release: v3.1.11

- Remove non-functional batch tool handling (OpenCode has no batch tool)
- Keep working direct tool call path (read/write/edit/multiedit)
- Apply same cleanup to directory-agents-injector and directory-readme-injector
- Add .sisyphus/rules directory support

.github/workflows/publish.yml

@@ -51,7 +51,6 @@ jobs:
           # Run them in separate processes to prevent cross-file contamination
           bun test src/plugin-handlers
           bun test src/hooks/atlas
-          bun test src/hooks/compaction-context-injector
           bun test src/features/tmux-subagent
 
       - name: Run remaining tests

.gitignore

@@ -33,4 +33,4 @@ yarn.lock
 test-injection/
 notepad.md
 oauth-success.html
-.188e87dbff6e7fd9-00000000.bun-build
+*.bun-build

.opencode/command/get-unpublished-changes.md

@@ -1,6 +1,5 @@
 ---
 description: Compare HEAD with the latest published npm version and list all unpublished changes
-model: anthropic/claude-haiku-4-5
 ---
 
 <command-instruction>
@@ -82,3 +81,68 @@ None 또는 목록
 - **Recommendation**: patch|minor|major
 - **Reason**: 이유
 </output-format>
+
+<oracle-safety-review>
+## Oracle 배포 안전성 검토 (사용자가 명시적으로 요청 시에만)
+
+**트리거 키워드**: "배포 가능", "배포해도 될까", "안전한지", "리뷰", "검토", "oracle", "오라클"
+
+사용자가 위 키워드 중 하나라도 포함하여 요청하면:
+
+### 1. 사전 검증 실행
+```bash
+bun run typecheck
+bun test
+```
+- 실패 시 → Oracle 소환 없이 즉시 "❌ 배포 불가" 보고
+
+### 2. Oracle 소환 프롬프트
+
+다음 정보를 수집하여 Oracle에게 전달:
+
+```
+## 배포 안전성 검토 요청
+
+### 변경사항 요약
+{위에서 분석한 변경사항 테이블}
+
+### 주요 diff (기능별로 정리)
+{각 feat/fix/refactor의 핵심 코드 변경 - 전체 diff가 아닌 핵심만}
+
+### 검증 결과
+- Typecheck: ✅/❌
+- Tests: {pass}/{total} (✅/❌)
+
+### 검토 요청사항
+1. **리그레션 위험**: 기존 기능에 영향을 줄 수 있는 변경이 있는가?
+2. **사이드이펙트**: 예상치 못한 부작용이 발생할 수 있는 부분은?
+3. **Breaking Changes**: 외부 사용자에게 영향을 주는 변경이 있는가?
+4. **Edge Cases**: 놓친 엣지 케이스가 있는가?
+5. **배포 권장 여부**: SAFE / CAUTION / UNSAFE
+
+### 요청
+위 변경사항을 깊이 분석하고, 배포 안전성에 대해 판단해주세요.
+리스크가 있다면 구체적인 시나리오와 함께 설명해주세요.
+배포 후 모니터링해야 할 키워드가 있다면 제안해주세요.
+```
+
+### 3. Oracle 응답 후 출력 포맷
+
+## 🔍 Oracle 배포 안전성 검토 결과
+
+### 판정: ✅ SAFE / ⚠️ CAUTION / ❌ UNSAFE
+
+### 리스크 분석
+| 영역 | 리스크 레벨 | 설명 |
+|------|-------------|------|
+| ... | 🟢/🟡/🔴 | ... |
+
+### 권장 사항
+- ...
+
+### 배포 후 모니터링 키워드
+- ...
+
+### 결론
+{Oracle의 최종 판단}
+</oracle-safety-review>

.opencode/skills/github-issue-triage/SKILL.md

@@ -0,0 +1,519 @@
+---
+name: github-issue-triage
+description: "Triage GitHub issues with parallel analysis. 1 issue = 1 background agent. Exhaustive pagination. Analyzes: question vs bug, project validity, resolution status, community engagement, linked PRs. Triggers: 'triage issues', 'analyze issues', 'issue report'."
+---
+
+# GitHub Issue Triage Specialist
+
+You are a GitHub issue triage automation agent. Your job is to:
+1. Fetch **EVERY SINGLE ISSUE** within a specified time range using **EXHAUSTIVE PAGINATION**
+2. Launch ONE background agent PER issue for parallel analysis
+3. Collect results and generate a comprehensive triage report
+
+---
+
+# CRITICAL: EXHAUSTIVE PAGINATION IS MANDATORY
+
+**THIS IS THE MOST IMPORTANT RULE. VIOLATION = COMPLETE FAILURE.**
+
+## YOU MUST FETCH ALL ISSUES. PERIOD.
+
+| WRONG | CORRECT |
+|----------|------------|
+| `gh issue list --limit 100` and stop | Paginate until ZERO results returned |
+| "I found 16 issues" (first page only) | "I found 61 issues after 5 pages" |
+| Assuming first page is enough | Using `--limit 500` and verifying count |
+| Stopping when you "feel" you have enough | Stopping ONLY when API returns empty |
+
+### WHY THIS MATTERS
+
+- GitHub API returns **max 100 issues per request** by default
+- A busy repo can have **50-100+ issues** in 48 hours
+- **MISSING ISSUES = MISSING CRITICAL BUGS = PRODUCTION OUTAGES**
+- The user asked for triage, not "sample triage"
+
+### THE ONLY ACCEPTABLE APPROACH
+
+```bash
+# ALWAYS use --limit 500 (maximum allowed)
+# ALWAYS check if more pages exist
+# ALWAYS continue until empty result
+
+gh issue list --repo $REPO --state all --limit 500 --json number,title,state,createdAt,updatedAt,labels,author
+```
+
+**If the result count equals your limit, THERE ARE MORE ISSUES. KEEP FETCHING.**
+
+---
+
+## PHASE 1: Issue Collection (EXHAUSTIVE Pagination)
+
+### 1.1 Determine Repository and Time Range
+
+Extract from user request:
+- `REPO`: Repository in `owner/repo` format (default: current repo via `gh repo view --json nameWithOwner -q .nameWithOwner`)
+- `TIME_RANGE`: Hours to look back (default: 48)
+
+---
+
+## AGENT CATEGORY RATIO RULES
+
+**Philosophy**: Use the cheapest agent that can do the job. Expensive agents = waste unless necessary.
+
+### Default Ratio: `unspecified-low:8, quick:1, writing:1`
+
+| Category | Ratio | Use For | Cost |
+|----------|-------|---------|------|
+| `unspecified-low` | 80% | Standard issue analysis - read issue, fetch comments, categorize | $ |
+| `quick` | 10% | Trivial issues - obvious duplicates, spam, clearly resolved | ¢ |
+| `writing` | 10% | Report generation, response drafting, summary synthesis | $$ |
+
+### When to Override Default Ratio
+
+| Scenario | Recommended Ratio | Reason |
+|----------|-------------------|--------|
+| Bug-heavy triage | `unspecified-low:7, quick:2, writing:1` | More simple duplicates |
+| Feature request triage | `unspecified-low:6, writing:3, quick:1` | More response drafting needed |
+| Security audit | `unspecified-high:5, unspecified-low:4, writing:1` | Deeper analysis required |
+| First-pass quick filter | `quick:8, unspecified-low:2` | Just categorize, don't analyze deeply |
+
+### Agent Assignment Algorithm
+
+```typescript
+function assignAgentCategory(issues: Issue[], ratio: Record<string, number>): Map<Issue, string> {
+  const assignments = new Map<Issue, string>();
+  const total = Object.values(ratio).reduce((a, b) => a + b, 0);
+  
+  // Calculate counts for each category
+  const counts: Record<string, number> = {};
+  for (const [category, weight] of Object.entries(ratio)) {
+    counts[category] = Math.floor(issues.length * (weight / total));
+  }
+  
+  // Assign remaining to largest category
+  const assigned = Object.values(counts).reduce((a, b) => a + b, 0);
+  const remaining = issues.length - assigned;
+  const largestCategory = Object.entries(ratio).sort((a, b) => b[1] - a[1])[0][0];
+  counts[largestCategory] += remaining;
+  
+  // Distribute issues
+  let issueIndex = 0;
+  for (const [category, count] of Object.entries(counts)) {
+    for (let i = 0; i < count && issueIndex < issues.length; i++) {
+      assignments.set(issues[issueIndex++], category);
+    }
+  }
+  
+  return assignments;
+}
+```
+
+### Category Selection Heuristics
+
+**Before launching agents, pre-classify issues for smarter category assignment:**
+
+| Issue Signal | Assign To | Reason |
+|--------------|-----------|--------|
+| Has `duplicate` label | `quick` | Just confirm and close |
+| Has `wontfix` label | `quick` | Just confirm and close |
+| No comments, < 50 char body | `quick` | Likely spam or incomplete |
+| Has linked PR | `quick` | Already being addressed |
+| Has `bug` label + long body | `unspecified-low` | Needs proper analysis |
+| Has `feature` label | `unspecified-low` or `writing` | May need response |
+| User is maintainer | `quick` | They know what they're doing |
+| 5+ comments | `unspecified-low` | Complex discussion |
+| Needs response drafted | `writing` | Prose quality matters |
+
+---
+
+### 1.2 Exhaustive Pagination Loop
+
+# STOP. READ THIS BEFORE EXECUTING.
+
+**YOU WILL FETCH EVERY. SINGLE. ISSUE. NO EXCEPTIONS.**
+
+## THE GOLDEN RULE
+
+```
+NEVER use --limit 100. ALWAYS use --limit 500.
+NEVER stop at first result. ALWAYS verify you got everything.
+NEVER assume "that's probably all". ALWAYS check if more exist.
+```
+
+## MANDATORY PAGINATION LOOP (COPY-PASTE THIS EXACTLY)
+
+You MUST execute this EXACT pagination loop. DO NOT simplify. DO NOT skip iterations.
+
+```bash
+#!/bin/bash
+# MANDATORY PAGINATION - Execute this EXACTLY as written
+
+REPO="code-yeongyu/oh-my-opencode"  # or use: gh repo view --json nameWithOwner -q .nameWithOwner
+TIME_RANGE=48  # hours
+CUTOFF_DATE=$(date -v-${TIME_RANGE}H +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || date -d "${TIME_RANGE} hours ago" -Iseconds)
+
+echo "=== EXHAUSTIVE PAGINATION START ==="
+echo "Repository: $REPO"
+echo "Cutoff date: $CUTOFF_DATE"
+echo ""
+
+# STEP 1: First fetch with --limit 500
+echo "[Page 1] Fetching issues..."
+FIRST_FETCH=$(gh issue list --repo $REPO --state all --limit 500 --json number,title,state,createdAt,updatedAt,labels,author)
+FIRST_COUNT=$(echo "$FIRST_FETCH" | jq 'length')
+echo "[Page 1] Raw count: $FIRST_COUNT"
+
+# STEP 2: Filter by time range
+ALL_ISSUES=$(echo "$FIRST_FETCH" | jq --arg cutoff "$CUTOFF_DATE" \
+  '[.[] | select(.createdAt >= $cutoff or .updatedAt >= $cutoff)]')
+FILTERED_COUNT=$(echo "$ALL_ISSUES" | jq 'length')
+echo "[Page 1] After time filter: $FILTERED_COUNT issues"
+
+# STEP 3: CHECK IF MORE PAGES NEEDED
+# If we got exactly 500, there are MORE issues!
+if [ "$FIRST_COUNT" -eq 500 ]; then
+  echo ""
+  echo "WARNING: Got exactly 500 results. MORE PAGES EXIST!"
+  echo "Continuing pagination..."
+  
+  PAGE=2
+  LAST_ISSUE_NUMBER=$(echo "$FIRST_FETCH" | jq '.[- 1].number')
+  
+  # Keep fetching until we get less than 500
+  while true; do
+    echo ""
+    echo "[Page $PAGE] Fetching more issues..."
+    
+    # Use search API with pagination for more results
+    NEXT_FETCH=$(gh issue list --repo $REPO --state all --limit 500 \
+      --json number,title,state,createdAt,updatedAt,labels,author \
+      --search "created:<$(echo "$FIRST_FETCH" | jq -r '.[-1].createdAt')")
+    
+    NEXT_COUNT=$(echo "$NEXT_FETCH" | jq 'length')
+    echo "[Page $PAGE] Raw count: $NEXT_COUNT"
+    
+    if [ "$NEXT_COUNT" -eq 0 ]; then
+      echo "[Page $PAGE] No more results. Pagination complete."
+      break
+    fi
+    
+    # Filter and merge
+    NEXT_FILTERED=$(echo "$NEXT_FETCH" | jq --arg cutoff "$CUTOFF_DATE" \
+      '[.[] | select(.createdAt >= $cutoff or .updatedAt >= $cutoff)]')
+    ALL_ISSUES=$(echo "$ALL_ISSUES $NEXT_FILTERED" | jq -s 'add | unique_by(.number)')
+    
+    CURRENT_TOTAL=$(echo "$ALL_ISSUES" | jq 'length')
+    echo "[Page $PAGE] Running total: $CURRENT_TOTAL issues"
+    
+    if [ "$NEXT_COUNT" -lt 500 ]; then
+      echo "[Page $PAGE] Less than 500 results. Pagination complete."
+      break
+    fi
+    
+    PAGE=$((PAGE + 1))
+    
+    # Safety limit
+    if [ $PAGE -gt 20 ]; then
+      echo "SAFETY LIMIT: Stopped at page 20"
+      break
+    fi
+  done
+fi
+
+# STEP 4: FINAL COUNT
+FINAL_COUNT=$(echo "$ALL_ISSUES" | jq 'length')
+echo ""
+echo "=== EXHAUSTIVE PAGINATION COMPLETE ==="
+echo "Total issues found: $FINAL_COUNT"
+echo ""
+
+# STEP 5: Verify we got everything
+if [ "$FINAL_COUNT" -lt 10 ]; then
+  echo "WARNING: Only $FINAL_COUNT issues found. Double-check time range!"
+fi
+```
+
+## VERIFICATION CHECKLIST (MANDATORY)
+
+BEFORE proceeding to Phase 2, you MUST verify:
+
+```
+CHECKLIST:
+[ ] Executed the FULL pagination loop above (not just --limit 500 once)
+[ ] Saw "EXHAUSTIVE PAGINATION COMPLETE" in output
+[ ] Counted total issues: _____ (fill this in)
+[ ] If first fetch returned 500, continued to page 2+
+[ ] Used --state all (not just open)
+```
+
+**If you did NOT see "EXHAUSTIVE PAGINATION COMPLETE", you did it WRONG. Start over.**
+
+## ANTI-PATTERNS (WILL CAUSE FAILURE)
+
+| NEVER DO THIS | Why It Fails |
+|------------------|--------------|
+| Single `gh issue list --limit 500` | If 500 returned, you missed the rest! |
+| `--limit 100` | Misses 80%+ of issues in active repos |
+| Stopping at first fetch | GitHub paginates - you got 1 page of N |
+| Not counting results | Can't verify completeness |
+| Filtering only by createdAt | Misses updated issues |
+| Assuming small repos have few issues | Even small repos can have bursts |
+
+**THE LOOP MUST RUN UNTIL:**
+1. Fetch returns 0 results, OR
+2. Fetch returns less than 500 results
+
+**IF FIRST FETCH RETURNS EXACTLY 500 = YOU MUST CONTINUE FETCHING.**
+
+### 1.3 Also Fetch All PRs (For Bug Correlation)
+
+```bash
+# Same pagination logic for PRs
+gh pr list --repo $REPO --state all --limit 500 --json number,title,state,createdAt,updatedAt,labels,author,body,headRefName | \
+  jq --arg cutoff "$CUTOFF_DATE" '[.[] | select(.createdAt >= $cutoff or .updatedAt >= $cutoff)]'
+```
+
+---
+
+## PHASE 2: Parallel Issue Analysis (1 Issue = 1 Agent)
+
+### 2.1 Agent Distribution Formula
+
+```
+Total issues: N
+Agent categories based on ratio:
+- unspecified-low: floor(N * 0.8)
+- quick: floor(N * 0.1)  
+- writing: ceil(N * 0.1)  # For report generation
+```
+
+### 2.2 Launch Background Agents
+
+**MANDATORY: Each issue gets its own dedicated background agent.**
+
+For each issue, launch:
+
+```typescript
+delegate_task(
+  category="unspecified-low",  // or quick/writing per ratio
+  load_skills=[],
+  run_in_background=true,
+  prompt=`
+## TASK
+Analyze GitHub issue #${issue.number} for ${REPO}.
+
+## ISSUE DATA
+- Number: #${issue.number}
+- Title: ${issue.title}
+- State: ${issue.state}
+- Author: ${issue.author.login}
+- Created: ${issue.createdAt}
+- Updated: ${issue.updatedAt}
+- Labels: ${issue.labels.map(l => l.name).join(', ')}
+
+## ISSUE BODY
+${issue.body}
+
+## FETCH COMMENTS
+Use: gh issue view ${issue.number} --repo ${REPO} --json comments
+
+## ANALYSIS CHECKLIST
+1. **TYPE**: Is this a BUG, QUESTION, FEATURE request, or INVALID?
+2. **PROJECT_VALID**: Is this issue relevant to OUR project? (YES/NO/UNCLEAR)
+3. **STATUS**: 
+   - RESOLVED: Already fixed (check for linked PRs, owner comments)
+   - NEEDS_ACTION: Requires maintainer attention
+   - CAN_CLOSE: Can be closed (duplicate, out of scope, stale, answered)
+   - NEEDS_INFO: Missing reproduction steps or details
+4. **COMMUNITY_RESPONSE**: 
+   - NONE: No comments
+   - HELPFUL: Useful workarounds or info provided
+   - WAITING: Awaiting user response
+5. **LINKED_PR**: If bug, search PRs that might fix this issue
+
+## PR CORRELATION
+Check these PRs for potential fixes:
+${PR_LIST}
+
+## RETURN FORMAT
+\`\`\`
+#${issue.number}: ${issue.title}
+TYPE: [BUG|QUESTION|FEATURE|INVALID]
+VALID: [YES|NO|UNCLEAR]
+STATUS: [RESOLVED|NEEDS_ACTION|CAN_CLOSE|NEEDS_INFO]
+COMMUNITY: [NONE|HELPFUL|WAITING]
+LINKED_PR: [#NUMBER or NONE]
+SUMMARY: [1-2 sentence summary]
+ACTION: [Recommended maintainer action]
+DRAFT_RESPONSE: [If auto-answerable, provide English draft. Otherwise "NEEDS_MANUAL_REVIEW"]
+\`\`\`
+`
+)
+```
+
+### 2.3 Collect All Results
+
+Wait for all background agents to complete, then collect:
+
+```typescript
+// Store all task IDs
+const taskIds: string[] = []
+
+// Launch all agents
+for (const issue of issues) {
+  const result = await delegate_task(...)
+  taskIds.push(result.task_id)
+}
+
+// Collect results
+const results = []
+for (const taskId of taskIds) {
+  const output = await background_output(task_id=taskId)
+  results.push(output)
+}
+```
+
+---
+
+## PHASE 3: Report Generation
+
+### 3.1 Categorize Results
+
+Group analyzed issues by status:
+
+| Category | Criteria |
+|----------|----------|
+| **CRITICAL** | Blocking bugs, security issues, data loss |
+| **CLOSE_IMMEDIATELY** | Resolved, duplicate, out of scope, stale |
+| **AUTO_RESPOND** | Can answer with template (version update, docs link) |
+| **NEEDS_INVESTIGATION** | Requires manual debugging or design decision |
+| **FEATURE_BACKLOG** | Feature requests for prioritization |
+| **NEEDS_INFO** | Missing details, request more info |
+
+### 3.2 Generate Report
+
+```markdown
+# Issue Triage Report
+
+**Repository:** ${REPO}
+**Time Range:** Last ${TIME_RANGE} hours
+**Generated:** ${new Date().toISOString()}
+**Total Issues Analyzed:** ${issues.length}
+
+## Summary
+
+| Category | Count |
+|----------|-------|
+| CRITICAL | N |
+| Close Immediately | N |
+| Auto-Respond | N |
+| Needs Investigation | N |
+| Feature Requests | N |
+| Needs Info | N |
+
+---
+
+## 1. CRITICAL (Immediate Action Required)
+
+[List issues with full details]
+
+## 2. Close Immediately
+
+[List with closing reason and template response]
+
+## 3. Auto-Respond (Template Answers)
+
+[List with draft responses ready to post]
+
+## 4. Needs Investigation
+
+[List with investigation notes]
+
+## 5. Feature Backlog
+
+[List for prioritization]
+
+## 6. Needs More Info
+
+[List with template questions to ask]
+
+---
+
+## Response Templates
+
+### Fixed in Version X
+\`\`\`
+This issue was resolved in vX.Y.Z via PR #NNN.
+Please update: \`bunx oh-my-opencode@X.Y.Z install\`
+If the issue persists, please reopen with \`opencode --print-logs\` output.
+\`\`\`
+
+### Needs More Info
+\`\`\`
+Thank you for reporting. To investigate, please provide:
+1. \`opencode --print-logs\` output
+2. Your configuration file
+3. Minimal reproduction steps
+Labeling as \`needs-info\`. Auto-closes in 7 days without response.
+\`\`\`
+
+### Out of Scope
+\`\`\`
+Thank you for reaching out. This request falls outside the scope of this project.
+[Suggest alternative or explanation]
+\`\`\`
+```
+
+---
+
+## ANTI-PATTERNS (BLOCKING VIOLATIONS)
+
+## IF YOU DO ANY OF THESE, THE TRIAGE IS INVALID
+
+| Violation | Why It's Wrong | Severity |
+|-----------|----------------|----------|
+| **Using `--limit 100`** | Misses 80%+ of issues in active repos | CRITICAL |
+| **Stopping at first fetch** | GitHub paginates - you only got page 1 | CRITICAL |
+| **Not counting results** | Can't verify completeness | CRITICAL |
+| Batching issues (7 per agent) | Loses detail, harder to track | HIGH |
+| Sequential agent calls | Slow, doesn't leverage parallelism | HIGH |
+| Skipping PR correlation | Misses linked fixes for bugs | MEDIUM |
+| Generic responses | Each issue needs specific analysis | MEDIUM |
+
+## MANDATORY VERIFICATION BEFORE PHASE 2
+
+```
+CHECKLIST:
+[ ] Used --limit 500 (not 100)
+[ ] Used --state all (not just open)  
+[ ] Counted issues: _____ total
+[ ] Verified: if count < 500, all issues fetched
+[ ] If count = 500, fetched additional pages
+```
+
+**DO NOT PROCEED TO PHASE 2 UNTIL ALL BOXES ARE CHECKED.**
+
+---
+
+## EXECUTION CHECKLIST
+
+- [ ] Fetched ALL pages of issues (pagination complete)
+- [ ] Fetched ALL pages of PRs for correlation
+- [ ] Launched 1 agent per issue (not batched)
+- [ ] All agents ran in background (parallel)
+- [ ] Collected all results before generating report
+- [ ] Report includes draft responses where applicable
+- [ ] Critical issues flagged at top
+
+---
+
+## Quick Start
+
+When invoked, immediately:
+
+1. `gh repo view --json nameWithOwner -q .nameWithOwner` (get current repo)
+2. Parse user's time range request (default: 48 hours)
+3. Exhaustive pagination for issues AND PRs
+4. Launch N background agents (1 per issue)
+5. Collect all results
+6. Generate categorized report with action items

assets/oh-my-opencode.schema.json

@@ -80,7 +80,8 @@
           "prometheus-md-only",
           "sisyphus-junior-notepad",
           "start-work",
-          "atlas"
+          "atlas",
+          "stop-continuation-guard"
         ]
       }
     },

bun.lock

@@ -1,6 +1,6 @@
 {
   "lockfileVersion": 1,
-  "configVersion": 0,
+  "configVersion": 1,
   "workspaces": {
     "": {
       "name": "oh-my-opencode",
@@ -28,13 +28,13 @@
         "typescript": "^5.7.3",
       },
       "optionalDependencies": {
-        "oh-my-opencode-darwin-arm64": "3.1.6",
-        "oh-my-opencode-darwin-x64": "3.1.6",
-        "oh-my-opencode-linux-arm64": "3.1.6",
-        "oh-my-opencode-linux-arm64-musl": "3.1.6",
-        "oh-my-opencode-linux-x64": "3.1.6",
-        "oh-my-opencode-linux-x64-musl": "3.1.6",
-        "oh-my-opencode-windows-x64": "3.1.6",
+        "oh-my-opencode-darwin-arm64": "3.1.10",
+        "oh-my-opencode-darwin-x64": "3.1.10",
+        "oh-my-opencode-linux-arm64": "3.1.10",
+        "oh-my-opencode-linux-arm64-musl": "3.1.10",
+        "oh-my-opencode-linux-x64": "3.1.10",
+        "oh-my-opencode-linux-x64-musl": "3.1.10",
+        "oh-my-opencode-windows-x64": "3.1.10",
       },
     },
   },
@@ -44,41 +44,41 @@
     "@code-yeongyu/comment-checker",
   ],
   "packages": {
-    "@ast-grep/cli": ["@ast-grep/cli@0.40.0", "", { "dependencies": { "detect-libc": "2.1.2" }, "optionalDependencies": { "@ast-grep/cli-darwin-arm64": "0.40.0", "@ast-grep/cli-darwin-x64": "0.40.0", "@ast-grep/cli-linux-arm64-gnu": "0.40.0", "@ast-grep/cli-linux-x64-gnu": "0.40.0", "@ast-grep/cli-win32-arm64-msvc": "0.40.0", "@ast-grep/cli-win32-ia32-msvc": "0.40.0", "@ast-grep/cli-win32-x64-msvc": "0.40.0" }, "bin": { "sg": "sg", "ast-grep": "ast-grep" } }, "sha512-L8AkflsfI2ZP70yIdrwqvjR02ScCuRmM/qNGnJWUkOFck+e6gafNVJ4e4jjGQlEul+dNdBpx36+O2Op629t47A=="],
+    "@ast-grep/cli": ["@ast-grep/cli@0.40.5", "", { "dependencies": { "detect-libc": "2.1.2" }, "optionalDependencies": { "@ast-grep/cli-darwin-arm64": "0.40.5", "@ast-grep/cli-darwin-x64": "0.40.5", "@ast-grep/cli-linux-arm64-gnu": "0.40.5", "@ast-grep/cli-linux-x64-gnu": "0.40.5", "@ast-grep/cli-win32-arm64-msvc": "0.40.5", "@ast-grep/cli-win32-ia32-msvc": "0.40.5", "@ast-grep/cli-win32-x64-msvc": "0.40.5" }, "bin": { "sg": "sg", "ast-grep": "ast-grep" } }, "sha512-yVXL7Gz0WIHerQLf+MVaVSkhIhidtWReG5akNVr/JS9OVCVkSdz7gWm7H8jVv2M9OO1tauuG76K3UaRGBPu5lQ=="],
 
-    "@ast-grep/cli-darwin-arm64": ["@ast-grep/cli-darwin-arm64@0.40.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-UehY2MMUkdJbsriP7NKc6+uojrqPn7d1Cl0em+WAkee7Eij81VdyIjRsRxtZSLh440ZWQBHI3PALZ9RkOO8pKQ=="],
+    "@ast-grep/cli-darwin-arm64": ["@ast-grep/cli-darwin-arm64@0.40.5", "", { "os": "darwin", "cpu": "arm64" }, "sha512-T9CzwJ1GqQhnANdsu6c7iT1akpvTVMK+AZrxnhIPv33Ze5hrXUUkqan+j4wUAukRJDqU7u94EhXLSLD+5tcJ8g=="],
 
-    "@ast-grep/cli-darwin-x64": ["@ast-grep/cli-darwin-x64@0.40.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-RFDJ2ZxUbT0+grntNlOLJx7wa9/ciVCeaVtQpQy8WJJTvXvkY0etl8Qlh2TmO2x2yr+i0Z6aMJi4IG/Yx5ghTQ=="],
+    "@ast-grep/cli-darwin-x64": ["@ast-grep/cli-darwin-x64@0.40.5", "", { "os": "darwin", "cpu": "x64" }, "sha512-ez9b2zKvXU8f4ghhjlqYvbx6tWCKJTuVlNVqDDfjqwwhGeiTYfnzMlSVat4ElYRMd21gLtXZIMy055v2f21Ztg=="],
 
-    "@ast-grep/cli-linux-arm64-gnu": ["@ast-grep/cli-linux-arm64-gnu@0.40.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-4p55gnTQ1mMFCyqjtM7bH9SB9r16mkwXtUcJQGX1YgFG4WD+QG8rC4GwSuNNZcdlYaOQuTWrgUEQ9z5K06UXfg=="],
+    "@ast-grep/cli-linux-arm64-gnu": ["@ast-grep/cli-linux-arm64-gnu@0.40.5", "", { "os": "linux", "cpu": "arm64" }, "sha512-VXa2L1IEYD66AMb0GuG7VlMMbPmEGoJUySWDcwSZo/D9neiry3MJ41LQR5oTG2HyhIPBsf9umrXnmuRq66BviA=="],
 
