release: v3.0.1

All documentation, agent prompts, and skill descriptions were still
referencing the old 'skills' parameter name for delegate_task, but the
tool implementation requires 'load_skills' (renamed in commit aa2b052).
This caused confusion and errors for users following the docs.

Fixes #1008

Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>

.github/workflows/publish-platform.yml

@@ -29,7 +29,12 @@ permissions:
 
 jobs:
   publish-platform:
-    runs-on: ubuntu-latest
+    # Use windows-latest for Windows to avoid cross-compilation segfault (oven-sh/bun#18416)
+    # Fixes: #873, #844
+    runs-on: ${{ matrix.platform == 'windows-x64' && 'windows-latest' || 'ubuntu-latest' }}
+    defaults:
+      run:
+        shell: bash
     strategy:
       fail-fast: false
       max-parallel: 2

.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>

AGENTS.md

@@ -1,12 +1,12 @@
 # PROJECT KNOWLEDGE BASE
 
-**Generated:** 2026-01-23T02:09:00+09:00
-**Commit:** 0e18efc7
+**Generated:** 2026-01-25T13:10:00+09:00
+**Commit:** 043b1a33
 **Branch:** dev
 
 ## 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, GLM-4.7). 31 lifecycle hooks, 20+ tools (LSP, AST-Grep, delegation), 10 specialized agents, full Claude Code compatibility. "oh-my-zsh" for OpenCode.
 
 ## STRUCTURE
 
@@ -21,7 +21,7 @@ oh-my-opencode/
 │   ├── 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 (601 lines)
 ├── script/            # build-schema.ts, build-binaries.ts
 ├── packages/          # 7 platform-specific binaries
 └── dist/              # Build output (ESM + .d.ts)
@@ -36,9 +36,10 @@ 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) |
+| Orchestrator | `src/hooks/atlas/` | Main orchestration hook (773 lines) |
 
 ## TDD (Test-Driven Development)
 
@@ -60,7 +61,7 @@ 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, 95 test files
 - **Temperature**: 0.1 for code agents, max 0.3
 
 ## ANTI-PATTERNS
@@ -88,8 +89,8 @@ oh-my-opencode/
 | Sisyphus | anthropic/claude-opus-4-5 | Primary orchestrator |
 | Atlas | anthropic/claude-opus-4-5 | Master orchestrator |
 | oracle | openai/gpt-5.2 | Consultation, debugging |
-| librarian | opencode/glm-4.7-free | Docs, GitHub search |
-| explore | opencode/grok-code | Fast codebase grep |
+| librarian | opencode/big-pickle | Docs, GitHub search |
+| explore | opencode/gpt-5-nano | Fast codebase grep |
 | multimodal-looker | google/gemini-3-flash | PDF/image analysis |
 | Prometheus | anthropic/claude-opus-4-5 | Strategic planning |
 
@@ -99,7 +100,7 @@ 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               # 95 test files
 ```
 
 ## DEPLOYMENT
@@ -113,12 +114,16 @@ 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/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` | 1039 | Category-based delegation |
+| `src/hooks/atlas/index.ts` | 773 | Orchestrator hook |
+| `src/cli/config-manager.ts` | 664 | JSONC config parsing |
+| `src/features/builtin-commands/templates/refactor.ts` | 619 | Refactor command template |
+| `src/index.ts` | 601 | Main plugin entry |
+| `src/tools/lsp/client.ts` | 596 | LSP JSON-RPC client |
+| `src/agents/atlas.ts` | 572 | Atlas orchestrator agent |
 
 ## 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>
 

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> -->

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!
 >

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>
 

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"
         ]
       }
     },
@@ -345,7 +346,7 @@
             }
           }
         },
-        "Sisyphus": {
+        "sisyphus": {
           "type": "object",
           "properties": {
             "model": {
@@ -471,7 +472,7 @@
             }
           }
         },
-        "Sisyphus-Junior": {
+        "sisyphus-junior": {
           "type": "object",
           "properties": {
             "model": {
@@ -723,7 +724,7 @@
             }
           }
         },
-        "Prometheus (Planner)": {
+        "prometheus": {
           "type": "object",
           "properties": {
             "model": {
@@ -849,7 +850,7 @@
             }
           }
         },
-        "Metis (Plan Consultant)": {
+        "metis": {
           "type": "object",
           "properties": {
             "model": {
@@ -975,7 +976,7 @@
             }
           }
         },
-        "Momus (Plan Reviewer)": {
+        "momus": {
           "type": "object",
           "properties": {
             "model": {
@@ -1605,7 +1606,7 @@
             }
           }
         },
-        "Atlas": {
+        "atlas": {
           "type": "object",
           "properties": {
             "model": {
@@ -1786,7 +1787,8 @@
             "enum": [
               "low",
               "medium",
-              "high"
+              "high",
+              "xhigh"
             ]
           },
           "textVerbosity": {

bun.lock

@@ -27,13 +27,13 @@
         "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": "3.0.0",
+        "oh-my-opencode-darwin-x64": "3.0.0",
+        "oh-my-opencode-linux-arm64": "3.0.0",
+        "oh-my-opencode-linux-arm64-musl": "3.0.0",
+        "oh-my-opencode-linux-x64": "3.0.0",
+        "oh-my-opencode-linux-x64-musl": "3.0.0",
+        "oh-my-opencode-windows-x64": "3.0.0",
       },
     },
   },
@@ -225,19 +225,19 @@
 
     "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@3.0.0", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-zelvb7qz5GsS+Dhyz9rACZrkUMtWbAZGijiHSQqmRcjlN/sRPNhXtsL55VheDjlPM3VP+t3+psv+se0WA/aw5w=="],
 
-    "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@3.0.0", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-dRMD1U5zIrb6BsiKQJZtAFtuD8clAQquZyU2LajMoFTHBNhcBDIgsaBBwvMBIq7dTe8rnFq91ExiFA8OfdrzBA=="],
 
-    "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@3.0.0", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-Wx6Cx2Nu2T69mfZa3FQ3gk0OFONvMh48rMVYK0Cp8VX5W4Zb/GZgTUFmZlYsApyxqP+7J9m18skd46qPOhzuEQ=="],
 
-    "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@3.0.0", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-mfOlptgLoXLVuhFRcXgZU7BYGuL1axZOMOOjONgncNzOp/BQYU5B9BRFihBUXdDsWGmeMiLowrYGBhVpSv3NlA=="],
 
-    "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@3.0.0", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-vVjshfaz0UC9NrGD9FfjlYK5NvckIW0sZaE/wRv/LKjrukHFH1jJpJa5KKXxBWLsEJjt6ooJRguXXxtfNXpAWw=="],
 
-    "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@3.0.0", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-N6cNJ7+Dj0a5dWqPf6OKfB39o8HWw5HQ3hB4omgYqc6Gzo6nChA4KIiVefEC3+tIL98x4XvMeD7OU+UYgwxHnQ=="],
 
-    "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@3.0.0", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-TaC0hiHpnsS42GWTVUKoTwCb+QzNLBlQtTkIQ0PjlkDYFjlEC2LuR2FFcscik055PRRIGishyB9A1n/8XAgcvA=="],
 
     "on-finished": ["on-finished@2.4.1", "", { "dependencies": { "ee-first": "1.1.1" } }, "sha512-oVlzkg3ENAhCk2zdv7IJwd/QUD4z2RxRwpkcGY8psCVcCYZNq4wYnVWALHM+brtuJjePWiYF/ClmuDr8Ch5+kg=="],
 

docs/category-skill-guide.md

@@ -21,13 +21,13 @@ 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 |
+| `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 +70,12 @@ 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 +110,17 @@ 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 +131,7 @@ 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 +177,7 @@ 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

@@ -175,7 +175,7 @@ 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",
     },
   },
 }

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 +83,7 @@ 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).
 
 ## Agents
 
@@ -127,7 +160,7 @@ Available agents: `oracle`, `librarian`, `explore`, `multimodal-looker`
 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.
+- **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`:
 
@@ -272,7 +305,7 @@ Categories enable domain-specific task delegation via the `delegate_task` tool.
 
 | Category         | Model                         | Description                                                                  |
 | ---------------- | ----------------------------- | ---------------------------------------------------------------------------- |
-| `visual`         | `google/gemini-3-pro-preview` | Frontend, UI/UX, design-focused tasks. High creativity (temp 0.7).           |
+| `visual`         | `google/gemini-3-pro` | 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). |
 
 **Usage:**
@@ -299,7 +332,7 @@ Add custom categories in `oh-my-opencode.json`:
       "prompt_append": "Focus on data analysis, ML pipelines, and statistical methods."
     },
     "visual": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3-pro",
       "prompt_append": "Use shadcn/ui components and Tailwind CSS."
     }
   }
@@ -370,9 +403,9 @@ Each agent has a defined provider priority chain. The system tries providers in
 |-------|-------------------|-------------------------|
 | **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 |
+| **librarian** | `big-pickle` | opencode → github-copilot → anthropic |
+| **explore** | `gpt-5-nano` | anthropic → opencode |
+| **multimodal-looker** | `gemini-3-flash` | google → openai → zai-coding-plan → anthropic → 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 |
@@ -384,13 +417,13 @@ 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 |
+| **visual-engineering** | `gemini-3-pro` | 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 |
+| **artistry** | `gemini-3-pro` | 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 |
+| **writing** | `gemini-3-flash` | google → openai → anthropic → github-copilot → opencode |
 
 ### Checking Your Configuration
 

docs/features.md

@@ -12,8 +12,8 @@ Oh-My-OpenCode provides 10 specialized AI agents. Each has distinct expertise, o
 |-------|-------|---------|
 | **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). |
 | **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. |
+| **librarian** | `opencode/big-pickle` | Multi-repo analysis, documentation lookup, OSS implementation examples. Deep codebase understanding with evidence-based answers. Inspired by AmpCode. |
+| **explore** | `opencode/gpt-5-nano` | 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. |
 
 ### Planning Agents

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/big-pickle`.
 
 When OpenCode Zen is the best available provider (no native or Copilot), these models are used:
 
@@ -211,8 +221,8 @@ 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`             |
-| **Librarian** | `opencode/glm-4.7-free`          |
+| **Explore**   | `opencode/gpt-5-nano`             |
+| **Librarian** | `opencode/big-pickle`          |
 
 ##### Setup
 

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)
   },

package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "3.0.0-beta.13",
+  "version": "3.0.1",
   "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",
@@ -73,13 +73,13 @@
     "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": "3.0.1",
+    "oh-my-opencode-darwin-x64": "3.0.1",
+    "oh-my-opencode-linux-arm64": "3.0.1",
+    "oh-my-opencode-linux-arm64-musl": "3.0.1",
+    "oh-my-opencode-linux-x64": "3.0.1",
+    "oh-my-opencode-linux-x64-musl": "3.0.1",
+    "oh-my-opencode-windows-x64": "3.0.1"
   },
   "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": "3.0.1",
   "description": "Platform-specific binary for oh-my-opencode (darwin-arm64)",
   "license": "MIT",
   "repository": {

packages/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-x64",
-  "version": "3.0.0-beta.13",
+  "version": "3.0.1",
   "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": "3.0.1",
   "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": "3.0.1",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64)",
   "license": "MIT",
   "repository": {

packages/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-musl",
-  "version": "3.0.0-beta.13",
+  "version": "3.0.1",
   "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": "3.0.1",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64)",
   "license": "MIT",
   "repository": {

packages/windows-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-windows-x64",
-  "version": "3.0.0-beta.13",
+  "version": "3.0.1",
   "description": "Platform-specific binary for oh-my-opencode (windows-x64)",
   "license": "MIT",
   "repository": {

signatures/cla.json

@@ -711,6 +711,110 @@
       "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
     }
   ]
 }

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

@@ -8,17 +8,17 @@
 
 ```
 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 (572 lines)
+├── sisyphus.ts                 # Main prompt (450 lines)
+├── sisyphus-junior.ts          # Delegated task executor (135 lines)
+├── dynamic-agent-prompt-builder.ts  # Dynamic prompt generation (359 lines)
 ├── oracle.ts                   # Strategic advisor (GPT-5.2)
-├── librarian.ts                # Multi-repo research (GLM-4.7-free)
+├── librarian.ts                # Multi-repo research (326 lines)
 ├── explore.ts                  # Fast 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
+├── metis.ts                    # Plan consultant (315 lines)
+├── momus.ts                    # Plan reviewer (444 lines)
 ├── types.ts                    # AgentModelConfig, AgentPromptMetadata
 ├── utils.ts                    # createBuiltinAgents(), resolveModelWithFallback()
 └── index.ts                    # builtinAgents export
@@ -31,8 +31,8 @@ agents/
 | Sisyphus | anthropic/claude-opus-4-5 | 0.1 | Primary orchestrator |
 | Atlas | anthropic/claude-opus-4-5 | 0.1 | Master orchestrator |
 | 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 | opencode/big-pickle | 0.1 | Docs, GitHub search |
+| explore | opencode/gpt-5-nano | 0.1 | Fast contextual grep |
 | 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 |

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") {

src/agents/sisyphus.ts

@@ -144,11 +144,11 @@ ${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 +205,34 @@ 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)

src/agents/types.ts

@@ -57,14 +57,14 @@ 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

@@ -12,46 +12,46 @@ 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 first fallback entry when no availableModels provided (no cache scenario)", async () => {
+    // #given - no available models simulates CI without model cache
 
     // #when
     const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
 
-    // #then - Oracle first fallbackChain entry is openai/gpt-5.2
+    // #then - uses first fallback entry (openai/gpt-5.2) instead of system default
     expect(agents.oracle.model).toBe("openai/gpt-5.2")
     expect(agents.oracle.reasoningEffort).toBe("medium")
     expect(agents.oracle.textVerbosity).toBe("high")
@@ -90,19 +90,19 @@ 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("buildAgent with category and skills", () => {
@@ -123,7 +123,7 @@ 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", () => {

src/agents/utils.ts

@@ -19,16 +19,16 @@ import type { LoadedSkill, SkillScope } from "../features/opencode-skill-loader/
 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,
 }
 
 /**
@@ -139,7 +139,7 @@ function mapScopeToLocation(scope: SkillScope): AvailableSkill["location"] {
 }
 
 export async function createBuiltinAgents(
-  disabledAgents: BuiltinAgentName[] = [],
+  disabledAgents: string[] = [],
   agentOverrides: AgentOverrides = {},
   directory?: string,
   systemDefaultModel?: string,
@@ -186,18 +186,18 @@ 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 (includesCaseInsensitive(disabledAgents, agentName)) continue
 
     const override = findCaseInsensitive(agentOverrides, agentName)
     const requirement = AGENT_MODEL_REQUIREMENTS[agentName]
     
     // Use resolver to determine model
-    const { model } = resolveModelWithFallback({
+    const { model, variant: resolvedVariant } = resolveModelWithFallback({
       userModel: override?.model,
       fallbackChain: requirement?.fallbackChain,
       availableModels,
@@ -206,11 +206,11 @@ export async function createBuiltinAgents(
 
     let config = buildAgent(source, model, mergedCategories, gitMasterConfig)
     
-    // Apply variant from override or requirement
+    // Apply variant from override or resolved fallback chain
     if (override?.variant) {
       config = { ...config, variant: override.variant }
-    } else if (requirement?.variant) {
-      config = { ...config, variant: requirement.variant }
+    } else if (resolvedVariant) {
+      config = { ...config, variant: resolvedVariant }
     }
 
     if (agentName === "librarian" && directory && config.prompt) {
@@ -234,12 +234,12 @@ 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 { model: sisyphusModel, variant: sisyphusResolvedVariant } = resolveModelWithFallback({
       userModel: sisyphusOverride?.model,
       fallbackChain: sisyphusRequirement?.fallbackChain,
       availableModels,
@@ -254,11 +254,11 @@ export async function createBuiltinAgents(
       availableCategories
     )
     
-    // Apply variant from override or requirement
+    // Apply variant from override or resolved fallback chain
     if (sisyphusOverride?.variant) {
       sisyphusConfig = { ...sisyphusConfig, variant: sisyphusOverride.variant }
-    } else if (sisyphusRequirement?.variant) {
-      sisyphusConfig = { ...sisyphusConfig, variant: sisyphusRequirement.variant }
+    } else if (sisyphusResolvedVariant) {
+      sisyphusConfig = { ...sisyphusConfig, variant: sisyphusResolvedVariant }
     }
 
     if (directory && sisyphusConfig.prompt) {
@@ -270,15 +270,15 @@ export async function createBuiltinAgents(
       sisyphusConfig = mergeAgentConfig(sisyphusConfig, sisyphusOverride)
     }
 
-    result["Sisyphus"] = sisyphusConfig
-  }
+     result["sisyphus"] = sisyphusConfig
+   }
 
-  if (!disabledAgents.includes("Atlas")) {
-    const orchestratorOverride = agentOverrides["Atlas"]
-    const atlasRequirement = AGENT_MODEL_REQUIREMENTS["Atlas"]
+   if (!disabledAgents.includes("atlas")) {
+     const orchestratorOverride = agentOverrides["atlas"]
+     const atlasRequirement = AGENT_MODEL_REQUIREMENTS["atlas"]
     
     // Use resolver to determine model
-    const { model: atlasModel } = resolveModelWithFallback({
+    const { model: atlasModel, variant: atlasResolvedVariant } = resolveModelWithFallback({
       userModel: orchestratorOverride?.model,
       fallbackChain: atlasRequirement?.fallbackChain,
       availableModels,
@@ -292,19 +292,19 @@ export async function createBuiltinAgents(
       userCategories: categories,
     })
     
-    // Apply variant from override or requirement
+    // Apply variant from override or resolved fallback chain
     if (orchestratorOverride?.variant) {
       orchestratorConfig = { ...orchestratorConfig, variant: orchestratorOverride.variant }
-    } else if (atlasRequirement?.variant) {
-      orchestratorConfig = { ...orchestratorConfig, variant: atlasRequirement.variant }
+    } else if (atlasResolvedVariant) {
+      orchestratorConfig = { ...orchestratorConfig, variant: atlasResolvedVariant }
     }
 
     if (orchestratorOverride) {
       orchestratorConfig = mergeAgentConfig(orchestratorConfig, orchestratorOverride)
     }
 
-    result["Atlas"] = orchestratorConfig
-  }
+     result["atlas"] = orchestratorConfig
+   }
 
-  return result
-}
+   return result
+ }

src/cli/AGENTS.md

@@ -10,8 +10,9 @@ CLI entry: `bunx oh-my-opencode`. Interactive installer, doctor diagnostics. Com
 cli/
 ├── index.ts              # Commander.js entry
 ├── 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
@@ -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

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", () => {
@@ -219,7 +258,7 @@ 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", () => {
@@ -238,7 +277,7 @@ describe("generateOmoConfig - model fallback system", () => {
     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", () => {
@@ -257,7 +296,7 @@ describe("generateOmoConfig - model fallback system", () => {
     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", () => {
@@ -277,7 +316,7 @@ 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/big-pickle")
   })
 
   test("uses zai-coding-plan/glm-4.7 for librarian when Z.ai available", () => {
@@ -298,7 +337,7 @@ 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", () => {
@@ -317,7 +356,7 @@ describe("generateOmoConfig - model fallback system", () => {
     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)
@@ -343,7 +382,7 @@ 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,
@@ -358,7 +397,7 @@ describe("generateOmoConfig - model fallback system", () => {
     // #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 } },
+        },
       },
     },
   },

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/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 +187,28 @@ 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: ${available.providers.length} (${available.providers.slice(0, 8).join(", ")}${available.providers.length > 8 ? "..." : ""})`)
+    details.push(`  Total models: ${available.modelCount}`)
+    details.push(`  Cache: ~/.cache/opencode/models.json`)
+    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 +232,7 @@ 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 +241,13 @@ 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/install.ts

