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/ISSUE_TEMPLATE/bug_report.yml

@@ -14,6 +14,8 @@ body:
       label: Prerequisites
       description: Please confirm the following before submitting
       options:
+        - label: I will write this issue in English (see our [Language Policy](https://github.com/code-yeongyu/oh-my-opencode/blob/dev/CONTRIBUTING.md#language-policy))
+          required: true
         - label: I have searched existing issues to avoid duplicates
           required: true
         - label: I am using the latest version of oh-my-opencode

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -14,6 +14,8 @@ body:
       label: Prerequisites
       description: Please confirm the following before submitting
       options:
+        - label: I will write this issue in English (see our [Language Policy](https://github.com/code-yeongyu/oh-my-opencode/blob/dev/CONTRIBUTING.md#language-policy))
+          required: true
         - label: I have searched existing issues and discussions to avoid duplicates
           required: true
         - label: This feature request is specific to oh-my-opencode (not OpenCode core)

.github/ISSUE_TEMPLATE/general.yml

@@ -14,6 +14,8 @@ body:
       label: Prerequisites
       description: Please confirm the following before submitting
       options:
+        - label: I will write this issue in English (see our [Language Policy](https://github.com/code-yeongyu/oh-my-opencode/blob/dev/CONTRIBUTING.md#language-policy))
+          required: true
         - label: I have searched existing issues and discussions
           required: true
         - label: I have read the [documentation](https://github.com/code-yeongyu/oh-my-opencode#readme)

.github/workflows/ci.yml

@@ -4,13 +4,32 @@ on:
   push:
     branches: [master, dev]
   pull_request:
-    branches: [dev]
+    branches: [master, dev]
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
 jobs:
+  # Block PRs targeting master branch
+  block-master-pr:
+    runs-on: ubuntu-latest
+    if: github.event_name == 'pull_request'
+    steps:
+      - name: Check PR target branch
+        run: |
+          if [ "${{ github.base_ref }}" = "master" ]; then
+            echo "::error::PRs to master branch are not allowed. Please target the 'dev' branch instead."
+            echo ""
+            echo "PULL REQUESTS TO MASTER ARE BLOCKED"
+            echo ""
+            echo "All PRs must target the 'dev' branch."
+            echo "Please close this PR and create a new one targeting 'dev'."
+            exit 1
+          else
+            echo "PR targets '${{ github.base_ref }}' branch - OK"
+          fi
+
   test:
     runs-on: ubuntu-latest
     steps:
@@ -25,8 +44,34 @@ jobs:
         env:
           BUN_INSTALL_ALLOW_SCRIPTS: "@ast-grep/napi"
 
-      - name: Run tests
-        run: bun test
+      - name: Run mock-heavy tests (isolated)
+        run: |
+          # These files use mock.module() which pollutes module cache
+          # 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
+        run: |
+          # Run all other tests (mock-heavy ones are re-run but that's acceptable)
+          bun test bin script src/cli src/config src/mcp src/index.test.ts \
+            src/agents src/tools src/shared \
+            src/hooks/anthropic-context-window-limit-recovery \
+            src/hooks/claude-code-compatibility \
+            src/hooks/context-injection \
+            src/hooks/provider-toast \
+            src/hooks/session-notification \
+            src/hooks/sisyphus \
+            src/hooks/todo-continuation-enforcer \
+            src/features/background-agent \
+            src/features/builtin-commands \
+            src/features/builtin-skills \
+            src/features/claude-code-session-state \
+            src/features/hook-message-injector \
+            src/features/opencode-skill-loader \
+            src/features/skill-mcp-manager
 
   typecheck:
     runs-on: ubuntu-latest

.github/workflows/cla.yml

@@ -25,7 +25,7 @@ jobs:
           path-to-signatures: 'signatures/cla.json'
           path-to-document: 'https://github.com/code-yeongyu/oh-my-opencode/blob/master/CLA.md'
           branch: 'dev'
-          allowlist: bot*,dependabot*,github-actions*,*[bot],sisyphus-dev-ai
+          allowlist: code-yeongyu,bot*,dependabot*,github-actions*,*[bot],sisyphus-dev-ai
           custom-notsigned-prcomment: |
             Thank you for your contribution! Before we can merge this PR, we need you to sign our [Contributor License Agreement (CLA)](https://github.com/code-yeongyu/oh-my-opencode/blob/master/CLA.md).
             

.github/workflows/publish-platform.yml

@@ -28,11 +28,20 @@ permissions:
   id-token: write
 
 jobs:
-  publish-platform:
-    runs-on: ubuntu-latest
+  # =============================================================================
+  # Job 1: Build binaries for all platforms
+  # - Windows builds on windows-latest (avoid bun cross-compile segfault)
+  # - All other platforms build on ubuntu-latest
+  # - Uploads compressed artifacts for the publish job
+  # =============================================================================
+  build:
+    runs-on: ${{ matrix.platform == 'windows-x64' && 'windows-latest' || 'ubuntu-latest' }}
+    defaults:
+      run:
+        shell: bash
     strategy:
       fail-fast: false
-      max-parallel: 2
+      max-parallel: 7
       matrix:
         platform: [darwin-arm64, darwin-x64, linux-x64, linux-arm64, linux-x64-musl, linux-arm64-musl, windows-x64]
     steps:
@@ -42,11 +51,6 @@ jobs:
         with:
           bun-version: latest
 
-      - uses: actions/setup-node@v4
-        with:
-          node-version: "24"
-          registry-url: "https://registry.npmjs.org"
-
       - name: Install dependencies
         run: bun install
         env:
@@ -58,15 +62,20 @@ jobs:
           PKG_NAME="oh-my-opencode-${{ matrix.platform }}"
           VERSION="${{ inputs.version }}"
           STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://registry.npmjs.org/${PKG_NAME}/${VERSION}")
+          # Convert platform name for output (replace - with _)
+          PLATFORM_KEY="${{ matrix.platform }}"
+          PLATFORM_KEY="${PLATFORM_KEY//-/_}"
           if [ "$STATUS" = "200" ]; then
             echo "skip=true" >> $GITHUB_OUTPUT
+            echo "skip_${PLATFORM_KEY}=true" >> $GITHUB_OUTPUT
             echo "✓ ${PKG_NAME}@${VERSION} already published"
           else
             echo "skip=false" >> $GITHUB_OUTPUT
+            echo "skip_${PLATFORM_KEY}=false" >> $GITHUB_OUTPUT
             echo "→ ${PKG_NAME}@${VERSION} needs publishing"
           fi
 
-      - name: Update version
+      - name: Update version in package.json
         if: steps.check.outputs.skip != 'true'
         run: |
           VERSION="${{ inputs.version }}"
@@ -94,15 +103,109 @@ jobs:
           fi
           
           bun build src/cli/index.ts --compile --minify --target=$TARGET --outfile=$OUTPUT
+          
+          echo "Built binary:"
+          ls -lh "$OUTPUT"
+
+      - name: Compress binary
+        if: steps.check.outputs.skip != 'true'
+        run: |
+          PLATFORM="${{ matrix.platform }}"
+          cd packages/${PLATFORM}
+          
+          if [ "$PLATFORM" = "windows-x64" ]; then
+            # Windows: use 7z (pre-installed on windows-latest)
+            7z a -tzip ../../binary-${PLATFORM}.zip bin/ package.json
+          else
+            # Unix: use tar.gz
+            tar -czvf ../../binary-${PLATFORM}.tar.gz bin/ package.json
+          fi
+          
+          cd ../..
+          echo "Compressed artifact:"
+          ls -lh binary-${PLATFORM}.*
+
+      - name: Upload artifact
+        if: steps.check.outputs.skip != 'true'
+        uses: actions/upload-artifact@v4
+        with:
+          name: binary-${{ matrix.platform }}
+          path: |
+            binary-${{ matrix.platform }}.tar.gz
+            binary-${{ matrix.platform }}.zip
+          retention-days: 1
+          if-no-files-found: error
+
+  # =============================================================================
+  # Job 2: Publish all platforms using OIDC/Provenance
+  # - Runs on ubuntu-latest for ALL platforms (just downloading artifacts)
+  # - Uses npm Trusted Publishing (OIDC) - no NODE_AUTH_TOKEN needed
+  # - Fresh OIDC token at publish time avoids timeout issues
+  # =============================================================================
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      max-parallel: 2
+      matrix:
+        platform: [darwin-arm64, darwin-x64, linux-x64, linux-arm64, linux-x64-musl, linux-arm64-musl, windows-x64]
+    steps:
+      - name: Check if already published
+        id: check
+        run: |
+          PKG_NAME="oh-my-opencode-${{ matrix.platform }}"
+          VERSION="${{ inputs.version }}"
+          STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://registry.npmjs.org/${PKG_NAME}/${VERSION}")
+          if [ "$STATUS" = "200" ]; then
+            echo "skip=true" >> $GITHUB_OUTPUT
+            echo "✓ ${PKG_NAME}@${VERSION} already published, skipping"
+          else
+            echo "skip=false" >> $GITHUB_OUTPUT
+            echo "→ ${PKG_NAME}@${VERSION} will be published"
+          fi
+
+      - name: Download artifact
+        if: steps.check.outputs.skip != 'true'
+        uses: actions/download-artifact@v4
+        with:
+          name: binary-${{ matrix.platform }}
+          path: .
+
+      - name: Extract artifact
+        if: steps.check.outputs.skip != 'true'
+        run: |
+          PLATFORM="${{ matrix.platform }}"
+          mkdir -p packages/${PLATFORM}
+          
+          if [ "$PLATFORM" = "windows-x64" ]; then
+            unzip binary-${PLATFORM}.zip -d packages/${PLATFORM}/
+          else
+            tar -xzvf binary-${PLATFORM}.tar.gz -C packages/${PLATFORM}/
+          fi
+          
+          echo "Extracted contents:"
+          ls -la packages/${PLATFORM}/
+          ls -la packages/${PLATFORM}/bin/
+
+      - uses: actions/setup-node@v4
+        if: steps.check.outputs.skip != 'true'
+        with:
+          node-version: "24"
+          registry-url: "https://registry.npmjs.org"
 
       - name: Publish ${{ matrix.platform }}
         if: steps.check.outputs.skip != 'true'
         run: |
           cd packages/${{ matrix.platform }}
+          
           TAG_ARG=""
           if [ -n "${{ inputs.dist_tag }}" ]; then
             TAG_ARG="--tag ${{ inputs.dist_tag }}"
           fi
-          npm publish --access public $TAG_ARG
+          
+          npm publish --access public --provenance $TAG_ARG
         env:
-          NPM_CONFIG_PROVENANCE: false
+          NODE_AUTH_TOKEN: ${{ secrets.NODE_AUTH_TOKEN }}
+          NPM_CONFIG_PROVENANCE: true
+        timeout-minutes: 15

.github/workflows/publish.yml

@@ -45,8 +45,33 @@ jobs:
         env:
           BUN_INSTALL_ALLOW_SCRIPTS: "@ast-grep/napi"
 
-      - name: Run tests
-        run: bun test
+      - name: Run mock-heavy tests (isolated)
+        run: |
+          # These files use mock.module() which pollutes module cache
+          # Run them in separate processes to prevent cross-file contamination
+          bun test src/plugin-handlers
+          bun test src/hooks/atlas
+          bun test src/features/tmux-subagent
+
+      - name: Run remaining tests
+        run: |
+          # Run all other tests (mock-heavy ones are re-run but that's acceptable)
+          bun test bin script src/cli src/config src/mcp src/index.test.ts \
+            src/agents src/tools src/shared \
+            src/hooks/anthropic-context-window-limit-recovery \
+            src/hooks/claude-code-compatibility \
+            src/hooks/context-injection \
+            src/hooks/provider-toast \
+            src/hooks/session-notification \
+            src/hooks/sisyphus \
+            src/hooks/todo-continuation-enforcer \
+            src/features/background-agent \
+            src/features/builtin-commands \
+            src/features/builtin-skills \
+            src/features/claude-code-session-state \
+            src/features/hook-message-injector \
+            src/features/opencode-skill-loader \
+            src/features/skill-mcp-manager
 
   typecheck:
     runs-on: ubuntu-latest

.github/workflows/sisyphus-agent.yml

@@ -152,6 +152,41 @@ jobs:
                   "limit": { "context": 200000, "output": 64000 }
                 }
               }
+            } |
+            .provider["zai-coding-plan"] = {
+              "name": "Z.AI Coding Plan",
+              "npm": "@ai-sdk/openai-compatible",
+              "options": {
+                "baseURL": "https://api.z.ai/api/paas/v4"
+              },
+              "models": {
+                "glm-4.7": {
+                  "id": "glm-4.7",
+                  "name": "GLM 4.7",
+                  "limit": { "context": 128000, "output": 16000 }
+                },
+                "glm-4.6v": {
+                  "id": "glm-4.6v",
+                  "name": "GLM 4.6 Vision",
+                  "limit": { "context": 128000, "output": 16000 }
+                }
+              }
+            } |
+            .provider.openai = {
+              "name": "OpenAI",
+              "npm": "@ai-sdk/openai",
+              "models": {
+                "gpt-5.2": {
+                  "id": "gpt-5.2",
+                  "name": "GPT-5.2",
+                  "limit": { "context": 128000, "output": 16000 }
+                },
+                "gpt-5.2-codex": {
+                  "id": "gpt-5.2-codex",
+                  "name": "GPT-5.2 Codex",
+                  "limit": { "context": 128000, "output": 32000 }
+                }
+              }
             }
           ' "$OPENCODE_JSON" > /tmp/oc.json && mv /tmp/oc.json "$OPENCODE_JSON"
 
@@ -287,6 +322,9 @@ jobs:
           )
           jq --arg append "$PROMPT_APPEND" '.agents.Sisyphus.prompt_append = $append' "$OMO_JSON" > /tmp/omo.json && mv /tmp/omo.json "$OMO_JSON"
 
+          # Add categories configuration for unspecified-low to use GLM 4.7
+          jq '.categories["unspecified-low"] = { "model": "zai-coding-plan/glm-4.7" }' "$OMO_JSON" > /tmp/omo.json && mv /tmp/omo.json "$OMO_JSON"
+
           mkdir -p ~/.local/share/opencode
           echo "$OPENCODE_AUTH_JSON" > ~/.local/share/opencode/auth.json
           chmod 600 ~/.local/share/opencode/auth.json

.gitignore

@@ -33,3 +33,4 @@ yarn.lock
 test-injection/
 notepad.md
 oauth-success.html
+*.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/command/publish.md

@@ -35,6 +35,8 @@ You are the release manager for oh-my-opencode. Execute the FULL publish workflo
   { "id": "draft-release-notes", "content": "Draft enhanced release notes content", "status": "pending", "priority": "high" },
   { "id": "update-release-notes", "content": "Update GitHub release with enhanced notes", "status": "pending", "priority": "high" },
   { "id": "verify-npm", "content": "Verify npm package published successfully", "status": "pending", "priority": "high" },
+  { "id": "wait-platform-workflow", "content": "Wait for publish-platform workflow completion", "status": "pending", "priority": "high" },
+  { "id": "verify-platform-binaries", "content": "Verify all 7 platform binary packages published", "status": "pending", "priority": "high" },
   { "id": "final-confirmation", "content": "Final confirmation to user with links", "status": "pending", "priority": "low" }
 ]
 ```
@@ -219,12 +221,64 @@ Compare with expected version. If not matching after 2 minutes, warn user about
 
 ---
 
+## STEP 8.5: WAIT FOR PLATFORM WORKFLOW COMPLETION
+
+The main publish workflow triggers a separate `publish-platform` workflow for platform-specific binaries.
+
+1. Find the publish-platform workflow run triggered by the main workflow:
+```bash
+gh run list --workflow=publish-platform --limit=1 --json databaseId,status,conclusion --jq '.[0]'
+```
+
+2. Poll workflow status every 30 seconds until completion:
+```bash
+gh run view {platform_run_id} --json status,conclusion --jq '{status: .status, conclusion: .conclusion}'
+```
+
+**IMPORTANT: Use polling loop, NOT sleep commands.**
+
+If conclusion is `failure`, show error logs:
+```bash
+gh run view {platform_run_id} --log-failed
+```
+
+---
+
+## STEP 8.6: VERIFY PLATFORM BINARY PACKAGES
+
+After publish-platform workflow completes, verify all 7 platform packages are published:
+
+```bash
+PLATFORMS="darwin-arm64 darwin-x64 linux-x64 linux-arm64 linux-x64-musl linux-arm64-musl windows-x64"
+for PLATFORM in $PLATFORMS; do
+  npm view "oh-my-opencode-${PLATFORM}" version
+done
+```
+
+All 7 packages should show the same version as the main package (`${NEW_VERSION}`).
+
+**Expected packages:**
+| Package | Description |
+|---------|-------------|
+| `oh-my-opencode-darwin-arm64` | macOS Apple Silicon |
+| `oh-my-opencode-darwin-x64` | macOS Intel |
+| `oh-my-opencode-linux-x64` | Linux x64 (glibc) |
+| `oh-my-opencode-linux-arm64` | Linux ARM64 (glibc) |
+| `oh-my-opencode-linux-x64-musl` | Linux x64 (musl/Alpine) |
+| `oh-my-opencode-linux-arm64-musl` | Linux ARM64 (musl/Alpine) |
+| `oh-my-opencode-windows-x64` | Windows x64 |
+
+If any platform package version doesn't match, warn the user and suggest checking the publish-platform workflow logs.
+
+---
+
 ## STEP 9: FINAL CONFIRMATION
 
 Report success to user with:
 - New version number
 - GitHub release URL: https://github.com/code-yeongyu/oh-my-opencode/releases/tag/v{version}
 - npm package URL: https://www.npmjs.com/package/oh-my-opencode
+- Platform packages status: List all 7 platform packages with their versions
 
 ---
 
@@ -234,6 +288,8 @@ Report success to user with:
 - **Release not found**: Wait and retry, may be propagation delay
 - **npm not updated**: npm can take 1-5 minutes to propagate, inform user
 - **Permission denied**: User may need to re-authenticate with `gh auth login`
+- **Platform workflow fails**: Show logs from publish-platform workflow, check which platform failed
+- **Platform package missing**: Some platforms may fail due to cross-compilation issues, suggest re-running publish-platform workflow manually
 
 ## LANGUAGE
 

.opencode/command/remove-deadcode.md

@@ -0,0 +1,342 @@
+---
+description: Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits
+---
+
+<command-instruction>
+You are a dead code removal specialist. Execute the FULL dead code removal workflow using ultrawork mode.
+
+Your core weapon: **LSP FindReferences**. If a symbol has ZERO external references, it's dead. Remove it.
+
+## CRITICAL RULES
+
+1. **LSP is law.** Never guess. Always verify with `LspFindReferences` before removing ANYTHING.
+2. **One removal = one commit.** Every dead code removal gets its own atomic commit.
+3. **Test after every removal.** Run `bun test` after each. If it fails, REVERT and skip.
+4. **Leaf-first order.** Remove deepest unused symbols first, then work up the dependency chain. Removing a leaf may expose new dead code upstream.
+5. **Never remove entry points.** `src/index.ts`, `src/cli/index.ts`, test files, config files, and files in `packages/` are off-limits unless explicitly targeted.
+
+---
+
+## STEP 0: REGISTER TODO LIST (MANDATORY FIRST ACTION)
+
+```
+TodoWrite([
+  {"id": "scan", "content": "PHASE 1: Scan codebase for dead code candidates using LSP + explore agents", "status": "pending", "priority": "high"},
+  {"id": "verify", "content": "PHASE 2: Verify each candidate with LspFindReferences - zero false positives", "status": "pending", "priority": "high"},
+  {"id": "plan", "content": "PHASE 3: Plan removal order (leaf-first dependency order)", "status": "pending", "priority": "high"},
+  {"id": "remove", "content": "PHASE 4: Remove dead code one-by-one (remove -> test -> commit loop)", "status": "pending", "priority": "high"},
+  {"id": "final", "content": "PHASE 5: Final verification - full test suite + build + typecheck", "status": "pending", "priority": "high"}
+])
+```
+
+---
+
+## PHASE 1: SCAN FOR DEAD CODE CANDIDATES
+
+**Mark scan as in_progress.**
+
+### 1.1: Launch Parallel Explore Agents (ALL BACKGROUND)
+
+Fire ALL simultaneously:
+
+```
+// Agent 1: Find all exported symbols
+delegate_task(subagent_type="explore", run_in_background=true,
+  prompt="Find ALL exported functions, classes, types, interfaces, and constants across src/.
+  List each with: file path, line number, symbol name, export type (named/default).
+  EXCLUDE: src/index.ts root exports, test files.
+  Return as structured list.")
+
+// Agent 2: Find potentially unused files
+delegate_task(subagent_type="explore", run_in_background=true,
+  prompt="Find files in src/ that are NOT imported by any other file.
+  Check import/require statements across the entire codebase.
+  EXCLUDE: index.ts files, test files, entry points, config files, .md files.
+  Return list of potentially orphaned files.")
+
+// Agent 3: Find unused imports within files
+delegate_task(subagent_type="explore", run_in_background=true,
+  prompt="Find unused imports across src/**/*.ts files.
+  Look for import statements where the imported symbol is never referenced in the file body.
+  Return: file path, line number, imported symbol name.")
+
+// Agent 4: Find functions/variables only used in their own declaration
+delegate_task(subagent_type="explore", run_in_background=true,
+  prompt="Find private/non-exported functions, variables, and types in src/**/*.ts that appear
+  to have zero usage beyond their declaration. Return: file path, line number, symbol name.")
+```
+
+### 1.2: Direct AST-Grep Scans (WHILE AGENTS RUN)
+
+```typescript
+// Find unused imports pattern
+ast_grep_search(pattern="import { $NAME } from '$PATH'", lang="typescript", paths=["src/"])
+
+// Find empty export objects
+ast_grep_search(pattern="export {}", lang="typescript", paths=["src/"])
+```
+
+### 1.3: Collect All Results
+
+Collect background agent results. Compile into a master candidate list:
+
+```
+## DEAD CODE CANDIDATES
+
+| # | File | Line | Symbol | Type | Confidence |
+|---|------|------|--------|------|------------|
+| 1 | src/foo.ts | 42 | unusedFunc | function | HIGH |
+| 2 | src/bar.ts | 10 | OldType | type | MEDIUM |
+```
+
+**Mark scan as completed.**
+
+---
+
+## PHASE 2: VERIFY WITH LSP (ZERO FALSE POSITIVES)
+
+**Mark verify as in_progress.**
+
+For EVERY candidate from Phase 1, run this verification:
+
+### 2.1: The LSP Verification Protocol
+
+For each candidate symbol:
+
+```typescript
+// Step 1: Find the symbol's exact position
+LspDocumentSymbols(filePath)  // Get line/character of the symbol
+
+// Step 2: Find ALL references across the ENTIRE workspace
+LspFindReferences(filePath, line, character, includeDeclaration=false)
+// includeDeclaration=false → only counts USAGES, not the definition itself
+
+// Step 3: Evaluate
+// 0 references → CONFIRMED DEAD CODE
+// 1+ references → NOT dead, remove from candidate list
+```
+
+### 2.2: False Positive Guards
+
+**NEVER mark as dead code if:**
+- Symbol is in `src/index.ts` (package entry point)
+- Symbol is in any `index.ts` that re-exports (barrel file check: look if it's re-exported)
+- Symbol is referenced in test files (tests are valid consumers)
+- Symbol has `@public` or `@api` JSDoc tags
+- Symbol is in a file listed in `package.json` exports
+- Symbol is a hook factory (`createXXXHook`) registered in `src/index.ts`
+- Symbol is a tool factory (`createXXXTool`) registered in tool loading
+- Symbol is an agent definition registered in `agentSources`
+- File is a command template, skill definition, or MCP config
+
+### 2.3: Build Confirmed Dead Code List
+
+After verification, produce:
+
+```
+## CONFIRMED DEAD CODE (LSP-verified, 0 external references)
+
+| # | File | Line | Symbol | Type | Safe to Remove |
+|---|------|------|--------|------|----------------|
+| 1 | src/foo.ts | 42 | unusedFunc | function | YES |
+```
+
+**If ZERO confirmed dead code found: Report "No dead code found" and STOP.**
+
+**Mark verify as completed.**
+
+---
+
+## PHASE 3: PLAN REMOVAL ORDER
+
+**Mark plan as in_progress.**
+
+### 3.1: Dependency Analysis
+
+For each confirmed dead symbol:
+1. Check if removing it would expose other dead code
+2. Check if other dead symbols depend on this one
+3. Build removal dependency graph
+
+### 3.2: Order by Leaf-First
+
+```
+Removal Order:
+1. [Leaf symbols - no other dead code depends on them]
+2. [Intermediate symbols - depended on only by already-removed dead code]
+3. [Dead files - entire files with no live exports]
+```
+
+### 3.3: Register Granular Todos
+
+Create one todo per removal:
+
+```
+TodoWrite([
+  {"id": "remove-1", "content": "Remove unusedFunc from src/foo.ts:42", "status": "pending", "priority": "high"},
+  {"id": "remove-2", "content": "Remove OldType from src/bar.ts:10", "status": "pending", "priority": "high"},
+  // ... one per confirmed dead symbol
+])
+```
+
+**Mark plan as completed.**
+
+---
+
+## PHASE 4: ITERATIVE REMOVAL LOOP
+
+**Mark remove as in_progress.**
+
+For EACH dead code item, execute this exact loop:
+
+### 4.1: Pre-Removal Check
+
+```typescript
+// Re-verify it's still dead (previous removals may have changed things)
+LspFindReferences(filePath, line, character, includeDeclaration=false)
+// If references > 0 now → SKIP (previous removal exposed a new consumer)
+```
+
+### 4.2: Remove the Dead Code
+
+Use appropriate tool:
+
+**For unused imports:**
+```typescript
+Edit(filePath, oldString="import { deadSymbol } from '...';\n", newString="")
+// Or if it's one of many imports, remove just the symbol from the import list
+```
+
+**For unused functions/classes/types:**
+```typescript
+// Read the full symbol extent first
+Read(filePath, offset=startLine, limit=endLine-startLine+1)
+// Then remove it
+Edit(filePath, oldString="[full symbol text]", newString="")
+```
+
+**For dead files:**
+```bash
+# Only after confirming ZERO imports point to this file
+rm "path/to/dead-file.ts"
+```
+
+**After removal, also clean up:**
+- Remove any imports that were ONLY used by the removed code
+- Remove any now-empty import statements
+- Fix any trailing whitespace / double blank lines left behind
+
+### 4.3: Post-Removal Verification
+
+```typescript
+// 1. LSP diagnostics on changed file
+LspDiagnostics(filePath, severity="error")
+// Must be clean (or only pre-existing errors)
+
+// 2. Run tests
+bash("bun test")
+// Must pass
+
+// 3. Typecheck
+bash("bun run typecheck")
+// Must pass
+```
+
+### 4.4: Handle Failures
+
+If ANY verification fails:
+1. **REVERT** the change immediately (`git checkout -- [file]`)
+2. Mark this removal todo as `cancelled` with note: "Removal caused [error]. Skipped."
+3. Proceed to next item
+
+### 4.5: Commit
+
+```bash
+git add [changed-files]
+git commit -m "refactor: remove unused [symbolType] [symbolName] from [filePath]"
+```
+
+Mark this removal todo as `completed`.
+
+### 4.6: Re-scan After Removal
+
+After removing a symbol, check if its removal exposed NEW dead code:
+- Were there imports that only existed to serve the removed symbol?
+- Are there other symbols in the same file now unreferenced?
+
+If new dead code is found, add it to the removal queue.
+
+**Repeat 4.1-4.6 for every item. Mark remove as completed when done.**
+
+---
+
+## PHASE 5: FINAL VERIFICATION
+
+**Mark final as in_progress.**
+
+### 5.1: Full Test Suite
+```bash
+bun test
+```
+
+### 5.2: Full Typecheck
+```bash
+bun run typecheck
+```
+
+### 5.3: Full Build
+```bash
+bun run build
+```
+
+### 5.4: Summary Report
+
+```markdown
+## Dead Code Removal Complete
+
+### Removed
+| # | Symbol | File | Type | Commit |
+|---|--------|------|------|--------|
+| 1 | unusedFunc | src/foo.ts | function | abc1234 |
+
+### Skipped (caused failures)
+| # | Symbol | File | Reason |
+|---|--------|------|--------|
+| 1 | riskyFunc | src/bar.ts | Test failure: [details] |
+
+### Verification
+- Tests: PASSED (X/Y passing)
+- Typecheck: CLEAN
+- Build: SUCCESS
+- Total dead code removed: N symbols across M files
+- Total commits: K atomic commits
+```
+
+**Mark final as completed.**
+
+---
+
+## SCOPE CONTROL
+
+**If $ARGUMENTS is provided**, narrow the scan to the specified scope:
+- File path: Only scan that file
+- Directory: Only scan that directory
+- Symbol name: Only check that specific symbol
+- "all" or empty: Full project scan (default)
+
+## ABORT CONDITIONS
+
+**STOP and report to user if:**
+- 3 consecutive removals cause test failures
+- Build breaks and cannot be fixed by reverting
+- More than 50 candidates found (ask user to narrow scope)
+
+## LANGUAGE
+
+Use English for commit messages and technical output.
+
+</command-instruction>
+
+<user-request>
+$ARGUMENTS
+</user-request>

.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

AGENTS.md

@@ -1,12 +1,24 @@
 # PROJECT KNOWLEDGE BASE
 
-**Generated:** 2026-01-23T02:09:00+09:00
-**Commit:** 0e18efc7
+**Generated:** 2026-01-26T14:50:00+09:00
+**Commit:** 9d66b807
 **Branch:** dev
 
+---
+
+## **IMPORTANT: PULL REQUEST TARGET BRANCH**
+
+> **ALL PULL REQUESTS MUST TARGET THE `dev` BRANCH.**
+>
+> **DO NOT CREATE PULL REQUESTS TARGETING `master` BRANCH.**
+>
+> PRs to `master` will be automatically rejected by CI.
+
+---
+
 ## OVERVIEW
 
-OpenCode plugin: multi-model agent orchestration (Claude Opus 4.5, GPT-5.2, Gemini 3, Grok, GLM-4.7). 31 lifecycle hooks, 20+ tools (LSP, AST-Grep, delegation), 10 specialized agents, full Claude Code compatibility. "oh-my-zsh" for OpenCode.
+OpenCode plugin: multi-model agent orchestration (Claude Opus 4.5, GPT-5.2, Gemini 3 Flash, Grok Code). 32 lifecycle hooks, 20+ tools (LSP, AST-Grep, delegation), 10 specialized agents, full Claude Code compatibility. "oh-my-zsh" for OpenCode.
 
 ## STRUCTURE
 
@@ -14,14 +26,14 @@ OpenCode plugin: multi-model agent orchestration (Claude Opus 4.5, GPT-5.2, Gemi
 oh-my-opencode/
 ├── src/
 │   ├── agents/        # 10 AI agents - see src/agents/AGENTS.md
-│   ├── hooks/         # 31 lifecycle hooks - see src/hooks/AGENTS.md
+│   ├── hooks/         # 32 lifecycle hooks - see src/hooks/AGENTS.md
 │   ├── tools/         # 20+ tools - see src/tools/AGENTS.md
 │   ├── features/      # Background agents, Claude Code compat - see src/features/AGENTS.md
-│   ├── shared/        # 50 cross-cutting utilities - see src/shared/AGENTS.md
+│   ├── shared/        # 55 cross-cutting utilities - see src/shared/AGENTS.md
 │   ├── cli/           # CLI installer, doctor - see src/cli/AGENTS.md
 │   ├── mcp/           # Built-in MCPs - see src/mcp/AGENTS.md
 │   ├── config/        # Zod schema, TypeScript types
-│   └── index.ts       # Main plugin entry (590 lines)
+│   └── index.ts       # Main plugin entry (672 lines)
 ├── script/            # build-schema.ts, build-binaries.ts
 ├── packages/          # 7 platform-specific binaries
 └── dist/              # Build output (ESM + .d.ts)
@@ -36,9 +48,10 @@ oh-my-opencode/
 | Add tool | `src/tools/` | Dir with index/types/constants/tools.ts |
 | Add MCP | `src/mcp/` | Create config, add to index.ts |
 | Add skill | `src/features/builtin-skills/` | Create dir with SKILL.md |
+| Add command | `src/features/builtin-commands/` | Add template + register in commands.ts |
 | Config schema | `src/config/schema.ts` | Zod schema, run `bun run build:schema` |
-| Background agents | `src/features/background-agent/` | manager.ts (1335 lines) |
-| Orchestrator | `src/hooks/atlas/` | Main orchestration hook (771 lines) |
+| Background agents | `src/features/background-agent/` | manager.ts (1377 lines) |
+| Orchestrator | `src/hooks/atlas/` | Main orchestration hook (752 lines) |
 
 ## TDD (Test-Driven Development)
 
@@ -50,8 +63,8 @@ oh-my-opencode/
 **Rules:**
 - NEVER write implementation before test
 - NEVER delete failing tests - fix the code
-- Test file: `*.test.ts` alongside source
-- BDD comments: `#given`, `#when`, `#then`
+- Test file: `*.test.ts` alongside source (100 test files)
+- BDD comments: `//#given`, `//#when`, `//#then`
 
 ## CONVENTIONS
 
@@ -60,7 +73,7 @@ oh-my-opencode/
 - **Build**: `bun build` (ESM) + `tsc --emitDeclarationOnly`
 - **Exports**: Barrel pattern via index.ts
 - **Naming**: kebab-case dirs, `createXXXHook`/`createXXXTool` factories
-- **Testing**: BDD comments, 90 test files
+- **Testing**: BDD comments, 100 test files
 - **Temperature**: 0.1 for code agents, max 0.3
 
 ## ANTI-PATTERNS
@@ -85,13 +98,13 @@ oh-my-opencode/
 
 | Agent | Model | Purpose |
 |-------|-------|---------|
-| Sisyphus | anthropic/claude-opus-4-5 | Primary orchestrator |
-| Atlas | anthropic/claude-opus-4-5 | Master orchestrator |
+| Sisyphus | anthropic/claude-opus-4-5 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro) |
+| Atlas | anthropic/claude-sonnet-4-5 | Master orchestrator (fallback: kimi-k2.5 → gpt-5.2) |
 | oracle | openai/gpt-5.2 | Consultation, debugging |
-| librarian | opencode/glm-4.7-free | Docs, GitHub search |
-| explore | opencode/grok-code | Fast codebase grep |
+| librarian | zai-coding-plan/glm-4.7 | Docs, GitHub search (fallback: glm-4.7-free) |
+| explore | anthropic/claude-haiku-4-5 | Fast codebase grep (fallback: gpt-5-mini → gpt-5-nano) |
 | multimodal-looker | google/gemini-3-flash | PDF/image analysis |
-| Prometheus | anthropic/claude-opus-4-5 | Strategic planning |
+| Prometheus | anthropic/claude-opus-4-5 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
 
 ## COMMANDS
 
@@ -99,7 +112,7 @@ oh-my-opencode/
 bun run typecheck      # Type check
 bun run build          # ESM + declarations + schema
 bun run rebuild        # Clean + Build
-bun test               # 90 test files
+bun test               # 100 test files
 ```
 
 ## DEPLOYMENT
@@ -113,12 +126,14 @@ bun test               # 90 test files
 
 | File | Lines | Description |
 |------|-------|-------------|
-| `src/agents/atlas.ts` | 1383 | Orchestrator, 7-section delegation |
-| `src/features/background-agent/manager.ts` | 1335 | Task lifecycle, concurrency |
-| `src/features/builtin-skills/skills.ts` | 1203 | Skill definitions |
+| `src/features/builtin-skills/skills.ts` | 1729 | Skill definitions |
+| `src/features/background-agent/manager.ts` | 1377 | Task lifecycle, concurrency |
 | `src/agents/prometheus-prompt.ts` | 1196 | Planning agent |
-| `src/tools/delegate-task/tools.ts` | 1038 | Category-based delegation |
-| `src/hooks/atlas/index.ts` | 771 | Orchestrator hook |
+| `src/tools/delegate-task/tools.ts` | 1070 | Category-based delegation |
+| `src/hooks/atlas/index.ts` | 752 | Orchestrator hook |
+| `src/cli/config-manager.ts` | 664 | JSONC config parsing |
+| `src/index.ts` | 672 | Main plugin entry |
+| `src/features/builtin-commands/templates/refactor.ts` | 619 | Refactor command template |
 
 ## MCP ARCHITECTURE
 

README.ja.md

@@ -16,8 +16,8 @@
 
 > [!TIP]
 >
-> [![The Orchestrator is now available in beta.](./.github/assets/orchestrator-atlas.png?v=3)](https://github.com/code-yeongyu/oh-my-opencode/releases/tag/v3.0.0-beta.10)
-> > **オーケストレーターがベータ版で利用可能になりました。`oh-my-opencode@3.0.0-beta.10`を使用してインストールしてください。**
+> [![Oh My OpenCode 3.0が正式リリースされました！](./.github/assets/orchestrator-atlas.png?v=3)](https://github.com/code-yeongyu/oh-my-opencode/releases/tag/v3.0.0)
+> > **Oh My OpenCode 3.0が正式リリースされました！`oh-my-opencode@latest`を使用してインストールしてください。**
 >
 > 一緒に歩みましょう！
 >
@@ -73,7 +73,9 @@
 [![GitHub Issues](https://img.shields.io/github/issues/code-yeongyu/oh-my-opencode?color=ff80eb&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/issues)
 [![License](https://img.shields.io/badge/license-SUL--1.0-white?labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/blob/master/LICENSE.md)
 
-[English](README.md) | [日本語](README.ja.md) | [简体中文](README.zh-cn.md)
+[English](README.md) | [한국어](README.ko.md) | [日本語](README.ja.md) | [简体中文](README.zh-cn.md)
+
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/code-yeongyu/oh-my-opencode)
 
 </div>
 
@@ -187,7 +189,7 @@ Windows から Linux に初めて乗り換えた時のこと、自分の思い
   - Oracle: 設計、デバッグ (GPT 5.2 Medium)
   - Frontend UI/UX Engineer: フロントエンド開発 (Gemini 3 Pro)
   - Librarian: 公式ドキュメント、オープンソース実装、コードベース探索 (Claude Sonnet 4.5)
-  - Explore: 超高速コードベース探索 (Contextual Grep) (Grok Code)
+   - Explore: 超高速コードベース探索 (Contextual Grep) (Claude Haiku 4.5)
 - Full LSP / AstGrep Support: 決定的にリファクタリングしましょう。
 - Todo Continuation Enforcer: 途中で諦めたら、続行を強制します。これがシジフォスに岩を転がし続けさせる秘訣です。
 - Comment Checker: AIが過剰なコメントを付けないようにします。シジフォスが生成したコードは、人間が書いたものと区別がつかないべきです。

README.ko.md

@@ -16,8 +16,8 @@
 >
 > [!TIP]
 >
-> [![The Orchestrator is now available in beta.](./.github/assets/orchestrator-atlas.png?v=3)](https://github.com/code-yeongyu/oh-my-opencode/releases/tag/v3.0.0-beta.10)
-> > **오케스트레이터가 베타 버전으로 사용 가능합니다. 설치하려면 `oh-my-opencode@3.0.0-beta.10`을 사용하세요.**
+> [![Oh My OpenCode 3.0이 정식 출시되었습니다!](./.github/assets/orchestrator-atlas.png?v=3)](https://github.com/code-yeongyu/oh-my-opencode/releases/tag/v3.0.0)
+> > **Oh My OpenCode 3.0이 정식 출시되었습니다! `oh-my-opencode@latest`를 사용하여 설치하세요.**
 >
 > 함께해요!
 >
@@ -73,10 +73,11 @@
 [![GitHub Stars](https://img.shields.io/github/stars/code-yeongyu/oh-my-opencode?color=ffcb47&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/stargazers)
 [![GitHub Issues](https://img.shields.io/github/issues/code-yeongyu/oh-my-opencode?color=ff80eb&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/issues)
 [![License](https://img.shields.io/badge/license-SUL--1.0-white?labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/blob/master/LICENSE.md)
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/code-yeongyu/oh-my-opencode)
 
 [English](README.md) | [한국어](README.ko.md) | [日本語](README.ja.md) | [简体中文](README.zh-cn.md)
 
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/code-yeongyu/oh-my-opencode)
+
 </div>
 
 <!-- </CENTERED SECTION FOR GITHUB DISPLAY> -->
@@ -196,7 +197,7 @@ Hey please read this readme and tell me why it is different from other agent har
   - Oracle: 디자인, 디버깅 (GPT 5.2 Medium)
   - Frontend UI/UX Engineer: 프론트엔드 개발 (Gemini 3 Pro)
   - Librarian: 공식 문서, 오픈 소스 구현, 코드베이스 탐색 (Claude Sonnet 4.5)
-  - Explore: 엄청나게 빠른 코드베이스 탐색 (Contextual Grep) (Grok Code)
+   - Explore: 엄청나게 빠른 코드베이스 탐색 (Contextual Grep) (Claude Haiku 4.5)
 - 완전한 LSP / AstGrep 지원: 결정적으로 리팩토링합니다.
 - TODO 연속 강제: 에이전트가 중간에 멈추면 계속하도록 강제합니다. **이것이 Sisyphus가 그 바위를 굴리게 하는 것입니다.**
 - 주석 검사기: AI가 과도한 주석을 추가하는 것을 방지합니다. Sisyphus가 생성한 코드는 인간이 작성한 것과 구별할 수 없어야 합니다.