-    "@ast-grep/cli-linux-x64-gnu": ["@ast-grep/cli-linux-x64-gnu@0.40.0", "", { "os": "linux", "cpu": "x64" }, "sha512-u2MXFceuwvrO+OQ6zFGoJ6wbATXn46HWwW79j4UPrXYJzVl97jRyjJOIQTJOzTflsk02fjP98DQkfvbXt2dl3Q=="],
+    "@ast-grep/cli-linux-x64-gnu": ["@ast-grep/cli-linux-x64-gnu@0.40.5", "", { "os": "linux", "cpu": "x64" }, "sha512-GQC5162eIOWXR2eQQ6Knzg7/8Trp5E1ODJkaErf0IubdQrZBGqj5AAcQPcWgPbbnmktjIp0H4NraPpOJ9eJ22A=="],
 
-    "@ast-grep/cli-win32-arm64-msvc": ["@ast-grep/cli-win32-arm64-msvc@0.40.0", "", { "os": "win32", "cpu": "arm64" }, "sha512-E/I1xpF/RQL2fo1CQsQfTxyDLnChsbZ+ERrQHKuF1FI4WrkaPOBibpqda60QgVmUcgOGZyZ/GRb3iKEVWPsQNQ=="],
+    "@ast-grep/cli-win32-arm64-msvc": ["@ast-grep/cli-win32-arm64-msvc@0.40.5", "", { "os": "win32", "cpu": "arm64" }, "sha512-YiZdnQZsSlXQTMsZJop/Ux9MmUGfuRvC2x/UbFgrt5OBSYxND+yoiMc0WcA3WG+wU+tt4ZkB5HUea3r/IkOLYA=="],
 
-    "@ast-grep/cli-win32-ia32-msvc": ["@ast-grep/cli-win32-ia32-msvc@0.40.0", "", { "os": "win32", "cpu": "ia32" }, "sha512-9h12OQu1BR0GxHEtT+Z4QkJk3LLWLiKwjBkjXUGlASHYDPTyLcs85KwDLeFHs4BwarF8TDdF+KySvB9WPGl/nQ=="],
+    "@ast-grep/cli-win32-ia32-msvc": ["@ast-grep/cli-win32-ia32-msvc@0.40.5", "", { "os": "win32", "cpu": "ia32" }, "sha512-MHkCxCITVTr8sY9CcVqNKbfUzMa3Hc6IilGXad0Clnw2vNmPfWqSky+hU/UTerr5YHWwWfAVURH7ANZgirtx0Q=="],
 
-    "@ast-grep/cli-win32-x64-msvc": ["@ast-grep/cli-win32-x64-msvc@0.40.0", "", { "os": "win32", "cpu": "x64" }, "sha512-n2+3WynEWFHhXg6KDgjwWQ0UEtIvqUITFbKEk5cDkUYrzYhg/A6kj0qauPwRbVMoJms49vtsNpLkzzqyunio5g=="],
+    "@ast-grep/cli-win32-x64-msvc": ["@ast-grep/cli-win32-x64-msvc@0.40.5", "", { "os": "win32", "cpu": "x64" }, "sha512-/MJ5un7yxlClaaxou9eYl+Kr2xr/yTtYtTq5aLBWjPWA6dmmJ1nAJgx5zKHVuplFXFBrFDQk3paEgAETMTGcrA=="],
 
-    "@ast-grep/napi": ["@ast-grep/napi@0.40.0", "", { "optionalDependencies": { "@ast-grep/napi-darwin-arm64": "0.40.0", "@ast-grep/napi-darwin-x64": "0.40.0", "@ast-grep/napi-linux-arm64-gnu": "0.40.0", "@ast-grep/napi-linux-arm64-musl": "0.40.0", "@ast-grep/napi-linux-x64-gnu": "0.40.0", "@ast-grep/napi-linux-x64-musl": "0.40.0", "@ast-grep/napi-win32-arm64-msvc": "0.40.0", "@ast-grep/napi-win32-ia32-msvc": "0.40.0", "@ast-grep/napi-win32-x64-msvc": "0.40.0" } }, "sha512-tq6nO/8KwUF/mHuk1ECaAOSOlz2OB/PmygnvprJzyAHGRVzdcffblaOOWe90M9sGz5MAasXoF+PTcayQj9TKKA=="],
+    "@ast-grep/napi": ["@ast-grep/napi@0.40.5", "", { "optionalDependencies": { "@ast-grep/napi-darwin-arm64": "0.40.5", "@ast-grep/napi-darwin-x64": "0.40.5", "@ast-grep/napi-linux-arm64-gnu": "0.40.5", "@ast-grep/napi-linux-arm64-musl": "0.40.5", "@ast-grep/napi-linux-x64-gnu": "0.40.5", "@ast-grep/napi-linux-x64-musl": "0.40.5", "@ast-grep/napi-win32-arm64-msvc": "0.40.5", "@ast-grep/napi-win32-ia32-msvc": "0.40.5", "@ast-grep/napi-win32-x64-msvc": "0.40.5" } }, "sha512-hJA62OeBKUQT68DD2gDyhOqJxZxycqg8wLxbqjgqSzYttCMSDL9tiAQ9abgekBYNHudbJosm9sWOEbmCDfpX2A=="],
 
-    "@ast-grep/napi-darwin-arm64": ["@ast-grep/napi-darwin-arm64@0.40.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-ZMjl5yLhKjxdwbqEEdMizgQdWH2NrWsM6Px+JuGErgCDe6Aedq9yurEPV7veybGdLVJQhOah6htlSflXxjHnYA=="],
+    "@ast-grep/napi-darwin-arm64": ["@ast-grep/napi-darwin-arm64@0.40.5", "", { "os": "darwin", "cpu": "arm64" }, "sha512-2F072fGN0WTq7KI3okuEnkGJVEHLbi56Bw1H6NAMf7j2mJJeQWsRyGOMcyNnUXZDeNdvoMH0OB2a5wwUegY/nQ=="],
 
-    "@ast-grep/napi-darwin-x64": ["@ast-grep/napi-darwin-x64@0.40.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-f9Ol5oQKNRMBkvDtzBK1WiNn2/3eejF2Pn9xwTj7PhXuSFseedOspPYllxQo0gbwUlw/DJqGFTce/jarhR/rBw=="],
+    "@ast-grep/napi-darwin-x64": ["@ast-grep/napi-darwin-x64@0.40.5", "", { "os": "darwin", "cpu": "x64" }, "sha512-dJMidHZhhxuLBYNi6/FKI812jQ7wcFPSKkVPwviez2D+KvYagapUMAV/4dJ7FCORfguVk8Y0jpPAlYmWRT5nvA=="],
 
-    "@ast-grep/napi-linux-arm64-gnu": ["@ast-grep/napi-linux-arm64-gnu@0.40.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-+tO+VW5GDhT9jGkKOK+3b8+ohKjC98WTzn7wSskd/myyhK3oYL1WTKqCm07WSYBZOJvb3z+WaX+wOUrc4bvtyQ=="],
+    "@ast-grep/napi-linux-arm64-gnu": ["@ast-grep/napi-linux-arm64-gnu@0.40.5", "", { "os": "linux", "cpu": "arm64" }, "sha512-nBRCbyoS87uqkaw4Oyfe5VO+SRm2B+0g0T8ME69Qry9ShMf41a2bTdpcQx9e8scZPogq+CTwDHo3THyBV71l9w=="],
 
-    "@ast-grep/napi-linux-arm64-musl": ["@ast-grep/napi-linux-arm64-musl@0.40.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-MS9qalLRjUnF2PCzuTKTvCMVSORYHxxe3Qa0+SSaVULsXRBmuy5C/b1FeWwMFnwNnC0uie3VDet31Zujwi8q6A=="],
+    "@ast-grep/napi-linux-arm64-musl": ["@ast-grep/napi-linux-arm64-musl@0.40.5", "", { "os": "linux", "cpu": "arm64" }, "sha512-/qKsmds5FMoaEj6FdNzepbmLMtlFuBLdrAn9GIWCqOIcVcYvM1Nka8+mncfeXB/MFZKOrzQsQdPTWqrrQzXLrA=="],
 
-    "@ast-grep/napi-linux-x64-gnu": ["@ast-grep/napi-linux-x64-gnu@0.40.0", "", { "os": "linux", "cpu": "x64" }, "sha512-BeHZVMNXhM3WV3XE2yghO0fRxhMOt8BTN972p5piYEQUvKeSHmS8oeGcs6Ahgx5znBclqqqq37ZfioYANiTqJA=="],
+    "@ast-grep/napi-linux-x64-gnu": ["@ast-grep/napi-linux-x64-gnu@0.40.5", "", { "os": "linux", "cpu": "x64" }, "sha512-DP4oDbq7f/1A2hRTFLhJfDFR6aI5mRWdEfKfHzRItmlKsR9WlcEl1qDJs/zX9R2EEtIDsSKRzuJNfJllY3/W8Q=="],
 
-    "@ast-grep/napi-linux-x64-musl": ["@ast-grep/napi-linux-x64-musl@0.40.0", "", { "os": "linux", "cpu": "x64" }, "sha512-rG1YujF7O+lszX8fd5u6qkFTuv4FwHXjWvt1CCvCxXwQLSY96LaCW88oVKg7WoEYQh54y++Fk57F+Wh9Gv9nVQ=="],
+    "@ast-grep/napi-linux-x64-musl": ["@ast-grep/napi-linux-x64-musl@0.40.5", "", { "os": "linux", "cpu": "x64" }, "sha512-BRZUvVBPUNpWPo6Ns8chXVzxHPY+k9gpsubGTHy92Q26ecZULd/dTkWWdnvfhRqttsSQ9Pe/XQdi5+hDQ6RYcg=="],
 
-    "@ast-grep/napi-win32-arm64-msvc": ["@ast-grep/napi-win32-arm64-msvc@0.40.0", "", { "os": "win32", "cpu": "arm64" }, "sha512-9SqmnQqd4zTEUk6yx0TuW2ycZZs2+e569O/R0QnhSiQNpgwiJCYOe/yPS0BC9HkiaozQm6jjAcasWpFtz/dp+w=="],
+    "@ast-grep/napi-win32-arm64-msvc": ["@ast-grep/napi-win32-arm64-msvc@0.40.5", "", { "os": "win32", "cpu": "arm64" }, "sha512-y95zSEwc7vhxmcrcH0GnK4ZHEBQrmrszRBNQovzaciF9GUqEcCACNLoBesn4V47IaOp4fYgD2/EhGRTIBFb2Ug=="],
 
-    "@ast-grep/napi-win32-ia32-msvc": ["@ast-grep/napi-win32-ia32-msvc@0.40.0", "", { "os": "win32", "cpu": "ia32" }, "sha512-0JkdBZi5l9vZhGEO38A1way0LmLRDU5Vos6MXrLIOVkymmzDTDlCdY394J1LMmmsfwWcyJg6J7Yv2dw41MCxDQ=="],
+    "@ast-grep/napi-win32-ia32-msvc": ["@ast-grep/napi-win32-ia32-msvc@0.40.5", "", { "os": "win32", "cpu": "ia32" }, "sha512-K/u8De62iUnFCzVUs7FBdTZ2Jrgc5/DLHqjpup66KxZ7GIM9/HGME/O8aSoPkpcAeCD4TiTZ11C1i5p5H98hTg=="],
 
-    "@ast-grep/napi-win32-x64-msvc": ["@ast-grep/napi-win32-x64-msvc@0.40.0", "", { "os": "win32", "cpu": "x64" }, "sha512-Hk2IwfPqMFGZt5SRxsoWmGLxBXxprow4LRp1eG6V8EEiJCNHxZ9ZiEaIc5bNvMDBjHVSnqZAXT22dROhrcSKQg=="],
+    "@ast-grep/napi-win32-x64-msvc": ["@ast-grep/napi-win32-x64-msvc@0.40.5", "", { "os": "win32", "cpu": "x64" }, "sha512-dqm5zg/o4Nh4VOQPEpMS23ot8HVd22gG0eg01t4CFcZeuzyuSgBlOL3N7xLbz3iH2sVkk7keuBwAzOIpTqziNQ=="],
 
     "@clack/core": ["@clack/core@0.5.0", "", { "dependencies": { "picocolors": "^1.0.0", "sisteransi": "^1.0.5" } }, "sha512-p3y0FIOwaYRUPRcMO7+dlmLh8PSRcrjuTndsiA0WAFbWES0mLZlrjVoBRZ9DzkPFJZG6KGkJmoEAY0ZcVWTkow=="],
 
@@ -86,17 +86,17 @@
 
     "@code-yeongyu/comment-checker": ["@code-yeongyu/comment-checker@0.6.1", "", { "os": [ "linux", "win32", "darwin", ], "cpu": [ "x64", "arm64", ], "bin": { "comment-checker": "bin/comment-checker" } }, "sha512-BBremX+Y5aW8sTzlhHrLsKParupYkPOVUYmq9STrlWvBvfAme6w5IWuZCLl6nHIQScRDdvGdrAjPycJC86EZFA=="],
 
-    "@hono/node-server": ["@hono/node-server@1.19.7", "", { "peerDependencies": { "hono": "^4" } }, "sha512-vUcD0uauS7EU2caukW8z5lJKtoGMokxNbJtBiwHgpqxEXokaHCBkQUmCHhjFB1VUTWdqj25QoMkMKzgjq+uhrw=="],
+    "@hono/node-server": ["@hono/node-server@1.19.9", "", { "peerDependencies": { "hono": "^4" } }, "sha512-vHL6w3ecZsky+8P5MD+eFfaGTyCeOHUIFYMGpQGbrBTSmNNoxv0if69rEZ5giu36weC5saFuznL411gRX7bJDw=="],
 
-    "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.25.1", "", { "dependencies": { "@hono/node-server": "^1.19.7", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.0.1", "express-rate-limit": "^7.5.0", "jose": "^6.1.1", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.0" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-yO28oVFFC7EBoiKdAn+VqRm+plcfv4v0xp6osG/VsCB0NlPZWi87ajbCZZ8f/RvOFLEu7//rSRmuZZ7lMoe3gQ=="],
+    "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.25.3", "", { "dependencies": { "@hono/node-server": "^1.19.9", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.0.1", "express-rate-limit": "^7.5.0", "jose": "^6.1.1", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.0" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-vsAMBMERybvYgKbg/l4L1rhS7VXV1c0CtyJg72vwxONVX0l4ZfKVAnZEWTQixJGTzKnELjQ59e4NbdFDALRiAQ=="],
 
-    "@opencode-ai/plugin": ["@opencode-ai/plugin@1.1.19", "", { "dependencies": { "@opencode-ai/sdk": "1.1.19", "zod": "4.1.8" } }, "sha512-Q6qBEjHb/dJMEw4BUqQxEswTMxCCHUpFMMb6jR8HTTs8X/28XRkKt5pHNPA82GU65IlSoPRph+zd8LReBDN53Q=="],
+    "@opencode-ai/plugin": ["@opencode-ai/plugin@1.1.47", "", { "dependencies": { "@opencode-ai/sdk": "1.1.47", "zod": "4.1.8" } }, "sha512-gNMPz72altieDfLhUw3VAT1xbduKi3w3wZ57GLeS7qU9W474HdvdIiLBnt2Xq3U7Ko0/0tvK3nzCker6IIDqmQ=="],
 
-    "@opencode-ai/sdk": ["@opencode-ai/sdk@1.1.19", "", {}, "sha512-XhZhFuvlLCqDpvNtUEjOsi/wvFj3YCXb1dySp+OONQRMuHlorNYnNa7P2A2ntKuhRdGT1Xt5na0nFzlUyNw+4A=="],
+    "@opencode-ai/sdk": ["@opencode-ai/sdk@1.1.47", "", {}, "sha512-s3PBHwk1sP6Zt/lJxIWSBWZ1TnrI1nFxSP97LCODUytouAQgbygZ1oDH7O2sGMBEuGdA8B1nNSPla0aRSN3IpA=="],
 
     "@types/js-yaml": ["@types/js-yaml@4.0.9", "", {}, "sha512-k4MGaQl5TGo/iipqb2UDG2UwjXziSWkh0uysQelTlJpX1qGlpUZYm8PnO4DxG1qBomtJUdYJ6qR6xdIah10JLg=="],
 
-    "@types/node": ["@types/node@24.10.1", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-GNWcUTRBgIRJD5zj+Tq0fKOJ5XZajIiBroOF0yvj2bSU1WvNdYS/dn9UxwsujGW4JX06dnHyjV2y9rRaybH0iQ=="],
+    "@types/node": ["@types/node@25.1.0", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-t7frlewr6+cbx+9Ohpl0NOTKXZNV9xHRmNOvql47BFJKcEG1CxtxlPEEe+gR9uhVWM4DwhnvTF110mIL4yP9RA=="],
 
     "@types/picomatch": ["@types/picomatch@3.0.2", "", {}, "sha512-n0i8TD3UDB7paoMMxA3Y65vUncFJXjcUf7lQY7YyKGl6031FNjfsLs6pdLFCy2GNFxItPJG8GvvpbZc2skH7WA=="],
 
@@ -108,9 +108,9 @@
 
     "argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],
 
-    "body-parser": ["body-parser@2.2.1", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^1.0.5", "debug": "^4.4.3", "http-errors": "^2.0.0", "iconv-lite": "^0.7.0", "on-finished": "^2.4.1", "qs": "^6.14.0", "raw-body": "^3.0.1", "type-is": "^2.0.1" } }, "sha512-nfDwkulwiZYQIGwxdy0RUmowMhKcFVcYXUU7m4QlKYim1rUtg83xm2yjZ40QjDuc291AJjjeSc9b++AWHSgSHw=="],
+    "body-parser": ["body-parser@2.2.2", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^1.0.5", "debug": "^4.4.3", "http-errors": "^2.0.0", "iconv-lite": "^0.7.0", "on-finished": "^2.4.1", "qs": "^6.14.1", "raw-body": "^3.0.1", "type-is": "^2.0.1" } }, "sha512-oP5VkATKlNwcgvxi0vM0p/D3n2C3EReYVX+DNYs5TjZFn/oQt2j+4sVJtSMr18pdRr8wjTcBl6LoV+FUwzPmNA=="],
 
-    "bun-types": ["bun-types@1.3.3", "", { "dependencies": { "@types/node": "*" } }, "sha512-z3Xwlg7j2l9JY27x5Qn3Wlyos8YAp0kKRlrePAOjgjMGS5IG6E7Jnlx736vH9UVI4wUICwwhC9anYL++XeOgTQ=="],
+    "bun-types": ["bun-types@1.3.8", "", { "dependencies": { "@types/node": "*" } }, "sha512-fL99nxdOWvV4LqjmC+8Q9kW3M4QTtTR1eePs94v5ctGqU8OeceWrSUaRw3JYb7tU3FkMIAjkueehrHPPPGKi5Q=="],
 
     "bytes": ["bytes@3.1.2", "", {}, "sha512-/Nf7TyzTx6S3yRJObOAV7956r8cr2+Oj8AC5dt8wSP3BQAoeX58NoHyCU8P8zGkNXStjTSi6fzO6F0pBdcYbEg=="],
 
@@ -118,7 +118,7 @@
 
     "call-bound": ["call-bound@1.0.4", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.2", "get-intrinsic": "^1.3.0" } }, "sha512-+ys997U96po4Kx/ABpBCqhA9EuxJaQWDQg7295H4hBphv3IZg0boBKuwYpt4YXp6MZ5AmZQnU/tyMTlRpaSejg=="],
 
-    "commander": ["commander@14.0.2", "", {}, "sha512-TywoWNNRbhoD0BXs1P3ZEScW8W5iKrnbithIl0YH+uCmBd0QpPOA8yc82DS3BIE5Ma6FnBVUsJ7wVUDz4dvOWQ=="],
+    "commander": ["commander@14.0.3", "", {}, "sha512-H+y0Jo/T1RZ9qPP4Eh1pkcQcLRglraJaSLoyOtHxu6AapkjWVCy2Sit1QQ4x3Dng8qDlSsZEet7g5Pq06MvTgw=="],
 
     "content-disposition": ["content-disposition@1.0.1", "", {}, "sha512-oIXISMynqSqm241k6kcQ5UwttDILMK4BiurCfGEREw6+X9jkkpEe5T9FZaApyLGGOnFuyMWZpdolTXMtvEJ08Q=="],
 
@@ -128,7 +128,7 @@
 
     "cookie-signature": ["cookie-signature@1.2.2", "", {}, "sha512-D76uU73ulSXrD1UXF4KE2TMxVVwhsnCgfAyTg9k8P6KGZjlXKrOLe4dJQKI3Bxi5wjesZoFXJWElNWBjPZMbhg=="],
 
-    "cors": ["cors@2.8.5", "", { "dependencies": { "object-assign": "^4", "vary": "^1" } }, "sha512-KIHbLJqu73RGr/hnbrO9uBeixNGuvSQjul/jdFvS/KFSIH1hWVd1ng7zOHx+YrEfInLG7q4n6GHQ9cDtxv/P6g=="],
+    "cors": ["cors@2.8.6", "", { "dependencies": { "object-assign": "^4", "vary": "^1" } }, "sha512-tJtZBBHA6vjIAaF6EnIaq6laBBP9aq/Y3ouVJjEfoHbRBcHBAHYcMh/w8LDrk2PvIMMq8gmopa5D4V8RmbrxGw=="],
 
     "cross-spawn": ["cross-spawn@7.0.6", "", { "dependencies": { "path-key": "^3.1.0", "shebang-command": "^2.0.0", "which": "^2.0.1" } }, "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA=="],
 
@@ -184,11 +184,11 @@
 
     "hasown": ["hasown@2.0.2", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ=="],
 
-    "hono": ["hono@4.10.8", "", {}, "sha512-DDT0A0r6wzhe8zCGoYOmMeuGu3dyTAE40HHjwUsWFTEy5WxK1x2WDSsBPlEXgPbRIFY6miDualuUDbasPogIww=="],
+    "hono": ["hono@4.11.7", "", {}, "sha512-l7qMiNee7t82bH3SeyUCt9UF15EVmaBvsppY2zQtrbIhl/yzBTny+YUxsVjSjQ6gaqaeVtZmGocom8TzBlA4Yw=="],
 
     "http-errors": ["http-errors@2.0.1", "", { "dependencies": { "depd": "~2.0.0", "inherits": "~2.0.4", "setprototypeof": "~1.2.0", "statuses": "~2.0.2", "toidentifier": "~1.0.1" } }, "sha512-4FbRdAX+bSdmo4AUFuS0WNiPz8NgFt+r8ThgNWmlrjQjt1Q7ZR9+zTlce2859x4KSXrwIsaeTqDoKQmtP8pLmQ=="],
 
-    "iconv-lite": ["iconv-lite@0.7.1", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-2Tth85cXwGFHfvRgZWszZSvdo+0Xsqmw8k8ZwxScfcBneNUraK+dxRxRm24nszx80Y0TVio8kKLt5sLE7ZCLlw=="],
+    "iconv-lite": ["iconv-lite@0.7.2", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-im9DjEDQ55s9fL4EYzOAv0yMqmMBSZp6G0VvFyTMPKWxiSBHUj9NW/qqLmXUwXrrM7AvqSlTCfvqRb0cM8yYqw=="],
 
     "inherits": ["inherits@2.0.4", "", {}, "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="],
 
@@ -226,19 +226,19 @@
 
     "object-inspect": ["object-inspect@1.13.4", "", {}, "sha512-W67iLl4J2EXEGTbfeHCffrjDfitvLANg0UlX3wFUUSTx92KXRFegMHUVgSqE+wvhAbi4WqjGg9czysTV2Epbew=="],
 
-    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.1.6", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-KK+ptnkBigvDYbRtF/B5izEC4IoXDS8mAnRHWFBSCINhzQR2No6AtEcwijd6vKBPR+/r71ofq/8mTsIeb1PEVQ=="],
+    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.1.10", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-6qsZQtrtBYZLufcXTTuUUMEG9PoG9Y98pX+HFVn2xHIEc6GpwR6i5xY8McFHmqPkC388tzybD556JhKqPX7Pnw=="],
 
-    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.1.6", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-UkPI/RUi7INarFasBUZ4Rous6RUQXsU2nr0V8KFJp+70END43D/96dDUwX+zmPtpDhD+DfWkejuwzqfkZJ2ZDQ=="],
+    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.1.10", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-I1tQQbcpSBvLGXTO652mBqlyIpwYhYuIlSJmrSM33YRGBiaUuhMASnHQsms+E0eC3U/TOyqomU/4KPnbWyxs4w=="],
 
-    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.1.6", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-gvmvgh7WtTtcHiCbG7z43DOYfY/jrf2S6TX/jBMX2/e1AGkcLKwz30NjGhZxeK5SyzxRVypgfZZK1IuriRgbdA=="],
+    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.1.10", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-r6Rm5Ru/WwcBKKuPIP0RreI0gnf+MYRV0mmzPBVhMZdPWSC/eTT3GdyqFDZ4cCN76n5aea0sa5PPW7iPF+Uw6Q=="],
 
-    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.1.6", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-j3R76pmQ4HGVGFJUMMCeF/1lO3Jg7xFdpcBUKCeFh42N1jMgn1aeyxkAaJYB9RwCF/p6+P8B6gVDLCEDu2mxjA=="],
+    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.1.10", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-UVo5OWO92DPIFhoEkw0tj8IcZyUKOG6NlFs1+tSExz7qrgkr0IloxpLslGMmdc895xxpljrr/FobYktLxyJbcg=="],
 
-    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.1.6", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-VDdo0tHCOr5nm7ajd652u798nPNOLRSTcPOnVh6vIPddkZ+ujRke+enOKOw9Pd5e+4AkthqHBwFXNm2VFgnEKg=="],
+    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.1.10", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-3g99z2FweMzHSUYuzgU0E2H0kjVmtOhPZdavwVqcHQtLQ9NNhwfnIvj3yFBif+kGJphP9RDnByC1oA8Q26UrCg=="],
 
-    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.1.6", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-hBG/dhsr8PZelUlYsPBruSLnelB9ocB7H92I+S9svTpDVo67rAmXOoR04twKQ9TeCO4ShOa6hhMhbQnuI8fgNw=="],
+    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.1.10", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-2HS9Ju0Cr433lMFJtu/7bShApOJywp+zmVCduQUBWFi3xbX1nm5sJwWDhw1Wx+VcqHEuJl/SQzWPE4vaqkEQng=="],
 
-    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.1.6", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-c8Awp03p2DsbS0G589nzveRCeJPgJRJ0vQrha4ChRmmo31Qc5OSmJ5xuMaF8L4nM+/trbTgAQMFMtCMLgtC8IQ=="],
+    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.1.10", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-QLncZJSlWmmcuXrAVKIH6a9Om1Ym6pkhG4hAxaD5K5aF1jw2QFsadjoT12VNq2WzQb+Pg5Y6IWvoow0ZR0aEvw=="],
 
     "on-finished": ["on-finished@2.4.1", "", { "dependencies": { "ee-first": "1.1.1" } }, "sha512-oVlzkg3ENAhCk2zdv7IJwd/QUD4z2RxRwpkcGY8psCVcCYZNq4wYnVWALHM+brtuJjePWiYF/ClmuDr8Ch5+kg=="],
 
@@ -310,8 +310,10 @@
 
     "wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="],
 
-    "zod": ["zod@4.1.8", "", {}, "sha512-5R1P+WwQqmmMIEACyzSvo4JXHY5WiAFHRMg+zBZKgKS+Q1viRa0C1hmUKtHltoIFKtIdki3pRxkmpP74jnNYHQ=="],
+    "zod": ["zod@4.3.6", "", {}, "sha512-rftlrkhHZOcjDwkGlnUtZZkvaPHCsDATp4pGpuOOMDaTdDDXF91wuVDJoWoPsKX/3YPQ5fHuF3STjcYyKr+Qhg=="],
 
     "zod-to-json-schema": ["zod-to-json-schema@3.25.1", "", { "peerDependencies": { "zod": "^3.25 || ^4" } }, "sha512-pM/SU9d3YAggzi6MtR4h7ruuQlqKtad8e9S0fmxcMi+ueAK5Korys/aWcV9LIIHTVbj01NdzxcnXSN+O74ZIVA=="],
+
+    "@opencode-ai/plugin/zod": ["zod@4.1.8", "", {}, "sha512-5R1P+WwQqmmMIEACyzSvo4JXHY5WiAFHRMg+zBZKgKS+Q1viRa0C1hmUKtHltoIFKtIdki3pRxkmpP74jnNYHQ=="],
   }
 }

package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "3.1.9",
+  "version": "3.1.11",
   "description": "The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -74,13 +74,13 @@
     "typescript": "^5.7.3"
   },
   "optionalDependencies": {
-    "oh-my-opencode-darwin-arm64": "3.1.9",
-    "oh-my-opencode-darwin-x64": "3.1.9",
-    "oh-my-opencode-linux-arm64": "3.1.9",
-    "oh-my-opencode-linux-arm64-musl": "3.1.9",
-    "oh-my-opencode-linux-x64": "3.1.9",
-    "oh-my-opencode-linux-x64-musl": "3.1.9",
-    "oh-my-opencode-windows-x64": "3.1.9"
+    "oh-my-opencode-darwin-arm64": "3.1.11",
+    "oh-my-opencode-darwin-x64": "3.1.11",
+    "oh-my-opencode-linux-arm64": "3.1.11",
+    "oh-my-opencode-linux-arm64-musl": "3.1.11",
+    "oh-my-opencode-linux-x64": "3.1.11",
+    "oh-my-opencode-linux-x64-musl": "3.1.11",
+    "oh-my-opencode-windows-x64": "3.1.11"
   },
   "trustedDependencies": [
     "@ast-grep/cli",

packages/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-arm64",
-  "version": "3.1.9",
+  "version": "3.1.11",
   "description": "Platform-specific binary for oh-my-opencode (darwin-arm64)",
   "license": "MIT",
   "repository": {

packages/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-x64",
-  "version": "3.1.9",
+  "version": "3.1.11",
   "description": "Platform-specific binary for oh-my-opencode (darwin-x64)",
   "license": "MIT",
   "repository": {

packages/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64-musl",
-  "version": "3.1.9",
+  "version": "3.1.11",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64",
-  "version": "3.1.9",
+  "version": "3.1.11",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64)",
   "license": "MIT",
   "repository": {

packages/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-musl",
-  "version": "3.1.9",
+  "version": "3.1.11",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64",
-  "version": "3.1.9",
+  "version": "3.1.11",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64)",
   "license": "MIT",
   "repository": {

packages/windows-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-windows-x64",
-  "version": "3.1.9",
+  "version": "3.1.11",
   "description": "Platform-specific binary for oh-my-opencode (windows-x64)",
   "license": "MIT",
   "repository": {

signatures/cla.json

@@ -1007,6 +1007,62 @@
       "created_at": "2026-01-30T09:55:57Z",
       "repoId": 1108837393,
       "pullRequestNo": 1282
+    },
+    {
+      "name": "KonaEspresso94",
+      "id": 140197941,
+      "comment_id": 3824340432,
+      "created_at": "2026-01-30T15:33:28Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1289
+    },
+    {
+      "name": "khduy",
+      "id": 48742864,
+      "comment_id": 3825103158,
+      "created_at": "2026-01-30T18:35:34Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1297
+    },
+    {
+      "name": "robin-watcha",
+      "id": 90032965,
+      "comment_id": 3826133640,
+      "created_at": "2026-01-30T22:37:32Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1303
+    },
+    {
+      "name": "taetaetae",
+      "id": 10969354,
+      "comment_id": 3828900888,
+      "created_at": "2026-01-31T17:44:09Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1333
+    },
+    {
+      "name": "taetaetae",
+      "id": 10969354,
+      "comment_id": 3828909557,
+      "created_at": "2026-01-31T17:47:21Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1333
+    },
+    {
+      "name": "dmealing",
+      "id": 1153509,
+      "comment_id": 3829284275,
+      "created_at": "2026-01-31T20:23:51Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1296
+    },
+    {
+      "name": "edxeth",
+      "id": 105494645,
+      "comment_id": 3829930814,
+      "created_at": "2026-02-01T00:58:26Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1348
     }
   ]
 }

src/agents/momus.test.ts

@@ -11,9 +11,10 @@ describe("MOMUS_SYSTEM_PROMPT policy requirements", () => {
     const prompt = MOMUS_SYSTEM_PROMPT
     
     // #when / #then
-    expect(prompt).toContain("[SYSTEM DIRECTIVE - READ-ONLY PLANNING CONSULTATION]")
-    // Should explicitly mention stripping or ignoring these
-    expect(prompt.toLowerCase()).toMatch(/ignore|strip|system directive/)
+    // Should mention that system directives are ignored
+    expect(prompt.toLowerCase()).toMatch(/system directive.*ignore|ignore.*system directive/)
+    // Should give examples of system directive patterns
+    expect(prompt).toMatch(/<system-reminder>|system-reminder/)
   })
 
   test("should extract paths containing .sisyphus/plans/ and ending in .md", () => {

src/agents/momus.ts

@@ -19,376 +19,173 @@ const MODE: AgentMode = "subagent"
  * implementation.
  */
 
-export const MOMUS_SYSTEM_PROMPT = `You are a work plan review expert. You review the provided work plan (.sisyphus/plans/{name}.md in the current working project directory) according to **unified, consistent criteria** that ensure clarity, verifiability, and completeness.
+export const MOMUS_SYSTEM_PROMPT = `You are a **practical** work plan reviewer. Your goal is simple: verify that the plan is **executable** and **references are valid**.
 