@@ -44,7 +44,7 @@ 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("")
   lines.push(color.dim("─".repeat(40)))
@@ -178,7 +178,7 @@ async function runTuiMode(detected: DetectedConfig): Promise<InstallConfig | nul
   const claude = await p.select({
     message: "Do you have a Claude Pro/Max subscription?",
     options: [
-      { value: "no" as const, label: "No", hint: "Will use opencode/glm-4.7-free as fallback" },
+      { value: "no" as const, label: "No", hint: "Will use opencode/big-pickle as fallback" },
       { value: "yes" as const, label: "Yes (standard)", hint: "Claude Opus 4.5 for orchestration" },
       { value: "max20" as const, label: "Yes (max20 mode)", hint: "Full power with Claude Sonnet 4.5 for Librarian" },
     ],
@@ -250,7 +250,7 @@ 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,
   })
@@ -363,7 +363,7 @@ async function runNonTuiInstall(args: InstallArgs): Promise<number> {
   }
 
   if (!config.hasClaude && !config.hasOpenAI && !config.hasGemini && !config.hasCopilot && !config.hasOpencodeZen) {
-    printWarning("No model providers configured. Using opencode/glm-4.7-free as fallback.")
+    printWarning("No model providers configured. Using opencode/big-pickle as fallback.")
   }
 
   console.log(`${SYMBOLS.star} ${color.bold(color.green(isUpdate ? "Configuration updated!" : "Installation complete!"))}`)
@@ -480,7 +480,7 @@ export async function install(args: InstallArgs): Promise<number> {
   }
 
   if (!config.hasClaude && !config.hasOpenAI && !config.hasGemini && !config.hasCopilot && !config.hasOpencodeZen) {
-    p.log.warn("No model providers configured. Using opencode/glm-4.7-free as fallback.")
+    p.log.warn("No model providers configured. Using opencode/big-pickle as fallback.")
   }
 
   p.note(formatConfigSummary(config), isUpdate ? "Updated Configuration" : "Installation Complete")

src/cli/model-fallback.test.ts

@@ -310,19 +310,19 @@ 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 +332,26 @@ 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")
     })
   })
 
@@ -364,7 +364,7 @@ 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 +375,7 @@ 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

@@ -36,7 +36,7 @@ export interface GeneratedOmoConfig {
 
 const ZAI_MODEL = "zai-coding-plan/glm-4.7"
 
-const ULTIMATE_FALLBACK = "opencode/glm-4.7-free"
+const ULTIMATE_FALLBACK = "opencode/big-pickle"
 const SCHEMA_URL = "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json"
 
 function toProviderAvailability(config: InstallConfig): ProviderAvailability {
@@ -97,13 +97,13 @@ 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: ["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" },
   ]
 }
 
@@ -139,21 +139,21 @@ export function generateModelConfig(config: InstallConfig): GeneratedOmoConfig {
       continue
     }
 
-    // Special case: explore has custom Gemini → Claude → Grok logic
+    // Special case: explore uses Claude haiku → 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 {
-        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/config/schema.test.ts

@@ -345,6 +345,20 @@ 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 +389,7 @@ describe("Sisyphus-Junior agent override", () => {
     // #given
     const config = {
       agents: {
-        "Sisyphus-Junior": {
+        "sisyphus-junior": {
           model: "openai/gpt-5.2",
           temperature: 0.2,
         },
@@ -388,18 +402,18 @@ 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 +424,17 @@ 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 +449,62 @@ 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")
+    }
+  })
 })

src/config/schema.ts

@@ -17,14 +17,15 @@ 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([
@@ -36,17 +37,17 @@ 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
@@ -117,17 +118,17 @@ export const AgentOverrideConfigSchema = z.object({
 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 +160,7 @@ 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(),

src/features/AGENTS.md

@@ -12,12 +12,14 @@ features/
 │   ├── manager.ts              # Launch → poll → complete
 │   ├── concurrency.ts          # Per-provider limits
 │   └── types.ts                # BackgroundTask, LaunchInput
-├── skill-mcp-manager/          # MCP client lifecycle
+├── skill-mcp-manager/          # MCP client lifecycle (520 lines)
 │   ├── 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
+├── builtin-commands/           # ralph-loop, refactor, init-deep, start-work, remove-deadcode
+│   ├── commands.ts             # Command registry
+│   └── templates/              # Command templates (4 files)
 ├── claude-code-agent-loader/   # ~/.claude/agents/*.md
 ├── claude-code-command-loader/ # ~/.claude/commands/*.md
 ├── claude-code-mcp-loader/     # .mcp.json
@@ -26,7 +28,8 @@ features/
 ├── 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
 ```
 
 ## LOADER PRIORITY

src/features/builtin-commands/commands.ts

@@ -55,7 +55,7 @@ ${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>
@@ -81,7 +81,7 @@ 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
 

src/features/builtin-skills/git-master/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: git-master
-description: "MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'."
+description: "MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'."
 ---
 
 # Git Master Agent

src/features/builtin-skills/skills.ts

@@ -95,7 +95,7 @@ Interpret creatively and make unexpected choices that feel genuinely designed fo
 const gitMasterSkill: BuiltinSkill = {
   name: "git-master",
   description:
-    "MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.",
+    "MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.",
   template: `# Git Master Agent
 
 You are a Git expert combining three specializations:

src/features/claude-code-mcp-loader/loader.ts

@@ -77,7 +77,13 @@ export async function loadMcpConfigs(): Promise<McpLoadResult> {
 
     for (const [name, serverConfig] of Object.entries(config.mcpServers)) {
       if (serverConfig.disabled) {
-        log(`Skipping disabled MCP server "${name}"`, { path })
+        log(`Disabling MCP server "${name}"`, { path })
+        delete servers[name]
+        const existingIndex = loadedServers.findIndex((s) => s.name === name)
+        if (existingIndex !== -1) {
+          loadedServers.splice(existingIndex, 1)
+          log(`Removed previously loaded MCP server "${name}"`, { path })
+        }
         continue
       }
 

src/features/claude-code-session-state/state.test.ts

@@ -123,4 +123,40 @@ describe("claude-code-session-state", () => {
       expect(getSessionAgent(sessionID)).toBeUndefined()
     })
   })
+
+  describe("issue #893: custom agent switch reset", () => {
+    test("should preserve custom agent when default agent is sent on subsequent messages", () => {
+      // #given - user switches to custom agent "MyCustomAgent"
+      const sessionID = "test-session-custom"
+      const customAgent = "MyCustomAgent"
+      const defaultAgent = "Sisyphus"
+
+      // User switches to custom agent (via UI)
+      setSessionAgent(sessionID, customAgent)
+      expect(getSessionAgent(sessionID)).toBe(customAgent)
+
+      // #when - first message after switch sends default agent
+      // This simulates the bug: input.agent = "Sisyphus" on first message
+      // Using setSessionAgent (first-write wins) should preserve custom agent
+      setSessionAgent(sessionID, defaultAgent)
+
+      // #then - custom agent should be preserved, NOT overwritten
+      expect(getSessionAgent(sessionID)).toBe(customAgent)
+    })
+
+    test("should allow explicit agent update via updateSessionAgent", () => {
+      // #given - custom agent is set
+      const sessionID = "test-session-explicit"
+      const customAgent = "MyCustomAgent"
+      const newAgent = "AnotherAgent"
+
+      setSessionAgent(sessionID, customAgent)
+
+      // #when - explicit update (user intentionally switches)
+      updateSessionAgent(sessionID, newAgent)
+
+      // #then - should be updated
+      expect(getSessionAgent(sessionID)).toBe(newAgent)
+    })
+  })
 })

src/features/task-toast-manager/manager.test.ts

@@ -30,7 +30,7 @@ describe("TaskToastManager", () => {
       const task = {
         id: "task_1",
         description: "Test task",
-        agent: "Sisyphus-Junior",
+        agent: "sisyphus-junior",
         isBackground: true,
         skills: ["playwright", "git-master"],
       }
@@ -127,7 +127,7 @@ describe("TaskToastManager", () => {
       const task = {
         id: "task_1",
         description: "Full info task",
-        agent: "Sisyphus-Junior",
+        agent: "sisyphus-junior",
         isBackground: true,
         skills: ["frontend-ui-ux"],
       }
@@ -149,9 +149,9 @@ describe("TaskToastManager", () => {
       const task = {
         id: "task_1",
         description: "Task with category default model",
-        agent: "Sisyphus-Junior",
+        agent: "sisyphus-junior",
         isBackground: false,
-        modelInfo: { model: "google/gemini-3-pro-preview", type: "category-default" as const },
+        modelInfo: { model: "google/gemini-3-pro", type: "category-default" as const },
       }
 
       // #when - addTask is called
@@ -169,7 +169,7 @@ describe("TaskToastManager", () => {
       const task = {
         id: "task_1b",
         description: "Task with system default model",
-        agent: "Sisyphus-Junior",
+        agent: "sisyphus-junior",
         isBackground: false,
         modelInfo: { model: "anthropic/claude-sonnet-4-5", type: "system-default" as const },
       }
@@ -190,7 +190,7 @@ describe("TaskToastManager", () => {
       const task = {
         id: "task_2",
         description: "Task with inherited model",
-        agent: "Sisyphus-Junior",
+        agent: "sisyphus-junior",
         isBackground: false,
         modelInfo: { model: "cliproxy/claude-opus-4-5", type: "inherited" as const },
       }
@@ -211,7 +211,7 @@ describe("TaskToastManager", () => {
       const task = {
         id: "task_3",
         description: "Task with user model",
-        agent: "Sisyphus-Junior",
+        agent: "sisyphus-junior",
         isBackground: false,
         modelInfo: { model: "my-provider/my-model", type: "user-defined" as const },
       }

src/hooks/AGENTS.md

@@ -8,9 +8,9 @@
 