README.md

@@ -16,8 +16,8 @@
 
 > [!TIP]
 >
-> [![The Orchestrator is now available in beta.](./.github/assets/orchestrator-atlas.png?v=3)](https://github.com/code-yeongyu/oh-my-opencode/releases/tag/v3.0.0-beta.10)
-> > **The Orchestrator is now available in beta. Use `oh-my-opencode@3.0.0-beta.10` to install it.**
+> [![Oh My OpenCode 3.0 is now stable!](./.github/assets/orchestrator-atlas.png?v=3)](https://github.com/code-yeongyu/oh-my-opencode/releases/tag/v3.0.0)
+> > **Oh My OpenCode 3.0 is now stable! Use `oh-my-opencode@latest` to install it.**
 >
 > Be with us!
 >
@@ -196,7 +196,7 @@ Meet our main agent: Sisyphus (Opus 4.5 High). Below are the tools Sisyphus uses
   - Oracle: Design, debugging (GPT 5.2 Medium)
   - Frontend UI/UX Engineer: Frontend development (Gemini 3 Pro)
   - Librarian: Official docs, open source implementations, codebase exploration (Claude Sonnet 4.5)
-  - Explore: Blazing fast codebase exploration (Contextual Grep) (Grok Code)
+  - Explore: Blazing fast codebase exploration (Contextual Grep) (Claude Haiku 4.5)
 - Full LSP / AstGrep Support: Refactor decisively.
 - Todo Continuation Enforcer: Forces the agent to continue if it quits halfway. **This is what keeps Sisyphus rolling that boulder.**
 - Comment Checker: Prevents AI from adding excessive comments. Code generated by Sisyphus should be indistinguishable from human-written code.

README.zh-cn.md

@@ -16,8 +16,8 @@
 
 > [!TIP]
 >
-> [![Orchestrator 现已进入测试阶段。](./.github/assets/orchestrator-atlas.png?v=3)](https://github.com/code-yeongyu/oh-my-opencode/releases/tag/v3.0.0-beta.10)
-> > **Orchestrator 现已进入测试阶段。使用 `oh-my-opencode@3.0.0-beta.10` 安装。**
+> [![Oh My OpenCode 3.0 正式发布！](./.github/assets/orchestrator-atlas.png?v=3)](https://github.com/code-yeongyu/oh-my-opencode/releases/tag/v3.0.0)
+> > **Oh My OpenCode 3.0 正式发布！使用 `oh-my-opencode@latest` 安装。**
 >
 > 加入我们！
 >
@@ -74,7 +74,9 @@
 [![GitHub Issues](https://img.shields.io/github/issues/code-yeongyu/oh-my-opencode?color=ff80eb&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/issues)
 [![许可证](https://img.shields.io/badge/license-SUL--1.0-white?labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/blob/master/LICENSE.md)
 
-[English](README.md) | [日本語](README.ja.md) | [简体中文](README.zh-cn.md)
+[English](README.md) | [한국어](README.ko.md) | [日本語](README.ja.md) | [简体中文](README.zh-cn.md)
+
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/code-yeongyu/oh-my-opencode)
 
 </div>
 
@@ -191,7 +193,7 @@
   - Oracle：设计、调试 (GPT 5.2 Medium)
   - Frontend UI/UX Engineer：前端开发 (Gemini 3 Pro)
   - Librarian：官方文档、开源实现、代码库探索 (Claude Sonnet 4.5)
-  - Explore：极速代码库探索（上下文感知 Grep）(Grok Code)
+   - Explore：极速代码库探索（上下文感知 Grep）(Claude Haiku 4.5)
 - 完整 LSP / AstGrep 支持：果断重构。
 - Todo 继续执行器：如果智能体中途退出，强制它继续。**这就是让 Sisyphus 继续推动巨石的关键。**
 - 注释检查器：防止 AI 添加过多注释。Sisyphus 生成的代码应该与人类编写的代码无法区分。

assets/oh-my-opencode.schema.json

@@ -20,14 +20,15 @@
       "items": {
         "type": "string",
         "enum": [
-          "Sisyphus",
+          "sisyphus",
+          "prometheus",
           "oracle",
           "librarian",
           "explore",
           "multimodal-looker",
-          "Metis (Plan Consultant)",
-          "Momus (Plan Reviewer)",
-          "Atlas"
+          "metis",
+          "momus",
+          "atlas"
         ]
       }
     },
@@ -37,6 +38,7 @@
         "type": "string",
         "enum": [
           "playwright",
+          "agent-browser",
           "frontend-ui-ux",
           "git-master"
         ]
@@ -69,14 +71,17 @@
           "interactive-bash-session",
           "thinking-block-validator",
           "ralph-loop",
+          "category-skill-reminder",
           "compaction-context-injector",
           "claude-code-hooks",
           "auto-slash-command",
           "edit-error-recovery",
           "delegate-task-retry",
           "prometheus-md-only",
+          "sisyphus-junior-notepad",
           "start-work",
-          "atlas"
+          "atlas",
+          "stop-continuation-guard"
         ]
       }
     },
@@ -216,6 +221,51 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         },
@@ -342,10 +392,55 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         },
-        "Sisyphus": {
+        "sisyphus": {
           "type": "object",
           "properties": {
             "model": {
@@ -468,10 +563,55 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         },
-        "Sisyphus-Junior": {
+        "sisyphus-junior": {
           "type": "object",
           "properties": {
             "model": {
@@ -594,6 +734,51 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         },
@@ -720,10 +905,55 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         },
-        "Prometheus (Planner)": {
+        "prometheus": {
           "type": "object",
           "properties": {
             "model": {
@@ -846,10 +1076,55 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         },
-        "Metis (Plan Consultant)": {
+        "metis": {
           "type": "object",
           "properties": {
             "model": {
@@ -972,10 +1247,55 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         },
-        "Momus (Plan Reviewer)": {
+        "momus": {
           "type": "object",
           "properties": {
             "model": {
@@ -1098,6 +1418,51 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         },
@@ -1224,6 +1589,51 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         },
@@ -1350,6 +1760,51 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         },
@@ -1476,6 +1931,51 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         },
@@ -1602,10 +2102,55 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         },
-        "Atlas": {
+        "atlas": {
           "type": "object",
           "properties": {
             "model": {
@@ -1728,6 +2273,51 @@
                   ]
                 }
               }
+            },
+            "maxTokens": {
+              "type": "number"
+            },
+            "thinking": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "enabled",
+                    "disabled"
+                  ]
+                },
+                "budgetTokens": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "type"
+              ]
+            },
+            "reasoningEffort": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high",
+                "xhigh"
+              ]
+            },
+            "textVerbosity": {
+              "type": "string",
+              "enum": [
+                "low",
+                "medium",
+                "high"
+              ]
+            },
+            "providerOptions": {
+              "type": "object",
+              "propertyNames": {
+                "type": "string"
+              },
+              "additionalProperties": {}
             }
           }
         }
@@ -1786,7 +2376,8 @@
             "enum": [
               "low",
               "medium",
-              "high"
+              "high",
+              "xhigh"
             ]
           },
           "textVerbosity": {
@@ -2169,6 +2760,100 @@
           "type": "boolean"
         }
       }
+    },
+    "browser_automation_engine": {
+      "type": "object",
+      "properties": {
+        "provider": {
+          "default": "playwright",
+          "type": "string",
+          "enum": [
+            "playwright",
+            "agent-browser",
+            "dev-browser"
+          ]
+        }
+      }
+    },
+    "tmux": {
+      "type": "object",
+      "properties": {
+        "enabled": {
+          "default": false,
+          "type": "boolean"
+        },
+        "layout": {
+          "default": "main-vertical",
+          "type": "string",
+          "enum": [
+            "main-horizontal",
+            "main-vertical",
+            "tiled",
+            "even-horizontal",
+            "even-vertical"
+          ]
+        },
+        "main_pane_size": {
+          "default": 60,
+          "type": "number",
+          "minimum": 20,
+          "maximum": 80
+        },
+        "main_pane_min_width": {
+          "default": 120,
+          "type": "number",
+          "minimum": 40
+        },
+        "agent_pane_min_width": {
+          "default": 40,
+          "type": "number",
+          "minimum": 20
+        }
+      }
+    },
+    "sisyphus": {
+      "type": "object",
+      "properties": {
+        "tasks": {
+          "type": "object",
+          "properties": {
+            "enabled": {
+              "default": false,
+              "type": "boolean"
+            },
+            "storage_path": {
+              "default": ".sisyphus/tasks",
+              "type": "string"
+            },
+            "claude_code_compat": {
+              "default": false,
+              "type": "boolean"
+            }
+          }
+        },
+        "swarm": {
+          "type": "object",
+          "properties": {
+            "enabled": {
+              "default": false,
+              "type": "boolean"
+            },
+            "storage_path": {
+              "default": ".sisyphus/teams",
+              "type": "string"
+            },
+            "ui_mode": {
+              "default": "toast",
+              "type": "string",
+              "enum": [
+                "toast",
+                "tmux",
+                "both"
+              ]
+            }
+          }
+        }
+      }
     }
   }
 }

bun.lock

@@ -1,6 +1,6 @@
 {
   "lockfileVersion": 1,
-  "configVersion": 0,
+  "configVersion": 1,
   "workspaces": {
     "": {
       "name": "oh-my-opencode",
@@ -18,6 +18,7 @@
         "jsonc-parser": "^3.3.1",
         "picocolors": "^1.1.1",
         "picomatch": "^4.0.2",
+        "vscode-jsonrpc": "^8.2.0",
         "zod": "^4.1.8",
       },
       "devDependencies": {
@@ -27,13 +28,13 @@
         "typescript": "^5.7.3",
       },
       "optionalDependencies": {
-        "oh-my-opencode-darwin-arm64": "3.0.0-beta.11",
-        "oh-my-opencode-darwin-x64": "3.0.0-beta.11",
-        "oh-my-opencode-linux-arm64": "3.0.0-beta.11",
-        "oh-my-opencode-linux-arm64-musl": "3.0.0-beta.11",
-        "oh-my-opencode-linux-x64": "3.0.0-beta.11",
-        "oh-my-opencode-linux-x64-musl": "3.0.0-beta.11",
-        "oh-my-opencode-windows-x64": "3.0.0-beta.11",
+        "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",
       },
     },
   },
@@ -43,41 +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=="],
 
@@ -85,17 +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=="],
 
@@ -107,9 +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=="],
 
@@ -117,7 +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=="],
 
@@ -127,7 +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=="],
 
@@ -183,11 +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=="],
 
@@ -225,19 +226,19 @@
 
     "object-inspect": ["object-inspect@1.13.4", "", {}, "sha512-W67iLl4J2EXEGTbfeHCffrjDfitvLANg0UlX3wFUUSTx92KXRFegMHUVgSqE+wvhAbi4WqjGg9czysTV2Epbew=="],
 
-    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.0.0-beta.11", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-7cFv2bbz9HTY7sshgVTu+IhvYf7CT0czDYqHEB+dYfEqFU6TaoSMimq6uHqcWegUUR1T7PNmc0dyjYVw69FeVA=="],
+    "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@3.0.0-beta.11", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-rGAbDdUySWITIdm2yiuNFB9lFYaSXT8LMtg97LTlOO5vZbI3M+obIS3QlIkBtAhgOTIPB7Ni+T0W44OmJpHoYA=="],
+    "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@3.0.0-beta.11", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-F9dqwWwGAdqeSkE7Tre5DmHQXwDpU2Z8Jk0lwTJMLj+kMqYFDVPjLPo4iVUdwPpxpmm0pR84u/oonG/2+84/zw=="],
+    "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@3.0.0-beta.11", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-H+zOtHkHd+TmdPj64M1A0zLOk7OHIK4C8yqfLFhfizOIBffT1yOhAs6EpK3EqPhfPLu54ADgcQcu8W96VP24UA=="],
+    "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@3.0.0-beta.11", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-IG+KODTJ8rs6cEJ2wN6Zpr6YtvCS5OpYP6jBdGJltmUpjQdMhdMsaY3ysZk+9Vxpx2KC3xj5KLHV1USg3uBTeg=="],
+    "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@3.0.0-beta.11", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-irV+AuWrHqNm7VT7HO56qgymR0+vEfJbtB3vCq68kprH2V4NQmGp2MNKIYPnUCYL7NEK3H2NX+h06YFZJ/8ELQ=="],
+    "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@3.0.0-beta.11", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-exZ/NEwGBlxyWszN7dvOfzbYX0cuhBZXftqAAFOlVP26elDHdo+AmSmLR/4cJyzpR9nCWz4xvl/RYF84bY6OEA=="],
+    "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=="],
 
@@ -303,12 +304,16 @@
 
     "vary": ["vary@1.1.2", "", {}, "sha512-BNGbWLfd0eUPabhkXUVm0j8uuvREyTh5ovRa/dyow/BqAbZJyC+5fU+IzQOzmAKzYqYRAISoRhdQr3eIZ/PXqg=="],
 
+    "vscode-jsonrpc": ["vscode-jsonrpc@8.2.1", "", {}, "sha512-kdjOSJ2lLIn7r1rtrMbbNCHjyMPfRnowdKjBQ+mGq6NAW5QY2bEZC/khaC5OR8svbbjvLEaIXkOq45e2X9BIbQ=="],
+
     "which": ["which@2.0.2", "", { "dependencies": { "isexe": "^2.0.0" }, "bin": { "node-which": "./bin/node-which" } }, "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA=="],
 
     "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=="],
   }
 }

docs/category-skill-guide.md

@@ -21,13 +21,14 @@ A Category is an agent configuration preset optimized for specific domains.
 
 | Category | Default Model | Use Cases |
 |----------|---------------|-----------|
-| `visual-engineering` | `google/gemini-3-pro-preview` | Frontend, UI/UX, design, styling, animation |
+| `visual-engineering` | `google/gemini-3-pro` | Frontend, UI/UX, design, styling, animation |
 | `ultrabrain` | `openai/gpt-5.2-codex` (xhigh) | Deep logical reasoning, complex architecture decisions requiring extensive analysis |
-| `artistry` | `google/gemini-3-pro-preview` (max) | Highly creative/artistic tasks, novel ideas |
+| `deep` | `openai/gpt-5.2-codex` (medium) | Goal-oriented autonomous problem-solving. Thorough research before action. For hairy problems requiring deep understanding. |
+| `artistry` | `google/gemini-3-pro` (max) | Highly creative/artistic tasks, novel ideas |
 | `quick` | `anthropic/claude-haiku-4-5` | Trivial tasks - single file changes, typo fixes, simple modifications |
 | `unspecified-low` | `anthropic/claude-sonnet-4-5` | Tasks that don't fit other categories, low effort required |
 | `unspecified-high` | `anthropic/claude-opus-4-5` (max) | Tasks that don't fit other categories, high effort required |
-| `writing` | `google/gemini-3-flash-preview` | Documentation, prose, technical writing |
+| `writing` | `google/gemini-3-flash` | Documentation, prose, technical writing |
 
 ### Usage
 
@@ -70,12 +71,12 @@ A Skill is a mechanism that injects **specialized knowledge (Context)** and **to
 
 ### Usage
 
-Add desired skill names to the `skills` array.
+Add desired skill names to the `load_skills` array.
 
 ```typescript
 delegate_task(
   category="quick",
-  skills=["git-master"],
+  load_skills=["git-master"],
   prompt="Commit current changes. Follow commit message style."
 )
 ```
@@ -110,17 +111,17 @@ You can create powerful specialized agents by combining Categories and Skills.
 
 ### 🎨 The Designer (UI Implementation)
 - **Category**: `visual-engineering`
-- **Skills**: `["frontend-ui-ux", "playwright"]`
+- **load_skills**: `["frontend-ui-ux", "playwright"]`
 - **Effect**: Implements aesthetic UI and verifies rendering results directly in browser.
 
 ### 🏗️ The Architect (Design Review)
 - **Category**: `ultrabrain`
-- **Skills**: `[]` (pure reasoning)
+- **load_skills**: `[]` (pure reasoning)
 - **Effect**: Leverages GPT-5.2's logical reasoning for in-depth system architecture analysis.
 
 ### ⚡ The Maintainer (Quick Fixes)
 - **Category**: `quick`
-- **Skills**: `["git-master"]`
+- **load_skills**: `["git-master"]`
 - **Effect**: Uses cost-effective models to quickly fix code and generate clean commits.
 
 ---
@@ -131,7 +132,7 @@ When delegating, **clear and specific** prompts are essential. Include these 7 e
 
 1. **TASK**: What needs to be done? (single objective)
 2. **EXPECTED OUTCOME**: What is the deliverable?
-3. **REQUIRED SKILLS**: Which skills should be used?
+3. **REQUIRED SKILLS**: Which skills should be loaded via `load_skills`?
 4. **REQUIRED TOOLS**: Which tools must be used? (whitelist)
 5. **MUST DO**: What must be done (constraints)
 6. **MUST NOT DO**: What must never be done
@@ -177,7 +178,7 @@ You can fine-tune categories in `oh-my-opencode.json`.
   "categories": {
     // 1. Define new custom category
     "korean-writer": {
-      "model": "google/gemini-3-flash-preview",
+      "model": "google/gemini-3-flash",
       "temperature": 0.5,
       "prompt_append": "You are a Korean technical writer. Maintain a friendly and clear tone."
     },

docs/cli-guide.md

@@ -134,7 +134,41 @@ bunx oh-my-opencode run [prompt]
 
 ---
 
-## 6. `auth` - Authentication Management
+## 6. `mcp oauth` - MCP OAuth Management
+
+Manages OAuth 2.1 authentication for remote MCP servers.
+
+### Usage
+
+```bash
+# Login to an OAuth-protected MCP server
+bunx oh-my-opencode mcp oauth login <server-name> --server-url https://api.example.com
+
+# Login with explicit client ID and scopes
+bunx oh-my-opencode mcp oauth login my-api --server-url https://api.example.com --client-id my-client --scopes "read,write"
+
+# Remove stored OAuth tokens
+bunx oh-my-opencode mcp oauth logout <server-name>
+
+# Check OAuth token status
+bunx oh-my-opencode mcp oauth status [server-name]
+```
+
+### Options
+
+| Option | Description |
+|--------|-------------|
+| `--server-url <url>` | MCP server URL (required for login) |
+| `--client-id <id>` | OAuth client ID (optional if server supports Dynamic Client Registration) |
+| `--scopes <scopes>` | Comma-separated OAuth scopes |
+
+### Token Storage
+
+Tokens are stored in `~/.config/opencode/mcp-oauth.json` with `0600` permissions (owner read/write only). Key format: `{serverHost}/{resource}`.
+
+---
+
+## 7. `auth` - Authentication Management
 
 Manages Google Antigravity OAuth authentication. Required for using Gemini models.
 
@@ -153,7 +187,7 @@ bunx oh-my-opencode auth status
 
 ---
 
-## 7. Configuration Files
+## 8. Configuration Files
 
 The CLI searches for configuration files in the following locations (in priority order):
 
@@ -175,7 +209,7 @@ Configuration files support **JSONC (JSON with Comments)** format. You can use c
   /* Category customization */
   "categories": {
     "visual-engineering": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3-pro",
     },
   },
 }
@@ -183,7 +217,7 @@ Configuration files support **JSONC (JSON with Comments)** format. You can use c
 
 ---
 
-## 8. Troubleshooting
+## 9. Troubleshooting
 
 ### "OpenCode version too old" Error
 
@@ -213,7 +247,7 @@ bunx oh-my-opencode doctor --category authentication
 
 ---
 
-## 9. Non-Interactive Mode
+## 10. Non-Interactive Mode
 
 Use the `--no-tui` option for CI/CD environments.
 
@@ -227,7 +261,7 @@ bunx oh-my-opencode doctor --json > doctor-report.json
 
 ---
 
-## 10. Developer Information
+## 11. Developer Information
 
 ### CLI Structure
 

docs/configurations.md

@@ -2,6 +2,39 @@
 
 Highly opinionated, but adjustable to taste.
 
+## Quick Start
+
+**Most users don't need to configure anything manually.** Run the interactive installer:
+
+```bash
+bunx oh-my-opencode install
+```
+
+It asks about your providers (Claude, OpenAI, Gemini, etc.) and generates optimal config automatically.
+
+**Want to customize?** Here's the common patterns:
+
+```jsonc
+{
+  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
+  
+  // Override specific agent models
+  "agents": {
+    "oracle": { "model": "openai/gpt-5.2" },           // Use GPT for debugging
+    "librarian": { "model": "zai-coding-plan/glm-4.7" }, // Cheap model for research
+    "explore": { "model": "opencode/gpt-5-nano" }        // Free model for grep
+  },
+  
+  // Override category models (used by delegate_task)
+  "categories": {
+    "quick": { "model": "opencode/gpt-5-nano" },         // Fast/cheap for trivial tasks
+    "visual-engineering": { "model": "google/gemini-3-pro" } // Gemini for UI
+  }
+}
+```
+
+**Find available models:** Run `opencode models` to see all models in your environment.
+
 ## Config File Locations
 
 Config file locations (priority order):
@@ -42,7 +75,7 @@ When both `oh-my-opencode.jsonc` and `oh-my-opencode.json` files exist, `.jsonc`
       "model": "openai/gpt-5.2"  // GPT for strategic reasoning
     },
     "explore": {
-      "model": "opencode/grok-code"  // Free & fast for exploration
+      "model": "opencode/gpt-5-nano"  // Free & fast for exploration
     },
   },
 }
@@ -50,7 +83,67 @@ When both `oh-my-opencode.jsonc` and `oh-my-opencode.json` files exist, `.jsonc`
 
 ## Google Auth
 
-**Recommended**: For Google Gemini authentication, install the [`opencode-antigravity-auth`](https://github.com/NoeFabris/opencode-antigravity-auth) plugin. It provides multi-account load balancing, more models (including Claude via Antigravity), and active maintenance. See [Installation > Google Gemini](../README.md#google-gemini-antigravity-oauth).
+**Recommended**: For Google Gemini authentication, install the [`opencode-antigravity-auth`](https://github.com/NoeFabris/opencode-antigravity-auth) plugin (`@latest`). It provides multi-account load balancing, variant-based thinking levels, dual quota system (Antigravity + Gemini CLI), and active maintenance. See [Installation > Google Gemini](docs/guide/installation.md#google-gemini-antigravity-oauth).
+
+## Ollama Provider
+
+**IMPORTANT**: When using Ollama as a provider, you **must** disable streaming to avoid JSON parsing errors.
+
+### Required Configuration
+
+```json
+{
+  "agents": {
+    "explore": {
+      "model": "ollama/qwen3-coder",
+      "stream": false
+    }
+  }
+}
+```
+
+### Why `stream: false` is Required
+
+Ollama returns NDJSON (newline-delimited JSON) when streaming is enabled, but Claude Code SDK expects a single JSON object. This causes `JSON Parse error: Unexpected EOF` when agents attempt tool calls.
+
+**Example of the problem**:
+```json
+// Ollama streaming response (NDJSON - multiple lines)
+{"message":{"tool_calls":[...]}, "done":false}
+{"message":{"content":""}, "done":true}
+
+// Claude Code SDK expects (single JSON object)
+{"message":{"tool_calls":[...], "content":""}, "done":true}
+```
+
+### Supported Models
+
+Common Ollama models that work with oh-my-opencode:
+
+| Model | Best For | Configuration |
+|-------|----------|---------------|
+| `ollama/qwen3-coder` | Code generation, build fixes | `{"model": "ollama/qwen3-coder", "stream": false}` |
+| `ollama/ministral-3:14b` | Exploration, codebase search | `{"model": "ollama/ministral-3:14b", "stream": false}` |
+| `ollama/lfm2.5-thinking` | Documentation, writing | `{"model": "ollama/lfm2.5-thinking", "stream": false}` |
+
+### Troubleshooting
+
+If you encounter `JSON Parse error: Unexpected EOF`:
+
+1. **Verify `stream: false` is set** in your agent configuration
+2. **Check Ollama is running**: `curl http://localhost:11434/api/tags`
+3. **Test with curl**:
+   ```bash
+   curl -s http://localhost:11434/api/chat \
+     -d '{"model": "qwen3-coder", "messages": [{"role": "user", "content": "Hello"}], "stream": false}'
+   ```
+4. **See detailed troubleshooting**: [docs/troubleshooting/ollama-streaming-issue.md](troubleshooting/ollama-streaming-issue.md)
+
+### Future SDK Fix
+
+The proper long-term fix requires Claude Code SDK to parse NDJSON responses correctly. Until then, use `stream: false` as a workaround.
+
+**Tracking**: https://github.com/code-yeongyu/oh-my-opencode/issues/1124
 
 ## Agents
 
@@ -70,7 +163,39 @@ Override built-in agent settings:
 }
 ```
 
-Each agent supports: `model`, `temperature`, `top_p`, `prompt`, `prompt_append`, `tools`, `disable`, `description`, `mode`, `color`, `permission`.
+Each agent supports: `model`, `temperature`, `top_p`, `prompt`, `prompt_append`, `tools`, `disable`, `description`, `mode`, `color`, `permission`, `category`, `variant`, `maxTokens`, `thinking`, `reasoningEffort`, `textVerbosity`, `providerOptions`.
+
+### Additional Agent Options
+
+| Option              | Type    | Description                                                                                     |
+| ------------------- | ------- | ----------------------------------------------------------------------------------------------- |
+| `category`          | string  | Category name to inherit model and other settings from category defaults                             |
+| `variant`           | string  | Model variant (e.g., `max`, `high`, `medium`, `low`, `xhigh`)                                 |
+| `maxTokens`         | number  | Maximum tokens for response. Passed directly to OpenCode SDK.                                      |
+| `thinking`          | object  | Extended thinking configuration for Anthropic models. See [Thinking Options](#thinking-options) below. |
+| `reasoningEffort`   | string  | OpenAI reasoning effort level. Values: `low`, `medium`, `high`, `xhigh`.                         |
+| `textVerbosity`      | string  | Text verbosity level. Values: `low`, `medium`, `high`.                                        |
+| `providerOptions`    | object  | Provider-specific options passed directly to OpenCode SDK.                                      |
+
+#### Thinking Options (Anthropic)
+
+```json
+{
+  "agents": {
+    "oracle": {
+      "thinking": {
+        "type": "enabled",
+        "budgetTokens": 200000
+      }
+    }
+  }
+}
+```
+
+| Option        | Type    | Default | Description                                  |
+| ------------- | ------- | ------- | -------------------------------------------- |
+| `type`        | string  | -       | `enabled` or `disabled`                      |
+| `budgetTokens`| number  | -       | Maximum budget tokens for extended thinking  |
 
 Use `prompt_append` to add extra instructions without replacing the default system prompt:
 
@@ -120,14 +245,14 @@ Or disable via `disabled_agents` in `~/.config/opencode/oh-my-opencode.json` or
 }
 ```
 
-Available agents: `oracle`, `librarian`, `explore`, `multimodal-looker`
+Available agents: `sisyphus`, `prometheus`, `oracle`, `librarian`, `explore`, `multimodal-looker`, `metis`, `momus`, `atlas`
 
 ## Built-in Skills
 
 Oh My OpenCode includes built-in skills that provide additional capabilities:
 
-- **playwright**: Browser automation with Playwright MCP. Use for web scraping, testing, screenshots, and browser interactions.
-- **git-master**: Git expert for atomic commits, rebase/squash, and history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with `delegate_task(category='quick', skills=['git-master'], ...)` to save context.
+- **playwright** (default) / **agent-browser**: Browser automation for web scraping, testing, screenshots, and browser interactions. See [Browser Automation](#browser-automation) for switching between providers.
+- **git-master**: Git expert for atomic commits, rebase/squash, and history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with `delegate_task(category='quick', load_skills=['git-master'], ...)` to save context.
 
 Disable built-in skills via `disabled_skills` in `~/.config/opencode/oh-my-opencode.json` or `.opencode/oh-my-opencode.json`:
 
@@ -137,7 +262,330 @@ Disable built-in skills via `disabled_skills` in `~/.config/opencode/oh-my-openc
 }
 ```
 
-Available built-in skills: `playwright`, `git-master`
+Available built-in skills: `playwright`, `agent-browser`, `git-master`
+
+## Skills Configuration
+
+Configure advanced skills settings including custom skill sources, enabling/disabling specific skills, and defining custom skills.
+
+```json
+{
+  "skills": {
+    "sources": [
+      { "path": "./custom-skills", "recursive": true },
+      "https://example.com/skill.yaml"
+    ],
+    "enable": ["my-custom-skill"],
+    "disable": ["other-skill"],
+    "my-skill": {
+      "description": "Custom skill description",
+      "template": "Custom prompt template",
+      "from": "source-file.ts",
+      "model": "custom/model",
+      "agent": "custom-agent",
+      "subtask": true,
+      "argument-hint": "usage hint",
+      "license": "MIT",
+      "compatibility": ">= 3.0.0",
+      "metadata": {
+        "author": "Your Name"
+      },
+      "allowed-tools": ["tool1", "tool2"]
+    }
+  }
+}
+```
+
+### Sources
+
+Load skills from local directories or remote URLs:
+
+```json
+{
+  "skills": {
+    "sources": [
+      { "path": "./custom-skills", "recursive": true },
+      { "path": "./single-skill.yaml" },
+      "https://example.com/skill.yaml",
+      "https://raw.githubusercontent.com/user/repo/main/skills/*"
+    ]
+  }
+}
+```
+
+| Option      | Default | Description                                    |
+| ----------- | ------- | ---------------------------------------------- |
+| `path`      | -       | Local file/directory path or remote URL            |
+| `recursive`  | `false`  | Recursively load from directory                 |
+| `glob`      | -       | Glob pattern for file selection                 |
+
+### Enable/Disable Skills
+
+```json
+{
+  "skills": {
+    "enable": ["skill-1", "skill-2"],
+    "disable": ["disabled-skill"]
+  }
+}
+```
+
+### Custom Skill Definition
+
+Define custom skills directly in your config:
+
+| Option           | Default | Description                                                                          |
+| ---------------- | ------- | ------------------------------------------------------------------------------------ |
+| `description`     | -       | Human-readable description of the skill                                                 |
+| `template`        | -       | Custom prompt template for the skill                                                    |
+| `from`           | -       | Source file to load template from                                                     |
+| `model`           | -       | Override model for this skill                                                         |
+| `agent`           | -       | Override agent for this skill                                                         |
+| `subtask`         | `false`  | Whether to run as a subtask                                                           |
+| `argument-hint`   | -       | Hint for how to use the skill                                                        |
+| `license`          | -       | Skill license                                                                       |
+| `compatibility`    | -       | Required oh-my-opencode version compatibility                                           |
+| `metadata`         | -       | Additional metadata as key-value pairs                                                |
+| `allowed-tools`    | -       | Array of tools this skill is allowed to use                                            |
+
+**Example: Custom skill**
+
+```json
+{
+  "skills": {
+    "data-analyst": {
+      "description": "Specialized for data analysis tasks",
+      "template": "You are a data analyst. Focus on statistical analysis, visualization, and data interpretation.",
+      "model": "openai/gpt-5.2",
+      "allowed-tools": ["read", "bash", "lsp_diagnostics"]
+    }
+  }
+}
+```
+
+## Browser Automation
+
+Choose between two browser automation providers:
+
+| Provider | Interface | Features | Installation |
+|----------|-----------|----------|--------------|
+| **playwright** (default) | MCP tools | Playwright MCP server with structured tool calls | Auto-installed via npx |
+| **agent-browser** | Bash CLI | Vercel's CLI with session management, parallel browsers | Requires `bun add -g agent-browser` |
+
+**Switch providers** via `browser_automation_engine` in `oh-my-opencode.json`:
+
+```json
+{
+  "browser_automation_engine": {
+    "provider": "agent-browser"
+  }
+}
+```
+
+### Playwright (Default)
+
+Uses the official Playwright MCP server (`@playwright/mcp`). Browser automation happens through structured MCP tool calls.
+
+### agent-browser
+
+Uses [Vercel's agent-browser CLI](https://github.com/vercel-labs/agent-browser). Key advantages:
+- **Session management**: Run multiple isolated browser instances with `--session` flag
+- **Persistent profiles**: Keep browser state across restarts with `--profile`
+- **Snapshot-based workflow**: Get element refs via `snapshot -i`, interact with `@e1`, `@e2`, etc.
+- **CLI-first**: All commands via Bash - great for scripting
+
+**Installation required**:
+```bash
+bun add -g agent-browser
+agent-browser install  # Download Chromium
+```
+
+**Example workflow**:
+```bash
+agent-browser open https://example.com
+agent-browser snapshot -i  # Get interactive elements with refs
+agent-browser fill @e1 "user@example.com"
+agent-browser click @e2
+agent-browser screenshot result.png
+agent-browser close
+```
+
+## Tmux Integration
+
+Run background subagents in separate tmux panes for **visual multi-agent execution**. See your agents working in parallel, each in their own terminal pane.
+
+**Enable tmux integration** via `tmux` in `oh-my-opencode.json`:
+
+```json
+{
+  "tmux": {
+    "enabled": true,
+    "layout": "main-vertical",
+    "main_pane_size": 60,
+    "main_pane_min_width": 120,
+    "agent_pane_min_width": 40
+  }
+}
+```
+
+| Option | Default | Description |
+|--------|---------|-------------|
+| `enabled` | `false` | Enable tmux subagent pane spawning. Only works when running inside an existing tmux session. |
+| `layout` | `main-vertical` | Tmux layout for agent panes. See [Layout Options](#layout-options) below. |
+| `main_pane_size` | `60` | Main pane size as percentage (20-80). |
+| `main_pane_min_width` | `120` | Minimum width for main pane in columns. |
+| `agent_pane_min_width` | `40` | Minimum width for each agent pane in columns. |
+
+### Layout Options
+
+| Layout | Description |
+|--------|-------------|
+| `main-vertical` | Main pane left, agent panes stacked on right (default) |
+| `main-horizontal` | Main pane top, agent panes stacked bottom |
+| `tiled` | All panes in equal-sized grid |
+| `even-horizontal` | All panes in horizontal row |
+| `even-vertical` | All panes in vertical stack |
+
+### Requirements
+
+1. **Must run inside tmux**: The feature only activates when OpenCode is already running inside a tmux session
+2. **Tmux installed**: Requires tmux to be available in PATH
+3. **Server mode**: OpenCode must run with `--port` flag to enable subagent pane spawning
+
+### How It Works
+
+When `tmux.enabled` is `true` and you're inside a tmux session:
+- Background agents (via `delegate_task(run_in_background=true)`) spawn in new tmux panes
+- Each pane shows the subagent's real-time output
+- Panes are automatically closed when the subagent completes
+- Layout is automatically adjusted based on your configuration
+
+### Running OpenCode with Tmux Subagent Support
+
+To enable tmux subagent panes, OpenCode must run in **server mode** with the `--port` flag. This starts an HTTP server that subagent panes connect to via `opencode attach`.
+
+**Basic setup**:
+```bash
+# Start tmux session
+tmux new -s dev
+
+# Run OpenCode with server mode (port 4096)
+opencode --port 4096
+
+# Now background agents will appear in separate panes
+```
+
+**Recommended: Shell Function**
+
+For convenience, create a shell function that automatically handles tmux sessions and port allocation. Here's an example for Fish shell:
+
+```fish
+# ~/.config/fish/config.fish
+function oc
+    set base_name (basename (pwd))
+    set path_hash (echo (pwd) | md5 | cut -c1-4)
+    set session_name "$base_name-$path_hash"
+    
+    # Find available port starting from 4096
+    function __oc_find_port
+        set port 4096
+        while test $port -lt 5096
+            if not lsof -i :$port >/dev/null 2>&1
+                echo $port
+                return 0
+            end
+            set port (math $port + 1)
+        end
+        echo 4096
+    end
+    
+    set oc_port (__oc_find_port)
+    set -x OPENCODE_PORT $oc_port
+    
+    if set -q TMUX
+        # Already inside tmux - just run with port
+        opencode --port $oc_port $argv
+    else
+        # Create tmux session and run opencode
+        set oc_cmd "OPENCODE_PORT=$oc_port opencode --port $oc_port $argv; exec fish"
+        if tmux has-session -t "$session_name" 2>/dev/null
+            tmux new-window -t "$session_name" -c (pwd) "$oc_cmd"
+            tmux attach-session -t "$session_name"
+        else
+            tmux new-session -s "$session_name" -c (pwd) "$oc_cmd"
+        end
+    end
+    
+    functions -e __oc_find_port
+end
+```
+
+**Bash/Zsh equivalent**:
+
+```bash
+# ~/.bashrc or ~/.zshrc
+oc() {
+    local base_name=$(basename "$PWD")
+    local path_hash=$(echo "$PWD" | md5sum | cut -c1-4)
+    local session_name="${base_name}-${path_hash}"
+    
+    # Find available port
+    local port=4096
+    while [ $port -lt 5096 ]; do
+        if ! lsof -i :$port >/dev/null 2>&1; then
+            break
+        fi
+        port=$((port + 1))
+    done
+    
+    export OPENCODE_PORT=$port
+    
+    if [ -n "$TMUX" ]; then
+        opencode --port $port "$@"
+    else
+        local oc_cmd="OPENCODE_PORT=$port opencode --port $port $*; exec $SHELL"
+        if tmux has-session -t "$session_name" 2>/dev/null; then
+            tmux new-window -t "$session_name" -c "$PWD" "$oc_cmd"
+            tmux attach-session -t "$session_name"
+        else
+            tmux new-session -s "$session_name" -c "$PWD" "$oc_cmd"
+        fi
+    fi
+}
+```
+
+**How subagent panes work**:
+
+1. Main OpenCode starts HTTP server on specified port (e.g., `http://localhost:4096`)
+2. When a background agent spawns, Oh My OpenCode creates a new tmux pane
+3. The pane runs: `opencode attach http://localhost:4096 --session <session-id>`
+4. Each subagent pane shows real-time streaming output
+5. Panes are automatically closed when the subagent completes
+
+**Environment variables**:
+
+| Variable | Description |
+|----------|-------------|
+| `OPENCODE_PORT` | Default port for the HTTP server (used if `--port` not specified) |
+
+### Server Mode Reference
+
+OpenCode's server mode exposes an HTTP API for programmatic interaction:
+
+```bash
+# Standalone server (no TUI)
+opencode serve --port 4096
+
+# TUI with server (recommended for tmux integration)
+opencode --port 4096
+```
+
+| Flag | Default | Description |
+|------|---------|-------------|
+| `--port` | `4096` | Port for HTTP server |
+| `--hostname` | `127.0.0.1` | Hostname to listen on |
+
+For more details, see the [OpenCode Server documentation](https://opencode.ai/docs/server/).
 
 ## Git Master
 
@@ -238,6 +686,7 @@ Configure concurrency limits for background agent tasks. This controls how many
 {
   "background_task": {
     "defaultConcurrency": 5,
+    "staleTimeoutMs": 180000,
     "providerConcurrency": {
       "anthropic": 3,
       "openai": 5,
@@ -254,6 +703,7 @@ Configure concurrency limits for background agent tasks. This controls how many
 | Option                | Default | Description                                                                                                             |
 | --------------------- | ------- | ----------------------------------------------------------------------------------------------------------------------- |
 | `defaultConcurrency`  | -       | Default maximum concurrent background tasks for all providers/models                                                    |
+| `staleTimeoutMs`      | `180000` | Stale timeout in milliseconds - interrupt tasks with no activity for this duration (minimum: 60000 = 1 minute)             |
 | `providerConcurrency` | -       | Per-provider concurrency limits. Keys are provider names (e.g., `anthropic`, `openai`, `google`)                        |
 | `modelConcurrency`    | -       | Per-model concurrency limits. Keys are full model names (e.g., `anthropic/claude-opus-4-5`). Overrides provider limits. |
 
@@ -268,27 +718,96 @@ Configure concurrency limits for background agent tasks. This controls how many
 
 Categories enable domain-specific task delegation via the `delegate_task` tool. Each category applies runtime presets (model, temperature, prompt additions) when calling the `Sisyphus-Junior` agent.
 
-**Default Categories:**
+### Built-in Categories
 
-| Category         | Model                         | Description                                                                  |
-| ---------------- | ----------------------------- | ---------------------------------------------------------------------------- |
-| `visual`         | `google/gemini-3-pro-preview` | Frontend, UI/UX, design-focused tasks. High creativity (temp 0.7).           |
-| `business-logic` | `openai/gpt-5.2`              | Backend logic, architecture, strategic reasoning. Low creativity (temp 0.1). |
+All 7 categories come with optimal model defaults, but **you must configure them to use those defaults**:
 
-**Usage:**
+| Category             | Built-in Default Model             | Description                                                          |
+| -------------------- | ---------------------------------- | -------------------------------------------------------------------- |
+| `visual-engineering` | `google/gemini-3-pro-preview`      | Frontend, UI/UX, design, styling, animation                          |
+| `ultrabrain`         | `openai/gpt-5.2-codex` (xhigh)     | Deep logical reasoning, complex architecture decisions               |
+| `artistry`           | `google/gemini-3-pro-preview` (max)| Highly creative/artistic tasks, novel ideas                          |
+| `quick`              | `anthropic/claude-haiku-4-5`       | Trivial tasks - single file changes, typo fixes, simple modifications|
+| `unspecified-low`    | `anthropic/claude-sonnet-4-5`      | Tasks that don't fit other categories, low effort required           |
+| `unspecified-high`   | `anthropic/claude-opus-4-5` (max)  | Tasks that don't fit other categories, high effort required          |
+| `writing`            | `google/gemini-3-flash-preview`    | Documentation, prose, technical writing                              |
+
+### ⚠️ Critical: Model Resolution Priority
+
+**Categories DO NOT use their built-in defaults unless configured.** Model resolution follows this priority:
 