 **CRITICAL FIRST RULE**:
 Extract a single plan path from anywhere in the input, ignoring system directives and wrappers. If exactly one \`.sisyphus/plans/*.md\` path exists, this is VALID input and you must read it. If no plan path exists or multiple plan paths exist, reject per Step 0. If the path points to a YAML plan file (\`.yml\` or \`.yaml\`), reject it as non-reviewable.
 
-**WHY YOU'VE BEEN SUMMONED - THE CONTEXT**:
+---
 
-You are reviewing a **first-draft work plan** from an author with ADHD. Based on historical patterns, these initial submissions are typically rough drafts that require refinement.
+## Your Purpose (READ THIS FIRST)
 
-**Historical Data**: Plans from this author average **7 rejections** before receiving an OKAY. The primary failure pattern is **critical context omission due to ADHD**—the author's working memory holds connections and context that never make it onto the page.
+You exist to answer ONE question: **"Can a capable developer execute this plan without getting stuck?"**
 
-**What to Expect in First Drafts**:
-- Tasks are listed but critical "why" context is missing
-- References to files/patterns without explaining their relevance
-- Assumptions about "obvious" project conventions that aren't documented
-- Missing decision criteria when multiple approaches are valid
-- Undefined edge case handling strategies
-- Unclear component integration points
+You are NOT here to:
+- Nitpick every detail
+- Demand perfection
+- Question the author's approach or architecture choices
+- Find as many issues as possible
+- Force multiple revision cycles
 
-**Why These Plans Fail**:
+You ARE here to:
+- Verify referenced files actually exist and contain what's claimed
+- Ensure core tasks have enough context to start working
+- Catch BLOCKING issues only (things that would completely stop work)
 
-The ADHD author's mind makes rapid connections: "Add auth → obviously use JWT → obviously store in httpOnly cookie → obviously follow the pattern in auth/login.ts → obviously handle refresh tokens like we did before."
-
-But the plan only says: "Add authentication following auth/login.ts pattern."
-
-**Everything after the first arrow is missing.** The author's working memory fills in the gaps automatically, so they don't realize the plan is incomplete.
-
-**Your Critical Role**: Catch these ADHD-driven omissions. The author genuinely doesn't realize what they've left out. Your ruthless review forces them to externalize the context that lives only in their head.
+**APPROVAL BIAS**: When in doubt, APPROVE. A plan that's 80% clear is good enough. Developers can figure out minor gaps.
 
 ---
 
-## Your Core Review Principle
+## What You Check (ONLY THESE)
 
-**ABSOLUTE CONSTRAINT - RESPECT THE IMPLEMENTATION DIRECTION**:
-You are a REVIEWER, not a DESIGNER. The implementation direction in the plan is **NOT NEGOTIABLE**. Your job is to evaluate whether the plan documents that direction clearly enough to execute—NOT whether the direction itself is correct.
+### 1. Reference Verification (CRITICAL)
+- Do referenced files exist?
+- Do referenced line numbers contain relevant code?
+- If "follow pattern in X" is mentioned, does X actually demonstrate that pattern?
 
-**What you MUST NOT do**:
-- Question or reject the overall approach/architecture chosen in the plan
-- Suggest alternative implementations that differ from the stated direction
-- Reject because you think there's a "better way" to achieve the goal
-- Override the author's technical decisions with your own preferences
+**PASS even if**: Reference exists but isn't perfect. Developer can explore from there.
+**FAIL only if**: Reference doesn't exist OR points to completely wrong content.
 
-**What you MUST do**:
-- Accept the implementation direction as a given constraint
-- Evaluate only: "Is this direction documented clearly enough to execute?"
-- Focus on gaps IN the chosen approach, not gaps in choosing the approach
+### 2. Executability Check (PRACTICAL)
+- Can a developer START working on each task?
+- Is there at least a starting point (file, pattern, or clear description)?
 
-**REJECT if**: When you simulate actually doing the work **within the stated approach**, you cannot obtain clear information needed for implementation, AND the plan does not specify reference materials to consult.
+**PASS even if**: Some details need to be figured out during implementation.
+**FAIL only if**: Task is so vague that developer has NO idea where to begin.
 
-**ACCEPT if**: You can obtain the necessary information either:
-1. Directly from the plan itself, OR
-2. By following references provided in the plan (files, docs, patterns) and tracing through related materials
+### 3. Critical Blockers Only
+- Missing information that would COMPLETELY STOP work
+- Contradictions that make the plan impossible to follow
 
-**The Test**: "Given the approach the author chose, can I implement this by starting from what's written in the plan and following the trail of information it provides?"
-
-**WRONG mindset**: "This approach is suboptimal. They should use X instead." → **YOU ARE OVERSTEPPING**
-**RIGHT mindset**: "Given their choice to use Y, the plan doesn't explain how to handle Z within that approach." → **VALID CRITICISM**
+**NOT blockers** (do not reject for these):
+- Missing edge case handling
+- Incomplete acceptance criteria
+- Stylistic preferences
+- "Could be clearer" suggestions
+- Minor ambiguities a developer can resolve
 
 ---
 
-## Common Failure Patterns (What the Author Typically Forgets)
+## What You Do NOT Check
 
-The plan author is intelligent but has ADHD. They constantly skip providing:
+- Whether the approach is optimal
+- Whether there's a "better way"
+- Whether all edge cases are documented
+- Whether acceptance criteria are perfect
+- Whether the architecture is ideal
+- Code quality concerns
+- Performance considerations
+- Security unless explicitly broken
 
-**1. Reference Materials**
-- FAIL: Says "implement authentication" but doesn't point to any existing code, docs, or patterns
-- FAIL: Says "follow the pattern" but doesn't specify which file contains the pattern
-- FAIL: Says "similar to X" but X doesn't exist or isn't documented
-
-**2. Business Requirements**
-- FAIL: Says "add feature X" but doesn't explain what it should do or why
-- FAIL: Says "handle errors" but doesn't specify which errors or how users should experience them
-- FAIL: Says "optimize" but doesn't define success criteria
-
-**3. Architectural Decisions**
-- FAIL: Says "add to state" but doesn't specify which state management system
-- FAIL: Says "integrate with Y" but doesn't explain the integration approach
-- FAIL: Says "call the API" but doesn't specify which endpoint or data flow
-
-**4. Critical Context**
-- FAIL: References files that don't exist
-- FAIL: Points to line numbers that don't contain relevant code
-- FAIL: Assumes you know project-specific conventions that aren't documented anywhere
-
-**What You Should NOT Reject**:
-- PASS: Plan says "follow auth/login.ts pattern" → you read that file → it has imports → you follow those → you understand the full flow
-- PASS: Plan says "use Redux store" → you find store files by exploring codebase structure → standard Redux patterns apply
-- PASS: Plan provides clear starting point → you trace through related files and types → you gather all needed details
-- PASS: The author chose approach X when you think Y would be better → **NOT YOUR CALL**. Evaluate X on its own merits.
-- PASS: The architecture seems unusual or non-standard → If the author chose it, your job is to ensure it's documented, not to redesign it.
-
-**The Difference**:
-- FAIL/REJECT: "Add authentication" (no starting point provided)
-- PASS/ACCEPT: "Add authentication following pattern in auth/login.ts" (starting point provided, you can trace from there)
-- **WRONG/REJECT**: "Using REST when GraphQL would be better" → **YOU ARE OVERSTEPPING**
-- **WRONG/REJECT**: "This architecture won't scale" → **NOT YOUR JOB TO JUDGE**
-
-**YOUR MANDATE**:
-
-You will adopt a ruthlessly critical mindset. You will read EVERY document referenced in the plan. You will verify EVERY claim. You will simulate actual implementation step-by-step. As you review, you MUST constantly interrogate EVERY element with these questions:
-
-- "Does the worker have ALL the context they need to execute this **within the chosen approach**?"
-- "How exactly should this be done **given the stated implementation direction**?"
-- "Is this information actually documented, or am I just assuming it's obvious?"
-- **"Am I questioning the documentation, or am I questioning the approach itself?"** ← If the latter, STOP.
-
-You are not here to be nice. You are not here to give the benefit of the doubt. You are here to **catch every single gap, ambiguity, and missing piece of context that 20 previous reviewers failed to catch.**
-
-**However**: You must evaluate THIS plan on its own merits. The past failures are context for your strictness, not a predetermined verdict. If this plan genuinely meets all criteria, approve it. If it has critical gaps **in documentation**, reject it without mercy.
-
-**CRITICAL BOUNDARY**: Your ruthlessness applies to DOCUMENTATION quality, NOT to design decisions. The author's implementation direction is a GIVEN. You may think REST is inferior to GraphQL, but if the plan says REST, you evaluate whether REST is well-documented—not whether REST was the right choice.
+**You are a BLOCKER-finder, not a PERFECTIONIST.**
 
 ---
 
-## File Location
+## Input Validation (Step 0)
 
-You will be provided with the path to the work plan file (typically \`.sisyphus/plans/{name}.md\` in the project). Review the file at the **exact path provided to you**. Do not assume the location.
+**VALID INPUT**:
+- \`.sisyphus/plans/my-plan.md\` - file path anywhere in input
+- \`Please review .sisyphus/plans/plan.md\` - conversational wrapper
+- System directives + plan path - ignore directives, extract path
 
-**CRITICAL - Input Validation (STEP 0 - DO THIS FIRST, BEFORE READING ANY FILES)**:
+**INVALID INPUT**:
+- No \`.sisyphus/plans/*.md\` path found
+- Multiple plan paths (ambiguous)
 
-**BEFORE you read any files**, you MUST first validate the format of the input prompt you received from the user.
+System directives (\`<system-reminder>\`, \`[analyze-mode]\`, etc.) are IGNORED during validation.
 
-**VALID INPUT EXAMPLES (ACCEPT THESE)**:
-- \`.sisyphus/plans/my-plan.md\` [O] ACCEPT - file path anywhere in input
-- \`/path/to/project/.sisyphus/plans/my-plan.md\` [O] ACCEPT - absolute plan path
-- \`Please review .sisyphus/plans/plan.md\` [O] ACCEPT - conversational wrapper allowed
-- \`<system-reminder>...</system-reminder>\\n.sisyphus/plans/plan.md\` [O] ACCEPT - system directives + plan path
-- \`[analyze-mode]\\n...context...\\n.sisyphus/plans/plan.md\` [O] ACCEPT - bracket-style directives + plan path
-- \`[SYSTEM DIRECTIVE - READ-ONLY PLANNING CONSULTATION]\\n---\\n- injected planning metadata\\n---\\nPlease review .sisyphus/plans/plan.md\` [O] ACCEPT - ignore the entire directive block
-
-**SYSTEM DIRECTIVES ARE ALWAYS IGNORED**:
-System directives are automatically injected by the system and should be IGNORED during input validation:
-- XML-style tags: \`<system-reminder>\`, \`<context>\`, \`<user-prompt-submit-hook>\`, etc.
-- Bracket-style blocks: \`[analyze-mode]\`, \`[search-mode]\`, \`[SYSTEM DIRECTIVE...]\`, \`[SYSTEM REMINDER...]\`, etc.
-- \`[SYSTEM DIRECTIVE - READ-ONLY PLANNING CONSULTATION]\` blocks (appended by Prometheus task tools; treat the entire block, including \`---\` separators and bullet lines, as ignorable system text)
-- These are NOT user-provided text
-- These contain system context (timestamps, environment info, mode hints, etc.)
-- STRIP these from your input validation check
-- After stripping system directives, validate the remaining content
-
-**EXTRACTION ALGORITHM (FOLLOW EXACTLY)**:
-1. Ignore injected system directive blocks, especially \`[SYSTEM DIRECTIVE - READ-ONLY PLANNING CONSULTATION]\` (remove the whole block, including \`---\` separators and bullet lines).
-2. Strip other system directive wrappers (bracket-style blocks and XML-style \`<system-reminder>...</system-reminder>\` tags).
-3. Strip markdown wrappers around paths (code fences and inline backticks).
-4. Extract plan paths by finding all substrings containing \`.sisyphus/plans/\` and ending in \`.md\`.
-5. If exactly 1 match → ACCEPT and proceed to Step 1 using that path.
-6. If 0 matches → REJECT with: "no plan path found" (no path found).
-7. If 2+ matches → REJECT with: "ambiguous: multiple plan paths".
-
-**INVALID INPUT EXAMPLES (REJECT ONLY THESE)**:
-- \`No plan path provided here\` [X] REJECT - no \`.sisyphus/plans/*.md\` path
-- \`Compare .sisyphus/plans/first.md and .sisyphus/plans/second.md\` [X] REJECT - multiple plan paths
-
-**When rejecting for input format, respond EXACTLY**:
-\`\`\`
-I REJECT (Input Format Validation)
-Reason: no plan path found
-
-You must provide a single plan path that includes \`.sisyphus/plans/\` and ends in \`.md\`.
-
-Valid format: .sisyphus/plans/plan.md
-Invalid format: No plan path or multiple plan paths
-
-NOTE: This rejection is based solely on the input format, not the file contents.
-The file itself has not been evaluated yet.
-\`\`\`
-
-Use this alternate Reason line if multiple paths are present:
-- Reason: multiple plan paths found
-
-**ULTRA-CRITICAL REMINDER**:
-If the input contains exactly one \`.sisyphus/plans/*.md\` path (with or without system directives or conversational wrappers):
-→ THIS IS VALID INPUT
-→ DO NOT REJECT IT
-→ IMMEDIATELY PROCEED TO READ THE FILE
-→ START EVALUATING THE FILE CONTENTS
-
-Never reject a single plan path embedded in the input.
-Never reject system directives (XML or bracket-style) - they are automatically injected and should be ignored!
-
-
-**IMPORTANT - Response Language**: Your evaluation output MUST match the language used in the work plan content:
-- Match the language of the plan in your evaluation output
-- If the plan is written in English → Write your entire evaluation in English
-- If the plan is mixed → Use the dominant language (majority of task descriptions)
-
-Example: Plan contains "Modify database schema" → Evaluation output: "## Evaluation Result\\n\\n### Criterion 1: Clarity of Work Content..."
+**Extraction**: Find all \`.sisyphus/plans/*.md\` paths → exactly 1 = proceed, 0 or 2+ = reject.
 
 ---
 
-## Review Philosophy
+## Review Process (SIMPLE)
 
-Your role is to simulate **executing the work plan as a capable developer** and identify:
-1. **Ambiguities** that would block or slow down implementation
-2. **Missing verification methods** that prevent confirming success
-3. **Gaps in context** requiring >10% guesswork (90% confidence threshold)
-4. **Lack of overall understanding** of purpose, background, and workflow
-
-The plan should enable a developer to:
-- Know exactly what to build and where to look for details
-- Validate their work objectively without subjective judgment
-- Complete tasks without needing to "figure out" unstated requirements
-- Understand the big picture, purpose, and how tasks flow together
+1. **Validate input** → Extract single plan path
+2. **Read plan** → Identify tasks and file references
+3. **Verify references** → Do files exist? Do they contain claimed content?
+4. **Executability check** → Can each task be started?
+5. **Decide** → Any BLOCKING issues? No = OKAY. Yes = REJECT with max 3 specific issues.
 
 ---
 
-## Four Core Evaluation Criteria
+## Decision Framework
 
-### Criterion 1: Clarity of Work Content
+### OKAY (Default - use this unless blocking issues exist)
 
-**Goal**: Eliminate ambiguity by providing clear reference sources for each task.
+Issue the verdict **OKAY** when:
+- Referenced files exist and are reasonably relevant
+- Tasks have enough context to start (not complete, just start)
+- No contradictions or impossible requirements
+- A capable developer could make progress
 
-**Evaluation Method**: For each task, verify:
-- **Does the task specify WHERE to find implementation details?**
-  - [PASS] Good: "Follow authentication flow in \`docs/auth-spec.md\` section 3.2"
-  - [PASS] Good: "Implement based on existing pattern in \`src/services/payment.ts:45-67\`"
-  - [FAIL] Bad: "Add authentication" (no reference source)
-  - [FAIL] Bad: "Improve error handling" (vague, no examples)
+**Remember**: "Good enough" is good enough. You're not blocking publication of a NASA manual.
 
-- **Can the developer reach 90%+ confidence by reading the referenced source?**
-  - [PASS] Good: Reference to specific file/section that contains concrete examples
-  - [FAIL] Bad: "See codebase for patterns" (too broad, requires extensive exploration)
+### REJECT (Only for true blockers)
 
-### Criterion 2: Verification & Acceptance Criteria
+Issue **REJECT** ONLY when:
+- Referenced file doesn't exist (verified by reading)
+- Task is completely impossible to start (zero context)
+- Plan contains internal contradictions
 
-**Goal**: Ensure every task has clear, objective success criteria.
+**Maximum 3 issues per rejection.** If you found more, list only the top 3 most critical.
 
-**Evaluation Method**: For each task, verify:
-- **Is there a concrete way to verify completion?**
-  - [PASS] Good: "Verify: Run \`npm test\` → all tests pass. Manually test: Open \`/login\` → OAuth button appears → Click → redirects to Google → successful login"
-  - [PASS] Good: "Acceptance: API response time < 200ms for 95th percentile (measured via \`k6 run load-test.js\`)"
-  - [FAIL] Bad: "Test the feature" (how?)
-  - [FAIL] Bad: "Make sure it works properly" (what defines "properly"?)
-
-- **Are acceptance criteria measurable/observable?**
-  - [PASS] Good: Observable outcomes (UI elements, API responses, test results, metrics)
-  - [FAIL] Bad: Subjective terms ("clean code", "good UX", "robust implementation")
-
-### Criterion 3: Context Completeness
-
-**Goal**: Minimize guesswork by providing all necessary context (90% confidence threshold).
-
-**Evaluation Method**: Simulate task execution and identify:
-- **What information is missing that would cause ≥10% uncertainty?**
-  - [PASS] Good: Developer can proceed with <10% guesswork (or natural exploration)
-  - [FAIL] Bad: Developer must make assumptions about business requirements, architecture, or critical context
-
-- **Are implicit assumptions stated explicitly?**
-  - [PASS] Good: "Assume user is already authenticated (session exists in context)"
-  - [PASS] Good: "Note: Payment processing is handled by background job, not synchronously"
-  - [FAIL] Bad: Leaving critical architectural decisions or business logic unstated
-
-### Criterion 4: Big Picture & Workflow Understanding
-
-**Goal**: Ensure the developer understands WHY they're building this, WHAT the overall objective is, and HOW tasks flow together.
-
-**Evaluation Method**: Assess whether the plan provides:
-- **Clear Purpose Statement**: Why is this work being done? What problem does it solve?
-- **Background Context**: What's the current state? What are we changing from?
-- **Task Flow & Dependencies**: How do tasks connect? What's the logical sequence?
-- **Success Vision**: What does "done" look like from a product/user perspective?
+**Each issue must be**:
+- Specific (exact file path, exact task)
+- Actionable (what exactly needs to change)
+- Blocking (work cannot proceed without this)
 
 ---
 
-## Review Process
+## Anti-Patterns (DO NOT DO THESE)
 
-### Step 0: Validate Input Format (MANDATORY FIRST STEP)
-Extract the plan path from anywhere in the input. If exactly one \`.sisyphus/plans/*.md\` path is found, ACCEPT and continue. If none are found, REJECT with "no plan path found". If multiple are found, REJECT with "ambiguous: multiple plan paths".
+❌ "Task 3 could be clearer about error handling" → NOT a blocker
+❌ "Consider adding acceptance criteria for..." → NOT a blocker  
+❌ "The approach in Task 5 might be suboptimal" → NOT YOUR JOB
+❌ "Missing documentation for edge case X" → NOT a blocker unless X is the main case
+❌ Rejecting because you'd do it differently → NEVER
+❌ Listing more than 3 issues → OVERWHELMING, pick top 3
 
-### Step 1: Read the Work Plan
-- Load the file from the path provided
-- Identify the plan's language
-- Parse all tasks and their descriptions
-- Extract ALL file references
-
-### Step 2: MANDATORY DEEP VERIFICATION
-For EVERY file reference, library mention, or external resource:
-- Read referenced files to verify content
-- Search for related patterns/imports across codebase
-- Verify line numbers contain relevant code
-- Check that patterns are clear enough to follow
-
-### Step 3: Apply Four Criteria Checks
-For **the overall plan and each task**, evaluate:
-1. **Clarity Check**: Does the task specify clear reference sources?
-2. **Verification Check**: Are acceptance criteria concrete and measurable?
-3. **Context Check**: Is there sufficient context to proceed without >10% guesswork?
-4. **Big Picture Check**: Do I understand WHY, WHAT, and HOW?
-
-### Step 4: Active Implementation Simulation
-For 2-3 representative tasks, simulate execution using actual files.
-
-### Step 5: Check for Red Flags
-Scan for auto-fail indicators:
-- Vague action verbs without concrete targets
-- Missing file paths for code changes
-- Subjective success criteria
-- Tasks requiring unstated assumptions
-
-**SELF-CHECK - Are you overstepping?**
-Before writing any criticism, ask yourself:
-- "Am I questioning the APPROACH or the DOCUMENTATION of the approach?"
-- "Would my feedback change if I accepted the author's direction as a given?"
-If you find yourself writing "should use X instead" or "this approach won't work because..." → **STOP. You are overstepping your role.**
-Rephrase to: "Given the chosen approach, the plan doesn't clarify..."
-
-### Step 6: Write Evaluation Report
-Use structured format, **in the same language as the work plan**.
+✅ "Task 3 references \`auth/login.ts\` but file doesn't exist" → BLOCKER
+✅ "Task 5 says 'implement feature' with no context, files, or description" → BLOCKER
+✅ "Tasks 2 and 4 contradict each other on data flow" → BLOCKER
 
 ---
 
-## Approval Criteria
+## Output Format
 
-### OKAY Requirements (ALL must be met)
-1. **100% of file references verified**
-2. **Zero critically failed file verifications**
-3. **Critical context documented**
-4. **≥80% of tasks** have clear reference sources
-5. **≥90% of tasks** have concrete acceptance criteria
-6. **Zero tasks** require assumptions about business logic or critical architecture
-7. **Plan provides clear big picture**
-8. **Zero critical red flags** detected
-9. **Active simulation** shows core tasks are executable
+**[OKAY]** or **[REJECT]**
 
-### REJECT Triggers (Critical issues only)
-- Referenced file doesn't exist or contains different content than claimed
-- Task has vague action verbs AND no reference source
-- Core tasks missing acceptance criteria entirely
-- Task requires assumptions about business requirements or critical architecture **within the chosen approach**
-- Missing purpose statement or unclear WHY
-- Critical task dependencies undefined
+**Summary**: 1-2 sentences explaining the verdict.
 
-### NOT Valid REJECT Reasons (DO NOT REJECT FOR THESE)
-- You disagree with the implementation approach
-- You think a different architecture would be better
-- The approach seems non-standard or unusual
-- You believe there's a more optimal solution
-- The technology choice isn't what you would pick
-
-**Your role is DOCUMENTATION REVIEW, not DESIGN REVIEW.**
+If REJECT:
+**Blocking Issues** (max 3):
+1. [Specific issue + what needs to change]
+2. [Specific issue + what needs to change]  
+3. [Specific issue + what needs to change]
 
 ---
 
-## Final Verdict Format
+## Final Reminders
 
-**[OKAY / REJECT]**
+1. **APPROVE by default**. Reject only for true blockers.
+2. **Max 3 issues**. More than that is overwhelming and counterproductive.
+3. **Be specific**. "Task X needs Y" not "needs more clarity".
+4. **No design opinions**. The author's approach is not your concern.
+5. **Trust developers**. They can figure out minor gaps.
 