 ```
 hooks/
-├── atlas/                      # Main orchestration (771 lines)
+├── atlas/                      # Main orchestration (773 lines)
 ├── anthropic-context-window-limit-recovery/  # Auto-summarize
-├── todo-continuation-enforcer.ts # Force TODO completion
+├── todo-continuation-enforcer.ts # Force TODO completion (489 lines)
 ├── ralph-loop/                 # Self-referential dev loop
 ├── claude-code-hooks/          # settings.json compat layer - see AGENTS.md
 ├── comment-checker/            # Prevents AI slop
@@ -28,7 +28,15 @@ hooks/
 ├── prometheus-md-only/         # Planner read-only mode
 ├── agent-usage-reminder/       # Specialized agent hints
 ├── auto-update-checker/        # Plugin update check
-└── tool-output-truncator.ts    # Prevents context bloat
+├── tool-output-truncator.ts    # Prevents context bloat
+├── compaction-context-injector/ # Injects context on compaction
+├── delegate-task-retry/        # Retries failed delegations
+├── interactive-bash-session/   # Tmux session management
+├── non-interactive-env/        # Non-TTY environment handling
+├── start-work/                 # Sisyphus work session starter
+├── task-resume-info/           # Resume info for cancelled tasks
+├── question-label-truncator/   # Auto-truncates question labels >30 chars
+└── index.ts                    # Hook aggregation + registration
 ```
 
 ## HOOK EVENTS

src/hooks/atlas/index.test.ts

@@ -123,7 +123,7 @@ describe("atlas hook", () => {
      test("should append standalone verification when no boulder state but caller is Atlas", async () => {
        // #given - no boulder state, but caller is Atlas
        const sessionID = "session-no-boulder-test"
-       setupMessageStorage(sessionID, "Atlas")
+       setupMessageStorage(sessionID, "atlas")
       
       const hook = createAtlasHook(createMockPluginInput())
       const output = {
@@ -141,7 +141,7 @@ describe("atlas hook", () => {
       // #then - standalone verification reminder appended
       expect(output.output).toContain("Task completed successfully")
       expect(output.output).toContain("MANDATORY:")
-      expect(output.output).toContain("delegate_task(resume=")
+      expect(output.output).toContain("delegate_task(session_id=")
       
       cleanupMessageStorage(sessionID)
     })
@@ -149,7 +149,7 @@ describe("atlas hook", () => {
      test("should transform output when caller is Atlas with boulder state", async () => {
        // #given - Atlas caller with boulder state
        const sessionID = "session-transform-test"
-       setupMessageStorage(sessionID, "Atlas")
+       setupMessageStorage(sessionID, "atlas")
       
       const planPath = join(TEST_DIR, "test-plan.md")
       writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [x] Task 2")
@@ -180,7 +180,7 @@ describe("atlas hook", () => {
       expect(output.output).toContain("SUBAGENT WORK COMPLETED")
       expect(output.output).toContain("test-plan")
       expect(output.output).toContain("LIE")
-      expect(output.output).toContain("delegate_task(resume=")
+      expect(output.output).toContain("delegate_task(session_id=")
       
       cleanupMessageStorage(sessionID)
     })
@@ -188,7 +188,7 @@ describe("atlas hook", () => {
      test("should still transform when plan is complete (shows progress)", async () => {
        // #given - boulder state with complete plan, Atlas caller
        const sessionID = "session-complete-plan-test"
-       setupMessageStorage(sessionID, "Atlas")
+       setupMessageStorage(sessionID, "atlas")
       
       const planPath = join(TEST_DIR, "complete-plan.md")
       writeFileSync(planPath, "# Plan\n- [x] Task 1\n- [x] Task 2")
@@ -225,7 +225,7 @@ describe("atlas hook", () => {
      test("should append session ID to boulder state if not present", async () => {
        // #given - boulder state without session-append-test, Atlas caller
        const sessionID = "session-append-test"
-       setupMessageStorage(sessionID, "Atlas")
+       setupMessageStorage(sessionID, "atlas")
       
       const planPath = join(TEST_DIR, "test-plan.md")
       writeFileSync(planPath, "# Plan\n- [ ] Task 1")
@@ -261,7 +261,7 @@ describe("atlas hook", () => {
      test("should not duplicate existing session ID", async () => {
        // #given - boulder state already has session-dup-test, Atlas caller
        const sessionID = "session-dup-test"
-       setupMessageStorage(sessionID, "Atlas")
+       setupMessageStorage(sessionID, "atlas")
       
       const planPath = join(TEST_DIR, "test-plan.md")
       writeFileSync(planPath, "# Plan\n- [ ] Task 1")
@@ -298,7 +298,7 @@ describe("atlas hook", () => {
      test("should include boulder.json path and notepad path in transformed output", async () => {
        // #given - boulder state, Atlas caller
        const sessionID = "session-path-test"
-       setupMessageStorage(sessionID, "Atlas")
+       setupMessageStorage(sessionID, "atlas")
       
       const planPath = join(TEST_DIR, "my-feature.md")
       writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [ ] Task 2\n- [x] Task 3")
@@ -332,10 +332,10 @@ describe("atlas hook", () => {
       cleanupMessageStorage(sessionID)
     })
 
-     test("should include resume and checkbox instructions in reminder", async () => {
+     test("should include session_id and checkbox instructions in reminder", async () => {
        // #given - boulder state, Atlas caller
        const sessionID = "session-resume-test"
-       setupMessageStorage(sessionID, "Atlas")
+       setupMessageStorage(sessionID, "atlas")
       
       const planPath = join(TEST_DIR, "test-plan.md")
       writeFileSync(planPath, "# Plan\n- [ ] Task 1")
@@ -361,8 +361,8 @@ describe("atlas hook", () => {
         output
       )
 
-      // #then - should include resume instructions and verification
-      expect(output.output).toContain("delegate_task(resume=")
+      // #then - should include session_id instructions and verification
+      expect(output.output).toContain("delegate_task(session_id=")
       expect(output.output).toContain("[x]")
       expect(output.output).toContain("MANDATORY:")
       

src/hooks/atlas/index.ts

@@ -179,13 +179,13 @@ If you were NOT given **exactly ONE atomic task**, you MUST:
 `
 
 function buildVerificationReminder(sessionId: string): string {
-  return `${VERIFICATION_REMINDER}
+   return `${VERIFICATION_REMINDER}
 
 ---
 
 **If ANY verification fails, use this immediately:**
 \`\`\`
-delegate_task(resume="${sessionId}", prompt="fix: [describe the specific failure]")
+delegate_task(session_id="${sessionId}", prompt="fix: [describe the specific failure]")
 \`\`\``
 }
 
@@ -274,6 +274,7 @@ function getGitDiffStats(directory: string): GitFileStat[] {
       cwd: directory,
       encoding: "utf-8",
       timeout: 5000,
+      stdio: ["pipe", "pipe", "pipe"],
     }).trim()
 
     if (!output) return []
@@ -282,6 +283,7 @@ function getGitDiffStats(directory: string): GitFileStat[] {
       cwd: directory,
       encoding: "utf-8",
       timeout: 5000,
+      stdio: ["pipe", "pipe", "pipe"],
     }).trim()
 
     const statusMap = new Map<string, "modified" | "added" | "deleted">()
@@ -397,7 +399,7 @@ function isCallerOrchestrator(sessionID?: string): boolean {
    const messageDir = getMessageDir(sessionID)
    if (!messageDir) return false
    const nearest = findNearestMessageWithFields(messageDir)
-   return nearest?.agent === "Atlas"
+   return nearest?.agent?.toLowerCase() === "atlas"
  }
 
 interface SessionState {
@@ -496,7 +498,7 @@ export function createAtlasHook(
        await ctx.client.session.prompt({
          path: { id: sessionID },
          body: {
-            agent: "Atlas",
+            agent: "atlas",
            ...(model !== undefined ? { model } : {}),
            parts: [{ type: "text", text: prompt }],
          },
@@ -709,8 +711,8 @@ export function createAtlasHook(
         return
       }
 
-      const outputStr = output.output && typeof output.output === "string" ? output.output : ""
-      const isBackgroundLaunch = outputStr.includes("Background task launched") || outputStr.includes("Background task resumed")
+       const outputStr = output.output && typeof output.output === "string" ? output.output : ""
+       const isBackgroundLaunch = outputStr.includes("Background task launched") || outputStr.includes("Background task continued")
       
       if (isBackgroundLaunch) {
         return

src/hooks/auto-update-checker/index.ts

@@ -5,6 +5,7 @@ import { PACKAGE_NAME } from "./constants"
 import { log } from "../../shared/logger"
 import { getConfigLoadErrors, clearConfigLoadErrors } from "../../shared/config-errors"
 import { runBunInstall } from "../../cli/config-manager"
+import { isModelCacheAvailable } from "../../shared/model-availability"
 import type { AutoUpdateCheckerOptions } from "./types"
 
 const SISYPHUS_SPINNER = ["·", "•", "●", "○", "◌", "◦", " "]
@@ -75,6 +76,7 @@ export function createAutoUpdateCheckerHook(ctx: PluginInput, options: AutoUpdat
         const displayVersion = localDevVersion ?? cachedVersion
 
         await showConfigErrorsIfAny(ctx)
+        await showModelCacheWarningIfNeeded(ctx)
 
         if (localDevVersion) {
           if (showStartupToast) {
@@ -167,6 +169,23 @@ async function runBunInstallSafe(): Promise<boolean> {
   }
 }
 
+async function showModelCacheWarningIfNeeded(ctx: PluginInput): Promise<void> {
+  if (isModelCacheAvailable()) return
+
+  await ctx.client.tui
+    .showToast({
+      body: {
+        title: "Model Cache Not Found",
+        message: "Run 'opencode models --refresh' or restart OpenCode to populate the models cache for optimal agent model selection.",
+        variant: "warning" as const,
+        duration: 10000,
+      },
+    })
+    .catch(() => {})
+
+  log("[auto-update-checker] Model cache warning shown")
+}
+
 async function showConfigErrorsIfAny(ctx: PluginInput): Promise<void> {
   const errors = getConfigLoadErrors()
   if (errors.length === 0) return

src/hooks/background-compaction/index.ts

@@ -1,87 +0,0 @@
-import type { BackgroundManager } from "../../features/background-agent"
-
-interface CompactingInput {
-  sessionID: string
-}
-
-interface CompactingOutput {
-  context: string[]
-  prompt?: string
-}
-
-/**
- * Background agent compaction hook - preserves task state during context compaction.
- * 
- * When OpenCode compacts session context to save tokens, this hook injects
- * information about running and recently completed background tasks so the
- * agent doesn't lose awareness of delegated work.
- */
-export function createBackgroundCompactionHook(manager: BackgroundManager) {
-  return {
-    "experimental.session.compacting": async (
-      input: CompactingInput,
-      output: CompactingOutput
-    ): Promise<void> => {
-      const { sessionID } = input
-
-      // Get running tasks for this session
-      const running = manager.getRunningTasks()
-        .filter(t => t.parentSessionID === sessionID)
-        .map(t => ({
-          id: t.id,
-          agent: t.agent,
-          description: t.description,
-          startedAt: t.startedAt,
-        }))
-
-      // Get recently completed tasks (still in memory within 5-min retention)
-      const completed = manager.getCompletedTasks()
-        .filter(t => t.parentSessionID === sessionID)
-        .slice(-10) // Last 10 completed
-        .map(t => ({
-          id: t.id,
-          agent: t.agent,
-          description: t.description,
-          status: t.status,
-        }))
-
-      // Early exit if nothing to preserve
-      if (running.length === 0 && completed.length === 0) return
-
-      const sections: string[] = ["<background-tasks>"]
-
-      // Running tasks section
-      if (running.length > 0) {
-        sections.push("## Running Background Tasks")
-        sections.push("")
-        for (const t of running) {
-          const elapsed = t.startedAt 
-            ? Math.floor((Date.now() - t.startedAt.getTime()) / 1000)
-            : 0
-          sections.push(`- **\`${t.id}\`** (${t.agent}): ${t.description} [${elapsed}s elapsed]`)
-        }
-        sections.push("")
-        sections.push("> **Note:** You WILL be notified when tasks complete.")
-        sections.push("> Do NOT poll - continue productive work.")
-        sections.push("")
-      }
-
-      // Completed tasks section
-      if (completed.length > 0) {
-        sections.push("## Recently Completed Tasks")
-        sections.push("")
-        for (const t of completed) {
-          const statusLabel = t.status === "completed" ? "[DONE]" : t.status === "error" ? "[ERROR]" : "[PENDING]"
-          sections.push(`- ${statusLabel} **\`${t.id}\`**: ${t.description}`)
-        }
-        sections.push("")
-      }
-
-      sections.push("## Retrieval")
-      sections.push('Use `background_output(task_id="<id>")` to retrieve task results.')
-      sections.push("</background-tasks>")
-
-      output.context.push(sections.join("\n"))
-    }
-  }
-}

src/hooks/index.ts

@@ -30,3 +30,4 @@ export { createTaskResumeInfoHook } from "./task-resume-info";
 export { createStartWorkHook } from "./start-work";
 export { createAtlasHook } from "./atlas";
 export { createDelegateTaskRetryHook } from "./delegate-task-retry";
+export { createQuestionLabelTruncatorHook } from "./question-label-truncator";

src/hooks/keyword-detector/constants.ts

@@ -169,10 +169,10 @@ TELL THE USER WHAT AGENTS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.
 ## AGENTS / **CATEGORY + SKILLS** UTILIZATION PRINCIPLES (by capability, not by name)
 - **Codebase Exploration**: Spawn exploration agents using BACKGROUND TASKS for file patterns, internal implementations, project structure
 - **Documentation & References**: Use librarian-type agents via BACKGROUND TASKS for API references, examples, external library docs
-- **Planning & Strategy**: NEVER plan yourself - ALWAYS spawn a dedicated planning agent for work breakdown
-  - MUST USE PLAN AGENT. MUST USE PLAN AGENT. MUST USE PLAN AGENT.
-  - ALWAYS ASK PLAN AGENT TO WHAT CATEGORY + SKILLS / AGENTS TO LEVERAGE.
-  - IF IMPLEMENT TASK, MUST ADD TODO NOW: "CONSULT WITH PLAN AGENT WITH CATEGORY + SKILLS"
+- **Planning & Strategy**: NEVER plan yourself - ALWAYS spawn the Plan agent for work breakdown
+  - MUST invoke: \`delegate_task(subagent_type="plan", prompt="<gathered context + user request>")\`
+  - In your prompt to the Plan agent, ASK it to recommend which CATEGORY + SKILLS / AGENTS to leverage for implementation.
+  - IF IMPLEMENT TASK, MUST ADD TODO NOW: "Consult Plan agent via delegate_task(subagent_type='plan') for work breakdown with category + skills recommendations"
 - **High-IQ Reasoning**: Leverage specialized agents for architecture decisions, code review, strategic planning
 - **SPECIAL TASKS COVERED WITH CATEGORY + LOAD_SKILLS**: Delegate to specialized agents with category+skills for design and implementation, as following guide:
   - CATEGORY + SKILL GUIDE
@@ -192,7 +192,7 @@ TELL THE USER WHAT AGENTS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.
 ## WORKFLOW
 1. Analyze the request and identify required capabilities
 2. Spawn exploration/librarian agents via delegate_task(background=true) in PARALLEL (10+ if needed)
-3. Always Use Plan agent with gathered context to create detailed work breakdown
+3. Spawn Plan agent: \`delegate_task(subagent_type="plan", prompt="<context + request>")\` to create detailed work breakdown
 4. Execute with continuous verification against original requirements
 
 ## VERIFICATION GUARANTEE (NON-NEGOTIABLE)
@@ -266,9 +266,9 @@ Write these criteria explicitly. Share with user if scope is non-trivial.
 
 THE USER ASKED FOR X. DELIVER EXACTLY X. NOT A SUBSET. NOT A DEMO. NOT A STARTING POINT.
 
-1. EXPLORES + LIBRARIANS
-2. GATHER -> PLAN AGENT SPAWN
-3. WORK BY DELEGATING TO ANOTHER AGENTS
+1. EXPLORES + LIBRARIANS (background)
+2. GATHER -> delegate_task(subagent_type="plan", prompt="<context + request>")
+3. WORK BY DELEGATING TO CATEGORY + SKILLS AGENTS
 
 NOW.
 

src/hooks/non-interactive-env/index.test.ts

@@ -178,7 +178,11 @@ describe("non-interactive-env hook", () => {
     })
   })
 
-  describe("cross-platform shell support", () => {
+  describe("bash tool always uses unix shell syntax", () => {
+    // The bash tool always runs in a Unix-like shell (bash/sh), even on Windows
+    // (via Git Bash, WSL, etc.), so we should always use unix export syntax.
+    // This fixes GitHub issues #983 and #889.
+
     test("#given macOS platform #when git command executes #then uses unix export syntax", async () => {
       delete process.env.PSModulePath
       process.env.SHELL = "/bin/zsh"
@@ -221,7 +225,9 @@ describe("non-interactive-env hook", () => {
       expect(cmd).toContain("; git commit")
     })
 
-    test("#given Windows with PowerShell #when git command executes #then uses powershell $env syntax", async () => {
+    test("#given Windows with PowerShell env #when bash tool git command executes #then still uses unix export syntax", async () => {
+      // Even when PSModulePath is set (indicating PowerShell environment),
+      // the bash tool runs in a Unix-like shell, so we use export syntax
       process.env.PSModulePath = "C:\\Program Files\\PowerShell\\Modules"
       Object.defineProperty(process, "platform", { value: "win32" })
 
@@ -236,13 +242,16 @@ describe("non-interactive-env hook", () => {
       )
 
       const cmd = output.args.command as string
-      expect(cmd).toContain("$env:")
+      // Should use unix export syntax, NOT PowerShell $env: syntax
+      expect(cmd).toStartWith("export ")
       expect(cmd).toContain("; git status")
-      expect(cmd).not.toStartWith("export ")
+      expect(cmd).not.toContain("$env:")
       expect(cmd).not.toContain("set ")
     })
 
-    test("#given Windows without PowerShell #when git command executes #then uses cmd set syntax", async () => {
+    test("#given Windows without SHELL env #when bash tool git command executes #then still uses unix export syntax", async () => {
+      // Even when detectShellType() would return "cmd" (no SHELL, no PSModulePath, win32),
+      // the bash tool runs in a Unix-like shell, so we use export syntax
       delete process.env.PSModulePath
       delete process.env.SHELL
       Object.defineProperty(process, "platform", { value: "win32" })
@@ -258,14 +267,18 @@ describe("non-interactive-env hook", () => {
       )
 
       const cmd = output.args.command as string
-      expect(cmd).toContain("set ")
-      expect(cmd).toContain("&&")
-      expect(cmd).not.toStartWith("export ")
+      // Should use unix export syntax, NOT cmd.exe set syntax
+      expect(cmd).toStartWith("export ")
+      expect(cmd).toContain("; git log")
+      expect(cmd).not.toContain("set ")
+      expect(cmd).not.toContain("&&")
       expect(cmd).not.toContain("$env:")
     })
 
-    test("#given PowerShell #when values contain quotes #then escapes correctly", async () => {
-      process.env.PSModulePath = "C:\\Program Files\\PowerShell\\Modules"
+    test("#given Windows Git Bash environment #when git command executes #then uses unix export syntax", async () => {
+      // Simulating Git Bash on Windows: SHELL might be set to /usr/bin/bash
+      delete process.env.PSModulePath
+      process.env.SHELL = "/usr/bin/bash"
       Object.defineProperty(process, "platform", { value: "win32" })
 
       const hook = createNonInteractiveEnvHook(mockCtx)
@@ -279,32 +292,16 @@ describe("non-interactive-env hook", () => {
       )
 
       const cmd = output.args.command as string
-      expect(cmd).toMatch(/\$env:\w+='[^']*'/)
+      expect(cmd).toStartWith("export ")
+      expect(cmd).toContain("; git status")
     })
 
-    test("#given cmd.exe #when values contain spaces #then escapes correctly", async () => {
+    test("#given any platform #when chained git commands via bash tool #then uses unix export syntax", async () => {
+      // Even on Windows, chained commands should use unix syntax
       delete process.env.PSModulePath
       delete process.env.SHELL
       Object.defineProperty(process, "platform", { value: "win32" })
 
-      const hook = createNonInteractiveEnvHook(mockCtx)
-      const output: { args: Record<string, unknown>; message?: string } = {
-        args: { command: "git status" },
-      }
-
-      await hook["tool.execute.before"](
-        { tool: "bash", sessionID: "test", callID: "1" },
-        output
-      )
-
-      const cmd = output.args.command as string
-      expect(cmd).toMatch(/set \w+="[^"]*"/)
-    })
-
-    test("#given PowerShell #when chained git commands #then env vars apply to all commands", async () => {
-      process.env.PSModulePath = "C:\\Program Files\\PowerShell\\Modules"
-      Object.defineProperty(process, "platform", { value: "win32" })
-
       const hook = createNonInteractiveEnvHook(mockCtx)
       const output: { args: Record<string, unknown>; message?: string } = {
         args: { command: "git add file && git commit -m 'test'" },
@@ -316,7 +313,7 @@ describe("non-interactive-env hook", () => {
       )
 
       const cmd = output.args.command as string
-      expect(cmd).toContain("$env:")
+      expect(cmd).toStartWith("export ")
       expect(cmd).toContain("; git add file && git commit")
     })
   })

src/hooks/non-interactive-env/index.ts

@@ -1,7 +1,8 @@
 import type { PluginInput } from "@opencode-ai/plugin"
+import type { ShellType } from "../../shared"
 import { HOOK_NAME, NON_INTERACTIVE_ENV, SHELL_COMMAND_PATTERNS } from "./constants"
 import { isNonInteractive } from "./detector"
-import { log, detectShellType, buildEnvPrefix } from "../../shared"
+import { log, buildEnvPrefix } from "../../shared"
 
 export * from "./constants"
 export * from "./detector"
@@ -50,7 +51,10 @@ export function createNonInteractiveEnvHook(_ctx: PluginInput) {
         return
       }
 
-      const shellType = detectShellType()
+      // The bash tool always runs in a Unix-like shell (bash/sh), even on Windows
+      // (via Git Bash, WSL, etc.), so we always use unix export syntax.
+      // This fixes GitHub issues #983 and #889.
+      const shellType: ShellType = "unix"
       const envPrefix = buildEnvPrefix(NON_INTERACTIVE_ENV, shellType)
       output.args.command = `${envPrefix} ${command}`
 

src/hooks/prometheus-md-only/constants.ts

@@ -1,8 +1,9 @@
 import { createSystemDirective, SystemDirectiveTypes } from "../../shared/system-directive"
+import { getAgentDisplayName } from "../../shared/agent-display-names"
 
 export const HOOK_NAME = "prometheus-md-only"
 
-export const PROMETHEUS_AGENTS = ["Prometheus (Planner)"]
+export const PROMETHEUS_AGENTS = ["prometheus"]
 
 export const ALLOWED_EXTENSIONS = [".md"]
 
@@ -16,7 +17,7 @@ export const PLANNING_CONSULT_WARNING = `
 
 ${createSystemDirective(SystemDirectiveTypes.PROMETHEUS_READ_ONLY)}
 
-You are being invoked by Prometheus (Planner), a READ-ONLY planning agent.
+You are being invoked by ${getAgentDisplayName("prometheus")}, a READ-ONLY planning agent.
 
 **CRITICAL CONSTRAINTS:**
 - DO NOT modify any files (no Write, Edit, or any file mutations)

src/hooks/prometheus-md-only/index.test.ts

@@ -41,10 +41,10 @@ describe("prometheus-md-only", () => {
     }
   })
 
-  describe("with Prometheus agent in message storage", () => {
-    beforeEach(() => {
-      setupMessageStorage(TEST_SESSION_ID, "Prometheus (Planner)")
-    })
+   describe("with Prometheus agent in message storage", () => {
+     beforeEach(() => {
+       setupMessageStorage(TEST_SESSION_ID, "prometheus")
+     })
 
     test("should block Prometheus from writing non-.md files", async () => {
       // #given
@@ -345,185 +345,195 @@ describe("prometheus-md-only", () => {
       setupMessageStorage(TEST_SESSION_ID, "Prometheus (Planner)")
     })
 
-    test("should allow Windows-style backslash paths under .sisyphus/", async () => {
-      // #given
-      const hook = createPrometheusMdOnlyHook(createMockPluginInput())
-      const input = {
-        tool: "Write",
-        sessionID: TEST_SESSION_ID,
-        callID: "call-1",
-      }
-      const output = {
-        args: { filePath: ".sisyphus\\plans\\work-plan.md" },
-      }
+     test("should allow Windows-style backslash paths under .sisyphus/", async () => {
+       // #given
+       setupMessageStorage(TEST_SESSION_ID, "prometheus")
+       const hook = createPrometheusMdOnlyHook(createMockPluginInput())
+       const input = {
+         tool: "Write",
+         sessionID: TEST_SESSION_ID,
+         callID: "call-1",
+       }
+       const output = {
+         args: { filePath: ".sisyphus\\plans\\work-plan.md" },
+       }
 
-      // #when / #then
-      await expect(
-        hook["tool.execute.before"](input, output)
-      ).resolves.toBeUndefined()
-    })
+       // #when / #then
+       await expect(
+         hook["tool.execute.before"](input, output)
+       ).resolves.toBeUndefined()
+     })
 
-    test("should allow mixed separator paths under .sisyphus/", async () => {
-      // #given
-      const hook = createPrometheusMdOnlyHook(createMockPluginInput())
-      const input = {
-        tool: "Write",
-        sessionID: TEST_SESSION_ID,
-        callID: "call-1",
-      }
-      const output = {
-        args: { filePath: ".sisyphus\\plans/work-plan.MD" },
-      }
+     test("should allow mixed separator paths under .sisyphus/", async () => {
+       // #given
+       setupMessageStorage(TEST_SESSION_ID, "prometheus")
+       const hook = createPrometheusMdOnlyHook(createMockPluginInput())
+       const input = {
+         tool: "Write",
+         sessionID: TEST_SESSION_ID,
+         callID: "call-1",
+       }
+       const output = {
+         args: { filePath: ".sisyphus\\plans/work-plan.MD" },
+       }
 
-      // #when / #then
-      await expect(
-        hook["tool.execute.before"](input, output)
-      ).resolves.toBeUndefined()
-    })
+       // #when / #then
+       await expect(
+         hook["tool.execute.before"](input, output)
+       ).resolves.toBeUndefined()
+     })
 
-    test("should allow uppercase .MD extension", async () => {
-      // #given
-      const hook = createPrometheusMdOnlyHook(createMockPluginInput())
-      const input = {
-        tool: "Write",
-        sessionID: TEST_SESSION_ID,
-        callID: "call-1",
-      }
-      const output = {
-        args: { filePath: ".sisyphus/plans/work-plan.MD" },
-      }
+     test("should allow uppercase .MD extension", async () => {
+       // #given
+       setupMessageStorage(TEST_SESSION_ID, "prometheus")
+       const hook = createPrometheusMdOnlyHook(createMockPluginInput())
+       const input = {
+         tool: "Write",
+         sessionID: TEST_SESSION_ID,
+         callID: "call-1",
+       }
+       const output = {
+         args: { filePath: ".sisyphus/plans/work-plan.MD" },
+       }
 
-      // #when / #then
-      await expect(
-        hook["tool.execute.before"](input, output)
-      ).resolves.toBeUndefined()
-    })
+       // #when / #then
+       await expect(
+         hook["tool.execute.before"](input, output)
+       ).resolves.toBeUndefined()
+     })
 