 ```
-// Via delegate_task tool
-delegate_task(category="visual", prompt="Create a responsive dashboard component")
-delegate_task(category="business-logic", prompt="Design the payment processing flow")
+1. User-configured model (in oh-my-opencode.json)
+2. Category's built-in default (if you add category to config)
+3. System default model (from opencode.json)
+```
 
-// Or target a specific agent directly
+**Example Problem:**
+
+```json
+// opencode.json
+{ "model": "anthropic/claude-sonnet-4-5" }
+
+// oh-my-opencode.json (empty categories section)
+{}
+
+// Result: ALL categories use claude-sonnet-4-5 (wasteful!)
+// - quick tasks use Sonnet instead of Haiku (expensive)
+// - ultrabrain uses Sonnet instead of GPT-5.2 (inferior reasoning)
+// - visual tasks use Sonnet instead of Gemini (suboptimal for UI)
+```
+
+### Recommended Configuration
+
+**To use optimal models for each category, add them to your config:**
+
+```json
+{
+  "categories": {
+    "visual-engineering": { 
+      "model": "google/gemini-3-pro-preview"
+    },
+    "ultrabrain": { 
+      "model": "openai/gpt-5.2-codex",
+      "variant": "xhigh"
+    },
+    "artistry": { 
+      "model": "google/gemini-3-pro-preview",
+      "variant": "max"
+    },
+    "quick": { 
+      "model": "anthropic/claude-haiku-4-5"  // Fast + cheap for trivial tasks
+    },
+    "unspecified-low": { 
+      "model": "anthropic/claude-sonnet-4-5"
+    },
+    "unspecified-high": { 
+      "model": "anthropic/claude-opus-4-5",
+      "variant": "max"
+    },
+    "writing": { 
+      "model": "google/gemini-3-flash-preview"
+    }
+  }
+}
+```
+
+**Only configure categories you have access to.** Unconfigured categories fall back to your system default model.
+
+### Usage
+
+```javascript
+// Via delegate_task tool
+delegate_task(category="visual-engineering", prompt="Create a responsive dashboard component")
+delegate_task(category="ultrabrain", prompt="Design the payment processing flow")
+
+// Or target a specific agent directly (bypasses categories)
 delegate_task(agent="oracle", prompt="Review this architecture")
 ```
 
-**Custom Categories:**
+### Custom Categories
 
-Add custom categories in `oh-my-opencode.json`:
+Add your own categories or override built-in ones:
 
 ```json
 {
@@ -298,7 +817,7 @@ Add custom categories in `oh-my-opencode.json`:
       "temperature": 0.2,
       "prompt_append": "Focus on data analysis, ML pipelines, and statistical methods."
     },
-    "visual": {
+    "visual-engineering": {
       "model": "google/gemini-3-pro-preview",
       "prompt_append": "Use shadcn/ui components and Tailwind CSS."
     }
@@ -306,7 +825,14 @@ Add custom categories in `oh-my-opencode.json`:
 }
 ```
 
-Each category supports: `model`, `temperature`, `top_p`, `maxTokens`, `thinking`, `reasoningEffort`, `textVerbosity`, `tools`, `prompt_append`.
+Each category supports: `model`, `temperature`, `top_p`, `maxTokens`, `thinking`, `reasoningEffort`, `textVerbosity`, `tools`, `prompt_append`, `variant`, `description`, `is_unstable_agent`.
+
+### Additional Category Options
+
+| Option             | Type    | Default | Description                                                                                         |
+| ------------------ | ------- | ------- | --------------------------------------------------------------------------------------------------- |
+| `description`       | string  | -       | Human-readable description of the category's purpose. Shown in delegate_task prompt.                     |
+| `is_unstable_agent`| boolean | `false`  | Mark agent as unstable - forces background mode for monitoring. Auto-enabled for gemini models. |
 
 ## Model Resolution System
 
@@ -368,15 +894,15 @@ Each agent has a defined provider priority chain. The system tries providers in
 
 | Agent | Model (no prefix) | Provider Priority Chain |
 |-------|-------------------|-------------------------|
-| **Sisyphus** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
-| **oracle** | `gpt-5.2` | openai → anthropic → google → github-copilot → opencode |
-| **librarian** | `glm-4.7-free` | opencode → github-copilot → anthropic |
-| **explore** | `grok-code` | opencode → anthropic → github-copilot |
-| **multimodal-looker** | `gemini-3-pro-preview` | google → openai → anthropic → github-copilot → opencode |
-| **Prometheus (Planner)** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
-| **Metis (Plan Consultant)** | `claude-sonnet-4-5` | anthropic → github-copilot → opencode → antigravity → google |
-| **Momus (Plan Reviewer)** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
-| **Atlas** | `claude-sonnet-4-5` | anthropic → github-copilot → opencode → antigravity → google |
+| **Sisyphus** | `claude-opus-4-5` | anthropic → kimi-for-coding → zai-coding-plan → openai → google |
+| **oracle** | `gpt-5.2` | openai → google → anthropic |
+| **librarian** | `glm-4.7` | zai-coding-plan → opencode → anthropic |
+| **explore** | `claude-haiku-4-5` | anthropic → github-copilot → opencode |
+| **multimodal-looker** | `gemini-3-flash` | google → openai → zai-coding-plan → kimi-for-coding → anthropic → opencode |
+| **Prometheus (Planner)** | `claude-opus-4-5` | anthropic → kimi-for-coding → openai → google |
+| **Metis (Plan Consultant)** | `claude-opus-4-5` | anthropic → kimi-for-coding → openai → google |
+| **Momus (Plan Reviewer)** | `gpt-5.2` | openai → anthropic → google |
+| **Atlas** | `claude-sonnet-4-5` | anthropic → kimi-for-coding → openai → google |
 
 ### Category Provider Chains
 
@@ -384,13 +910,14 @@ Categories follow the same resolution logic:
 
 | Category | Model (no prefix) | Provider Priority Chain |
 |----------|-------------------|-------------------------|
-| **visual-engineering** | `gemini-3-pro-preview` | google → openai → anthropic → github-copilot → opencode |
-| **ultrabrain** | `gpt-5.2-codex` | openai → anthropic → google → github-copilot → opencode |
-| **artistry** | `gemini-3-pro-preview` | google → openai → anthropic → github-copilot → opencode |
-| **quick** | `claude-haiku-4-5` | anthropic → github-copilot → opencode → antigravity → google |
-| **unspecified-low** | `claude-sonnet-4-5` | anthropic → github-copilot → opencode → antigravity → google |
-| **unspecified-high** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
-| **writing** | `gemini-3-flash-preview` | google → openai → anthropic → github-copilot → opencode |
+| **visual-engineering** | `gemini-3-pro` | google → anthropic → zai-coding-plan |
+| **ultrabrain** | `gpt-5.2-codex` | openai → google → anthropic |
+| **deep** | `gpt-5.2-codex` | openai → anthropic → google |
+| **artistry** | `gemini-3-pro` | google → anthropic → openai |
+| **quick** | `claude-haiku-4-5` | anthropic → google → opencode |
+| **unspecified-low** | `claude-sonnet-4-5` | anthropic → openai → google |
+| **unspecified-high** | `claude-opus-4-5` | anthropic → openai → google |
+| **writing** | `gemini-3-flash` | google → anthropic → zai-coding-plan → openai |
 
 ### Checking Your Configuration
 
@@ -440,10 +967,93 @@ Disable specific built-in hooks via `disabled_hooks` in `~/.config/opencode/oh-m
 }
 ```
 
-Available hooks: `todo-continuation-enforcer`, `context-window-monitor`, `session-recovery`, `session-notification`, `comment-checker`, `grep-output-truncator`, `tool-output-truncator`, `directory-agents-injector`, `directory-readme-injector`, `empty-task-response-detector`, `think-mode`, `anthropic-context-window-limit-recovery`, `rules-injector`, `background-notification`, `auto-update-checker`, `startup-toast`, `keyword-detector`, `agent-usage-reminder`, `non-interactive-env`, `interactive-bash-session`, `compaction-context-injector`, `thinking-block-validator`, `claude-code-hooks`, `ralph-loop`, `preemptive-compaction`
+Available hooks: `todo-continuation-enforcer`, `context-window-monitor`, `session-recovery`, `session-notification`, `comment-checker`, `grep-output-truncator`, `tool-output-truncator`, `directory-agents-injector`, `directory-readme-injector`, `empty-task-response-detector`, `think-mode`, `anthropic-context-window-limit-recovery`, `rules-injector`, `background-notification`, `auto-update-checker`, `startup-toast`, `keyword-detector`, `agent-usage-reminder`, `non-interactive-env`, `interactive-bash-session`, `compaction-context-injector`, `thinking-block-validator`, `claude-code-hooks`, `ralph-loop`, `preemptive-compaction`, `auto-slash-command`, `sisyphus-junior-notepad`, `start-work`
+
+**Note on `directory-agents-injector`**: This hook is **automatically disabled** when running on OpenCode 1.1.37+ because OpenCode now has native support for dynamically resolving AGENTS.md files from subdirectories (PR #10678). This prevents duplicate AGENTS.md injection. For older OpenCode versions, the hook remains active to provide the same functionality.
 
 **Note on `auto-update-checker` and `startup-toast`**: The `startup-toast` hook is a sub-feature of `auto-update-checker`. To disable only the startup toast notification while keeping update checking enabled, add `"startup-toast"` to `disabled_hooks`. To disable all update checking features (including the toast), add `"auto-update-checker"` to `disabled_hooks`.
 
+## Disabled Commands
+
+Disable specific built-in commands via `disabled_commands` in `~/.config/opencode/oh-my-opencode.json` or `.opencode/oh-my-opencode.json`:
+
+```json
+{
+  "disabled_commands": ["init-deep", "start-work"]
+}
+```
+
+Available commands: `init-deep`, `start-work`
+
+## Comment Checker
+
+Configure comment-checker hook behavior. The comment checker warns when excessive comments are added to code.
+
+```json
+{
+  "comment_checker": {
+    "custom_prompt": "Your custom warning message. Use {{comments}} placeholder for detected comments XML."
+  }
+}
+```
+
+| Option        | Default | Description                                                                |
+| ------------- | ------- | -------------------------------------------------------------------------- |
+| `custom_prompt` | -       | Custom warning message to replace the default. Use `{{comments}}` placeholder. |
+
+## Notification
+
+Configure notification behavior for background task completion.
+
+```json
+{
+  "notification": {
+    "force_enable": true
+  }
+}
+```
+
+| Option         | Default | Description                                                                                   |
+| -------------- | ------- | ---------------------------------------------------------------------------------------------- |
+| `force_enable` | `false` | Force enable session-notification even if external notification plugins are detected. Default: `false`. |
+
+## Sisyphus Tasks & Swarm
+
+Configure Sisyphus Tasks and Swarm systems for advanced task management and multi-agent orchestration.
+
+```json
+{
+  "sisyphus": {
+    "tasks": {
+      "enabled": false,
+      "storage_path": ".sisyphus/tasks",
+      "claude_code_compat": false
+    },
+    "swarm": {
+      "enabled": false,
+      "storage_path": ".sisyphus/teams",
+      "ui_mode": "toast"
+    }
+  }
+}
+```
+
+### Tasks Configuration
+
+| Option               | Default            | Description                                                               |
+| -------------------- | ------------------ | ------------------------------------------------------------------------- |
+| `enabled`            | `false`            | Enable Sisyphus Tasks system                                               |
+| `storage_path`       | `.sisyphus/tasks`  | Storage path for tasks (relative to project root)                           |
+| `claude_code_compat` | `false`            | Enable Claude Code path compatibility mode                                   |
+
+### Swarm Configuration
+
+| Option         | Default            | Description                                                    |
+| -------------- | ------------------ | -------------------------------------------------------------- |
+| `enabled`      | `false`            | Enable Sisyphus Swarm system for multi-agent orchestration        |
+| `storage_path` | `.sisyphus/teams`  | Storage path for teams (relative to project root)                |
+| `ui_mode`      | `toast`            | UI mode: `toast` (notifications), `tmux` (panes), or `both`     |
+
 ## MCPs
 
 Exa, Context7 and grep.app MCP enabled by default.
@@ -485,6 +1095,38 @@ Add LSP servers via the `lsp` option in `~/.config/opencode/oh-my-opencode.json`
 
 Each server supports: `command`, `extensions`, `priority`, `env`, `initialization`, `disabled`.
 
+| Option         | Type     | Default | Description                                                            |
+| -------------- | -------- | ------- | ---------------------------------------------------------------------- |
+| `command`       | array    | -       | Command to start the LSP server (executable + args)                          |
+| `extensions`    | array    | -       | File extensions this server handles (e.g., `[".ts", ".tsx"]`)               |
+| `priority`      | number   | -       | Server priority when multiple servers match a file                               |
+| `env`           | object   | -       | Environment variables for the LSP server (key-value pairs)                     |
+| `initialization`| object   | -       | Custom initialization options passed to the LSP server                        |
+| `disabled`      | boolean  | `false`  | Whether to disable this LSP server                                         |
+
+**Example with advanced options:**
+
+```json
+{
+  "lsp": {
+    "typescript-language-server": {
+      "command": ["typescript-language-server", "--stdio"],
+      "extensions": [".ts", ".tsx"],
+      "priority": 10,
+      "env": {
+        "NODE_OPTIONS": "--max-old-space-size=4096"
+      },
+      "initialization": {
+        "preferences": {
+          "includeInlayParameterNameHints": "all",
+          "includeInlayFunctionParameterTypeHints": true
+        }
+      }
+    }
+  }
+}
+```
+
 ## Experimental
 
 Opt-in experimental features that may change or be removed in future versions. Use with caution.
@@ -494,7 +1136,29 @@ Opt-in experimental features that may change or be removed in future versions. U
   "experimental": {
     "truncate_all_tool_outputs": true,
     "aggressive_truncation": true,
-    "auto_resume": true
+    "auto_resume": true,
+    "dynamic_context_pruning": {
+      "enabled": false,
+      "notification": "detailed",
+      "turn_protection": {
+        "enabled": true,
+        "turns": 3
+      },
+      "protected_tools": ["task", "todowrite", "lsp_rename"],
+      "strategies": {
+        "deduplication": {
+          "enabled": true
+        },
+        "supersede_writes": {
+          "enabled": true,
+          "aggressive": false
+        },
+        "purge_errors": {
+          "enabled": true,
+          "turns": 5
+        }
+      }
+    }
   }
 }
 ```
@@ -503,7 +1167,72 @@ Opt-in experimental features that may change or be removed in future versions. U
 | --------------------------- | ------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `truncate_all_tool_outputs` | `false` | Truncates ALL tool outputs instead of just whitelisted tools (Grep, Glob, LSP, AST-grep). Tool output truncator is enabled by default - disable via `disabled_hooks`.                         |
 | `aggressive_truncation`     | `false` | When token limit is exceeded, aggressively truncates tool outputs to fit within limits. More aggressive than the default truncation behavior. Falls back to summarize/revert if insufficient. |
-| `auto_resume`               | `false` | Automatically resumes session after successful recovery from thinking block errors or thinking disabled violations. Extracts the last user message and continues.                             |
+| `auto_resume`               | `false` | Automatically resumes session after successful recovery from thinking block errors or thinking disabled violations. Extracts last user message and continues.                             |
+| `dynamic_context_pruning`    | See below | Dynamic context pruning configuration for managing context window usage automatically. See [Dynamic Context Pruning](#dynamic-context-pruning) below.                              |
+
+### Dynamic Context Pruning
+
+Dynamic context pruning automatically manages context window by intelligently pruning old tool outputs. This feature helps maintain performance in long sessions.
+
+```json
+{
+  "experimental": {
+    "dynamic_context_pruning": {
+      "enabled": false,
+      "notification": "detailed",
+      "turn_protection": {
+        "enabled": true,
+        "turns": 3
+      },
+      "protected_tools": ["task", "todowrite", "todoread", "lsp_rename", "session_read", "session_write", "session_search"],
+      "strategies": {
+        "deduplication": {
+          "enabled": true
+        },
+        "supersede_writes": {
+          "enabled": true,
+          "aggressive": false
+        },
+        "purge_errors": {
+          "enabled": true,
+          "turns": 5
+        }
+      }
+    }
+  }
+}
+```
+
+| Option            | Default | Description                                                                               |
+| ----------------- | ------- | ----------------------------------------------------------------------------------------- |
+| `enabled`         | `false`  | Enable dynamic context pruning                                                               |
+| `notification`     | `detailed` | Notification level: `off`, `minimal`, or `detailed`                                        |
+| `turn_protection` | See below | Turn protection settings - prevent pruning recent tool outputs                                 |
+
+#### Turn Protection
+
+| Option    | Default | Description                                                  |
+| --------- | ------- | ------------------------------------------------------------ |
+| `enabled` | `true`  | Enable turn protection                                         |
+| `turns`   | `3`     | Number of recent turns to protect from pruning (1-10)           |
+
+#### Protected Tools
+
+Tools that should never be pruned (default):
+
+```json
+["task", "todowrite", "todoread", "lsp_rename", "session_read", "session_write", "session_search"]
+```
+
+#### Pruning Strategies
+
+| Strategy            | Option       | Default | Description                                                                  |
+| ------------------- | ------------ | ------- | ---------------------------------------------------------------------------- |
+| **deduplication**   | `enabled`    | `true`  | Remove duplicate tool calls (same tool + same args)                              |
+| **supersede_writes**| `enabled`    | `true`  | Prune write inputs when file subsequently read                                   |
+|                     | `aggressive` | `false` | Aggressive mode: prune any write if ANY subsequent read                         |
+| **purge_errors**   | `enabled`    | `true`  | Prune errored tool inputs after N turns                                        |
+|                     | `turns`      | `5`     | Number of turns before pruning errors (1-20)                                    |
 
 **Warning**: These features are experimental and may cause unexpected behavior. Enable only if you understand the implications.
 

docs/features.md

@@ -10,19 +10,19 @@ Oh-My-OpenCode provides 10 specialized AI agents. Each has distinct expertise, o
 
 | Agent | Model | Purpose |
 |-------|-------|---------|
-| **Sisyphus** | `anthropic/claude-opus-4-5` | **The default orchestrator.** Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). |
+| **Sisyphus** | `anthropic/claude-opus-4-5` | **The default orchestrator.** Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). Fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro. |
 | **oracle** | `openai/gpt-5.2` | Architecture decisions, code review, debugging. Read-only consultation - stellar logical reasoning and deep analysis. Inspired by AmpCode. |
-| **librarian** | `opencode/glm-4.7-free` | Multi-repo analysis, documentation lookup, OSS implementation examples. Deep codebase understanding with evidence-based answers. Inspired by AmpCode. |
-| **explore** | `opencode/grok-code` | Fast codebase exploration and contextual grep. Uses Gemini 3 Flash when Antigravity auth is configured, Haiku when Claude max20 is available, otherwise Grok. Inspired by Claude Code. |
-| **multimodal-looker** | `google/gemini-3-flash` | Visual content specialist. Analyzes PDFs, images, diagrams to extract information. Saves tokens by having another agent process media. |
+| **librarian** | `zai-coding-plan/glm-4.7` | Multi-repo analysis, documentation lookup, OSS implementation examples. Deep codebase understanding with evidence-based answers. Fallback: glm-4.7-free → claude-sonnet-4-5. |
+| **explore** | `anthropic/claude-haiku-4-5` | Fast codebase exploration and contextual grep. Fallback: gpt-5-mini → gpt-5-nano. |
+| **multimodal-looker** | `google/gemini-3-flash` | Visual content specialist. Analyzes PDFs, images, diagrams to extract information. Fallback: gpt-5.2 → glm-4.6v → kimi-k2.5 → claude-haiku-4-5 → gpt-5-nano. |
 
 ### Planning Agents
 
 | Agent | Model | Purpose |
 |-------|-------|---------|
-| **Prometheus** | `anthropic/claude-opus-4-5` | Strategic planner with interview mode. Creates detailed work plans through iterative questioning. |
-| **Metis** | `anthropic/claude-sonnet-4-5` | Plan consultant - pre-planning analysis. Identifies hidden intentions, ambiguities, and AI failure points. |
-| **Momus** | `anthropic/claude-sonnet-4-5` | Plan reviewer - validates plans against clarity, verifiability, and completeness standards. |
+| **Prometheus** | `anthropic/claude-opus-4-5` | Strategic planner with interview mode. Creates detailed work plans through iterative questioning. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
+| **Metis** | `anthropic/claude-opus-4-5` | Plan consultant - pre-planning analysis. Identifies hidden intentions, ambiguities, and AI failure points. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
+| **Momus** | `openai/gpt-5.2` | Plan reviewer - validates plans against clarity, verifiability, and completeness standards. Fallback: gpt-5.2 → claude-opus-4-5 → gemini-3-pro. |
 
 ### Invoking Agents
 
@@ -62,6 +62,27 @@ delegate_task(agent="explore", background=true, prompt="Find auth implementation
 background_output(task_id="bg_abc123")
 ```
 
+#### Visual Multi-Agent with Tmux
+
+Enable `tmux.enabled` to see background agents in separate tmux panes:
+
+```json
+{
+  "tmux": {
+    "enabled": true,
+    "layout": "main-vertical"
+  }
+}
+```
+
+When running inside tmux:
+- Background agents spawn in new panes
+- Watch multiple agents work in real-time
+- Each pane shows agent output live
+- Auto-cleanup when agents complete
+
+See [Tmux Integration](configurations.md#tmux-integration) for full configuration options.
+
 Customize agent models, prompts, and permissions in `oh-my-opencode.json`. See [Configuration](configurations.md#agents).
 
 ---
@@ -78,11 +99,15 @@ Skills provide specialized workflows with embedded MCP servers and detailed inst
 | **frontend-ui-ux** | UI/UX tasks, styling | Designer-turned-developer persona. Crafts stunning UI/UX even without design mockups. Emphasizes bold aesthetic direction, distinctive typography, cohesive color palettes. |
 | **git-master** | commit, rebase, squash, blame | MUST USE for ANY git operations. Atomic commits with automatic splitting, rebase/squash workflows, history search (blame, bisect, log -S). |
 
-### Skill: playwright
+### Skill: Browser Automation (playwright / agent-browser)
 
 **Trigger**: Any browser-related request
 
-Provides browser automation via Playwright MCP server:
+Oh-My-OpenCode provides two browser automation providers, configurable via `browser_automation_engine.provider`:
+
+#### Option 1: Playwright MCP (Default)
+
+The default provider uses Playwright MCP server:
 
 ```yaml
 mcp:
@@ -91,18 +116,41 @@ mcp:
     args: ["@playwright/mcp@latest"]
 ```
 
-**Capabilities**:
+**Usage**:
+```
+/playwright Navigate to example.com and take a screenshot
+```
+
+#### Option 2: Agent Browser CLI (Vercel)
+
+Alternative provider using [Vercel's agent-browser CLI](https://github.com/vercel-labs/agent-browser):
+
+```json
+{
+  "browser_automation_engine": {
+    "provider": "agent-browser"
+  }
+}
+```
+
+**Requires installation**:
+```bash
+bun add -g agent-browser
+```
+
+**Usage**:
+```
+Use agent-browser to navigate to example.com and extract the main heading
+```
+
+#### Capabilities (Both Providers)
+
 - Navigate and interact with web pages
 - Take screenshots and PDFs
 - Fill forms and click elements
 - Wait for network requests
 - Scrape content
 
-**Usage**:
-```
-/playwright Navigate to example.com and take a screenshot
-```
-
 ### Skill: frontend-ui-ux
 
 **Trigger**: UI design tasks, visual changes
@@ -272,7 +320,7 @@ Hooks intercept and modify behavior at key points in the agent lifecycle.
 
 | Hook | Event | Description |
 |------|-------|-------------|
-| **directory-agents-injector** | PostToolUse | Auto-injects AGENTS.md when reading files. Walks from file to project root, collecting all AGENTS.md files. |
+| **directory-agents-injector** | PostToolUse | Auto-injects AGENTS.md when reading files. Walks from file to project root, collecting all AGENTS.md files. **Deprecated for OpenCode 1.1.37+** - Auto-disabled when native AGENTS.md injection is available. |
 | **directory-readme-injector** | PostToolUse | Auto-injects README.md for directory context. |
 | **rules-injector** | PostToolUse | Injects rules from `.claude/rules/` when conditions match. Supports globs and alwaysApply. |
 | **compaction-context-injector** | Stop | Preserves critical context during session compaction. |
@@ -418,6 +466,29 @@ Disable specific hooks in config:
 | **session_search** | Full-text search across session messages |
 | **session_info** | Get session metadata and statistics |
 
+### Interactive Terminal Tools
+
+| Tool | Description |
+|------|-------------|
+| **interactive_bash** | Tmux-based terminal for TUI apps (vim, htop, pudb). Pass tmux subcommands directly without prefix. |
+
+**Usage Examples**:
+```bash
+# Create a new session
+interactive_bash(tmux_command="new-session -d -s dev-app")
+
+# Send keystrokes to a session
+interactive_bash(tmux_command="send-keys -t dev-app 'vim main.py' Enter")
+
+# Capture pane output
+interactive_bash(tmux_command="capture-pane -p -t dev-app")
+```
+
+**Key Points**:
+- Commands are tmux subcommands (no `tmux` prefix)
+- Use for interactive apps that need persistent sessions
+- One-shot commands should use regular `Bash` tool with `&`
+
 ---
 
 ## MCPs: Built-in Servers
@@ -450,6 +521,37 @@ mcp:
 
 The `skill_mcp` tool invokes these operations with full schema discovery.
 
+#### OAuth-Enabled MCPs
+
+Skills can define OAuth-protected remote MCP servers. OAuth 2.1 with full RFC compliance (RFC 9728, 8414, 8707, 7591) is supported:
+
+```yaml
+---
+description: My API skill
+mcp:
+  my-api:
+    url: https://api.example.com/mcp
+    oauth:
+      clientId: ${CLIENT_ID}
+      scopes: ["read", "write"]
+---
+```
+
+When a skill MCP has `oauth` configured:
+- **Auto-discovery**: Fetches `/.well-known/oauth-protected-resource` (RFC 9728), falls back to `/.well-known/oauth-authorization-server` (RFC 8414)
+- **Dynamic Client Registration**: Auto-registers with servers supporting RFC 7591 (clientId becomes optional)
+- **PKCE**: Mandatory for all flows
+- **Resource Indicators**: Auto-generated from MCP URL per RFC 8707
+- **Token Storage**: Persisted in `~/.config/opencode/mcp-oauth.json` (chmod 0600)
+- **Auto-refresh**: Tokens refresh on 401; step-up authorization on 403 with `WWW-Authenticate`
+- **Dynamic Port**: OAuth callback server uses an auto-discovered available port
+
+Pre-authenticate via CLI:
+
+```bash
+bunx oh-my-opencode mcp oauth login <server-name> --server-url https://api.example.com
+```
+
 ---
 
 ## Context Injection

docs/guide/installation.md

@@ -132,7 +132,7 @@ First, add the opencode-antigravity-auth plugin:
 {
   "plugin": [
     "oh-my-opencode",
-    "opencode-antigravity-auth@1.2.8"
+    "opencode-antigravity-auth@latest"
   ]
 }
 ```
@@ -140,7 +140,7 @@ First, add the opencode-antigravity-auth plugin:
 ##### Model Configuration
 
 You'll also need full model settings in `opencode.json`.
-Read the [opencode-antigravity-auth documentation](https://github.com/NoeFabris/opencode-antigravity-auth), copy provider/models config from the README, and merge carefully to avoid breaking the user's existing setup.
+Read the [opencode-antigravity-auth documentation](https://github.com/NoeFabris/opencode-antigravity-auth), copy the full model configuration from the README, and merge carefully to avoid breaking the user's existing setup. The plugin now uses a **variant system** — models like `antigravity-gemini-3-pro` support `low`/`high` variants instead of separate `-low`/`-high` model entries.
 
 ##### oh-my-opencode Agent Model Override
 
@@ -154,7 +154,17 @@ The `opencode-antigravity-auth` plugin uses different model names than the built
 }
 ```
 
-**Available model names**: `google/antigravity-gemini-3-pro-high`, `google/antigravity-gemini-3-pro-low`, `google/antigravity-gemini-3-flash`, `google/antigravity-claude-sonnet-4-5`, `google/antigravity-claude-sonnet-4-5-thinking-low`, `google/antigravity-claude-sonnet-4-5-thinking-medium`, `google/antigravity-claude-sonnet-4-5-thinking-high`, `google/antigravity-claude-opus-4-5-thinking-low`, `google/antigravity-claude-opus-4-5-thinking-medium`, `google/antigravity-claude-opus-4-5-thinking-high`, `google/gemini-3-pro-preview`, `google/gemini-3-flash-preview`, `google/gemini-2.5-pro`, `google/gemini-2.5-flash`
+**Available models (Antigravity quota)**:
+- `google/antigravity-gemini-3-pro` — variants: `low`, `high`
+- `google/antigravity-gemini-3-flash` — variants: `minimal`, `low`, `medium`, `high`
+- `google/antigravity-claude-sonnet-4-5` — no variants
+- `google/antigravity-claude-sonnet-4-5-thinking` — variants: `low`, `max`
+- `google/antigravity-claude-opus-4-5-thinking` — variants: `low`, `max`
+
+**Available models (Gemini CLI quota)**:
+- `google/gemini-2.5-flash`, `google/gemini-2.5-pro`, `google/gemini-3-flash-preview`, `google/gemini-3-pro-preview`
+
+> **Note**: Legacy tier-suffixed names like `google/antigravity-gemini-3-pro-high` still work but variants are recommended. Use `--variant=high` with the base model name instead.
 
 Then authenticate:
 
@@ -183,7 +193,7 @@ When GitHub Copilot is the best available provider, oh-my-opencode uses these mo
 | ------------- | -------------------------------- |
 | **Sisyphus**  | `github-copilot/claude-opus-4.5` |
 | **Oracle**    | `github-copilot/gpt-5.2`         |
-| **Explore**   | `github-copilot/grok-code-fast-1`|
+| **Explore**   | `opencode/gpt-5-nano`              |
 | **Librarian** | `zai-coding-plan/glm-4.7` (if Z.ai available) or fallback |
 
 GitHub Copilot acts as a proxy provider, routing requests to underlying models based on your subscription.
@@ -203,7 +213,7 @@ If Z.ai is the only provider available, all agents will use GLM models:
 
 #### OpenCode Zen
 
-OpenCode Zen provides access to `opencode/` prefixed models including `opencode/claude-opus-4-5`, `opencode/gpt-5.2`, `opencode/grok-code`, and `opencode/glm-4.7-free`.
+OpenCode Zen provides access to `opencode/` prefixed models including `opencode/claude-opus-4-5`, `opencode/gpt-5.2`, `opencode/gpt-5-nano`, and `opencode/glm-4.7-free`.
 
 When OpenCode Zen is the best available provider (no native or Copilot), these models are used:
 
@@ -211,7 +221,7 @@ When OpenCode Zen is the best available provider (no native or Copilot), these m
 | ------------- | -------------------------------- |
 | **Sisyphus**  | `opencode/claude-opus-4-5`       |
 | **Oracle**    | `opencode/gpt-5.2`               |
-| **Explore**   | `opencode/grok-code`             |
+| **Explore**   | `opencode/gpt-5-nano`             |
 | **Librarian** | `opencode/glm-4.7-free`          |
 
 ##### Setup
@@ -268,7 +278,7 @@ After everything is set up and working, ask the user:
 
 If the user agrees, run:
 ```bash
-gh repo star code-yeongyu/oh-my-opencode
+gh api --silent --method PUT /user/starred/code-yeongyu/oh-my-opencode >/dev/null 2>&1 || true
 ```
 
 **Important**: Only run the command if the user explicitly says yes. Never run it automatically without consent.

docs/guide/overview.md

@@ -54,7 +54,7 @@ For complex or critical tasks, press **Tab** to switch to Prometheus (Planner) m
 
 2. **Plan generation** - Based on the interview, Prometheus generates a detailed work plan with tasks, acceptance criteria, and guardrails. Optionally reviewed by Momus (plan reviewer) for high-accuracy validation.
 
-3. **Run `/start-work`** - The Orchestrator-Sisyphus takes over:
+3. **Run `/start-work`** - The Atlas takes over:
    - Distributes tasks to specialized sub-agents
    - Verifies each task completion independently
    - Accumulates learnings across tasks
@@ -84,7 +84,78 @@ The orchestrator is designed to execute work plans created by Prometheus. Using
 4. Run /start-work → Orchestrator executes
 ```
 
-**Prometheus and Orchestrator-Sisyphus are a pair. Always use them together.**
+**Prometheus and Atlas are a pair. Always use them together.**
+
+---
+
+## Model Configuration
+
+Oh My OpenCode automatically configures models based on your available providers. You don't need to manually specify every model.
+
+### How Models Are Determined
+
+**1. At Installation Time (Interactive Installer)**
+
+When you run `bunx oh-my-opencode install`, the installer asks which providers you have:
+- Claude Pro/Max subscription?
+- OpenAI/ChatGPT Plus?
+- Google Gemini?
+- GitHub Copilot?
+- OpenCode Zen?
+- Z.ai Coding Plan?
+
+Based on your answers, it generates `~/.config/opencode/oh-my-opencode.json` with optimal model assignments for each agent and category.
+
+**2. At Runtime (Fallback Chain)**
+
+Each agent has a **provider priority chain**. The system tries providers in order until it finds an available model:
+
+```
+Example: multimodal-looker
+google → openai → zai-coding-plan → anthropic → opencode
+   ↓        ↓           ↓              ↓           ↓
+gemini   gpt-5.2     glm-4.6v       haiku     gpt-5-nano
+```
+
+If you have Gemini, it uses `google/gemini-3-flash`. No Gemini but have Claude? Uses `anthropic/claude-haiku-4-5`. And so on.
+
+### Example Configuration
+
+Here's a real-world config for a user with **Claude, OpenAI, Gemini, and Z.ai** all available:
+
+```jsonc
+{
+  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
+  "agents": {
+    // Override specific agents only - rest use fallback chain
+    "atlas": { "model": "anthropic/claude-sonnet-4-5", "variant": "max" },
+    "librarian": { "model": "zai-coding-plan/glm-4.7" },
+    "explore": { "model": "opencode/gpt-5-nano" },
+    "multimodal-looker": { "model": "zai-coding-plan/glm-4.6v" }
+  },
+  "categories": {
+    // Override categories for cost optimization
+    "quick": { "model": "opencode/gpt-5-nano" },
+    "unspecified-low": { "model": "zai-coding-plan/glm-4.7" }
+  },
+  "experimental": {
+    "aggressive_truncation": true
+  }
+}
+```
+
+**Key points:**
+- You only need to override what you want to change
+- Unspecified agents/categories use the automatic fallback chain
+- Mix providers freely (Claude for main work, Z.ai for cheap tasks, etc.)
+
+### Finding Available Models
+
+Run `opencode models` to see all available models in your environment. Model names follow the format `provider/model-name`.
+
+### Learn More
+
+For detailed configuration options including per-agent settings, category customization, and more, see the [Configuration Guide](../configurations.md).
 
 ---
 

docs/guide/understanding-orchestration-system.md

@@ -1,6 +1,6 @@
 # Understanding the Orchestration System
 
-Oh My OpenCode's orchestration system transforms a simple AI agent into a coordinated development team. This document explains how the Prometheus → Orchestrator → Junior workflow creates high-quality, reliable code output.
+Oh My OpenCode's orchestration system transforms a simple AI agent into a coordinated development team. This document explains how the Prometheus → Atlas → Junior workflow creates high-quality, reliable code output.
 
 ---
 
@@ -29,7 +29,7 @@ flowchart TB
     end
     
     subgraph Execution["Execution Layer (Orchestrator)"]
-        Orchestrator["⚡ Orchestrator-Sisyphus<br/>(Conductor)<br/>Claude Opus 4.5"]
+        Orchestrator["⚡ Atlas<br/>(Conductor)<br/>Claude Opus 4.5"]
     end
     
     subgraph Workers["Worker Layer (Specialized Agents)"]
@@ -152,7 +152,7 @@ If REJECTED, Prometheus fixes issues and resubmits. **No maximum retry limit.**
 
 ---
 
-## Layer 2: Execution (Orchestrator-Sisyphus)
+## Layer 2: Execution (Atlas)
 
 ### The Conductor Mindset
 
@@ -160,7 +160,7 @@ The Orchestrator is like an orchestra conductor: **it doesn't play instruments,
 
 ```mermaid
 flowchart LR
-    subgraph Orchestrator["Orchestrator-Sisyphus"]
+    subgraph Orchestrator["Atlas"]
         Read["1. Read Plan"]
         Analyze["2. Analyze Tasks"]
         Wisdom["3. Accumulate Wisdom"]
@@ -326,13 +326,13 @@ Skills prepend specialized instructions to subagent prompts:
 // Category + Skill combination
 delegate_task(
   category="visual-engineering", 
-  skills=["frontend-ui-ux"],  // Adds UI/UX expertise
+  load_skills=["frontend-ui-ux"],  // Adds UI/UX expertise
   prompt="..."
 )
 
 delegate_task(
   category="general",
-  skills=["playwright"],  // Adds browser automation expertise
+  load_skills=["playwright"],  // Adds browser automation expertise
   prompt="..."
 )
 ```
@@ -341,8 +341,8 @@ delegate_task(
 
 | Before | After |
 |--------|-------|
-| Hardcoded: `frontend-ui-ux-engineer` (Gemini 3 Pro) | `category="visual-engineering" + skills=["frontend-ui-ux"]` |
-| One-size-fits-all | `category="visual-engineering" + skills=["unity-master"]` |
+| Hardcoded: `frontend-ui-ux-engineer` (Gemini 3 Pro) | `category="visual-engineering" + load_skills=["frontend-ui-ux"]` |
+| One-size-fits-all | `category="visual-engineering" + load_skills=["unity-master"]` |
 | Model bias | Category-based: model abstraction eliminates bias |
 
 ---
@@ -352,7 +352,7 @@ delegate_task(
 ```mermaid
 sequenceDiagram
     participant User
-    participant Orchestrator as Orchestrator-Sisyphus
+    participant Orchestrator as Atlas
     participant Junior as Sisyphus-Junior
     participant Notepad as .sisyphus/notepads/
     
@@ -365,7 +365,7 @@ sequenceDiagram
         
         Note over Orchestrator: Prompt Structure:<br/>1. TASK (exact checkbox)<br/>2. EXPECTED OUTCOME<br/>3. REQUIRED SKILLS<br/>4. REQUIRED TOOLS<br/>5. MUST DO<br/>6. MUST NOT DO<br/>7. CONTEXT + Wisdom
         
-        Orchestrator->>Junior: delegate_task(category, skills, prompt)
+        Orchestrator->>Junior: delegate_task(category, load_skills, prompt)
         
         Junior->>Junior: Create todos, execute
         Junior->>Junior: Verify (lsp_diagnostics, tests)
@@ -392,7 +392,7 @@ sequenceDiagram
 ### 1. Separation of Concerns
 
 - **Planning** (Prometheus): High reasoning, interview, strategic thinking
-- **Orchestration** (Sisyphus): Coordination, verification, wisdom accumulation
+- **Orchestration** (Atlas): Coordination, verification, wisdom accumulation
 - **Execution** (Junior): Focused implementation, no distractions
 
 ### 2. Explicit Over Implicit

docs/orchestration-guide.md

@@ -6,9 +6,10 @@
 |------------|----------|-------------|
 | **Simple** | Just prompt | Simple tasks, quick fixes, single-file changes |
 | **Complex + Lazy** | Just type `ulw` or `ultrawork` | Complex tasks where explaining context is tedious. Agent figures it out. |
-| **Complex + Precise** | `@plan` → `/start-work` | Precise, multi-step work requiring true orchestration. Prometheus plans, Sisyphus executes. |
+| **Complex + Precise** | `@plan` → `/start-work` | Precise, multi-step work requiring true orchestration. Prometheus plans, Atlas executes. |
 
 **Decision Flow:**
+
 ```
 Is it a quick fix or simple task?
   └─ YES → Just prompt normally
@@ -30,7 +31,7 @@ Traditional AI agents often mix planning and execution, leading to context pollu
 Oh-My-OpenCode solves this by clearly separating two roles:
 
 1. **Prometheus (Planner)**: A pure strategist who never writes code. Establishes perfect plans through interviews and analysis.
-2. **Sisyphus (Executor)**: An orchestrator who executes plans. Delegates work to specialized agents and never stops until completion.
+2. **Atlas (Executor)**: An orchestrator who executes plans. Delegates work to specialized agents and never stops until completion.
 
 ---
 
@@ -52,10 +53,10 @@ flowchart TD
     StartWork --> BoulderState[boulder.json]
     
     subgraph Execution Phase
-        BoulderState --> Sisyphus[Sisyphus<br>Orchestrator]
-        Sisyphus --> Oracle[Oracle]
-        Sisyphus --> Frontend[Frontend<br>Engineer]
-        Sisyphus --> Explore[Explore]
+        BoulderState --> Atlas[Atlas<br>Orchestrator]
+        Atlas --> Oracle[Oracle]
+        Atlas --> Frontend[Frontend<br>Engineer]
+        Atlas --> Explore[Explore]
     end
 ```
 
@@ -64,22 +65,26 @@ flowchart TD
 ## 3. Key Components
 
 ### 🔮 Prometheus (The Planner)
+
 - **Model**: `anthropic/claude-opus-4-5`
 - **Role**: Strategic planning, requirements interviews, work plan creation
 - **Constraint**: **READ-ONLY**. Can only create/modify markdown files within `.sisyphus/` directory.
 - **Characteristic**: Never writes code directly, focuses solely on "how to do it".
 
