oh-my-opencode 4.3.1 → 4.5.0

package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/outputs/code-changes.md

@@ -0,0 +1,334 @@
+# Code Changes: Fix Atlas Hook Crash on Missing worktree_path
+
+## Change 1: Harden `readBoulderState()` validation
+
+**File:** `src/features/boulder-state/storage.ts`
+
+### Before (lines 16-36):
+```typescript
+export function readBoulderState(directory: string): BoulderState | null {
+  const filePath = getBoulderFilePath(directory)
+
+  if (!existsSync(filePath)) {
+    return null
+  }
+
+  try {
+    const content = readFileSync(filePath, "utf-8")
+    const parsed = JSON.parse(content)
+    if (!parsed || typeof parsed !== "object" || Array.isArray(parsed)) {
+      return null
+    }
+    if (!Array.isArray(parsed.session_ids)) {
+      parsed.session_ids = []
+    }
+    return parsed as BoulderState
+  } catch {
+    return null
+  }
+}
+```
+
+### After:
+```typescript
+export function readBoulderState(directory: string): BoulderState | null {
+  const filePath = getBoulderFilePath(directory)
+
+  if (!existsSync(filePath)) {
+    return null
+  }
+
+  try {
+    const content = readFileSync(filePath, "utf-8")
+    const parsed = JSON.parse(content)
+    if (!parsed || typeof parsed !== "object" || Array.isArray(parsed)) {
+      return null
+    }
+    if (typeof parsed.active_plan !== "string" || typeof parsed.plan_name !== "string") {
+      return null
+    }
+    if (!Array.isArray(parsed.session_ids)) {
+      parsed.session_ids = []
+    }
+    if (parsed.worktree_path !== undefined && typeof parsed.worktree_path !== "string") {
+      delete parsed.worktree_path
+    }
+    return parsed as BoulderState
+  } catch {
+    return null
+  }
+}
+```
+
+**Rationale:** Validates that required fields (`active_plan`, `plan_name`) are strings. Strips `worktree_path` if it's present but not a string (e.g., `null`, number). This prevents downstream crashes from `existsSync(undefined)` and ensures type safety at the boundary.
+
+---
+
+## Change 2: Add try/catch in setTimeout retry callback
+
+**File:** `src/hooks/atlas/idle-event.ts`
+
+### Before (lines 62-88):
+```typescript
+sessionState.pendingRetryTimer = setTimeout(async () => {
+    sessionState.pendingRetryTimer = undefined
+
+    if (sessionState.promptFailureCount >= 2) return
+    if (sessionState.waitingForFinalWaveApproval) return
+
+    const currentBoulder = readBoulderState(ctx.directory)
+    if (!currentBoulder) return
+    if (!currentBoulder.session_ids?.includes(sessionID)) return
+
+    const currentProgress = getPlanProgress(currentBoulder.active_plan)
+    if (currentProgress.isComplete) return
+    if (options?.isContinuationStopped?.(sessionID)) return
+    if (options?.shouldSkipContinuation?.(sessionID)) return
+    if (hasRunningBackgroundTasks(sessionID, options)) return
+
+    await injectContinuation({
+      ctx,
+      sessionID,
+      sessionState,
+      options,
+      planName: currentBoulder.plan_name,
+      progress: currentProgress,
+      agent: currentBoulder.agent,
+      worktreePath: currentBoulder.worktree_path,
+    })
+  }, RETRY_DELAY_MS)
+```
+
+### After:
+```typescript
+sessionState.pendingRetryTimer = setTimeout(async () => {
+    sessionState.pendingRetryTimer = undefined
+
+    try {
+      if (sessionState.promptFailureCount >= 2) return
+      if (sessionState.waitingForFinalWaveApproval) return
+
+      const currentBoulder = readBoulderState(ctx.directory)
+      if (!currentBoulder) return
+      if (!currentBoulder.session_ids?.includes(sessionID)) return
+
