completed tasks", () => {
     cleanup(base);
   }
 });
+
+// ─── verifyExpectedArtifact: plan-slice task plan check (#739) ────────────
+
+test("verifyExpectedArtifact plan-slice passes when all task plan files exist", () => {
+  const base = makeTmpBase();
+  try {
+    const tasksDir = join(base, ".gsd", "milestones", "M001", "slices", "S01", "tasks");
+    const planPath = join(base, ".gsd", "milestones", "M001", "slices", "S01", "S01-PLAN.md");
+    const planContent = [
+      "# S01: Test Slice",
+      "",
+      "## Tasks",
+      "",
+      "- [ ] **T01: First task** `est:1h`",
+      "- [ ] **T02: Second task** `est:2h`",
+    ].join("\n");
+    writeFileSync(planPath, planContent);
+    writeFileSync(join(tasksDir, "T01-PLAN.md"), "# T01 Plan\n\nDo the thing.");
+    writeFileSync(join(tasksDir, "T02-PLAN.md"), "# T02 Plan\n\nDo the other thing.");
+
+    const result = verifyExpectedArtifact("plan-slice", "M001/S01", base);
+    assert.equal(result, true, "should pass when all task plan files exist");
+  } finally {
+    cleanup(base);
+  }
+});
+
+test("verifyExpectedArtifact plan-slice fails when a task plan file is missing (#739)", () => {
+  const base = makeTmpBase();
+  try {
+    const tasksDir = join(base, ".gsd", "milestones", "M001", "slices", "S01", "tasks");
+    const planPath = join(base, ".gsd", "milestones", "M001", "slices", "S01", "S01-PLAN.md");
+    const planContent = [
+      "# S01: Test Slice",
+      "",
+      "## Tasks",
+      "",
+      "- [ ] **T01: First task** `est:1h`",
+      "- [ ] **T02: Second task** `est:2h`",
+    ].join("\n");
+    writeFileSync(planPath, planContent);
+    // Only write T01-PLAN.md — T02 is missing
+    writeFileSync(join(tasksDir, "T01-PLAN.md"), "# T01 Plan\n\nDo the thing.");
+
+    const result = verifyExpectedArtifact("plan-slice", "M001/S01", base);
+    assert.equal(result, false, "should fail when T02-PLAN.md is missing");
+  } finally {
+    cleanup(base);
+  }
+});
+
+test("verifyExpectedArtifact plan-slice fails for plan with no tasks (#699)", () => {
+  const base = makeTmpBase();
+  try {
+    const planPath = join(base, ".gsd", "milestones", "M001", "slices", "S01", "S01-PLAN.md");
+    const planContent = [
+      "# S01: Test Slice",
+      "",
+      "## Goal",
+      "",
+      "Just some documentation updates, no tasks.",
+    ].join("\n");
+    writeFileSync(planPath, planContent);
+
+    const result = verifyExpectedArtifact("plan-slice", "M001/S01", base);
+    assert.equal(result, false, "should fail when plan has no task entries (empty scaffold, #699)");
+  } finally {
+    cleanup(base);
+  }
+});