-### 🦉 Metis (The Consultant)
+### 🦉 Metis (The Plan Consultant)
+
 - **Role**: Pre-analysis and gap detection
 - **Function**: Identifies hidden user intent, prevents AI over-engineering, eliminates ambiguity.
 - **Workflow**: Metis consultation is mandatory before plan creation.
 
-### ⚖️ Momus (The Reviewer)
+### ⚖️ Momus (The Plan Reviewer)
+
 - **Role**: High-precision plan validation (High Accuracy Mode)
 - **Function**: Rejects and demands revisions until the plan is perfect.
 - **Trigger**: Activated when user requests "high accuracy".
 
-### 🪨 Sisyphus (The Orchestrator)
+### ⚡ Atlas (The Plan Executor)
+
 - **Model**: `anthropic/claude-opus-4-5` (Extended Thinking 32k)
 - **Role**: Execution and delegation
 - **Characteristic**: Doesn't do everything directly, actively delegates to specialized agents (Frontend, Librarian, etc.).
@@ -89,6 +94,7 @@ flowchart TD
 ## 4. Workflow
 
 ### Phase 1: Interview and Planning (Interview Mode)
+
 Prometheus starts in **interview mode** by default. Instead of immediately creating a plan, it collects sufficient context.
 
 1. **Intent Identification**: Classifies whether the user's request is Refactoring or New Feature.
@@ -96,6 +102,7 @@ Prometheus starts in **interview mode** by default. Instead of immediately creat
 3. **Draft Creation**: Continuously records discussion content in `.sisyphus/drafts/`.
 
 ### Phase 2: Plan Generation
+
 When the user requests "Make it a plan", plan generation begins.
 
 1. **Metis Consultation**: Confirms any missed requirements or risk factors.
@@ -103,10 +110,11 @@ When the user requests "Make it a plan", plan generation begins.
 3. **Handoff**: Once plan creation is complete, guides user to use `/start-work` command.
 
 ### Phase 3: Execution
+
 When the user enters `/start-work`, the execution phase begins.
 
 1. **State Management**: Creates `boulder.json` file to track current plan and session ID.
-2. **Task Execution**: Sisyphus reads the plan and processes TODOs one by one.
+2. **Task Execution**: Atlas reads the plan and processes TODOs one by one.
 3. **Delegation**: UI work is delegated to Frontend agent, complex logic to Oracle.
 4. **Continuity**: Even if the session is interrupted, work continues in the next session through `boulder.json`.
 
@@ -115,11 +123,15 @@ When the user enters `/start-work`, the execution phase begins.
 ## 5. Commands and Usage
 
 ### `@plan [request]`
+
 Invokes Prometheus to start a planning session.
+
 - Example: `@plan "I want to refactor the authentication system to NextAuth"`
 
 ### `/start-work`
+
 Executes the generated plan.
+
 - Function: Finds plan in `.sisyphus/plans/` and enters execution mode.
 - If there's interrupted work, automatically resumes from where it left off.
 
@@ -132,7 +144,7 @@ You can control related features in `oh-my-opencode.json`.
 ```jsonc
 {
   "sisyphus_agent": {
-    "disabled": false,           // Enable Sisyphus orchestration (default: false)
+    "disabled": false,           // Enable Atlas orchestration (default: false)
     "planner_enabled": true,     // Enable Prometheus (default: true)
     "replace_plan": true         // Replace default plan agent with Prometheus (default: true)
   },

docs/troubleshooting/ollama-streaming-issue.md

@@ -0,0 +1,126 @@
+# Ollama Streaming Issue - JSON Parse Error
+
+## Problem
+
+When using Ollama as a provider with oh-my-opencode agents, you may encounter:
+
+```
+JSON Parse error: Unexpected EOF
+```
+
+This occurs when agents attempt tool calls (e.g., `explore` agent using `mcp_grep_search`).
+
+## Root Cause
+
+Ollama returns **NDJSON** (newline-delimited JSON) when `stream: true` is used in API requests:
+
+```json
+{"message":{"tool_calls":[{"function":{"name":"read","arguments":{"filePath":"README.md"}}}]}, "done":false}
+{"message":{"content":""}, "done":true}
+```
+
+Claude Code SDK expects a single JSON object, not multiple NDJSON lines, causing the parse error.
+
+### Why This Happens
+
+- **Ollama API**: Returns streaming responses as NDJSON by design
+- **Claude Code SDK**: Doesn't properly handle NDJSON responses for tool calls
+- **oh-my-opencode**: Passes through the SDK's behavior (can't fix at this layer)
+
+## Solutions
+
+### Option 1: Disable Streaming (Recommended - Immediate Fix)
+
+Configure your Ollama provider to use `stream: false`:
+
+```json
+{
+  "provider": "ollama",
+  "model": "qwen3-coder",
+  "stream": false
+}
+```
+
+**Pros:**
+- Works immediately
+- No code changes needed
+- Simple configuration
+
+**Cons:**
+- Slightly slower response time (no streaming)
+- Less interactive feedback
+
+### Option 2: Use Non-Tool Agents Only
+
+If you need streaming, avoid agents that use tools:
+
+- ✅ **Safe**: Simple text generation, non-tool tasks
+- ❌ **Problematic**: Any agent with tool calls (explore, librarian, etc.)
+
+### Option 3: Wait for SDK Fix (Long-term)
+
+The proper fix requires Claude Code SDK to:
+
+1. Detect NDJSON responses
+2. Parse each line separately
+3. Merge `tool_calls` from multiple lines
+4. Return a single merged response
+
+**Tracking**: https://github.com/code-yeongyu/oh-my-opencode/issues/1124
+
+## Workaround Implementation
+
+Until the SDK is fixed, here's how to implement NDJSON parsing (for SDK maintainers):
+
+```typescript
+async function parseOllamaStreamResponse(response: string): Promise<object> {
+  const lines = response.split('\n').filter(line => line.trim());
+  const mergedMessage = { tool_calls: [] };
+
+  for (const line of lines) {
+    try {
+      const json = JSON.parse(line);
+      if (json.message?.tool_calls) {
+        mergedMessage.tool_calls.push(...json.message.tool_calls);
+      }
+      if (json.message?.content) {
+        mergedMessage.content = json.message.content;
+      }
+    } catch (e) {
+      // Skip malformed lines
+      console.warn('Skipping malformed NDJSON line:', line);
+    }
+  }
+
+  return mergedMessage;
+}
+```
+
+## Testing
+
+To verify the fix works:
+
+```bash
+# Test with curl (should work with stream: false)
+curl -s http://localhost:11434/api/chat \
+  -d '{
+    "model": "qwen3-coder",
+    "messages": [{"role": "user", "content": "Read file README.md"}],
+    "stream": false,
+    "tools": [{"type": "function", "function": {"name": "read", "description": "Read a file", "parameters": {"type": "object", "properties": {"filePath": {"type": "string"}}, "required": ["filePath"]}}}]
+  }'
+```
+
+## Related Issues
+
+- **oh-my-opencode**: https://github.com/code-yeongyu/oh-my-opencode/issues/1124
+- **Ollama API Docs**: https://github.com/ollama/ollama/blob/main/docs/api.md
+
+## Getting Help
+
+If you encounter this issue:
+
+1. Check your Ollama provider configuration
+2. Set `stream: false` as a workaround
+3. Report any additional errors to the issue tracker
+4. Provide your configuration (without secrets) for debugging

package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "3.0.0-beta.13",
+  "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",
@@ -64,6 +64,7 @@
     "jsonc-parser": "^3.3.1",
     "picocolors": "^1.1.1",
     "picomatch": "^4.0.2",
+    "vscode-jsonrpc": "^8.2.0",
     "zod": "^4.1.8"
   },
   "devDependencies": {
@@ -73,13 +74,13 @@
     "typescript": "^5.7.3"
   },
   "optionalDependencies": {
-    "oh-my-opencode-darwin-arm64": "3.0.0-beta.13",
-    "oh-my-opencode-darwin-x64": "3.0.0-beta.13",
-    "oh-my-opencode-linux-arm64": "3.0.0-beta.13",
-    "oh-my-opencode-linux-arm64-musl": "3.0.0-beta.13",
-    "oh-my-opencode-linux-x64": "3.0.0-beta.13",
-    "oh-my-opencode-linux-x64-musl": "3.0.0-beta.13",
-    "oh-my-opencode-windows-x64": "3.0.0-beta.13"
+    "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": "3.0.0-beta.13",
+  "version": "3.1.11",
   "description": "Platform-specific binary for oh-my-opencode (darwin-arm64)",
   "license": "MIT",
   "repository": {

packages/darwin-x64-baseline/package.json

@@ -0,0 +1,22 @@
+{
+  "name": "oh-my-opencode-darwin-x64-baseline",
+  "version": "3.1.1",
+  "description": "Platform-specific binary for oh-my-opencode (darwin-x64-baseline, no AVX2)",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/code-yeongyu/oh-my-opencode"
+  },
+  "os": [
+    "darwin"
+  ],
+  "cpu": [
+    "x64"
+  ],
+  "files": [
+    "bin"
+  ],
+  "bin": {
+    "oh-my-opencode": "./bin/oh-my-opencode"
+  }
+}

packages/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-x64",
-  "version": "3.0.0-beta.13",
+  "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": "3.0.0-beta.13",
+  "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": "3.0.0-beta.13",
+  "version": "3.1.11",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64)",
   "license": "MIT",
   "repository": {

packages/linux-x64-baseline/package.json

@@ -0,0 +1,25 @@
+{
+  "name": "oh-my-opencode-linux-x64-baseline",
+  "version": "3.1.1",
+  "description": "Platform-specific binary for oh-my-opencode (linux-x64-baseline, no AVX2)",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/code-yeongyu/oh-my-opencode"
+  },
+  "os": [
+    "linux"
+  ],
+  "cpu": [
+    "x64"
+  ],
+  "libc": [
+    "glibc"
+  ],
+  "files": [
+    "bin"
+  ],
+  "bin": {
+    "oh-my-opencode": "./bin/oh-my-opencode"
+  }
+}

packages/linux-x64-musl-baseline/package.json

@@ -0,0 +1,25 @@
+{
+  "name": "oh-my-opencode-linux-x64-musl-baseline",
+  "version": "3.1.1",
+  "description": "Platform-specific binary for oh-my-opencode (linux-x64-musl-baseline, no AVX2)",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/code-yeongyu/oh-my-opencode"
+  },
+  "os": [
+    "linux"
+  ],
+  "cpu": [
+    "x64"
+  ],
+  "libc": [
+    "musl"
+  ],
+  "files": [
+    "bin"
+  ],
+  "bin": {
+    "oh-my-opencode": "./bin/oh-my-opencode"
+  }
+}

packages/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-musl",
-  "version": "3.0.0-beta.13",
+  "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": "3.0.0-beta.13",
+  "version": "3.1.11",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64)",
   "license": "MIT",
   "repository": {

packages/windows-x64-baseline/package.json

@@ -0,0 +1,22 @@
+{
+  "name": "oh-my-opencode-windows-x64-baseline",
+  "version": "3.1.1",
+  "description": "Platform-specific binary for oh-my-opencode (windows-x64-baseline, no AVX2)",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/code-yeongyu/oh-my-opencode"
+  },
+  "os": [
+    "win32"
+  ],
+  "cpu": [
+    "x64"
+  ],
+  "files": [
+    "bin"
+  ],
+  "bin": {
+    "oh-my-opencode": "./bin/oh-my-opencode.exe"
+  }
+}

packages/windows-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-windows-x64",
-  "version": "3.0.0-beta.13",
+  "version": "3.1.11",
   "description": "Platform-specific binary for oh-my-opencode (windows-x64)",
   "license": "MIT",
   "repository": {

script/build-binaries.test.ts

@@ -0,0 +1,79 @@
+// script/build-binaries.test.ts
+// Tests for platform binary build configuration
+
+import { describe, expect, it } from "bun:test";
+
+// Import PLATFORMS from build-binaries.ts
+// We need to export it first, but for now we'll test the expected structure
+const EXPECTED_BASELINE_TARGETS = [
+  "bun-linux-x64-baseline",
+  "bun-linux-x64-musl-baseline",
+  "bun-darwin-x64-baseline",
+  "bun-windows-x64-baseline",
+];
+
+describe("build-binaries", () => {
+  describe("PLATFORMS array", () => {
+    it("includes baseline variants for non-AVX2 CPU support", async () => {
+      // given
+      const module = await import("./build-binaries.ts");
+      const platforms = (module as { PLATFORMS: { target: string }[] }).PLATFORMS;
+      const targets = platforms.map((p) => p.target);
+
+      // when
+      const hasAllBaselineTargets = EXPECTED_BASELINE_TARGETS.every((baseline) =>
+        targets.includes(baseline)
+      );
+
+      // then
+      expect(hasAllBaselineTargets).toBe(true);
+      for (const baseline of EXPECTED_BASELINE_TARGETS) {
+        expect(targets).toContain(baseline);
+      }
+    });
+
+    it("has correct directory names for baseline platforms", async () => {
+      // given
+      const module = await import("./build-binaries.ts");
+      const platforms = (module as { PLATFORMS: { dir: string; target: string }[] }).PLATFORMS;
+
+      // when
+      const baselinePlatforms = platforms.filter((p) => p.target.includes("baseline"));
+
+      // then
+      expect(baselinePlatforms.length).toBe(4);
+      expect(baselinePlatforms.map((p) => p.dir)).toContain("linux-x64-baseline");
+      expect(baselinePlatforms.map((p) => p.dir)).toContain("linux-x64-musl-baseline");
+      expect(baselinePlatforms.map((p) => p.dir)).toContain("darwin-x64-baseline");
+      expect(baselinePlatforms.map((p) => p.dir)).toContain("windows-x64-baseline");
+    });
+
+    it("has correct binary names for baseline platforms", async () => {
+      // given
+      const module = await import("./build-binaries.ts");
+      const platforms = (module as { PLATFORMS: { dir: string; target: string; binary: string }[] }).PLATFORMS;
+
+      // when
+      const windowsBaseline = platforms.find((p) => p.target === "bun-windows-x64-baseline");
+      const linuxBaseline = platforms.find((p) => p.target === "bun-linux-x64-baseline");
+
+      // then
+      expect(windowsBaseline?.binary).toBe("oh-my-opencode.exe");
+      expect(linuxBaseline?.binary).toBe("oh-my-opencode");
+    });
+
+    it("has descriptions mentioning no AVX2 for baseline platforms", async () => {
+      // given
+      const module = await import("./build-binaries.ts");
+      const platforms = (module as { PLATFORMS: { target: string; description: string }[] }).PLATFORMS;
+
+      // when
+      const baselinePlatforms = platforms.filter((p) => p.target.includes("baseline"));
+
+      // then
+      for (const platform of baselinePlatforms) {
+        expect(platform.description).toContain("no AVX2");
+      }
+    });
+  });
+});

script/build-binaries.ts

@@ -13,14 +13,18 @@ interface PlatformTarget {
   description: string;
 }
 
-const PLATFORMS: PlatformTarget[] = [
+export const PLATFORMS: PlatformTarget[] = [
   { dir: "darwin-arm64", target: "bun-darwin-arm64", binary: "oh-my-opencode", description: "macOS ARM64" },
   { dir: "darwin-x64", target: "bun-darwin-x64", binary: "oh-my-opencode", description: "macOS x64" },
+  { dir: "darwin-x64-baseline", target: "bun-darwin-x64-baseline", binary: "oh-my-opencode", description: "macOS x64 (no AVX2)" },
   { dir: "linux-x64", target: "bun-linux-x64", binary: "oh-my-opencode", description: "Linux x64 (glibc)" },
+  { dir: "linux-x64-baseline", target: "bun-linux-x64-baseline", binary: "oh-my-opencode", description: "Linux x64 (glibc, no AVX2)" },
   { dir: "linux-arm64", target: "bun-linux-arm64", binary: "oh-my-opencode", description: "Linux ARM64 (glibc)" },
   { dir: "linux-x64-musl", target: "bun-linux-x64-musl", binary: "oh-my-opencode", description: "Linux x64 (musl)" },
+  { dir: "linux-x64-musl-baseline", target: "bun-linux-x64-musl-baseline", binary: "oh-my-opencode", description: "Linux x64 (musl, no AVX2)" },
   { dir: "linux-arm64-musl", target: "bun-linux-arm64-musl", binary: "oh-my-opencode", description: "Linux ARM64 (musl)" },
   { dir: "windows-x64", target: "bun-windows-x64", binary: "oh-my-opencode.exe", description: "Windows x64" },
+  { dir: "windows-x64-baseline", target: "bun-windows-x64-baseline", binary: "oh-my-opencode.exe", description: "Windows x64 (no AVX2)" },
 ];
 
 const ENTRY_POINT = "src/cli/index.ts";

signatures/cla.json

@@ -711,6 +711,358 @@
       "created_at": "2026-01-22T12:39:26Z",
       "repoId": 1108837393,
       "pullRequestNo": 989
+    },
+    {
+      "name": "l3aro",
+      "id": 25253808,
+      "comment_id": 3786383804,
+      "created_at": "2026-01-22T19:52:42Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 999
+    },
+    {
+      "name": "Ssoon-m",
+      "id": 89559826,
+      "comment_id": 3788539617,
+      "created_at": "2026-01-23T06:31:24Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1014
+    },
+    {
+      "name": "veetase",
+      "id": 2784250,
+      "comment_id": 3789028002,
+      "created_at": "2026-01-23T08:27:02Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 985
+    },
+    {
+      "name": "RouHim",
+      "id": 3582050,
+      "comment_id": 3791988227,
+      "created_at": "2026-01-23T19:32:01Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1031
+    },
+    {
+      "name": "gongxh0901",
+      "id": 15622561,
+      "comment_id": 3793478620,
+      "created_at": "2026-01-24T02:15:02Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1037
+    },
+    {
+      "name": "gongxh0901",
+      "id": 15622561,
+      "comment_id": 3793521632,
+      "created_at": "2026-01-24T02:23:34Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1037
+    },
+    {
+      "name": "AndersHsueh",
+      "id": 121805544,
+      "comment_id": 3793787614,
+      "created_at": "2026-01-24T04:41:46Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1042
+    },
+    {
+      "name": "AamiRobin",
+      "id": 22963668,
+      "comment_id": 3794632200,
+      "created_at": "2026-01-24T13:28:22Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1067
+    },
+    {
+      "name": "ThanhNguyxn",
+      "id": 74597207,
+      "comment_id": 3795232176,
+      "created_at": "2026-01-24T17:41:53Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1075
+    },
+    {
+      "name": "sadnow",
+      "id": 87896100,
+      "comment_id": 3795495342,
+      "created_at": "2026-01-24T20:49:29Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1080
+    },
+    {
+      "name": "jsl9208",
+      "id": 4048787,
+      "comment_id": 3795582626,
+      "created_at": "2026-01-24T21:41:24Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1082
+    },
+    {
+      "name": "potb",
+      "id": 10779093,
+      "comment_id": 3795856573,
+      "created_at": "2026-01-25T02:38:16Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1083
+    },
+    {
+      "name": "kvokka",
+      "id": 15954013,
+      "comment_id": 3795884358,
+      "created_at": "2026-01-25T03:13:52Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1084
+    },
+    {
+      "name": "misyuari",
+      "id": 12197761,
+      "comment_id": 3798225767,
+      "created_at": "2026-01-26T07:31:02Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1132
+    },
+    {
+      "name": "boguan",
+      "id": 3226538,
+      "comment_id": 3798448537,
+      "created_at": "2026-01-26T08:40:37Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1137
+    },
+    {
+      "name": "boguan",
+      "id": 3226538,
+      "comment_id": 3798471978,
+      "created_at": "2026-01-26T08:46:03Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1137
+    },
+    {
+      "name": "Jeremy-Kr",
+      "id": 110771206,
+      "comment_id": 3799211732,
+      "created_at": "2026-01-26T11:59:13Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1141
+    },
+    {
+      "name": "orientpine",
+      "id": 32758428,
+      "comment_id": 3799897021,
+      "created_at": "2026-01-26T14:30:33Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1145
+    },
+    {
+      "name": "craftaholic",
+      "id": 63741110,
+      "comment_id": 3797014417,
+      "created_at": "2026-01-25T17:52:34Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1110
+    },
+    {
+      "name": "acamq",
+      "id": 179265037,
+      "comment_id": 3801038978,
+      "created_at": "2026-01-26T18:20:17Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1151
+    },
+    {
+      "name": "itsmylife44",
+      "id": 34112129,
+      "comment_id": 3802225779,
+      "created_at": "2026-01-26T23:20:30Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1157
+    },
+    {
+      "name": "ghtndl",
+      "id": 117787238,
+      "comment_id": 3802593326,
+      "created_at": "2026-01-27T01:27:17Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1158
+    },
+    {
+      "name": "alvinunreal",
+      "id": 204474669,
+      "comment_id": 3796402213,
+      "created_at": "2026-01-25T10:26:58Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1100
+    },
+    {
+      "name": "MoerAI",
+      "id": 26067127,
+      "comment_id": 3803968993,
+      "created_at": "2026-01-27T09:00:57Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1172
+    },
+    {
+      "name": "moha-abdi",
+      "id": 83307623,
+      "comment_id": 3804988070,
+      "created_at": "2026-01-27T12:36:21Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1179
+    },
+    {
+      "name": "zycaskevin",
+      "id": 223135116,
+      "comment_id": 3806137669,
+      "created_at": "2026-01-27T16:20:38Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1184
+    },
+    {
+      "name": "agno01",
+      "id": 4479380,
+      "comment_id": 3808373433,
+      "created_at": "2026-01-28T01:02:02Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1188
+    },
+    {
+      "name": "rooftop-Owl",
+      "id": 254422872,
+      "comment_id": 3809867225,
+      "created_at": "2026-01-28T08:46:58Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1197
+    },
+    {
+      "name": "youming-ai",
+      "id": 173424537,
+      "comment_id": 3811195276,
+      "created_at": "2026-01-28T13:04:16Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1203
+    },
+    {
+      "name": "KennyDizi",
+      "id": 16578966,
+      "comment_id": 3811619818,
+      "created_at": "2026-01-28T14:26:10Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1214
+    },
+    {
+      "name": "mrdavidlaing",
+      "id": 227505,
+      "comment_id": 3813542625,
+      "created_at": "2026-01-28T19:51:34Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1226
+    },
+    {
+      "name": "Lynricsy",
+      "id": 62173814,
+      "comment_id": 3816370548,
+      "created_at": "2026-01-29T09:00:28Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1241
+    },
+    {
+      "name": "LeekJay",
+      "id": 39609783,
+      "comment_id": 3819009761,
+      "created_at": "2026-01-29T17:03:24Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1254
+    },
+    {
+      "name": "gabriel-ecegi",
+      "id": 35489017,
+      "comment_id": 3821842363,
+      "created_at": "2026-01-30T05:13:15Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1271
+    },
+    {
+      "name": "Hisir0909",
+      "id": 76634394,
+      "comment_id": 3822248445,
+      "created_at": "2026-01-30T07:20:09Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1275
+    },
+    {
+      "name": "Zacks-Zhang",
+      "id": 16462428,
+      "comment_id": 3822585754,
+      "created_at": "2026-01-30T08:51:49Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1280
+    },
+    {
+      "name": "kunal70006",
+      "id": 62700112,
+      "comment_id": 3822849937,
+      "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
     }
   ]
 }

sisyphus-prompt.md

@@ -239,7 +239,7 @@ Ask yourself:
 I will use delegate_task with:
 - **Category**: [selected-category-name]
 - **Why this category**: [how category description matches task domain]
-- **Skills**: [list of selected skills]
+- **load_skills**: [list of selected skills]
 - **Skill evaluation**:
   - [skill-1]: INCLUDED because [reason based on skill description]
   - [skill-2]: OMITTED because [reason why skill domain doesn't apply]
@@ -256,7 +256,7 @@ I will use delegate_task with:
 I will use delegate_task with:
 - **Category**: [category-name]
 - **Why this category**: Category description says "[quote description]" which matches this task's requirements
-- **Skills**: ["skill-a", "skill-b"]
+- **load_skills**: ["skill-a", "skill-b"]
 - **Skill evaluation**:
   - skill-a: INCLUDED - description says "[quote]" which applies to this task
   - skill-b: INCLUDED - description says "[quote]" which is needed here
@@ -265,7 +265,7 @@ I will use delegate_task with:
 
 delegate_task(
   category="[category-name]",
-  skills=["skill-a", "skill-b"],
+  load_skills=["skill-a", "skill-b"],
   prompt="..."
 )
 ```
@@ -276,12 +276,12 @@ delegate_task(
 I will use delegate_task with:
 - **Agent**: [agent-name]
 - **Reason**: This requires [agent's specialty] based on agent description
-- **Skills**: [] (agents have built-in expertise)
+- **load_skills**: [] (agents have built-in expertise)
 - **Expected Outcome**: [what agent should return]
 
 delegate_task(
   subagent_type="[agent-name]",
-  skills=[],
+  load_skills=[],
   prompt="..."
 )
 ```
@@ -292,13 +292,13 @@ delegate_task(
 I will use delegate_task with:
 - **Agent**: explore
 - **Reason**: Need to find all authentication implementations across the codebase - this is contextual grep
-- **Skills**: []
+- **load_skills**: []
 - **Expected Outcome**: List of files containing auth patterns
 
 delegate_task(
   subagent_type="explore",
   run_in_background=true,
-  skills=[],
+  load_skills=[],
   prompt="Find all authentication implementations in the codebase"
 )
 ```
@@ -306,7 +306,7 @@ delegate_task(
 **WRONG: No Skill Evaluation**
 
 ```
-delegate_task(category="...", skills=[], prompt="...")  // Where's the justification?
+delegate_task(category="...", load_skills=[], prompt="...")  // Where's the justification?
 ```
 