+      const currentProgress = getPlanProgress(currentBoulder.active_plan)
+      if (currentProgress.isComplete) return
+      if (options?.isContinuationStopped?.(sessionID)) return
+      if (options?.shouldSkipContinuation?.(sessionID)) return
+      if (hasRunningBackgroundTasks(sessionID, options)) return
+
+      await injectContinuation({
+        ctx,
+        sessionID,
+        sessionState,
+        options,
+        planName: currentBoulder.plan_name,
+        progress: currentProgress,
+        agent: currentBoulder.agent,
+        worktreePath: currentBoulder.worktree_path,
+      })
+    } catch (error) {
+      log(`[${HOOK_NAME}] Retry continuation failed`, { sessionID, error: String(error) })
+    }
+  }, RETRY_DELAY_MS)
+```
+
+**Rationale:** The async callback in setTimeout creates a floating promise. Without try/catch, any error becomes an unhandled rejection that can crash the process. This is the critical safety net even after the `readBoulderState` fix.
+
+---
+
+## Change 3: Defensive guard in `getPlanProgress`
+
+**File:** `src/features/boulder-state/storage.ts`
+
+### Before (lines 115-118):
+```typescript
+export function getPlanProgress(planPath: string): PlanProgress {
+  if (!existsSync(planPath)) {
+    return { total: 0, completed: 0, isComplete: true }
+  }
+```
+
+### After:
+```typescript
+export function getPlanProgress(planPath: string): PlanProgress {
+  if (typeof planPath !== "string" || !existsSync(planPath)) {
+    return { total: 0, completed: 0, isComplete: true }
+  }
+```
+
+**Rationale:** Defense-in-depth. Even though `readBoulderState` now validates `active_plan`, the `getPlanProgress` function is a public API that could be called from other paths with invalid input. A `typeof` check before `existsSync` prevents the TypeError from `existsSync(undefined)`.
+
+---
+
+## Change 4: New tests
+
+### File: `src/features/boulder-state/storage.test.ts` (additions)
+
+```typescript
+test("should return null when active_plan is missing", () => {
+  // given - boulder.json without active_plan
+  const boulderFile = join(SISYPHUS_DIR, "boulder.json")
+  writeFileSync(boulderFile, JSON.stringify({
+    started_at: "2026-01-01T00:00:00Z",
+    session_ids: ["ses-1"],
+    plan_name: "plan",
+  }))
+
+  // when
+  const result = readBoulderState(TEST_DIR)
+
+  // then
+  expect(result).toBeNull()
+})
+
+test("should return null when plan_name is missing", () => {
+  // given - boulder.json without plan_name
+  const boulderFile = join(SISYPHUS_DIR, "boulder.json")
+  writeFileSync(boulderFile, JSON.stringify({
+    active_plan: "/path/to/plan.md",
+    started_at: "2026-01-01T00:00:00Z",
+    session_ids: ["ses-1"],
+  }))
+
+  // when
+  const result = readBoulderState(TEST_DIR)
+
+  // then
+  expect(result).toBeNull()
+})
+
+test("should strip non-string worktree_path from boulder state", () => {
+  // given - boulder.json with worktree_path set to null
+  const boulderFile = join(SISYPHUS_DIR, "boulder.json")
+  writeFileSync(boulderFile, JSON.stringify({
+    active_plan: "/path/to/plan.md",
+    started_at: "2026-01-01T00:00:00Z",
+    session_ids: ["ses-1"],
+    plan_name: "plan",
+    worktree_path: null,
+  }))
+
+  // when
+  const result = readBoulderState(TEST_DIR)
+
+  // then
+  expect(result).not.toBeNull()
+  expect(result!.worktree_path).toBeUndefined()
+})
+
+test("should preserve valid worktree_path string", () => {
+  // given - boulder.json with valid worktree_path
+  const boulderFile = join(SISYPHUS_DIR, "boulder.json")
+  writeFileSync(boulderFile, JSON.stringify({
+    active_plan: "/path/to/plan.md",