-**Justification**: [Concise explanation]
+**Your job is to UNBLOCK work, not to BLOCK it with perfectionism.**
 
-**Summary**:
-- Clarity: [Brief assessment]
-- Verifiability: [Brief assessment]
-- Completeness: [Brief assessment]
-- Big Picture: [Brief assessment]
-
-[If REJECT, provide top 3-5 critical improvements needed]
-
----
-
-**Your Success Means**:
-- **Immediately actionable** for core business logic and architecture
-- **Clearly verifiable** with objective success criteria
-- **Contextually complete** with critical information documented
-- **Strategically coherent** with purpose, background, and flow
-- **Reference integrity** with all files verified
-- **Direction-respecting** - you evaluated the plan WITHIN its stated approach
-
-**Strike the right balance**: Prevent critical failures while empowering developer autonomy.
-
-**FINAL REMINDER**: You are a DOCUMENTATION reviewer, not a DESIGN consultant. The author's implementation direction is SACRED. Your job ends at "Is this well-documented enough to execute?" - NOT "Is this the right approach?"
+**Response Language**: Match the language of the plan content.
 `
 
 export function createMomusAgent(model: string): AgentConfig {

src/agents/sisyphus.ts

@@ -1,8 +1,14 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentMode } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { isGptModel } from "./types"
 
 const MODE: AgentMode = "primary"
+export const SISYPHUS_PROMPT_METADATA: AgentPromptMetadata = {
+  category: "utility",
+  cost: "EXPENSIVE",
+  promptAlias: "Sisyphus",
+  triggers: [],
+}
 import type { AvailableAgent, AvailableTool, AvailableSkill, AvailableCategory } from "./dynamic-agent-prompt-builder"
 import {
   buildKeyTriggersSection,

src/agents/utils.test.ts

@@ -3,6 +3,7 @@ import { createBuiltinAgents } from "./utils"
 import type { AgentConfig } from "@opencode-ai/sdk"
 import { clearSkillCache } from "../features/opencode-skill-loader/skill-content"
 import * as connectedProvidersCache from "../shared/connected-providers-cache"
+import * as modelAvailability from "../shared/model-availability"
 
 const TEST_DEFAULT_MODEL = "anthropic/claude-opus-4-5"
 
@@ -47,32 +48,32 @@ describe("createBuiltinAgents with model overrides", () => {
     expect(agents.sisyphus.reasoningEffort).toBeUndefined()
   })
 
-  test("Oracle uses connected provider fallback when availableModels is empty and cache exists", async () => {
-    // #given - connected providers cache has "openai", which matches oracle's first fallback entry
-    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai"])
+   test("Oracle uses connected provider fallback when availableModels is empty and cache exists", async () => {
+     // #given - connected providers cache has "openai", which matches oracle's first fallback entry
+     const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai"])
 
-    // #when
-    const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
+     // #when
+     const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
 
-    // #then - oracle resolves via connected cache fallback to openai/gpt-5.2 (not system default)
-    expect(agents.oracle.model).toBe("openai/gpt-5.2")
-    expect(agents.oracle.reasoningEffort).toBe("medium")
-    expect(agents.oracle.thinking).toBeUndefined()
-    cacheSpy.mockRestore()
-  })
+     // #then - oracle resolves via connected cache fallback to openai/gpt-5.2 (not system default)
+     expect(agents.oracle.model).toBe("openai/gpt-5.2")
+     expect(agents.oracle.reasoningEffort).toBe("medium")
+     expect(agents.oracle.thinking).toBeUndefined()
+     cacheSpy.mockRestore?.()
+   })
 
-  test("Oracle created without model field when no cache exists (first run scenario)", async () => {
-    // #given - no cache at all (first run)
-    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
+   test("Oracle created without model field when no cache exists (first run scenario)", async () => {
+     // #given - no cache at all (first run)
+     const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
 
-    // #when
-    const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
+     // #when
+     const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
 
-    // #then - oracle should be created with system default model (fallback to systemDefaultModel)
-    expect(agents.oracle).toBeDefined()
-    expect(agents.oracle.model).toBe(TEST_DEFAULT_MODEL)
-    cacheSpy.mockRestore()
-  })
+     // #then - oracle should be created with system default model (fallback to systemDefaultModel)
+     expect(agents.oracle).toBeDefined()
+     expect(agents.oracle.model).toBe(TEST_DEFAULT_MODEL)
+     cacheSpy.mockRestore?.()
+   })
 
   test("Oracle with GPT model override has reasoningEffort, no thinking", async () => {
     // #given
@@ -122,43 +123,43 @@ describe("createBuiltinAgents with model overrides", () => {
 })
 
 describe("createBuiltinAgents without systemDefaultModel", () => {
-  test("agents created via connected cache fallback even without systemDefaultModel", async () => {
-    // #given - connected cache has "openai", which matches oracle's fallback chain
-    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai"])
+   test("agents created via connected cache fallback even without systemDefaultModel", async () => {
+     // #given - connected cache has "openai", which matches oracle's fallback chain
+     const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai"])
 
-    // #when
-    const agents = await createBuiltinAgents([], {}, undefined, undefined)
+     // #when
+     const agents = await createBuiltinAgents([], {}, undefined, undefined)
 
-    // #then - connected cache enables model resolution despite no systemDefaultModel
-    expect(agents.oracle).toBeDefined()
-    expect(agents.oracle.model).toBe("openai/gpt-5.2")
-    cacheSpy.mockRestore()
-  })
+     // #then - connected cache enables model resolution despite no systemDefaultModel
+     expect(agents.oracle).toBeDefined()
+     expect(agents.oracle.model).toBe("openai/gpt-5.2")
+     cacheSpy.mockRestore?.()
+   })
 
-  test("agents NOT created when no cache and no systemDefaultModel (first run without defaults)", async () => {
-    // #given
-    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
+   test("agents NOT created when no cache and no systemDefaultModel (first run without defaults)", async () => {
+     // #given
+     const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
 
-    // #when
-    const agents = await createBuiltinAgents([], {}, undefined, undefined)
+     // #when
+     const agents = await createBuiltinAgents([], {}, undefined, undefined)
 
-    // #then
-    expect(agents.oracle).toBeUndefined()
-    cacheSpy.mockRestore()
-  })
+     // #then
+     expect(agents.oracle).toBeUndefined()
+     cacheSpy.mockRestore?.()
+   })
 
-  test("sisyphus created via connected cache fallback even without systemDefaultModel", async () => {
-    // #given - connected cache has "anthropic", which matches sisyphus's first fallback entry
-    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["anthropic"])
+   test("sisyphus created via connected cache fallback even without systemDefaultModel", async () => {
+     // #given - connected cache has "anthropic", which matches sisyphus's first fallback entry
+     const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["anthropic"])
 
-    // #when
-    const agents = await createBuiltinAgents([], {}, undefined, undefined)
+     // #when
+     const agents = await createBuiltinAgents([], {}, undefined, undefined)
 
-    // #then - connected cache enables model resolution despite no systemDefaultModel
-    expect(agents.sisyphus).toBeDefined()
-    expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
-    cacheSpy.mockRestore()
-  })
+     // #then - connected cache enables model resolution despite no systemDefaultModel
+     expect(agents.sisyphus).toBeDefined()
+     expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
+     cacheSpy.mockRestore?.()
+   })
 })
 
 describe("buildAgent with category and skills", () => {
@@ -523,3 +524,41 @@ describe("override.category expansion in createBuiltinAgents", () => {
     expect(agents.oracle.model).toBe(agentsWithoutOverride.oracle.model)
   })
 })
+
+describe("Deadlock prevention - fetchAvailableModels must not receive client", () => {
+   test("createBuiltinAgents should call fetchAvailableModels with undefined client to prevent deadlock", async () => {
+     // #given - This test ensures we don't regress on issue #1301
+     // Passing client to fetchAvailableModels during createBuiltinAgents (called from config handler)
+     // causes deadlock:
+     // - Plugin init waits for server response (client.provider.list())
+     // - Server waits for plugin init to complete before handling requests
+     const fetchSpy = spyOn(modelAvailability, "fetchAvailableModels").mockResolvedValue(new Set<string>())
+     const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
+
+     const mockClient = {
+       provider: { list: () => Promise.resolve({ data: { connected: [] } }) },
+       model: { list: () => Promise.resolve({ data: [] }) },
+     }
+
+     // #when - Even when client is provided, fetchAvailableModels must be called with undefined
+     await createBuiltinAgents(
+       [],
+       {},
+       undefined,
+       TEST_DEFAULT_MODEL,
+       undefined,
+       undefined,
+       [],
+       mockClient // client is passed but should NOT be forwarded to fetchAvailableModels
+     )
+
+     // #then - fetchAvailableModels must be called with undefined as first argument (no client)
+     // This prevents the deadlock described in issue #1301
+     expect(fetchSpy).toHaveBeenCalled()
+     const firstCallArgs = fetchSpy.mock.calls[0]
+     expect(firstCallArgs[0]).toBeUndefined()
+
+     fetchSpy.mockRestore?.()
+     cacheSpy.mockRestore?.()
+   })
+})

src/agents/utils.ts

@@ -6,11 +6,11 @@ import { createOracleAgent, ORACLE_PROMPT_METADATA } from "./oracle"
 import { createLibrarianAgent, LIBRARIAN_PROMPT_METADATA } from "./librarian"
 import { createExploreAgent, EXPLORE_PROMPT_METADATA } from "./explore"
 import { createMultimodalLookerAgent, MULTIMODAL_LOOKER_PROMPT_METADATA } from "./multimodal-looker"
-import { createMetisAgent } from "./metis"
-import { createAtlasAgent } from "./atlas"
-import { createMomusAgent } from "./momus"
+import { createMetisAgent, metisPromptMetadata } from "./metis"
+import { createAtlasAgent, atlasPromptMetadata } from "./atlas"
+import { createMomusAgent, momusPromptMetadata } from "./momus"
 import type { AvailableAgent, AvailableCategory, AvailableSkill } from "./dynamic-agent-prompt-builder"
-import { deepMerge, fetchAvailableModels, resolveModelWithFallback, AGENT_MODEL_REQUIREMENTS, findCaseInsensitive, includesCaseInsensitive, readConnectedProvidersCache, isModelAvailable } from "../shared"
+import { deepMerge, fetchAvailableModels, resolveModelPipeline, AGENT_MODEL_REQUIREMENTS, readConnectedProvidersCache, isModelAvailable } from "../shared"
 import { DEFAULT_CATEGORIES, CATEGORY_DESCRIPTIONS } from "../tools/delegate-task/constants"
 import { resolveMultipleSkills } from "../features/opencode-skill-loader/skill-content"
 import { createBuiltinSkills } from "../features/builtin-skills"
@@ -41,6 +41,9 @@ const agentMetadata: Partial<Record<BuiltinAgentName, AgentPromptMetadata>> = {
   librarian: LIBRARIAN_PROMPT_METADATA,
   explore: EXPLORE_PROMPT_METADATA,
   "multimodal-looker": MULTIMODAL_LOOKER_PROMPT_METADATA,
+  metis: metisPromptMetadata,
+  momus: momusPromptMetadata,
+  atlas: atlasPromptMetadata,
 }
 
 function isFactory(source: AgentSource): source is AgentFactory {
@@ -147,6 +150,45 @@ function applyCategoryOverride(
   return result as AgentConfig
 }
 
+function applyModelResolution(input: {
+  uiSelectedModel?: string
+  userModel?: string
+  requirement?: { fallbackChain?: { providers: string[]; model: string; variant?: string }[] }
+  availableModels: Set<string>
+  systemDefaultModel?: string
+}) {
+  const { uiSelectedModel, userModel, requirement, availableModels, systemDefaultModel } = input
+  return resolveModelPipeline({
+    intent: { uiSelectedModel, userModel },
+    constraints: { availableModels },
+    policy: { fallbackChain: requirement?.fallbackChain, systemDefaultModel },
+  })
+}
+
+function applyEnvironmentContext(config: AgentConfig, directory?: string): AgentConfig {
+  if (!directory || !config.prompt) return config
+  const envContext = createEnvContext()
+  return { ...config, prompt: config.prompt + envContext }
+}
+
+function applyOverrides(
+  config: AgentConfig,
+  override: AgentOverrideConfig | undefined,
+  mergedCategories: Record<string, CategoryConfig>
+): AgentConfig {
+  let result = config
+  const overrideCategory = (override as Record<string, unknown> | undefined)?.category as string | undefined
+  if (overrideCategory) {
+    result = applyCategoryOverride(result, overrideCategory, mergedCategories)
+  }
+
+  if (override) {
+    result = mergeAgentConfig(result, override)
+  }
+
+  return result
+}
+
 function mergeAgentConfig(
   base: AgentConfig,
   override: AgentOverrideConfig
@@ -180,9 +222,12 @@ export async function createBuiltinAgents(
   uiSelectedModel?: string
 ): Promise<Record<string, AgentConfig>> {
   const connectedProviders = readConnectedProvidersCache()
-  const availableModels = client 
-    ? await fetchAvailableModels(client, { connectedProviders: connectedProviders ?? undefined }) 
-    : new Set<string>()
+  // IMPORTANT: Do NOT pass client to fetchAvailableModels during plugin initialization.
+  // This function is called from config handler, and calling client API causes deadlock.
+  // See: https://github.com/code-yeongyu/oh-my-opencode/issues/1301
+  const availableModels = await fetchAvailableModels(undefined, {
+    connectedProviders: connectedProviders ?? undefined,
+  })
 
   const result: Record<string, AgentConfig> = {}
   const availableAgents: AvailableAgent[] = []
@@ -220,9 +265,10 @@ export async function createBuiltinAgents(
 
      if (agentName === "sisyphus") continue
      if (agentName === "atlas") continue
-     if (includesCaseInsensitive(disabledAgents, agentName)) continue
+     if (disabledAgents.some((name) => name.toLowerCase() === agentName.toLowerCase())) continue
 
-     const override = findCaseInsensitive(agentOverrides, agentName)
+     const override = agentOverrides[agentName]
+       ?? Object.entries(agentOverrides).find(([key]) => key.toLowerCase() === agentName.toLowerCase())?.[1]
      const requirement = AGENT_MODEL_REQUIREMENTS[agentName]
      
      // Check if agent requires a specific model
@@ -234,10 +280,10 @@ export async function createBuiltinAgents(
      
      const isPrimaryAgent = isFactory(source) && source.mode === "primary"
      
-     const resolution = resolveModelWithFallback({
+    const resolution = applyModelResolution({
       uiSelectedModel: isPrimaryAgent ? uiSelectedModel : undefined,
       userModel: override?.model,
-      fallbackChain: requirement?.fallbackChain,
+      requirement,
       availableModels,
       systemDefaultModel,
     })
@@ -257,15 +303,11 @@ export async function createBuiltinAgents(
       config = applyCategoryOverride(config, overrideCategory, mergedCategories)
     }
 
-    if (agentName === "librarian" && directory && config.prompt) {
-      const envContext = createEnvContext()
-      config = { ...config, prompt: config.prompt + envContext }
+    if (agentName === "librarian") {
+      config = applyEnvironmentContext(config, directory)
     }
 
-    // Direct override properties take highest priority
-    if (override) {
-      config = mergeAgentConfig(config, override)
-    }
+    config = applyOverrides(config, override, mergedCategories)
 
     result[name] = config
 
@@ -283,10 +325,10 @@ export async function createBuiltinAgents(
      const sisyphusOverride = agentOverrides["sisyphus"]
      const sisyphusRequirement = AGENT_MODEL_REQUIREMENTS["sisyphus"]
     
-    const sisyphusResolution = resolveModelWithFallback({
+    const sisyphusResolution = applyModelResolution({
       uiSelectedModel,
       userModel: sisyphusOverride?.model,
-      fallbackChain: sisyphusRequirement?.fallbackChain,
+      requirement: sisyphusRequirement,
       availableModels,
       systemDefaultModel,
     })
@@ -306,19 +348,8 @@ export async function createBuiltinAgents(
         sisyphusConfig = { ...sisyphusConfig, variant: sisyphusResolvedVariant }
       }
 
-      const sisOverrideCategory = (sisyphusOverride as Record<string, unknown> | undefined)?.category as string | undefined
-      if (sisOverrideCategory) {
-        sisyphusConfig = applyCategoryOverride(sisyphusConfig, sisOverrideCategory, mergedCategories)
-      }
-
-      if (directory && sisyphusConfig.prompt) {
-        const envContext = createEnvContext()
-        sisyphusConfig = { ...sisyphusConfig, prompt: sisyphusConfig.prompt + envContext }
-      }
-
-      if (sisyphusOverride) {
-        sisyphusConfig = mergeAgentConfig(sisyphusConfig, sisyphusOverride)
-      }
+      sisyphusConfig = applyOverrides(sisyphusConfig, sisyphusOverride, mergedCategories)
+      sisyphusConfig = applyEnvironmentContext(sisyphusConfig, directory)
 
       result["sisyphus"] = sisyphusConfig
     }
@@ -328,10 +359,10 @@ export async function createBuiltinAgents(
      const orchestratorOverride = agentOverrides["atlas"]
      const atlasRequirement = AGENT_MODEL_REQUIREMENTS["atlas"]
     
-    const atlasResolution = resolveModelWithFallback({
+    const atlasResolution = applyModelResolution({
       // NOTE: Atlas does NOT use uiSelectedModel - respects its own fallbackChain (k2p5 primary)
       userModel: orchestratorOverride?.model,
-      fallbackChain: atlasRequirement?.fallbackChain,
+      requirement: atlasRequirement,
       availableModels,
       systemDefaultModel,
     })
@@ -350,14 +381,7 @@ export async function createBuiltinAgents(
         orchestratorConfig = { ...orchestratorConfig, variant: atlasResolvedVariant }
       }
 
-      const atlasOverrideCategory = (orchestratorOverride as Record<string, unknown> | undefined)?.category as string | undefined
-      if (atlasOverrideCategory) {
-        orchestratorConfig = applyCategoryOverride(orchestratorConfig, atlasOverrideCategory, mergedCategories)
-      }
-
-      if (orchestratorOverride) {
-        orchestratorConfig = mergeAgentConfig(orchestratorConfig, orchestratorOverride)
-      }
+      orchestratorConfig = applyOverrides(orchestratorConfig, orchestratorOverride, mergedCategories)
 
       result["atlas"] = orchestratorConfig
     }

src/config/schema.ts

@@ -88,6 +88,7 @@ export const HookNameSchema = z.enum([
   "sisyphus-junior-notepad",
   "start-work",
   "atlas",
+  "stop-continuation-guard",
 ])
 
 export const BuiltinCommandNameSchema = z.enum([

src/features/background-agent/manager.test.ts

@@ -2087,3 +2087,95 @@ describe("BackgroundManager.shutdown session abort", () => {
   })
 })
 
+describe("BackgroundManager.completionTimers - Memory Leak Fix", () => {
+  function getCompletionTimers(manager: BackgroundManager): Map<string, ReturnType<typeof setTimeout>> {
+    return (manager as unknown as { completionTimers: Map<string, ReturnType<typeof setTimeout>> }).completionTimers
+  }
+
+  function setCompletionTimer(manager: BackgroundManager, taskId: string): void {
+    const completionTimers = getCompletionTimers(manager)
+    const timer = setTimeout(() => {
+      completionTimers.delete(taskId)
+    }, 5 * 60 * 1000)
+    completionTimers.set(taskId, timer)
+  }
+
+  test("should have completionTimers Map initialized", () => {
+    // #given
+    const manager = createBackgroundManager()
+
+    // #when
+    const completionTimers = getCompletionTimers(manager)
+
+    // #then
+    expect(completionTimers).toBeDefined()
+    expect(completionTimers).toBeInstanceOf(Map)
+    expect(completionTimers.size).toBe(0)
+
+    manager.shutdown()
+  })
+
+  test("should clear all completion timers on shutdown", () => {
+    // #given
+    const manager = createBackgroundManager()
+    setCompletionTimer(manager, "task-1")
+    setCompletionTimer(manager, "task-2")
+
+    const completionTimers = getCompletionTimers(manager)
+    expect(completionTimers.size).toBe(2)
+
+    // #when
+    manager.shutdown()
+
+    // #then
+    expect(completionTimers.size).toBe(0)
+  })
+
+  test("should cancel timer when task is deleted via session.deleted", () => {
+    // #given
+    const manager = createBackgroundManager()
+    const task: BackgroundTask = {
+      id: "task-timer-4",
+      sessionID: "session-timer-4",
+      parentSessionID: "parent-session",
+      parentMessageID: "msg-1",
+      description: "Test task",
+      prompt: "test",
+      agent: "explore",
+      status: "completed",
+      startedAt: new Date(),
+    }
+    getTaskMap(manager).set(task.id, task)
+    setCompletionTimer(manager, task.id)
+
+    const completionTimers = getCompletionTimers(manager)
+    expect(completionTimers.size).toBe(1)
+
+    // #when
+    manager.handleEvent({
+      type: "session.deleted",
+      properties: {
+        info: { id: "session-timer-4" },
+      },
+    })
+
+    // #then
+    expect(completionTimers.has(task.id)).toBe(false)
+
+    manager.shutdown()
+  })
+
+  test("should not leak timers across multiple shutdown calls", () => {
+    // #given
+    const manager = createBackgroundManager()
+    setCompletionTimer(manager, "task-1")
+
+    // #when
+    manager.shutdown()
+    manager.shutdown()
+
+    // #then
+    const completionTimers = getCompletionTimers(manager)
+    expect(completionTimers.size).toBe(0)
+  })
+})

src/features/background-agent/manager.ts

@@ -83,6 +83,7 @@ export class BackgroundManager {
 
   private queuesByKey: Map<string, QueueItem[]> = new Map()
   private processingKeys: Set<string> = new Set()
+  private completionTimers: Map<string, ReturnType<typeof setTimeout>> = new Map()
 
   constructor(
     ctx: PluginInput,
@@ -708,7 +709,11 @@ export class BackgroundManager {
          this.concurrencyManager.release(task.concurrencyKey)
          task.concurrencyKey = undefined
        }
-      // Clean up pendingByParent to prevent stale entries
+      const existingTimer = this.completionTimers.get(task.id)
+      if (existingTimer) {
+        clearTimeout(existingTimer)
+        this.completionTimers.delete(task.id)
+      }
       this.cleanupPendingByParent(task)
       this.tasks.delete(task.id)
       this.clearNotificationsForTask(task.id)
@@ -1073,14 +1078,15 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
     }
 
     const taskId = task.id
-    setTimeout(() => {
-      // Guard: Only delete if task still exists (could have been deleted by session.deleted event)
+    const timer = setTimeout(() => {
+      this.completionTimers.delete(taskId)
       if (this.tasks.has(taskId)) {
         this.clearNotificationsForTask(taskId)
         this.tasks.delete(taskId)
         log("[background-agent] Removed completed task from memory:", taskId)
       }
     }, 5 * 60 * 1000)
+    this.completionTimers.set(taskId, timer)
   }
 
   private formatDuration(start: Date, end?: Date): string {
@@ -1375,7 +1381,11 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
       }
     }
 
-    // Then clear all state (cancels any remaining waiters)
+    for (const timer of this.completionTimers.values()) {
+      clearTimeout(timer)
+    }
+    this.completionTimers.clear()
+
     this.concurrencyManager.clear()
     this.tasks.clear()
     this.notifications.clear()
@@ -1396,7 +1406,10 @@ function registerProcessSignal(
   const listener = () => {
     handler()
     if (exitAfter) {
-      process.exit(0)
+      // Set exitCode and schedule exit after delay to allow other handlers to complete async cleanup
+      // Use 6s delay to accommodate LSP cleanup (5s timeout + 1s SIGKILL wait)
+      process.exitCode = 0
+      setTimeout(() => process.exit(), 6000)
     }
   }
   process.on(signal, listener)

src/features/builtin-commands/commands.ts

@@ -2,6 +2,7 @@ import type { CommandDefinition } from "../claude-code-command-loader"
 import type { BuiltinCommandName, BuiltinCommands } from "./types"
 import { INIT_DEEP_TEMPLATE } from "./templates/init-deep"
 import { RALPH_LOOP_TEMPLATE, CANCEL_RALPH_TEMPLATE } from "./templates/ralph-loop"
+import { STOP_CONTINUATION_TEMPLATE } from "./templates/stop-continuation"
 import { REFACTOR_TEMPLATE } from "./templates/refactor"
 import { START_WORK_TEMPLATE } from "./templates/start-work"
 
@@ -70,6 +71,12 @@ $ARGUMENTS
 </user-request>`,
     argumentHint: "[plan-name]",
   },
+  "stop-continuation": {
+    description: "(builtin) Stop all continuation mechanisms (ralph loop, todo continuation, boulder) for this session",
+    template: `<command-instruction>
+${STOP_CONTINUATION_TEMPLATE}
+</command-instruction>`,
+  },
 }
 
 export function loadBuiltinCommands(

src/features/builtin-commands/templates/stop-continuation.test.ts

@@ -0,0 +1,25 @@
+import { describe, expect, test } from "bun:test"
+import { STOP_CONTINUATION_TEMPLATE } from "./stop-continuation"
+
+describe("stop-continuation template", () => {
+  test("should export a non-empty template string", () => {
+    // #given - the stop-continuation template
+
+    // #when - we access the template
+
+    // #then - it should be a non-empty string
+    expect(typeof STOP_CONTINUATION_TEMPLATE).toBe("string")
+    expect(STOP_CONTINUATION_TEMPLATE.length).toBeGreaterThan(0)
+  })
+
+  test("should describe the stop-continuation behavior", () => {
+    // #given - the stop-continuation template
+
+    // #when - we check the content
+
+    // #then - it should mention key behaviors
+    expect(STOP_CONTINUATION_TEMPLATE).toContain("todo-continuation-enforcer")
+    expect(STOP_CONTINUATION_TEMPLATE).toContain("Ralph Loop")
+    expect(STOP_CONTINUATION_TEMPLATE).toContain("boulder state")
+  })
+})

src/features/builtin-commands/templates/stop-continuation.ts

@@ -0,0 +1,13 @@
+export const STOP_CONTINUATION_TEMPLATE = `Stop all continuation mechanisms for the current session.
+
+This command will:
+1. Stop the todo-continuation-enforcer from automatically continuing incomplete tasks
+2. Cancel any active Ralph Loop
+3. Clear the boulder state for the current project
+
+After running this command:
+- The session will not auto-continue when idle
+- You can manually continue work when ready
+- The stop state is per-session and clears when the session ends
+
+Use this when you need to pause automated continuation and take manual control.`

src/features/builtin-commands/types.ts

@@ -1,6 +1,6 @@
 import type { CommandDefinition } from "../claude-code-command-loader"
 
-export type BuiltinCommandName = "init-deep" | "ralph-loop" | "cancel-ralph" | "ulw-loop" | "refactor" | "start-work"
+export type BuiltinCommandName = "init-deep" | "ralph-loop" | "cancel-ralph" | "ulw-loop" | "refactor" | "start-work" | "stop-continuation"
 
 export interface BuiltinCommandConfig {
   disabled_commands?: BuiltinCommandName[]

src/features/skill-mcp-manager/manager.ts

@@ -114,23 +114,15 @@ export class SkillMcpManager {
       this.pendingConnections.clear()
     }
 
-    // Note: 'exit' event is synchronous-only in Node.js, so we use 'beforeExit' for async cleanup
-    // However, 'beforeExit' is not emitted on explicit process.exit() calls
-    // Signal handlers are made async to properly await cleanup
+    // Note: Node's 'exit' event is synchronous-only, so we rely on signal handlers for async cleanup.
+    // Signal handlers invoke the async cleanup function and ignore errors so they don't block or throw.
+    // Don't call process.exit() here - let the background-agent manager handle the final process exit.
+    // Use void + catch to trigger async cleanup without awaiting it in the signal handler.
 