 **WRONG: Vague Category Selection**
@@ -329,11 +329,11 @@ I'll use this category because it seems right.
 ```typescript
 // CORRECT: Always background, always parallel
 // Contextual Grep (internal)
-delegate_task(subagent_type="explore", run_in_background=true, skills=[], prompt="Find auth implementations in our codebase...")
-delegate_task(subagent_type="explore", run_in_background=true, skills=[], prompt="Find error handling patterns here...")
+delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="Find auth implementations in our codebase...")
+delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="Find error handling patterns here...")
 // Reference Grep (external)
-delegate_task(subagent_type="librarian", run_in_background=true, skills=[], prompt="Find JWT best practices in official docs...")
-delegate_task(subagent_type="librarian", run_in_background=true, skills=[], prompt="Find how production apps handle auth in Express...")
+delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="Find JWT best practices in official docs...")
+delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="Find how production apps handle auth in Express...")
 // Continue working immediately. Collect with background_output when needed.
 
 // WRONG: Sequential or blocking
@@ -416,7 +416,7 @@ Skills inject specialized instructions into the subagent. Read the description t
 For EVERY skill listed above, ask yourself:
 > "Does this skill's expertise domain overlap with my task?"
 
-- If YES → INCLUDE in `skills=[...]`
+- If YES → INCLUDE in `load_skills=[...]`
 - If NO → You MUST justify why (see below)
 
 **STEP 3: Justify Omissions**
@@ -444,14 +444,14 @@ SKILL EVALUATION for "[skill-name]":
 ```typescript
 delegate_task(
   category="[selected-category]",
-  skills=["skill-1", "skill-2"],  // Include ALL relevant skills
+  load_skills=["skill-1", "skill-2"],  // Include ALL relevant skills
   prompt="..."
 )
 ```
 
 **ANTI-PATTERN (will produce poor results):**
 ```typescript
-delegate_task(category="...", skills=[], prompt="...")  // Empty skills without justification
+delegate_task(category="...", load_skills=[], prompt="...")  // Empty load_skills without justification
 ```
 ### Delegation Table:
 
@@ -724,7 +724,7 @@ If the user's approach seems problematic:
 | **Error Handling** | Empty catch blocks `catch(e) {}` |
 | **Testing** | Deleting failing tests to "pass" |
 | **Search** | Firing agents for single-line typos or obvious syntax errors |
-| **Delegation** | Using `skills=[]` without justifying why no skills apply |
+| **Delegation** | Using `load_skills=[]` without justifying why no skills apply |
 | **Debugging** | Shotgun debugging, random changes |
 ## Soft Guidelines
 

src/agents/AGENTS.md

@@ -1,53 +1,48 @@
 # AGENTS KNOWLEDGE BASE
 
 ## OVERVIEW
-
 10 AI agents for multi-model orchestration. Sisyphus (primary), Atlas (orchestrator), oracle, librarian, explore, multimodal-looker, Prometheus, Metis, Momus, Sisyphus-Junior.
 
 ## STRUCTURE
-
 ```
 agents/
-├── atlas.ts                    # Master Orchestrator (1383 lines)
-├── sisyphus.ts                 # Main prompt (615 lines)
-├── sisyphus-junior.ts          # Delegated task executor
-├── dynamic-agent-prompt-builder.ts  # Dynamic prompt generation
+├── atlas.ts                    # Master Orchestrator (holds todo list)
+├── sisyphus.ts                 # Main prompt (SF Bay Area engineer identity)
+├── sisyphus-junior.ts          # Delegated task executor (category-spawned)
 ├── oracle.ts                   # Strategic advisor (GPT-5.2)
-├── librarian.ts                # Multi-repo research (GLM-4.7-free)
-├── explore.ts                  # Fast grep (Grok Code)
+├── librarian.ts                # Multi-repo research (GitHub CLI, Context7)
+├── explore.ts                  # Fast contextual grep (Grok Code)
 ├── multimodal-looker.ts        # Media analyzer (Gemini 3 Flash)
-├── prometheus-prompt.ts        # Planning (1196 lines)
-├── metis.ts                    # Plan consultant
-├── momus.ts                    # Plan reviewer
+├── prometheus-prompt.ts        # Planning (Interview/Consultant mode, 1196 lines)
+├── metis.ts                    # Pre-planning analysis (Gap detection)
+├── momus.ts                    # Plan reviewer (Ruthless fault-finding)
+├── dynamic-agent-prompt-builder.ts  # Dynamic prompt generation
 ├── types.ts                    # AgentModelConfig, AgentPromptMetadata
 ├── utils.ts                    # createBuiltinAgents(), resolveModelWithFallback()
 └── index.ts                    # builtinAgents export
 ```
 
 ## AGENT MODELS
-
 | Agent | Model | Temp | Purpose |
 |-------|-------|------|---------|
-| Sisyphus | anthropic/claude-opus-4-5 | 0.1 | Primary orchestrator |
-| Atlas | anthropic/claude-opus-4-5 | 0.1 | Master orchestrator |
+| Sisyphus | anthropic/claude-opus-4-5 | 0.1 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro) |
+| Atlas | anthropic/claude-sonnet-4-5 | 0.1 | Master orchestrator (fallback: kimi-k2.5 → gpt-5.2) |
 | oracle | openai/gpt-5.2 | 0.1 | Consultation, debugging |
-| librarian | opencode/glm-4.7-free | 0.1 | Docs, GitHub search |
-| explore | opencode/grok-code | 0.1 | Fast contextual grep |
+| librarian | zai-coding-plan/glm-4.7 | 0.1 | Docs, GitHub search (fallback: glm-4.7-free) |
+| explore | anthropic/claude-haiku-4-5 | 0.1 | Fast contextual grep (fallback: gpt-5-mini → gpt-5-nano) |
 | multimodal-looker | google/gemini-3-flash | 0.1 | PDF/image analysis |
-| Prometheus | anthropic/claude-opus-4-5 | 0.1 | Strategic planning |
-| Metis | anthropic/claude-sonnet-4-5 | 0.3 | Pre-planning analysis |
-| Momus | anthropic/claude-sonnet-4-5 | 0.1 | Plan validation |
+| Prometheus | anthropic/claude-opus-4-5 | 0.1 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
+| Metis | anthropic/claude-opus-4-5 | 0.3 | Pre-planning analysis (fallback: kimi-k2.5 → gpt-5.2) |
+| Momus | openai/gpt-5.2 | 0.1 | Plan validation (fallback: claude-opus-4-5) |
 | Sisyphus-Junior | anthropic/claude-sonnet-4-5 | 0.1 | Category-spawned executor |
 
 ## HOW TO ADD
-
-1. Create `src/agents/my-agent.ts` exporting factory + metadata
-2. Add to `agentSources` in `src/agents/utils.ts`
-3. Update `AgentNameSchema` in `src/config/schema.ts`
-4. Register in `src/index.ts` initialization
+1. Create `src/agents/my-agent.ts` exporting factory + metadata.
+2. Add to `agentSources` in `src/agents/utils.ts`.
+3. Update `AgentNameSchema` in `src/config/schema.ts`.
+4. Register in `src/index.ts` initialization.
 
 ## TOOL RESTRICTIONS
-
 | Agent | Denied Tools |
 |-------|-------------|
 | oracle | write, edit, task, delegate_task |
@@ -57,14 +52,13 @@ agents/
 | Sisyphus-Junior | task, delegate_task |
 
 ## PATTERNS
-
-- **Factory**: `createXXXAgent(model?: string): AgentConfig`
-- **Metadata**: `XXX_PROMPT_METADATA` with category, cost, triggers
-- **Tool restrictions**: `createAgentToolRestrictions(tools)` or `createAgentToolAllowlist(tools)`
-- **Thinking**: 32k budget tokens for Sisyphus, Oracle, Prometheus, Atlas
+- **Factory**: `createXXXAgent(model: string): AgentConfig`
+- **Metadata**: `XXX_PROMPT_METADATA` with category, cost, triggers.
+- **Tool restrictions**: `createAgentToolRestrictions(tools)` or `createAgentToolAllowlist(tools)`.
+- **Thinking**: 32k budget tokens for Sisyphus, Oracle, Prometheus, Atlas.
 
 ## ANTI-PATTERNS
-
-- **Trust reports**: NEVER trust "I'm done" - verify outputs
-- **High temp**: Don't use >0.3 for code agents
-- **Sequential calls**: Use `delegate_task` with `run_in_background`
+- **Trust reports**: NEVER trust "I'm done" - verify outputs.
+- **High temp**: Don't use >0.3 for code agents.
+- **Sequential calls**: Use `delegate_task` with `run_in_background` for exploration.
+- **Prometheus writing code**: Planner only - never implements.

src/agents/explore.ts

@@ -1,7 +1,9 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { createAgentToolRestrictions } from "../shared/permission-compat"
 
+const MODE: AgentMode = "subagent"
+
 export const EXPLORE_PROMPT_METADATA: AgentPromptMetadata = {
   category: "exploration",
   cost: "FREE",
@@ -33,8 +35,8 @@ export function createExploreAgent(model: string): AgentConfig {
 
   return {
     description:
-      'Contextual grep for codebases. Answers "Where is X?", "Which file has Y?", "Find the code that does Z". Fire multiple in parallel for broad searches. Specify thoroughness: "quick" for basic, "medium" for moderate, "very thorough" for comprehensive analysis.',
-    mode: "subagent" as const,
+      'Contextual grep for codebases. Answers "Where is X?", "Which file has Y?", "Find the code that does Z". Fire multiple in parallel for broad searches. Specify thoroughness: "quick" for basic, "medium" for moderate, "very thorough" for comprehensive analysis. (Explore - OhMyOpenCode)',
+    mode: MODE,
     model,
     temperature: 0.1,
     ...restrictions,
@@ -119,4 +121,4 @@ Use the right tool for the job:
 Flood with parallel calls. Cross-validate findings across multiple tools.`,
   }
 }
-
+createExploreAgent.mode = MODE

src/agents/librarian.ts

@@ -1,7 +1,9 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { createAgentToolRestrictions } from "../shared/permission-compat"
 
+const MODE: AgentMode = "subagent"
+
 export const LIBRARIAN_PROMPT_METADATA: AgentPromptMetadata = {
   category: "exploration",
   cost: "CHEAP",
@@ -30,8 +32,8 @@ export function createLibrarianAgent(model: string): AgentConfig {
 
   return {
     description:
-      "Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search. MUST BE USED when users ask to look up code in remote repositories, explain library internals, or find usage examples in open source.",
-    mode: "subagent" as const,
+      "Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search. MUST BE USED when users ask to look up code in remote repositories, explain library internals, or find usage examples in open source. (Librarian - OhMyOpenCode)",
+    mode: MODE,
     model,
     temperature: 0.1,
     ...restrictions,
@@ -323,4 +325,4 @@ grep_app_searchGitHub(query: "useQuery")
 `,
   }
 }
-
+createLibrarianAgent.mode = MODE

src/agents/metis.ts

@@ -1,7 +1,9 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { createAgentToolRestrictions } from "../shared/permission-compat"
 
+const MODE: AgentMode = "subagent"
+
 /**
  * Metis - Plan Consultant Agent
  *
@@ -230,6 +232,8 @@ call_omo_agent(subagent_type="librarian", prompt="Find OSS implementations of Z.
 - [Risk 2]: [Mitigation]
 
 ## Directives for Prometheus
+
+### Core Directives
 - MUST: [Required action]
 - MUST: [Required action]
 - MUST NOT: [Forbidden action]
@@ -237,6 +241,29 @@ call_omo_agent(subagent_type="librarian", prompt="Find OSS implementations of Z.
 - PATTERN: Follow \`[file:lines]\`
 - TOOL: Use \`[specific tool]\` for [purpose]
 
+### QA/Acceptance Criteria Directives (MANDATORY)
+> **ZERO USER INTERVENTION PRINCIPLE**: All acceptance criteria MUST be executable by agents.
+
+- MUST: Write acceptance criteria as executable commands (curl, bun test, playwright actions)
+- MUST: Include exact expected outputs, not vague descriptions
+- MUST: Specify verification tool for each deliverable type (playwright for UI, curl for API, etc.)
+- MUST NOT: Create criteria requiring "user manually tests..."
+- MUST NOT: Create criteria requiring "user visually confirms..."
+- MUST NOT: Create criteria requiring "user clicks/interacts..."
+- MUST NOT: Use placeholders without concrete examples (bad: "[endpoint]", good: "/api/users")
+
+Example of GOOD acceptance criteria:
+\`\`\`
+curl -s http://localhost:3000/api/health | jq '.status'
+# Assert: Output is "ok"
+\`\`\`
+
+Example of BAD acceptance criteria (FORBIDDEN):
+\`\`\`
+User opens browser and checks if the page loads correctly.
+User confirms the button works as expected.
+\`\`\`
+
 ## Recommended Approach
 [1-2 sentence summary of how to proceed]
 \`\`\`
@@ -263,12 +290,16 @@ call_omo_agent(subagent_type="librarian", prompt="Find OSS implementations of Z.
 - Ask generic questions ("What's the scope?")
 - Proceed without addressing ambiguity
 - Make assumptions about user's codebase
+- Suggest acceptance criteria requiring user intervention ("user manually tests", "user confirms", "user clicks")
+- Leave QA/acceptance criteria vague or placeholder-heavy
 
 **ALWAYS**:
 - Classify intent FIRST
 - Be specific ("Should this change UserService only, or also AuthService?")
 - Explore before asking (for Build/Research intents)
 - Provide actionable directives for Prometheus
+- Include QA automation directives in every output
+- Ensure acceptance criteria are agent-executable (commands, not human actions)
 `
 
 const metisRestrictions = createAgentToolRestrictions([
@@ -281,8 +312,8 @@ const metisRestrictions = createAgentToolRestrictions([
 export function createMetisAgent(model: string): AgentConfig {
   return {
     description:
-      "Pre-planning consultant that analyzes requests to identify hidden intentions, ambiguities, and AI failure points.",
-    mode: "subagent" as const,
+      "Pre-planning consultant that analyzes requests to identify hidden intentions, ambiguities, and AI failure points. (Metis - OhMyOpenCode)",
+    mode: MODE,
     model,
     temperature: 0.3,
     ...metisRestrictions,
@@ -290,7 +321,7 @@ export function createMetisAgent(model: string): AgentConfig {
     thinking: { type: "enabled", budgetTokens: 32000 },
   } as AgentConfig
 }
-
+createMetisAgent.mode = MODE
 
 export const metisPromptMetadata: AgentPromptMetadata = {
   category: "advisor",

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

@@ -1,8 +1,10 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { isGptModel } from "./types"
 import { createAgentToolRestrictions } from "../shared/permission-compat"
 
+const MODE: AgentMode = "subagent"
+
 /**
  * Momus - Plan Reviewer Agent
  *
@@ -17,376 +19,173 @@ import { createAgentToolRestrictions } from "../shared/permission-compat"
  * 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 {
@@ -399,8 +198,8 @@ export function createMomusAgent(model: string): AgentConfig {
 
   const base = {
     description:
-      "Expert reviewer for evaluating work plans against rigorous clarity, verifiability, and completeness standards.",
-    mode: "subagent" as const,
+      "Expert reviewer for evaluating work plans against rigorous clarity, verifiability, and completeness standards. (Momus - OhMyOpenCode)",
+    mode: MODE,
     model,
     temperature: 0.1,
     ...restrictions,
@@ -413,7 +212,7 @@ export function createMomusAgent(model: string): AgentConfig {
 
   return { ...base, thinking: { type: "enabled", budgetTokens: 32000 } } as AgentConfig
 }
-
+createMomusAgent.mode = MODE
 
 export const momusPromptMetadata: AgentPromptMetadata = {
   category: "advisor",

src/agents/multimodal-looker.ts

@@ -1,7 +1,9 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { createAgentToolAllowlist } from "../shared/permission-compat"
 
+const MODE: AgentMode = "subagent"
+
 export const MULTIMODAL_LOOKER_PROMPT_METADATA: AgentPromptMetadata = {
   category: "utility",
   cost: "CHEAP",
@@ -14,8 +16,8 @@ export function createMultimodalLookerAgent(model: string): AgentConfig {
 
   return {
     description:
-      "Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents.",
-    mode: "subagent" as const,
+      "Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents. (Multimodal-Looker - OhMyOpenCode)",
+    mode: MODE,
     model,
     temperature: 0.1,
     ...restrictions,
@@ -53,4 +55,4 @@ Response rules:
 Your output goes straight to the main agent for continued work.`,
   }
 }
-
+createMultimodalLookerAgent.mode = MODE

src/agents/oracle.ts

@@ -1,8 +1,10 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { isGptModel } from "./types"
 import { createAgentToolRestrictions } from "../shared/permission-compat"
 
+const MODE: AgentMode = "subagent"
+
 export const ORACLE_PROMPT_METADATA: AgentPromptMetadata = {
   category: "advisor",
   cost: "EXPENSIVE",
@@ -105,8 +107,8 @@ export function createOracleAgent(model: string): AgentConfig {
 
   const base = {
     description:
-      "Read-only consultation agent. High-IQ reasoning specialist for debugging hard problems and high-difficulty architecture design.",
-    mode: "subagent" as const,
+      "Read-only consultation agent. High-IQ reasoning specialist for debugging hard problems and high-difficulty architecture design. (Oracle - OhMyOpenCode)",
+    mode: MODE,
     model,
     temperature: 0.1,
     ...restrictions,
@@ -119,4 +121,5 @@ export function createOracleAgent(model: string): AgentConfig {
 
   return { ...base, thinking: { type: "enabled", budgetTokens: 32000 } } as AgentConfig
 }
+createOracleAgent.mode = MODE
 

src/agents/prometheus-prompt.ts

@@ -319,8 +319,8 @@ Or should I just note down this single fix?"
 
 **Research First:**
 \`\`\`typescript
-delegate_task(agent="explore", prompt="Find all usages of [target] using lsp_find_references pattern...", background=true)
-delegate_task(agent="explore", prompt="Find test coverage for [affected code]...", background=true)
+delegate_task(subagent_type="explore", prompt="Find all usages of [target] using lsp_find_references pattern...", run_in_background=true)
+delegate_task(subagent_type="explore", prompt="Find test coverage for [affected code]...", run_in_background=true)
 \`\`\`
 
 **Interview Focus:**
@@ -343,9 +343,9 @@ delegate_task(agent="explore", prompt="Find test coverage for [affected code]...
 **Pre-Interview Research (MANDATORY):**
 \`\`\`typescript
 // Launch BEFORE asking user questions
-delegate_task(agent="explore", prompt="Find similar implementations in codebase...", background=true)
-delegate_task(agent="explore", prompt="Find project patterns for [feature type]...", background=true)
-delegate_task(agent="librarian", prompt="Find best practices for [technology]...", background=true)
+delegate_task(subagent_type="explore", prompt="Find similar implementations in codebase...", run_in_background=true)
+delegate_task(subagent_type="explore", prompt="Find project patterns for [feature type]...", run_in_background=true)
+delegate_task(subagent_type="librarian", prompt="Find best practices for [technology]...", run_in_background=true)
 \`\`\`
 
 **Interview Focus** (AFTER research):
@@ -384,7 +384,7 @@ Based on your stack, I'd recommend NextAuth.js - it integrates well with Next.js
 
 Run this check:
 \`\`\`typescript
-delegate_task(agent="explore", prompt="Find test infrastructure: package.json test scripts, test config files (jest.config, vitest.config, pytest.ini, etc.), existing test files (*.test.*, *.spec.*, test_*). Report: 1) Does test infra exist? 2) What framework? 3) Example test file patterns.", background=true)
+delegate_task(subagent_type="explore", prompt="Find test infrastructure: package.json test scripts, test config files (jest.config, vitest.config, pytest.ini, etc.), existing test files (*.test.*, *.spec.*, test_*). Report: 1) Does test infra exist? 2) What framework? 3) Example test file patterns.", run_in_background=true)
 \`\`\`
 
 #### Step 2: Ask the Test Question (MANDATORY)
@@ -473,13 +473,13 @@ Add to draft immediately:
 
 **Research First:**
 \`\`\`typescript
-delegate_task(agent="explore", prompt="Find current system architecture and patterns...", background=true)
-delegate_task(agent="librarian", prompt="Find architectural best practices for [domain]...", background=true)
+delegate_task(subagent_type="explore", prompt="Find current system architecture and patterns...", run_in_background=true)
+delegate_task(subagent_type="librarian", prompt="Find architectural best practices for [domain]...", run_in_background=true)
 \`\`\`
 
 **Oracle Consultation** (recommend when stakes are high):
 \`\`\`typescript
-delegate_task(agent="oracle", prompt="Architecture consultation needed: [context]...", background=false)
+delegate_task(subagent_type="oracle", prompt="Architecture consultation needed: [context]...", run_in_background=false)
 \`\`\`
 
 **Interview Focus:**
@@ -496,9 +496,9 @@ delegate_task(agent="oracle", prompt="Architecture consultation needed: [context
 
 **Parallel Investigation:**
 \`\`\`typescript
-delegate_task(agent="explore", prompt="Find how X is currently handled...", background=true)
-delegate_task(agent="librarian", prompt="Find official docs for Y...", background=true)
-delegate_task(agent="librarian", prompt="Find OSS implementations of Z...", background=true)
+delegate_task(subagent_type="explore", prompt="Find how X is currently handled...", run_in_background=true)
+delegate_task(subagent_type="librarian", prompt="Find official docs for Y...", run_in_background=true)
+delegate_task(subagent_type="librarian", prompt="Find OSS implementations of Z...", run_in_background=true)
 \`\`\`
 
 **Interview Focus:**
@@ -524,17 +524,17 @@ delegate_task(agent="librarian", prompt="Find OSS implementations of Z...", back
 
 **For Understanding Codebase:**
 \`\`\`typescript
-delegate_task(agent="explore", prompt="Find all files related to [topic]. Show patterns, conventions, and structure.", background=true)
+delegate_task(subagent_type="explore", prompt="Find all files related to [topic]. Show patterns, conventions, and structure.", run_in_background=true)
 \`\`\`
 
 **For External Knowledge:**
 \`\`\`typescript
-delegate_task(agent="librarian", prompt="Find official documentation for [library]. Focus on [specific feature] and best practices.", background=true)
+delegate_task(subagent_type="librarian", prompt="Find official documentation for [library]. Focus on [specific feature] and best practices.", run_in_background=true)
 \`\`\`
 
 **For Implementation Examples:**
 \`\`\`typescript
-delegate_task(agent="librarian", prompt="Find open source implementations of [feature]. Look for production-quality examples.", background=true)
+delegate_task(subagent_type="librarian", prompt="Find open source implementations of [feature]. Look for production-quality examples.", run_in_background=true)
 \`\`\`
 
 ## Interview Mode Anti-Patterns
@@ -631,7 +631,7 @@ todoWrite([
 
 \`\`\`typescript
 delegate_task(
-  agent="Metis (Plan Consultant)",
+  subagent_type="metis",
   prompt=\`Review this planning session before I generate the work plan:
 
   **User's Goal**: {summarize what user wants}
@@ -652,7 +652,7 @@ delegate_task(
   4. Assumptions I'm making that need validation
   5. Missing acceptance criteria
   6. Edge cases not addressed\`,
-  background=false
+  run_in_background=false
 )
 \`\`\`
 
@@ -797,9 +797,9 @@ Question({
 // After generating initial plan
 while (true) {
   const result = delegate_task(
-    agent="Momus (Plan Reviewer)",
+    subagent_type="momus",
     prompt=".sisyphus/plans/{name}.md",
-    background=false
+    run_in_background=false
   )
 
   if (result.verdict === "OKAY") {
@@ -863,6 +863,20 @@ Generate plan to: \`.sisyphus/plans/{name}.md\`
 \`\`\`markdown
 # {Plan Title}
 
+## TL;DR
+
+> **Quick Summary**: [1-2 sentences capturing the core objective and approach]
+> 
+> **Deliverables**: [Bullet list of concrete outputs]
+> - [Output 1]
+> - [Output 2]
+> 
+> **Estimated Effort**: [Quick | Short | Medium | Large | XL]
+> **Parallel Execution**: [YES - N waves | NO - sequential]
+> **Critical Path**: [Task X → Task Y → Task Z]
+
+---
+
 ## Context
 
 ### Original Request
@@ -939,53 +953,89 @@ Each TODO follows RED-GREEN-REFACTOR:
   - Example: Create \`src/__tests__/example.test.ts\`
   - Verify: \`bun test\` → 1 test passes
 
-### If Manual QA Only
+### If Automated Verification Only (NO User Intervention)
 
-**CRITICAL**: Without automated tests, manual verification MUST be exhaustive.
+> **CRITICAL PRINCIPLE: ZERO USER INTERVENTION**
+>
+> **NEVER** create acceptance criteria that require:
+> - "User manually tests..." / "사용자가 직접 테스트..."
+> - "User visually confirms..." / "사용자가 눈으로 확인..."
+> - "User interacts with..." / "사용자가 직접 조작..."
+> - "Ask user to verify..." / "사용자에게 확인 요청..."
+> - ANY step that requires a human to perform an action
+>
+> **ALL verification MUST be automated and executable by the agent.**
+> If a verification cannot be automated, find an automated alternative or explicitly note it as a known limitation.
 
-Each TODO includes detailed verification procedures:
+Each TODO includes EXECUTABLE verification procedures that agents can run directly:
 
 **By Deliverable Type:**
 
-| Type | Verification Tool | Procedure |
-|------|------------------|-----------|
-| **Frontend/UI** | Playwright browser | Navigate, interact, screenshot |
-| **TUI/CLI** | interactive_bash (tmux) | Run command, verify output |
-| **API/Backend** | curl / httpie | Send request, verify response |
-| **Library/Module** | Node/Python REPL | Import, call, verify |
-| **Config/Infra** | Shell commands | Apply, verify state |
+| Type | Verification Tool | Automated Procedure |
+|------|------------------|---------------------|
+| **Frontend/UI** | Playwright browser via playwright skill | Agent navigates, clicks, screenshots, asserts DOM state |
+| **TUI/CLI** | interactive_bash (tmux) | Agent runs command, captures output, validates expected strings |
+| **API/Backend** | curl / httpie via Bash | Agent sends request, parses response, validates JSON fields |
+| **Library/Module** | Node/Python REPL via Bash | Agent imports, calls function, compares output |
+| **Config/Infra** | Shell commands via Bash | Agent applies config, runs state check, validates output |
 
-**Evidence Required:**
-- Commands run with actual output
-- Screenshots for visual changes
-- Response bodies for API changes
-- Terminal output for CLI changes
+**Evidence Requirements (Agent-Executable):**
+- Command output captured and compared against expected patterns
+- Screenshots saved to .sisyphus/evidence/ for visual verification
+- JSON response fields validated with specific assertions
+- Exit codes checked (0 = success)
 
 ---
 
-## Task Flow
+## Execution Strategy
+
+### Parallel Execution Waves
+
+> Maximize throughput by grouping independent tasks into parallel waves.
+> Each wave completes before the next begins.
 
 \`\`\`
-Task 1 → Task 2 → Task 3
-              ↘ Task 4 (parallel)
+Wave 1 (Start Immediately):
+├── Task 1: [no dependencies]
+└── Task 5: [no dependencies]
+
+Wave 2 (After Wave 1):
+├── Task 2: [depends: 1]
+├── Task 3: [depends: 1]
+└── Task 6: [depends: 5]
+
+Wave 3 (After Wave 2):
+└── Task 4: [depends: 2, 3]
+
+Critical Path: Task 1 → Task 2 → Task 4
+Parallel Speedup: ~40% faster than sequential
 \`\`\`
 
-## Parallelization
+### Dependency Matrix
 
-| Group | Tasks | Reason |
-|-------|-------|--------|
-| A | 2, 3 | Independent files |
+| Task | Depends On | Blocks | Can Parallelize With |
+|------|------------|--------|---------------------|
+| 1 | None | 2, 3 | 5 |
+| 2 | 1 | 4 | 3, 6 |
+| 3 | 1 | 4 | 2, 6 |
+| 4 | 2, 3 | None | None (final) |
+| 5 | None | 6 | 1 |
+| 6 | 5 | None | 2, 3 |
 
-| Task | Depends On | Reason |
-|------|------------|--------|
-| 4 | 1 | Requires output from 1 |
+### Agent Dispatch Summary
+
+| Wave | Tasks | Recommended Agents |
+|------|-------|-------------------|
+| 1 | 1, 5 | delegate_task(category="...", load_skills=[...], run_in_background=true) |
+| 2 | 2, 3, 6 | dispatch parallel after Wave 1 completes |
+| 3 | 4 | final integration task |
 
 ---
 
 ## TODOs
 
 > Implementation + Test = ONE Task. Never separate.
-> Specify parallelizability for EVERY task.
+> EVERY task MUST have: Recommended Agent Profile + Parallelization info.
 
 - [ ] 1. [Task Title]
 
@@ -996,7 +1046,21 @@ Task 1 → Task 2 → Task 3
   **Must NOT do**:
   - [Specific exclusions from guardrails]
 
-  **Parallelizable**: YES (with 3, 4) | NO (depends on 0)
+  **Recommended Agent Profile**:
+  > Select category + skills based on task domain. Justify each choice.
+  - **Category**: \`[visual-engineering | ultrabrain | artistry | quick | unspecified-low | unspecified-high | writing]\`
+    - Reason: [Why this category fits the task domain]
+  - **Skills**: [\`skill-1\`, \`skill-2\`]
+    - \`skill-1\`: [Why needed - domain overlap explanation]
+    - \`skill-2\`: [Why needed - domain overlap explanation]
+  - **Skills Evaluated but Omitted**:
+    - \`omitted-skill\`: [Why domain doesn't overlap]
+
+  **Parallelization**:
+  - **Can Run In Parallel**: YES | NO
+  - **Parallel Group**: Wave N (with Tasks X, Y) | Sequential
+  - **Blocks**: [Tasks that depend on this task completing]
+  - **Blocked By**: [Tasks this depends on] | None (can start immediately)
 
   **References** (CRITICAL - Be Exhaustive):
 
@@ -1029,53 +1093,76 @@ Task 1 → Task 2 → Task 3
 
   **Acceptance Criteria**:
 
-  > CRITICAL: Acceptance = EXECUTION, not just "it should work".
-  > The executor MUST run these commands and verify output.
+  > **CRITICAL: AGENT-EXECUTABLE VERIFICATION ONLY**
+  >
+  > - Acceptance = EXECUTION by the agent, not "user checks if it works"
+  > - Every criterion MUST be verifiable by running a command or using a tool
+  > - NO steps like "user opens browser", "user clicks", "user confirms"
+  > - If you write "[placeholder]" - REPLACE IT with actual values based on task context
 
   **If TDD (tests enabled):**
-  - [ ] Test file created: \`[path].test.ts\`
-  - [ ] Test covers: [specific scenario]
-  - [ ] \`bun test [file]\` → PASS (N tests, 0 failures)
+  - [ ] Test file created: src/auth/login.test.ts
+  - [ ] Test covers: successful login returns JWT token
+  - [ ] bun test src/auth/login.test.ts → PASS (3 tests, 0 failures)
 
-  **Manual Execution Verification (ALWAYS include, even with tests):**
+  **Automated Verification (ALWAYS include, choose by deliverable type):**
 
-  *Choose based on deliverable type:*
+  **For Frontend/UI changes** (using playwright skill):
+  \\\`\\\`\\\`
+  # Agent executes via playwright browser automation:
+  1. Navigate to: http://localhost:3000/login
+  2. Fill: input[name="email"] with "test@example.com"
+  3. Fill: input[name="password"] with "password123"
+  4. Click: button[type="submit"]
+  5. Wait for: selector ".dashboard-welcome" to be visible
+  6. Assert: text "Welcome back" appears on page
+  7. Screenshot: .sisyphus/evidence/task-1-login-success.png
+  \\\`\\\`\\\`
 
-  **For Frontend/UI changes:**
-  - [ ] Using playwright browser automation:
-    - Navigate to: \`http://localhost:[port]/[path]\`
-    - Action: [click X, fill Y, scroll to Z]
-    - Verify: [visual element appears, animation completes, state changes]
-    - Screenshot: Save evidence to \`.sisyphus/evidence/[task-id]-[step].png\`
+  **For TUI/CLI changes** (using interactive_bash):
+  \\\`\\\`\\\`
+  # Agent executes via tmux session:
+  1. Command: ./my-cli --config test.yaml
+  2. Wait for: "Configuration loaded" in output
+  3. Send keys: "q" to quit
+  4. Assert: Exit code 0
+  5. Assert: Output contains "Goodbye"
+  \\\`\\\`\\\`
 
-  **For TUI/CLI changes:**
-  - [ ] Using interactive_bash (tmux session):
-    - Command: \`[exact command to run]\`
-    - Input sequence: [if interactive, list inputs]
-    - Expected output contains: \`[expected string or pattern]\`
-    - Exit code: [0 for success, specific code if relevant]
+  **For API/Backend changes** (using Bash curl):
+  \\\`\\\`\\\`bash
+  # Agent runs:
+  curl -s -X POST http://localhost:8080/api/users \\
+    -H "Content-Type: application/json" \\
+    -d '{"email":"new@test.com","name":"Test User"}' \\
+    | jq '.id'
+  # Assert: Returns non-empty UUID
+  # Assert: HTTP status 201
+  \\\`\\\`\\\`
 
-  **For API/Backend changes:**
-  - [ ] Request: \`curl -X [METHOD] http://localhost:[port]/[endpoint] -H "Content-Type: application/json" -d '[body]'\`
-  - [ ] Response status: [200/201/etc]
-  - [ ] Response body contains: \`{"key": "expected_value"}\`
+  **For Library/Module changes** (using Bash node/bun):
+  \\\`\\\`\\\`bash
+  # Agent runs:
+  bun -e "import { validateEmail } from './src/utils/validate'; console.log(validateEmail('test@example.com'))"
+  # Assert: Output is "true"
+  
+  bun -e "import { validateEmail } from './src/utils/validate'; console.log(validateEmail('invalid'))"
+  # Assert: Output is "false"
+  \\\`\\\`\\\`
 
-  **For Library/Module changes:**
-  - [ ] REPL verification:
-    \`\`\`
-    > import { [function] } from '[module]'
-    > [function]([args])
-    Expected: [output]
-    \`\`\`
+  **For Config/Infra changes** (using Bash):
+  \\\`\\\`\\\`bash
+  # Agent runs:
+  docker compose up -d
+  # Wait 5s for containers
+  docker compose ps --format json | jq '.[].State'
+  # Assert: All states are "running"
+  \\\`\\\`\\\`
 
-  **For Config/Infra changes:**
-  - [ ] Apply: \`[command to apply config]\`
-  - [ ] Verify state: \`[command to check state]\` → \`[expected output]\`
-
-  **Evidence Required:**
-  - [ ] Command output captured (copy-paste actual terminal output)
-  - [ ] Screenshot saved (for visual changes)
-  - [ ] Response body logged (for API changes)
+  **Evidence to Capture:**
+  - [ ] Terminal output from verification commands (actual output, not expected)
+  - [ ] Screenshot files in .sisyphus/evidence/ for UI changes
+  - [ ] JSON response bodies for API changes
 
   **Commit**: YES | NO (groups with N)
   - Message: \`type(scope): desc\`

src/agents/sisyphus-junior.ts

@@ -1,4 +1,5 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
+import type { AgentMode } from "./types"
 import { isGptModel } from "./types"
 import type { AgentOverrideConfig } from "../config/schema"
 import {
@@ -6,6 +7,8 @@ import {
   type PermissionValue,
 } from "../shared/permission-compat"
 
+const MODE: AgentMode = "subagent"
+
 const SISYPHUS_JUNIOR_PROMPT = `<Role>
 Sisyphus-Junior - Focused executor from OhMyOpenCode.
 Execute tasks directly. NEVER delegate or spawn other agents.
@@ -20,32 +23,6 @@ ALLOWED: call_omo_agent - You CAN spawn explore/librarian agents for research.
 You work ALONE for implementation. No delegation of implementation tasks.
 </Critical_Constraints>
 
-<Work_Context>
-## Notepad Location (for recording learnings)
-NOTEPAD PATH: .sisyphus/notepads/{plan-name}/
-- learnings.md: Record patterns, conventions, successful approaches
-- issues.md: Record problems, blockers, gotchas encountered
-- decisions.md: Record architectural choices and rationales
-- problems.md: Record unresolved issues, technical debt
-
-You SHOULD append findings to notepad files after completing work.
-IMPORTANT: Always APPEND to notepad files - never overwrite or use Edit tool.
-
-## Plan Location (READ ONLY)
-PLAN PATH: .sisyphus/plans/{plan-name}.md
-
-CRITICAL RULE: NEVER MODIFY THE PLAN FILE
-
-The plan file (.sisyphus/plans/*.md) is SACRED and READ-ONLY.
-- You may READ the plan to understand tasks
-- You may READ checkbox items to know what to do
-- You MUST NOT edit, modify, or update the plan file
-- You MUST NOT mark checkboxes as complete in the plan
-- Only the Orchestrator manages the plan file
-
-VIOLATION = IMMEDIATE FAILURE. The Orchestrator tracks plan state.
-</Work_Context>
-
 <Todo_Discipline>
 TODO OBSESSION (NON-NEGOTIABLE):
 - 2+ steps → todowrite FIRST, atomic breakdown
@@ -110,8 +87,8 @@ export function createSisyphusJuniorAgentWithOverrides(
 
   const base: AgentConfig = {
     description: override?.description ??
-      "Sisyphus-Junior - Focused task executor. Same discipline, no delegation.",
-    mode: "subagent" as const,
+      "Focused task executor. Same discipline, no delegation. (Sisyphus-Junior - OhMyOpenCode)",
+    mode: MODE,
     model,
     temperature,
     maxTokens: 64000,
@@ -133,3 +110,5 @@ export function createSisyphusJuniorAgentWithOverrides(
     thinking: { type: "enabled", budgetTokens: 32000 },
   } as AgentConfig
 }
+
+createSisyphusJuniorAgentWithOverrides.mode = MODE

src/agents/sisyphus.ts

@@ -1,5 +1,14 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
+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,
@@ -144,11 +153,11 @@ ${librarianSection}
 \`\`\`typescript
 // CORRECT: Always background, always parallel
 // Contextual Grep (internal)
-delegate_task(subagent_type="explore", run_in_background=true, skills=[], prompt="Find auth implementations in our codebase...")
-delegate_task(subagent_type="explore", run_in_background=true, skills=[], prompt="Find error handling patterns here...")
+delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="Find auth implementations in our codebase...")
+delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="Find error handling patterns here...")
 // Reference Grep (external)
-delegate_task(subagent_type="librarian", run_in_background=true, skills=[], prompt="Find JWT best practices in official docs...")
-delegate_task(subagent_type="librarian", run_in_background=true, skills=[], prompt="Find how production apps handle auth in Express...")
+delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="Find JWT best practices in official docs...")
+delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="Find how production apps handle auth in Express...")
 // Continue working immediately. Collect with background_output when needed.
 
 // WRONG: Sequential or blocking
@@ -205,6 +214,34 @@ AFTER THE WORK YOU DELEGATED SEEMS DONE, ALWAYS VERIFY THE RESULTS AS FOLLOWING:
 
 **Vague prompts = rejected. Be exhaustive.**
 
+### Session Continuity (MANDATORY)
+
+Every \`delegate_task()\` output includes a session_id. **USE IT.**
+
+**ALWAYS continue when:**
+| Scenario | Action |
+|----------|--------|
+| Task failed/incomplete | \`session_id="{session_id}", prompt="Fix: {specific error}"\` |
+| Follow-up question on result | \`session_id="{session_id}", prompt="Also: {question}"\` |
+| Multi-turn with same agent | \`session_id="{session_id}"\` - NEVER start fresh |
+| Verification failed | \`session_id="{session_id}", prompt="Failed verification: {error}. Fix."\` |
+
+**Why session_id is CRITICAL:**
+- Subagent has FULL conversation context preserved
+- No repeated file reads, exploration, or setup
+- Saves 70%+ tokens on follow-ups
+- Subagent knows what it already tried/learned
+
+\`\`\`typescript
+// WRONG: Starting fresh loses all context
+delegate_task(category="quick", prompt="Fix the type error in auth.ts...")
+
+// CORRECT: Resume preserves everything
+delegate_task(session_id="ses_abc123", prompt="Fix: Type error on line 42")
+\`\`\`
+
+**After EVERY delegation, STORE the session_id for potential continuation.**
+
 ### Code Changes:
 - Match existing patterns (if codebase is disciplined)
 - Propose approach first (if codebase is chaotic)
@@ -405,8 +442,8 @@ export function createSisyphusAgent(
   const permission = { question: "allow", call_omo_agent: "deny" } as AgentConfig["permission"]
   const base = {
     description:
-      "Sisyphus - Powerful AI orchestrator from OhMyOpenCode. Plans obsessively with todos, assesses search complexity before exploration, delegates strategically via category+skills combinations. Uses explore for internal code (parallel-friendly), librarian for external docs.",
-    mode: "primary" as const,
+      "Powerful AI orchestrator. Plans obsessively with todos, assesses search complexity before exploration, delegates strategically via category+skills combinations. Uses explore for internal code (parallel-friendly), librarian for external docs. (Sisyphus - OhMyOpenCode)",
+    mode: MODE,
     model,
     maxTokens: 64000,
     prompt,
@@ -420,3 +457,4 @@ export function createSisyphusAgent(
 
   return { ...base, thinking: { type: "enabled", budgetTokens: 32000 } }
 }
+createSisyphusAgent.mode = MODE

src/agents/types.ts

@@ -1,6 +1,20 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
 
-export type AgentFactory = (model: string) => AgentConfig
+/**
+ * Agent mode determines UI model selection behavior:
+ * - "primary": Respects user's UI-selected model (sisyphus, atlas)
+ * - "subagent": Uses own fallback chain, ignores UI selection (oracle, explore, etc.)
+ * - "all": Available in both contexts (OpenCode compatibility)
+ */
+export type AgentMode = "primary" | "subagent" | "all"
+
+/**
+ * Agent factory function with static mode property.
+ * Mode is exposed as static property for pre-instantiation access.
+ */
+export type AgentFactory = ((model: string) => AgentConfig) & {
+  mode: AgentMode
+}
 
 /**
  * Agent category for grouping in Sisyphus prompt sections
@@ -57,14 +71,14 @@ export function isGptModel(model: string): boolean {
 }
 
 export type BuiltinAgentName =
-  | "Sisyphus"
+  | "sisyphus"
   | "oracle"
   | "librarian"
   | "explore"
   | "multimodal-looker"
-  | "Metis (Plan Consultant)"
-  | "Momus (Plan Reviewer)"
-  | "Atlas"
+  | "metis"
+  | "momus"
+  | "atlas"
 
 export type OverridableAgentName =
   | "build"

src/agents/utils.test.ts

@@ -1,6 +1,9 @@
-import { describe, test, expect } from "bun:test"
+import { describe, test, expect, beforeEach, spyOn, afterEach } from "bun:test"
 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"
 
@@ -12,51 +15,65 @@ describe("createBuiltinAgents with model overrides", () => {
     const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
 
     // #then
-    expect(agents.Sisyphus.model).toBe("anthropic/claude-opus-4-5")
-    expect(agents.Sisyphus.thinking).toEqual({ type: "enabled", budgetTokens: 32000 })
-    expect(agents.Sisyphus.reasoningEffort).toBeUndefined()
+    expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
+    expect(agents.sisyphus.thinking).toEqual({ type: "enabled", budgetTokens: 32000 })
+    expect(agents.sisyphus.reasoningEffort).toBeUndefined()
   })
 
   test("Sisyphus with GPT model override has reasoningEffort, no thinking", async () => {
     // #given
     const overrides = {
-      Sisyphus: { model: "github-copilot/gpt-5.2" },
+      sisyphus: { model: "github-copilot/gpt-5.2" },
     }
 
     // #when
     const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
 
     // #then
-    expect(agents.Sisyphus.model).toBe("github-copilot/gpt-5.2")
-    expect(agents.Sisyphus.reasoningEffort).toBe("medium")
-    expect(agents.Sisyphus.thinking).toBeUndefined()
+    expect(agents.sisyphus.model).toBe("github-copilot/gpt-5.2")
+    expect(agents.sisyphus.reasoningEffort).toBe("medium")
+    expect(agents.sisyphus.thinking).toBeUndefined()
   })
 
-  test("Sisyphus uses first fallbackChain entry when no availableModels provided", async () => {
+  test("Sisyphus uses system default when no availableModels provided", async () => {
     // #given
-    const systemDefaultModel = "openai/gpt-5.2"
+    const systemDefaultModel = "anthropic/claude-opus-4-5"
 
     // #when
     const agents = await createBuiltinAgents([], {}, undefined, systemDefaultModel)
 
-    // #then - Sisyphus first fallbackChain entry is anthropic/claude-opus-4-5
-    expect(agents.Sisyphus.model).toBe("anthropic/claude-opus-4-5")
-    expect(agents.Sisyphus.thinking).toEqual({ type: "enabled", budgetTokens: 32000 })
-    expect(agents.Sisyphus.reasoningEffort).toBeUndefined()
+    // #then - falls back to system default when no availability match
+    expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
+    expect(agents.sisyphus.thinking).toEqual({ type: "enabled", budgetTokens: 32000 })
+    expect(agents.sisyphus.reasoningEffort).toBeUndefined()
   })
 
-  test("Oracle uses first fallbackChain entry when no availableModels provided", async () => {
-    // #given - Oracle's first fallbackChain entry is openai/gpt-5.2
+   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 first fallbackChain entry is openai/gpt-5.2
-    expect(agents.oracle.model).toBe("openai/gpt-5.2")
-    expect(agents.oracle.reasoningEffort).toBe("medium")
-    expect(agents.oracle.textVerbosity).toBe("high")
-    expect(agents.oracle.thinking).toBeUndefined()
-  })
+     // #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)
+
+     // #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?.()
+   })
 
   test("Oracle with GPT model override has reasoningEffort, no thinking", async () => {
     // #given
@@ -90,25 +107,69 @@ describe("createBuiltinAgents with model overrides", () => {
     expect(agents.oracle.textVerbosity).toBeUndefined()
   })
 
-  test("non-model overrides are still applied after factory rebuild", async () => {
-    // #given
-    const overrides = {
-      Sisyphus: { model: "github-copilot/gpt-5.2", temperature: 0.5 },
-    }
+   test("non-model overrides are still applied after factory rebuild", async () => {
+     // #given
+     const overrides = {
+       sisyphus: { model: "github-copilot/gpt-5.2", temperature: 0.5 },
+     }
 
-    // #when
-    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+     // #when
+     const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
 
-    // #then
-    expect(agents.Sisyphus.model).toBe("github-copilot/gpt-5.2")
-    expect(agents.Sisyphus.temperature).toBe(0.5)
-  })
+     // #then
+     expect(agents.sisyphus.model).toBe("github-copilot/gpt-5.2")
+     expect(agents.sisyphus.temperature).toBe(0.5)
+   })
+})
+
+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"])
+
+     // #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?.()
+   })
+
+   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)
+
+     // #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"])
+
+     // #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?.()
+   })
 })
 
 describe("buildAgent with category and skills", () => {
   const { buildAgent } = require("./utils")
   const TEST_MODEL = "anthropic/claude-opus-4-5"
 
+  beforeEach(() => {
+    clearSkillCache()
+  })
+
   test("agent with category inherits category settings", () => {
     // #given - agent factory that sets category but no model
     const source = {
@@ -123,7 +184,7 @@ describe("buildAgent with category and skills", () => {
     const agent = buildAgent(source["test-agent"], TEST_MODEL)
 
     // #then - category's built-in model is applied
-    expect(agent.model).toBe("google/gemini-3-pro-preview")
+    expect(agent.model).toBe("google/gemini-3-pro")
   })
 
   test("agent with category and existing model keeps existing model", () => {
@@ -308,4 +369,196 @@ describe("buildAgent with category and skills", () => {
     // #then
     expect(agent.prompt).toBe("Base prompt")
   })
+
+  test("agent with agent-browser skill resolves when browserProvider is set", () => {
+    // #given
+    const source = {
+      "test-agent": () =>
+        ({
+          description: "Test agent",
+          skills: ["agent-browser"],
+          prompt: "Base prompt",
+        }) as AgentConfig,
+    }
+
+    // #when - browserProvider is "agent-browser"
+    const agent = buildAgent(source["test-agent"], TEST_MODEL, undefined, undefined, "agent-browser")
+
+    // #then - agent-browser skill content should be in prompt
+    expect(agent.prompt).toContain("agent-browser")
+    expect(agent.prompt).toContain("Base prompt")
+  })
+
+  test("agent with agent-browser skill NOT resolved when browserProvider not set", () => {
+    // #given
+    const source = {
+      "test-agent": () =>
+        ({
+          description: "Test agent",
+          skills: ["agent-browser"],
+          prompt: "Base prompt",
+        }) as AgentConfig,
+    }
+
+    // #when - no browserProvider (defaults to playwright)
+    const agent = buildAgent(source["test-agent"], TEST_MODEL)
+
+    // #then - agent-browser skill not found, only base prompt remains
+    expect(agent.prompt).toBe("Base prompt")
+    expect(agent.prompt).not.toContain("agent-browser open")
+  })
+})
+
+describe("override.category expansion in createBuiltinAgents", () => {
+  test("standard agent override with category expands category properties", async () => {
+    // #given
+    const overrides = {
+      oracle: { category: "ultrabrain" } as any,
+    }
+
+    // #when
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+
+    // #then - ultrabrain category: model=openai/gpt-5.2-codex, variant=xhigh
+    expect(agents.oracle).toBeDefined()
+    expect(agents.oracle.model).toBe("openai/gpt-5.2-codex")
+    expect(agents.oracle.variant).toBe("xhigh")
+  })
+
+  test("standard agent override with category AND direct variant - direct wins", async () => {
+    // #given - ultrabrain has variant=xhigh, but direct override says "max"
+    const overrides = {
+      oracle: { category: "ultrabrain", variant: "max" } as any,
+    }
+
+    // #when
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+
+    // #then - direct variant overrides category variant
+    expect(agents.oracle).toBeDefined()
+    expect(agents.oracle.variant).toBe("max")
+  })
+
+  test("standard agent override with category AND direct reasoningEffort - direct wins", async () => {
+    // #given - custom category has reasoningEffort=xhigh, direct override says "low"
+    const categories = {
+      "test-cat": {
+        model: "openai/gpt-5.2",
+        reasoningEffort: "xhigh" as const,
+      },
+    }
+    const overrides = {
+      oracle: { category: "test-cat", reasoningEffort: "low" } as any,
+    }
+
+    // #when
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, categories)
+
+    // #then - direct reasoningEffort wins over category
+    expect(agents.oracle).toBeDefined()
+    expect(agents.oracle.reasoningEffort).toBe("low")
+  })
+
+  test("standard agent override with category applies reasoningEffort from category when no direct override", async () => {
+    // #given - custom category has reasoningEffort, no direct reasoningEffort in override
+    const categories = {
+      "reasoning-cat": {
+        model: "openai/gpt-5.2",
+        reasoningEffort: "high" as const,
+      },
+    }
+    const overrides = {
+      oracle: { category: "reasoning-cat" } as any,
+    }
+
+    // #when
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, categories)
+
+    // #then - category reasoningEffort is applied
+    expect(agents.oracle).toBeDefined()
+    expect(agents.oracle.reasoningEffort).toBe("high")
+  })
+
+  test("sisyphus override with category expands category properties", async () => {
+    // #given
+    const overrides = {
+      sisyphus: { category: "ultrabrain" } as any,
+    }
+
+    // #when
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+
+    // #then - ultrabrain category: model=openai/gpt-5.2-codex, variant=xhigh
+    expect(agents.sisyphus).toBeDefined()
+    expect(agents.sisyphus.model).toBe("openai/gpt-5.2-codex")
+    expect(agents.sisyphus.variant).toBe("xhigh")
+  })
+
+  test("atlas override with category expands category properties", async () => {
+    // #given
+    const overrides = {
+      atlas: { category: "ultrabrain" } as any,
+    }
+
+    // #when
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+
+    // #then - ultrabrain category: model=openai/gpt-5.2-codex, variant=xhigh
+    expect(agents.atlas).toBeDefined()
+    expect(agents.atlas.model).toBe("openai/gpt-5.2-codex")
+    expect(agents.atlas.variant).toBe("xhigh")
+  })
+
+  test("override with non-existent category has no effect on config", async () => {
+    // #given
+    const overrides = {
+      oracle: { category: "non-existent-category" } as any,
+    }
+
+    // #when
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+
+    // #then - no category-specific variant/reasoningEffort applied from non-existent category
+    expect(agents.oracle).toBeDefined()
+    const agentsWithoutOverride = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
+    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

@@ -6,29 +6,30 @@ 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 } 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"
 import type { LoadedSkill, SkillScope } from "../features/opencode-skill-loader/types"
+import type { BrowserAutomationProvider } from "../config/schema"
 
 type AgentSource = AgentFactory | AgentConfig
 
 const agentSources: Record<BuiltinAgentName, AgentSource> = {
-  Sisyphus: createSisyphusAgent,
+  sisyphus: createSisyphusAgent,
   oracle: createOracleAgent,
   librarian: createLibrarianAgent,
   explore: createExploreAgent,
   "multimodal-looker": createMultimodalLookerAgent,
-  "Metis (Plan Consultant)": createMetisAgent,
-  "Momus (Plan Reviewer)": createMomusAgent,
+  metis: createMetisAgent,
+  momus: createMomusAgent,
   // Note: Atlas is handled specially in createBuiltinAgents()
   // because it needs OrchestratorContext, not just a model string
-  Atlas: createAtlasAgent as unknown as AgentFactory,
+  atlas: createAtlasAgent as unknown as AgentFactory,
 }
 
 /**
@@ -40,6 +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 {
@@ -50,7 +54,8 @@ export function buildAgent(
   source: AgentSource,
   model: string,
   categories?: CategoriesConfig,
-  gitMasterConfig?: GitMasterConfig
+  gitMasterConfig?: GitMasterConfig,
+  browserProvider?: BrowserAutomationProvider
 ): AgentConfig {
   const base = isFactory(source) ? source(model) : source
   const categoryConfigs: Record<string, CategoryConfig> = categories
@@ -74,7 +79,7 @@ export function buildAgent(
   }
 
   if (agentWithCategory.skills?.length) {
-    const { resolved } = resolveMultipleSkills(agentWithCategory.skills, { gitMasterConfig })
+    const { resolved } = resolveMultipleSkills(agentWithCategory.skills, { gitMasterConfig, browserProvider })
     if (resolved.size > 0) {
       const skillContent = Array.from(resolved.values()).join("\n\n")
       base.prompt = skillContent + (base.prompt ? "\n\n" + base.prompt : "")
@@ -118,6 +123,72 @@ export function createEnvContext(): string {
 </omo-env>`
 }
 
+/**
+ * Expands a category reference from an agent override into concrete config properties.
+ * Category properties are applied unconditionally (overwriting factory defaults),
+ * because the user's chosen category should take priority over factory base values.
+ * Direct override properties applied later via mergeAgentConfig() will supersede these.
+ */
+function applyCategoryOverride(
+  config: AgentConfig,
+  categoryName: string,
+  mergedCategories: Record<string, CategoryConfig>
+): AgentConfig {
+  const categoryConfig = mergedCategories[categoryName]
+  if (!categoryConfig) return config
+
+  const result = { ...config } as AgentConfig & Record<string, unknown>
+  if (categoryConfig.model) result.model = categoryConfig.model
+  if (categoryConfig.variant !== undefined) result.variant = categoryConfig.variant
+  if (categoryConfig.temperature !== undefined) result.temperature = categoryConfig.temperature
+  if (categoryConfig.reasoningEffort !== undefined) result.reasoningEffort = categoryConfig.reasoningEffort
+  if (categoryConfig.textVerbosity !== undefined) result.textVerbosity = categoryConfig.textVerbosity
+  if (categoryConfig.thinking !== undefined) result.thinking = categoryConfig.thinking
+  if (categoryConfig.top_p !== undefined) result.top_p = categoryConfig.top_p
+  if (categoryConfig.maxTokens !== undefined) result.maxTokens = categoryConfig.maxTokens
+
+  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
@@ -139,21 +210,24 @@ function mapScopeToLocation(scope: SkillScope): AvailableSkill["location"] {
 }
 
 export async function createBuiltinAgents(
-  disabledAgents: BuiltinAgentName[] = [],
+  disabledAgents: string[] = [],
   agentOverrides: AgentOverrides = {},
   directory?: string,
   systemDefaultModel?: string,
   categories?: CategoriesConfig,
   gitMasterConfig?: GitMasterConfig,
   discoveredSkills: LoadedSkill[] = [],
-  client?: any
+  client?: any,
+  browserProvider?: BrowserAutomationProvider,
+  uiSelectedModel?: string
 ): Promise<Record<string, AgentConfig>> {
-  if (!systemDefaultModel) {
-    throw new Error("createBuiltinAgents requires systemDefaultModel")
-  }
-
-  // Fetch available models at plugin init
-  const availableModels = client ? await fetchAvailableModels(client) : new Set<string>()
+  const connectedProviders = readConnectedProvidersCache()
+  // 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[] = []
@@ -167,7 +241,7 @@ export async function createBuiltinAgents(
     description: categories?.[name]?.description ?? CATEGORY_DESCRIPTIONS[name] ?? "General tasks",
   }))
 
-  const builtinSkills = createBuiltinSkills()
+  const builtinSkills = createBuiltinSkills({ browserProvider })
   const builtinSkillNames = new Set(builtinSkills.map(s => s.name))
 
   const builtinAvailable: AvailableSkill[] = builtinSkills.map((skill) => ({
@@ -186,42 +260,55 @@ export async function createBuiltinAgents(
 
   const availableSkills: AvailableSkill[] = [...builtinAvailable, ...discoveredAvailable]
 
-  for (const [name, source] of Object.entries(agentSources)) {
-    const agentName = name as BuiltinAgentName
+   for (const [name, source] of Object.entries(agentSources)) {
+     const agentName = name as BuiltinAgentName
 
-    if (agentName === "Sisyphus") continue
-    if (agentName === "Atlas") continue
-    if (includesCaseInsensitive(disabledAgents, agentName)) continue
+     if (agentName === "sisyphus") continue
+     if (agentName === "atlas") continue
+     if (disabledAgents.some((name) => name.toLowerCase() === agentName.toLowerCase())) continue
 
-    const override = findCaseInsensitive(agentOverrides, agentName)
-    const requirement = AGENT_MODEL_REQUIREMENTS[agentName]
-    
-    // Use resolver to determine model
-    const { model } = resolveModelWithFallback({
+     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
+     if (requirement?.requiresModel && availableModels) {
+       if (!isModelAvailable(requirement.requiresModel, availableModels)) {
+         continue
+       }
+     }
+     
+     const isPrimaryAgent = isFactory(source) && source.mode === "primary"
+     
+    const resolution = applyModelResolution({
+      uiSelectedModel: isPrimaryAgent ? uiSelectedModel : undefined,
       userModel: override?.model,
-      fallbackChain: requirement?.fallbackChain,
+      requirement,
       availableModels,
       systemDefaultModel,
     })
+    if (!resolution) continue
+    const { model, variant: resolvedVariant } = resolution
 
-    let config = buildAgent(source, model, mergedCategories, gitMasterConfig)
+    let config = buildAgent(source, model, mergedCategories, gitMasterConfig, browserProvider)
     
-    // Apply variant from override or requirement
-    if (override?.variant) {
-      config = { ...config, variant: override.variant }
-    } else if (requirement?.variant) {
-      config = { ...config, variant: requirement.variant }
+    // Apply resolved variant from model fallback chain
+    if (resolvedVariant) {
+      config = { ...config, variant: resolvedVariant }
     }
 
-    if (agentName === "librarian" && directory && config.prompt) {
-      const envContext = createEnvContext()
-      config = { ...config, prompt: config.prompt + envContext }
+    // Expand override.category into concrete properties (higher priority than factory/resolved)
+    const overrideCategory = (override as Record<string, unknown> | undefined)?.category as string | undefined
+    if (overrideCategory) {
+      config = applyCategoryOverride(config, overrideCategory, mergedCategories)
     }
 
-    if (override) {
-      config = mergeAgentConfig(config, override)
+    if (agentName === "librarian") {
+      config = applyEnvironmentContext(config, directory)
     }
 
+    config = applyOverrides(config, override, mergedCategories)
+
     result[name] = config
 
     const metadata = agentMetadata[agentName]
@@ -234,77 +321,71 @@ export async function createBuiltinAgents(
     }
   }
 
-  if (!disabledAgents.includes("Sisyphus")) {
-    const sisyphusOverride = agentOverrides["Sisyphus"]
-    const sisyphusRequirement = AGENT_MODEL_REQUIREMENTS["Sisyphus"]
+   if (!disabledAgents.includes("sisyphus")) {
+     const sisyphusOverride = agentOverrides["sisyphus"]
+     const sisyphusRequirement = AGENT_MODEL_REQUIREMENTS["sisyphus"]
     
-    // Use resolver to determine model
-    const { model: sisyphusModel } = resolveModelWithFallback({
+    const sisyphusResolution = applyModelResolution({
+      uiSelectedModel,
       userModel: sisyphusOverride?.model,
-      fallbackChain: sisyphusRequirement?.fallbackChain,
+      requirement: sisyphusRequirement,
       availableModels,
       systemDefaultModel,
     })
 
-    let sisyphusConfig = createSisyphusAgent(
-      sisyphusModel,
-      availableAgents,
-      undefined,
-      availableSkills,
-      availableCategories
-    )
+    if (sisyphusResolution) {
+      const { model: sisyphusModel, variant: sisyphusResolvedVariant } = sisyphusResolution
+
+      let sisyphusConfig = createSisyphusAgent(
+        sisyphusModel,
+        availableAgents,
+        undefined,
+        availableSkills,
+        availableCategories
+      )
+      
+      if (sisyphusResolvedVariant) {
+        sisyphusConfig = { ...sisyphusConfig, variant: sisyphusResolvedVariant }
+      }
+
+      sisyphusConfig = applyOverrides(sisyphusConfig, sisyphusOverride, mergedCategories)
+      sisyphusConfig = applyEnvironmentContext(sisyphusConfig, directory)
+
+      result["sisyphus"] = sisyphusConfig
+    }
+   }
+
+   if (!disabledAgents.includes("atlas")) {
+     const orchestratorOverride = agentOverrides["atlas"]
+     const atlasRequirement = AGENT_MODEL_REQUIREMENTS["atlas"]
     
-    // Apply variant from override or requirement
-    if (sisyphusOverride?.variant) {
-      sisyphusConfig = { ...sisyphusConfig, variant: sisyphusOverride.variant }
-    } else if (sisyphusRequirement?.variant) {
-      sisyphusConfig = { ...sisyphusConfig, variant: sisyphusRequirement.variant }
-    }
-
-    if (directory && sisyphusConfig.prompt) {
-      const envContext = createEnvContext()
-      sisyphusConfig = { ...sisyphusConfig, prompt: sisyphusConfig.prompt + envContext }
-    }
-
-    if (sisyphusOverride) {
-      sisyphusConfig = mergeAgentConfig(sisyphusConfig, sisyphusOverride)
-    }
-
-    result["Sisyphus"] = sisyphusConfig
-  }
-
-  if (!disabledAgents.includes("Atlas")) {
-    const orchestratorOverride = agentOverrides["Atlas"]
-    const atlasRequirement = AGENT_MODEL_REQUIREMENTS["Atlas"]
-    
-    // Use resolver to determine model
-    const { model: atlasModel } = 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,
     })
     
-    let orchestratorConfig = createAtlasAgent({
-      model: atlasModel,
-      availableAgents,
-      availableSkills,
-      userCategories: categories,
-    })
-    
-    // Apply variant from override or requirement
-    if (orchestratorOverride?.variant) {
-      orchestratorConfig = { ...orchestratorConfig, variant: orchestratorOverride.variant }
-    } else if (atlasRequirement?.variant) {
-      orchestratorConfig = { ...orchestratorConfig, variant: atlasRequirement.variant }
+    if (atlasResolution) {
+      const { model: atlasModel, variant: atlasResolvedVariant } = atlasResolution
+
+      let orchestratorConfig = createAtlasAgent({
+        model: atlasModel,
+        availableAgents,
+        availableSkills,
+        userCategories: categories,
+      })
+      
+      if (atlasResolvedVariant) {
+        orchestratorConfig = { ...orchestratorConfig, variant: atlasResolvedVariant }
+      }
+
+      orchestratorConfig = applyOverrides(orchestratorConfig, orchestratorOverride, mergedCategories)
+
+      result["atlas"] = orchestratorConfig
     }
+   }
 
-    if (orchestratorOverride) {
-      orchestratorConfig = mergeAgentConfig(orchestratorConfig, orchestratorOverride)
-    }
-
-    result["Atlas"] = orchestratorConfig
-  }
-
-  return result
-}
+   return result
+ }

src/cli/AGENTS.md

@@ -8,16 +8,17 @@ CLI entry: `bunx oh-my-opencode`. Interactive installer, doctor diagnostics. Com
 