-    test("should block paths outside workspace root even if containing .sisyphus", async () => {
-      // #given
-      const hook = createPrometheusMdOnlyHook(createMockPluginInput())
-      const input = {
-        tool: "Write",
-        sessionID: TEST_SESSION_ID,
-        callID: "call-1",
-      }
-      const output = {
-        args: { filePath: "/other/project/.sisyphus/plans/x.md" },
-      }
+     test("should block paths outside workspace root even if containing .sisyphus", async () => {
+       // #given
+       setupMessageStorage(TEST_SESSION_ID, "prometheus")
+       const hook = createPrometheusMdOnlyHook(createMockPluginInput())
+       const input = {
+         tool: "Write",
+         sessionID: TEST_SESSION_ID,
+         callID: "call-1",
+       }
+       const output = {
+         args: { filePath: "/other/project/.sisyphus/plans/x.md" },
+       }
 
-      // #when / #then
-      await expect(
-        hook["tool.execute.before"](input, output)
-      ).rejects.toThrow("can only write/edit .md files inside .sisyphus/")
-    })
+       // #when / #then
+       await expect(
+         hook["tool.execute.before"](input, output)
+       ).rejects.toThrow("can only write/edit .md files inside .sisyphus/")
+     })
 
-    test("should allow nested .sisyphus directories (ctx.directory may be parent)", async () => {
-      // #given - when ctx.directory is parent of actual project, path includes project name
-      const hook = createPrometheusMdOnlyHook(createMockPluginInput())
-      const input = {
-        tool: "Write",
-        sessionID: TEST_SESSION_ID,
-        callID: "call-1",
-      }
-      const output = {
-        args: { filePath: "src/.sisyphus/plans/x.md" },
-      }
+     test("should allow nested .sisyphus directories (ctx.directory may be parent)", async () => {
+       // #given - when ctx.directory is parent of actual project, path includes project name
+       setupMessageStorage(TEST_SESSION_ID, "prometheus")
+       const hook = createPrometheusMdOnlyHook(createMockPluginInput())
+       const input = {
+         tool: "Write",
+         sessionID: TEST_SESSION_ID,
+         callID: "call-1",
+       }
+       const output = {
+         args: { filePath: "src/.sisyphus/plans/x.md" },
+       }
 
-      // #when / #then - should allow because .sisyphus is in path
-      await expect(
-        hook["tool.execute.before"](input, output)
-      ).resolves.toBeUndefined()
-    })
+       // #when / #then - should allow because .sisyphus is in path
+       await expect(
+         hook["tool.execute.before"](input, output)
+       ).resolves.toBeUndefined()
+     })
 
-    test("should block path traversal attempts", async () => {
-      // #given
-      const hook = createPrometheusMdOnlyHook(createMockPluginInput())
-      const input = {
-        tool: "Write",
-        sessionID: TEST_SESSION_ID,
-        callID: "call-1",
-      }
-      const output = {
-        args: { filePath: ".sisyphus/../secrets.md" },
-      }
+     test("should block path traversal attempts", async () => {
+       // #given
+       setupMessageStorage(TEST_SESSION_ID, "prometheus")
+       const hook = createPrometheusMdOnlyHook(createMockPluginInput())
+       const input = {
+         tool: "Write",
+         sessionID: TEST_SESSION_ID,
+         callID: "call-1",
+       }
+       const output = {
+         args: { filePath: ".sisyphus/../secrets.md" },
+       }
 
-      // #when / #then
-      await expect(
-        hook["tool.execute.before"](input, output)
-      ).rejects.toThrow("can only write/edit .md files inside .sisyphus/")
-    })
+       // #when / #then
+       await expect(
+         hook["tool.execute.before"](input, output)
+       ).rejects.toThrow("can only write/edit .md files inside .sisyphus/")
+     })
 
-    test("should allow case-insensitive .SISYPHUS directory", async () => {
-      // #given
-      const hook = createPrometheusMdOnlyHook(createMockPluginInput())
-      const input = {
-        tool: "Write",
-        sessionID: TEST_SESSION_ID,
-        callID: "call-1",
-      }
-      const output = {
-        args: { filePath: ".SISYPHUS/plans/work-plan.md" },
-      }
+     test("should allow case-insensitive .SISYPHUS directory", async () => {
+       // #given
+       setupMessageStorage(TEST_SESSION_ID, "prometheus")
+       const hook = createPrometheusMdOnlyHook(createMockPluginInput())
+       const input = {
+         tool: "Write",
+         sessionID: TEST_SESSION_ID,
+         callID: "call-1",
+       }
+       const output = {
+         args: { filePath: ".SISYPHUS/plans/work-plan.md" },
+       }
 
-      // #when / #then
-      await expect(
-        hook["tool.execute.before"](input, output)
-      ).resolves.toBeUndefined()
-    })
+       // #when / #then
+       await expect(
+         hook["tool.execute.before"](input, output)
+       ).resolves.toBeUndefined()
+     })
 
-    test("should allow nested project path with .sisyphus (Windows real-world case)", async () => {
-      // #given - simulates when ctx.directory is parent of actual project
-      // User reported: xauusd-dxy-plan\.sisyphus\drafts\supabase-email-templates.md
-      const hook = createPrometheusMdOnlyHook(createMockPluginInput())
-      const input = {
-        tool: "Write",
-        sessionID: TEST_SESSION_ID,
-        callID: "call-1",
-      }
-      const output = {
-        args: { filePath: "xauusd-dxy-plan\\.sisyphus\\drafts\\supabase-email-templates.md" },
-      }
+     test("should allow nested project path with .sisyphus (Windows real-world case)", async () => {
+       // #given - simulates when ctx.directory is parent of actual project
+       // User reported: xauusd-dxy-plan\.sisyphus\drafts\supabase-email-templates.md
+       setupMessageStorage(TEST_SESSION_ID, "prometheus")
+       const hook = createPrometheusMdOnlyHook(createMockPluginInput())
+       const input = {
+         tool: "Write",
+         sessionID: TEST_SESSION_ID,
+         callID: "call-1",
+       }
+       const output = {
+         args: { filePath: "xauusd-dxy-plan\\.sisyphus\\drafts\\supabase-email-templates.md" },
+       }
 
-      // #when / #then
-      await expect(
-        hook["tool.execute.before"](input, output)
-      ).resolves.toBeUndefined()
-    })
+       // #when / #then
+       await expect(
+         hook["tool.execute.before"](input, output)
+       ).resolves.toBeUndefined()
+     })
 
-    test("should allow nested project path with mixed separators", async () => {
-      // #given
-      const hook = createPrometheusMdOnlyHook(createMockPluginInput())
-      const input = {
-        tool: "Write",
-        sessionID: TEST_SESSION_ID,
-        callID: "call-1",
-      }
-      const output = {
-        args: { filePath: "my-project/.sisyphus\\plans/task.md" },
-      }
+     test("should allow nested project path with mixed separators", async () => {
+       // #given
+       setupMessageStorage(TEST_SESSION_ID, "prometheus")
+       const hook = createPrometheusMdOnlyHook(createMockPluginInput())
+       const input = {
+         tool: "Write",
+         sessionID: TEST_SESSION_ID,
+         callID: "call-1",
+       }
+       const output = {
+         args: { filePath: "my-project/.sisyphus\\plans/task.md" },
+       }
 
-      // #when / #then
-      await expect(
-        hook["tool.execute.before"](input, output)
-      ).resolves.toBeUndefined()
-    })
+       // #when / #then
+       await expect(
+         hook["tool.execute.before"](input, output)
+       ).resolves.toBeUndefined()
+     })
 
-    test("should block nested project path without .sisyphus", async () => {
-      // #given
-      const hook = createPrometheusMdOnlyHook(createMockPluginInput())
-      const input = {
-        tool: "Write",
-        sessionID: TEST_SESSION_ID,
-        callID: "call-1",
-      }
-      const output = {
-        args: { filePath: "my-project\\src\\code.ts" },
-      }
+     test("should block nested project path without .sisyphus", async () => {
+       // #given
+       setupMessageStorage(TEST_SESSION_ID, "prometheus")
+       const hook = createPrometheusMdOnlyHook(createMockPluginInput())
+       const input = {
+         tool: "Write",
+         sessionID: TEST_SESSION_ID,
+         callID: "call-1",
+       }
+       const output = {
+         args: { filePath: "my-project\\src\\code.ts" },
+       }
 
-      // #when / #then
-      await expect(
-        hook["tool.execute.before"](input, output)
-      ).rejects.toThrow("can only write/edit .md files")
-    })
+       // #when / #then
+       await expect(
+         hook["tool.execute.before"](input, output)
+       ).rejects.toThrow("can only write/edit .md files")
+     })
   })
 })

src/hooks/prometheus-md-only/index.ts

@@ -6,6 +6,7 @@ import { findNearestMessageWithFields, findFirstMessageWithAgent, MESSAGE_STORAG
 import { getSessionAgent } from "../../features/claude-code-session-state"
 import { log } from "../../shared/logger"
 import { SYSTEM_DIRECTIVE_PREFIX } from "../../shared/system-directive"
+import { getAgentDisplayName } from "../../shared/agent-display-names"
 
 export * from "./constants"
 
@@ -110,20 +111,20 @@ export function createPrometheusMdOnlyHook(ctx: PluginInput) {
         return
       }
 
-      if (!isAllowedFile(filePath, ctx.directory)) {
-        log(`[${HOOK_NAME}] Blocked: Prometheus can only write to .sisyphus/*.md`, {
-          sessionID: input.sessionID,
-          tool: toolName,
-          filePath,
-          agent: agentName,
-        })
-        throw new Error(
-          `[${HOOK_NAME}] Prometheus (Planner) can only write/edit .md files inside .sisyphus/ directory. ` +
-          `Attempted to modify: ${filePath}. ` +
-          `Prometheus is a READ-ONLY planner. Use /start-work to execute the plan. ` +
-          `APOLOGIZE TO THE USER, REMIND OF YOUR PLAN WRITING PROCESSES, TELL USER WHAT YOU WILL GOING TO DO AS THE PROCESS, WRITE THE PLAN`
-        )
-      }
+       if (!isAllowedFile(filePath, ctx.directory)) {
+         log(`[${HOOK_NAME}] Blocked: Prometheus can only write to .sisyphus/*.md`, {
+           sessionID: input.sessionID,
+           tool: toolName,
+           filePath,
+           agent: agentName,
+         })
+         throw new Error(
+           `[${HOOK_NAME}] ${getAgentDisplayName("prometheus")} can only write/edit .md files inside .sisyphus/ directory. ` +
+           `Attempted to modify: ${filePath}. ` +
+           `${getAgentDisplayName("prometheus")} is a READ-ONLY planner. Use /start-work to execute the plan. ` +
+           `APOLOGIZE TO THE USER, REMIND OF YOUR PLAN WRITING PROCESSES, TELL USER WHAT YOU WILL GOING TO DO AS THE PROCESS, WRITE THE PLAN`
+         )
+       }
 
       const normalizedPath = filePath.toLowerCase().replace(/\\/g, "/")
       if (normalizedPath.includes(".sisyphus/plans/") || normalizedPath.includes(".sisyphus\\plans\\")) {

src/hooks/question-label-truncator/index.test.ts

@@ -0,0 +1,136 @@
+import { describe, it, expect } from "bun:test";
+import { createQuestionLabelTruncatorHook } from "./index";
+
+describe("createQuestionLabelTruncatorHook", () => {
+  const hook = createQuestionLabelTruncatorHook();
+
+  describe("tool.execute.before", () => {
+    it("truncates labels exceeding 30 characters with ellipsis", async () => {
+      // #given
+      const longLabel = "This is a very long label that exceeds thirty characters";
+      const input = { tool: "AskUserQuestion" };
+      const output = {
+        args: {
+          questions: [
+            {
+              question: "Choose an option",
+              options: [
+                { label: longLabel, description: "A long option" },
+              ],
+            },
+          ],
+        },
+      };
+
+      // #when
+      await hook["tool.execute.before"]?.(input as any, output as any);
+
+      // #then
+      const truncatedLabel = (output.args as any).questions[0].options[0].label;
+      expect(truncatedLabel.length).toBeLessThanOrEqual(30);
+      expect(truncatedLabel).toBe("This is a very long label t...");
+      expect(truncatedLabel.endsWith("...")).toBe(true);
+    });
+
+    it("preserves labels within 30 characters", async () => {
+      // #given
+      const shortLabel = "Short label";
+      const input = { tool: "AskUserQuestion" };
+      const output = {
+        args: {
+          questions: [
+            {
+              question: "Choose an option",
+              options: [
+                { label: shortLabel, description: "A short option" },
+              ],
+            },
+          ],
+        },
+      };
+
+      // #when
+      await hook["tool.execute.before"]?.(input as any, output as any);
+
+      // #then
+      const resultLabel = (output.args as any).questions[0].options[0].label;
+      expect(resultLabel).toBe(shortLabel);
+    });
+
+    it("handles exactly 30 character labels without truncation", async () => {
+      // #given
+      const exactLabel = "Exactly thirty chars here!!!!!"; // 30 chars
+      expect(exactLabel.length).toBe(30);
+      const input = { tool: "ask_user_question" };
+      const output = {
+        args: {
+          questions: [
+            {
+              question: "Choose",
+              options: [{ label: exactLabel }],
+            },
+          ],
+        },
+      };
+
+      // #when
+      await hook["tool.execute.before"]?.(input as any, output as any);
+
+      // #then
+      const resultLabel = (output.args as any).questions[0].options[0].label;
+      expect(resultLabel).toBe(exactLabel);
+    });
+
+    it("ignores non-AskUserQuestion tools", async () => {
+      // #given
+      const input = { tool: "Bash" };
+      const output = {
+        args: { command: "echo hello" },
+      };
+      const originalArgs = { ...output.args };
+
+      // #when
+      await hook["tool.execute.before"]?.(input as any, output as any);
+
+      // #then
+      expect(output.args).toEqual(originalArgs);
+    });
+
+    it("handles multiple questions with multiple options", async () => {
+      // #given
+      const input = { tool: "AskUserQuestion" };
+      const output = {
+        args: {
+          questions: [
+            {
+              question: "Q1",
+              options: [
+                { label: "Very long label number one that needs truncation" },
+                { label: "Short" },
+              ],
+            },
+            {
+              question: "Q2",
+              options: [
+                { label: "Another extremely long label for testing purposes" },
+              ],
+            },
+          ],
+        },
+      };
+
+      // #when
+      await hook["tool.execute.before"]?.(input as any, output as any);
+
+      // #then
+      const q1opts = (output.args as any).questions[0].options;
+      const q2opts = (output.args as any).questions[1].options;
+      
+      expect(q1opts[0].label).toBe("Very long label number one ...");
+      expect(q1opts[0].label.length).toBeLessThanOrEqual(30);
+      expect(q1opts[1].label).toBe("Short");
+      expect(q2opts[0].label).toBe("Another extremely long labe...");
+      expect(q2opts[0].label.length).toBeLessThanOrEqual(30);
+    });
+  });
+});

src/hooks/question-label-truncator/index.ts

@@ -0,0 +1,61 @@
+const MAX_LABEL_LENGTH = 30;
+
+interface QuestionOption {
+  label: string;
+  description?: string;
+}
+
+interface Question {
+  question: string;
+  header?: string;
+  options: QuestionOption[];
+  multiSelect?: boolean;
+}
+
+interface AskUserQuestionArgs {
+  questions: Question[];
+}
+
+function truncateLabel(label: string, maxLength: number = MAX_LABEL_LENGTH): string {
+  if (label.length <= maxLength) {
+    return label;
+  }
+  return label.substring(0, maxLength - 3) + "...";
+}
+
+function truncateQuestionLabels(args: AskUserQuestionArgs): AskUserQuestionArgs {
+  if (!args.questions || !Array.isArray(args.questions)) {
+    return args;
+  }
+
+  return {
+    ...args,
+    questions: args.questions.map((question) => ({
+      ...question,
+      options: question.options?.map((option) => ({
+        ...option,
+        label: truncateLabel(option.label),
+      })) ?? [],
+    })),
+  };
+}
+
+export function createQuestionLabelTruncatorHook() {
+  return {
+    "tool.execute.before": async (
+      input: { tool: string },
+      output: { args: Record<string, unknown> }
+    ): Promise<void> => {
+      const toolName = input.tool?.toLowerCase();
+
+      if (toolName === "askuserquestion" || toolName === "ask_user_question") {
+        const args = output.args as unknown as AskUserQuestionArgs | undefined;
+
+        if (args?.questions) {
+          const truncatedArgs = truncateQuestionLabels(args);
+          Object.assign(output.args, truncatedArgs);
+        }
+      }
+    },
+  };
+}

src/hooks/ralph-loop/index.test.ts

@@ -459,7 +459,7 @@ describe("ralph-loop", () => {
       })
       hook.startLoop("session-123", "Build something", { completionPromise: "COMPLETE" })
 
-      writeFileSync(transcriptPath, JSON.stringify({ content: "Task done <promise>COMPLETE</promise>" }))
+      writeFileSync(transcriptPath, JSON.stringify({ type: "tool_result", tool_name: "write", tool_output: { output: "Task done <promise>COMPLETE</promise>" } }) + "\n")
 
       // #when - session goes idle (transcriptPath now derived from sessionID via getTranscriptPath)
       await hook.event({
@@ -703,10 +703,105 @@ describe("ralph-loop", () => {
       expect(promptCalls[0].text).toContain("2/50")
     })
 
+    test("should NOT detect completion from user message in transcript (issue #622)", async () => {
+      // #given - transcript contains user message with template text that includes completion promise
+      // This reproduces the bug where the RALPH_LOOP_TEMPLATE instructional text
+      // containing `<promise>DONE</promise>` is recorded as a user message and
+      // falsely triggers completion detection
+      const transcriptPath = join(TEST_DIR, "transcript.jsonl")
+      const templateText = `You are starting a Ralph Loop...
+Output <promise>DONE</promise> when fully complete`
+      const userEntry = JSON.stringify({
+        type: "user",
+        timestamp: new Date().toISOString(),
+        content: templateText,
+      })
+      writeFileSync(transcriptPath, userEntry + "\n")
+
+      const hook = createRalphLoopHook(createMockPluginInput(), {
+        getTranscriptPath: () => transcriptPath,
+      })
+      hook.startLoop("session-123", "Build something", { completionPromise: "DONE" })
+
+      // #when - session goes idle
+      await hook.event({
+        event: {
+          type: "session.idle",
+          properties: { sessionID: "session-123" },
+        },
+      })
+
+      // #then - loop should CONTINUE (user message completion promise is instructional, not actual)
+      expect(promptCalls.length).toBe(1)
+      expect(hook.getState()?.iteration).toBe(2)
+    })
+
+    test("should NOT detect completion from continuation prompt in transcript (issue #622)", async () => {
+      // #given - transcript contains continuation prompt (also a user message) with completion promise
+      const transcriptPath = join(TEST_DIR, "transcript.jsonl")
+      const continuationText = `RALPH LOOP 2/100
+When FULLY complete, output: <promise>DONE</promise>
+Original task: Build something`
+      const userEntry = JSON.stringify({
+        type: "user",
+        timestamp: new Date().toISOString(),
+        content: continuationText,
+      })
+      writeFileSync(transcriptPath, userEntry + "\n")
+
+      const hook = createRalphLoopHook(createMockPluginInput(), {
+        getTranscriptPath: () => transcriptPath,
+      })
+      hook.startLoop("session-123", "Build something", { completionPromise: "DONE" })
+
+      // #when - session goes idle
+      await hook.event({
+        event: {
+          type: "session.idle",
+          properties: { sessionID: "session-123" },
+        },
+      })
+
+      // #then - loop should CONTINUE (continuation prompt text is not actual completion)
+      expect(promptCalls.length).toBe(1)
+      expect(hook.getState()?.iteration).toBe(2)
+    })
+
+    test("should detect completion from tool_result entry in transcript", async () => {
+      // #given - transcript contains a tool_result with completion promise
+      const transcriptPath = join(TEST_DIR, "transcript.jsonl")
+      const toolResultEntry = JSON.stringify({
+        type: "tool_result",
+        timestamp: new Date().toISOString(),
+        tool_name: "write",
+        tool_input: {},
+        tool_output: { output: "Task complete! <promise>DONE</promise>" },
+      })
+      writeFileSync(transcriptPath, toolResultEntry + "\n")
+
+      const hook = createRalphLoopHook(createMockPluginInput(), {
+        getTranscriptPath: () => transcriptPath,
+      })
+      hook.startLoop("session-123", "Build something", { completionPromise: "DONE" })
+
+      // #when - session goes idle
+      await hook.event({
+        event: {
+          type: "session.idle",
+          properties: { sessionID: "session-123" },
+        },
+      })
+
+      // #then - loop should complete (tool_result contains actual completion output)
+      expect(promptCalls.length).toBe(0)
+      expect(toastCalls.some((t) => t.title === "Ralph Loop Complete!")).toBe(true)
+      expect(hook.getState()).toBeNull()
+    })
+
     test("should check transcript BEFORE API to optimize performance", async () => {
       // #given - transcript has completion promise
       const transcriptPath = join(TEST_DIR, "transcript.jsonl")
-      writeFileSync(transcriptPath, JSON.stringify({ content: "<promise>DONE</promise>" }))
+      writeFileSync(transcriptPath, JSON.stringify({ type: "tool_result", tool_name: "write", tool_output: { output: "<promise>DONE</promise>" } }) + "\n")
       mockSessionMessages = [
         { info: { role: "assistant" }, parts: [{ type: "text", text: "No promise here" }] },
       ]
@@ -736,7 +831,7 @@ describe("ralph-loop", () => {
       const hook = createRalphLoopHook(createMockPluginInput(), {
         getTranscriptPath: () => transcriptPath,
       })
-      writeFileSync(transcriptPath, JSON.stringify({ content: "<promise>DONE</promise>" }))
+      writeFileSync(transcriptPath, JSON.stringify({ type: "tool_result", tool_name: "write", tool_output: { output: "<promise>DONE</promise>" } }) + "\n")
       hook.startLoop("test-id", "Build API", { ultrawork: true })
 
       // #when - idle event triggered
@@ -754,7 +849,7 @@ describe("ralph-loop", () => {
       const hook = createRalphLoopHook(createMockPluginInput(), {
         getTranscriptPath: () => transcriptPath,
       })
-      writeFileSync(transcriptPath, JSON.stringify({ content: "<promise>DONE</promise>" }))
+      writeFileSync(transcriptPath, JSON.stringify({ type: "tool_result", tool_name: "write", tool_output: { output: "<promise>DONE</promise>" } }) + "\n")
       hook.startLoop("test-id", "Build API")
 
       // #when - idle event triggered

src/hooks/ralph-loop/index.ts

@@ -100,7 +100,18 @@ export function createRalphLoopHook(
 
       const content = readFileSync(transcriptPath, "utf-8")
       const pattern = new RegExp(`<promise>\\s*${escapeRegex(promise)}\\s*</promise>`, "is")
-      return pattern.test(content)
+      const lines = content.split("\n").filter(l => l.trim())
+
+      for (const line of lines) {
+        try {
+          const entry = JSON.parse(line)
+          if (entry.type === "user") continue
+          if (pattern.test(line)) return true
+        } catch {
+          continue
+        }
+      }
+      return false
     } catch {
       return false
     }

src/hooks/start-work/index.test.ts

@@ -395,7 +395,7 @@ describe("start-work hook", () => {
       )
 
       // #then
-      expect(updateSpy).toHaveBeenCalledWith("ses-prometheus-to-sisyphus", "Atlas")
+      expect(updateSpy).toHaveBeenCalledWith("ses-prometheus-to-sisyphus", "atlas")
       updateSpy.mockRestore()
     })
   })

src/hooks/start-work/index.ts

@@ -71,7 +71,7 @@ export function createStartWorkHook(ctx: PluginInput) {
         sessionID: input.sessionID,
       })
 
-      updateSessionAgent(input.sessionID, "Atlas")
+      updateSessionAgent(input.sessionID, "atlas")
 
       const existingState = readBoulderState(ctx.directory)
       const sessionId = input.sessionID

src/hooks/task-resume-info/index.ts

@@ -16,21 +16,21 @@ function extractSessionId(output: string): string | null {
 }
 
 export function createTaskResumeInfoHook() {
-  const toolExecuteAfter = async (
-    input: { tool: string; sessionID: string; callID: string },
-    output: { title: string; output: string; metadata: unknown }
-  ) => {
-    if (!TARGET_TOOLS.includes(input.tool)) return
-    if (output.output.startsWith("Error:") || output.output.startsWith("Failed")) return
-    if (output.output.includes("\nto resume:")) return
+   const toolExecuteAfter = async (
+     input: { tool: string; sessionID: string; callID: string },
+     output: { title: string; output: string; metadata: unknown }
+   ) => {
+     if (!TARGET_TOOLS.includes(input.tool)) return
+     if (output.output.startsWith("Error:") || output.output.startsWith("Failed")) return
+     if (output.output.includes("\nto continue:")) return
 
-    const sessionId = extractSessionId(output.output)
-    if (!sessionId) return
+     const sessionId = extractSessionId(output.output)
+     if (!sessionId) return
 
-    output.output = output.output.trimEnd() + `\n\nto resume: delegate_task(resume="${sessionId}", prompt="...")`
-  }
+     output.output = output.output.trimEnd() + `\n\nto continue: delegate_task(session_id="${sessionId}", prompt="...")`
+   }
 
-  return {
-    "tool.execute.after": toolExecuteAfter,
-  }
+   return {
+     "tool.execute.after": toolExecuteAfter,
+   }
 }

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

@@ -103,7 +103,7 @@ describe("createThinkModeHook integration", () => {
         const hook = createThinkModeHook()
         const input = createMockInput(
           "github-copilot",
-          "gemini-3-pro-preview",
+          "gemini-3-pro",
           "think about this"
         )
 
@@ -112,7 +112,7 @@ describe("createThinkModeHook integration", () => {
 
         // #then should upgrade to high variant and inject google thinking config
         const message = input.message as MessageWithInjectedProps
-        expect(input.message.model?.modelID).toBe("gemini-3-pro-preview-high")
+        expect(input.message.model?.modelID).toBe("gemini-3-pro-high")
         expect(message.providerOptions).toBeDefined()
         const googleOptions = (
           message.providerOptions as Record<string, unknown>
@@ -125,7 +125,7 @@ describe("createThinkModeHook integration", () => {
         const hook = createThinkModeHook()
         const input = createMockInput(
           "github-copilot",
-          "gemini-3-flash-preview",
+          "gemini-3-flash",
           "ultrathink"
         )
 
@@ -134,7 +134,7 @@ describe("createThinkModeHook integration", () => {
 
         // #then should upgrade to high variant