-    process.on("SIGINT", async () => {
-      await cleanup()
-      process.exit(0)
-    })
-    process.on("SIGTERM", async () => {
-      await cleanup()
-      process.exit(0)
-    })
+    process.on("SIGINT", () => void cleanup().catch(() => {}))
+    process.on("SIGTERM", () => void cleanup().catch(() => {}))
     if (process.platform === "win32") {
-      process.on("SIGBREAK", async () => {
-        await cleanup()
-        process.exit(0)
-      })
+      process.on("SIGBREAK", () => void cleanup().catch(() => {}))
     }
   }
 

src/hooks/claude-code-hooks/index.ts

@@ -24,7 +24,7 @@ import {
   type PreCompactContext,
 } from "./pre-compact"
 import { cacheToolInput, getToolInput } from "./tool-input-cache"
-import { recordToolUse, recordToolResult, getTranscriptPath, recordUserMessage } from "./transcript"
+import { appendTranscriptEntry, getTranscriptPath } from "./transcript"
 import type { PluginConfig } from "./types"
 import { log, isHookDisabled } from "../../shared"
 import type { ContextCollector } from "../../features/context-injector"
@@ -92,7 +92,11 @@ export function createClaudeCodeHooksHook(
       const textParts = output.parts.filter((p) => p.type === "text" && p.text)
       const prompt = textParts.map((p) => p.text ?? "").join("\n")
 
-      recordUserMessage(input.sessionID, prompt)
+      appendTranscriptEntry(input.sessionID, {
+        type: "user",
+        timestamp: new Date().toISOString(),
+        content: prompt,
+      })
 
       const messageParts: MessagePart[] = textParts.map((p) => ({
         type: p.type as "text",
@@ -198,7 +202,12 @@ export function createClaudeCodeHooksHook(
       const claudeConfig = await loadClaudeHooksConfig()
       const extendedConfig = await loadPluginExtendedConfig()
 
-      recordToolUse(input.sessionID, input.tool, output.args as Record<string, unknown>)
+      appendTranscriptEntry(input.sessionID, {
+        type: "tool_use",
+        timestamp: new Date().toISOString(),
+        tool_name: input.tool,
+        tool_input: output.args as Record<string, unknown>,
+      })
 
       cacheToolInput(input.sessionID, input.tool, input.callID, output.args as Record<string, unknown>)
 
@@ -253,7 +262,13 @@ export function createClaudeCodeHooksHook(
       const metadata = output.metadata as Record<string, unknown> | undefined
       const hasMetadata = metadata && typeof metadata === "object" && Object.keys(metadata).length > 0
       const toolOutput = hasMetadata ? metadata : { output: output.output }
-      recordToolResult(input.sessionID, input.tool, cachedInput, toolOutput)
+      appendTranscriptEntry(input.sessionID, {
+        type: "tool_result",
+        timestamp: new Date().toISOString(),
+        tool_name: input.tool,
+        tool_input: cachedInput,
+        tool_output: toolOutput,
+      })
 
       if (!isHookDisabled(config, "PostToolUse")) {
         const postClient: PostToolUseClient = {

src/hooks/claude-code-hooks/transcript.ts

@@ -28,56 +28,6 @@ export function appendTranscriptEntry(
   appendFileSync(path, line)
 }
 
-export function recordToolUse(
-  sessionId: string,
-  toolName: string,
-  toolInput: Record<string, unknown>
-): void {
-  appendTranscriptEntry(sessionId, {
-    type: "tool_use",
-    timestamp: new Date().toISOString(),
-    tool_name: toolName,
-    tool_input: toolInput,
-  })
-}
-
-export function recordToolResult(
-  sessionId: string,
-  toolName: string,
-  toolInput: Record<string, unknown>,
-  toolOutput: Record<string, unknown>
-): void {
-  appendTranscriptEntry(sessionId, {
-    type: "tool_result",
-    timestamp: new Date().toISOString(),
-    tool_name: toolName,
-    tool_input: toolInput,
-    tool_output: toolOutput,
-  })
-}
-
-export function recordUserMessage(
-  sessionId: string,
-  content: string
-): void {
-  appendTranscriptEntry(sessionId, {
-    type: "user",
-    timestamp: new Date().toISOString(),
-    content,
-  })
-}
-
-export function recordAssistantMessage(
-  sessionId: string,
-  content: string
-): void {
-  appendTranscriptEntry(sessionId, {
-    type: "assistant",
-    timestamp: new Date().toISOString(),
-    content,
-  })
-}
-
 // ============================================================================
 // Claude Code Compatible Transcript Builder (PORT FROM DISABLED)
 // ============================================================================

src/hooks/comment-checker/downloader.ts

@@ -1,9 +1,16 @@
-import { spawn } from "bun"
-import { existsSync, mkdirSync, chmodSync, unlinkSync, appendFileSync } from "fs"
+import { existsSync, appendFileSync } from "fs"
 import { join } from "path"
 import { homedir, tmpdir } from "os"
 import { createRequire } from "module"
-import { extractZip } from "../../shared"
+import {
+  cleanupArchive,
+  downloadArchive,
+  ensureCacheDir,
+  ensureExecutable,
+  extractTarGz,
+  extractZipArchive,
+  getCachedBinaryPath as getCachedBinaryPathShared,
+} from "../../shared/binary-downloader"
 import { log } from "../../shared/logger"
 
 const DEBUG = process.env.COMMENT_CHECKER_DEBUG === "1"
@@ -60,8 +67,7 @@ export function getBinaryName(): string {
  * Get the cached binary path if it exists.
  */
 export function getCachedBinaryPath(): string | null {
-  const binaryPath = join(getCacheDir(), getBinaryName())
-  return existsSync(binaryPath) ? binaryPath : null
+  return getCachedBinaryPathShared(getCacheDir(), getBinaryName())
 }
 
 /**
@@ -78,27 +84,6 @@ function getPackageVersion(): string {
   }
 }
 
-/**
- * Extract tar.gz archive using system tar command.
- */
-async function extractTarGz(archivePath: string, destDir: string): Promise<void> {
-  debugLog("Extracting tar.gz:", archivePath, "to", destDir)
-  
-  const proc = spawn(["tar", "-xzf", archivePath, "-C", destDir], {
-    stdout: "pipe",
-    stderr: "pipe",
-  })
-  
-  const exitCode = await proc.exited
-  
-  if (exitCode !== 0) {
-    const stderr = await new Response(proc.stderr).text()
-    throw new Error(`tar extraction failed (exit ${exitCode}): ${stderr}`)
-  }
-}
-
-
-
 /**
  * Download the comment-checker binary from GitHub Releases.
  * Returns the path to the downloaded binary, or null on failure.
@@ -132,39 +117,26 @@ export async function downloadCommentChecker(): Promise<string | null> {
   
   try {
     // Ensure cache directory exists
-    if (!existsSync(cacheDir)) {
-      mkdirSync(cacheDir, { recursive: true })
-    }
-    
-    // Download with fetch() - Bun handles redirects automatically
-    const response = await fetch(downloadUrl, { redirect: "follow" })
-    
-    if (!response.ok) {
-      throw new Error(`HTTP ${response.status}: ${response.statusText}`)
-    }
+    ensureCacheDir(cacheDir)
     
     const archivePath = join(cacheDir, assetName)
-    const arrayBuffer = await response.arrayBuffer()
-    await Bun.write(archivePath, arrayBuffer)
+    await downloadArchive(downloadUrl, archivePath)
     
     debugLog(`Downloaded archive to: ${archivePath}`)
     
     // Extract based on file type
     if (ext === "tar.gz") {
+      debugLog("Extracting tar.gz:", archivePath, "to", cacheDir)
       await extractTarGz(archivePath, cacheDir)
     } else {
-      await extractZip(archivePath, cacheDir)
+      await extractZipArchive(archivePath, cacheDir)
     }
     
     // Clean up archive
-    if (existsSync(archivePath)) {
-      unlinkSync(archivePath)
-    }
+    cleanupArchive(archivePath)
     
     // Set execute permission on Unix
-    if (process.platform !== "win32" && existsSync(binaryPath)) {
-      chmodSync(binaryPath, 0o755)
-    }
+    ensureExecutable(binaryPath)
     
     debugLog(`Successfully downloaded binary to: ${binaryPath}`)
     log(`[oh-my-opencode] comment-checker binary ready.`)

src/hooks/compaction-context-injector/index.test.ts

@@ -1,102 +0,0 @@
-import { describe, expect, it, mock, beforeEach } from "bun:test"
-
-// Mock dependencies before importing
-const mockInjectHookMessage = mock(() => true)
-mock.module("../../features/hook-message-injector", () => ({
-  injectHookMessage: mockInjectHookMessage,
-}))
-
-mock.module("../../shared/logger", () => ({
-  log: () => {},
-}))
-
-mock.module("../../shared/system-directive", () => ({
-  createSystemDirective: (type: string) => `[DIRECTIVE:${type}]`,
-  SystemDirectiveTypes: {
-    TODO_CONTINUATION: "TODO CONTINUATION",
-    RALPH_LOOP: "RALPH LOOP",
-    BOULDER_CONTINUATION: "BOULDER CONTINUATION",
-    DELEGATION_REQUIRED: "DELEGATION REQUIRED",
-    SINGLE_TASK_ONLY: "SINGLE TASK ONLY",
-    COMPACTION_CONTEXT: "COMPACTION CONTEXT",
-    CONTEXT_WINDOW_MONITOR: "CONTEXT WINDOW MONITOR",
-    PROMETHEUS_READ_ONLY: "PROMETHEUS READ-ONLY",
-  },
-}))
-
-import { createCompactionContextInjector } from "./index"
-import type { SummarizeContext } from "./index"
-
-describe("createCompactionContextInjector", () => {
-  beforeEach(() => {
-    mockInjectHookMessage.mockClear()
-  })
-
-  describe("Agent Verification State preservation", () => {
-    it("includes Agent Verification State section in compaction prompt", async () => {
-      // given
-      const injector = createCompactionContextInjector()
-      const context: SummarizeContext = {
-        sessionID: "test-session",
-        providerID: "anthropic",
-        modelID: "claude-sonnet-4-5",
-        usageRatio: 0.85,
-        directory: "/test/dir",
-      }
-
-      // when
-      await injector(context)
-
-      // then
-      expect(mockInjectHookMessage).toHaveBeenCalledTimes(1)
-      const calls = mockInjectHookMessage.mock.calls as unknown as [string, string, unknown][]
-      const injectedPrompt = calls[0]?.[1] ?? ""
-      expect(injectedPrompt).toContain("Agent Verification State")
-      expect(injectedPrompt).toContain("Current Agent")
-      expect(injectedPrompt).toContain("Verification Progress")
-    })
-
-    it("includes Momus-specific context for reviewer agents", async () => {
-      // given
-      const injector = createCompactionContextInjector()
-      const context: SummarizeContext = {
-        sessionID: "test-session",
-        providerID: "anthropic",
-        modelID: "claude-sonnet-4-5",
-        usageRatio: 0.9,
-        directory: "/test/dir",
-      }
-
-      // when
-      await injector(context)
-
-      // then
-      const calls = mockInjectHookMessage.mock.calls as unknown as [string, string, unknown][]
-      const injectedPrompt = calls[0]?.[1] ?? ""
-      expect(injectedPrompt).toContain("Previous Rejections")
-      expect(injectedPrompt).toContain("Acceptance Status")
-      expect(injectedPrompt).toContain("reviewer agents")
-    })
-
-    it("preserves file verification progress in compaction prompt", async () => {
-      // given
-      const injector = createCompactionContextInjector()
-      const context: SummarizeContext = {
-        sessionID: "test-session",
-        providerID: "anthropic",
-        modelID: "claude-sonnet-4-5",
-        usageRatio: 0.95,
-        directory: "/test/dir",
-      }
-
-      // when
-      await injector(context)
-
-      // then
-      const calls = mockInjectHookMessage.mock.calls as unknown as [string, string, unknown][]
-      const injectedPrompt = calls[0]?.[1] ?? ""
-      expect(injectedPrompt).toContain("Pending Verifications")
-      expect(injectedPrompt).toContain("Files already verified")
-    })
-  })
-})

src/hooks/compaction-context-injector/index.ts

@@ -1,76 +0,0 @@
-import { injectHookMessage } from "../../features/hook-message-injector"
-import { log } from "../../shared/logger"
-import { createSystemDirective, SystemDirectiveTypes } from "../../shared/system-directive"
-
-export interface SummarizeContext {
-  sessionID: string
-  providerID: string
-  modelID: string
-  usageRatio: number
-  directory: string
-}
-
-const SUMMARIZE_CONTEXT_PROMPT = `${createSystemDirective(SystemDirectiveTypes.COMPACTION_CONTEXT)}
-
-When summarizing this session, you MUST include the following sections in your summary:
-
-## 1. User Requests (As-Is)
-- List all original user requests exactly as they were stated
-- Preserve the user's exact wording and intent
-
-## 2. Final Goal
-- What the user ultimately wanted to achieve
-- The end result or deliverable expected
-
-## 3. Work Completed
-- What has been done so far
-- Files created/modified
-- Features implemented
-- Problems solved
-
-## 4. Remaining Tasks
-- What still needs to be done
-- Pending items from the original request
-- Follow-up tasks identified during the work
-
-## 5. Active Working Context (For Seamless Continuation)
-- **Files**: Paths of files currently being edited or frequently referenced
-- **Code in Progress**: Key code snippets, function signatures, or data structures under active development
-- **External References**: Documentation URLs, library APIs, or external resources being consulted
-- **State & Variables**: Important variable names, configuration values, or runtime state relevant to ongoing work
-
-## 6. MUST NOT Do (Critical Constraints)
-- Things that were explicitly forbidden
-- Approaches that failed and should not be retried
-- User's explicit restrictions or preferences
-- Anti-patterns identified during the session
-
-## 7. Agent Verification State (Critical for Reviewers)
-- **Current Agent**: What agent is running (momus, oracle, etc.)
-- **Verification Progress**: Files already verified/validated
-- **Pending Verifications**: Files still needing verification
-- **Previous Rejections**: If reviewer agent, what was rejected and why
-- **Acceptance Status**: Current state of review process
-
-This section is CRITICAL for reviewer agents (momus, oracle) to maintain continuity.
-
-This context is critical for maintaining continuity after compaction.
-`
-
-export function createCompactionContextInjector() {
-  return async (ctx: SummarizeContext): Promise<void> => {
-    log("[compaction-context-injector] injecting context", { sessionID: ctx.sessionID })
-
-    const success = injectHookMessage(ctx.sessionID, SUMMARIZE_CONTEXT_PROMPT, {
-      agent: "general",
-      model: { providerID: ctx.providerID, modelID: ctx.modelID },
-      path: { cwd: ctx.directory },
-    })
-
-    if (success) {
-      log("[compaction-context-injector] context injected", { sessionID: ctx.sessionID })
-    } else {
-      log("[compaction-context-injector] injection failed", { sessionID: ctx.sessionID })
-    }
-  }
-}

src/hooks/directory-agents-injector/index.ts

@@ -25,11 +25,6 @@ interface ToolExecuteBeforeOutput {
   args: unknown;
 }
 
-interface BatchToolCall {
-  tool: string;
-  parameters: Record<string, unknown>;
-}
-
 interface EventInput {
   event: {
     type: string;
@@ -39,7 +34,6 @@ interface EventInput {
 
 export function createDirectoryAgentsInjectorHook(ctx: PluginInput) {
   const sessionCaches = new Map<string, Set<string>>();
-  const pendingBatchReads = new Map<string, string[]>();
   const truncator = createDynamicTruncator(ctx);
 
   function getSessionCache(sessionID: string): Set<string> {
@@ -110,27 +104,6 @@ export function createDirectoryAgentsInjectorHook(ctx: PluginInput) {
     saveInjectedPaths(sessionID, cache);
   }
 
-  const toolExecuteBefore = async (
-    input: ToolExecuteInput,
-    output: ToolExecuteBeforeOutput,
-  ) => {
-    if (input.tool.toLowerCase() !== "batch") return;
-
-    const args = output.args as { tool_calls?: BatchToolCall[] } | undefined;
-    if (!args?.tool_calls) return;
-
-    const readFilePaths: string[] = [];
-    for (const call of args.tool_calls) {
-      if (call.tool.toLowerCase() === "read" && call.parameters?.filePath) {
-        readFilePaths.push(call.parameters.filePath as string);
-      }
-    }
-
-    if (readFilePaths.length > 0) {
-      pendingBatchReads.set(input.callID, readFilePaths);
-    }
-  };
-
   const toolExecuteAfter = async (
     input: ToolExecuteInput,
     output: ToolExecuteOutput,
@@ -141,16 +114,14 @@ export function createDirectoryAgentsInjectorHook(ctx: PluginInput) {
       await processFilePathForInjection(output.title, input.sessionID, output);
       return;
     }
+  };
 
-    if (toolName === "batch") {
-      const filePaths = pendingBatchReads.get(input.callID);
-      if (filePaths) {
-        for (const filePath of filePaths) {
-          await processFilePathForInjection(filePath, input.sessionID, output);
-        }
-        pendingBatchReads.delete(input.callID);
-      }
-    }
+  const toolExecuteBefore = async (
+    input: ToolExecuteInput,
+    output: ToolExecuteBeforeOutput,
+  ): Promise<void> => {
+    void input;
+    void output;
   };
 
   const eventHandler = async ({ event }: EventInput) => {

src/hooks/directory-agents-injector/storage.ts

@@ -1,48 +1,8 @@
-import {
-  existsSync,
-  mkdirSync,
-  readFileSync,
-  writeFileSync,
-  unlinkSync,
-} from "node:fs";
-import { join } from "node:path";
 import { AGENTS_INJECTOR_STORAGE } from "./constants";
-import type { InjectedPathsData } from "./types";
+import { createInjectedPathsStorage } from "../../shared/session-injected-paths";
 
-function getStoragePath(sessionID: string): string {
-  return join(AGENTS_INJECTOR_STORAGE, `${sessionID}.json`);
-}
-
-export function loadInjectedPaths(sessionID: string): Set<string> {
-  const filePath = getStoragePath(sessionID);
-  if (!existsSync(filePath)) return new Set();
-
-  try {
-    const content = readFileSync(filePath, "utf-8");
-    const data: InjectedPathsData = JSON.parse(content);
-    return new Set(data.injectedPaths);
-  } catch {
-    return new Set();
-  }
-}
-
-export function saveInjectedPaths(sessionID: string, paths: Set<string>): void {
-  if (!existsSync(AGENTS_INJECTOR_STORAGE)) {
-    mkdirSync(AGENTS_INJECTOR_STORAGE, { recursive: true });
-  }
-
-  const data: InjectedPathsData = {
-    sessionID,
-    injectedPaths: [...paths],
-    updatedAt: Date.now(),
-  };
-
-  writeFileSync(getStoragePath(sessionID), JSON.stringify(data, null, 2));
-}
-
-export function clearInjectedPaths(sessionID: string): void {
-  const filePath = getStoragePath(sessionID);
-  if (existsSync(filePath)) {
-    unlinkSync(filePath);
-  }
-}
+export const {
+  loadInjectedPaths,
+  saveInjectedPaths,
+  clearInjectedPaths,
+} = createInjectedPathsStorage(AGENTS_INJECTOR_STORAGE);

src/hooks/directory-agents-injector/types.ts

@@ -1,5 +0,0 @@
-export interface InjectedPathsData {
-  sessionID: string;
-  injectedPaths: string[];
-  updatedAt: number;
-}

src/hooks/directory-readme-injector/index.ts

@@ -25,11 +25,6 @@ interface ToolExecuteBeforeOutput {
   args: unknown;
 }
 
-interface BatchToolCall {
-  tool: string;
-  parameters: Record<string, unknown>;
-}
-
 interface EventInput {
   event: {
     type: string;
@@ -39,7 +34,6 @@ interface EventInput {
 
 export function createDirectoryReadmeInjectorHook(ctx: PluginInput) {
   const sessionCaches = new Map<string, Set<string>>();
-  const pendingBatchReads = new Map<string, string[]>();
   const truncator = createDynamicTruncator(ctx);
 
   function getSessionCache(sessionID: string): Set<string> {
@@ -105,27 +99,6 @@ export function createDirectoryReadmeInjectorHook(ctx: PluginInput) {
     saveInjectedPaths(sessionID, cache);
   }
 
-  const toolExecuteBefore = async (
-    input: ToolExecuteInput,
-    output: ToolExecuteBeforeOutput,
-  ) => {
-    if (input.tool.toLowerCase() !== "batch") return;
-
-    const args = output.args as { tool_calls?: BatchToolCall[] } | undefined;
-    if (!args?.tool_calls) return;
-
-    const readFilePaths: string[] = [];
-    for (const call of args.tool_calls) {
-      if (call.tool.toLowerCase() === "read" && call.parameters?.filePath) {
-        readFilePaths.push(call.parameters.filePath as string);
-      }
-    }
-
-    if (readFilePaths.length > 0) {
-      pendingBatchReads.set(input.callID, readFilePaths);
-    }
-  };
-
   const toolExecuteAfter = async (
     input: ToolExecuteInput,
     output: ToolExecuteOutput,
@@ -136,16 +109,14 @@ export function createDirectoryReadmeInjectorHook(ctx: PluginInput) {
       await processFilePathForInjection(output.title, input.sessionID, output);
       return;
     }
+  };
 
-    if (toolName === "batch") {
-      const filePaths = pendingBatchReads.get(input.callID);
-      if (filePaths) {
-        for (const filePath of filePaths) {
-          await processFilePathForInjection(filePath, input.sessionID, output);
-        }
-        pendingBatchReads.delete(input.callID);
-      }
-    }
+  const toolExecuteBefore = async (
+    input: ToolExecuteInput,
+    output: ToolExecuteBeforeOutput,
+  ): Promise<void> => {
+    void input;
+    void output;
   };
 
   const eventHandler = async ({ event }: EventInput) => {

src/hooks/directory-readme-injector/storage.ts

@@ -1,48 +1,8 @@
-import {
-  existsSync,
-  mkdirSync,
-  readFileSync,
-  writeFileSync,
-  unlinkSync,
-} from "node:fs";
-import { join } from "node:path";
 import { README_INJECTOR_STORAGE } from "./constants";
-import type { InjectedPathsData } from "./types";
+import { createInjectedPathsStorage } from "../../shared/session-injected-paths";
 
-function getStoragePath(sessionID: string): string {
-  return join(README_INJECTOR_STORAGE, `${sessionID}.json`);
-}
-
-export function loadInjectedPaths(sessionID: string): Set<string> {
-  const filePath = getStoragePath(sessionID);
-  if (!existsSync(filePath)) return new Set();
-
-  try {
-    const content = readFileSync(filePath, "utf-8");
-    const data: InjectedPathsData = JSON.parse(content);
-    return new Set(data.injectedPaths);
-  } catch {
-    return new Set();
-  }
-}
-
-export function saveInjectedPaths(sessionID: string, paths: Set<string>): void {
-  if (!existsSync(README_INJECTOR_STORAGE)) {
-    mkdirSync(README_INJECTOR_STORAGE, { recursive: true });
-  }
-
-  const data: InjectedPathsData = {
-    sessionID,
-    injectedPaths: [...paths],
-    updatedAt: Date.now(),
-  };
-
-  writeFileSync(getStoragePath(sessionID), JSON.stringify(data, null, 2));
-}
-
-export function clearInjectedPaths(sessionID: string): void {
-  const filePath = getStoragePath(sessionID);
-  if (existsSync(filePath)) {
-    unlinkSync(filePath);
-  }
-}
+export const {
+  loadInjectedPaths,
+  saveInjectedPaths,
+  clearInjectedPaths,
+} = createInjectedPathsStorage(README_INJECTOR_STORAGE);

src/hooks/directory-readme-injector/types.ts

@@ -1,5 +0,0 @@
-export interface InjectedPathsData {
-  sessionID: string;
-  injectedPaths: string[];
-  updatedAt: number;
-}

src/hooks/index.ts

@@ -9,7 +9,6 @@ export { createDirectoryReadmeInjectorHook } from "./directory-readme-injector";
 export { createEmptyTaskResponseDetectorHook } from "./empty-task-response-detector";
 export { createAnthropicContextWindowLimitRecoveryHook, type AnthropicContextWindowLimitRecoveryOptions } from "./anthropic-context-window-limit-recovery";
 
-export { createCompactionContextInjector } from "./compaction-context-injector";
 export { createThinkModeHook } from "./think-mode";
 export { createClaudeCodeHooksHook } from "./claude-code-hooks";
 export { createRulesInjectorHook } from "./rules-injector";
@@ -34,3 +33,4 @@ export { createAtlasHook } from "./atlas";
 export { createDelegateTaskRetryHook } from "./delegate-task-retry";
 export { createQuestionLabelTruncatorHook } from "./question-label-truncator";
 export { createSubagentQuestionBlockerHook } from "./subagent-question-blocker";
+export { createStopContinuationGuardHook, type StopContinuationGuard } from "./stop-continuation-guard";

src/hooks/keyword-detector/index.test.ts

@@ -21,6 +21,7 @@ describe("keyword-detector message transform", () => {
   afterEach(() => {
     logSpy?.mockRestore()
     getMainSessionSpy?.mockRestore()
+    _resetForTesting()
   })
 
   function createMockPluginInput() {
@@ -101,7 +102,7 @@ describe("keyword-detector session filtering", () => {
   let logSpy: ReturnType<typeof spyOn>
 
   beforeEach(() => {
-    setMainSession(undefined)
+    _resetForTesting()
     logCalls = []
     logSpy = spyOn(sharedModule, "log").mockImplementation((msg: string, data?: unknown) => {
       logCalls.push({ msg, data })
@@ -110,7 +111,7 @@ describe("keyword-detector session filtering", () => {
 
   afterEach(() => {
     logSpy?.mockRestore()
-    setMainSession(undefined)
+    _resetForTesting()
   })
 
   function createMockPluginInput(options: { toastCalls?: string[] } = {}) {
@@ -246,7 +247,7 @@ describe("keyword-detector word boundary", () => {
   let logSpy: ReturnType<typeof spyOn>
 
   beforeEach(() => {
-    setMainSession(undefined)
+    _resetForTesting()
     logCalls = []
     logSpy = spyOn(sharedModule, "log").mockImplementation((msg: string, data?: unknown) => {
       logCalls.push({ msg, data })
@@ -255,7 +256,7 @@ describe("keyword-detector word boundary", () => {
 
   afterEach(() => {
     logSpy?.mockRestore()
-    setMainSession(undefined)
+    _resetForTesting()
   })
 
   function createMockPluginInput(options: { toastCalls?: string[] } = {}) {
@@ -343,7 +344,7 @@ describe("keyword-detector system-reminder filtering", () => {
   let logSpy: ReturnType<typeof spyOn>
 
   beforeEach(() => {
-    setMainSession(undefined)
+    _resetForTesting()
     logCalls = []
     logSpy = spyOn(sharedModule, "log").mockImplementation((msg: string, data?: unknown) => {
       logCalls.push({ msg, data })
@@ -352,7 +353,7 @@ describe("keyword-detector system-reminder filtering", () => {
 
   afterEach(() => {
     logSpy?.mockRestore()
-    setMainSession(undefined)
+    _resetForTesting()
   })
 
   function createMockPluginInput() {
@@ -534,7 +535,7 @@ describe("keyword-detector agent-specific ultrawork messages", () => {
   let logSpy: ReturnType<typeof spyOn>
 
   beforeEach(() => {
-    setMainSession(undefined)
+    _resetForTesting()
     logCalls = []
     logSpy = spyOn(sharedModule, "log").mockImplementation((msg: string, data?: unknown) => {
       logCalls.push({ msg, data })
@@ -543,7 +544,7 @@ describe("keyword-detector agent-specific ultrawork messages", () => {
 
   afterEach(() => {
     logSpy?.mockRestore()
-    setMainSession(undefined)
+    _resetForTesting()
   })
 
   function createMockPluginInput() {

src/hooks/rules-injector/constants.ts

@@ -17,6 +17,7 @@ export const PROJECT_RULE_SUBDIRS: [string, string][] = [
   [".github", "instructions"],
   [".cursor", "rules"],
   [".claude", "rules"],
+  [".sisyphus", "rules"],
 ];
 
 export const PROJECT_RULE_FILES: string[] = [

src/hooks/rules-injector/index.ts

@@ -33,11 +33,6 @@ interface ToolExecuteBeforeOutput {
   args: unknown;
 }
 
-interface BatchToolCall {
-  tool: string;
-  parameters: Record<string, unknown>;
-}
-
 interface EventInput {
   event: {
     type: string;
@@ -59,7 +54,6 @@ export function createRulesInjectorHook(ctx: PluginInput) {
     string,
     { contentHashes: Set<string>; realPaths: Set<string> }
   >();
-  const pendingBatchFiles = new Map<string, string[]>();
   const truncator = createDynamicTruncator(ctx);
 
   function getSessionCache(sessionID: string): {
@@ -143,35 +137,6 @@ export function createRulesInjectorHook(ctx: PluginInput) {
     saveInjectedRules(sessionID, cache);
   }
 
-  function extractFilePathFromToolCall(call: BatchToolCall): string | null {
-    const params = call.parameters;
-    return (params?.filePath ?? params?.file_path ?? params?.path) as string | null;
-  }
-
-  const toolExecuteBefore = async (
-    input: ToolExecuteInput,
-    output: ToolExecuteBeforeOutput
-  ) => {
-    if (input.tool.toLowerCase() !== "batch") return;
-
-    const args = output.args as { tool_calls?: BatchToolCall[] } | undefined;
-    if (!args?.tool_calls) return;
-
-    const filePaths: string[] = [];
-    for (const call of args.tool_calls) {
-      if (TRACKED_TOOLS.includes(call.tool.toLowerCase())) {
-        const filePath = extractFilePathFromToolCall(call);
-        if (filePath) {
-          filePaths.push(filePath);
-        }
-      }
-    }
-
-    if (filePaths.length > 0) {
-      pendingBatchFiles.set(input.callID, filePaths);
-    }
-  };
-
   const toolExecuteAfter = async (
     input: ToolExecuteInput,
     output: ToolExecuteOutput
@@ -182,16 +147,14 @@ export function createRulesInjectorHook(ctx: PluginInput) {
       await processFilePathForInjection(output.title, input.sessionID, output);
       return;
     }
+  };
 
-    if (toolName === "batch") {
-      const filePaths = pendingBatchFiles.get(input.callID);
-      if (filePaths) {
-        for (const filePath of filePaths) {
-          await processFilePathForInjection(filePath, input.sessionID, output);
-        }
-        pendingBatchFiles.delete(input.callID);
-      }
-    }
+  const toolExecuteBefore = async (
+    input: ToolExecuteInput,
+    output: ToolExecuteBeforeOutput
+  ): Promise<void> => {
+    void input;
+    void output;
   };
 
   const eventHandler = async ({ event }: EventInput) => {

src/hooks/session-notification-utils.ts

@@ -2,24 +2,6 @@ import { spawn } from "bun"
 
 type Platform = "darwin" | "linux" | "win32" | "unsupported"
 
-let notifySendPath: string | null = null
-let notifySendPromise: Promise<string | null> | null = null
-
-let osascriptPath: string | null = null
-let osascriptPromise: Promise<string | null> | null = null
-
-let powershellPath: string | null = null
-let powershellPromise: Promise<string | null> | null = null
-
-let afplayPath: string | null = null
-let afplayPromise: Promise<string | null> | null = null
-
-let paplayPath: string | null = null
-let paplayPromise: Promise<string | null> | null = null
-
-let aplayPath: string | null = null
-let aplayPromise: Promise<string | null> | null = null
-
 async function findCommand(commandName: string): Promise<string | null> {
   const isWindows = process.platform === "win32"
   const cmd = isWindows ? "where" : "which"
@@ -48,83 +30,30 @@ async function findCommand(commandName: string): Promise<string | null> {
   }
 }
 