+    started_at: "2026-01-01T00:00:00Z",
+    session_ids: ["ses-1"],
+    plan_name: "plan",
+    worktree_path: "/valid/worktree/path",
+  }))
+
+  // when
+  const result = readBoulderState(TEST_DIR)
+
+  // then
+  expect(result).not.toBeNull()
+  expect(result!.worktree_path).toBe("/valid/worktree/path")
+})
+```
+
+### File: `src/features/boulder-state/storage.test.ts` (getPlanProgress additions)
+
+```typescript
+test("should handle undefined planPath without crashing", () => {
+  // given - undefined as planPath (from malformed boulder state)
+
+  // when
+  const progress = getPlanProgress(undefined as unknown as string)
+
+  // then
+  expect(progress.total).toBe(0)
+  expect(progress.isComplete).toBe(true)
+})
+```
+
+### File: `src/hooks/atlas/index.test.ts` (additions to session.idle section)
+
+```typescript
+test("should handle boulder state without worktree_path gracefully", async () => {
+  // given - boulder state with incomplete plan, no worktree_path
+  const planPath = join(TEST_DIR, "test-plan.md")
+  writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [x] Task 2")
+
+  const state: BoulderState = {
+    active_plan: planPath,
+    started_at: "2026-01-02T10:00:00Z",
+    session_ids: [MAIN_SESSION_ID],
+    plan_name: "test-plan",
+    // worktree_path intentionally omitted
+  }
+  writeBoulderState(TEST_DIR, state)
+
+  const mockInput = createMockPluginInput()
+  const hook = createAtlasHook(mockInput)
+
+  // when
+  await hook.handler({
+    event: {
+      type: "session.idle",
+      properties: { sessionID: MAIN_SESSION_ID },
+    },
+  })
+
+  // then - should call prompt without crashing, continuation should not contain worktree context
+  expect(mockInput._promptMock).toHaveBeenCalled()
+  const callArgs = mockInput._promptMock.mock.calls[0][0]
+  expect(callArgs.body.parts[0].text).toContain("incomplete tasks")
+  expect(callArgs.body.parts[0].text).not.toContain("[Worktree:")
+})
+
+test("should include worktree context when worktree_path is present in boulder state", async () => {
+  // given - boulder state with worktree_path
+  const planPath = join(TEST_DIR, "test-plan.md")
+  writeFileSync(planPath, "# Plan\n- [ ] Task 1")
+
+  const state: BoulderState = {
+    active_plan: planPath,
+    started_at: "2026-01-02T10:00:00Z",
+    session_ids: [MAIN_SESSION_ID],
+    plan_name: "test-plan",
+    worktree_path: "/some/worktree/path",
+  }
+  writeBoulderState(TEST_DIR, state)
+
+  const mockInput = createMockPluginInput()
+  const hook = createAtlasHook(mockInput)
+
+  // when
+  await hook.handler({
+    event: {
+      type: "session.idle",
+      properties: { sessionID: MAIN_SESSION_ID },
+    },
+  })
+
+  // then - should include worktree context in continuation prompt
+  expect(mockInput._promptMock).toHaveBeenCalled()
+  const callArgs = mockInput._promptMock.mock.calls[0][0]
+  expect(callArgs.body.parts[0].text).toContain("[Worktree: /some/worktree/path]")
+})
+```
+
+---
+
+## Summary of Changes
+
+| File | Change | Lines Modified |
+|------|--------|---------------|
+| `src/features/boulder-state/storage.ts` | Validate required fields + sanitize worktree_path + guard getPlanProgress | ~8 lines added |
+| `src/hooks/atlas/idle-event.ts` | try/catch around setTimeout async callback | ~4 lines added |
+| `src/features/boulder-state/storage.test.ts` | 5 new tests for validation | ~60 lines added |
+| `src/hooks/atlas/index.test.ts` | 2 new tests for worktree_path handling | ~50 lines added |
+
+Total: ~4 production lines changed, ~8 defensive lines added, ~110 test lines added.