         const message = input.message as MessageWithInjectedProps
-        expect(input.message.model?.modelID).toBe("gemini-3-flash-preview-high")
+        expect(input.message.model?.modelID).toBe("gemini-3-flash-high")
         expect(message.providerOptions).toBeDefined()
       })
     })

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

@@ -50,7 +50,7 @@ describe("think-mode switcher", () => {
     describe("Gemini models via github-copilot", () => {
       it("should resolve github-copilot Gemini Pro to google config", () => {
         // #given a github-copilot provider with Gemini Pro model
-        const config = getThinkingConfig("github-copilot", "gemini-3-pro-preview")
+        const config = getThinkingConfig("github-copilot", "gemini-3-pro")
 
         // #then should return google thinking config
         expect(config).not.toBeNull()
@@ -65,7 +65,7 @@ describe("think-mode switcher", () => {
         // #given a github-copilot provider with Gemini Flash model
         const config = getThinkingConfig(
           "github-copilot",
-          "gemini-3-flash-preview"
+          "gemini-3-flash"
         )
 
         // #then should return google thinking config
@@ -159,11 +159,11 @@ describe("think-mode switcher", () => {
 
       it("should handle Gemini preview variants", () => {
         // #given Gemini preview model IDs
-        expect(getHighVariant("gemini-3-pro-preview")).toBe(
-          "gemini-3-pro-preview-high"
+        expect(getHighVariant("gemini-3-pro")).toBe(
+          "gemini-3-pro-high"
         )
-        expect(getHighVariant("gemini-3-flash-preview")).toBe(
-          "gemini-3-flash-preview-high"
+        expect(getHighVariant("gemini-3-flash")).toBe(
+          "gemini-3-flash-high"
         )
       })
 

src/hooks/think-mode/switcher.ts

@@ -89,12 +89,10 @@ const HIGH_VARIANT_MAP: Record<string, string> = {
   // Claude
   "claude-sonnet-4-5": "claude-sonnet-4-5-high",
   "claude-opus-4-5": "claude-opus-4-5-high",
-  // Gemini
-  "gemini-3-pro": "gemini-3-pro-high",
-  "gemini-3-pro-low": "gemini-3-pro-high",
-  "gemini-3-pro-preview": "gemini-3-pro-preview-high",
-  "gemini-3-flash": "gemini-3-flash-high",
-  "gemini-3-flash-preview": "gemini-3-flash-preview-high",
+   // Gemini
+   "gemini-3-pro": "gemini-3-pro-high",
+   "gemini-3-pro-low": "gemini-3-pro-high",
+   "gemini-3-flash": "gemini-3-flash-high",
   // GPT-5
   "gpt-5": "gpt-5-high",
   "gpt-5-mini": "gpt-5-mini-high",

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

@@ -873,4 +873,193 @@ describe("todo-continuation-enforcer", () => {
     expect(promptCalls.length).toBe(1)
     expect(promptCalls[0].model).toEqual({ providerID: "openai", modelID: "gpt-5.2" })
   })
+
+  // ============================================================
+  // COMPACTION AGENT FILTERING TESTS
+  // These tests verify that compaction agent messages are filtered
+  // when resolving agent info, preventing infinite continuation loops
+  // ============================================================
+
+  test("should skip compaction agent messages when resolving agent info", async () => {
+    // #given - session where last message is from compaction agent but previous was Sisyphus
+    const sessionID = "main-compaction-filter"
+    setMainSession(sessionID)
+
+    const mockMessagesWithCompaction = [
+      { info: { id: "msg-1", role: "user", agent: "Sisyphus", model: { providerID: "anthropic", modelID: "claude-sonnet-4-5" } } },
+      { info: { id: "msg-2", role: "assistant", agent: "Sisyphus", modelID: "claude-sonnet-4-5", providerID: "anthropic" } },
+      { info: { id: "msg-3", role: "assistant", agent: "compaction", modelID: "claude-sonnet-4-5", providerID: "anthropic" } },
+    ]
+
+    const mockInput = {
+      client: {
+        session: {
+          todo: async () => ({
+            data: [{ id: "1", content: "Task 1", status: "pending", priority: "high" }],
+          }),
+          messages: async () => ({ data: mockMessagesWithCompaction }),
+          prompt: async (opts: any) => {
+            promptCalls.push({
+              sessionID: opts.path.id,
+              agent: opts.body.agent,
+              model: opts.body.model,
+              text: opts.body.parts[0].text,
+            })
+            return {}
+          },
+        },
+        tui: { showToast: async () => ({}) },
+      },
+      directory: "/tmp/test",
+    } as any
+
+    const hook = createTodoContinuationEnforcer(mockInput, {
+      backgroundManager: createMockBackgroundManager(false),
+    })
+
+    // #when - session goes idle
+    await hook.handler({ event: { type: "session.idle", properties: { sessionID } } })
+    await new Promise(r => setTimeout(r, 2500))
+
+    // #then - continuation uses Sisyphus (skipped compaction agent)
+    expect(promptCalls.length).toBe(1)
+    expect(promptCalls[0].agent).toBe("Sisyphus")
+  })
+
+  test("should skip injection when only compaction agent messages exist", async () => {
+    // #given - session with only compaction agent (post-compaction, no prior agent info)
+    const sessionID = "main-only-compaction"
+    setMainSession(sessionID)
+
+    const mockMessagesOnlyCompaction = [
+      { info: { id: "msg-1", role: "assistant", agent: "compaction" } },
+    ]
+
+    const mockInput = {
+      client: {
+        session: {
+          todo: async () => ({
+            data: [{ id: "1", content: "Task 1", status: "pending", priority: "high" }],
+          }),
+          messages: async () => ({ data: mockMessagesOnlyCompaction }),
+          prompt: async (opts: any) => {
+            promptCalls.push({
+              sessionID: opts.path.id,
+              agent: opts.body.agent,
+              model: opts.body.model,
+              text: opts.body.parts[0].text,
+            })
+            return {}
+          },
+        },
+        tui: { showToast: async () => ({}) },
+      },
+      directory: "/tmp/test",
+    } as any
+
+    const hook = createTodoContinuationEnforcer(mockInput, {})
+
+    // #when - session goes idle
+    await hook.handler({
+      event: { type: "session.idle", properties: { sessionID } },
+    })
+
+    await new Promise(r => setTimeout(r, 3000))
+
+    // #then - no continuation (compaction is in default skipAgents)
+    expect(promptCalls).toHaveLength(0)
+  })
+
+  test("should skip injection when prometheus agent is after compaction", async () => {
+    // #given - prometheus session that was compacted
+    const sessionID = "main-prometheus-compacted"
+    setMainSession(sessionID)
+
+    const mockMessagesPrometheusCompacted = [
+      { info: { id: "msg-1", role: "user", agent: "prometheus" } },
+      { info: { id: "msg-2", role: "assistant", agent: "prometheus" } },
+      { info: { id: "msg-3", role: "assistant", agent: "compaction" } },
+    ]
+
+    const mockInput = {
+      client: {
+        session: {
+          todo: async () => ({
+            data: [{ id: "1", content: "Task 1", status: "pending", priority: "high" }],
+          }),
+          messages: async () => ({ data: mockMessagesPrometheusCompacted }),
+          prompt: async (opts: any) => {
+            promptCalls.push({
+              sessionID: opts.path.id,
+              agent: opts.body.agent,
+              model: opts.body.model,
+              text: opts.body.parts[0].text,
+            })
+            return {}
+          },
+        },
+        tui: { showToast: async () => ({}) },
+      },
+      directory: "/tmp/test",
+    } as any
+
+    const hook = createTodoContinuationEnforcer(mockInput, {})
+
+    // #when - session goes idle
+    await hook.handler({
+      event: { type: "session.idle", properties: { sessionID } },
+    })
+
+    await new Promise(r => setTimeout(r, 3000))
+
+    // #then - no continuation (prometheus found after filtering compaction, prometheus is in skipAgents)
+    expect(promptCalls).toHaveLength(0)
+  })
+
+  test("should inject when agent info is undefined but skipAgents is empty", async () => {
+    // #given - session with no agent info but skipAgents is empty
+    const sessionID = "main-no-agent-no-skip"
+    setMainSession(sessionID)
+
+    const mockMessagesNoAgent = [
+      { info: { id: "msg-1", role: "user" } },
+      { info: { id: "msg-2", role: "assistant" } },
+    ]
+
+    const mockInput = {
+      client: {
+        session: {
+          todo: async () => ({
+            data: [{ id: "1", content: "Task 1", status: "pending", priority: "high" }],
+          }),
+          messages: async () => ({ data: mockMessagesNoAgent }),
+          prompt: async (opts: any) => {
+            promptCalls.push({
+              sessionID: opts.path.id,
+              agent: opts.body.agent,
+              model: opts.body.model,
+              text: opts.body.parts[0].text,
+            })
+            return {}
+          },
+        },
+        tui: { showToast: async () => ({}) },
+      },
+      directory: "/tmp/test",
+    } as any
+
+    const hook = createTodoContinuationEnforcer(mockInput, {
+      skipAgents: [],
+    })
+
+    // #when - session goes idle
+    await hook.handler({
+      event: { type: "session.idle", properties: { sessionID } },
+    })
+
+    await new Promise(r => setTimeout(r, 3000))
+
+    // #then - continuation injected (no agents to skip)
+    expect(promptCalls.length).toBe(1)
+  })
 })

src/hooks/todo-continuation-enforcer.ts

@@ -13,7 +13,7 @@ import { createSystemDirective, SystemDirectiveTypes } from "../shared/system-di
 
 const HOOK_NAME = "todo-continuation-enforcer"
 
-const DEFAULT_SKIP_AGENTS = ["Prometheus (Planner)"]
+const DEFAULT_SKIP_AGENTS = ["prometheus", "compaction"]
 
 export interface TodoContinuationEnforcerOptions {
   backgroundManager?: BackgroundManager
@@ -373,6 +373,7 @@ export function createTodoContinuationEnforcer(
       }
 
       let resolvedInfo: ResolvedMessageInfo | undefined
+      let hasCompactionMessage = false
       try {
         const messagesResp = await ctx.client.session.messages({
           path: { id: sessionID },
@@ -388,6 +389,10 @@ export function createTodoContinuationEnforcer(
         }>
         for (let i = messages.length - 1; i >= 0; i--) {
           const info = messages[i].info
+          if (info?.agent === "compaction") {
+            hasCompactionMessage = true
+            continue
+          }
           if (info?.agent || info?.model || (info?.modelID && info?.providerID)) {
             resolvedInfo = {
               agent: info.agent,
@@ -401,11 +406,15 @@ export function createTodoContinuationEnforcer(
         log(`[${HOOK_NAME}] Failed to fetch messages for agent check`, { sessionID, error: String(err) })
       }
 
-      log(`[${HOOK_NAME}] Agent check`, { sessionID, agentName: resolvedInfo?.agent, skipAgents })
+      log(`[${HOOK_NAME}] Agent check`, { sessionID, agentName: resolvedInfo?.agent, skipAgents, hasCompactionMessage })
       if (resolvedInfo?.agent && skipAgents.includes(resolvedInfo.agent)) {
         log(`[${HOOK_NAME}] Skipped: agent in skipAgents list`, { sessionID, agent: resolvedInfo.agent })
         return
       }
+      if (hasCompactionMessage && !resolvedInfo?.agent) {
+        log(`[${HOOK_NAME}] Skipped: compaction occurred but no agent info resolved`, { sessionID })
+        return
+      }
 
       startCountdown(sessionID, incompleteCount, todos.length, resolvedInfo)
       return

src/index.test.ts

@@ -0,0 +1,81 @@
+import { describe, expect, it } from "bun:test"
+import { includesCaseInsensitive } from "./shared"
+
+/**
+ * Tests for conditional tool registration logic in index.ts
+ * 
+ * The actual plugin initialization is complex to test directly,
+ * so we test the underlying logic that determines tool registration.
+ */
+describe("look_at tool conditional registration", () => {
+  describe("isMultimodalLookerEnabled logic", () => {
+    // #given multimodal-looker is in disabled_agents
+    // #when checking if agent is enabled
+    // #then should return false (disabled)
+    it("returns false when multimodal-looker is disabled (exact case)", () => {
+      const disabledAgents = ["multimodal-looker"]
+      const isEnabled = !includesCaseInsensitive(disabledAgents, "multimodal-looker")
+      expect(isEnabled).toBe(false)
+    })
+
+    // #given multimodal-looker is in disabled_agents with different case
+    // #when checking if agent is enabled
+    // #then should return false (case-insensitive match)
+    it("returns false when multimodal-looker is disabled (case-insensitive)", () => {
+      const disabledAgents = ["Multimodal-Looker"]
+      const isEnabled = !includesCaseInsensitive(disabledAgents, "multimodal-looker")
+      expect(isEnabled).toBe(false)
+    })
+
+    // #given multimodal-looker is NOT in disabled_agents
+    // #when checking if agent is enabled
+    // #then should return true (enabled)
+    it("returns true when multimodal-looker is not disabled", () => {
+      const disabledAgents = ["oracle", "librarian"]
+      const isEnabled = !includesCaseInsensitive(disabledAgents, "multimodal-looker")
+      expect(isEnabled).toBe(true)
+    })
+
+    // #given disabled_agents is empty
+    // #when checking if agent is enabled
+    // #then should return true (enabled by default)
+    it("returns true when disabled_agents is empty", () => {
+      const disabledAgents: string[] = []
+      const isEnabled = !includesCaseInsensitive(disabledAgents, "multimodal-looker")
+      expect(isEnabled).toBe(true)
+    })
+
+    // #given disabled_agents is undefined (simulated as empty array)
+    // #when checking if agent is enabled
+    // #then should return true (enabled by default)
+    it("returns true when disabled_agents is undefined (fallback to empty)", () => {
+      const disabledAgents = undefined
+      const isEnabled = !includesCaseInsensitive(disabledAgents ?? [], "multimodal-looker")
+      expect(isEnabled).toBe(true)
+    })
+  })
+
+  describe("conditional tool spread pattern", () => {
+    // #given lookAt is not null (agent enabled)
+    // #when spreading into tool object
+    // #then look_at should be included
+    it("includes look_at when lookAt is not null", () => {
+      const lookAt = { execute: () => {} } // mock tool
+      const tools = {
+        ...(lookAt ? { look_at: lookAt } : {}),
+      }
+      expect(tools).toHaveProperty("look_at")
+    })
+
+    // #given lookAt is null (agent disabled)
+    // #when spreading into tool object
+    // #then look_at should NOT be included
+    it("excludes look_at when lookAt is null", () => {
+      const lookAt = null
+      const tools = {
+        ...(lookAt ? { look_at: lookAt } : {}),
+      }
+      expect(tools).not.toHaveProperty("look_at")
+    })
+  })
+})

src/index.ts

@@ -31,6 +31,7 @@ import {
   createStartWorkHook,
   createAtlasHook,
   createPrometheusMdOnlyHook,
+  createQuestionLabelTruncatorHook,
 } from "./hooks";
 import {
   contextCollector,
@@ -79,6 +80,7 @@ import { createModelCacheState, getModelLimit } from "./plugin-state";
 import { createConfigHandler } from "./plugin-handlers";
 
 const OhMyOpenCodePlugin: Plugin = async (ctx) => {
+  log("[OhMyOpenCodePlugin] ENTRY - plugin loading", { directory: ctx.directory })
   // Start background tmux check immediately
   startTmuxCheck();
 
@@ -198,17 +200,19 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
     ? createStartWorkHook(ctx)
     : null;
 
-  const atlasHook = isHookEnabled("atlas")
-    ? createAtlasHook(ctx)
-    : null;
-
   const prometheusMdOnly = isHookEnabled("prometheus-md-only")
     ? createPrometheusMdOnlyHook(ctx)
     : null;
 
+  const questionLabelTruncator = createQuestionLabelTruncatorHook();
+
   const taskResumeInfo = createTaskResumeInfoHook();
 
-  const backgroundManager = new BackgroundManager(ctx);
+  const backgroundManager = new BackgroundManager(ctx, pluginConfig.background_task);
+
+  const atlasHook = isHookEnabled("atlas")
+    ? createAtlasHook(ctx, { directory: ctx.directory, backgroundManager })
+    : null;
 
   initTaskToastManager(ctx.client);
 
@@ -229,13 +233,18 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
   const backgroundTools = createBackgroundTools(backgroundManager, ctx.client);
 
   const callOmoAgent = createCallOmoAgent(ctx, backgroundManager);
-  const lookAt = createLookAt(ctx);
+  const isMultimodalLookerEnabled = !includesCaseInsensitive(
+    pluginConfig.disabled_agents ?? [],
+    "multimodal-looker"
+  );
+  const lookAt = isMultimodalLookerEnabled ? createLookAt(ctx) : null;
   const delegateTask = createDelegateTask({
     manager: backgroundManager,
     client: ctx.client,
     directory: ctx.directory,
     userCategories: pluginConfig.categories,
     gitMasterConfig: pluginConfig.git_master,
+    sisyphusJuniorModel: pluginConfig.agents?.["sisyphus-junior"]?.model,
   });
   const disabledSkills = new Set(pluginConfig.disabled_skills ?? []);
   const systemMcpNames = getSystemMcpServerNames();
@@ -298,7 +307,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
       ...builtinTools,
       ...backgroundTools,
       call_omo_agent: callOmoAgent,
-      look_at: lookAt,
+      ...(lookAt ? { look_at: lookAt } : {}),
       delegate_task: delegateTask,
       skill: skillTool,
       skill_mcp: skillMcpTool,
@@ -308,7 +317,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
 
     "chat.message": async (input, output) => {
       if (input.agent) {
-        updateSessionAgent(input.sessionID, input.agent);
+        setSessionAgent(input.sessionID, input.agent);
       }
 
       const message = (output as { message: { variant?: string } }).message
@@ -478,6 +487,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
     },
 
     "tool.execute.before": async (input, output) => {
+      await questionLabelTruncator["tool.execute.before"]?.(input, output);
       await claudeCodeHooks["tool.execute.before"](input, output);
       await nonInteractiveEnv?.["tool.execute.before"](input, output);
       await commentChecker?.["tool.execute.before"](input, output);
@@ -485,6 +495,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
       await directoryReadmeInjector?.["tool.execute.before"]?.(input, output);
       await rulesInjector?.["tool.execute.before"]?.(input, output);
       await prometheusMdOnly?.["tool.execute.before"]?.(input, output);
+      await atlasHook?.["tool.execute.before"]?.(input, output);
 
       if (input.tool === "task") {
         const args = output.args as Record<string, unknown>;

src/plugin-config.test.ts

@@ -27,7 +27,7 @@ describe("mergeConfigs", () => {
             temperature: 0.3,
           },
           visual: {
-            model: "google/gemini-3-pro-preview",
+            model: "google/gemini-3-pro",
           },
         },
       } as unknown as OhMyOpenCodeConfig;
@@ -41,7 +41,7 @@ describe("mergeConfigs", () => {
       // #then quick should be preserved from base
       expect(result.categories?.quick?.model).toBe("anthropic/claude-haiku-4-5");
       // #then visual should be added from override
-      expect(result.categories?.visual?.model).toBe("google/gemini-3-pro-preview");
+      expect(result.categories?.visual?.model).toBe("google/gemini-3-pro");
     });
 
     it("should preserve base categories when override has no categories", () => {

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

@@ -25,7 +25,7 @@ describe("Prometheus category config resolution", () => {
 
     // #then
     expect(config).toBeDefined()
-    expect(config?.model).toBe("google/gemini-3-pro-preview")
+    expect(config?.model).toBe("google/gemini-3-pro")
   })
 
   test("user categories override default categories", () => {

src/plugin-handlers/config-handler.ts

@@ -106,13 +106,38 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
     }
 
     if (!(config.model as string | undefined)?.trim()) {
-      const paths = getOpenCodeConfigPaths({ binary: "opencode", version: null })
-      throw new Error(
-        'oh-my-opencode requires a default model.\n\n' +
-        `Add this to ${paths.configJsonc}:\n\n` +
-        '  "model": "anthropic/claude-sonnet-4-5"\n\n' +
-        '(Replace with your preferred provider/model)'
-      )
+      let fallbackModel: string | undefined
+
+      for (const agentConfig of Object.values(pluginConfig.agents ?? {})) {
+        const model = (agentConfig as { model?: string })?.model
+        if (model && typeof model === 'string' && model.trim()) {
+          fallbackModel = model.trim()
+          break
+        }
+      }
+
+      if (!fallbackModel) {
+        for (const categoryConfig of Object.values(pluginConfig.categories ?? {})) {
+          const model = (categoryConfig as { model?: string })?.model
+          if (model && typeof model === 'string' && model.trim()) {
+            fallbackModel = model.trim()
+            break
+          }
+        }
+      }
+
+      if (fallbackModel) {
+        config.model = fallbackModel
+        log(`No default model specified, using fallback from config: ${fallbackModel}`)
+      } else {
+        const paths = getOpenCodeConfigPaths({ binary: "opencode", version: null })
+        throw new Error(
+          'oh-my-opencode requires a default model.\n\n' +
+          `Add this to ${paths.configJsonc}:\n\n` +
+          '  "model": "anthropic/claude-sonnet-4-5"\n\n' +
+          '(Replace with your preferred provider/model)'
+        )
+      }
     }
 
     // Migrate disabled_agents from old names to new names
@@ -186,20 +211,20 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
       explore?: { tools?: Record<string, unknown> };
       librarian?: { tools?: Record<string, unknown> };
       "multimodal-looker"?: { tools?: Record<string, unknown> };
-      Atlas?: { tools?: Record<string, unknown> };
-      Sisyphus?: { tools?: Record<string, unknown> };
+      atlas?: { tools?: Record<string, unknown> };
+      sisyphus?: { tools?: Record<string, unknown> };
     };
     const configAgent = config.agent as AgentConfig | undefined;
 
-    if (isSisyphusEnabled && builtinAgents.Sisyphus) {
-      (config as { default_agent?: string }).default_agent = "Sisyphus";
+    if (isSisyphusEnabled && builtinAgents.sisyphus) {
+      (config as { default_agent?: string }).default_agent = "sisyphus";
 
       const agentConfig: Record<string, unknown> = {
-        Sisyphus: builtinAgents.Sisyphus,
+        sisyphus: builtinAgents.sisyphus,
       };
 
-      agentConfig["Sisyphus-Junior"] = createSisyphusJuniorAgentWithOverrides(
-        pluginConfig.agents?.["Sisyphus-Junior"],
+      agentConfig["sisyphus-junior"] = createSisyphusJuniorAgentWithOverrides(
+        pluginConfig.agents?.["sisyphus-junior"],
         config.model as string | undefined
       );
 
@@ -228,7 +253,7 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
           planConfigWithoutName as Record<string, unknown>
         );
         const prometheusOverride =
-          pluginConfig.agents?.["Prometheus (Planner)"] as
+          pluginConfig.agents?.["prometheus"] as
             | (Record<string, unknown> & { category?: string; model?: string })
             | undefined;
         const defaultModel = config.model as string | undefined;
@@ -275,7 +300,7 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
             : {}),
         };
 
-        agentConfig["Prometheus (Planner)"] = prometheusOverride
+        agentConfig["prometheus"] = prometheusOverride
           ? { ...prometheusBase, ...prometheusOverride }
           : prometheusBase;
       }
@@ -310,7 +335,7 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
       config.agent = {
         ...agentConfig,
         ...Object.fromEntries(
-          Object.entries(builtinAgents).filter(([k]) => k !== "Sisyphus")
+          Object.entries(builtinAgents).filter(([k]) => k !== "sisyphus")
         ),
         ...userAgents,
         ...projectAgents,
@@ -349,20 +374,20 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
       const agent = agentResult["multimodal-looker"] as AgentWithPermission;
       agent.permission = { ...agent.permission, task: "deny", look_at: "deny" };
     }
-    if (agentResult["Atlas"]) {
-      const agent = agentResult["Atlas"] as AgentWithPermission;
+    if (agentResult["atlas"]) {
+      const agent = agentResult["atlas"] as AgentWithPermission;
       agent.permission = { ...agent.permission, task: "deny", call_omo_agent: "deny", delegate_task: "allow" };
     }
-    if (agentResult.Sisyphus) {
-      const agent = agentResult.Sisyphus as AgentWithPermission;
+    if (agentResult.sisyphus) {
+      const agent = agentResult.sisyphus as AgentWithPermission;
       agent.permission = { ...agent.permission, call_omo_agent: "deny", delegate_task: "allow", question: "allow" };
     }
-    if (agentResult["Prometheus (Planner)"]) {
-      const agent = agentResult["Prometheus (Planner)"] as AgentWithPermission;
+    if (agentResult["prometheus"]) {
+      const agent = agentResult["prometheus"] as AgentWithPermission;
       agent.permission = { ...agent.permission, call_omo_agent: "deny", delegate_task: "allow", question: "allow" };
     }
-    if (agentResult["Sisyphus-Junior"]) {
-      const agent = agentResult["Sisyphus-Junior"] as AgentWithPermission;
+    if (agentResult["sisyphus-junior"]) {
+      const agent = agentResult["sisyphus-junior"] as AgentWithPermission;
       agent.permission = { ...agent.permission, delegate_task: "allow" };
     }
 

src/shared/AGENTS.md

@@ -2,7 +2,7 @@
 
 ## OVERVIEW
 
-50 cross-cutting utilities: path resolution, token truncation, config parsing, model resolution.
+34 cross-cutting utilities: path resolution, token truncation, config parsing, model resolution, agent display names.
 
 ## STRUCTURE
 
@@ -19,12 +19,27 @@ shared/
 ├── migration.ts           # Legacy config migration
 ├── opencode-version.ts    # Version comparison
 ├── external-plugin-detector.ts # OAuth spoofing detection
-├── env-expander.ts        # ${VAR} expansion
 ├── model-requirements.ts  # Agent/Category requirements
 ├── model-availability.ts  # Models fetch + fuzzy match
 ├── model-resolver.ts      # 3-step resolution
+├── model-sanitizer.ts     # Model ID normalization
 ├── shell-env.ts           # Cross-platform shell
-├── prompt-parts-helper.ts # Prompt manipulation
+├── agent-display-names.ts # Agent display name mapping
+├── agent-tool-restrictions.ts # Tool restriction helpers
+├── agent-variant.ts       # Agent variant detection
+├── command-executor.ts    # Subprocess execution
+├── config-errors.ts       # Config error types
+├── deep-merge.ts          # Deep object merge
+├── file-reference-resolver.ts # File path resolution
+├── file-utils.ts          # File utilities
+├── hook-disabled.ts       # Hook enable/disable check
+├── pattern-matcher.ts     # Glob pattern matching
+├── session-cursor.ts      # Session cursor tracking
+├── snake-case.ts          # String case conversion
+├── system-directive.ts    # System prompt helpers
+├── tool-name.ts           # Tool name constants
+├── zip-extractor.ts       # ZIP file extraction
+├── index.ts               # Barrel export
 └── *.test.ts              # Colocated tests
 ```
 