 ```
 cli/
-├── index.ts              # Commander.js entry
+├── index.ts              # Commander.js entry (4 commands)
 ├── install.ts            # Interactive TUI (520 lines)
-├── config-manager.ts     # JSONC parsing (641 lines)
+├── config-manager.ts     # JSONC parsing (664 lines)
 ├── types.ts              # InstallArgs, InstallConfig
+├── model-fallback.ts     # Model fallback configuration
 ├── doctor/
 │   ├── index.ts          # Doctor entry
 │   ├── runner.ts         # Check orchestration
 │   ├── formatter.ts      # Colored output
 │   ├── constants.ts      # Check IDs, symbols
-│   ├── types.ts          # CheckResult, CheckDefinition
+│   ├── types.ts          # CheckResult, CheckDefinition (114 lines)
 │   └── checks/           # 14 checks, 21 files
 │       ├── version.ts    # OpenCode + plugin version
 │       ├── config.ts     # JSONC validity, Zod
@@ -25,6 +26,7 @@ cli/
 │       ├── dependencies.ts # AST-Grep, Comment Checker
 │       ├── lsp.ts        # LSP connectivity
 │       ├── mcp.ts        # MCP validation
+│       ├── model-resolution.ts # Model resolution check
 │       └── gh.ts         # GitHub CLI
 ├── run/
 │   └── index.ts          # Session launcher
@@ -36,36 +38,37 @@ cli/
 
 | Command | Purpose |
 |---------|---------|
-| `install` | Interactive setup |
-| `doctor` | 14 health checks |
-| `run` | Launch session |
-| `get-local-version` | Version check |
+| `install` | Interactive setup with provider selection |
+| `doctor` | 14 health checks for diagnostics |
+| `run` | Launch session with todo enforcement |
+| `get-local-version` | Version detection and update check |
 
-## DOCTOR CATEGORIES
+## DOCTOR CATEGORIES (14 Checks)
 
 | Category | Checks |
 |----------|--------|
 | installation | opencode, plugin |
-| configuration | config validity, Zod |
+| configuration | config validity, Zod, model-resolution |
 | authentication | anthropic, openai, google |
-| dependencies | ast-grep, comment-checker |
+| dependencies | ast-grep, comment-checker, gh-cli |
 | tools | LSP, MCP |
 | updates | version comparison |
 
 ## HOW TO ADD CHECK
 
 1. Create `src/cli/doctor/checks/my-check.ts`
-2. Export from `checks/index.ts`
-3. Add to `getAllCheckDefinitions()`
+2. Export `getXXXCheckDefinition()` factory returning `CheckDefinition`
+3. Add to `getAllCheckDefinitions()` in `checks/index.ts`
 
 ## TUI FRAMEWORK
 
-- **@clack/prompts**: `select()`, `spinner()`, `intro()`
-- **picocolors**: Terminal colors
-- **Symbols**: ✓ (pass), ✗ (fail), ⚠ (warn)
+- **@clack/prompts**: `select()`, `spinner()`, `intro()`, `outro()`
+- **picocolors**: Terminal colors for status and headers
+- **Symbols**: ✓ (pass), ✗ (fail), ⚠ (warn), ℹ (info)
 
 ## ANTI-PATTERNS
 
-- **Blocking in non-TTY**: Check `process.stdout.isTTY`
-- **Direct JSON.parse**: Use `parseJsonc()`
-- **Silent failures**: Return warn/fail in doctor
+- **Blocking in non-TTY**: Always check `process.stdout.isTTY`
+- **Direct JSON.parse**: Use `parseJsonc()` from shared utils
+- **Silent failures**: Return `warn` or `fail` in doctor instead of throwing
+- **Hardcoded paths**: Use `getOpenCodeConfigPaths()` from `config-manager.ts`

src/cli/config-manager.test.ts

@@ -170,7 +170,7 @@ describe("fetchNpmDistTags", () => {
 })
 
 describe("config-manager ANTIGRAVITY_PROVIDER_CONFIG", () => {
-  test("Gemini models include full spec (limit + modalities)", () => {
+  test("all models include full spec (limit + modalities + Antigravity label)", () => {
     const google = (ANTIGRAVITY_PROVIDER_CONFIG as any).google
     expect(google).toBeTruthy()
 
@@ -178,9 +178,11 @@ describe("config-manager ANTIGRAVITY_PROVIDER_CONFIG", () => {
     expect(models).toBeTruthy()
 
     const required = [
-      "antigravity-gemini-3-pro-high",
-      "antigravity-gemini-3-pro-low",
+      "antigravity-gemini-3-pro",
       "antigravity-gemini-3-flash",
+      "antigravity-claude-sonnet-4-5",
+      "antigravity-claude-sonnet-4-5-thinking",
+      "antigravity-claude-opus-4-5-thinking",
     ]
 
     for (const key of required) {
@@ -198,6 +200,43 @@ describe("config-manager ANTIGRAVITY_PROVIDER_CONFIG", () => {
       expect(Array.isArray(model.modalities.output)).toBe(true)
     }
   })
+
+  test("Gemini models have variant definitions", () => {
+    // #given the antigravity provider config
+    const models = (ANTIGRAVITY_PROVIDER_CONFIG as any).google.models as Record<string, any>
+
+    // #when checking Gemini Pro variants
+    const pro = models["antigravity-gemini-3-pro"]
+    // #then should have low and high variants
+    expect(pro.variants).toBeTruthy()
+    expect(pro.variants.low).toBeTruthy()
+    expect(pro.variants.high).toBeTruthy()
+
+    // #when checking Gemini Flash variants
+    const flash = models["antigravity-gemini-3-flash"]
+    // #then should have minimal, low, medium, high variants
+    expect(flash.variants).toBeTruthy()
+    expect(flash.variants.minimal).toBeTruthy()
+    expect(flash.variants.low).toBeTruthy()
+    expect(flash.variants.medium).toBeTruthy()
+    expect(flash.variants.high).toBeTruthy()
+  })
+
+  test("Claude thinking models have variant definitions", () => {
+    // #given the antigravity provider config
+    const models = (ANTIGRAVITY_PROVIDER_CONFIG as any).google.models as Record<string, any>
+
+    // #when checking Claude thinking variants
+    const sonnetThinking = models["antigravity-claude-sonnet-4-5-thinking"]
+    const opusThinking = models["antigravity-claude-opus-4-5-thinking"]
+
+    // #then both should have low and max variants
+    for (const model of [sonnetThinking, opusThinking]) {
+      expect(model.variants).toBeTruthy()
+      expect(model.variants.low).toBeTruthy()
+      expect(model.variants.max).toBeTruthy()
+    }
+  })
 })
 
 describe("generateOmoConfig - model fallback system", () => {
@@ -211,6 +250,7 @@ describe("generateOmoConfig - model fallback system", () => {
       hasCopilot: false,
       hasOpencodeZen: false,
       hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
     }
 
     // #when generating config
@@ -219,7 +259,7 @@ describe("generateOmoConfig - model fallback system", () => {
     // #then should use native anthropic sonnet (cost-efficient for standard plan)
     expect(result.$schema).toBe("https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json")
     expect(result.agents).toBeDefined()
-    expect((result.agents as Record<string, { model: string }>).Sisyphus.model).toBe("anthropic/claude-sonnet-4-5")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-sonnet-4-5")
   })
 
   test("generates native opus models when Claude max20 subscription", () => {
@@ -232,13 +272,14 @@ describe("generateOmoConfig - model fallback system", () => {
       hasCopilot: false,
       hasOpencodeZen: false,
       hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
     }
 
     // #when generating config
     const result = generateOmoConfig(config)
 
     // #then should use native anthropic opus (max power for max20 plan)
-    expect((result.agents as Record<string, { model: string }>).Sisyphus.model).toBe("anthropic/claude-opus-4-5")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-5")
   })
 
   test("uses github-copilot sonnet fallback when only copilot available", () => {
@@ -251,13 +292,14 @@ describe("generateOmoConfig - model fallback system", () => {
       hasCopilot: true,
       hasOpencodeZen: false,
       hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
     }
 
     // #when generating config
     const result = generateOmoConfig(config)
 
     // #then should use github-copilot sonnet models (copilot fallback)
-    expect((result.agents as Record<string, { model: string }>).Sisyphus.model).toBe("github-copilot/claude-sonnet-4.5")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("github-copilot/claude-sonnet-4.5")
   })
 
   test("uses ultimate fallback when no providers configured", () => {
@@ -270,6 +312,7 @@ describe("generateOmoConfig - model fallback system", () => {
       hasCopilot: false,
       hasOpencodeZen: false,
       hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
     }
 
     // #when generating config
@@ -277,7 +320,7 @@ describe("generateOmoConfig - model fallback system", () => {
 
     // #then should use ultimate fallback for all agents
     expect(result.$schema).toBe("https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json")
-    expect((result.agents as Record<string, { model: string }>).Sisyphus.model).toBe("opencode/glm-4.7-free")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("opencode/glm-4.7-free")
   })
 
   test("uses zai-coding-plan/glm-4.7 for librarian when Z.ai available", () => {
@@ -290,6 +333,7 @@ describe("generateOmoConfig - model fallback system", () => {
       hasCopilot: false,
       hasOpencodeZen: false,
       hasZaiCodingPlan: true,
+      hasKimiForCoding: false,
     }
 
     // #when generating config
@@ -298,7 +342,7 @@ describe("generateOmoConfig - model fallback system", () => {
     // #then librarian should use zai-coding-plan/glm-4.7
     expect((result.agents as Record<string, { model: string }>).librarian.model).toBe("zai-coding-plan/glm-4.7")
     // #then other agents should use native opus (max20 plan)
-    expect((result.agents as Record<string, { model: string }>).Sisyphus.model).toBe("anthropic/claude-opus-4-5")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-5")
   })
 
   test("uses native OpenAI models when only ChatGPT available", () => {
@@ -311,13 +355,14 @@ describe("generateOmoConfig - model fallback system", () => {
       hasCopilot: false,
       hasOpencodeZen: false,
       hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
     }
 
     // #when generating config
     const result = generateOmoConfig(config)
 
     // #then Sisyphus should use native OpenAI (fallback within native tier)
-    expect((result.agents as Record<string, { model: string }>).Sisyphus.model).toBe("openai/gpt-5.2")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("openai/gpt-5.2")
     // #then Oracle should use native OpenAI (first fallback entry)
     expect((result.agents as Record<string, { model: string }>).oracle.model).toBe("openai/gpt-5.2")
     // #then multimodal-looker should use native OpenAI (fallback within native tier)
@@ -334,6 +379,7 @@ describe("generateOmoConfig - model fallback system", () => {
       hasCopilot: false,
       hasOpencodeZen: false,
       hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
     }
 
     // #when generating config
@@ -343,7 +389,7 @@ describe("generateOmoConfig - model fallback system", () => {
     expect((result.agents as Record<string, { model: string }>).explore.model).toBe("anthropic/claude-haiku-4-5")
   })
 
-  test("uses grok-code for explore when not max20", () => {
+  test("uses haiku for explore regardless of max20 flag", () => {
     // #given user has Claude but not max20
     const config: InstallConfig = {
       hasClaude: true,
@@ -353,12 +399,13 @@ describe("generateOmoConfig - model fallback system", () => {
       hasCopilot: false,
       hasOpencodeZen: false,
       hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
     }
 
     // #when generating config
     const result = generateOmoConfig(config)
 
-    // #then explore should use grok-code (preserve Claude quota)
-    expect((result.agents as Record<string, { model: string }>).explore.model).toBe("opencode/grok-code")
+    // #then explore should use haiku (isMax20 doesn't affect explore anymore)
+    expect((result.agents as Record<string, { model: string }>).explore.model).toBe("anthropic/claude-haiku-4-5")
   })
 })

src/cli/config-manager.ts

@@ -497,38 +497,61 @@ export async function runBunInstallWithDetails(): Promise<BunInstallResult> {
  *
  * IMPORTANT: Model names MUST use `antigravity-` prefix for stability.
  *
- * The opencode-antigravity-auth plugin supports two naming conventions:
- * - `antigravity-gemini-3-pro-high` (RECOMMENDED, explicit Antigravity quota routing)
- * - `gemini-3-pro-high` (LEGACY, backward compatible but may break in future)
+ * Since opencode-antigravity-auth v1.3.0, models use a variant system:
+ * - `antigravity-gemini-3-pro` with variants: low, high
+ * - `antigravity-gemini-3-flash` with variants: minimal, low, medium, high
  *
- * Legacy names rely on Gemini CLI using `-preview` suffix for disambiguation.
- * If Google removes `-preview`, legacy names may route to wrong quota.
+ * Legacy tier-suffixed names (e.g., `antigravity-gemini-3-pro-high`) still work
+ * but variants are the recommended approach.
  *
- * @see https://github.com/NoeFabris/opencode-antigravity-auth#migration-guide-v127
+ * @see https://github.com/NoeFabris/opencode-antigravity-auth#models
  */
 export const ANTIGRAVITY_PROVIDER_CONFIG = {
   google: {
     name: "Google",
     models: {
-      "antigravity-gemini-3-pro-high": {
-        name: "Gemini 3 Pro High (Antigravity)",
-        thinking: true,
-        attachment: true,
-        limit: { context: 1048576, output: 65535 },
-        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
-      },
-      "antigravity-gemini-3-pro-low": {
-        name: "Gemini 3 Pro Low (Antigravity)",
-        thinking: true,
-        attachment: true,
+      "antigravity-gemini-3-pro": {
+        name: "Gemini 3 Pro (Antigravity)",
         limit: { context: 1048576, output: 65535 },
         modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          low: { thinkingLevel: "low" },
+          high: { thinkingLevel: "high" },
+        },
       },
       "antigravity-gemini-3-flash": {
         name: "Gemini 3 Flash (Antigravity)",
-        attachment: true,
         limit: { context: 1048576, output: 65536 },
         modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          minimal: { thinkingLevel: "minimal" },
+          low: { thinkingLevel: "low" },
+          medium: { thinkingLevel: "medium" },
+          high: { thinkingLevel: "high" },
+        },
+      },
+      "antigravity-claude-sonnet-4-5": {
+        name: "Claude Sonnet 4.5 (Antigravity)",
+        limit: { context: 200000, output: 64000 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+      },
+      "antigravity-claude-sonnet-4-5-thinking": {
+        name: "Claude Sonnet 4.5 Thinking (Antigravity)",
+        limit: { context: 200000, output: 64000 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          low: { thinkingConfig: { thinkingBudget: 8192 } },
+          max: { thinkingConfig: { thinkingBudget: 32768 } },
+        },
+      },
+      "antigravity-claude-opus-4-5-thinking": {
+        name: "Claude Opus 4.5 Thinking (Antigravity)",
+        limit: { context: 200000, output: 64000 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          low: { thinkingConfig: { thinkingBudget: 8192 } },
+          max: { thinkingConfig: { thinkingBudget: 32768 } },
+        },
       },
     },
   },
@@ -575,27 +598,28 @@ export function addProviderConfig(config: InstallConfig): ConfigMergeResult {
   }
 }
 
-function detectProvidersFromOmoConfig(): { hasOpenAI: boolean; hasOpencodeZen: boolean; hasZaiCodingPlan: boolean } {
+function detectProvidersFromOmoConfig(): { hasOpenAI: boolean; hasOpencodeZen: boolean; hasZaiCodingPlan: boolean; hasKimiForCoding: boolean } {
   const omoConfigPath = getOmoConfig()
   if (!existsSync(omoConfigPath)) {
-    return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false }
+    return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
   }
 
   try {
     const content = readFileSync(omoConfigPath, "utf-8")
     const omoConfig = parseJsonc<Record<string, unknown>>(content)
     if (!omoConfig || typeof omoConfig !== "object") {
-      return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false }
+      return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
     }
 
     const configStr = JSON.stringify(omoConfig)
     const hasOpenAI = configStr.includes('"openai/')
     const hasOpencodeZen = configStr.includes('"opencode/')
     const hasZaiCodingPlan = configStr.includes('"zai-coding-plan/')
+    const hasKimiForCoding = configStr.includes('"kimi-for-coding/')
 
-    return { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan }
+    return { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan, hasKimiForCoding }
   } catch {
-    return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false }
+    return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
   }
 }
 
@@ -609,6 +633,7 @@ export function detectCurrentConfig(): DetectedConfig {
     hasCopilot: false,
     hasOpencodeZen: true,
     hasZaiCodingPlan: false,
+    hasKimiForCoding: false,
   }
 
   const { format, path } = detectConfigFormat()
@@ -632,10 +657,11 @@ export function detectCurrentConfig(): DetectedConfig {
   // Gemini auth plugin detection still works via plugin presence
   result.hasGemini = plugins.some((p) => p.startsWith("opencode-antigravity-auth"))
 
-  const { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan } = detectProvidersFromOmoConfig()
+  const { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan, hasKimiForCoding } = detectProvidersFromOmoConfig()
   result.hasOpenAI = hasOpenAI
   result.hasOpencodeZen = hasOpencodeZen
   result.hasZaiCodingPlan = hasZaiCodingPlan
+  result.hasKimiForCoding = hasKimiForCoding
 
   return result
 }

src/cli/doctor/checks/dependencies.test.ts

@@ -16,10 +16,10 @@ describe("dependencies check", () => {
   })
 
   describe("checkAstGrepNapi", () => {
-    it("returns dependency info", () => {
+    it("returns dependency info", async () => {
       // #given
       // #when checking ast-grep napi
-      const info = deps.checkAstGrepNapi()
+      const info = await deps.checkAstGrepNapi()
 
       // #then should return valid info
       expect(info.name).toBe("AST-Grep NAPI")
@@ -95,7 +95,7 @@ describe("dependencies check", () => {
 
     it("returns pass when installed", async () => {
       // #given napi installed
-      checkSpy = spyOn(deps, "checkAstGrepNapi").mockReturnValue({
+      checkSpy = spyOn(deps, "checkAstGrepNapi").mockResolvedValue({
         name: "AST-Grep NAPI",
         required: false,
         installed: true,

src/cli/doctor/checks/dependencies.ts

@@ -56,9 +56,10 @@ export async function checkAstGrepCli(): Promise<DependencyInfo> {
   }
 }
 
-export function checkAstGrepNapi(): DependencyInfo {
+export async function checkAstGrepNapi(): Promise<DependencyInfo> {
+  // Try dynamic import first (works in bunx temporary environments)
   try {
-    require.resolve("@ast-grep/napi")
+    await import("@ast-grep/napi")
     return {
       name: "AST-Grep NAPI",
       required: false,
@@ -67,6 +68,28 @@ export function checkAstGrepNapi(): DependencyInfo {
       path: null,
     }
   } catch {
+    // Fallback: check common installation paths
+    const { existsSync } = await import("fs")
+    const { join } = await import("path")
+    const { homedir } = await import("os")
+
+    const pathsToCheck = [
+      join(homedir(), ".config", "opencode", "node_modules", "@ast-grep", "napi"),
+      join(process.cwd(), "node_modules", "@ast-grep", "napi"),
+    ]
+
+    for (const napiPath of pathsToCheck) {
+      if (existsSync(napiPath)) {
+        return {
+          name: "AST-Grep NAPI",
+          required: false,
+          installed: true,
+          version: null,
+          path: napiPath,
+        }
+      }
+    }
+
     return {
       name: "AST-Grep NAPI",
       required: false,
@@ -127,7 +150,7 @@ export async function checkDependencyAstGrepCli(): Promise<CheckResult> {
 }
 
 export async function checkDependencyAstGrepNapi(): Promise<CheckResult> {
-  const info = checkAstGrepNapi()
+  const info = await checkAstGrepNapi()
   return dependencyToCheckResult(info, CHECK_NAMES[CHECK_IDS.DEP_AST_GREP_NAPI])
 }
 

src/cli/doctor/checks/index.ts

@@ -8,6 +8,7 @@ import { getDependencyCheckDefinitions } from "./dependencies"
 import { getGhCliCheckDefinition } from "./gh"
 import { getLspCheckDefinition } from "./lsp"
 import { getMcpCheckDefinitions } from "./mcp"
+import { getMcpOAuthCheckDefinition } from "./mcp-oauth"
 import { getVersionCheckDefinition } from "./version"
 
 export * from "./opencode"
@@ -19,6 +20,7 @@ export * from "./dependencies"
 export * from "./gh"
 export * from "./lsp"
 export * from "./mcp"
+export * from "./mcp-oauth"
 export * from "./version"
 
 export function getAllCheckDefinitions(): CheckDefinition[] {
@@ -32,6 +34,7 @@ export function getAllCheckDefinitions(): CheckDefinition[] {
     getGhCliCheckDefinition(),
     getLspCheckDefinition(),
     ...getMcpCheckDefinitions(),
+    getMcpOAuthCheckDefinition(),
     getVersionCheckDefinition(),
   ]
 }

src/cli/doctor/checks/mcp-oauth.test.ts

@@ -0,0 +1,133 @@
+import { describe, it, expect, spyOn, afterEach } from "bun:test"
+import * as mcpOauth from "./mcp-oauth"
+
+describe("mcp-oauth check", () => {
+  describe("getMcpOAuthCheckDefinition", () => {
+    it("returns check definition with correct properties", () => {
+      // #given
+      // #when getting definition
+      const def = mcpOauth.getMcpOAuthCheckDefinition()
+
+      // #then should have correct structure
+      expect(def.id).toBe("mcp-oauth-tokens")
+      expect(def.name).toBe("MCP OAuth Tokens")
+      expect(def.category).toBe("tools")
+      expect(def.critical).toBe(false)
+      expect(typeof def.check).toBe("function")
+    })
+  })
+
+  describe("checkMcpOAuthTokens", () => {
+    let readStoreSpy: ReturnType<typeof spyOn>
+
+    afterEach(() => {
+      readStoreSpy?.mockRestore()
+    })
+
+    it("returns skip when no tokens stored", async () => {
+      // #given no OAuth tokens configured
+      readStoreSpy = spyOn(mcpOauth, "readTokenStore").mockReturnValue(null)
+
+      // #when checking OAuth tokens
+      const result = await mcpOauth.checkMcpOAuthTokens()
+
+      // #then should skip
+      expect(result.status).toBe("skip")
+      expect(result.message).toContain("No OAuth")
+    })
+
+    it("returns pass when all tokens valid", async () => {
+      // #given valid tokens with future expiry (expiresAt is in epoch seconds)
+      const futureTime = Math.floor(Date.now() / 1000) + 3600
+      readStoreSpy = spyOn(mcpOauth, "readTokenStore").mockReturnValue({
+        "example.com/resource1": {
+          accessToken: "token1",
+          expiresAt: futureTime,
+        },
+        "example.com/resource2": {
+          accessToken: "token2",
+          expiresAt: futureTime,
+        },
+      })
+
+      // #when checking OAuth tokens
+      const result = await mcpOauth.checkMcpOAuthTokens()
+
+      // #then should pass
+      expect(result.status).toBe("pass")
+      expect(result.message).toContain("2")
+      expect(result.message).toContain("valid")
+    })
+
+    it("returns warn when some tokens expired", async () => {
+      // #given mix of valid and expired tokens (expiresAt is in epoch seconds)
+      const futureTime = Math.floor(Date.now() / 1000) + 3600
+      const pastTime = Math.floor(Date.now() / 1000) - 3600
+      readStoreSpy = spyOn(mcpOauth, "readTokenStore").mockReturnValue({
+        "example.com/resource1": {
+          accessToken: "token1",
+          expiresAt: futureTime,
+        },
+        "example.com/resource2": {
+          accessToken: "token2",
+          expiresAt: pastTime,
+        },
+      })
+
+      // #when checking OAuth tokens
+      const result = await mcpOauth.checkMcpOAuthTokens()
+
+      // #then should warn
+      expect(result.status).toBe("warn")
+      expect(result.message).toContain("1")
+      expect(result.message).toContain("expired")
+      expect(result.details?.some((d: string) => d.includes("Expired"))).toBe(
+        true
+      )
+    })
+
+    it("returns pass when tokens have no expiry", async () => {
+      // #given tokens without expiry info
+      readStoreSpy = spyOn(mcpOauth, "readTokenStore").mockReturnValue({
+        "example.com/resource1": {
+          accessToken: "token1",
+        },
+      })
+
+      // #when checking OAuth tokens
+      const result = await mcpOauth.checkMcpOAuthTokens()
+
+      // #then should pass (no expiry = assume valid)
+      expect(result.status).toBe("pass")
+      expect(result.message).toContain("1")
+    })
+
+    it("includes token details in output", async () => {
+      // #given multiple tokens
+      const futureTime = Math.floor(Date.now() / 1000) + 3600
+      readStoreSpy = spyOn(mcpOauth, "readTokenStore").mockReturnValue({
+        "api.example.com/v1": {
+          accessToken: "token1",
+          expiresAt: futureTime,
+        },
+        "auth.example.com/oauth": {
+          accessToken: "token2",
+          expiresAt: futureTime,
+        },
+      })
+
+      // #when checking OAuth tokens
+      const result = await mcpOauth.checkMcpOAuthTokens()
+
+      // #then should list tokens in details
+      expect(result.details).toBeDefined()
+      expect(result.details?.length).toBeGreaterThan(0)
+      expect(
+        result.details?.some((d: string) => d.includes("api.example.com"))
+      ).toBe(true)
+      expect(
+        result.details?.some((d: string) => d.includes("auth.example.com"))
+      ).toBe(true)
+    })
+  })
+})

src/cli/doctor/checks/mcp-oauth.ts

@@ -0,0 +1,80 @@
+import type { CheckResult, CheckDefinition } from "../types"
+import { CHECK_IDS, CHECK_NAMES } from "../constants"
+import { getMcpOauthStoragePath } from "../../../features/mcp-oauth/storage"
+import { existsSync, readFileSync } from "node:fs"
+
+interface OAuthTokenData {
+  accessToken: string
+  refreshToken?: string
+  expiresAt?: number
+  clientInfo?: {
+    clientId: string
+    clientSecret?: string
+  }
+}
+
+type TokenStore = Record<string, OAuthTokenData>
+
+export function readTokenStore(): TokenStore | null {
+  const filePath = getMcpOauthStoragePath()
+  if (!existsSync(filePath)) {
+    return null
+  }
+
+  try {
+    const content = readFileSync(filePath, "utf-8")
+    return JSON.parse(content) as TokenStore
+  } catch {
+    return null
+  }
+}
+
+export async function checkMcpOAuthTokens(): Promise<CheckResult> {
+  const store = readTokenStore()
+
+  if (!store || Object.keys(store).length === 0) {
+    return {
+      name: CHECK_NAMES[CHECK_IDS.MCP_OAUTH_TOKENS],
+      status: "skip",
+      message: "No OAuth tokens configured",
+      details: ["Optional: Configure OAuth tokens for MCP servers"],
+    }
+  }
+
+  const now = Math.floor(Date.now() / 1000)
+  const tokens = Object.entries(store)
+  const expiredTokens = tokens.filter(
+    ([, token]) => token.expiresAt && token.expiresAt < now
+  )
+
+  if (expiredTokens.length > 0) {
+    return {
+      name: CHECK_NAMES[CHECK_IDS.MCP_OAUTH_TOKENS],
+      status: "warn",
+      message: `${expiredTokens.length} of ${tokens.length} token(s) expired`,
+      details: [
+        ...tokens
+          .filter(([, token]) => !token.expiresAt || token.expiresAt >= now)
+          .map(([key]) => `Valid: ${key}`),
+        ...expiredTokens.map(([key]) => `Expired: ${key}`),
+      ],
+    }
+  }
+
+  return {
+    name: CHECK_NAMES[CHECK_IDS.MCP_OAUTH_TOKENS],
+    status: "pass",
+    message: `${tokens.length} OAuth token(s) valid`,
+    details: tokens.map(([key]) => `Configured: ${key}`),
+  }
+}
+
+export function getMcpOAuthCheckDefinition(): CheckDefinition {
+  return {
+    id: CHECK_IDS.MCP_OAUTH_TOKENS,
+    name: CHECK_NAMES[CHECK_IDS.MCP_OAUTH_TOKENS],
+    category: "tools",
+    check: checkMcpOAuthTokens,
+    critical: false,
+  }
+}

src/cli/doctor/checks/model-resolution.test.ts

@@ -12,7 +12,7 @@ describe("model-resolution check", () => {
       const info = getModelResolutionInfo()
 
       // #then: Should have agent entries
-      const sisyphus = info.agents.find((a) => a.name === "Sisyphus")
+      const sisyphus = info.agents.find((a) => a.name === "sisyphus")
       expect(sisyphus).toBeDefined()
       expect(sisyphus!.requirement.fallbackChain[0]?.model).toBe("claude-opus-4-5")
       expect(sisyphus!.requirement.fallbackChain[0]?.providers).toContain("anthropic")
@@ -27,7 +27,7 @@ describe("model-resolution check", () => {
       // #then: Should have category entries
       const visual = info.categories.find((c) => c.name === "visual-engineering")
       expect(visual).toBeDefined()
-      expect(visual!.requirement.fallbackChain[0]?.model).toBe("gemini-3-pro-preview")
+      expect(visual!.requirement.fallbackChain[0]?.model).toBe("gemini-3-pro")
       expect(visual!.requirement.fallbackChain[0]?.providers).toContain("google")
     })
   })
@@ -84,7 +84,7 @@ describe("model-resolution check", () => {
       const info = getModelResolutionInfoWithOverrides(mockConfig)
 
       // #then: Should show provider fallback chain
-      const sisyphus = info.agents.find((a) => a.name === "Sisyphus")
+      const sisyphus = info.agents.find((a) => a.name === "sisyphus")
       expect(sisyphus).toBeDefined()
       expect(sisyphus!.userOverride).toBeUndefined()
       expect(sisyphus!.effectiveResolution).toContain("Provider fallback:")
@@ -97,13 +97,14 @@ describe("model-resolution check", () => {
     // #when: Running the model resolution check
     // #then: Returns pass with details showing resolution flow
 
-    it("returns pass status with agent and category counts", async () => {
+    it("returns pass or warn status with agent and category counts", async () => {
       const { checkModelResolution } = await import("./model-resolution")
 
       const result = await checkModelResolution()
 
-      // #then: Should pass and show counts
-      expect(result.status).toBe("pass")
+      // #then: Should pass (with cache) or warn (no cache) and show counts
+      // In CI without model cache, status is "warn"; locally with cache, status is "pass"
+      expect(["pass", "warn"]).toContain(result.status)
       expect(result.message).toMatch(/\d+ agents?, \d+ categories?/)
     })
 
@@ -115,8 +116,9 @@ describe("model-resolution check", () => {
       // #then: Details should contain agent/category resolution info
       expect(result.details).toBeDefined()
       expect(result.details!.length).toBeGreaterThan(0)
-      // Should have Current Models header and sections
-      expect(result.details!.some((d) => d.includes("Current Models"))).toBe(true)
+      // Should have Available Models and Configured Models headers
+      expect(result.details!.some((d) => d.includes("Available Models"))).toBe(true)
+      expect(result.details!.some((d) => d.includes("Configured Models"))).toBe(true)
       expect(result.details!.some((d) => d.includes("Agents:"))).toBe(true)
       expect(result.details!.some((d) => d.includes("Categories:"))).toBe(true)
       // Should have legend

src/cli/doctor/checks/model-resolution.ts

@@ -1,4 +1,4 @@
-import { readFileSync } from "node:fs"
+import { readFileSync, existsSync } from "node:fs"
 import type { CheckResult, CheckDefinition } from "../types"
 import { CHECK_IDS, CHECK_NAMES } from "../constants"
 import { parseJsonc, detectConfigFile } from "../../../shared"
@@ -10,6 +10,38 @@ import {
 import { homedir } from "node:os"
 import { join } from "node:path"
 
+function getOpenCodeCacheDir(): string {
+  const xdgCache = process.env.XDG_CACHE_HOME
+  if (xdgCache) return join(xdgCache, "opencode")
+  return join(homedir(), ".cache", "opencode")
+}
+
+function loadAvailableModels(): { providers: string[]; modelCount: number; cacheExists: boolean } {
+  const cacheFile = join(getOpenCodeCacheDir(), "models.json")
+  
+  if (!existsSync(cacheFile)) {
+    return { providers: [], modelCount: 0, cacheExists: false }
+  }
+
+  try {
+    const content = readFileSync(cacheFile, "utf-8")
+    const data = JSON.parse(content) as Record<string, { models?: Record<string, unknown> }>
+    
+    const providers = Object.keys(data)
+    let modelCount = 0
+    for (const providerId of providers) {
+      const models = data[providerId]?.models
+      if (models && typeof models === "object") {
+        modelCount += Object.keys(models).length
+      }
+    }
+    
+    return { providers, modelCount, cacheExists: true }
+  } catch {
+    return { providers: [], modelCount: 0, cacheExists: false }
+  }
+}
+
 const PACKAGE_NAME = "oh-my-opencode"
 const USER_CONFIG_DIR = join(homedir(), ".config", "opencode")
 const USER_CONFIG_BASE = join(USER_CONFIG_DIR, PACKAGE_NAME)
@@ -155,10 +187,30 @@ function getEffectiveVariant(requirement: ModelRequirement): string | undefined
   return firstEntry?.variant ?? requirement.variant
 }
 
-function buildDetailsArray(info: ModelResolutionInfo): string[] {
+interface AvailableModelsInfo {
+  providers: string[]
+  modelCount: number
+  cacheExists: boolean
+}
+
+function buildDetailsArray(info: ModelResolutionInfo, available: AvailableModelsInfo): string[] {
   const details: string[] = []
 