package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/outputs/execution-plan.md

@@ -0,0 +1,86 @@
+# Execution Plan: Fix Atlas Hook Crash on Missing worktree_path
+
+## Bug Analysis
+
+### Root Cause
+
+`readBoulderState()` in `src/features/boulder-state/storage.ts` performs minimal validation when parsing `boulder.json`:
+
+```typescript
+const parsed = JSON.parse(content)
+if (!parsed || typeof parsed !== "object" || Array.isArray(parsed)) return null
+if (!Array.isArray(parsed.session_ids)) parsed.session_ids = []
+return parsed as BoulderState  // <-- unsafe cast, no field validation
+```
+
+It validates `session_ids` but NOT `active_plan`, `plan_name`, or `worktree_path`. This means a malformed `boulder.json` (e.g., `{}` or missing key fields) passes through and downstream code crashes.
+
+### Crash Path
+
+1. `boulder.json` is written without required fields (manual edit, corruption, partial write)
+2. `readBoulderState()` returns it as `BoulderState` with `active_plan: undefined`
+3. Multiple call sites pass `boulderState.active_plan` to `getPlanProgress(planPath: string)`:
+   - `src/hooks/atlas/idle-event.ts:72` (inside `setTimeout` callback - unhandled rejection!)
+   - `src/hooks/atlas/resolve-active-boulder-session.ts:21`
+   - `src/hooks/atlas/tool-execute-after.ts:74`
+4. `getPlanProgress()` calls `existsSync(undefined)` which throws: `TypeError: The "path" argument must be of type string`
+
+### worktree_path-Specific Issues
+
+When `worktree_path` field is missing from `boulder.json`:
+- The `idle-event.ts` `scheduleRetry` setTimeout callback (lines 62-88) has NO try/catch. An unhandled promise rejection from the async callback crashes the process.
+- `readBoulderState()` returns `worktree_path: undefined` which itself is handled in `boulder-continuation-injector.ts` (line 42 uses truthiness check), but the surrounding code in the setTimeout lacks error protection.
+
+### Secondary Issue: Unhandled Promise in setTimeout
+
+In `idle-event.ts` lines 62-88:
+```typescript
+sessionState.pendingRetryTimer = setTimeout(async () => {
+  // ... no try/catch wrapper
+  const currentBoulder = readBoulderState(ctx.directory)
+  const currentProgress = getPlanProgress(currentBoulder.active_plan)  // CRASH if active_plan undefined
+  // ...
+}, RETRY_DELAY_MS)
+```
+
+The async callback creates a floating promise. Any thrown error becomes an unhandled rejection.
+
+---
+
+## Step-by-Step Plan
+
+### Step 1: Harden `readBoulderState()` validation
+**File:** `src/features/boulder-state/storage.ts`
+
+- After the `session_ids` fix, add validation for `active_plan` and `plan_name` (required fields)
+- Validate `worktree_path` is either `undefined` or a string (not `null`, not a number)
+- Return `null` for boulder states with missing required fields
+
+### Step 2: Add try/catch in setTimeout callback
+**File:** `src/hooks/atlas/idle-event.ts`
+
+- Wrap the `setTimeout` async callback body in try/catch
+- Log errors with the atlas hook logger
+
+### Step 3: Add defensive guard in `getPlanProgress`
+**File:** `src/features/boulder-state/storage.ts`
+
+- Add early return for non-string `planPath` argument
+
+### Step 4: Add tests
+**Files:**
+- `src/features/boulder-state/storage.test.ts` - test missing/malformed fields
+- `src/hooks/atlas/index.test.ts` - test atlas hook with boulder missing worktree_path
+
+### Step 5: Run CI checks
+```bash
+bun run typecheck
+bun test src/features/boulder-state/storage.test.ts
+bun test src/hooks/atlas/index.test.ts
+bun test  # full suite
+```
+
+### Step 6: Create PR
+- Branch: `fix/atlas-hook-missing-worktree-path`
+- Target: `dev`
+- Run CI and verify passes

package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/outputs/pr-description.md