@@ -40,6 +55,7 @@ shared/
 | Resolve paths | `getOpenCodeConfigDir()` |
 | Compare versions | `isOpenCodeVersionAtLeast("1.1.0")` |
 | Resolve model | `resolveModelWithFallback()` |
+| Agent display name | `getAgentDisplayName(agentName)` |
 
 ## PATTERNS
 

src/shared/agent-config-integration.test.ts

@@ -0,0 +1,224 @@
+import { describe, test, expect } from "bun:test"
+import { migrateAgentNames } from "./migration"
+import { getAgentDisplayName } from "./agent-display-names"
+import { AGENT_MODEL_REQUIREMENTS } from "./model-requirements"
+
+describe("Agent Config Integration", () => {
+  describe("Old format config migration", () => {
+    test("migrates old format agent keys to lowercase", () => {
+      // #given - config with old format keys
+      const oldConfig = {
+        Sisyphus: { model: "anthropic/claude-opus-4-5" },
+        Atlas: { model: "anthropic/claude-opus-4-5" },
+        "Prometheus (Planner)": { model: "anthropic/claude-opus-4-5" },
+        "Metis (Plan Consultant)": { model: "anthropic/claude-sonnet-4-5" },
+        "Momus (Plan Reviewer)": { model: "anthropic/claude-sonnet-4-5" },
+      }
+
+      // #when - migration is applied
+      const result = migrateAgentNames(oldConfig)
+
+      // #then - keys are lowercase
+      expect(result.migrated).toHaveProperty("sisyphus")
+      expect(result.migrated).toHaveProperty("atlas")
+      expect(result.migrated).toHaveProperty("prometheus")
+      expect(result.migrated).toHaveProperty("metis")
+      expect(result.migrated).toHaveProperty("momus")
+
+      // #then - old keys are removed
+      expect(result.migrated).not.toHaveProperty("Sisyphus")
+      expect(result.migrated).not.toHaveProperty("Atlas")
+      expect(result.migrated).not.toHaveProperty("Prometheus (Planner)")
+      expect(result.migrated).not.toHaveProperty("Metis (Plan Consultant)")
+      expect(result.migrated).not.toHaveProperty("Momus (Plan Reviewer)")
+
+      // #then - values are preserved
+      expect(result.migrated.sisyphus).toEqual({ model: "anthropic/claude-opus-4-5" })
+      expect(result.migrated.atlas).toEqual({ model: "anthropic/claude-opus-4-5" })
+      expect(result.migrated.prometheus).toEqual({ model: "anthropic/claude-opus-4-5" })
+      
+      // #then - changed flag is true
+      expect(result.changed).toBe(true)
+    })
+
+    test("preserves already lowercase keys", () => {
+      // #given - config with lowercase keys
+      const config = {
+        sisyphus: { model: "anthropic/claude-opus-4-5" },
+        oracle: { model: "openai/gpt-5.2" },
+        librarian: { model: "opencode/big-pickle" },
+      }
+
+      // #when - migration is applied
+      const result = migrateAgentNames(config)
+
+      // #then - keys remain unchanged
+      expect(result.migrated).toEqual(config)
+      
+      // #then - changed flag is false
+      expect(result.changed).toBe(false)
+    })
+
+    test("handles mixed case config", () => {
+      // #given - config with mixed old and new format
+      const mixedConfig = {
+        Sisyphus: { model: "anthropic/claude-opus-4-5" },
+        oracle: { model: "openai/gpt-5.2" },
+        "Prometheus (Planner)": { model: "anthropic/claude-opus-4-5" },
+        librarian: { model: "opencode/big-pickle" },
+      }
+
+      // #when - migration is applied
+      const result = migrateAgentNames(mixedConfig)
+
+      // #then - all keys are lowercase
+      expect(result.migrated).toHaveProperty("sisyphus")
+      expect(result.migrated).toHaveProperty("oracle")
+      expect(result.migrated).toHaveProperty("prometheus")
+      expect(result.migrated).toHaveProperty("librarian")
+      expect(Object.keys(result.migrated).every((key) => key === key.toLowerCase())).toBe(true)
+      
+      // #then - changed flag is true
+      expect(result.changed).toBe(true)
+    })
+  })
+
+  describe("Display name resolution", () => {
+    test("returns correct display names for all builtin agents", () => {
+      // #given - lowercase config keys
+      const agents = ["sisyphus", "atlas", "prometheus", "metis", "momus", "oracle", "librarian", "explore", "multimodal-looker"]
+
+      // #when - display names are requested
+      const displayNames = agents.map((agent) => getAgentDisplayName(agent))
+
+      // #then - display names are correct
+      expect(displayNames).toContain("Sisyphus (Ultraworker)")
+      expect(displayNames).toContain("Atlas (Plan Execution Orchestrator)")
+      expect(displayNames).toContain("Prometheus (Plan Builder)")
+      expect(displayNames).toContain("Metis (Plan Consultant)")
+      expect(displayNames).toContain("Momus (Plan Reviewer)")
+      expect(displayNames).toContain("oracle")
+      expect(displayNames).toContain("librarian")
+      expect(displayNames).toContain("explore")
+      expect(displayNames).toContain("multimodal-looker")
+    })
+
+    test("handles lowercase keys case-insensitively", () => {
+      // #given - various case formats of lowercase keys
+      const keys = ["Sisyphus", "Atlas", "SISYPHUS", "atlas", "prometheus", "PROMETHEUS"]
+
+      // #when - display names are requested
+      const displayNames = keys.map((key) => getAgentDisplayName(key))
+
+      // #then - correct display names are returned
+      expect(displayNames[0]).toBe("Sisyphus (Ultraworker)")
+      expect(displayNames[1]).toBe("Atlas (Plan Execution Orchestrator)")
+      expect(displayNames[2]).toBe("Sisyphus (Ultraworker)")
+      expect(displayNames[3]).toBe("Atlas (Plan Execution Orchestrator)")
+      expect(displayNames[4]).toBe("Prometheus (Plan Builder)")
+      expect(displayNames[5]).toBe("Prometheus (Plan Builder)")
+    })
+
+    test("returns original key for unknown agents", () => {
+      // #given - unknown agent key
+      const unknownKey = "custom-agent"
+
+      // #when - display name is requested
+      const displayName = getAgentDisplayName(unknownKey)
+
+      // #then - original key is returned
+      expect(displayName).toBe(unknownKey)
+    })
+  })
+
+  describe("Model requirements integration", () => {
+    test("all model requirements use lowercase keys", () => {
+      // #given - AGENT_MODEL_REQUIREMENTS object
+      const agentKeys = Object.keys(AGENT_MODEL_REQUIREMENTS)
+
+      // #when - checking key format
+      const allLowercase = agentKeys.every((key) => key === key.toLowerCase())
+
+      // #then - all keys are lowercase
+      expect(allLowercase).toBe(true)
+    })
+
+    test("model requirements include all builtin agents", () => {
+      // #given - expected builtin agents
+      const expectedAgents = ["sisyphus", "atlas", "prometheus", "metis", "momus", "oracle", "librarian", "explore", "multimodal-looker"]
+
+      // #when - checking AGENT_MODEL_REQUIREMENTS
+      const agentKeys = Object.keys(AGENT_MODEL_REQUIREMENTS)
+
+      // #then - all expected agents are present
+      for (const agent of expectedAgents) {
+        expect(agentKeys).toContain(agent)
+      }
+    })
+
+    test("no uppercase keys in model requirements", () => {
+      // #given - AGENT_MODEL_REQUIREMENTS object
+      const agentKeys = Object.keys(AGENT_MODEL_REQUIREMENTS)
+
+      // #when - checking for uppercase keys
+      const uppercaseKeys = agentKeys.filter((key) => key !== key.toLowerCase())
+
+      // #then - no uppercase keys exist
+      expect(uppercaseKeys).toEqual([])
+    })
+  })
+
+  describe("End-to-end config flow", () => {
+    test("old config migrates and displays correctly", () => {
+      // #given - old format config
+      const oldConfig = {
+        Sisyphus: { model: "anthropic/claude-opus-4-5", temperature: 0.1 },
+        "Prometheus (Planner)": { model: "anthropic/claude-opus-4-5" },
+      }
+
+      // #when - config is migrated
+      const result = migrateAgentNames(oldConfig)
+
+      // #then - keys are lowercase
+      expect(result.migrated).toHaveProperty("sisyphus")
+      expect(result.migrated).toHaveProperty("prometheus")
+
+      // #when - display names are retrieved
+      const sisyphusDisplay = getAgentDisplayName("sisyphus")
+      const prometheusDisplay = getAgentDisplayName("prometheus")
+
+      // #then - display names are correct
+      expect(sisyphusDisplay).toBe("Sisyphus (Ultraworker)")
+      expect(prometheusDisplay).toBe("Prometheus (Plan Builder)")
+
+      // #then - config values are preserved
+      expect(result.migrated.sisyphus).toEqual({ model: "anthropic/claude-opus-4-5", temperature: 0.1 })
+      expect(result.migrated.prometheus).toEqual({ model: "anthropic/claude-opus-4-5" })
+    })
+
+    test("new config works without migration", () => {
+      // #given - new format config (already lowercase)
+      const newConfig = {
+        sisyphus: { model: "anthropic/claude-opus-4-5" },
+        atlas: { model: "anthropic/claude-opus-4-5" },
+      }
+
+      // #when - migration is applied (should be no-op)
+      const result = migrateAgentNames(newConfig)
+
+      // #then - config is unchanged
+      expect(result.migrated).toEqual(newConfig)
+      
+      // #then - changed flag is false
+      expect(result.changed).toBe(false)
+
+      // #when - display names are retrieved
+      const sisyphusDisplay = getAgentDisplayName("sisyphus")
+      const atlasDisplay = getAgentDisplayName("atlas")
+
+      // #then - display names are correct
+      expect(sisyphusDisplay).toBe("Sisyphus (Ultraworker)")
+      expect(atlasDisplay).toBe("Atlas (Plan Execution Orchestrator)")
+    })
+  })
+})