-  details.push("═══ Current Models ═══")
+  details.push("═══ Available Models (from cache) ═══")
+  details.push("")
+  if (available.cacheExists) {
+    details.push(`  Providers in cache: ${available.providers.length}`)
+    details.push(`  Sample: ${available.providers.slice(0, 6).join(", ")}${available.providers.length > 6 ? "..." : ""}`)
+    details.push(`  Total models: ${available.modelCount}`)
+    details.push(`  Cache: ~/.cache/opencode/models.json`)
+    details.push(`  ℹ Runtime: only connected providers used`)
+    details.push(`  Refresh: opencode models --refresh`)
+  } else {
+    details.push("  ⚠ Cache not found. Run 'opencode' to populate.")
+  }
+  details.push("")
+
+  details.push("═══ Configured Models ═══")
   details.push("")
   details.push("Agents:")
   for (const agent of info.agents) {
@@ -182,6 +234,7 @@ function buildDetailsArray(info: ModelResolutionInfo): string[] {
 export async function checkModelResolution(): Promise<CheckResult> {
   const config = loadConfig() ?? {}
   const info = getModelResolutionInfoWithOverrides(config)
+  const available = loadAvailableModels()
 
   const agentCount = info.agents.length
   const categoryCount = info.categories.length
@@ -190,12 +243,13 @@ export async function checkModelResolution(): Promise<CheckResult> {
   const totalOverrides = agentOverrides + categoryOverrides
 
   const overrideNote = totalOverrides > 0 ? ` (${totalOverrides} override${totalOverrides > 1 ? "s" : ""})` : ""
+  const cacheNote = available.cacheExists ? `, ${available.modelCount} available` : ", cache not found"
 
   return {
     name: CHECK_NAMES[CHECK_IDS.MODEL_RESOLUTION],
-    status: "pass",
-    message: `${agentCount} agents, ${categoryCount} categories${overrideNote}`,
-    details: buildDetailsArray(info),
+    status: available.cacheExists ? "pass" : "warn",
+    message: `${agentCount} agents, ${categoryCount} categories${overrideNote}${cacheNote}`,
+    details: buildDetailsArray(info, available),
   }
 }
 

src/cli/doctor/checks/plugin.ts

@@ -22,6 +22,9 @@ function findPluginEntry(plugins: string[]): { entry: string; isPinned: boolean;
       const version = isPinned ? plugin.split("@")[1] : null
       return { entry: plugin, isPinned, version }
     }
+    if (plugin.startsWith("file://") && plugin.includes(PACKAGE_NAME)) {
+      return { entry: plugin, isPinned: false, version: "local-dev" }
+    }
   }
   return null
 }

src/cli/doctor/constants.ts

@@ -32,6 +32,7 @@ export const CHECK_IDS = {
   LSP_SERVERS: "lsp-servers",
   MCP_BUILTIN: "mcp-builtin",
   MCP_USER: "mcp-user",
+  MCP_OAUTH_TOKENS: "mcp-oauth-tokens",
   VERSION_STATUS: "version-status",
 } as const
 
@@ -50,6 +51,7 @@ export const CHECK_NAMES: Record<string, string> = {
   [CHECK_IDS.LSP_SERVERS]: "LSP Servers",
   [CHECK_IDS.MCP_BUILTIN]: "Built-in MCP Servers",
   [CHECK_IDS.MCP_USER]: "User MCP Configuration",
+  [CHECK_IDS.MCP_OAUTH_TOKENS]: "MCP OAuth Tokens",
   [CHECK_IDS.VERSION_STATUS]: "Version Status",
 } as const
 

src/cli/index.test.ts

@@ -0,0 +1,17 @@
+import { describe, it, expect } from "bun:test"
+import packageJson from "../../package.json" with { type: "json" }
+
+describe("CLI version", () => {
+  it("reads version from package.json as valid semver", () => {
+    //#given
+    const semverRegex = /^\d+\.\d+\.\d+(-[\w.]+)?$/
+
+    //#when
+    const version = packageJson.version
+
+    //#then
+    expect(version).toMatch(semverRegex)
+    expect(typeof version).toBe("string")
+    expect(version.length).toBeGreaterThan(0)
+  })
+})

src/cli/index.ts

@@ -4,6 +4,7 @@ import { install } from "./install"
 import { run } from "./run"
 import { getLocalVersion } from "./get-local-version"
 import { doctor } from "./doctor"
+import { createMcpOAuthCommand } from "./mcp-oauth"
 import type { InstallArgs } from "./types"
 import type { RunOptions } from "./run"
 import type { GetLocalVersionOptions } from "./get-local-version/types"
@@ -29,6 +30,7 @@ program
   .option("--copilot <value>", "GitHub Copilot subscription: no, yes")
   .option("--opencode-zen <value>", "OpenCode Zen access: no, yes (default: no)")
   .option("--zai-coding-plan <value>", "Z.ai Coding Plan subscription: no, yes (default: no)")
+  .option("--kimi-for-coding <value>", "Kimi For Coding subscription: no, yes (default: no)")
   .option("--skip-auth", "Skip authentication setup hints")
   .addHelpText("after", `
 Examples:
@@ -36,13 +38,14 @@ Examples:
   $ bunx oh-my-opencode install --no-tui --claude=max20 --openai=yes --gemini=yes --copilot=no
   $ bunx oh-my-opencode install --no-tui --claude=no --gemini=no --copilot=yes --opencode-zen=yes
 
-Model Providers (Priority: Native > Copilot > OpenCode Zen > Z.ai):
+Model Providers (Priority: Native > Copilot > OpenCode Zen > Z.ai > Kimi):
   Claude        Native anthropic/ models (Opus, Sonnet, Haiku)
   OpenAI        Native openai/ models (GPT-5.2 for Oracle)
   Gemini        Native google/ models (Gemini 3 Pro, Flash)
   Copilot       github-copilot/ models (fallback)
   OpenCode Zen  opencode/ models (opencode/claude-opus-4-5, etc.)
   Z.ai          zai-coding-plan/glm-4.7 (Librarian priority)
+  Kimi          kimi-for-coding/k2p5 (Sisyphus/Prometheus fallback)
 `)
   .action(async (options) => {
     const args: InstallArgs = {
@@ -53,6 +56,7 @@ Model Providers (Priority: Native > Copilot > OpenCode Zen > Z.ai):
       copilot: options.copilot,
       opencodeZen: options.opencodeZen,
       zaiCodingPlan: options.zaiCodingPlan,
+      kimiForCoding: options.kimiForCoding,
       skipAuth: options.skipAuth ?? false,
     }
     const exitCode = await install(args)
@@ -150,4 +154,6 @@ program
     console.log(`oh-my-opencode v${VERSION}`)
   })
 
+program.addCommand(createMcpOAuthCommand())
+
 program.parse()

src/cli/install.ts

@@ -44,7 +44,8 @@ function formatConfigSummary(config: InstallConfig): string {
   lines.push(formatProvider("Gemini", config.hasGemini))
   lines.push(formatProvider("GitHub Copilot", config.hasCopilot, "fallback"))
   lines.push(formatProvider("OpenCode Zen", config.hasOpencodeZen, "opencode/ models"))
-  lines.push(formatProvider("Z.ai Coding Plan", config.hasZaiCodingPlan, "Librarian: glm-4.7"))
+  lines.push(formatProvider("Z.ai Coding Plan", config.hasZaiCodingPlan, "Librarian/Multimodal"))
+  lines.push(formatProvider("Kimi For Coding", config.hasKimiForCoding, "Sisyphus/Prometheus fallback"))
 
   lines.push("")
   lines.push(color.dim("─".repeat(40)))
@@ -141,6 +142,10 @@ function validateNonTuiArgs(args: InstallArgs): { valid: boolean; errors: string
     errors.push(`Invalid --zai-coding-plan value: ${args.zaiCodingPlan} (expected: no, yes)`)
   }
 
+  if (args.kimiForCoding !== undefined && !["no", "yes"].includes(args.kimiForCoding)) {
+    errors.push(`Invalid --kimi-for-coding value: ${args.kimiForCoding} (expected: no, yes)`)
+  }
+
   return { valid: errors.length === 0, errors }
 }
 
@@ -153,10 +158,11 @@ function argsToConfig(args: InstallArgs): InstallConfig {
     hasCopilot: args.copilot === "yes",
     hasOpencodeZen: args.opencodeZen === "yes",
     hasZaiCodingPlan: args.zaiCodingPlan === "yes",
+    hasKimiForCoding: args.kimiForCoding === "yes",
   }
 }
 
-function detectedToInitialValues(detected: DetectedConfig): { claude: ClaudeSubscription; openai: BooleanArg; gemini: BooleanArg; copilot: BooleanArg; opencodeZen: BooleanArg; zaiCodingPlan: BooleanArg } {
+function detectedToInitialValues(detected: DetectedConfig): { claude: ClaudeSubscription; openai: BooleanArg; gemini: BooleanArg; copilot: BooleanArg; opencodeZen: BooleanArg; zaiCodingPlan: BooleanArg; kimiForCoding: BooleanArg } {
   let claude: ClaudeSubscription = "no"
   if (detected.hasClaude) {
     claude = detected.isMax20 ? "max20" : "yes"
@@ -169,6 +175,7 @@ function detectedToInitialValues(detected: DetectedConfig): { claude: ClaudeSubs
     copilot: detected.hasCopilot ? "yes" : "no",
     opencodeZen: detected.hasOpencodeZen ? "yes" : "no",
     zaiCodingPlan: detected.hasZaiCodingPlan ? "yes" : "no",
+    kimiForCoding: detected.hasKimiForCoding ? "yes" : "no",
   }
 }
 
@@ -250,7 +257,7 @@ async function runTuiMode(detected: DetectedConfig): Promise<InstallConfig | nul
     message: "Do you have a Z.ai Coding Plan subscription?",
     options: [
       { value: "no" as const, label: "No", hint: "Will use other configured providers" },
-      { value: "yes" as const, label: "Yes", hint: "zai-coding-plan/glm-4.7 for Librarian" },
+      { value: "yes" as const, label: "Yes", hint: "Fallback for Librarian and Multimodal Looker" },
     ],
     initialValue: initial.zaiCodingPlan,
   })
@@ -260,6 +267,20 @@ async function runTuiMode(detected: DetectedConfig): Promise<InstallConfig | nul
     return null
   }
 
+  const kimiForCoding = await p.select({
+    message: "Do you have a Kimi For Coding subscription?",
+    options: [
+      { value: "no" as const, label: "No", hint: "Will use other configured providers" },
+      { value: "yes" as const, label: "Yes", hint: "Kimi K2.5 for Sisyphus/Prometheus fallback" },
+    ],
+    initialValue: initial.kimiForCoding,
+  })
+
+  if (p.isCancel(kimiForCoding)) {
+    p.cancel("Installation cancelled.")
+    return null
+  }
+
   return {
     hasClaude: claude !== "no",
     isMax20: claude === "max20",
@@ -268,6 +289,7 @@ async function runTuiMode(detected: DetectedConfig): Promise<InstallConfig | nul
     hasCopilot: copilot === "yes",
     hasOpencodeZen: opencodeZen === "yes",
     hasZaiCodingPlan: zaiCodingPlan === "yes",
+    hasKimiForCoding: kimiForCoding === "yes",
   }
 }
 
@@ -378,7 +400,7 @@ async function runNonTuiInstall(args: InstallArgs): Promise<number> {
   )
 
   console.log(`${SYMBOLS.star} ${color.yellow("If you found this helpful, consider starring the repo!")}`)
-  console.log(`  ${color.dim("gh repo star code-yeongyu/oh-my-opencode")}`)
+  console.log(`  ${color.dim("gh api --silent --method PUT /user/starred/code-yeongyu/oh-my-opencode >/dev/null 2>&1 || true")}`)
   console.log()
   console.log(color.dim("oMoMoMoMo... Enjoy!"))
   console.log()
@@ -496,7 +518,7 @@ export async function install(args: InstallArgs): Promise<number> {
   )
 
   p.log.message(`${color.yellow("★")} If you found this helpful, consider starring the repo!`)
-  p.log.message(`  ${color.dim("gh repo star code-yeongyu/oh-my-opencode")}`)
+  p.log.message(`  ${color.dim("gh api --silent --method PUT /user/starred/code-yeongyu/oh-my-opencode >/dev/null 2>&1 || true")}`)
 
   p.outro(color.green("oMoMoMoMo... Enjoy!"))
 

src/cli/mcp-oauth/index.test.ts

@@ -0,0 +1,123 @@
+import { describe, it, expect } from "bun:test"
+import { Command } from "commander"
+import { createMcpOAuthCommand } from "./index"
+
+describe("mcp oauth command", () => {
+
+  describe("command structure", () => {
+    it("creates mcp command group with oauth subcommand", () => {
+      // given
+      const mcpCommand = createMcpOAuthCommand()
+
+      // when
+      const subcommands = mcpCommand.commands.map((cmd: Command) => cmd.name())
+
+      // then
+      expect(subcommands).toContain("oauth")
+    })
+
+    it("oauth subcommand has login, logout, and status subcommands", () => {
+      // given
+      const mcpCommand = createMcpOAuthCommand()
+      const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
+
+      // when
+      const subcommands = oauthCommand?.commands.map((cmd: Command) => cmd.name()) ?? []
+
+      // then
+      expect(subcommands).toContain("login")
+      expect(subcommands).toContain("logout")
+      expect(subcommands).toContain("status")
+    })
+  })
+
+  describe("login subcommand", () => {
+    it("exists and has description", () => {
+      // given
+      const mcpCommand = createMcpOAuthCommand()
+      const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
+      const loginCommand = oauthCommand?.commands.find((cmd: Command) => cmd.name() === "login")
+
+      // when
+      const description = loginCommand?.description() ?? ""
+
+      // then
+      expect(loginCommand).toBeDefined()
+      expect(description).toContain("OAuth")
+    })
+
+    it("accepts --server-url option", () => {
+      // given
+      const mcpCommand = createMcpOAuthCommand()
+      const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
+      const loginCommand = oauthCommand?.commands.find((cmd: Command) => cmd.name() === "login")
+
+      // when
+      const options = loginCommand?.options ?? []
+      const serverUrlOption = options.find((opt: { long?: string }) => opt.long === "--server-url")
+
+      // then
+      expect(serverUrlOption).toBeDefined()
+    })
+
+    it("accepts --client-id option", () => {
+      // given
+      const mcpCommand = createMcpOAuthCommand()
+      const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
+      const loginCommand = oauthCommand?.commands.find((cmd: Command) => cmd.name() === "login")
+
+      // when
+      const options = loginCommand?.options ?? []
+      const clientIdOption = options.find((opt: { long?: string }) => opt.long === "--client-id")
+
+      // then
+      expect(clientIdOption).toBeDefined()
+    })
+
+    it("accepts --scopes option", () => {
+      // given
+      const mcpCommand = createMcpOAuthCommand()
+      const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
+      const loginCommand = oauthCommand?.commands.find((cmd: Command) => cmd.name() === "login")
+
+      // when
+      const options = loginCommand?.options ?? []
+      const scopesOption = options.find((opt: { long?: string }) => opt.long === "--scopes")
+
+      // then
+      expect(scopesOption).toBeDefined()
+    })
+  })
+
+  describe("logout subcommand", () => {
+    it("exists and has description", () => {
+      // given
+      const mcpCommand = createMcpOAuthCommand()
+      const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
+      const logoutCommand = oauthCommand?.commands.find((cmd: Command) => cmd.name() === "logout")
+
+      // when
+      const description = logoutCommand?.description() ?? ""
+
+      // then
+      expect(logoutCommand).toBeDefined()
+      expect(description).toContain("tokens")
+    })
+  })
+
+  describe("status subcommand", () => {
+    it("exists and has description", () => {
+      // given
+      const mcpCommand = createMcpOAuthCommand()
+      const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
+      const statusCommand = oauthCommand?.commands.find((cmd: Command) => cmd.name() === "status")
+
+      // when
+      const description = statusCommand?.description() ?? ""
+
+      // then
+      expect(statusCommand).toBeDefined()
+      expect(description).toContain("status")
+    })
+  })
+})

src/cli/mcp-oauth/index.ts

@@ -0,0 +1,43 @@
+import { Command } from "commander"
+import { login } from "./login"
+import { logout } from "./logout"
+import { status } from "./status"
+
+export function createMcpOAuthCommand(): Command {
+  const mcp = new Command("mcp").description("MCP server management")
+
+  const oauth = new Command("oauth").description("OAuth token management for MCP servers")
+
+  oauth
+    .command("login <server-name>")
+    .description("Authenticate with an MCP server using OAuth")
+    .option("--server-url <url>", "OAuth server URL (required if not in config)")
+    .option("--client-id <id>", "OAuth client ID (optional, uses DCR if not provided)")
+    .option("--scopes <scopes...>", "OAuth scopes to request")
+    .action(async (serverName: string, options) => {
+      const exitCode = await login(serverName, options)
+      process.exit(exitCode)
+    })
+
+  oauth
+    .command("logout <server-name>")
+    .description("Remove stored OAuth tokens for an MCP server")
+    .option("--server-url <url>", "OAuth server URL (use if server name differs from URL)")
+    .action(async (serverName: string, options) => {
+      const exitCode = await logout(serverName, options)
+      process.exit(exitCode)
+    })
+
+  oauth
+    .command("status [server-name]")
+    .description("Show OAuth token status for MCP servers")
+    .action(async (serverName: string | undefined) => {
+      const exitCode = await status(serverName)
+      process.exit(exitCode)
+    })
+
+  mcp.addCommand(oauth)
+  return mcp
+}
+
+export { login, logout, status }

src/cli/mcp-oauth/login.test.ts

@@ -0,0 +1,80 @@
+import { describe, it, expect, beforeEach, afterEach, mock } from "bun:test"
+
+const mockLogin = mock(() => Promise.resolve({ accessToken: "test-token", expiresAt: 1710000000 }))
+
+mock.module("../../features/mcp-oauth/provider", () => ({
+  McpOAuthProvider: class MockMcpOAuthProvider {
+    constructor(public options: { serverUrl: string; clientId?: string; scopes?: string[] }) {}
+    async login() {
+      return mockLogin()
+    }
+  },
+}))
+
+const { login } = await import("./login")
+
+describe("login command", () => {
+  beforeEach(() => {
+    mockLogin.mockClear()
+  })
+
+  afterEach(() => {
+    // cleanup
+  })
+
+  it("returns error code when server-url is not provided", async () => {
+    // given
+    const serverName = "test-server"
+    const options = {}
+
+    // when
+    const exitCode = await login(serverName, options)
+
+    // then
+    expect(exitCode).toBe(1)
+  })
+
+  it("returns success code when login succeeds", async () => {
+    // given
+    const serverName = "test-server"
+    const options = {
+      serverUrl: "https://oauth.example.com",
+    }
+
+    // when
+    const exitCode = await login(serverName, options)
+
+    // then
+    expect(exitCode).toBe(0)
+    expect(mockLogin).toHaveBeenCalledTimes(1)
+  })
+
+  it("returns error code when login throws", async () => {
+    // given
+    const serverName = "test-server"
+    const options = {
+      serverUrl: "https://oauth.example.com",
+    }
+    mockLogin.mockRejectedValueOnce(new Error("Network error"))
+
+    // when
+    const exitCode = await login(serverName, options)
+
+    // then
+    expect(exitCode).toBe(1)
+  })
+
+  it("returns error code when server-url is missing", async () => {
+    // given
+    const serverName = "test-server"
+    const options = {
+      clientId: "test-client-id",
+    }
+
+    // when
+    const exitCode = await login(serverName, options)
+
+    // then
+    expect(exitCode).toBe(1)
+  })
+})

src/cli/mcp-oauth/login.ts

@@ -0,0 +1,38 @@
+import { McpOAuthProvider } from "../../features/mcp-oauth/provider"
+
+export interface LoginOptions {
+  serverUrl?: string
+  clientId?: string
+  scopes?: string[]
+}
+
+export async function login(serverName: string, options: LoginOptions): Promise<number> {
+  try {
+    const serverUrl = options.serverUrl
+    if (!serverUrl) {
+      console.error(`Error: --server-url is required for server "${serverName}"`)
+      return 1
+    }
+
+    const provider = new McpOAuthProvider({
+      serverUrl,
+      clientId: options.clientId,
+      scopes: options.scopes,
+    })
+
+    console.log(`Authenticating with ${serverName}...`)
+    const tokenData = await provider.login()
+
+    console.log(`✓ Successfully authenticated with ${serverName}`)
+    if (tokenData.expiresAt) {
+      const expiryDate = new Date(tokenData.expiresAt * 1000)
+      console.log(`  Token expires at: ${expiryDate.toISOString()}`)
+    }
+
+    return 0
+  } catch (error) {
+    const message = error instanceof Error ? error.message : String(error)
+    console.error(`Error: Failed to authenticate with ${serverName}: ${message}`)
+    return 1
+  }
+}

src/cli/mcp-oauth/logout.test.ts

@@ -0,0 +1,65 @@
+import { describe, it, expect, beforeEach, afterEach, mock } from "bun:test"
+import { existsSync, mkdirSync, rmSync } from "node:fs"
+import { join } from "node:path"
+import { tmpdir } from "node:os"
+import { saveToken } from "../../features/mcp-oauth/storage"
+
+const { logout } = await import("./logout")
+
+describe("logout command", () => {
+  const TEST_CONFIG_DIR = join(tmpdir(), "mcp-oauth-logout-test-" + Date.now())
+  let originalConfigDir: string | undefined
+
+  beforeEach(() => {
+    originalConfigDir = process.env.OPENCODE_CONFIG_DIR
+    process.env.OPENCODE_CONFIG_DIR = TEST_CONFIG_DIR
+    if (!existsSync(TEST_CONFIG_DIR)) {
+      mkdirSync(TEST_CONFIG_DIR, { recursive: true })
+    }
+  })
+
+  afterEach(() => {
+    if (originalConfigDir === undefined) {
+      delete process.env.OPENCODE_CONFIG_DIR
+    } else {
+      process.env.OPENCODE_CONFIG_DIR = originalConfigDir
+    }
+    if (existsSync(TEST_CONFIG_DIR)) {
+      rmSync(TEST_CONFIG_DIR, { recursive: true, force: true })
+    }
+  })
+
+  it("returns success code when logout succeeds", async () => {
+    // given
+    const serverUrl = "https://test-server.example.com"
+    saveToken(serverUrl, serverUrl, { accessToken: "test-token" })
+
+    // when
+    const exitCode = await logout("test-server", { serverUrl })
+
+    // then
+    expect(exitCode).toBe(0)
+  })
+
+  it("handles non-existent server gracefully", async () => {
+    // given
+    const serverName = "non-existent-server"
+
+    // when
+    const exitCode = await logout(serverName, { serverUrl: "https://nonexistent.example.com" })
+
+    // then
+    expect(exitCode).toBe(0)
+  })
+
+  it("returns error when --server-url is not provided", async () => {
+    // given
+    const serverName = "test-server"
+
+    // when
+    const exitCode = await logout(serverName)
+
+    // then
+    expect(exitCode).toBe(1)
+  })
+})

src/cli/mcp-oauth/logout.ts

@@ -0,0 +1,30 @@
+import { deleteToken } from "../../features/mcp-oauth/storage"
+
+export interface LogoutOptions {
+  serverUrl?: string
+}
+
+export async function logout(serverName: string, options?: LogoutOptions): Promise<number> {
+  try {
+    const serverUrl = options?.serverUrl
+    if (!serverUrl) {
+      console.error(`Error: --server-url is required for logout. Token storage uses server URLs, not names.`)
+      console.error(`  Usage: mcp oauth logout ${serverName} --server-url https://your-server.example.com`)
+      return 1
+    }
+
+    const success = deleteToken(serverUrl, serverUrl)
+
+    if (success) {
+      console.log(`✓ Successfully removed tokens for ${serverName}`)
+      return 0
+    }
+
+    console.error(`Error: Failed to remove tokens for ${serverName}`)
+    return 1
+  } catch (error) {
+    const message = error instanceof Error ? error.message : String(error)
+    console.error(`Error: Failed to remove tokens for ${serverName}: ${message}`)
+    return 1
+  }
+}

src/cli/mcp-oauth/status.test.ts

@@ -0,0 +1,48 @@
+import { describe, it, expect, beforeEach, afterEach } from "bun:test"
+import { status } from "./status"
+
+describe("status command", () => {
+  beforeEach(() => {
+    // setup
+  })
+
+  afterEach(() => {
+    // cleanup
+  })
+
+  it("returns success code when checking status for specific server", async () => {
+    // given
+    const serverName = "test-server"
+
+    // when
+    const exitCode = await status(serverName)
+
+    // then
+    expect(typeof exitCode).toBe("number")
+    expect(exitCode).toBe(0)
+  })
+
+  it("returns success code when checking status for all servers", async () => {
+    // given
+    const serverName = undefined
+
+    // when
+    const exitCode = await status(serverName)
+
+    // then
+    expect(typeof exitCode).toBe("number")
+    expect(exitCode).toBe(0)
+  })
+
+  it("handles non-existent server gracefully", async () => {
+    // given
+    const serverName = "non-existent-server"
+
+    // when
+    const exitCode = await status(serverName)
+
+    // then
+    expect(typeof exitCode).toBe("number")
+    expect(exitCode).toBe(0)
+  })
+})

src/cli/mcp-oauth/status.ts

@@ -0,0 +1,50 @@
+import { listAllTokens, listTokensByHost } from "../../features/mcp-oauth/storage"
+
+export async function status(serverName: string | undefined): Promise<number> {
+  try {
+    if (serverName) {
+      const tokens = listTokensByHost(serverName)
+
+      if (Object.keys(tokens).length === 0) {
+        console.log(`No tokens found for ${serverName}`)
+        return 0
+      }
+
+      console.log(`OAuth Status for ${serverName}:`)
+      for (const [key, token] of Object.entries(tokens)) {
+        console.log(`  ${key}:`)
+        console.log(`    Access Token: [REDACTED]`)
+        if (token.refreshToken) {
+          console.log(`    Refresh Token: [REDACTED]`)
+        }
+        if (token.expiresAt) {
+          const expiryDate = new Date(token.expiresAt * 1000)
+          const now = Date.now() / 1000
+          const isExpired = token.expiresAt < now
+          const tokenStatus = isExpired ? "EXPIRED" : "VALID"
+          console.log(`    Expiry: ${expiryDate.toISOString()} (${tokenStatus})`)
+        }
+      }
+      return 0
+    }
+
+    const tokens = listAllTokens()
+    if (Object.keys(tokens).length === 0) {
+      console.log("No OAuth tokens stored")
+      return 0
+    }
+
+    console.log("Stored OAuth Tokens:")
+    for (const [key, token] of Object.entries(tokens)) {
+      const isExpired = token.expiresAt && token.expiresAt < Date.now() / 1000
+      const tokenStatus = isExpired ? "EXPIRED" : "VALID"
+      console.log(`  ${key}: ${tokenStatus}`)
+    }
+
+    return 0
+  } catch (error) {
+    const message = error instanceof Error ? error.message : String(error)
+    console.error(`Error: Failed to get token status: ${message}`)
+    return 1
+  }
+}

src/cli/model-fallback.test.ts

@@ -12,6 +12,7 @@ function createConfig(overrides: Partial<InstallConfig> = {}): InstallConfig {
     hasCopilot: false,
     hasOpencodeZen: false,
     hasZaiCodingPlan: false,
+    hasKimiForCoding: false,
     ...overrides,
   }
 }
@@ -310,19 +311,19 @@ describe("generateModelConfig", () => {
   })
 
   describe("explore agent special cases", () => {
-    test("explore uses Gemini flash when Gemini available", () => {
-      // #given Gemini is available
+    test("explore uses gpt-5-nano when only Gemini available (no Claude)", () => {
+      // #given only Gemini is available (no Claude)
       const config = createConfig({ hasGemini: true })
 
       // #when generateModelConfig is called
       const result = generateModelConfig(config)
 
-      // #then explore should use gemini-3-flash-preview
-      expect(result.agents?.explore?.model).toBe("google/gemini-3-flash-preview")
+      // #then explore should use gpt-5-nano (Claude haiku not available)
+      expect(result.agents?.explore?.model).toBe("opencode/gpt-5-nano")
     })
 
-    test("explore uses Claude haiku when Claude + isMax20 but no Gemini", () => {
-      // #given Claude is available with Max 20 plan but no Gemini
+    test("explore uses Claude haiku when Claude available", () => {
+      // #given Claude is available
       const config = createConfig({ hasClaude: true, isMax20: true })
 
       // #when generateModelConfig is called
@@ -332,26 +333,37 @@ describe("generateModelConfig", () => {
       expect(result.agents?.explore?.model).toBe("anthropic/claude-haiku-4-5")
     })
 
-    test("explore uses grok-code when Claude without isMax20 and no Gemini", () => {
-      // #given Claude is available without Max 20 plan and no Gemini
+    test("explore uses Claude haiku regardless of isMax20 flag", () => {
+      // #given Claude is available without Max 20 plan
       const config = createConfig({ hasClaude: true, isMax20: false })
 
       // #when generateModelConfig is called
       const result = generateModelConfig(config)
 
-      // #then explore should use grok-code
-      expect(result.agents?.explore?.model).toBe("opencode/grok-code")
+      // #then explore should use claude-haiku-4-5 (isMax20 doesn't affect explore)
+      expect(result.agents?.explore?.model).toBe("anthropic/claude-haiku-4-5")
     })
 
-    test("explore uses grok-code when only OpenAI available", () => {
+    test("explore uses gpt-5-nano when only OpenAI available", () => {
       // #given only OpenAI is available
       const config = createConfig({ hasOpenAI: true })
 
       // #when generateModelConfig is called
       const result = generateModelConfig(config)
 
-      // #then explore should use grok-code (fallback)
-      expect(result.agents?.explore?.model).toBe("opencode/grok-code")
+      // #then explore should use gpt-5-nano (fallback)
+      expect(result.agents?.explore?.model).toBe("opencode/gpt-5-nano")
+    })
+
+    test("explore uses gpt-5-mini when only Copilot available", () => {
+      // #given only Copilot is available
+      const config = createConfig({ hasCopilot: true })
+
+      // #when generateModelConfig is called
+      const result = generateModelConfig(config)
+
+      // #then explore should use gpt-5-mini (Copilot fallback)
+      expect(result.agents?.explore?.model).toBe("github-copilot/gpt-5-mini")
     })
   })
 
@@ -364,7 +376,7 @@ describe("generateModelConfig", () => {
       const result = generateModelConfig(config)
 
       // #then Sisyphus should use opus (sisyphus-high)
-      expect(result.agents?.Sisyphus?.model).toBe("anthropic/claude-opus-4-5")
+      expect(result.agents?.sisyphus?.model).toBe("anthropic/claude-opus-4-5")
     })
 
     test("Sisyphus uses sisyphus-low capability when isMax20 is false", () => {
@@ -375,7 +387,7 @@ describe("generateModelConfig", () => {
       const result = generateModelConfig(config)
 
       // #then Sisyphus should use sonnet (sisyphus-low)
-      expect(result.agents?.Sisyphus?.model).toBe("anthropic/claude-sonnet-4-5")
+      expect(result.agents?.sisyphus?.model).toBe("anthropic/claude-sonnet-4-5")
     })
   })
 

src/cli/model-fallback.ts

@@ -14,6 +14,7 @@ interface ProviderAvailability {
   opencodeZen: boolean
   copilot: boolean
   zai: boolean
+  kimiForCoding: boolean
   isMaxPlan: boolean
 }
 
@@ -49,6 +50,7 @@ function toProviderAvailability(config: InstallConfig): ProviderAvailability {
     opencodeZen: config.hasOpencodeZen,
     copilot: config.hasCopilot,
     zai: config.hasZaiCodingPlan,
+    kimiForCoding: config.hasKimiForCoding,
     isMaxPlan: config.isMax20,
   }
 }
@@ -61,6 +63,7 @@ function isProviderAvailable(provider: string, avail: ProviderAvailability): boo
     "github-copilot": avail.copilot,
     opencode: avail.opencodeZen,
     "zai-coding-plan": avail.zai,
+    "kimi-for-coding": avail.kimiForCoding,
   }
   return mapping[provider] ?? false
 }
@@ -97,13 +100,15 @@ function resolveModelFromChain(
 function getSisyphusFallbackChain(isMaxPlan: boolean): FallbackEntry[] {
   // Sisyphus uses opus when isMaxPlan, sonnet otherwise
   if (isMaxPlan) {
-    return AGENT_MODEL_REQUIREMENTS.Sisyphus.fallbackChain
+    return AGENT_MODEL_REQUIREMENTS.sisyphus.fallbackChain
   }
   // For non-max plan, use sonnet instead of opus
   return [
     { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" },
+    { providers: ["kimi-for-coding"], model: "k2p5" },
+    { providers: ["opencode"], model: "kimi-k2.5-free" },
     { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
-    { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro-preview" },
+    { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
   ]
 }
 
@@ -115,7 +120,8 @@ export function generateModelConfig(config: InstallConfig): GeneratedOmoConfig {
     avail.native.gemini ||
     avail.opencodeZen ||
     avail.copilot ||
-    avail.zai
+    avail.zai ||
+    avail.kimiForCoding
 
   if (!hasAnyProvider) {
     return {
@@ -139,21 +145,23 @@ export function generateModelConfig(config: InstallConfig): GeneratedOmoConfig {
       continue
     }
 
-    // Special case: explore has custom Gemini → Claude → Grok logic
+    // Special case: explore uses Claude haiku → GitHub Copilot gpt-5-mini → OpenCode gpt-5-nano
     if (role === "explore") {
-      if (avail.native.gemini) {
-        agents[role] = { model: "google/gemini-3-flash-preview" }
-      } else if (avail.native.claude && avail.isMaxPlan) {
+      if (avail.native.claude) {
         agents[role] = { model: "anthropic/claude-haiku-4-5" }
+      } else if (avail.opencodeZen) {
+        agents[role] = { model: "opencode/claude-haiku-4-5" }
+      } else if (avail.copilot) {
+        agents[role] = { model: "github-copilot/gpt-5-mini" }
       } else {
-        agents[role] = { model: "opencode/grok-code" }
+        agents[role] = { model: "opencode/gpt-5-nano" }
       }
       continue
     }
 
     // Special case: Sisyphus uses different fallbackChain based on isMaxPlan
     const fallbackChain =
-      role === "Sisyphus" ? getSisyphusFallbackChain(avail.isMaxPlan) : req.fallbackChain
+      role === "sisyphus" ? getSisyphusFallbackChain(avail.isMaxPlan) : req.fallbackChain
 
     const resolved = resolveModelFromChain(fallbackChain, avail)
     if (resolved) {

src/cli/run/events.test.ts

@@ -82,6 +82,7 @@ describe("createEventState", () => {
     expect(state.lastOutput).toBe("")
     expect(state.lastPartText).toBe("")
     expect(state.currentTool).toBe(null)
+    expect(state.hasReceivedMeaningfulWork).toBe(false)
   })
 })
 
@@ -126,6 +127,119 @@ describe("event handling", () => {
     expect(state.mainSessionIdle).toBe(false)
   })
 
+  it("hasReceivedMeaningfulWork is false initially after session.idle", async () => {
+    // #given - session goes idle without any assistant output (race condition scenario)
+    const ctx = createMockContext("my-session")
+    const state = createEventState()
+
+    const payload: EventPayload = {
+      type: "session.idle",
+      properties: { sessionID: "my-session" },
+    }
+
+    const events = toAsyncIterable([payload])
+    const { processEvents } = await import("./events")
+
+    // #when
+    await processEvents(ctx, events, state)
+
+    // #then - idle but no meaningful work yet
+    expect(state.mainSessionIdle).toBe(true)
+    expect(state.hasReceivedMeaningfulWork).toBe(false)
+  })
+
+  it("message.updated with assistant role sets hasReceivedMeaningfulWork", async () => {
+    // #given
+    const ctx = createMockContext("my-session")
+    const state = createEventState()
+
+    const payload: EventPayload = {
+      type: "message.updated",
+      properties: {
+        info: { sessionID: "my-session", role: "assistant" },
+      },
+    }
+
+    const events = toAsyncIterable([payload])
+    const { processEvents } = await import("./events")
+
+    // #when
+    await processEvents(ctx, events, state)
+
+    // #then
+    expect(state.hasReceivedMeaningfulWork).toBe(true)
+  })
+
+  it("message.updated with user role does not set hasReceivedMeaningfulWork", async () => {
+    // #given - user message should not count as meaningful work
+    const ctx = createMockContext("my-session")
+    const state = createEventState()
+
+    const payload: EventPayload = {
+      type: "message.updated",
+      properties: {
+        info: { sessionID: "my-session", role: "user" },
+      },
+    }
+
+    const events = toAsyncIterable([payload])
+    const { processEvents } = await import("./events")
+
+    // #when
+    await processEvents(ctx, events, state)
+
+    // #then - user role should not count as meaningful work
+    expect(state.hasReceivedMeaningfulWork).toBe(false)
+  })
+
+  it("tool.execute sets hasReceivedMeaningfulWork", async () => {
+    // #given
+    const ctx = createMockContext("my-session")
+    const state = createEventState()
+
+    const payload: EventPayload = {
+      type: "tool.execute",
+      properties: {
+        sessionID: "my-session",
+        name: "read_file",
+        input: { filePath: "/src/index.ts" },
+      },
+    }
+
+    const events = toAsyncIterable([payload])
+    const { processEvents } = await import("./events")
+
+    // #when
+    await processEvents(ctx, events, state)
+
+    // #then
+    expect(state.hasReceivedMeaningfulWork).toBe(true)
+  })
+
+  it("tool.execute from different session does not set hasReceivedMeaningfulWork", async () => {
+    // #given
+    const ctx = createMockContext("my-session")
+    const state = createEventState()
+
+    const payload: EventPayload = {
+      type: "tool.execute",
+      properties: {
+        sessionID: "other-session",
+        name: "read_file",
+        input: { filePath: "/src/index.ts" },
+      },
+    }
+
+    const events = toAsyncIterable([payload])
+    const { processEvents } = await import("./events")
+
+    // #when
+    await processEvents(ctx, events, state)
+
+    // #then - different session's tool call shouldn't count
+    expect(state.hasReceivedMeaningfulWork).toBe(false)
+  })
+
   it("session.status with busy type sets mainSessionIdle to false", async () => {
     // #given
     const ctx = createMockContext("my-session")
@@ -136,6 +250,7 @@ describe("event handling", () => {
       lastOutput: "",
       lastPartText: "",
       currentTool: null,
+      hasReceivedMeaningfulWork: false,
     }
 
     const payload: EventPayload = {

src/cli/run/events.ts

@@ -63,6 +63,8 @@ export interface EventState {
   lastOutput: string
   lastPartText: string
   currentTool: string | null
+  /** Set to true when the main session has produced meaningful work (text, tool call, or tool result) */
+  hasReceivedMeaningfulWork: boolean
 }
 
 export function createEventState(): EventState {
@@ -73,6 +75,7 @@ export function createEventState(): EventState {
     lastOutput: "",
     lastPartText: "",
     currentTool: null,
+    hasReceivedMeaningfulWork: false,
   }
 }
 
@@ -113,7 +116,9 @@ function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
   const isMainSession = sessionID === ctx.sessionID
   const sessionTag = isMainSession
     ? pc.green("[MAIN]")
-    : pc.yellow(`[${String(sessionID).slice(0, 8)}]`)
+    : sessionID
+      ? pc.yellow(`[${String(sessionID).slice(0, 8)}]`)
+      : pc.dim("[system]")
 
   switch (payload.type) {
     case "session.idle":
@@ -124,8 +129,6 @@ function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
     }
 
     case "message.part.updated": {
-      // Skip verbose logging for partial message updates
-      // Only log tool invocation state changes, not text streaming
       const partProps = props as MessagePartUpdatedProps | undefined
       const part = partProps?.part
       if (part?.type === "tool-invocation") {
@@ -133,6 +136,11 @@ function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
         console.error(
           pc.dim(`${sessionTag} message.part (tool): ${toolPart.toolName} [${toolPart.state}]`)
         )
+      } else if (part?.type === "text" && part.text) {
+        const preview = part.text.slice(0, 80).replace(/\n/g, "\\n")
+        console.error(
+          pc.dim(`${sessionTag} message.part (text): "${preview}${part.text.length > 80 ? "..." : ""}"`)
+        )
       }
       break
     }
@@ -140,11 +148,10 @@ function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
     case "message.updated": {
       const msgProps = props as MessageUpdatedProps | undefined
       const role = msgProps?.info?.role ?? "unknown"
-      const content = msgProps?.content ?? ""
-      const preview = content.slice(0, 100).replace(/\n/g, "\\n")
-      console.error(
-        pc.dim(`${sessionTag} message.updated (${role}): "${preview}${content.length > 100 ? "..." : ""}"`)
-      )
+      const model = msgProps?.info?.modelID
+      const agent = msgProps?.info?.agent
+      const details = [role, agent, model].filter(Boolean).join(", ")
+      console.error(pc.dim(`${sessionTag} message.updated (${details})`))
       break
     }
 
@@ -241,6 +248,7 @@ function handleMessagePartUpdated(
     const newText = part.text.slice(state.lastPartText.length)
     if (newText) {
       process.stdout.write(newText)
+      state.hasReceivedMeaningfulWork = true
     }
     state.lastPartText = part.text
   }
@@ -257,16 +265,7 @@ function handleMessageUpdated(
   if (props?.info?.sessionID !== ctx.sessionID) return
   if (props?.info?.role !== "assistant") return
 
-  const content = props.content
-  if (!content || content === state.lastOutput) return
-
-  if (state.lastPartText.length === 0) {
-    const newContent = content.slice(state.lastOutput.length)
-    if (newContent) {
-      process.stdout.write(newContent)
-    }
-  }
-  state.lastOutput = content
+  state.hasReceivedMeaningfulWork = true
 }
 
 function handleToolExecute(
@@ -296,6 +295,7 @@ function handleToolExecute(
     }
   }
 