@@ -0,0 +1,23 @@
+## Summary
+
+- Fix crash in atlas hook when `boulder.json` is missing `worktree_path` (or other required fields) by hardening `readBoulderState()` validation
+- Wrap the unprotected `setTimeout` retry callback in `idle-event.ts` with try/catch to prevent unhandled promise rejections
+- Add defensive type guard in `getPlanProgress()` to prevent `existsSync(undefined)` TypeError
+
+## Context
+
+When `boulder.json` is malformed or manually edited to omit fields, `readBoulderState()` returns an object cast as `BoulderState` without validating required fields. Downstream callers like `getPlanProgress(boulderState.active_plan)` then pass `undefined` to `existsSync()`, which throws a TypeError. This crash is especially dangerous in the `setTimeout` retry callback in `idle-event.ts`, where the error becomes an unhandled promise rejection.
+
+## Changes
+
+### `src/features/boulder-state/storage.ts`
+- `readBoulderState()`: Validate `active_plan` and `plan_name` are strings (return `null` if not)
+- `readBoulderState()`: Strip `worktree_path` if present but not a string type
+- `getPlanProgress()`: Add `typeof planPath !== "string"` guard before `existsSync`
+
+### `src/hooks/atlas/idle-event.ts`
+- Wrap `scheduleRetry` setTimeout async callback body in try/catch
+
+### Tests
+- `src/features/boulder-state/storage.test.ts`: 5 new tests for missing/malformed fields
+- `src/hooks/atlas/index.test.ts`: 2 new tests for worktree_path presence/absence in continuation prompt

package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/outputs/verification-strategy.md

@@ -0,0 +1,119 @@
+# Verification Strategy
+
+## 1. Unit Tests (Direct Verification)
+
+### boulder-state storage tests
+```bash
+bun test src/features/boulder-state/storage.test.ts
+```
+
+Verify:
+- `readBoulderState()` returns `null` when `active_plan` missing
+- `readBoulderState()` returns `null` when `plan_name` missing
+- `readBoulderState()` strips non-string `worktree_path` (e.g., `null`)
+- `readBoulderState()` preserves valid string `worktree_path`
+- `getPlanProgress(undefined)` returns safe default without crashing
+- Existing tests still pass (session_ids defaults, empty object, etc.)
+
+### atlas hook tests
+```bash
+bun test src/hooks/atlas/index.test.ts
+```
+
+Verify:
+- session.idle handler works with boulder state missing `worktree_path` (no crash, prompt injected)
+- session.idle handler includes `[Worktree: ...]` context when `worktree_path` IS present
+- All 30+ existing tests still pass
+
+### atlas idle-event lineage tests
+```bash
+bun test src/hooks/atlas/idle-event-lineage.test.ts
+```
+
+Verify existing lineage tests unaffected.
+
+### start-work hook tests
+```bash
+bun test src/hooks/start-work/index.test.ts
+```
+
+Verify worktree-related start-work tests still pass (these create boulder states with/without `worktree_path`).
+
+## 2. Type Safety
+
+```bash
+bun run typecheck
+```
+
+Verify zero new TypeScript errors. The changes are purely additive runtime guards that align with existing types (`worktree_path?: string`).
+
+## 3. LSP Diagnostics on Changed Files
+
+```
+lsp_diagnostics on:
+  - src/features/boulder-state/storage.ts
+  - src/hooks/atlas/idle-event.ts
+```
+
+Verify zero errors/warnings.
+
+## 4. Full Test Suite
+
+```bash
+bun test
+```
+
+Verify no regressions across the entire codebase.
+
+## 5. Build
+
+```bash
+bun run build
+```
+
+Verify build succeeds.
+
+## 6. Manual Smoke Test (Reproduction)
+
+To manually verify the fix:
+
+```bash
+# Create a malformed boulder.json (missing worktree_path)
+mkdir -p .sisyphus
+echo '{"active_plan": ".sisyphus/plans/test.md", "plan_name": "test", "session_ids": ["ses-1"]}' > .sisyphus/boulder.json
+
+# Create a plan file
+mkdir -p .sisyphus/plans
+echo '# Plan\n- [ ] Task 1' > .sisyphus/plans/test.md
+
+# Start opencode - atlas hook should NOT crash when session.idle fires
+# Verify /tmp/oh-my-opencode.log shows normal continuation behavior
+```
+
+Also test the extreme case:
+```bash
+# boulder.json with no required fields
+echo '{}' > .sisyphus/boulder.json
+
+# After fix: readBoulderState returns null, atlas hook gracefully skips
+```
+
+## 7. CI Pipeline
+
+After pushing the branch, verify:
+- `ci.yml` workflow passes: tests (split: mock-heavy isolated + batch), typecheck, build
+- No new lint warnings
+
+## 8. Edge Cases Covered
+
+| Scenario | Expected Behavior |
+|----------|-------------------|
+| `boulder.json` = `{}` | `readBoulderState` returns `null` |
+| `boulder.json` missing `active_plan` | `readBoulderState` returns `null` |
+| `boulder.json` missing `plan_name` | `readBoulderState` returns `null` |
+| `boulder.json` has `worktree_path: null` | Field stripped, returned as `undefined` |
+| `boulder.json` has `worktree_path: 42` | Field stripped, returned as `undefined` |
+| `boulder.json` has no `worktree_path` | Works normally, no crash |
+| `boulder.json` has valid `worktree_path` | Preserved, included in continuation prompt |
+| setTimeout retry with corrupted boulder.json | Error caught and logged, no process crash |
+| `getPlanProgress(undefined)` | Returns `{ total: 0, completed: 0, isComplete: true }` |