src/shared/agent-display-names.test.ts

@@ -0,0 +1,158 @@
+import { describe, it, expect } from "bun:test"
+import { AGENT_DISPLAY_NAMES, getAgentDisplayName } from "./agent-display-names"
+
+describe("getAgentDisplayName", () => {
+  it("returns display name for lowercase config key (new format)", () => {
+    // #given config key "sisyphus"
+    const configKey = "sisyphus"
+
+    // #when getAgentDisplayName called
+    const result = getAgentDisplayName(configKey)
+
+    // #then returns "Sisyphus (Ultraworker)"
+    expect(result).toBe("Sisyphus (Ultraworker)")
+  })
+
+  it("returns display name for uppercase config key (old format - case-insensitive)", () => {
+    // #given config key "Sisyphus" (old format)
+    const configKey = "Sisyphus"
+
+    // #when getAgentDisplayName called
+    const result = getAgentDisplayName(configKey)
+
+    // #then returns "Sisyphus (Ultraworker)" (case-insensitive lookup)
+    expect(result).toBe("Sisyphus (Ultraworker)")
+  })
+
+  it("returns original key for unknown agents (fallback)", () => {
+    // #given config key "custom-agent"
+    const configKey = "custom-agent"
+
+    // #when getAgentDisplayName called
+    const result = getAgentDisplayName(configKey)
+
+    // #then returns "custom-agent" (original key unchanged)
+    expect(result).toBe("custom-agent")
+  })
+
+  it("returns display name for atlas", () => {
+    // #given config key "atlas"
+    const configKey = "atlas"
+
+    // #when getAgentDisplayName called
+    const result = getAgentDisplayName(configKey)
+
+    // #then returns "Atlas (Plan Execution Orchestrator)"
+    expect(result).toBe("Atlas (Plan Execution Orchestrator)")
+  })
+
+  it("returns display name for prometheus", () => {
+    // #given config key "prometheus"
+    const configKey = "prometheus"
+
+    // #when getAgentDisplayName called
+    const result = getAgentDisplayName(configKey)
+
+    // #then returns "Prometheus (Plan Builder)"
+    expect(result).toBe("Prometheus (Plan Builder)")
+  })
+
+  it("returns display name for sisyphus-junior", () => {
+    // #given config key "sisyphus-junior"
+    const configKey = "sisyphus-junior"
+
+    // #when getAgentDisplayName called
+    const result = getAgentDisplayName(configKey)
+
+    // #then returns "Sisyphus-Junior"
+    expect(result).toBe("Sisyphus-Junior")
+  })
+
+  it("returns display name for metis", () => {
+    // #given config key "metis"
+    const configKey = "metis"
+
+    // #when getAgentDisplayName called
+    const result = getAgentDisplayName(configKey)
+
+    // #then returns "Metis (Plan Consultant)"
+    expect(result).toBe("Metis (Plan Consultant)")
+  })
+
+  it("returns display name for momus", () => {
+    // #given config key "momus"
+    const configKey = "momus"
+
+    // #when getAgentDisplayName called
+    const result = getAgentDisplayName(configKey)
+
+    // #then returns "Momus (Plan Reviewer)"
+    expect(result).toBe("Momus (Plan Reviewer)")
+  })
+
+  it("returns display name for oracle", () => {
+    // #given config key "oracle"
+    const configKey = "oracle"
+
+    // #when getAgentDisplayName called
+    const result = getAgentDisplayName(configKey)
+
+    // #then returns "oracle"
+    expect(result).toBe("oracle")
+  })
+
+  it("returns display name for librarian", () => {
+    // #given config key "librarian"
+    const configKey = "librarian"
+
+    // #when getAgentDisplayName called
+    const result = getAgentDisplayName(configKey)
+
+    // #then returns "librarian"
+    expect(result).toBe("librarian")
+  })
+
+  it("returns display name for explore", () => {
+    // #given config key "explore"
+    const configKey = "explore"
+
+    // #when getAgentDisplayName called
+    const result = getAgentDisplayName(configKey)
+
+    // #then returns "explore"
+    expect(result).toBe("explore")
+  })
+
+  it("returns display name for multimodal-looker", () => {
+    // #given config key "multimodal-looker"
+    const configKey = "multimodal-looker"
+
+    // #when getAgentDisplayName called
+    const result = getAgentDisplayName(configKey)
+
+    // #then returns "multimodal-looker"
+    expect(result).toBe("multimodal-looker")
+  })
+})
+
+describe("AGENT_DISPLAY_NAMES", () => {
+  it("contains all expected agent mappings", () => {
+    // #given expected mappings
+    const expectedMappings = {
+      sisyphus: "Sisyphus (Ultraworker)",
+      atlas: "Atlas (Plan Execution Orchestrator)",
+      prometheus: "Prometheus (Plan Builder)",
+      "sisyphus-junior": "Sisyphus-Junior",
+      metis: "Metis (Plan Consultant)",
+      momus: "Momus (Plan Reviewer)",
+      oracle: "oracle",
+      librarian: "librarian",
+      explore: "explore",
+      "multimodal-looker": "multimodal-looker",
+    }
+
+    // #when checking the constant
+    // #then contains all expected mappings
+    expect(AGENT_DISPLAY_NAMES).toEqual(expectedMappings)
+  })
+})

src/shared/agent-display-names.ts

@@ -0,0 +1,37 @@
+/**
+ * Agent config keys to display names mapping.
+ * Config keys are lowercase (e.g., "sisyphus", "atlas").
+ * Display names include suffixes for UI/logs (e.g., "Sisyphus (Ultraworker)").
+ */
+export const AGENT_DISPLAY_NAMES: Record<string, string> = {
+  sisyphus: "Sisyphus (Ultraworker)",
+  atlas: "Atlas (Plan Execution Orchestrator)",
+  prometheus: "Prometheus (Plan Builder)",
+  "sisyphus-junior": "Sisyphus-Junior",
+  metis: "Metis (Plan Consultant)",
+  momus: "Momus (Plan Reviewer)",
+  oracle: "oracle",
+  librarian: "librarian",
+  explore: "explore",
+  "multimodal-looker": "multimodal-looker",
+}
+
+/**
+ * Get display name for an agent config key.
+ * Uses case-insensitive lookup for backward compatibility.
+ * Returns original key if not found.
+ */
+export function getAgentDisplayName(configKey: string): string {
+  // Try exact match first
+  const exactMatch = AGENT_DISPLAY_NAMES[configKey]
+  if (exactMatch !== undefined) return exactMatch
+  
+  // Fall back to case-insensitive search
+  const lowerKey = configKey.toLowerCase()
+  for (const [k, v] of Object.entries(AGENT_DISPLAY_NAMES)) {
+    if (k.toLowerCase() === lowerKey) return v
+  }
+  
+  // Unknown agent: return original key
+  return configKey
+}

src/shared/agent-tool-restrictions.ts

@@ -30,7 +30,7 @@ const AGENT_RESTRICTIONS: Record<string, Record<string, boolean>> = {
     read: true,
   },
 
-  "Sisyphus-Junior": {
+  "sisyphus-junior": {
     task: false,
     delegate_task: false,
   },

src/shared/agent-variant.ts

@@ -1,4 +1,5 @@
 import type { OhMyOpenCodeConfig } from "../config"
+import { findCaseInsensitive } from "./case-insensitive"
 
 export function resolveAgentVariant(
   config: OhMyOpenCodeConfig,
@@ -11,7 +12,7 @@ export function resolveAgentVariant(
   const agentOverrides = config.agents as
     | Record<string, { variant?: string; category?: string }>
     | undefined
-  const agentOverride = agentOverrides?.[agentName]
+  const agentOverride = agentOverrides ? findCaseInsensitive(agentOverrides, agentName) : undefined
   if (!agentOverride) {
     return undefined
   }

src/shared/config-path.ts

@@ -1,43 +0,0 @@
-import * as path from "path"
-import * as os from "os"
-import * as fs from "fs"
-
-/**
- * Returns the user-level config directory based on the OS.
- * @deprecated Use getOpenCodeConfigDir() from opencode-config-dir.ts instead.
- */
-export function getUserConfigDir(): string {
-  if (process.platform === "win32") {
-    const crossPlatformDir = path.join(os.homedir(), ".config")
-    const crossPlatformConfigPath = path.join(crossPlatformDir, "opencode", "oh-my-opencode.json")
-
-    const appdataDir = process.env.APPDATA || path.join(os.homedir(), "AppData", "Roaming")
-    const appdataConfigPath = path.join(appdataDir, "opencode", "oh-my-opencode.json")
-
-    if (fs.existsSync(crossPlatformConfigPath)) {
-      return crossPlatformDir
-    }
-
-    if (fs.existsSync(appdataConfigPath)) {
-      return appdataDir
-    }
-
-    return crossPlatformDir
-  }
-
-  return process.env.XDG_CONFIG_HOME || path.join(os.homedir(), ".config")
-}
-
-/**
- * Returns the full path to the user-level oh-my-opencode config file.
- */
-export function getUserConfigPath(): string {
-  return path.join(getUserConfigDir(), "opencode", "oh-my-opencode.json")
-}
-
-/**
- * Returns the full path to the project-level oh-my-opencode config file.
- */
-export function getProjectConfigPath(directory: string): string {
-  return path.join(directory, ".opencode", "oh-my-opencode.json")
-}

src/shared/index.ts

@@ -10,7 +10,6 @@ export * from "./hook-disabled"
 export * from "./deep-merge"
 export * from "./file-utils"
 export * from "./dynamic-truncator"
-export * from "./config-path"
 export * from "./data-path"
 export * from "./config-errors"
 export * from "./claude-config-dir"

src/shared/migration.test.ts

@@ -12,7 +12,7 @@ import {
 } from "./migration"
 
 describe("migrateAgentNames", () => {
-  test("migrates legacy OmO names to Sisyphus", () => {
+  test("migrates legacy OmO names to lowercase", () => {
     // #given: Config with legacy OmO agent names
     const agents = {
       omo: { model: "anthropic/claude-opus-4-5" },
@@ -23,10 +23,10 @@ describe("migrateAgentNames", () => {
     // #when: Migrate agent names
     const { migrated, changed } = migrateAgentNames(agents)
 
-    // #then: Legacy names should be migrated to Sisyphus/Prometheus
+    // #then: Legacy names should be migrated to lowercase
     expect(changed).toBe(true)
-    expect(migrated["Sisyphus"]).toEqual({ temperature: 0.5 })
-    expect(migrated["Prometheus (Planner)"]).toEqual({ prompt: "custom prompt" })
+    expect(migrated["sisyphus"]).toEqual({ temperature: 0.5 })
+    expect(migrated["prometheus"]).toEqual({ prompt: "custom prompt" })
     expect(migrated["omo"]).toBeUndefined()
     expect(migrated["OmO"]).toBeUndefined()
     expect(migrated["OmO-Plan"]).toBeUndefined()
@@ -37,7 +37,7 @@ describe("migrateAgentNames", () => {
     const agents = {
       oracle: { model: "openai/gpt-5.2" },
       librarian: { model: "google/gemini-3-flash" },
-      explore: { model: "opencode/grok-code" },
+      explore: { model: "opencode/gpt-5-nano" },
     }
 
     // #when: Migrate agent names
@@ -47,7 +47,7 @@ describe("migrateAgentNames", () => {
     expect(changed).toBe(false)
     expect(migrated["oracle"]).toEqual({ model: "openai/gpt-5.2" })
     expect(migrated["librarian"]).toEqual({ model: "google/gemini-3-flash" })
-    expect(migrated["explore"]).toEqual({ model: "opencode/grok-code" })
+    expect(migrated["explore"]).toEqual({ model: "opencode/gpt-5-nano" })
   })
 
   test("handles case-insensitive migration", () => {
@@ -62,9 +62,9 @@ describe("migrateAgentNames", () => {
     const { migrated, changed } = migrateAgentNames(agents)
 
     // #then: Case-insensitive lookup should migrate correctly
-    expect(migrated["Sisyphus"]).toEqual({ model: "test" })
-    expect(migrated["Prometheus (Planner)"]).toEqual({ prompt: "test" })
-    expect(migrated["Atlas"]).toEqual({ model: "openai/gpt-5.2" })
+    expect(migrated["sisyphus"]).toEqual({ model: "test" })
+    expect(migrated["prometheus"]).toEqual({ prompt: "test" })
+    expect(migrated["atlas"]).toEqual({ model: "openai/gpt-5.2" })
   })
 
   test("passes through unknown agent names unchanged", () => {
@@ -81,7 +81,7 @@ describe("migrateAgentNames", () => {
     expect(migrated["custom-agent"]).toEqual({ model: "custom/model" })
   })
 
-  test("migrates orchestrator-sisyphus to Atlas", () => {
+  test("migrates orchestrator-sisyphus to atlas", () => {
     // #given: Config with legacy orchestrator-sisyphus agent name
     const agents = {
       "orchestrator-sisyphus": { model: "anthropic/claude-opus-4-5" },
@@ -90,13 +90,13 @@ describe("migrateAgentNames", () => {
     // #when: Migrate agent names
     const { migrated, changed } = migrateAgentNames(agents)
 
-    // #then: orchestrator-sisyphus should be migrated to Atlas
+    // #then: orchestrator-sisyphus should be migrated to atlas
     expect(changed).toBe(true)
-    expect(migrated["Atlas"]).toEqual({ model: "anthropic/claude-opus-4-5" })
+    expect(migrated["atlas"]).toEqual({ model: "anthropic/claude-opus-4-5" })
     expect(migrated["orchestrator-sisyphus"]).toBeUndefined()
   })
 
-  test("migrates lowercase atlas to Atlas", () => {
+  test("migrates lowercase atlas to atlas", () => {
     // #given: Config with lowercase atlas agent name
     const agents = {
       atlas: { model: "anthropic/claude-opus-4-5" },
@@ -105,10 +105,96 @@ describe("migrateAgentNames", () => {
     // #when: Migrate agent names
     const { migrated, changed } = migrateAgentNames(agents)
 
-    // #then: lowercase atlas should be migrated to Atlas
+    // #then: lowercase atlas should remain atlas (no change needed)
+    expect(changed).toBe(false)
+    expect(migrated["atlas"]).toEqual({ model: "anthropic/claude-opus-4-5" })
+  })
+
+  test("migrates Sisyphus variants to lowercase", () => {
+    // #given agents config with "Sisyphus" key
+    // #when migrateAgentNames called
+    // #then key becomes "sisyphus"
+    const agents = { "Sisyphus": { model: "test" } }
+    const { migrated, changed } = migrateAgentNames(agents)
     expect(changed).toBe(true)
-    expect(migrated["Atlas"]).toEqual({ model: "anthropic/claude-opus-4-5" })
-    expect(migrated["atlas"]).toBeUndefined()
+    expect(migrated["sisyphus"]).toEqual({ model: "test" })
+    expect(migrated["Sisyphus"]).toBeUndefined()
+  })
+
+  test("migrates omo key to sisyphus", () => {
+    // #given agents config with "omo" key
+    // #when migrateAgentNames called
+    // #then key becomes "sisyphus"
+    const agents = { "omo": { model: "test" } }
+    const { migrated, changed } = migrateAgentNames(agents)
+    expect(changed).toBe(true)
+    expect(migrated["sisyphus"]).toEqual({ model: "test" })
+    expect(migrated["omo"]).toBeUndefined()
+  })
+
+  test("migrates Atlas variants to lowercase", () => {
+    // #given agents config with "Atlas" key
+    // #when migrateAgentNames called
+    // #then key becomes "atlas"
+    const agents = { "Atlas": { model: "test" } }
+    const { migrated, changed } = migrateAgentNames(agents)
+    expect(changed).toBe(true)
+    expect(migrated["atlas"]).toEqual({ model: "test" })
+    expect(migrated["Atlas"]).toBeUndefined()
+  })
+
+  test("migrates Prometheus variants to lowercase", () => {
+    // #given agents config with "Prometheus (Planner)" key
+    // #when migrateAgentNames called
+    // #then key becomes "prometheus"
+    const agents = { "Prometheus (Planner)": { model: "test" } }
+    const { migrated, changed } = migrateAgentNames(agents)
+    expect(changed).toBe(true)
+    expect(migrated["prometheus"]).toEqual({ model: "test" })
+    expect(migrated["Prometheus (Planner)"]).toBeUndefined()
+  })
+
+  test("migrates Metis variants to lowercase", () => {
+    // #given agents config with "Metis (Plan Consultant)" key
+    // #when migrateAgentNames called
+    // #then key becomes "metis"
+    const agents = { "Metis (Plan Consultant)": { model: "test" } }
+    const { migrated, changed } = migrateAgentNames(agents)
+    expect(changed).toBe(true)
+    expect(migrated["metis"]).toEqual({ model: "test" })
+    expect(migrated["Metis (Plan Consultant)"]).toBeUndefined()
+  })
+
+  test("migrates Momus variants to lowercase", () => {
+    // #given agents config with "Momus (Plan Reviewer)" key
+    // #when migrateAgentNames called
+    // #then key becomes "momus"
+    const agents = { "Momus (Plan Reviewer)": { model: "test" } }
+    const { migrated, changed } = migrateAgentNames(agents)
+    expect(changed).toBe(true)
+    expect(migrated["momus"]).toEqual({ model: "test" })
+    expect(migrated["Momus (Plan Reviewer)"]).toBeUndefined()
+  })
+
+  test("migrates Sisyphus-Junior to lowercase", () => {
+    // #given agents config with "Sisyphus-Junior" key
+    // #when migrateAgentNames called
+    // #then key becomes "sisyphus-junior"
+    const agents = { "Sisyphus-Junior": { model: "test" } }
+    const { migrated, changed } = migrateAgentNames(agents)
+    expect(changed).toBe(true)
+    expect(migrated["sisyphus-junior"]).toEqual({ model: "test" })
+    expect(migrated["Sisyphus-Junior"]).toBeUndefined()
+  })
+
+  test("preserves lowercase passthrough", () => {
+    // #given agents config with "oracle" key
+    // #when migrateAgentNames called
+    // #then key remains "oracle" (no change needed)
+    const agents = { "oracle": { model: "test" } }
+    const { migrated, changed } = migrateAgentNames(agents)
+    expect(changed).toBe(false)
+    expect(migrated["oracle"]).toEqual({ model: "test" })
   })
 })
 