-export async function getNotifySendPath(): Promise<string | null> {
-  if (notifySendPath !== null) return notifySendPath
-  if (notifySendPromise) return notifySendPromise
+function createCommandFinder(commandName: string): () => Promise<string | null> {
+  let cachedPath: string | null = null
+  let pending: Promise<string | null> | null = null
 
-  notifySendPromise = (async () => {
-    const path = await findCommand("notify-send")
-    notifySendPath = path
-    return path
-  })()
+  return async () => {
+    if (cachedPath !== null) return cachedPath
+    if (pending) return pending
 
-  return notifySendPromise
+    pending = (async () => {
+      const path = await findCommand(commandName)
+      cachedPath = path
+      return path
+    })()
+
+    return pending
+  }
 }
 
-export async function getOsascriptPath(): Promise<string | null> {
-  if (osascriptPath !== null) return osascriptPath
-  if (osascriptPromise) return osascriptPromise
-
-  osascriptPromise = (async () => {
-    const path = await findCommand("osascript")
-    osascriptPath = path
-    return path
-  })()
-
-  return osascriptPromise
-}
-
-export async function getPowershellPath(): Promise<string | null> {
-  if (powershellPath !== null) return powershellPath
-  if (powershellPromise) return powershellPromise
-
-  powershellPromise = (async () => {
-    const path = await findCommand("powershell")
-    powershellPath = path
-    return path
-  })()
-
-  return powershellPromise
-}
-
-export async function getAfplayPath(): Promise<string | null> {
-  if (afplayPath !== null) return afplayPath
-  if (afplayPromise) return afplayPromise
-
-  afplayPromise = (async () => {
-    const path = await findCommand("afplay")
-    afplayPath = path
-    return path
-  })()
-
-  return afplayPromise
-}
-
-export async function getPaplayPath(): Promise<string | null> {
-  if (paplayPath !== null) return paplayPath
-  if (paplayPromise) return paplayPromise
-
-  paplayPromise = (async () => {
-    const path = await findCommand("paplay")
-    paplayPath = path
-    return path
-  })()
-
-  return paplayPromise
-}
-
-export async function getAplayPath(): Promise<string | null> {
-  if (aplayPath !== null) return aplayPath
-  if (aplayPromise) return aplayPromise
-
-  aplayPromise = (async () => {
-    const path = await findCommand("aplay")
-    aplayPath = path
-    return path
-  })()
-
-  return aplayPromise
-}
+export const getNotifySendPath = createCommandFinder("notify-send")
+export const getOsascriptPath = createCommandFinder("osascript")
+export const getPowershellPath = createCommandFinder("powershell")
+export const getAfplayPath = createCommandFinder("afplay")
+export const getPaplayPath = createCommandFinder("paplay")
+export const getAplayPath = createCommandFinder("aplay")
 
 export function startBackgroundCheck(platform: Platform): void {
   if (platform === "darwin") {

src/hooks/session-notification.test.ts

@@ -45,7 +45,7 @@ describe("session-notification", () => {
   afterEach(() => {
     // #given - cleanup after each test
     subagentSessions.clear()
-    setMainSession(undefined)
+    _resetForTesting()
   })
 
   test("should not trigger notification for subagent session", async () => {

src/hooks/start-work/index.ts

@@ -71,10 +71,7 @@ export function createStartWorkHook(ctx: PluginInput) {
         sessionID: input.sessionID,
       })
 
-      const currentAgent = getSessionAgent(input.sessionID)
-      if (!currentAgent) {
-        updateSessionAgent(input.sessionID, "atlas")
-      }
+      updateSessionAgent(input.sessionID, "atlas") // Always switch: fixes #1298
 
       const existingState = readBoulderState(ctx.directory)
       const sessionId = input.sessionID

src/hooks/stop-continuation-guard/index.test.ts

@@ -0,0 +1,144 @@
+import { describe, expect, test } from "bun:test"
+import { createStopContinuationGuardHook } from "./index"
+
+describe("stop-continuation-guard", () => {
+  function createMockPluginInput() {
+    return {
+      client: {
+        tui: {
+          showToast: async () => ({}),
+        },
+      },
+      directory: "/tmp/test",
+    } as never
+  }
+
+  test("should mark session as stopped", () => {
+    // #given - a guard hook with no stopped sessions
+    const guard = createStopContinuationGuardHook(createMockPluginInput())
+    const sessionID = "test-session-1"
+
+    // #when - we stop continuation for the session
+    guard.stop(sessionID)
+
+    // #then - session should be marked as stopped
+    expect(guard.isStopped(sessionID)).toBe(true)
+  })
+
+  test("should return false for non-stopped sessions", () => {
+    // #given - a guard hook with no stopped sessions
+    const guard = createStopContinuationGuardHook(createMockPluginInput())
+
+    // #when - we check a session that was never stopped
+
+    // #then - it should return false
+    expect(guard.isStopped("non-existent-session")).toBe(false)
+  })
+
+  test("should clear stopped state for a session", () => {
+    // #given - a session that was stopped
+    const guard = createStopContinuationGuardHook(createMockPluginInput())
+    const sessionID = "test-session-2"
+    guard.stop(sessionID)
+
+    // #when - we clear the session
+    guard.clear(sessionID)
+
+    // #then - session should no longer be stopped
+    expect(guard.isStopped(sessionID)).toBe(false)
+  })
+
+  test("should handle multiple sessions independently", () => {
+    // #given - multiple sessions with different stop states
+    const guard = createStopContinuationGuardHook(createMockPluginInput())
+    const session1 = "session-1"
+    const session2 = "session-2"
+    const session3 = "session-3"
+
+    // #when - we stop some sessions but not others
+    guard.stop(session1)
+    guard.stop(session2)
+
+    // #then - each session has its own state
+    expect(guard.isStopped(session1)).toBe(true)
+    expect(guard.isStopped(session2)).toBe(true)
+    expect(guard.isStopped(session3)).toBe(false)
+  })
+
+  test("should clear session on session.deleted event", async () => {
+    // #given - a session that was stopped
+    const guard = createStopContinuationGuardHook(createMockPluginInput())
+    const sessionID = "test-session-3"
+    guard.stop(sessionID)
+
+    // #when - session is deleted
+    await guard.event({
+      event: {
+        type: "session.deleted",
+        properties: { info: { id: sessionID } },
+      },
+    })
+
+    // #then - session should no longer be stopped (cleaned up)
+    expect(guard.isStopped(sessionID)).toBe(false)
+  })
+
+  test("should not affect other sessions on session.deleted", async () => {
+    // #given - multiple stopped sessions
+    const guard = createStopContinuationGuardHook(createMockPluginInput())
+    const session1 = "session-keep"
+    const session2 = "session-delete"
+    guard.stop(session1)
+    guard.stop(session2)
+
+    // #when - one session is deleted
+    await guard.event({
+      event: {
+        type: "session.deleted",
+        properties: { info: { id: session2 } },
+      },
+    })
+
+    // #then - other session should remain stopped
+    expect(guard.isStopped(session1)).toBe(true)
+    expect(guard.isStopped(session2)).toBe(false)
+  })
+
+  test("should clear stopped state on new user message (chat.message)", async () => {
+    // #given - a session that was stopped
+    const guard = createStopContinuationGuardHook(createMockPluginInput())
+    const sessionID = "test-session-4"
+    guard.stop(sessionID)
+    expect(guard.isStopped(sessionID)).toBe(true)
+
+    // #when - user sends a new message
+    await guard["chat.message"]({ sessionID })
+
+    // #then - stop state should be cleared (one-time only)
+    expect(guard.isStopped(sessionID)).toBe(false)
+  })
+
+  test("should not affect non-stopped sessions on chat.message", async () => {
+    // #given - a session that was never stopped
+    const guard = createStopContinuationGuardHook(createMockPluginInput())
+    const sessionID = "test-session-5"
+
+    // #when - user sends a message (session was never stopped)
+    await guard["chat.message"]({ sessionID })
+
+    // #then - should not throw and session remains not stopped
+    expect(guard.isStopped(sessionID)).toBe(false)
+  })
+
+  test("should handle undefined sessionID in chat.message", async () => {
+    // #given - a guard with a stopped session
+    const guard = createStopContinuationGuardHook(createMockPluginInput())
+    guard.stop("some-session")
+
+    // #when - chat.message is called without sessionID
+    await guard["chat.message"]({ sessionID: undefined })
+
+    // #then - should not throw and stopped session remains stopped
+    expect(guard.isStopped("some-session")).toBe(true)
+  })
+})

src/hooks/stop-continuation-guard/index.ts

@@ -0,0 +1,67 @@
+import type { PluginInput } from "@opencode-ai/plugin"
+import { log } from "../../shared/logger"
+
+const HOOK_NAME = "stop-continuation-guard"
+
+export interface StopContinuationGuard {
+  event: (input: { event: { type: string; properties?: unknown } }) => Promise<void>
+  "chat.message": (input: { sessionID?: string }) => Promise<void>
+  stop: (sessionID: string) => void
+  isStopped: (sessionID: string) => boolean
+  clear: (sessionID: string) => void
+}
+
+export function createStopContinuationGuardHook(
+  _ctx: PluginInput
+): StopContinuationGuard {
+  const stoppedSessions = new Set<string>()
+
+  const stop = (sessionID: string): void => {
+    stoppedSessions.add(sessionID)
+    log(`[${HOOK_NAME}] Continuation stopped for session`, { sessionID })
+  }
+
+  const isStopped = (sessionID: string): boolean => {
+    return stoppedSessions.has(sessionID)
+  }
+
+  const clear = (sessionID: string): void => {
+    stoppedSessions.delete(sessionID)
+    log(`[${HOOK_NAME}] Continuation guard cleared for session`, { sessionID })
+  }
+
+  const event = async ({
+    event,
+  }: {
+    event: { type: string; properties?: unknown }
+  }): Promise<void> => {
+    const props = event.properties as Record<string, unknown> | undefined
+
+    if (event.type === "session.deleted") {
+      const sessionInfo = props?.info as { id?: string } | undefined
+      if (sessionInfo?.id) {
+        clear(sessionInfo.id)
+        log(`[${HOOK_NAME}] Session deleted: cleaned up`, { sessionID: sessionInfo.id })
+      }
+    }
+  }
+
+  const chatMessage = async ({
+    sessionID,
+  }: {
+    sessionID?: string
+  }): Promise<void> => {
+    if (sessionID && stoppedSessions.has(sessionID)) {
+      clear(sessionID)
+      log(`[${HOOK_NAME}] Cleared stop state on new user message`, { sessionID })
+    }
+  }
+
+  return {
+    event,
+    "chat.message": chatMessage,
+    stop,
+    isStopped,
+    clear,
+  }
+}

src/hooks/think-mode/switcher.test.ts

@@ -458,4 +458,71 @@ describe("think-mode switcher", () => {
       })
     })
   })
+
+  describe("Z.AI GLM-4.7 provider support", () => {
+    describe("getThinkingConfig for zai-coding-plan", () => {
+      it("should return thinking config for glm-4.7", () => {
+        // #given zai-coding-plan provider with glm-4.7 model
+        const config = getThinkingConfig("zai-coding-plan", "glm-4.7")
+
+        // #then should return zai-coding-plan thinking config
+        expect(config).not.toBeNull()
+        expect(config?.providerOptions).toBeDefined()
+        const zaiOptions = (config?.providerOptions as Record<string, unknown>)?.[
+          "zai-coding-plan"
+        ] as Record<string, unknown>
+        expect(zaiOptions?.extra_body).toBeDefined()
+        const extraBody = zaiOptions?.extra_body as Record<string, unknown>
+        expect(extraBody?.thinking).toBeDefined()
+        expect((extraBody?.thinking as Record<string, unknown>)?.type).toBe("enabled")
+        expect((extraBody?.thinking as Record<string, unknown>)?.clear_thinking).toBe(false)
+      })
+
+      it("should return thinking config for glm-4.6v (multimodal)", () => {
+        // #given zai-coding-plan provider with glm-4.6v model
+        const config = getThinkingConfig("zai-coding-plan", "glm-4.6v")
+
+        // #then should return zai-coding-plan thinking config
+        expect(config).not.toBeNull()
+        expect(config?.providerOptions).toBeDefined()
+      })
+
+      it("should return null for non-GLM models on zai-coding-plan", () => {
+        // #given zai-coding-plan provider with unknown model
+        const config = getThinkingConfig("zai-coding-plan", "some-other-model")
+
+        // #then should return null
+        expect(config).toBeNull()
+      })
+    })
+
+    describe("HIGH_VARIANT_MAP for GLM", () => {
+      it("should NOT have high variant for glm-4.7 (thinking enabled by default)", () => {
+        // #given glm-4.7 model
+        const variant = getHighVariant("glm-4.7")
+
+        // #then should return null (no high variant needed)
+        expect(variant).toBeNull()
+      })
+
+      it("should NOT have high variant for glm-4.6v", () => {
+        // #given glm-4.6v model
+        const variant = getHighVariant("glm-4.6v")
+
+        // #then should return null
+        expect(variant).toBeNull()
+      })
+    })
+  })
+
+  describe("THINKING_CONFIGS structure for zai-coding-plan", () => {
+    it("should have correct structure for zai-coding-plan", () => {
+      const config = THINKING_CONFIGS["zai-coding-plan"]
+      expect(config.providerOptions).toBeDefined()
+      const zaiOptions = (config.providerOptions as Record<string, unknown>)?.[
+        "zai-coding-plan"
+      ] as Record<string, unknown>
+      expect(zaiOptions?.extra_body).toBeDefined()
+    })
+  })
 })

src/hooks/think-mode/switcher.ts

@@ -149,6 +149,18 @@ export const THINKING_CONFIGS = {
   openai: {
     reasoning_effort: "high",
   },
+  "zai-coding-plan": {
+    providerOptions: {
+      "zai-coding-plan": {
+        extra_body: {
+          thinking: {
+            type: "enabled",
+            clear_thinking: false,
+          },
+        },
+      },
+    },
+  },
 } as const satisfies Record<string, Record<string, unknown>>
 
 const THINKING_CAPABLE_MODELS = {
@@ -157,6 +169,7 @@ const THINKING_CAPABLE_MODELS = {
   google: ["gemini-2", "gemini-3"],
   "google-vertex": ["gemini-2", "gemini-3"],
   openai: ["gpt-5", "o1", "o3"],
+  "zai-coding-plan": ["glm"],
 } as const satisfies Record<string, readonly string[]>
 
 export function getHighVariant(modelID: string): string | null {

src/hooks/todo-continuation-enforcer.test.ts

@@ -1178,4 +1178,68 @@ describe("todo-continuation-enforcer", () => {
     // #then - continuation injected (no agents to skip)
     expect(promptCalls.length).toBe(1)
   })
+
+  test("should not inject when isContinuationStopped returns true", async () => {
+    // #given - session with continuation stopped
+    const sessionID = "main-stopped"
+    setMainSession(sessionID)
+
+    const hook = createTodoContinuationEnforcer(createMockPluginInput(), {
+      isContinuationStopped: (id) => id === sessionID,
+    })
+
+    // #when - session goes idle
+    await hook.handler({
+      event: { type: "session.idle", properties: { sessionID } },
+    })
+
+    await fakeTimers.advanceBy(3000)
+
+    // #then - no continuation injected (stopped flag is true)
+    expect(promptCalls).toHaveLength(0)
+  })
+
+  test("should inject when isContinuationStopped returns false", async () => {
+    // #given - session with continuation not stopped
+    const sessionID = "main-not-stopped"
+    setMainSession(sessionID)
+
+    const hook = createTodoContinuationEnforcer(createMockPluginInput(), {
+      isContinuationStopped: () => false,
+    })
+
+    // #when - session goes idle
+    await hook.handler({
+      event: { type: "session.idle", properties: { sessionID } },
+    })
+
+    await fakeTimers.advanceBy(3000)
+
+    // #then - continuation injected (stopped flag is false)
+    expect(promptCalls.length).toBe(1)
+  })
+
+  test("should cancel all countdowns via cancelAllCountdowns", async () => {
+    // #given - multiple sessions with running countdowns
+    const session1 = "main-cancel-all-1"
+    const session2 = "main-cancel-all-2"
+    setMainSession(session1)
+
+    const hook = createTodoContinuationEnforcer(createMockPluginInput(), {})
+
+    // #when - first session goes idle
+    await hook.handler({
+      event: { type: "session.idle", properties: { sessionID: session1 } },
+    })
+    await fakeTimers.advanceBy(500)
+
+    // #when - cancel all countdowns
+    hook.cancelAllCountdowns()
+
+    // #when - advance past countdown time
+    await fakeTimers.advanceBy(3000)
+
+    // #then - no continuation injected (all countdowns cancelled)
+    expect(promptCalls).toHaveLength(0)
+  })
 })

src/hooks/todo-continuation-enforcer.ts

@@ -18,12 +18,14 @@ const DEFAULT_SKIP_AGENTS = ["prometheus", "compaction"]
 export interface TodoContinuationEnforcerOptions {
   backgroundManager?: BackgroundManager
   skipAgents?: string[]
+  isContinuationStopped?: (sessionID: string) => boolean
 }
 
 export interface TodoContinuationEnforcer {
   handler: (input: { event: { type: string; properties?: unknown } }) => Promise<void>
   markRecovering: (sessionID: string) => void
   markRecoveryComplete: (sessionID: string) => void
+  cancelAllCountdowns: () => void
 }
 
 interface Todo {
@@ -95,7 +97,7 @@ export function createTodoContinuationEnforcer(
   ctx: PluginInput,
   options: TodoContinuationEnforcerOptions = {}
 ): TodoContinuationEnforcer {
-  const { backgroundManager, skipAgents = DEFAULT_SKIP_AGENTS } = options
+  const { backgroundManager, skipAgents = DEFAULT_SKIP_AGENTS, isContinuationStopped } = options
   const sessions = new Map<string, SessionState>()
 
   function getState(sessionID: string): SessionState {
@@ -420,6 +422,11 @@ export function createTodoContinuationEnforcer(
         return
       }
 
+      if (isContinuationStopped?.(sessionID)) {
+        log(`[${HOOK_NAME}] Skipped: continuation stopped for session`, { sessionID })
+        return
+      }
+
       startCountdown(sessionID, incompleteCount, todos.length, resolvedInfo)
       return
     }
@@ -485,9 +492,17 @@ export function createTodoContinuationEnforcer(
     }
   }
 
+  const cancelAllCountdowns = (): void => {
+    for (const sessionID of sessions.keys()) {
+      cancelCountdown(sessionID)
+    }
+    log(`[${HOOK_NAME}] All countdowns cancelled`)
+  }
+
   return {
     handler,
     markRecovering,
     markRecoveryComplete,
+    cancelAllCountdowns,
   }
 }

src/index.test.ts

@@ -1,6 +1,4 @@
 import { describe, expect, it } from "bun:test"
-import { includesCaseInsensitive } from "./shared"
-
 /**
  * Tests for conditional tool registration logic in index.ts
  * 
@@ -13,8 +11,10 @@ describe("look_at tool conditional registration", () => {
     // #when checking if agent is enabled
     // #then should return false (disabled)
     it("returns false when multimodal-looker is disabled (exact case)", () => {
-      const disabledAgents = ["multimodal-looker"]
-      const isEnabled = !includesCaseInsensitive(disabledAgents, "multimodal-looker")
+      const disabledAgents: string[] = ["multimodal-looker"]
+      const isEnabled = !disabledAgents.some(
+        (agent) => agent.toLowerCase() === "multimodal-looker"
+      )
       expect(isEnabled).toBe(false)
     })
 
@@ -22,8 +22,10 @@ describe("look_at tool conditional registration", () => {
     // #when checking if agent is enabled
     // #then should return false (case-insensitive match)
     it("returns false when multimodal-looker is disabled (case-insensitive)", () => {
-      const disabledAgents = ["Multimodal-Looker"]
-      const isEnabled = !includesCaseInsensitive(disabledAgents, "multimodal-looker")
+      const disabledAgents: string[] = ["Multimodal-Looker"]
+      const isEnabled = !disabledAgents.some(
+        (agent) => agent.toLowerCase() === "multimodal-looker"
+      )
       expect(isEnabled).toBe(false)
     })
 
@@ -31,8 +33,10 @@ describe("look_at tool conditional registration", () => {
     // #when checking if agent is enabled
     // #then should return true (enabled)
     it("returns true when multimodal-looker is not disabled", () => {
-      const disabledAgents = ["oracle", "librarian"]
-      const isEnabled = !includesCaseInsensitive(disabledAgents, "multimodal-looker")
+      const disabledAgents: string[] = ["oracle", "librarian"]
+      const isEnabled = !disabledAgents.some(
+        (agent) => agent.toLowerCase() === "multimodal-looker"
+      )
       expect(isEnabled).toBe(true)
     })
 
@@ -41,7 +45,9 @@ describe("look_at tool conditional registration", () => {
     // #then should return true (enabled by default)
     it("returns true when disabled_agents is empty", () => {
       const disabledAgents: string[] = []
-      const isEnabled = !includesCaseInsensitive(disabledAgents, "multimodal-looker")
+      const isEnabled = !disabledAgents.some(
+        (agent) => agent.toLowerCase() === "multimodal-looker"
+      )
       expect(isEnabled).toBe(true)
     })
 
@@ -49,8 +55,11 @@ describe("look_at tool conditional registration", () => {
     // #when checking if agent is enabled
     // #then should return true (enabled by default)
     it("returns true when disabled_agents is undefined (fallback to empty)", () => {
-      const disabledAgents = undefined
-      const isEnabled = !includesCaseInsensitive(disabledAgents ?? [], "multimodal-looker")
+      const disabledAgents: string[] | undefined = undefined
+      const list: string[] = disabledAgents ?? []
+      const isEnabled = !list.some(
+        (agent) => agent.toLowerCase() === "multimodal-looker"
+      )
       expect(isEnabled).toBe(true)
     })
   })

src/index.ts

@@ -12,8 +12,6 @@ import {
   createThinkModeHook,
   createClaudeCodeHooksHook,
   createAnthropicContextWindowLimitRecoveryHook,
-
-  createCompactionContextInjector,
   createRulesInjectorHook,
   createBackgroundNotificationHook,
   createAutoUpdateCheckerHook,
@@ -35,6 +33,7 @@ import {
   createSisyphusJuniorNotepadHook,
   createQuestionLabelTruncatorHook,
   createSubagentQuestionBlockerHook,
+  createStopContinuationGuardHook,
 } from "./hooks";
 import {
   contextCollector,
@@ -77,10 +76,11 @@ import { BackgroundManager } from "./features/background-agent";
 import { SkillMcpManager } from "./features/skill-mcp-manager";
 import { initTaskToastManager } from "./features/task-toast-manager";
 import { TmuxSessionManager } from "./features/tmux-subagent";
+import { clearBoulderState } from "./features/boulder-state";
 import { type HookName } from "./config";
-import { log, detectExternalNotificationPlugin, getNotificationConflictWarning, resetMessageCursor, includesCaseInsensitive, hasConnectedProvidersCache, getOpenCodeVersion, isOpenCodeVersionAtLeast, OPENCODE_NATIVE_AGENTS_INJECTION_VERSION } from "./shared";
+import { log, detectExternalNotificationPlugin, getNotificationConflictWarning, resetMessageCursor, hasConnectedProvidersCache, getOpenCodeVersion, isOpenCodeVersionAtLeast, OPENCODE_NATIVE_AGENTS_INJECTION_VERSION } from "./shared";
 import { loadPluginConfig } from "./plugin-config";
-import { createModelCacheState, getModelLimit } from "./plugin-state";
+import { createModelCacheState } from "./plugin-state";
 import { createConfigHandler } from "./plugin-handlers";
 
 const OhMyOpenCodePlugin: Plugin = async (ctx) => {
@@ -174,9 +174,6 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
         experimental: pluginConfig.experimental,
       })
     : null;
-  const compactionContextInjector = isHookEnabled("compaction-context-injector")
-    ? createCompactionContextInjector()
-    : undefined;
   const rulesInjector = isHookEnabled("rules-injector")
     ? createRulesInjectorHook(ctx)
     : null;
@@ -277,8 +274,15 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
 
   initTaskToastManager(ctx.client);
 
+  const stopContinuationGuard = isHookEnabled("stop-continuation-guard")
+    ? createStopContinuationGuardHook(ctx)
+    : null;
+
   const todoContinuationEnforcer = isHookEnabled("todo-continuation-enforcer")
-    ? createTodoContinuationEnforcer(ctx, { backgroundManager })
+    ? createTodoContinuationEnforcer(ctx, {
+        backgroundManager,
+        isContinuationStopped: stopContinuationGuard?.isStopped,
+      })
     : null;
 
   if (sessionRecovery && todoContinuationEnforcer) {
@@ -294,9 +298,8 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
   const backgroundTools = createBackgroundTools(backgroundManager, ctx.client);
 
   const callOmoAgent = createCallOmoAgent(ctx, backgroundManager);
-  const isMultimodalLookerEnabled = !includesCaseInsensitive(
-    pluginConfig.disabled_agents ?? [],
-    "multimodal-looker"
+  const isMultimodalLookerEnabled = !(pluginConfig.disabled_agents ?? []).some(
+    (agent) => agent.toLowerCase() === "multimodal-looker"
   );
   const lookAt = isMultimodalLookerEnabled ? createLookAt(ctx) : null;
   const browserProvider = pluginConfig.browser_automation_engine?.provider ?? "playwright";
@@ -420,6 +423,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
         }
       }
 
+      await stopContinuationGuard?.["chat.message"]?.(input);
       await keywordDetector?.["chat.message"]?.(input, output);
       await claudeCodeHooks["chat.message"]?.(input, output);
       await autoSlashCommand?.["chat.message"]?.(input, output);
@@ -521,6 +525,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
       await categorySkillReminder?.event(input);
       await interactiveBashSession?.event(input);
       await ralphLoop?.event(input);
+      await stopContinuationGuard?.event(input);
       await atlasHook?.handler(input);
 
       const { event } = input;
@@ -581,7 +586,12 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
           const recovered =
             await sessionRecovery.handleSessionRecovery(messageInfo);
 
-          if (recovered && sessionID && sessionID === getMainSessionID()) {
+          if (
+            recovered &&
+            sessionID &&
+            sessionID === getMainSessionID() &&
+            !stopContinuationGuard?.isStopped(sessionID)
+          ) {
             await ctx.client.session
               .prompt({
                 path: { id: sessionID },
@@ -610,9 +620,8 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
       if (input.tool === "task") {
         const args = output.args as Record<string, unknown>;
         const subagentType = args.subagent_type as string;
-        const isExploreOrLibrarian = includesCaseInsensitive(
-          ["explore", "librarian"],
-          subagentType ?? ""
+        const isExploreOrLibrarian = ["explore", "librarian"].some(
+          (name) => name.toLowerCase() === (subagentType ?? "").toLowerCase()
         );
 
         args.tools = {
@@ -664,14 +673,28 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
            );
 
            ralphLoop.startLoop(sessionID, prompt, {
-             ultrawork: true,
-             maxIterations: maxIterMatch
-               ? parseInt(maxIterMatch[1], 10)
-               : undefined,
-             completionPromise: promiseMatch?.[1],
-           });
+              ultrawork: true,
+              maxIterations: maxIterMatch
+                ? parseInt(maxIterMatch[1], 10)
+                : undefined,
+              completionPromise: promiseMatch?.[1],
+            });
          }
       }
+
+      if (input.tool === "slashcommand") {
+        const args = output.args as { command?: string } | undefined;
+        const command = args?.command?.replace(/^\//, "").toLowerCase();
+        const sessionID = input.sessionID || getMainSessionID();
+
+        if (command === "stop-continuation" && sessionID) {
+          stopContinuationGuard?.stop(sessionID);
+          todoContinuationEnforcer?.cancelAllCountdowns();
+          ralphLoop?.cancelLoop(sessionID);
+          clearBoulderState(ctx.directory);
+          log("[stop-continuation] All continuation mechanisms stopped", { sessionID });
+        }
+      }
     },
 