package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/timing.json

@@ -0,0 +1 @@
+{"total_tokens": null, "duration_ms": 325000, "total_duration_seconds": 325}

package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/eval_metadata.json

@@ -0,0 +1,32 @@
+{
+  "eval_id": 3,
+  "eval_name": "refactor-split-constants",
+  "prompt": "Refactor src/tools/delegate-task/constants.ts to split DEFAULT_CATEGORIES and CATEGORY_MODEL_REQUIREMENTS into separate files. Keep backward compatibility with the barrel export. Make a PR.",
+  "assertions": [
+    {
+      "id": "worktree-isolation",
+      "text": "Plan uses git worktree in a sibling directory",
+      "type": "manual"
+    },
+    {
+      "id": "multiple-atomic-commits",
+      "text": "Uses 2+ commits for the multi-file refactor",
+      "type": "manual"
+    },
+    {
+      "id": "barrel-export",
+      "text": "Maintains backward compatibility via barrel re-export in constants.ts or index.ts",
+      "type": "manual"
+    },
+    {
+      "id": "three-gates",
+      "text": "Verification loop includes all 3 gates",
+      "type": "manual"
+    },
+    {
+      "id": "real-constants-file",
+      "text": "References actual src/tools/delegate-task/constants.ts file and its exports",
+      "type": "manual"
+    }
+  ]
+}

package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/grading.json

@@ -0,0 +1,10 @@
+{
+  "run_id": "eval-3-with_skill",
+  "expectations": [
+    {"text": "Plan uses git worktree in a sibling directory", "passed": true, "evidence": "../omo-wt/refactor-delegate-task-constants"},
+    {"text": "Uses 2+ commits for the multi-file refactor", "passed": true, "evidence": "Commit 1: category defaults+appends, Commit 2: plan agent prompt+names"},
+    {"text": "Maintains backward compatibility via barrel re-export", "passed": true, "evidence": "constants.ts converted to re-export from 4 new files, full import map verified"},
+    {"text": "Verification loop includes all 3 gates", "passed": true, "evidence": "Gate A (CI), Gate B (review-work), Gate C (Cubic)"},
+    {"text": "References actual src/tools/delegate-task/constants.ts", "passed": true, "evidence": "654 lines analyzed, 4 responsibilities identified, full external+internal import map"}
+  ]
+}