+  state.hasReceivedMeaningfulWork = true
   process.stdout.write(`\n${pc.cyan(">")} ${pc.bold(toolName)}${inputPreview}\n`)
 }
 

src/cli/run/runner.ts

@@ -31,8 +31,18 @@ export async function run(options: RunOptions): Promise<number> {
   }
 
   try {
+    // Support custom OpenCode server port via environment variable
+    // This allows Open Agent and other orchestrators to run multiple
+    // concurrent missions without port conflicts
+    const serverPort = process.env.OPENCODE_SERVER_PORT
+      ? parseInt(process.env.OPENCODE_SERVER_PORT, 10)
+      : undefined
+    const serverHostname = process.env.OPENCODE_SERVER_HOSTNAME || undefined
+
     const { client, server } = await createOpencode({
       signal: abortController.signal,
+      ...(serverPort && !isNaN(serverPort) ? { port: serverPort } : {}),
+      ...(serverHostname ? { hostname: serverHostname } : {}),
     })
 
     const cleanup = () => {
@@ -133,6 +143,14 @@ export async function run(options: RunOptions): Promise<number> {
           process.exit(1)
         }
 
+        // Guard against premature completion: don't check completion until the
+        // session has produced meaningful work (text output, tool call, or tool result).
+        // Without this, a session that goes busy->idle before the LLM responds
+        // would exit immediately because 0 todos + 0 children = "complete".
+        if (!eventState.hasReceivedMeaningfulWork) {
+          continue
+        }
+
         const shouldExit = await checkCompletionConditions(ctx)
         if (shouldExit) {
           console.log(pc.green("\n\nAll tasks completed."))

src/cli/run/types.ts

@@ -44,8 +44,13 @@ export interface SessionStatusProps {
 }
 
 export interface MessageUpdatedProps {
-  info?: { sessionID?: string; role?: string }
-  content?: string
+  info?: {
+    sessionID?: string
+    role?: string
+    modelID?: string
+    providerID?: string
+    agent?: string
+  }
 }
 
 export interface MessagePartUpdatedProps {

src/cli/types.ts

@@ -9,6 +9,7 @@ export interface InstallArgs {
   copilot?: BooleanArg
   opencodeZen?: BooleanArg
   zaiCodingPlan?: BooleanArg
+  kimiForCoding?: BooleanArg
   skipAuth?: boolean
 }
 
@@ -20,6 +21,7 @@ export interface InstallConfig {
   hasCopilot: boolean
   hasOpencodeZen: boolean
   hasZaiCodingPlan: boolean
+  hasKimiForCoding: boolean
 }
 
 export interface ConfigMergeResult {
@@ -37,4 +39,5 @@ export interface DetectedConfig {
   hasCopilot: boolean
   hasOpencodeZen: boolean
   hasZaiCodingPlan: boolean
+  hasKimiForCoding: boolean
 }

src/config/index.ts

@@ -9,6 +9,8 @@ export {
   SisyphusAgentConfigSchema,
   ExperimentalConfigSchema,
   RalphLoopConfigSchema,
+  TmuxConfigSchema,
+  TmuxLayoutSchema,
 } from "./schema"
 
 export type {
@@ -23,4 +25,6 @@ export type {
   ExperimentalConfig,
   DynamicContextPruningConfig,
   RalphLoopConfig,
+  TmuxConfig,
+  TmuxLayout,
 } from "./schema"

src/config/schema.test.ts

@@ -1,5 +1,12 @@
 import { describe, expect, test } from "bun:test"
-import { AgentOverrideConfigSchema, BuiltinCategoryNameSchema, CategoryConfigSchema, OhMyOpenCodeConfigSchema } from "./schema"
+import {
+  AgentOverrideConfigSchema,
+  BrowserAutomationConfigSchema,
+  BrowserAutomationProviderSchema,
+  BuiltinCategoryNameSchema,
+  CategoryConfigSchema,
+  OhMyOpenCodeConfigSchema,
+} from "./schema"
 
 describe("disabled_mcps schema", () => {
   test("should accept built-in MCP names", () => {
@@ -345,6 +352,20 @@ describe("CategoryConfigSchema", () => {
     }
   })
 
+  test("accepts reasoningEffort as optional string with xhigh", () => {
+    // #given
+    const config = { reasoningEffort: "xhigh" }
+
+    // #when
+    const result = CategoryConfigSchema.safeParse(config)
+
+    // #then
+    expect(result.success).toBe(true)
+    if (result.success) {
+      expect(result.data.reasoningEffort).toBe("xhigh")
+    }
+  })
+
   test("rejects non-string variant", () => {
     // #given
     const config = { model: "openai/gpt-5.2", variant: 123 }
@@ -375,7 +396,7 @@ describe("Sisyphus-Junior agent override", () => {
     // #given
     const config = {
       agents: {
-        "Sisyphus-Junior": {
+        "sisyphus-junior": {
           model: "openai/gpt-5.2",
           temperature: 0.2,
         },
@@ -388,18 +409,18 @@ describe("Sisyphus-Junior agent override", () => {
     // #then
     expect(result.success).toBe(true)
     if (result.success) {
-      expect(result.data.agents?.["Sisyphus-Junior"]).toBeDefined()
-      expect(result.data.agents?.["Sisyphus-Junior"]?.model).toBe("openai/gpt-5.2")
-      expect(result.data.agents?.["Sisyphus-Junior"]?.temperature).toBe(0.2)
+      expect(result.data.agents?.["sisyphus-junior"]).toBeDefined()
+      expect(result.data.agents?.["sisyphus-junior"]?.model).toBe("openai/gpt-5.2")
+      expect(result.data.agents?.["sisyphus-junior"]?.temperature).toBe(0.2)
     }
   })
 
-  test("schema accepts Sisyphus-Junior with prompt_append", () => {
+  test("schema accepts sisyphus-junior with prompt_append", () => {
     // #given
     const config = {
       agents: {
-        "Sisyphus-Junior": {
-          prompt_append: "Additional instructions for Sisyphus-Junior",
+        "sisyphus-junior": {
+          prompt_append: "Additional instructions for sisyphus-junior",
         },
       },
     }
@@ -410,17 +431,17 @@ describe("Sisyphus-Junior agent override", () => {
     // #then
     expect(result.success).toBe(true)
     if (result.success) {
-      expect(result.data.agents?.["Sisyphus-Junior"]?.prompt_append).toBe(
-        "Additional instructions for Sisyphus-Junior"
+      expect(result.data.agents?.["sisyphus-junior"]?.prompt_append).toBe(
+        "Additional instructions for sisyphus-junior"
       )
     }
   })
 
-  test("schema accepts Sisyphus-Junior with tools override", () => {
+  test("schema accepts sisyphus-junior with tools override", () => {
     // #given
     const config = {
       agents: {
-        "Sisyphus-Junior": {
+        "sisyphus-junior": {
           tools: {
             read: true,
             write: false,
@@ -435,10 +456,153 @@ describe("Sisyphus-Junior agent override", () => {
     // #then
     expect(result.success).toBe(true)
     if (result.success) {
-      expect(result.data.agents?.["Sisyphus-Junior"]?.tools).toEqual({
+      expect(result.data.agents?.["sisyphus-junior"]?.tools).toEqual({
         read: true,
         write: false,
       })
     }
   })
+
+  test("schema accepts lowercase agent names (sisyphus, atlas, prometheus)", () => {
+    // #given
+    const config = {
+      agents: {
+        sisyphus: {
+          temperature: 0.1,
+        },
+        atlas: {
+          temperature: 0.2,
+        },
+        prometheus: {
+          temperature: 0.3,
+        },
+      },
+    }
+
+    // #when
+    const result = OhMyOpenCodeConfigSchema.safeParse(config)
+
+    // #then
+    expect(result.success).toBe(true)
+    if (result.success) {
+      expect(result.data.agents?.sisyphus?.temperature).toBe(0.1)
+      expect(result.data.agents?.atlas?.temperature).toBe(0.2)
+      expect(result.data.agents?.prometheus?.temperature).toBe(0.3)
+    }
+  })
+
+  test("schema accepts lowercase metis and momus agent names", () => {
+    // #given
+    const config = {
+      agents: {
+        metis: {
+          category: "ultrabrain",
+        },
+        momus: {
+          category: "quick",
+        },
+      },
+    }
+
+    // #when
+    const result = OhMyOpenCodeConfigSchema.safeParse(config)
+
+    // #then
+    expect(result.success).toBe(true)
+    if (result.success) {
+      expect(result.data.agents?.metis?.category).toBe("ultrabrain")
+      expect(result.data.agents?.momus?.category).toBe("quick")
+    }
+  })
+})
+
+describe("BrowserAutomationProviderSchema", () => {
+  test("accepts 'playwright' as valid provider", () => {
+    // #given
+    const input = "playwright"
+
+    // #when
+    const result = BrowserAutomationProviderSchema.safeParse(input)
+
+    // #then
+    expect(result.success).toBe(true)
+    expect(result.data).toBe("playwright")
+  })
+
+  test("accepts 'agent-browser' as valid provider", () => {
+    // #given
+    const input = "agent-browser"
+
+    // #when
+    const result = BrowserAutomationProviderSchema.safeParse(input)
+
+    // #then
+    expect(result.success).toBe(true)
+    expect(result.data).toBe("agent-browser")
+  })
+
+  test("rejects invalid provider", () => {
+    // #given
+    const input = "invalid-provider"
+
+    // #when
+    const result = BrowserAutomationProviderSchema.safeParse(input)
+
+    // #then
+    expect(result.success).toBe(false)
+  })
+})
+
+describe("BrowserAutomationConfigSchema", () => {
+  test("defaults provider to 'playwright' when not specified", () => {
+    // #given
+    const input = {}
+
+    // #when
+    const result = BrowserAutomationConfigSchema.parse(input)
+
+    // #then
+    expect(result.provider).toBe("playwright")
+  })
+
+  test("accepts agent-browser provider", () => {
+    // #given
+    const input = { provider: "agent-browser" }
+
+    // #when
+    const result = BrowserAutomationConfigSchema.parse(input)
+
+    // #then
+    expect(result.provider).toBe("agent-browser")
+  })
+})
+
+describe("OhMyOpenCodeConfigSchema - browser_automation_engine", () => {
+  test("accepts browser_automation_engine config", () => {
+    // #given
+    const input = {
+      browser_automation_engine: {
+        provider: "agent-browser",
+      },
+    }
+
+    // #when
+    const result = OhMyOpenCodeConfigSchema.safeParse(input)
+
+    // #then
+    expect(result.success).toBe(true)
+    expect(result.data?.browser_automation_engine?.provider).toBe("agent-browser")
+  })
+
+  test("accepts config without browser_automation_engine", () => {
+    // #given
+    const input = {}
+
+    // #when
+    const result = OhMyOpenCodeConfigSchema.safeParse(input)
+
+    // #then
+    expect(result.success).toBe(true)
+    expect(result.data?.browser_automation_engine).toBeUndefined()
+  })
 })

src/config/schema.ts

@@ -17,18 +17,20 @@ const AgentPermissionSchema = z.object({
 })
 
 export const BuiltinAgentNameSchema = z.enum([
-  "Sisyphus",
+  "sisyphus",
+  "prometheus",
   "oracle",
   "librarian",
   "explore",
   "multimodal-looker",
-  "Metis (Plan Consultant)",
-  "Momus (Plan Reviewer)",
-  "Atlas",
+  "metis",
+  "momus",
+  "atlas",
 ])
 
 export const BuiltinSkillNameSchema = z.enum([
   "playwright",
+  "agent-browser",
   "frontend-ui-ux",
   "git-master",
 ])
@@ -36,17 +38,17 @@ export const BuiltinSkillNameSchema = z.enum([
 export const OverridableAgentNameSchema = z.enum([
   "build",
   "plan",
-  "Sisyphus",
-  "Sisyphus-Junior",
+  "sisyphus",
+  "sisyphus-junior",
   "OpenCode-Builder",
-  "Prometheus (Planner)",
-  "Metis (Plan Consultant)",
-  "Momus (Plan Reviewer)",
+  "prometheus",
+  "metis",
+  "momus",
   "oracle",
   "librarian",
   "explore",
   "multimodal-looker",
-  "Atlas",
+  "atlas",
 ])
 
 export const AgentNameSchema = BuiltinAgentNameSchema
@@ -75,6 +77,7 @@ export const HookNameSchema = z.enum([
 
   "thinking-block-validator",
   "ralph-loop",
+  "category-skill-reminder",
 
   "compaction-context-injector",
   "claude-code-hooks",
@@ -82,8 +85,10 @@ export const HookNameSchema = z.enum([
   "edit-error-recovery",
   "delegate-task-retry",
   "prometheus-md-only",
+  "sisyphus-junior-notepad",
   "start-work",
   "atlas",
+  "stop-continuation-guard",
 ])
 
 export const BuiltinCommandNameSchema = z.enum([
@@ -112,22 +117,35 @@ export const AgentOverrideConfigSchema = z.object({
     .regex(/^#[0-9A-Fa-f]{6}$/)
     .optional(),
   permission: AgentPermissionSchema.optional(),
+  /** Maximum tokens for response. Passed directly to OpenCode SDK. */
+  maxTokens: z.number().optional(),
+  /** Extended thinking configuration (Anthropic). Overrides category and default settings. */
+  thinking: z.object({
+    type: z.enum(["enabled", "disabled"]),
+    budgetTokens: z.number().optional(),
+  }).optional(),
+  /** Reasoning effort level (OpenAI). Overrides category and default settings. */
+  reasoningEffort: z.enum(["low", "medium", "high", "xhigh"]).optional(),
+  /** Text verbosity level. */
+  textVerbosity: z.enum(["low", "medium", "high"]).optional(),
+  /** Provider-specific options. Passed directly to OpenCode SDK. */
+  providerOptions: z.record(z.string(), z.unknown()).optional(),
 })
 
 export const AgentOverridesSchema = z.object({
   build: AgentOverrideConfigSchema.optional(),
   plan: AgentOverrideConfigSchema.optional(),
-  Sisyphus: AgentOverrideConfigSchema.optional(),
-  "Sisyphus-Junior": AgentOverrideConfigSchema.optional(),
+  sisyphus: AgentOverrideConfigSchema.optional(),
+  "sisyphus-junior": AgentOverrideConfigSchema.optional(),
   "OpenCode-Builder": AgentOverrideConfigSchema.optional(),
-  "Prometheus (Planner)": AgentOverrideConfigSchema.optional(),
-  "Metis (Plan Consultant)": AgentOverrideConfigSchema.optional(),
-  "Momus (Plan Reviewer)": AgentOverrideConfigSchema.optional(),
+  prometheus: AgentOverrideConfigSchema.optional(),
+  metis: AgentOverrideConfigSchema.optional(),
+  momus: AgentOverrideConfigSchema.optional(),
   oracle: AgentOverrideConfigSchema.optional(),
   librarian: AgentOverrideConfigSchema.optional(),
   explore: AgentOverrideConfigSchema.optional(),
   "multimodal-looker": AgentOverrideConfigSchema.optional(),
-  Atlas: AgentOverrideConfigSchema.optional(),
+  atlas: AgentOverrideConfigSchema.optional(),
 })
 
 export const ClaudeCodeConfigSchema = z.object({
@@ -159,7 +177,7 @@ export const CategoryConfigSchema = z.object({
     type: z.enum(["enabled", "disabled"]),
     budgetTokens: z.number().optional(),
   }).optional(),
-  reasoningEffort: z.enum(["low", "medium", "high"]).optional(),
+  reasoningEffort: z.enum(["low", "medium", "high", "xhigh"]).optional(),
   textVerbosity: z.enum(["low", "medium", "high"]).optional(),
   tools: z.record(z.string(), z.boolean()).optional(),
   prompt_append: z.string().optional(),
@@ -170,6 +188,7 @@ export const CategoryConfigSchema = z.object({
 export const BuiltinCategoryNameSchema = z.enum([
   "visual-engineering",
   "ultrabrain",
+  "deep",
   "artistry",
   "quick",
   "unspecified-low",
@@ -296,6 +315,56 @@ export const GitMasterConfigSchema = z.object({
   include_co_authored_by: z.boolean().default(true),
 })
 
+export const BrowserAutomationProviderSchema = z.enum(["playwright", "agent-browser", "dev-browser"])
+
+export const BrowserAutomationConfigSchema = z.object({
+  /**
+   * Browser automation provider to use for the "playwright" skill.
+   * - "playwright": Uses Playwright MCP server (@playwright/mcp) - default
+   * - "agent-browser": Uses Vercel's agent-browser CLI (requires: bun add -g agent-browser)
+   * - "dev-browser": Uses dev-browser skill with persistent browser state
+   */
+  provider: BrowserAutomationProviderSchema.default("playwright"),
+})
+
+export const TmuxLayoutSchema = z.enum([
+  'main-horizontal',  // main pane top, agent panes bottom stack
+  'main-vertical',    // main pane left, agent panes right stack (default)
+  'tiled',            // all panes same size grid
+  'even-horizontal',  // all panes horizontal row
+  'even-vertical',    // all panes vertical stack
+])
+
+export const TmuxConfigSchema = z.object({
+  enabled: z.boolean().default(false),
+  layout: TmuxLayoutSchema.default('main-vertical'),
+  main_pane_size: z.number().min(20).max(80).default(60),
+  main_pane_min_width: z.number().min(40).default(120),
+  agent_pane_min_width: z.number().min(20).default(40),
+})
+
+export const SisyphusTasksConfigSchema = z.object({
+  /** Enable Sisyphus Tasks system (default: false) */
+  enabled: z.boolean().default(false),
+  /** Storage path for tasks (default: .sisyphus/tasks) */
+  storage_path: z.string().default(".sisyphus/tasks"),
+  /** Enable Claude Code path compatibility mode */
+  claude_code_compat: z.boolean().default(false),
+})
+
+export const SisyphusSwarmConfigSchema = z.object({
+  /** Enable Sisyphus Swarm system (default: false) */
+  enabled: z.boolean().default(false),
+  /** Storage path for teams (default: .sisyphus/teams) */
+  storage_path: z.string().default(".sisyphus/teams"),
+  /** UI mode: toast notifications, tmux panes, or both */
+  ui_mode: z.enum(["toast", "tmux", "both"]).default("toast"),
+})
+
+export const SisyphusConfigSchema = z.object({
+  tasks: SisyphusTasksConfigSchema.optional(),
+  swarm: SisyphusSwarmConfigSchema.optional(),
+})
 export const OhMyOpenCodeConfigSchema = z.object({
   $schema: z.string().optional(),
   disabled_mcps: z.array(AnyMcpNameSchema).optional(),
@@ -315,6 +384,9 @@ export const OhMyOpenCodeConfigSchema = z.object({
   background_task: BackgroundTaskConfigSchema.optional(),
   notification: NotificationConfigSchema.optional(),
   git_master: GitMasterConfigSchema.optional(),
+  browser_automation_engine: BrowserAutomationConfigSchema.optional(),
+  tmux: TmuxConfigSchema.optional(),
+  sisyphus: SisyphusConfigSchema.optional(),
 })
 
 export type OhMyOpenCodeConfig = z.infer<typeof OhMyOpenCodeConfigSchema>
@@ -337,5 +409,12 @@ export type CategoryConfig = z.infer<typeof CategoryConfigSchema>
 export type CategoriesConfig = z.infer<typeof CategoriesConfigSchema>
 export type BuiltinCategoryName = z.infer<typeof BuiltinCategoryNameSchema>
 export type GitMasterConfig = z.infer<typeof GitMasterConfigSchema>
+export type BrowserAutomationProvider = z.infer<typeof BrowserAutomationProviderSchema>
+export type BrowserAutomationConfig = z.infer<typeof BrowserAutomationConfigSchema>
+export type TmuxConfig = z.infer<typeof TmuxConfigSchema>
+export type TmuxLayout = z.infer<typeof TmuxLayoutSchema>
+export type SisyphusTasksConfig = z.infer<typeof SisyphusTasksConfigSchema>
+export type SisyphusSwarmConfig = z.infer<typeof SisyphusSwarmConfigSchema>
+export type SisyphusConfig = z.infer<typeof SisyphusConfigSchema>
 
 export { AnyMcpNameSchema, type AnyMcpName, McpNameSchema, type McpName } from "../mcp/types"

src/features/AGENTS.md

@@ -2,31 +2,31 @@
 
 ## OVERVIEW
 
-Core feature modules + Claude Code compatibility layer. Background agents, skill MCP, builtin skills/commands, 5 loaders.
+Core feature modules + Claude Code compatibility layer. Orchestrates background agents, skill MCPs, builtin skills/commands, and 16 feature modules.
 
 ## STRUCTURE
 
 ```
 features/
-├── background-agent/           # Task lifecycle (1335 lines)
+├── background-agent/           # Task lifecycle (1377 lines)
 │   ├── manager.ts              # Launch → poll → complete
-│   ├── concurrency.ts          # Per-provider limits
-│   └── types.ts                # BackgroundTask, LaunchInput
-├── skill-mcp-manager/          # MCP client lifecycle
-│   ├── manager.ts              # Lazy loading, cleanup
-│   └── types.ts                # SkillMcpConfig
-├── builtin-skills/             # Playwright, git-master, frontend-ui-ux
-│   └── skills.ts               # 1203 lines
-├── builtin-commands/           # ralph-loop, refactor, init-deep
+│   └── concurrency.ts          # Per-provider limits
+├── builtin-skills/             # Core skills (1729 lines)
+│   └── skills.ts               # agent-browser, dev-browser, frontend-ui-ux, git-master, typescript-programmer
+├── builtin-commands/           # ralph-loop, refactor, ulw-loop, init-deep, start-work, cancel-ralph
 ├── claude-code-agent-loader/   # ~/.claude/agents/*.md
 ├── claude-code-command-loader/ # ~/.claude/commands/*.md
-├── claude-code-mcp-loader/     # .mcp.json
+├── claude-code-mcp-loader/     # .mcp.json with ${VAR} expansion
 ├── claude-code-plugin-loader/  # installed_plugins.json
 ├── claude-code-session-state/  # Session persistence
 ├── opencode-skill-loader/      # Skills from 6 directories
 ├── context-injector/           # AGENTS.md/README.md injection
 ├── boulder-state/              # Todo state persistence
-└── hook-message-injector/      # Message injection
+├── hook-message-injector/      # Message injection
+├── task-toast-manager/         # Background task notifications
+├── skill-mcp-manager/          # MCP client lifecycle (520 lines)
+├── tmux-subagent/              # Tmux session management
+└── ... (16 modules total)
 ```
 
 ## LOADER PRIORITY
@@ -41,8 +41,9 @@ features/
 
 - **Lifecycle**: `launch` → `poll` (2s) → `complete`
 - **Stability**: 3 consecutive polls = idle
-- **Concurrency**: Per-provider/model limits
+- **Concurrency**: Per-provider/model limits via `ConcurrencyManager`
 - **Cleanup**: 30m TTL, 3m stale timeout
+- **State**: Per-session Maps, cleaned on `session.deleted`
 
 ## SKILL MCP
 
@@ -55,3 +56,4 @@ features/
 - **Sequential delegation**: Use `delegate_task` parallel
 - **Trust self-reports**: ALWAYS verify
 - **Main thread blocks**: No heavy I/O in loader init
+- **Direct state mutation**: Use managers for boulder/session state

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

@@ -176,8 +176,8 @@ describe("ConcurrencyManager.acquire/release", () => {
     await manager.acquire("model-a")
     await manager.acquire("model-a")
 
-    // #then - both resolved without waiting
-    expect(true).toBe(true)
+    // #then - both resolved without waiting, count should be 2
+    expect(manager.getCount("model-a")).toBe(2)
   })
 
   test("should allow acquires up to default limit of 5", async () => {
@@ -190,8 +190,8 @@ describe("ConcurrencyManager.acquire/release", () => {
     await manager.acquire("model-a")
     await manager.acquire("model-a")
 
-    // #then - all 5 resolved
-    expect(true).toBe(true)
+    // #then - all 5 resolved, count should be 5
+    expect(manager.getCount("model-a")).toBe(5)
   })
 
   test("should queue when limit reached", async () => {
@@ -276,8 +276,8 @@ describe("ConcurrencyManager.acquire/release", () => {
     manager.release("model-a")
     await manager.acquire("model-a")
 
-    // #then
-    expect(true).toBe(true)
+    // #then - count should be 1 after re-acquiring
+    expect(manager.getCount("model-a")).toBe(1)
   })
 
   test("should handle release when no acquire", () => {
@@ -288,21 +288,21 @@ describe("ConcurrencyManager.acquire/release", () => {
     // #when - release without acquire
     manager.release("model-a")
 
-    // #then - should not throw
-    expect(true).toBe(true)
+    // #then - count should be 0 (no negative count)
+    expect(manager.getCount("model-a")).toBe(0)
   })
 
   test("should handle release when no prior acquire", () => {
     // #given - default config
 
-    // #when - release without acquire
-    manager.release("model-a")
+     // #when - release without acquire
+     manager.release("model-a")
 
-    // #then - should not throw
-    expect(true).toBe(true)
-  })
+     // #then - count should be 0 (no negative count)
+     expect(manager.getCount("model-a")).toBe(0)
+   })
 
-  test("should handle multiple acquires and releases correctly", async () => {
+   test("should handle multiple acquires and releases correctly", async () => {
     // #given
     const config: BackgroundTaskConfig = { defaultConcurrency: 3 }
     manager = new ConcurrencyManager(config)
@@ -317,11 +317,11 @@ describe("ConcurrencyManager.acquire/release", () => {
     manager.release("model-a")
     manager.release("model-a")
 
-    // Should be able to acquire again
-    await manager.acquire("model-a")
+     // Should be able to acquire again
+     await manager.acquire("model-a")
 
-    // #then
-    expect(true).toBe(true)
+     // #then - count should be 1 after re-acquiring
+     expect(manager.getCount("model-a")).toBe(1)
   })
 
   test("should use model-specific limit for acquire", async () => {

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

@@ -170,6 +170,7 @@ function createBackgroundManager(): BackgroundManager {
   const client = {
     session: {
       prompt: async () => ({}),
+      abort: async () => ({}),
     },
   }
   return new BackgroundManager({ client, directory: tmpdir() } as unknown as PluginInput)
@@ -776,7 +777,7 @@ describe("BackgroundManager.notifyParentSession - dynamic message lookup", () =>
       parentModel: { providerID: "old", modelID: "old-model" },
     }
     const currentMessage: CurrentMessage = {
-      agent: "Sisyphus",
+      agent: "sisyphus",
       model: { providerID: "anthropic", modelID: "claude-opus-4-5" },
     }
 
@@ -784,7 +785,7 @@ describe("BackgroundManager.notifyParentSession - dynamic message lookup", () =>
     const promptBody = buildNotificationPromptBody(task, currentMessage)
 
     // #then - uses currentMessage values, not task.parentModel/parentAgent
-    expect(promptBody.agent).toBe("Sisyphus")
+    expect(promptBody.agent).toBe("sisyphus")
     expect(promptBody.model).toEqual({ providerID: "anthropic", modelID: "claude-opus-4-5" })
   })
 
@@ -827,11 +828,11 @@ describe("BackgroundManager.notifyParentSession - dynamic message lookup", () =>
       status: "completed",
       startedAt: new Date(),
       completedAt: new Date(),
-      parentAgent: "Sisyphus",
+      parentAgent: "sisyphus",
       parentModel: { providerID: "anthropic", modelID: "claude-opus" },
     }
     const currentMessage: CurrentMessage = {
-      agent: "Sisyphus",
+      agent: "sisyphus",
       model: { providerID: "anthropic" },
     }
 
@@ -839,7 +840,7 @@ describe("BackgroundManager.notifyParentSession - dynamic message lookup", () =>
     const promptBody = buildNotificationPromptBody(task, currentMessage)
 
     // #then - model not passed due to incomplete data
-    expect(promptBody.agent).toBe("Sisyphus")
+    expect(promptBody.agent).toBe("sisyphus")
     expect("model" in promptBody).toBe(false)
   })
 
@@ -856,7 +857,7 @@ describe("BackgroundManager.notifyParentSession - dynamic message lookup", () =>
       status: "completed",
       startedAt: new Date(),
       completedAt: new Date(),
-      parentAgent: "Sisyphus",
+      parentAgent: "sisyphus",
       parentModel: { providerID: "anthropic", modelID: "claude-opus" },
     }
 
@@ -864,7 +865,7 @@ describe("BackgroundManager.notifyParentSession - dynamic message lookup", () =>
     const promptBody = buildNotificationPromptBody(task, null)
 
     // #then - falls back to task.parentAgent, no model
-    expect(promptBody.agent).toBe("Sisyphus")
+    expect(promptBody.agent).toBe("sisyphus")
     expect("model" in promptBody).toBe(false)
   })
 })
@@ -1053,6 +1054,7 @@ describe("BackgroundManager.resume model persistence", () => {
           promptCalls.push(args)
           return {}
         },
+        abort: async () => ({}),
       },
     }
     manager = new BackgroundManager({ client, directory: tmpdir() } as unknown as PluginInput)
@@ -1926,3 +1928,254 @@ describe("BackgroundManager.checkAndInterruptStaleTasks", () => {
   })
 })
 
+describe("BackgroundManager.shutdown session abort", () => {
+  test("should call session.abort for all running tasks during shutdown", () => {
+    // #given
+    const abortedSessionIDs: string[] = []
+    const client = {
+      session: {
+        prompt: async () => ({}),
+        abort: async (args: { path: { id: string } }) => {
+          abortedSessionIDs.push(args.path.id)
+          return {}
+        },
+      },
+    }
+    const manager = new BackgroundManager({ client, directory: tmpdir() } as unknown as PluginInput)
+
+    const task1: BackgroundTask = {
+      id: "task-1",
+      sessionID: "session-1",
+      parentSessionID: "parent-1",
+      parentMessageID: "msg-1",
+      description: "Running task 1",
+      prompt: "Test",
+      agent: "test-agent",
+      status: "running",
+      startedAt: new Date(),
+    }
+    const task2: BackgroundTask = {
+      id: "task-2",
+      sessionID: "session-2",
+      parentSessionID: "parent-2",
+      parentMessageID: "msg-2",
+      description: "Running task 2",
+      prompt: "Test",
+      agent: "test-agent",
+      status: "running",
+      startedAt: new Date(),
+    }
+
+    getTaskMap(manager).set(task1.id, task1)
+    getTaskMap(manager).set(task2.id, task2)
+
+    // #when
+    manager.shutdown()
+
+    // #then
+    expect(abortedSessionIDs).toContain("session-1")
+    expect(abortedSessionIDs).toContain("session-2")
+    expect(abortedSessionIDs).toHaveLength(2)
+  })
+
+  test("should not call session.abort for completed or cancelled tasks", () => {
+    // #given
+    const abortedSessionIDs: string[] = []
+    const client = {
+      session: {
+        prompt: async () => ({}),
+        abort: async (args: { path: { id: string } }) => {
+          abortedSessionIDs.push(args.path.id)
+          return {}
+        },
+      },
+    }
+    const manager = new BackgroundManager({ client, directory: tmpdir() } as unknown as PluginInput)
+
+    const completedTask: BackgroundTask = {
+      id: "task-completed",
+      sessionID: "session-completed",
+      parentSessionID: "parent-1",
+      parentMessageID: "msg-1",
+      description: "Completed task",
+      prompt: "Test",
+      agent: "test-agent",
+      status: "completed",
+      startedAt: new Date(),
+      completedAt: new Date(),
+    }
+    const cancelledTask: BackgroundTask = {
+      id: "task-cancelled",
+      sessionID: "session-cancelled",
+      parentSessionID: "parent-2",
+      parentMessageID: "msg-2",
+      description: "Cancelled task",
+      prompt: "Test",
+      agent: "test-agent",
+      status: "cancelled",
+      startedAt: new Date(),
+      completedAt: new Date(),
+    }
+    const pendingTask: BackgroundTask = {
+      id: "task-pending",
+      parentSessionID: "parent-3",
+      parentMessageID: "msg-3",
+      description: "Pending task",
+      prompt: "Test",
+      agent: "test-agent",
+      status: "pending",
+      queuedAt: new Date(),
+    }
+
+    getTaskMap(manager).set(completedTask.id, completedTask)
+    getTaskMap(manager).set(cancelledTask.id, cancelledTask)
+    getTaskMap(manager).set(pendingTask.id, pendingTask)
+
+    // #when
+    manager.shutdown()
+
+    // #then
+    expect(abortedSessionIDs).toHaveLength(0)
+  })
+
+  test("should call onShutdown callback during shutdown", () => {
+    // #given
+    let shutdownCalled = false
+    const client = {
+      session: {
+        prompt: async () => ({}),
+        abort: async () => ({}),
+      },
+    }
+    const manager = new BackgroundManager(
+      { client, directory: tmpdir() } as unknown as PluginInput,
+      undefined,
+      {
+        onShutdown: () => {
+          shutdownCalled = true
+        },
+      }
+    )
+
+    // #when
+    manager.shutdown()
+
+    // #then
+    expect(shutdownCalled).toBe(true)
+  })
+
+  test("should not throw when onShutdown callback throws", () => {
+    // #given
+    const client = {
+      session: {
+        prompt: async () => ({}),
+        abort: async () => ({}),
+      },
+    }
+    const manager = new BackgroundManager(
+      { client, directory: tmpdir() } as unknown as PluginInput,
+      undefined,
+      {
+        onShutdown: () => {
+          throw new Error("cleanup failed")
+        },
+      }
+    )
+
+    // #when / #then
+    expect(() => manager.shutdown()).not.toThrow()
+  })
+})
+
+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

@@ -5,9 +5,10 @@ import type {
   LaunchInput,
   ResumeInput,
 } from "./types"
-import { log, getAgentToolRestrictions } from "../../shared"
+import { log, getAgentToolRestrictions, promptWithModelSuggestionRetry } from "../../shared"
 import { ConcurrencyManager } from "./concurrency"
-import type { BackgroundTaskConfig } from "../../config/schema"
+import type { BackgroundTaskConfig, TmuxConfig } from "../../config/schema"
+import { isInsideTmux } from "../../shared/tmux"
 
 import { subagentSessions } from "../claude-code-session-state"
 import { getTaskToastManager } from "../task-toast-manager"
@@ -54,6 +55,14 @@ interface QueueItem {
   input: LaunchInput
 }
 
+export interface SubagentSessionCreatedEvent {
+  sessionID: string
+  parentID: string
+  title: string
+}
+
+export type OnSubagentSessionCreated = (event: SubagentSessionCreatedEvent) => Promise<void>
+
 export class BackgroundManager {
   private static cleanupManagers = new Set<BackgroundManager>()
   private static cleanupRegistered = false
@@ -68,12 +77,23 @@ export class BackgroundManager {
   private concurrencyManager: ConcurrencyManager
   private shutdownTriggered = false
   private config?: BackgroundTaskConfig
-
+  private tmuxEnabled: boolean
+  private onSubagentSessionCreated?: OnSubagentSessionCreated
+  private onShutdown?: () => void
 
   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, config?: BackgroundTaskConfig) {
+  constructor(
+    ctx: PluginInput,
+    config?: BackgroundTaskConfig,
+    options?: {
+      tmuxConfig?: TmuxConfig
+      onSubagentSessionCreated?: OnSubagentSessionCreated
+      onShutdown?: () => void
+    }
+  ) {
     this.tasks = new Map()
     this.notifications = new Map()
     this.pendingByParent = new Map()
@@ -81,6 +101,9 @@ export class BackgroundManager {
     this.directory = ctx.directory
     this.concurrencyManager = new ConcurrencyManager(config)
     this.config = config
+    this.tmuxEnabled = options?.tmuxConfig?.enabled ?? false
+    this.onSubagentSessionCreated = options?.onSubagentSessionCreated
+    this.onShutdown = options?.onShutdown
     this.registerProcessCleanup()
   }
 
@@ -205,7 +228,10 @@ export class BackgroundManager {
       body: {
         parentID: input.parentSessionID,
         title: `Background: ${input.description}`,
-      },
+        permission: [
+          { permission: "question", action: "deny" as const, pattern: "*" },
+        ],
+      } as any,
       query: {
         directory: parentDirectory,
       },
@@ -222,6 +248,29 @@ export class BackgroundManager {
     const sessionID = createResult.data.id
     subagentSessions.add(sessionID)
 
+    log("[background-agent] tmux callback check", {
+      hasCallback: !!this.onSubagentSessionCreated,
+      tmuxEnabled: this.tmuxEnabled,
+      isInsideTmux: isInsideTmux(),
+      sessionID,
+      parentID: input.parentSessionID,
+    })
+
+    if (this.onSubagentSessionCreated && this.tmuxEnabled && isInsideTmux()) {
+      log("[background-agent] Invoking tmux callback NOW", { sessionID })
+      await this.onSubagentSessionCreated({
+        sessionID,
+        parentID: input.parentSessionID,
+        title: input.description,
+      }).catch((err) => {
+        log("[background-agent] Failed to spawn tmux pane:", err)
+      })
+      log("[background-agent] tmux callback completed, waiting 200ms")
+      await new Promise(r => setTimeout(r, 200))
+    } else {
+      log("[background-agent] SKIP tmux callback - conditions not met")
+    }
+
     // Update task to running state
     task.status = "running"
     task.startedAt = new Date()
@@ -252,17 +301,26 @@ export class BackgroundManager {
 
     // Use prompt() instead of promptAsync() to properly initialize agent loop (fire-and-forget)
     // Include model if caller provided one (e.g., from Sisyphus category configs)
-    this.client.session.prompt({
+    // IMPORTANT: variant must be a top-level field in the body, NOT nested inside model
+    // OpenCode's PromptInput schema expects: { model: { providerID, modelID }, variant: "max" }
+    const launchModel = input.model
+      ? { providerID: input.model.providerID, modelID: input.model.modelID }
+      : undefined
+    const launchVariant = input.model?.variant
+
+    promptWithModelSuggestionRetry(this.client, {
       path: { id: sessionID },
       body: {
         agent: input.agent,
-        ...(input.model ? { model: input.model } : {}),
+        ...(launchModel ? { model: launchModel } : {}),
+        ...(launchVariant ? { variant: launchVariant } : {}),
         system: input.skillContent,
         tools: {
           ...getAgentToolRestrictions(input.agent),
           task: false,
           delegate_task: false,
           call_omo_agent: true,
+          question: false,
         },
         parts: [{ type: "text", text: input.prompt }],
       },
@@ -499,16 +557,24 @@ export class BackgroundManager {
 
     // Use prompt() instead of promptAsync() to properly initialize agent loop
     // Include model if task has one (preserved from original launch with category config)
+    // variant must be top-level in body, not nested inside model (OpenCode PromptInput schema)
+    const resumeModel = existingTask.model
+      ? { providerID: existingTask.model.providerID, modelID: existingTask.model.modelID }
+      : undefined
+    const resumeVariant = existingTask.model?.variant
+
     this.client.session.prompt({
       path: { id: existingTask.sessionID },
       body: {
         agent: existingTask.agent,
-        ...(existingTask.model ? { model: existingTask.model } : {}),
+        ...(resumeModel ? { model: resumeModel } : {}),
+        ...(resumeVariant ? { variant: resumeVariant } : {}),
         tools: {
           ...getAgentToolRestrictions(existingTask.agent),
           task: false,
           delegate_task: false,
           call_omo_agent: true,
+          question: false,
         },
         parts: [{ type: "text", text: input.prompt }],
       },
@@ -643,7 +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)
@@ -1008,14 +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 {
@@ -1284,7 +1355,25 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
     log("[background-agent] Shutting down BackgroundManager")
     this.stopPolling()
 
-    // Release concurrency for all running tasks first
+    // Abort all running sessions to prevent zombie processes (#1240)
+    for (const task of this.tasks.values()) {
+      if (task.status === "running" && task.sessionID) {
+        this.client.session.abort({
+          path: { id: task.sessionID },
+        }).catch(() => {})
+      }
+    }
+
+    // Notify shutdown listeners (e.g., tmux cleanup)
+    if (this.onShutdown) {
+      try {
+        this.onShutdown()
+      } catch (error) {
+        log("[background-agent] Error in onShutdown callback:", error)
+      }
+    }
+
+    // Release concurrency for all running tasks
     for (const task of this.tasks.values()) {
       if (task.concurrencyKey) {
         this.concurrencyManager.release(task.concurrencyKey)
@@ -1292,7 +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()
@@ -1313,7 +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"
 
@@ -55,7 +56,7 @@ ${REFACTOR_TEMPLATE}
   },
   "start-work": {
     description: "(builtin) Start Sisyphus work session from Prometheus plan",
-    agent: "Atlas",
+    agent: "atlas",
     template: `<command-instruction>
 ${START_WORK_TEMPLATE}
 </command-instruction>
@@ -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(
@@ -81,7 +88,7 @@ export function loadBuiltinCommands(
   for (const [name, definition] of Object.entries(BUILTIN_COMMAND_DEFINITIONS)) {
     if (!disabled.has(name as BuiltinCommandName)) {
       const { argumentHint: _argumentHint, ...openCodeCompatible } = definition
-      commands[name] = openCodeCompatible as CommandDefinition
+      commands[name] = { ...openCodeCompatible, name } as CommandDefinition
     }
   }
 

src/features/builtin-commands/templates/ralph-loop.ts

@@ -17,7 +17,7 @@ export const RALPH_LOOP_TEMPLATE = `You are starting a Ralph Loop - a self-refer
 
 ## Exit Conditions
 
-1. **Completion**: Output \`<promise>DONE</promise>\` (or custom promise text) when fully complete
+1. **Completion**: Output your completion promise tag when fully complete
 2. **Max Iterations**: Loop stops automatically at limit
 3. **Cancel**: User runs \`/cancel-ralph\` command