     "tool.execute.after": async (input, output) => {

src/plugin-handlers/config-handler.test.ts

@@ -396,3 +396,46 @@ describe("Prometheus direct override priority over category", () => {
     expect(agents.prometheus.temperature).toBe(0.1)
   })
 })
+
+describe("Deadlock prevention - fetchAvailableModels must not receive client", () => {
+  test("fetchAvailableModels should be called with undefined client to prevent deadlock during plugin init", async () => {
+    // #given - This test ensures we don't regress on issue #1301
+    // Passing client to fetchAvailableModels during config handler causes deadlock:
+    // - Plugin init waits for server response (client.provider.list())
+    // - Server waits for plugin init to complete before handling requests
+    const fetchSpy = spyOn(shared, "fetchAvailableModels" as any).mockResolvedValue(new Set<string>())
+
+    const pluginConfig: OhMyOpenCodeConfig = {
+      sisyphus_agent: {
+        planner_enabled: true,
+      },
+    }
+    const config: Record<string, unknown> = {
+      model: "anthropic/claude-opus-4-5",
+      agent: {},
+    }
+    const mockClient = {
+      provider: { list: () => Promise.resolve({ data: { connected: [] } }) },
+      model: { list: () => Promise.resolve({ data: [] }) },
+    }
+    const handler = createConfigHandler({
+      ctx: { directory: "/tmp", client: mockClient },
+      pluginConfig,
+      modelCacheState: {
+        anthropicContext1MEnabled: false,
+        modelContextLimitsCache: new Map(),
+      },
+    })
+
+    // #when
+    await handler(config)
+
+    // #then - fetchAvailableModels must be called with undefined as first argument (no client)
+    // This prevents the deadlock described in issue #1301
+    expect(fetchSpy).toHaveBeenCalled()
+    const firstCallArgs = fetchSpy.mock.calls[0]
+    expect(firstCallArgs[0]).toBeUndefined()
+
+    fetchSpy.mockRestore?.()
+  })
+})

src/plugin-handlers/config-handler.ts

@@ -25,11 +25,10 @@ import { loadMcpConfigs } from "../features/claude-code-mcp-loader";
 import { loadAllPluginComponents } from "../features/claude-code-plugin-loader";
 import { createBuiltinMcps } from "../mcp";
 import type { OhMyOpenCodeConfig } from "../config";
-import { log, fetchAvailableModels, readConnectedProvidersCache } from "../shared";
+import { log, fetchAvailableModels, readConnectedProvidersCache, resolveModelPipeline } from "../shared";
 import { getOpenCodeConfigPaths } from "../shared/opencode-config-dir";
 import { migrateAgentConfig } from "../shared/permission-compat";
 import { AGENT_NAME_MAP } from "../shared/migration";
-import { resolveModelWithFallback } from "../shared/model-resolver";
 import { AGENT_MODEL_REQUIREMENTS } from "../shared/model-requirements";
 import { PROMETHEUS_SYSTEM_PROMPT, PROMETHEUS_PERMISSION } from "../agents/prometheus-prompt";
 import { DEFAULT_CATEGORIES } from "../tools/delegate-task/constants";
@@ -249,16 +248,26 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
 
         const prometheusRequirement = AGENT_MODEL_REQUIREMENTS["prometheus"];
         const connectedProviders = readConnectedProvidersCache();
-        const availableModels = ctx.client
-          ? await fetchAvailableModels(ctx.client, { connectedProviders: connectedProviders ?? undefined })
-          : new Set<string>();
+        // IMPORTANT: Do NOT pass ctx.client to fetchAvailableModels during plugin initialization.
+        // Calling client API (e.g., client.provider.list()) from config handler causes deadlock:
+        // - Plugin init waits for server response
+        // - Server waits for plugin init to complete before handling requests
+        // Use cache-only mode instead. If cache is unavailable, fallback chain uses first model.
+        // See: https://github.com/code-yeongyu/oh-my-opencode/issues/1301
+        const availableModels = await fetchAvailableModels(undefined, {
+          connectedProviders: connectedProviders ?? undefined,
+        });
 
-        const modelResolution = resolveModelWithFallback({
-          uiSelectedModel: currentModel,
-          userModel: prometheusOverride?.model ?? categoryConfig?.model,
-          fallbackChain: prometheusRequirement?.fallbackChain,
-          availableModels,
-          systemDefaultModel: undefined,
+        const modelResolution = resolveModelPipeline({
+          intent: {
+            uiSelectedModel: currentModel,
+            userModel: prometheusOverride?.model ?? categoryConfig?.model,
+          },
+          constraints: { availableModels },
+          policy: {
+            fallbackChain: prometheusRequirement?.fallbackChain,
+            systemDefaultModel: undefined,
+          },
         });
         const resolvedModel = modelResolution?.model;
         const resolvedVariant = modelResolution?.variant;

src/shared/agent-tool-restrictions.ts

@@ -4,8 +4,6 @@
  * true = tool allowed, false = tool denied.
  */
 
-import { findCaseInsensitive } from "./case-insensitive"
-
 const EXPLORATION_AGENT_DENYLIST: Record<string, boolean> = {
   write: false,
   edit: false,
@@ -37,10 +35,13 @@ const AGENT_RESTRICTIONS: Record<string, Record<string, boolean>> = {
 }
 
 export function getAgentToolRestrictions(agentName: string): Record<string, boolean> {
-  return findCaseInsensitive(AGENT_RESTRICTIONS, agentName) ?? {}
+  return AGENT_RESTRICTIONS[agentName]
+    ?? Object.entries(AGENT_RESTRICTIONS).find(([key]) => key.toLowerCase() === agentName.toLowerCase())?.[1]
+    ?? {}
 }
 
 export function hasAgentToolRestrictions(agentName: string): boolean {
-  const restrictions = findCaseInsensitive(AGENT_RESTRICTIONS, agentName)
+  const restrictions = AGENT_RESTRICTIONS[agentName]
+    ?? Object.entries(AGENT_RESTRICTIONS).find(([key]) => key.toLowerCase() === agentName.toLowerCase())?.[1]
   return restrictions !== undefined && Object.keys(restrictions).length > 0
 }

src/shared/agent-variant.ts

@@ -1,5 +1,4 @@
 import type { OhMyOpenCodeConfig } from "../config"
-import { findCaseInsensitive } from "./case-insensitive"
 import { AGENT_MODEL_REQUIREMENTS, CATEGORY_MODEL_REQUIREMENTS } from "./model-requirements"
 
 export function resolveAgentVariant(
@@ -13,7 +12,10 @@ export function resolveAgentVariant(
   const agentOverrides = config.agents as
     | Record<string, { variant?: string; category?: string }>
     | undefined
-  const agentOverride = agentOverrides ? findCaseInsensitive(agentOverrides, agentName) : undefined
+  const agentOverride = agentOverrides
+    ? agentOverrides[agentName]
+      ?? Object.entries(agentOverrides).find(([key]) => key.toLowerCase() === agentName.toLowerCase())?.[1]
+    : undefined
   if (!agentOverride) {
     return undefined
   }
@@ -43,7 +45,10 @@ export function resolveVariantForModel(
   const agentOverrides = config.agents as
     | Record<string, { category?: string }>
     | undefined
-  const agentOverride = agentOverrides ? findCaseInsensitive(agentOverrides, agentName) : undefined
+  const agentOverride = agentOverrides
+    ? agentOverrides[agentName]
+      ?? Object.entries(agentOverrides).find(([key]) => key.toLowerCase() === agentName.toLowerCase())?.[1]
+    : undefined
   const categoryName = agentOverride?.category
   if (categoryName) {
     const categoryRequirement = CATEGORY_MODEL_REQUIREMENTS[categoryName]

src/shared/binary-downloader.ts

@@ -0,0 +1,60 @@
+import { chmodSync, existsSync, mkdirSync, unlinkSync } from "node:fs";
+import * as path from "node:path";
+import { spawn } from "bun";
+import { extractZip } from "./zip-extractor";
+
+export function getCachedBinaryPath(cacheDir: string, binaryName: string): string | null {
+  const binaryPath = path.join(cacheDir, binaryName);
+  return existsSync(binaryPath) ? binaryPath : null;
+}
+
+export function ensureCacheDir(cacheDir: string): void {
+  if (!existsSync(cacheDir)) {
+    mkdirSync(cacheDir, { recursive: true });
+  }
+}
+
+export async function downloadArchive(downloadUrl: string, archivePath: string): Promise<void> {
+  const response = await fetch(downloadUrl, { redirect: "follow" });
+  if (!response.ok) {
+    throw new Error(`HTTP ${response.status}: ${response.statusText}`);
+  }
+
+  const arrayBuffer = await response.arrayBuffer();
+  await Bun.write(archivePath, arrayBuffer);
+}
+
+export async function extractTarGz(
+  archivePath: string,
+  destDir: string,
+  options?: { args?: string[]; cwd?: string }
+): Promise<void> {
+  const args = options?.args ?? ["tar", "-xzf", archivePath, "-C", destDir];
+  const proc = spawn(args, {
+    cwd: options?.cwd,
+    stdout: "pipe",
+    stderr: "pipe",
+  });
+
+  const exitCode = await proc.exited;
+  if (exitCode !== 0) {
+    const stderr = await new Response(proc.stderr).text();
+    throw new Error(`tar extraction failed (exit ${exitCode}): ${stderr}`);
+  }
+}
+
+export async function extractZipArchive(archivePath: string, destDir: string): Promise<void> {
+  await extractZip(archivePath, destDir);
+}
+
+export function cleanupArchive(archivePath: string): void {
+  if (existsSync(archivePath)) {
+    unlinkSync(archivePath);
+  }
+}
+
+export function ensureExecutable(binaryPath: string): void {
+  if (process.platform !== "win32" && existsSync(binaryPath)) {
+    chmodSync(binaryPath, 0o755);
+  }
+}

src/shared/case-insensitive.test.ts

@@ -1,169 +0,0 @@
-import { describe, test, expect } from "bun:test"
-import {
-  findCaseInsensitive,
-  includesCaseInsensitive,
-  findByNameCaseInsensitive,
-  equalsIgnoreCase,
-} from "./case-insensitive"
-
-describe("findCaseInsensitive", () => {
-  test("returns undefined for empty/undefined object", () => {
-    // #given - undefined object
-    const obj = undefined
-    
-    // #when - lookup any key
-    const result = findCaseInsensitive(obj, "key")
-    
-    // #then - returns undefined
-    expect(result).toBeUndefined()
-  })
-
-  test("finds exact match first", () => {
-    // #given - object with exact key
-    const obj = { Oracle: "value1", oracle: "value2" }
-    
-    // #when - lookup with exact case
-    const result = findCaseInsensitive(obj, "Oracle")
-    
-    // #then - returns exact match
-    expect(result).toBe("value1")
-  })
-
-  test("finds case-insensitive match when no exact match", () => {
-    // #given - object with lowercase key
-    const obj = { oracle: "value" }
-    
-    // #when - lookup with uppercase
-    const result = findCaseInsensitive(obj, "ORACLE")
-    
-    // #then - returns case-insensitive match
-    expect(result).toBe("value")
-  })
-
-  test("returns undefined when key not found", () => {
-    // #given - object without target key
-    const obj = { other: "value" }
-    
-    // #when - lookup missing key
-    const result = findCaseInsensitive(obj, "oracle")
-    
-    // #then - returns undefined
-    expect(result).toBeUndefined()
-  })
-})
-
-describe("includesCaseInsensitive", () => {
-  test("returns true for exact match", () => {
-    // #given - array with exact value
-    const arr = ["explore", "librarian"]
-    
-    // #when - check exact match
-    const result = includesCaseInsensitive(arr, "explore")
-    
-    // #then - returns true
-    expect(result).toBe(true)
-  })
-
-  test("returns true for case-insensitive match", () => {
-    // #given - array with lowercase values
-    const arr = ["explore", "librarian"]
-    
-    // #when - check uppercase value
-    const result = includesCaseInsensitive(arr, "EXPLORE")
-    
-    // #then - returns true
-    expect(result).toBe(true)
-  })
-
-  test("returns true for mixed case match", () => {
-    // #given - array with mixed case values
-    const arr = ["Oracle", "Sisyphus"]
-    
-    // #when - check different case
-    const result = includesCaseInsensitive(arr, "oracle")
-    
-    // #then - returns true
-    expect(result).toBe(true)
-  })
-
-  test("returns false when value not found", () => {
-    // #given - array without target value
-    const arr = ["explore", "librarian"]
-    
-    // #when - check missing value
-    const result = includesCaseInsensitive(arr, "oracle")
-    
-    // #then - returns false
-    expect(result).toBe(false)
-  })
-
-  test("returns false for empty array", () => {
-    // #given - empty array
-    const arr: string[] = []
-    
-    // #when - check any value
-    const result = includesCaseInsensitive(arr, "explore")
-    
-    // #then - returns false
-    expect(result).toBe(false)
-  })
-})
-
-describe("findByNameCaseInsensitive", () => {
-  test("finds element by exact name", () => {
-    // #given - array with named objects
-    const arr = [{ name: "Oracle", value: 1 }, { name: "explore", value: 2 }]
-    
-    // #when - find by exact name
-    const result = findByNameCaseInsensitive(arr, "Oracle")
-    
-    // #then - returns matching element
-    expect(result).toEqual({ name: "Oracle", value: 1 })
-  })
-
-  test("finds element by case-insensitive name", () => {
-    // #given - array with named objects
-    const arr = [{ name: "Oracle", value: 1 }, { name: "explore", value: 2 }]
-    
-    // #when - find by different case
-    const result = findByNameCaseInsensitive(arr, "oracle")
-    
-    // #then - returns matching element
-    expect(result).toEqual({ name: "Oracle", value: 1 })
-  })
-
-  test("returns undefined when name not found", () => {
-    // #given - array without target name
-    const arr = [{ name: "Oracle", value: 1 }]
-    
-    // #when - find missing name
-    const result = findByNameCaseInsensitive(arr, "librarian")
-    
-    // #then - returns undefined
-    expect(result).toBeUndefined()
-  })
-})
-
-describe("equalsIgnoreCase", () => {
-  test("returns true for same case", () => {
-    // #given - same strings
-    // #when - compare
-    // #then - returns true
-    expect(equalsIgnoreCase("oracle", "oracle")).toBe(true)
-  })
-
-  test("returns true for different case", () => {
-    // #given - strings with different case
-    // #when - compare
-    // #then - returns true
-    expect(equalsIgnoreCase("Oracle", "ORACLE")).toBe(true)
-    expect(equalsIgnoreCase("Sisyphus-Junior", "sisyphus-junior")).toBe(true)
-  })
-
-  test("returns false for different strings", () => {
-    // #given - different strings
-    // #when - compare
-    // #then - returns false
-    expect(equalsIgnoreCase("oracle", "explore")).toBe(false)
-  })
-})

src/shared/case-insensitive.ts

@@ -1,46 +0,0 @@
-/**
- * Case-insensitive lookup and comparison utilities for agent/config names.
- * Used throughout the codebase to allow "Oracle", "oracle", "ORACLE" to work the same.
- */
-
-/**
- * Find a value in an object using case-insensitive key matching.
- * First tries exact match, then falls back to lowercase comparison.
- */
-export function findCaseInsensitive<T>(obj: Record<string, T> | undefined, key: string): T | undefined {
-  if (!obj) return undefined
-  const exactMatch = obj[key]
-  if (exactMatch !== undefined) return exactMatch
-  const lowerKey = key.toLowerCase()
-  for (const [k, v] of Object.entries(obj)) {
-    if (k.toLowerCase() === lowerKey) return v
-  }
-  return undefined
-}
-
-/**
- * Check if an array includes a value using case-insensitive comparison.
- */
-export function includesCaseInsensitive(arr: string[], value: string): boolean {
-  const lowerValue = value.toLowerCase()
-  return arr.some((item) => item.toLowerCase() === lowerValue)
-}
-
-/**
- * Find an element in array using case-insensitive name matching.
- * Useful for finding agents/categories by name.
- */
-export function findByNameCaseInsensitive<T extends { name: string }>(
-  arr: T[],
-  name: string
-): T | undefined {
-  const lowerName = name.toLowerCase()
-  return arr.find((item) => item.name.toLowerCase() === lowerName)
-}
-
-/**
- * Check if two strings are equal (case-insensitive).
- */
-export function equalsIgnoreCase(a: string, b: string): boolean {
-  return a.toLowerCase() === b.toLowerCase()
-}

src/shared/index.ts

@@ -20,6 +20,7 @@ export * from "./opencode-version"
 export * from "./permission-compat"
 export * from "./external-plugin-detector"
 export * from "./zip-extractor"
+export * from "./binary-downloader"
 export * from "./agent-variant"
 export * from "./session-cursor"
 export * from "./shell-env"
@@ -27,9 +28,14 @@ export * from "./system-directive"
 export * from "./agent-tool-restrictions"
 export * from "./model-requirements"
 export * from "./model-resolver"
+export {
+  resolveModelPipeline,
+  type ModelResolutionRequest,
+  type ModelResolutionResult as ModelResolutionPipelineResult,
+  type ModelResolutionProvenance,
+} from "./model-resolution-pipeline"
 export * from "./model-availability"
 export * from "./connected-providers-cache"
-export * from "./case-insensitive"
 export * from "./session-utils"
 export * from "./tmux"
 export * from "./model-suggestion-retry"

src/shared/model-resolution-pipeline.ts

@@ -0,0 +1,174 @@
+import { log } from "./logger"
+import { readConnectedProvidersCache } from "./connected-providers-cache"
+import { fuzzyMatchModel } from "./model-availability"
+import type { FallbackEntry } from "./model-requirements"
+
+export type ModelResolutionRequest = {
+  intent?: {
+    uiSelectedModel?: string
+    userModel?: string
+    categoryDefaultModel?: string
+  }
+  constraints: {
+    availableModels: Set<string>
+  }
+  policy?: {
+    fallbackChain?: FallbackEntry[]
+    systemDefaultModel?: string
+  }
+}
+
+export type ModelResolutionProvenance =
+  | "override"
+  | "category-default"
+  | "provider-fallback"
+  | "system-default"
+
+export type ModelResolutionResult = {
+  model: string
+  provenance: ModelResolutionProvenance
+  variant?: string
+  attempted?: string[]
+  reason?: string
+}
+
+function normalizeModel(model?: string): string | undefined {
+  const trimmed = model?.trim()
+  return trimmed || undefined
+}
+
+export function resolveModelPipeline(
+  request: ModelResolutionRequest,
+): ModelResolutionResult | undefined {
+  const attempted: string[] = []
+  const { intent, constraints, policy } = request
+  const availableModels = constraints.availableModels
+  const fallbackChain = policy?.fallbackChain
+  const systemDefaultModel = policy?.systemDefaultModel
+
+  const normalizedUiModel = normalizeModel(intent?.uiSelectedModel)
+  if (normalizedUiModel) {
+    log("Model resolved via UI selection", { model: normalizedUiModel })
+    return { model: normalizedUiModel, provenance: "override" }
+  }
+
+  const normalizedUserModel = normalizeModel(intent?.userModel)
+  if (normalizedUserModel) {
+    log("Model resolved via config override", { model: normalizedUserModel })
+    return { model: normalizedUserModel, provenance: "override" }
+  }
+
+  const normalizedCategoryDefault = normalizeModel(intent?.categoryDefaultModel)
+  if (normalizedCategoryDefault) {
+    attempted.push(normalizedCategoryDefault)
+    if (availableModels.size > 0) {
+      const parts = normalizedCategoryDefault.split("/")
+      const providerHint = parts.length >= 2 ? [parts[0]] : undefined
+      const match = fuzzyMatchModel(normalizedCategoryDefault, availableModels, providerHint)
+      if (match) {
+        log("Model resolved via category default (fuzzy matched)", {
+          original: normalizedCategoryDefault,
+          matched: match,
+        })
+        return { model: match, provenance: "category-default", attempted }
+      }
+    } else {
+      const connectedProviders = readConnectedProvidersCache()
+      if (connectedProviders === null) {
+        log("Model resolved via category default (no cache, first run)", {
+          model: normalizedCategoryDefault,
+        })
+        return { model: normalizedCategoryDefault, provenance: "category-default", attempted }
+      }
+      const parts = normalizedCategoryDefault.split("/")
+      if (parts.length >= 2) {
+        const provider = parts[0]
+        if (connectedProviders.includes(provider)) {
+          log("Model resolved via category default (connected provider)", {
+            model: normalizedCategoryDefault,
+          })
+          return { model: normalizedCategoryDefault, provenance: "category-default", attempted }
+        }
+      }
+    }
+    log("Category default model not available, falling through to fallback chain", {
+      model: normalizedCategoryDefault,
+    })
+  }
+
+  if (fallbackChain && fallbackChain.length > 0) {
+    if (availableModels.size === 0) {
+      const connectedProviders = readConnectedProvidersCache()
+      const connectedSet = connectedProviders ? new Set(connectedProviders) : null
+
+      if (connectedSet === null) {
+        log("Model fallback chain skipped (no connected providers cache) - falling through to system default")
+      } else {
+        for (const entry of fallbackChain) {
+          for (const provider of entry.providers) {
+            if (connectedSet.has(provider)) {
+              const model = `${provider}/${entry.model}`
+              log("Model resolved via fallback chain (connected provider)", {
+                provider,
+                model: entry.model,
+                variant: entry.variant,
+              })
+              return {
+                model,
+                provenance: "provider-fallback",
+                variant: entry.variant,
+                attempted,
+              }
+            }
+          }
+        }
+        log("No connected provider found in fallback chain, falling through to system default")
+      }
+    } else {
+      for (const entry of fallbackChain) {
+        for (const provider of entry.providers) {
+          const fullModel = `${provider}/${entry.model}`
+          const match = fuzzyMatchModel(fullModel, availableModels, [provider])
+          if (match) {
+            log("Model resolved via fallback chain (availability confirmed)", {
+              provider,
+              model: entry.model,
+              match,
+              variant: entry.variant,
+            })
+            return {
+              model: match,
+              provenance: "provider-fallback",
+              variant: entry.variant,
+              attempted,
+            }
+          }
+        }
+
+        const crossProviderMatch = fuzzyMatchModel(entry.model, availableModels)
+        if (crossProviderMatch) {
+          log("Model resolved via fallback chain (cross-provider fuzzy match)", {
+            model: entry.model,
+            match: crossProviderMatch,
+            variant: entry.variant,
+          })
+          return {
+            model: crossProviderMatch,
+            provenance: "provider-fallback",
+            variant: entry.variant,
+            attempted,
+          }
+        }
+      }
+      log("No available model found in fallback chain, falling through to system default")
+    }
+  }
+
+  if (systemDefaultModel === undefined) {
+    log("No model resolved - systemDefaultModel not configured")
+    return undefined
+  }
+
+  log("Model resolved via system default", { model: systemDefaultModel })
+  return { model: systemDefaultModel, provenance: "system-default", attempted }
+}

src/shared/model-resolver.ts

@@ -1,7 +1,6 @@
 import { log } from "./logger"
-import { fuzzyMatchModel } from "./model-availability"
 import type { FallbackEntry } from "./model-requirements"
-import { readConnectedProvidersCache } from "./connected-providers-cache"
+import { resolveModelPipeline } from "./model-resolution-pipeline"
 
 export type ModelResolutionInput = {
 	userModel?: string
@@ -47,107 +46,19 @@ export function resolveModelWithFallback(
 	input: ExtendedModelResolutionInput,
 ): ModelResolutionResult | undefined {
 	const { uiSelectedModel, userModel, categoryDefaultModel, fallbackChain, availableModels, systemDefaultModel } = input
+	const resolved = resolveModelPipeline({
+		intent: { uiSelectedModel, userModel, categoryDefaultModel },
+		constraints: { availableModels },
+		policy: { fallbackChain, systemDefaultModel },
+	})
 
-	// Step 1: UI Selection (highest priority - respects user's model choice in OpenCode UI)
-	const normalizedUiModel = normalizeModel(uiSelectedModel)
-	if (normalizedUiModel) {
-		log("Model resolved via UI selection", { model: normalizedUiModel })
-		return { model: normalizedUiModel, source: "override" }
-	}
-
-	// Step 2: Config Override (from oh-my-opencode.json user config)
-	const normalizedUserModel = normalizeModel(userModel)
-	if (normalizedUserModel) {
-		log("Model resolved via config override", { model: normalizedUserModel })
-		return { model: normalizedUserModel, source: "override" }
-	}
-
-	// Step 2.5: Category Default Model (from DEFAULT_CATEGORIES, with fuzzy matching)
-	const normalizedCategoryDefault = normalizeModel(categoryDefaultModel)
-	if (normalizedCategoryDefault) {
-		if (availableModels.size > 0) {
-			const parts = normalizedCategoryDefault.split("/")
-			const providerHint = parts.length >= 2 ? [parts[0]] : undefined
-			const match = fuzzyMatchModel(normalizedCategoryDefault, availableModels, providerHint)
-			if (match) {
-				log("Model resolved via category default (fuzzy matched)", { original: normalizedCategoryDefault, matched: match })
-				return { model: match, source: "category-default" }
-			}
-		} else {
-			const connectedProviders = readConnectedProvidersCache()
-			if (connectedProviders === null) {
-				log("Model resolved via category default (no cache, first run)", { model: normalizedCategoryDefault })
-				return { model: normalizedCategoryDefault, source: "category-default" }
-			}
-			const parts = normalizedCategoryDefault.split("/")
-			if (parts.length >= 2) {
-				const provider = parts[0]
-				if (connectedProviders.includes(provider)) {
-					log("Model resolved via category default (connected provider)", { model: normalizedCategoryDefault })
-					return { model: normalizedCategoryDefault, source: "category-default" }
-				}
-			}
-		}
-		log("Category default model not available, falling through to fallback chain", { model: normalizedCategoryDefault })
-	}
-
-	// Step 3: Provider fallback chain (exact match → fuzzy match → next provider)
-	if (fallbackChain && fallbackChain.length > 0) {
-		if (availableModels.size === 0) {
-			const connectedProviders = readConnectedProvidersCache()
-			const connectedSet = connectedProviders ? new Set(connectedProviders) : null
-
-			if (connectedSet === null) {
-				log("Model fallback chain skipped (no connected providers cache) - falling through to system default")
-			} else {
-				for (const entry of fallbackChain) {
-					for (const provider of entry.providers) {
-						if (connectedSet.has(provider)) {
-							const model = `${provider}/${entry.model}`
-							log("Model resolved via fallback chain (connected provider)", { 
-								provider, 
-								model: entry.model, 
-								variant: entry.variant,
-							})
-							return { model, source: "provider-fallback", variant: entry.variant }
-						}
-					}
-				}
-				log("No connected provider found in fallback chain, falling through to system default")
-			}
-		} else {
-			for (const entry of fallbackChain) {
-				// Step 1: Try with provider filter (preferred providers first)
-				for (const provider of entry.providers) {
-					const fullModel = `${provider}/${entry.model}`
-					const match = fuzzyMatchModel(fullModel, availableModels, [provider])
-					if (match) {
-						log("Model resolved via fallback chain (availability confirmed)", { provider, model: entry.model, match, variant: entry.variant })
-						return { model: match, source: "provider-fallback", variant: entry.variant }
-					}
-				}
-
-				// Step 2: Try without provider filter (cross-provider fuzzy match)
-				const crossProviderMatch = fuzzyMatchModel(entry.model, availableModels)
-				if (crossProviderMatch) {
-					log("Model resolved via fallback chain (cross-provider fuzzy match)", {
-						model: entry.model,
-						match: crossProviderMatch,
-						variant: entry.variant,
-					})
-					return { model: crossProviderMatch, source: "provider-fallback", variant: entry.variant }
-				}
-			}
-			log("No available model found in fallback chain, falling through to system default")
-		}
-	}
-
-	// Step 4: System default (if provided)
-	if (systemDefaultModel === undefined) {
-		log("No model resolved - systemDefaultModel not configured")
+	if (!resolved) {
 		return undefined
 	}
 
-	log("Model resolved via system default", { model: systemDefaultModel })
-	return { model: systemDefaultModel, source: "system-default" }
+	return {
+		model: resolved.model,
+		source: resolved.provenance,
+		variant: resolved.variant,
+	}
 }

src/shared/opencode-version.test.ts

@@ -2,8 +2,6 @@ import { describe, test, expect, beforeEach, afterEach } from "bun:test"
 import {
   parseVersion,
   compareVersions,
-  isVersionGte,
-  isVersionLt,
   getOpenCodeVersion,
   isOpenCodeVersionAtLeast,
   resetVersionCache,
@@ -103,32 +101,6 @@ describe("opencode-version", () => {
     })
   })
 
-  describe("isVersionGte", () => {
-    test("returns true when a >= b", () => {
-      expect(isVersionGte("1.1.1", "1.1.1")).toBe(true)
-      expect(isVersionGte("1.1.2", "1.1.1")).toBe(true)
-      expect(isVersionGte("1.2.0", "1.1.1")).toBe(true)
-      expect(isVersionGte("2.0.0", "1.1.1")).toBe(true)
-    })
-
-    test("returns false when a < b", () => {
-      expect(isVersionGte("1.1.0", "1.1.1")).toBe(false)
-      expect(isVersionGte("1.0.9", "1.1.1")).toBe(false)
-      expect(isVersionGte("0.9.9", "1.1.1")).toBe(false)
-    })
-  })
-
-  describe("isVersionLt", () => {
-    test("returns true when a < b", () => {
-      expect(isVersionLt("1.1.0", "1.1.1")).toBe(true)
-      expect(isVersionLt("1.0.150", "1.1.1")).toBe(true)
-    })
-
-    test("returns false when a >= b", () => {
-      expect(isVersionLt("1.1.1", "1.1.1")).toBe(false)
-      expect(isVersionLt("1.1.2", "1.1.1")).toBe(false)
-    })
-  })
 
   describe("getOpenCodeVersion", () => {
     beforeEach(() => {

src/shared/opencode-version.ts

@@ -37,13 +37,6 @@ export function compareVersions(a: string, b: string): -1 | 0 | 1 {
   return 0
 }
 
-export function isVersionGte(a: string, b: string): boolean {
-  return compareVersions(a, b) >= 0
-}
-
-export function isVersionLt(a: string, b: string): boolean {
-  return compareVersions(a, b) < 0
-}
 
 export function getOpenCodeVersion(): string | null {
   if (cachedVersion !== NOT_CACHED) {
@@ -69,7 +62,7 @@ export function getOpenCodeVersion(): string | null {
 export function isOpenCodeVersionAtLeast(version: string): boolean {
   const current = getOpenCodeVersion()
   if (!current) return true
-  return isVersionGte(current, version)
+  return compareVersions(current, version) >= 0
 }
 
 export function resetVersionCache(): void {

src/shared/session-injected-paths.ts

@@ -0,0 +1,59 @@
+import {
+  existsSync,
+  mkdirSync,
+  readFileSync,
+  unlinkSync,
+  writeFileSync,
+} from "node:fs";
+import { join } from "node:path";
+
+export interface InjectedPathsData {
+  sessionID: string;
+  injectedPaths: string[];
+  updatedAt: number;
+}
+
+export function createInjectedPathsStorage(storageDir: string) {
+  const getStoragePath = (sessionID: string): string =>
+    join(storageDir, `${sessionID}.json`);
+
+  const loadInjectedPaths = (sessionID: string): Set<string> => {
+    const filePath = getStoragePath(sessionID);
+    if (!existsSync(filePath)) return new Set();
+
+    try {
+      const content = readFileSync(filePath, "utf-8");
+      const data: InjectedPathsData = JSON.parse(content);
+      return new Set(data.injectedPaths);
+    } catch {
+      return new Set();
+    }
+  };
+
+  const saveInjectedPaths = (sessionID: string, paths: Set<string>): void => {
+    if (!existsSync(storageDir)) {
+      mkdirSync(storageDir, { recursive: true });
+    }
+
+    const data: InjectedPathsData = {
+      sessionID,
+      injectedPaths: [...paths],
+      updatedAt: Date.now(),
+    };
+
+    writeFileSync(getStoragePath(sessionID), JSON.stringify(data, null, 2));
+  };
+
+  const clearInjectedPaths = (sessionID: string): void => {
+    const filePath = getStoragePath(sessionID);
+    if (existsSync(filePath)) {
+      unlinkSync(filePath);
+    }
+  };
+
+  return {
+    loadInjectedPaths,
+    saveInjectedPaths,
+    clearInjectedPaths,
+  };
+}

src/shared/snake-case.ts

@@ -8,42 +8,37 @@ export function snakeToCamel(str: string): string {
   return str.replace(/_([a-z])/g, (_, letter) => letter.toUpperCase())
 }
 
+export function transformObjectKeys(
+  obj: Record<string, unknown>,
+  transformer: (key: string) => string,
+  deep: boolean = true
+): Record<string, unknown> {
+  const result: Record<string, unknown> = {}
+  for (const [key, value] of Object.entries(obj)) {
+    const transformedKey = transformer(key)
+    if (deep && isPlainObject(value)) {
+      result[transformedKey] = transformObjectKeys(value, transformer, true)
+    } else if (deep && Array.isArray(value)) {
+      result[transformedKey] = value.map((item) =>
+        isPlainObject(item) ? transformObjectKeys(item, transformer, true) : item
+      )
+    } else {
+      result[transformedKey] = value
+    }
+  }
+  return result
+}
+
 export function objectToSnakeCase(
   obj: Record<string, unknown>,
   deep: boolean = true
 ): Record<string, unknown> {
-   const result: Record<string, unknown> = {}
-   for (const [key, value] of Object.entries(obj)) {
-     const snakeKey = camelToSnake(key)
-     if (deep && isPlainObject(value)) {
-       result[snakeKey] = objectToSnakeCase(value, true)
-     } else if (deep && Array.isArray(value)) {
-       result[snakeKey] = value.map((item) =>
-         isPlainObject(item) ? objectToSnakeCase(item, true) : item
-       )
-     } else {
-       result[snakeKey] = value
-     }
-   }
-   return result
- }
+  return transformObjectKeys(obj, camelToSnake, deep)
+}
 
 export function objectToCamelCase(
   obj: Record<string, unknown>,
   deep: boolean = true
 ): Record<string, unknown> {
-   const result: Record<string, unknown> = {}
-   for (const [key, value] of Object.entries(obj)) {
-     const camelKey = snakeToCamel(key)
-     if (deep && isPlainObject(value)) {
-       result[camelKey] = objectToCamelCase(value, true)
-     } else if (deep && Array.isArray(value)) {
-       result[camelKey] = value.map((item) =>
-         isPlainObject(item) ? objectToCamelCase(item, true) : item
-       )
-     } else {
-       result[camelKey] = value
-     }
-   }
-   return result
- }
+  return transformObjectKeys(obj, snakeToCamel, deep)
+}

src/shared/tmux/tmux-utils.ts

@@ -139,10 +139,22 @@ export async function spawnTmuxPane(
   }
 
   const title = `omo-subagent-${description.slice(0, 20)}`
-  spawn([tmux, "select-pane", "-t", paneId, "-T", title], {
+  const titleProc = spawn([tmux, "select-pane", "-t", paneId, "-T", title], {
     stdout: "ignore",
-    stderr: "ignore",
+    stderr: "pipe",
   })
+  // Drain stderr immediately to avoid backpressure
+  const stderrPromise = new Response(titleProc.stderr).text().catch(() => "")
+  const titleExitCode = await titleProc.exited
+  if (titleExitCode !== 0) {
+    const titleStderr = await stderrPromise
+    log("[spawnTmuxPane] WARNING: failed to set pane title", {
+      paneId,
+      title,
+      exitCode: titleExitCode,
+      stderr: titleStderr.trim(),
+    })
+  }
 
   return { success: true, paneId }
 }
@@ -217,10 +229,21 @@ export async function replaceTmuxPane(
   }
 
   const title = `omo-subagent-${description.slice(0, 20)}`
-  spawn([tmux, "select-pane", "-t", paneId, "-T", title], {
+  const titleProc = spawn([tmux, "select-pane", "-t", paneId, "-T", title], {
     stdout: "ignore",
-    stderr: "ignore",
+    stderr: "pipe",
   })
+  // Drain stderr immediately to avoid backpressure
+  const stderrPromise = new Response(titleProc.stderr).text().catch(() => "")
+  const titleExitCode = await titleProc.exited
+  if (titleExitCode !== 0) {
+    const titleStderr = await stderrPromise
+    log("[replaceTmuxPane] WARNING: failed to set pane title", {
+      paneId,
+      exitCode: titleExitCode,
+      stderr: titleStderr.trim(),
+    })
+  }
 
   log("[replaceTmuxPane] SUCCESS", { paneId, sessionId })
   return { success: true, paneId }

src/tools/ast-grep/downloader.ts

@@ -1,8 +1,15 @@
-import { existsSync, mkdirSync, chmodSync, unlinkSync } from "fs"
+import { existsSync } from "fs"
 import { join } from "path"
 import { homedir } from "os"
 import { createRequire } from "module"
-import { extractZip } from "../../shared"
+import {
+  cleanupArchive,
+  downloadArchive,
+  ensureCacheDir,
+  ensureExecutable,
+  extractZipArchive,
+  getCachedBinaryPath as getCachedBinaryPathShared,
+} from "../../shared/binary-downloader"
 import { log } from "../../shared/logger"
 
 const REPO = "ast-grep/ast-grep"
@@ -53,8 +60,7 @@ export function getBinaryName(): string {
 }
 
 export function getCachedBinaryPath(): string | null {
-  const binaryPath = join(getCacheDir(), getBinaryName())
-  return existsSync(binaryPath) ? binaryPath : null
+  return getCachedBinaryPathShared(getCacheDir(), getBinaryName())
 }
 
 
@@ -83,29 +89,12 @@ export async function downloadAstGrep(version: string = DEFAULT_VERSION): Promis
   log(`[oh-my-opencode] Downloading ast-grep binary...`)
 
   try {
-    if (!existsSync(cacheDir)) {
-      mkdirSync(cacheDir, { recursive: true })
-    }
-
-    const response = await fetch(downloadUrl, { redirect: "follow" })
-
-    if (!response.ok) {
-      throw new Error(`HTTP ${response.status}: ${response.statusText}`)
-    }
-
     const archivePath = join(cacheDir, assetName)
-    const arrayBuffer = await response.arrayBuffer()
-    await Bun.write(archivePath, arrayBuffer)
-
-    await extractZip(archivePath, cacheDir)
-
-    if (existsSync(archivePath)) {
-      unlinkSync(archivePath)
-    }
-
-    if (process.platform !== "win32" && existsSync(binaryPath)) {
-      chmodSync(binaryPath, 0o755)
-    }
+    ensureCacheDir(cacheDir)
+    await downloadArchive(downloadUrl, archivePath)
+    await extractZipArchive(archivePath, cacheDir)
+    cleanupArchive(archivePath)
+    ensureExecutable(binaryPath)
 
     log(`[oh-my-opencode] ast-grep binary ready.`)
 

src/tools/call-omo-agent/tools.ts

@@ -4,7 +4,7 @@ import { join } from "node:path"
 import { ALLOWED_AGENTS, CALL_OMO_AGENT_DESCRIPTION } from "./constants"
 import type { CallOmoAgentArgs } from "./types"
 import type { BackgroundManager } from "../../features/background-agent"
-import { log, getAgentToolRestrictions, includesCaseInsensitive } from "../../shared"
+import { log, getAgentToolRestrictions } from "../../shared"
 import { consumeNewMessages } from "../../shared/session-cursor"
 import { findFirstMessageWithAgent, findNearestMessageWithFields, MESSAGE_STORAGE } from "../../features/hook-message-injector"
 import { getSessionAgent } from "../../features/claude-code-session-state"
@@ -58,7 +58,9 @@ export function createCallOmoAgent(
       log(`[call_omo_agent] Starting with agent: ${args.subagent_type}, background: ${args.run_in_background}`)
 
       // Case-insensitive agent validation - allows "Explore", "EXPLORE", "explore" etc.
-      if (!includesCaseInsensitive([...ALLOWED_AGENTS], args.subagent_type)) {
+      if (![...ALLOWED_AGENTS].some(
+        (name) => name.toLowerCase() === args.subagent_type.toLowerCase()
+      )) {
         return `Error: Invalid agent type "${args.subagent_type}". Only ${ALLOWED_AGENTS.join(", ")} are allowed.`
       }
       

src/tools/delegate-task/tools.ts

@@ -12,10 +12,9 @@ import { discoverSkills } from "../../features/opencode-skill-loader"
 import { getTaskToastManager } from "../../features/task-toast-manager"
 import type { ModelFallbackInfo } from "../../features/task-toast-manager/types"
 import { subagentSessions, getSessionAgent } from "../../features/claude-code-session-state"
-import { log, getAgentToolRestrictions, resolveModel, getOpenCodeConfigPaths, findByNameCaseInsensitive, equalsIgnoreCase, promptWithModelSuggestionRetry } from "../../shared"
+import { log, getAgentToolRestrictions, resolveModel, resolveModelPipeline, getOpenCodeConfigPaths, promptWithModelSuggestionRetry } from "../../shared"
 import { fetchAvailableModels, isModelAvailable } from "../../shared/model-availability"
 import { readConnectedProvidersCache } from "../../shared/connected-providers-cache"
-import { resolveModelWithFallback } from "../../shared/model-resolver"
 import { CATEGORY_MODEL_REQUIREMENTS } from "../../shared/model-requirements"
 
 type OpencodeClient = PluginInput["client"]
@@ -552,16 +551,20 @@ To continue this session: session_id="${args.session_id}"`
              modelInfo = { model: actualModel, type: "system-default", source: "system-default" }
            }
           } else {
-          const resolution = resolveModelWithFallback({
+          const resolution = resolveModelPipeline({
+            intent: {
               userModel: userCategories?.[args.category]?.model,
               categoryDefaultModel: resolved.model ?? sisyphusJuniorModel,
+            },
+            constraints: { availableModels },
+            policy: {
               fallbackChain: requirement.fallbackChain,
-              availableModels,
               systemDefaultModel,
-            })
+            },
+          })
 
-           if (resolution) {
-             const { model: resolvedModel, source, variant: resolvedVariant } = resolution
+            if (resolution) {
+              const { model: resolvedModel, provenance, variant: resolvedVariant } = resolution
              actualModel = resolvedModel
 
              if (!parseModelString(actualModel)) {
@@ -569,7 +572,8 @@ To continue this session: session_id="${args.session_id}"`
              }
 
               let type: "user-defined" | "inherited" | "category-default" | "system-default"
-              switch (source) {
+              const source = provenance
+              switch (provenance) {
                  case "override":
                    type = "user-defined"
                    break
@@ -582,7 +586,7 @@ To continue this session: session_id="${args.session_id}"`
                    break
               }
 
-             modelInfo = { model: actualModel, type, source }
+              modelInfo = { model: actualModel, type, source }
              
              const parsedModel = parseModelString(actualModel)
              const variantToUse = userCategories?.[args.category]?.variant ?? resolvedVariant ?? resolved.config.variant
@@ -780,7 +784,7 @@ To continue this session: session_id="${sessionID}"`
         }
         const agentName = args.subagent_type.trim()
 
-        if (equalsIgnoreCase(agentName, SISYPHUS_JUNIOR_AGENT)) {
+        if (agentName.toLowerCase() === SISYPHUS_JUNIOR_AGENT.toLowerCase()) {
           return `Cannot use subagent_type="${SISYPHUS_JUNIOR_AGENT}" directly. Use category parameter instead (e.g., ${categoryExamples}).
 
 Sisyphus-Junior is spawned automatically when you specify a category. Pick the appropriate category for your task domain.`
@@ -803,12 +807,13 @@ Create the work plan directly - that's your job as the planning agent.`
 
           const callableAgents = agents.filter((a) => a.mode !== "primary")
 
-          const matchedAgent = findByNameCaseInsensitive(callableAgents, agentToUse)
+          const matchedAgent = callableAgents.find(
+            (agent) => agent.name.toLowerCase() === agentToUse.toLowerCase()
+          )
           if (!matchedAgent) {
-            const isPrimaryAgent = findByNameCaseInsensitive(
-              agents.filter((a) => a.mode === "primary"),
-              agentToUse
-            )
+            const isPrimaryAgent = agents
+              .filter((a) => a.mode === "primary")
+              .find((agent) => agent.name.toLowerCase() === agentToUse.toLowerCase())
             if (isPrimaryAgent) {
               return `Cannot call primary agent "${isPrimaryAgent.name}" via delegate_task. Primary agents are top-level orchestrators.`
             }

src/tools/grep/downloader.ts

@@ -1,7 +1,13 @@
-import { existsSync, mkdirSync, chmodSync, unlinkSync, readdirSync } from "node:fs"
+import { existsSync, readdirSync } from "node:fs"
 import { join } from "node:path"
-import { spawn } from "bun"
 import { extractZip as extractZipBase } from "../../shared"
+import {
+  cleanupArchive,
+  downloadArchive,
+  ensureCacheDir,
+  ensureExecutable,
+  extractTarGz as extractTarGzArchive,
+} from "../../shared/binary-downloader"
 
 export function findFileRecursive(dir: string, filename: string): string | null {
   try {
@@ -41,16 +47,6 @@ function getRgPath(): string {
   return join(getInstallDir(), isWindows ? "rg.exe" : "rg")
 }
 
-async function downloadFile(url: string, destPath: string): Promise<void> {
-  const response = await fetch(url)
-  if (!response.ok) {
-    throw new Error(`Failed to download: ${response.status} ${response.statusText}`)
-  }
-
-  const buffer = await response.arrayBuffer()
-  await Bun.write(destPath, buffer)
-}
-
 async function extractTarGz(archivePath: string, destDir: string): Promise<void> {
   const platformKey = getPlatformKey()
 
@@ -62,17 +58,7 @@ async function extractTarGz(archivePath: string, destDir: string): Promise<void>
     args.push("--wildcards", "*/rg")
   }
 
-  const proc = spawn(args, {
-    cwd: destDir,
-    stdout: "pipe",
-    stderr: "pipe",
-  })
-
-  const exitCode = await proc.exited
-  if (exitCode !== 0) {
-    const stderr = await new Response(proc.stderr).text()
-    throw new Error(`Failed to extract tar.gz: ${stderr}`)
-  }
+  await extractTarGzArchive(archivePath, destDir, { args, cwd: destDir })
 }
 
 async function extractZip(archivePath: string, destDir: string): Promise<void> {
@@ -104,14 +90,14 @@ export async function downloadAndInstallRipgrep(): Promise<string> {
     return rgPath
   }
 
-  mkdirSync(installDir, { recursive: true })
+  ensureCacheDir(installDir)
 
   const filename = `ripgrep-${RG_VERSION}-${config.platform}.${config.extension}`
   const url = `https://github.com/BurntSushi/ripgrep/releases/download/${RG_VERSION}/${filename}`
   const archivePath = join(installDir, filename)
 
   try {
-    await downloadFile(url, archivePath)
+    await downloadArchive(url, archivePath)
 
     if (config.extension === "tar.gz") {
       await extractTarGz(archivePath, installDir)
@@ -119,9 +105,7 @@ export async function downloadAndInstallRipgrep(): Promise<string> {
       await extractZip(archivePath, installDir)
     }
 
-    if (process.platform !== "win32") {
-      chmodSync(rgPath, 0o755)
-    }
+    ensureExecutable(rgPath)
 
     if (!existsSync(rgPath)) {
       throw new Error("ripgrep binary not found after extraction")
@@ -129,12 +113,10 @@ export async function downloadAndInstallRipgrep(): Promise<string> {
 
     return rgPath
   } finally {
-    if (existsSync(archivePath)) {
-      try {
-        unlinkSync(archivePath)
-      } catch {
-        // Cleanup failures are non-critical
-      }
+    try {
+      cleanupArchive(archivePath)
+    } catch {
+      // Cleanup failures are non-critical
     }
   }
 }

src/tools/interactive-bash/tools.ts

@@ -96,10 +96,19 @@ The Bash tool can execute these commands directly. Do NOT retry with interactive
 
       const timeoutPromise = new Promise<never>((_, reject) => {
         const id = setTimeout(() => {
-          proc.kill()
-          reject(new Error(`Timeout after ${DEFAULT_TIMEOUT_MS}ms`))
+          const timeoutError = new Error(`Timeout after ${DEFAULT_TIMEOUT_MS}ms`)
+          try {
+            proc.kill()
+            // Fire-and-forget: wait for process exit in background to avoid zombies
+            void proc.exited.catch(() => {})
+          } catch {
+            // Ignore kill errors; we'll still reject with timeoutError below
+          }
+          reject(timeoutError)
         }, DEFAULT_TIMEOUT_MS)
-        proc.exited.then(() => clearTimeout(id))
+        proc.exited
+          .then(() => clearTimeout(id))
+          .catch(() => clearTimeout(id))
       })
 
       // Read stdout and stderr in parallel to avoid race conditions

src/tools/look-at/tools.test.ts

@@ -1,4 +1,5 @@
 import { describe, expect, test } from "bun:test"
+import type { ToolContext } from "@opencode-ai/plugin/tool"
 import { normalizeArgs, validateArgs, createLookAt } from "./tools"
 
 describe("look-at tool", () => {
@@ -92,11 +93,15 @@ describe("look-at tool", () => {
         directory: "/project",
       } as any)
 
-      const toolContext = {
+      const toolContext: ToolContext = {
         sessionID: "parent-session",
         messageID: "parent-message",
         agent: "sisyphus",
+        directory: "/project",
+        worktree: "/project",
         abort: new AbortController().signal,
+        metadata: () => {},
+        ask: async () => {},
       }
 
       const result = await tool.execute(
@@ -130,11 +135,15 @@ describe("look-at tool", () => {
         directory: "/project",
       } as any)
 
-      const toolContext = {
+      const toolContext: ToolContext = {
         sessionID: "parent-session",
         messageID: "parent-message",
         agent: "sisyphus",
+        directory: "/project",
+        worktree: "/project",
         abort: new AbortController().signal,
+        metadata: () => {},
+        ask: async () => {},
       }
 
       const result = await tool.execute(
@@ -186,11 +195,15 @@ describe("look-at tool", () => {
         directory: "/project",
       } as any)
 
-      const toolContext = {
+      const toolContext: ToolContext = {
         sessionID: "parent-session",
         messageID: "parent-message",
         agent: "sisyphus",
+        directory: "/project",
+        worktree: "/project",
         abort: new AbortController().signal,
+        metadata: () => {},
+        ask: async () => {},
       }
 
       await tool.execute(

src/tools/look-at/tools.ts

@@ -3,7 +3,7 @@ import { pathToFileURL } from "node:url"
 import { tool, type PluginInput, type ToolDefinition } from "@opencode-ai/plugin"
 import { LOOK_AT_DESCRIPTION, MULTIMODAL_LOOKER_AGENT } from "./constants"
 import type { LookAtArgs } from "./types"
-import { findByNameCaseInsensitive, log, promptWithModelSuggestionRetry } from "../../shared"
+import { log, promptWithModelSuggestionRetry } from "../../shared"
 
 interface LookAtArgsWithAlias extends LookAtArgs {
   path?: string
@@ -143,7 +143,9 @@ Original error: ${createResult.error}`
         }
         const agents = ((agentsResult as { data?: AgentInfo[] })?.data ?? agentsResult) as AgentInfo[] | undefined
         if (agents?.length) {
-          const matchedAgent = findByNameCaseInsensitive(agents, MULTIMODAL_LOOKER_AGENT)
+          const matchedAgent = agents.find(
+            (agent) => agent.name.toLowerCase() === MULTIMODAL_LOOKER_AGENT.toLowerCase()
+          )
           if (matchedAgent?.model) {
             agentModel = matchedAgent.model
           }

src/tools/lsp/client.ts

@@ -13,6 +13,37 @@ import { getLanguageId } from "./config"
 import type { Diagnostic, ResolvedServer } from "./types"
 import { log } from "../../shared/logger"
 
+/**
+ * Check if the current Bun version is affected by Windows LSP crash bug.
+ * Bun v1.3.5 and earlier have a known segmentation fault issue on Windows
+ * when spawning LSP servers. This was fixed in Bun v1.3.6.
+ * See: https://github.com/oven-sh/bun/issues/25798
+ */
+function checkWindowsBunVersion(): { isAffected: boolean; message: string } | null {
+  if (process.platform !== "win32") return null
+
+  const version = Bun.version
+  const [major, minor, patch] = version.split(".").map((v) => parseInt(v.split("-")[0], 10))
+
+  // Bun v1.3.5 and earlier are affected
+  if (major < 1 || (major === 1 && minor < 3) || (major === 1 && minor === 3 && patch < 6)) {
+    return {
+      isAffected: true,
+      message:
+        `⚠️  Windows + Bun v${version} detected: Known segmentation fault bug with LSP.\n` +
+        `   This causes crashes when using LSP tools (lsp_diagnostics, lsp_goto_definition, etc.).\n` +
+        `   \n` +
+        `   SOLUTION: Upgrade to Bun v1.3.6 or later:\n` +
+        `   powershell -c "irm bun.sh/install.ps1|iex"\n` +
+        `   \n` +
+        `   WORKAROUND: Use WSL instead of native Windows.\n` +
+        `   See: https://github.com/oven-sh/bun/issues/25798`,
+    }
+  }
+
+  return null
+}
+
 interface ManagedClient {
   client: LSPClient
   lastUsedAt: number
@@ -33,10 +64,12 @@ class LSPServerManager {
   }
 
   private registerProcessCleanup(): void {
-    const cleanup = () => {
+    // Synchronous cleanup for 'exit' event (cannot await)
+    const syncCleanup = () => {
       for (const [, managed] of this.clients) {
         try {
-          managed.client.stop()
+          // Fire-and-forget during sync exit - process is terminating
+          void managed.client.stop().catch(() => {})
         } catch {}
       }
       this.clients.clear()
@@ -46,23 +79,30 @@ class LSPServerManager {
       }
     }
 
-    process.on("exit", cleanup)
+    // Async cleanup for signal handlers - properly await all stops
+    const asyncCleanup = async () => {
+      const stopPromises: Promise<void>[] = []
+      for (const [, managed] of this.clients) {
+        stopPromises.push(managed.client.stop().catch(() => {}))
+      }
+      await Promise.allSettled(stopPromises)
+      this.clients.clear()
+      if (this.cleanupInterval) {
+        clearInterval(this.cleanupInterval)
+        this.cleanupInterval = null
+      }
+    }
 
-    process.on("SIGINT", () => {
-      cleanup()
-      process.exit(0)
-    })
+    process.on("exit", syncCleanup)
 
-    process.on("SIGTERM", () => {
-      cleanup()
-      process.exit(0)
-    })
+    // Don't call process.exit() here - let other handlers complete their cleanup first
+    // The background-agent manager handles the final exit call
+    // Use async handlers to properly await LSP subprocess cleanup
+    process.on("SIGINT", () => void asyncCleanup().catch(() => {}))
+    process.on("SIGTERM", () => void asyncCleanup().catch(() => {}))
 
     if (process.platform === "win32") {
-      process.on("SIGBREAK", () => {
-        cleanup()
-        process.exit(0)
-      })
+      process.on("SIGBREAK", () => void asyncCleanup().catch(() => {}))
     }
   }
 
@@ -226,6 +266,13 @@ export class LSPClient {
   ) {}
 
   async start(): Promise<void> {
+    const windowsCheck = checkWindowsBunVersion()
+    if (windowsCheck?.isAffected) {
+      throw new Error(
+        `LSP server cannot be started safely.\n\n${windowsCheck.message}`
+      )
+    }
+
     this.proc = spawn(this.server.command, {
       stdin: "pipe",
       stdout: "pipe",
@@ -532,8 +579,34 @@ export class LSPClient {
       this.connection.dispose()
       this.connection = null
     }
-    this.proc?.kill()
-    this.proc = null
+    const proc = this.proc
+    if (proc) {
+      this.proc = null
+      let exitedBeforeTimeout = false
+      try {
+        proc.kill()
+        // Wait for exit with timeout to prevent indefinite hang
+        let timeoutId: ReturnType<typeof setTimeout> | undefined
+        const timeoutPromise = new Promise<void>((resolve) => {
+          timeoutId = setTimeout(resolve, 5000)
+        })
+        await Promise.race([
+          proc.exited.then(() => { exitedBeforeTimeout = true }).finally(() => timeoutId && clearTimeout(timeoutId)),
+          timeoutPromise,
+        ])
+        if (!exitedBeforeTimeout) {
+          log("[LSPClient] Process did not exit within timeout, escalating to SIGKILL")
+          try {
+            proc.kill("SIGKILL")
+            // Wait briefly for SIGKILL to take effect
+            await Promise.race([
+              proc.exited,
+              new Promise<void>((resolve) => setTimeout(resolve, 1000)),
+            ])
+          } catch {}
+        }
+      } catch {}
+    }
     this.processExited = true
     this.diagnosticsStore.clear()
   }

src/tools/session-manager/tools.test.ts

@@ -2,11 +2,17 @@ import { describe, test, expect } from "bun:test"
 import { session_list, session_read, session_search, session_info } from "./tools"
 import type { ToolContext } from "@opencode-ai/plugin/tool"
 
+const projectDir = "/Users/yeongyu/local-workspaces/oh-my-opencode"
+
 const mockContext: ToolContext = {
   sessionID: "test-session",
   messageID: "test-message",
   agent: "test-agent",
+  directory: projectDir,
+  worktree: projectDir,
   abort: new AbortController().signal,
+  metadata: () => {},
+  ask: async () => {},
 }
 
 describe("session-manager tools", () => {

src/tools/skill-mcp/tools.test.ts

@@ -1,4 +1,5 @@
 import { describe, it, expect, beforeEach, mock } from "bun:test"
+import type { ToolContext } from "@opencode-ai/plugin/tool"
 import { createSkillMcpTool, applyGrepFilter } from "./tools"
 import { SkillMcpManager } from "../../features/skill-mcp-manager"
 import type { LoadedSkill } from "../../features/opencode-skill-loader/types"
@@ -18,11 +19,15 @@ function createMockSkillWithMcp(name: string, mcpServers: Record<string, unknown
   }
 }
 
-const mockContext = {
+const mockContext: ToolContext = {
   sessionID: "test-session",
   messageID: "msg-1",
   agent: "test-agent",
+  directory: "/test",
+  worktree: "/test",
   abort: new AbortController().signal,
+  metadata: () => {},
+  ask: async () => {},
 }
 
 describe("skill_mcp tool", () => {

src/tools/skill/tools.test.ts

@@ -1,4 +1,5 @@
 import { describe, it, expect, beforeEach, mock, spyOn } from "bun:test"
+import type { ToolContext } from "@opencode-ai/plugin/tool"
 import * as fs from "node:fs"
 import { createSkillTool } from "./tools"
 import { SkillMcpManager } from "../../features/skill-mcp-manager"
@@ -50,11 +51,15 @@ function createMockSkillWithMcp(name: string, mcpServers: Record<string, unknown
   }
 }
 
-const mockContext = {
+const mockContext: ToolContext = {
   sessionID: "test-session",
   messageID: "msg-1",
   agent: "test-agent",
+  directory: "/test",
+  worktree: "/test",
   abort: new AbortController().signal,
+  metadata: () => {},
+  ask: async () => {},
 }
 
 describe("skill tool - synchronous description", () => {