@@ -249,7 +335,7 @@ describe("migrateConfigFile", () => {
     // #then: Agent names should be migrated
     expect(needsWrite).toBe(true)
     const agents = rawConfig.agents as Record<string, unknown>
-    expect(agents["Sisyphus"]).toBeDefined()
+    expect(agents["sisyphus"]).toBeDefined()
   })
 
   test("migrates legacy hook names in disabled_hooks", () => {
@@ -272,7 +358,7 @@ describe("migrateConfigFile", () => {
     const rawConfig: Record<string, unknown> = {
       sisyphus_agent: { disabled: false },
       agents: {
-        Sisyphus: { model: "test" },
+        sisyphus: { model: "test" },
       },
       disabled_hooks: ["anthropic-context-window-limit-recovery"],
     }
@@ -303,8 +389,8 @@ describe("migrateConfigFile", () => {
     expect(rawConfig.sisyphus_agent).toEqual({ disabled: false })
     expect(rawConfig.omo_agent).toBeUndefined()
     const agents = rawConfig.agents as Record<string, unknown>
-    expect(agents["Sisyphus"]).toBeDefined()
-    expect(agents["Prometheus (Planner)"]).toBeDefined()
+    expect(agents["sisyphus"]).toBeDefined()
+    expect(agents["prometheus"]).toBeDefined()
     expect(rawConfig.disabled_hooks).toContain("anthropic-context-window-limit-recovery")
   })
 })
@@ -312,13 +398,13 @@ describe("migrateConfigFile", () => {
 describe("migration maps", () => {
   test("AGENT_NAME_MAP contains all expected legacy mappings", () => {
     // #given/#when: Check AGENT_NAME_MAP
-    // #then: Should contain all legacy → current mappings
-    expect(AGENT_NAME_MAP["omo"]).toBe("Sisyphus")
-    expect(AGENT_NAME_MAP["OmO"]).toBe("Sisyphus")
-    expect(AGENT_NAME_MAP["OmO-Plan"]).toBe("Prometheus (Planner)")
-    expect(AGENT_NAME_MAP["omo-plan"]).toBe("Prometheus (Planner)")
-    expect(AGENT_NAME_MAP["Planner-Sisyphus"]).toBe("Prometheus (Planner)")
-    expect(AGENT_NAME_MAP["plan-consultant"]).toBe("Metis (Plan Consultant)")
+    // #then: Should contain all legacy → lowercase mappings
+    expect(AGENT_NAME_MAP["omo"]).toBe("sisyphus")
+    expect(AGENT_NAME_MAP["OmO"]).toBe("sisyphus")
+    expect(AGENT_NAME_MAP["OmO-Plan"]).toBe("prometheus")
+    expect(AGENT_NAME_MAP["omo-plan"]).toBe("prometheus")
+    expect(AGENT_NAME_MAP["Planner-Sisyphus"]).toBe("prometheus")
+    expect(AGENT_NAME_MAP["plan-consultant"]).toBe("metis")
   })
 
   test("HOOK_NAME_MAP contains anthropic-auto-compact migration", () => {
@@ -332,7 +418,7 @@ describe("migrateAgentConfigToCategory", () => {
   test("migrates model to category when mapping exists", () => {
     // #given: Config with a model that has a category mapping
     const config = {
-      model: "google/gemini-3-pro-preview",
+      model: "google/gemini-3-pro",
       temperature: 0.5,
       top_p: 0.9,
     }
@@ -381,14 +467,15 @@ describe("migrateAgentConfigToCategory", () => {
   test("handles all mapped models correctly", () => {
     // #given: Configs for each mapped model
     const configs = [
-      { model: "google/gemini-3-pro-preview" },
+      { model: "google/gemini-3-pro" },
+      { model: "google/gemini-3-flash" },
       { model: "openai/gpt-5.2" },
       { model: "anthropic/claude-haiku-4-5" },
       { model: "anthropic/claude-opus-4-5" },
       { model: "anthropic/claude-sonnet-4-5" },
     ]
 
-    const expectedCategories = ["visual-engineering", "ultrabrain", "quick", "unspecified-high", "unspecified-low"]
+    const expectedCategories = ["visual-engineering", "writing", "ultrabrain", "quick", "unspecified-high", "unspecified-low"]
 
     // #when: Migrate each config
     const results = configs.map(migrateAgentConfigToCategory)
@@ -450,7 +537,7 @@ describe("shouldDeleteAgentConfig", () => {
     // #given: Config with fields matching category defaults
     const config = {
       category: "visual-engineering",
-      model: "google/gemini-3-pro-preview",
+      model: "google/gemini-3-pro",
     }
 
     // #when: Check if config should be deleted
@@ -578,7 +665,7 @@ describe("migrateConfigFile with backup", () => {
       agents: {
         "multimodal-looker": { model: "anthropic/claude-haiku-4-5" },
         oracle: { model: "openai/gpt-5.2" },
-        "my-custom-agent": { model: "google/gemini-3-pro-preview" },
+        "my-custom-agent": { model: "google/gemini-3-pro" },
       },
     }
 
@@ -594,7 +681,7 @@ describe("migrateConfigFile with backup", () => {
     const agents = rawConfig.agents as Record<string, Record<string, unknown>>
     expect(agents["multimodal-looker"].model).toBe("anthropic/claude-haiku-4-5")
     expect(agents.oracle.model).toBe("openai/gpt-5.2")
-    expect(agents["my-custom-agent"].model).toBe("google/gemini-3-pro-preview")
+    expect(agents["my-custom-agent"].model).toBe("google/gemini-3-pro")
   })
 
   test("preserves category setting when explicitly set", () => {
@@ -622,29 +709,41 @@ describe("migrateConfigFile with backup", () => {
   })
 
   test("does not write when no migration needed", () => {
-    // #given: Config with no migrations needed
-    const testConfigPath = "/tmp/test-config-no-migration.json"
-    const rawConfig: Record<string, unknown> = {
-      agents: {
-        Sisyphus: { model: "test" },
-      },
-    }
+     // #given: Config with no migrations needed
+     const testConfigPath = "/tmp/test-config-no-migration.json"
+     const rawConfig: Record<string, unknown> = {
+       agents: {
+         sisyphus: { model: "test" },
+       },
+     }
 
-    fs.writeFileSync(testConfigPath, globalThis.JSON.stringify({ agents: { Sisyphus: { model: "test" } } }, null, 2))
-    cleanupPaths.push(testConfigPath)
+     fs.writeFileSync(testConfigPath, globalThis.JSON.stringify({ agents: { sisyphus: { model: "test" } } }, null, 2))
+     cleanupPaths.push(testConfigPath)
 
-    // #when: Migrate config file
-    const needsWrite = migrateConfigFile(testConfigPath, rawConfig)
+     // Clean up any existing backup files from previous test runs
+     const dir = path.dirname(testConfigPath)
+     const basename = path.basename(testConfigPath)
+     const existingFiles = fs.readdirSync(dir)
+     const existingBackups = existingFiles.filter((f) => f.startsWith(`${basename}.bak.`))
+     existingBackups.forEach((f) => {
+       const backupPath = path.join(dir, f)
+       try {
+         fs.unlinkSync(backupPath)
+         cleanupPaths.splice(cleanupPaths.indexOf(backupPath), 1)
+       } catch {
+       }
+     })
 
-    // #then: Should not write or create backup
-    expect(needsWrite).toBe(false)
+     // #when: Migrate config file
+     const needsWrite = migrateConfigFile(testConfigPath, rawConfig)
 
-    const dir = path.dirname(testConfigPath)
-    const basename = path.basename(testConfigPath)
-    const files = fs.readdirSync(dir)
-    const backupFiles = files.filter((f) => f.startsWith(`${basename}.bak.`))
-    expect(backupFiles.length).toBe(0)
-  })
+     // #then: Should not write or create backup
+     expect(needsWrite).toBe(false)
+
+     const files = fs.readdirSync(dir)
+     const backupFiles = files.filter((f) => f.startsWith(`${basename}.bak.`))
+     expect(backupFiles.length).toBe(0)
+   })
 
 
 })

src/shared/migration.ts

@@ -3,35 +3,56 @@ import { log } from "./logger"
 
 // Migration map: old keys → new keys (for backward compatibility)
 export const AGENT_NAME_MAP: Record<string, string> = {
-  omo: "Sisyphus",
-  "OmO": "Sisyphus",
-  sisyphus: "Sisyphus",
-  "OmO-Plan": "Prometheus (Planner)",
-  "omo-plan": "Prometheus (Planner)",
-  "Planner-Sisyphus": "Prometheus (Planner)",
-  "planner-sisyphus": "Prometheus (Planner)",
-  prometheus: "Prometheus (Planner)",
-  "plan-consultant": "Metis (Plan Consultant)",
-  metis: "Metis (Plan Consultant)",
+  // Sisyphus variants → "sisyphus"
+  omo: "sisyphus",
+  OmO: "sisyphus",
+  Sisyphus: "sisyphus",
+  sisyphus: "sisyphus",
+
+  // Prometheus variants → "prometheus"
+  "OmO-Plan": "prometheus",
+  "omo-plan": "prometheus",
+  "Planner-Sisyphus": "prometheus",
+  "planner-sisyphus": "prometheus",
+  "Prometheus (Planner)": "prometheus",
+  prometheus: "prometheus",
+
+  // Atlas variants → "atlas"
+  "orchestrator-sisyphus": "atlas",
+  Atlas: "atlas",
+  atlas: "atlas",
+
+  // Metis variants → "metis"
+  "plan-consultant": "metis",
+  "Metis (Plan Consultant)": "metis",
+  metis: "metis",
+
+  // Momus variants → "momus"
+  "Momus (Plan Reviewer)": "momus",
+  momus: "momus",
+
+  // Sisyphus-Junior → "sisyphus-junior"
+  "Sisyphus-Junior": "sisyphus-junior",
+  "sisyphus-junior": "sisyphus-junior",
+
+  // Already lowercase - passthrough
   build: "build",
   oracle: "oracle",
   librarian: "librarian",
   explore: "explore",
   "multimodal-looker": "multimodal-looker",
-  "orchestrator-sisyphus": "Atlas",
-  atlas: "Atlas",
 }
 
 export const BUILTIN_AGENT_NAMES = new Set([
-  "Sisyphus",
+  "sisyphus",           // was "Sisyphus"
   "oracle",
   "librarian",
   "explore",
   "multimodal-looker",
-  "Metis (Plan Consultant)",
-  "Momus (Plan Reviewer)",
-  "Prometheus (Planner)",
-  "Atlas",
+  "metis",              // was "Metis (Plan Consultant)"
+  "momus",              // was "Momus (Plan Reviewer)"
+  "prometheus",         // was "Prometheus (Planner)"
+  "atlas",              // was "Atlas"
   "build",
 ])
 
@@ -61,7 +82,8 @@ export const HOOK_NAME_MAP: Record<string, string | null> = {
  * This map will be removed in a future major version once migration period ends.
  */
 export const MODEL_TO_CATEGORY_MAP: Record<string, string> = {
-  "google/gemini-3-pro-preview": "visual-engineering",
+  "google/gemini-3-pro": "visual-engineering",
+  "google/gemini-3-flash": "writing",
   "openai/gpt-5.2": "ultrabrain",
   "anthropic/claude-haiku-4-5": "quick",
   "anthropic/claude-opus-4-5": "unspecified-high",

src/shared/model-availability.test.ts

@@ -1,26 +1,43 @@
-import { describe, it, expect, beforeEach } from "bun:test"
+import { describe, it, expect, beforeEach, afterEach } from "bun:test"
+import { mkdtempSync, writeFileSync, rmSync } from "fs"
+import { tmpdir } from "os"
+import { join } from "path"
 import { fetchAvailableModels, fuzzyMatchModel, __resetModelCache } from "./model-availability"
 
 describe("fetchAvailableModels", () => {
-  let mockClient: any
+  let tempDir: string
+  let originalXdgCache: string | undefined
 
   beforeEach(() => {
     __resetModelCache()
+    tempDir = mkdtempSync(join(tmpdir(), "opencode-test-"))
+    originalXdgCache = process.env.XDG_CACHE_HOME
+    process.env.XDG_CACHE_HOME = tempDir
   })
 
-  it("#given API returns list of models #when fetchAvailableModels called #then returns Set of model IDs", async () => {
-    const mockModels = [
-      { id: "openai/gpt-5.2", name: "GPT-5.2" },
-      { id: "anthropic/claude-opus-4-5", name: "Claude Opus 4.5" },
-      { id: "google/gemini-3-pro", name: "Gemini 3 Pro" },
-    ]
-    mockClient = {
-      model: {
-        list: async () => mockModels,
-      },
+  afterEach(() => {
+    if (originalXdgCache !== undefined) {
+      process.env.XDG_CACHE_HOME = originalXdgCache
+    } else {
+      delete process.env.XDG_CACHE_HOME
     }
+    rmSync(tempDir, { recursive: true, force: true })
+  })
 
-    const result = await fetchAvailableModels(mockClient)
+  function writeModelsCache(data: Record<string, any>) {
+    const cacheDir = join(tempDir, "opencode")
+    require("fs").mkdirSync(cacheDir, { recursive: true })
+    writeFileSync(join(cacheDir, "models.json"), JSON.stringify(data))
+  }
+
+  it("#given cache file with models #when fetchAvailableModels called #then returns Set of model IDs", async () => {
+    writeModelsCache({
+      openai: { id: "openai", models: { "gpt-5.2": { id: "gpt-5.2" } } },
+      anthropic: { id: "anthropic", models: { "claude-opus-4-5": { id: "claude-opus-4-5" } } },
+      google: { id: "google", models: { "gemini-3-pro": { id: "gemini-3-pro" } } },
+    })
+
+    const result = await fetchAvailableModels()
 
     expect(result).toBeInstanceOf(Set)
     expect(result.size).toBe(3)
@@ -29,77 +46,50 @@ describe("fetchAvailableModels", () => {
     expect(result.has("google/gemini-3-pro")).toBe(true)
   })
 
-  it("#given API fails #when fetchAvailableModels called #then returns empty Set without throwing", async () => {
-    mockClient = {
-      model: {
-        list: async () => {
-          throw new Error("API connection failed")
-        },
-      },
-    }
-
-    const result = await fetchAvailableModels(mockClient)
+  it("#given cache file not found #when fetchAvailableModels called #then returns empty Set", async () => {
+    const result = await fetchAvailableModels()
 
     expect(result).toBeInstanceOf(Set)
     expect(result.size).toBe(0)
   })
 
-  it("#given API called twice #when second call made #then uses cached result without re-fetching", async () => {
-    let callCount = 0
-    const mockModels = [
-      { id: "openai/gpt-5.2", name: "GPT-5.2" },
-      { id: "anthropic/claude-opus-4-5", name: "Claude Opus 4.5" },
-    ]
-    mockClient = {
-      model: {
-        list: async () => {
-          callCount++
-          return mockModels
-        },
-      },
-    }
+  it("#given cache read twice #when second call made #then uses cached result", async () => {
+    writeModelsCache({
+      openai: { id: "openai", models: { "gpt-5.2": { id: "gpt-5.2" } } },
+      anthropic: { id: "anthropic", models: { "claude-opus-4-5": { id: "claude-opus-4-5" } } },
+    })
 
-    const result1 = await fetchAvailableModels(mockClient)
-    const result2 = await fetchAvailableModels(mockClient)
+    const result1 = await fetchAvailableModels()
+    const result2 = await fetchAvailableModels()
 
-    expect(callCount).toBe(1)
     expect(result1).toEqual(result2)
     expect(result1.has("openai/gpt-5.2")).toBe(true)
   })
 
-  it("#given empty model list from API #when fetchAvailableModels called #then returns empty Set", async () => {
-    mockClient = {
-      model: {
-        list: async () => [],
-      },
-    }
+  it("#given empty providers in cache #when fetchAvailableModels called #then returns empty Set", async () => {
+    writeModelsCache({})
 
-    const result = await fetchAvailableModels(mockClient)
+    const result = await fetchAvailableModels()
 
     expect(result).toBeInstanceOf(Set)
     expect(result.size).toBe(0)
   })
 
-  it("#given API returns models with various formats #when fetchAvailableModels called #then extracts all IDs correctly", async () => {
-    const mockModels = [
-      { id: "openai/gpt-5.2-codex", name: "GPT-5.2 Codex" },
-      { id: "anthropic/claude-sonnet-4-5", name: "Claude Sonnet 4.5" },
-      { id: "google/gemini-3-flash", name: "Gemini 3 Flash" },
-      { id: "opencode/grok-code", name: "Grok Code" },
-    ]
-    mockClient = {
-      model: {
-        list: async () => mockModels,
-      },
-    }
+  it("#given cache file with various providers #when fetchAvailableModels called #then extracts all IDs correctly", async () => {
+    writeModelsCache({
+      openai: { id: "openai", models: { "gpt-5.2-codex": { id: "gpt-5.2-codex" } } },
+      anthropic: { id: "anthropic", models: { "claude-sonnet-4-5": { id: "claude-sonnet-4-5" } } },
+      google: { id: "google", models: { "gemini-3-flash": { id: "gemini-3-flash" } } },
+      opencode: { id: "opencode", models: { "gpt-5-nano": { id: "gpt-5-nano" } } },
+    })
 
-    const result = await fetchAvailableModels(mockClient)
+    const result = await fetchAvailableModels()
 
     expect(result.size).toBe(4)
     expect(result.has("openai/gpt-5.2-codex")).toBe(true)
     expect(result.has("anthropic/claude-sonnet-4-5")).toBe(true)
     expect(result.has("google/gemini-3-flash")).toBe(true)
-	expect(result.has("opencode/grok-code")).toBe(true)
+    expect(result.has("opencode/gpt-5-nano")).toBe(true)
   })
 })
 

src/shared/model-availability.ts

@@ -3,6 +3,9 @@
  * Supports substring matching with provider filtering and priority-based selection
  */
 
+import { existsSync, readFileSync } from "fs"
+import { homedir } from "os"
+import { join } from "path"
 import { log } from "./logger"
 
 /**
@@ -90,36 +93,62 @@ export function fuzzyMatchModel(
 
 let cachedModels: Set<string> | null = null
 
-export async function fetchAvailableModels(client: any): Promise<Set<string>> {
+function getOpenCodeCacheDir(): string {
+	const xdgCache = process.env.XDG_CACHE_HOME
+	if (xdgCache) return join(xdgCache, "opencode")
+	return join(homedir(), ".cache", "opencode")
+}
+
+export async function fetchAvailableModels(_client?: any): Promise<Set<string>> {
+	log("[fetchAvailableModels] CALLED")
+	
 	if (cachedModels !== null) {
 		log("[fetchAvailableModels] returning cached models", { count: cachedModels.size, models: Array.from(cachedModels).slice(0, 20) })
 		return cachedModels
 	}
 
+	const modelSet = new Set<string>()
+	const cacheFile = join(getOpenCodeCacheDir(), "models.json")
+
+	log("[fetchAvailableModels] reading cache file", { cacheFile })
+
+	if (!existsSync(cacheFile)) {
+		log("[fetchAvailableModels] cache file not found, returning empty set")
+		return modelSet
+	}
+
 	try {
-		const models = await client.model.list()
-		const modelSet = new Set<string>()
+		const content = readFileSync(cacheFile, "utf-8")
+		const data = JSON.parse(content) as Record<string, { id?: string; models?: Record<string, { id?: string }> }>
 
-		log("[fetchAvailableModels] raw response", { isArray: Array.isArray(models), length: Array.isArray(models) ? models.length : 0, sample: Array.isArray(models) ? models.slice(0, 5) : models })
+		const providerIds = Object.keys(data)
+		log("[fetchAvailableModels] providers found", { count: providerIds.length, providers: providerIds.slice(0, 10) })
 
-		if (Array.isArray(models)) {
-			for (const model of models) {
-				if (model.id && typeof model.id === "string") {
-					modelSet.add(model.id)
-				}
+		for (const providerId of providerIds) {
+			const provider = data[providerId]
+			const models = provider?.models
+			if (!models || typeof models !== "object") continue
+
+			for (const modelKey of Object.keys(models)) {
+				modelSet.add(`${providerId}/${modelKey}`)
 			}
 		}
 
-		log("[fetchAvailableModels] parsed models", { count: modelSet.size, models: Array.from(modelSet) })
+		log("[fetchAvailableModels] parsed models", { count: modelSet.size, models: Array.from(modelSet).slice(0, 20) })
 
 		cachedModels = modelSet
 		return modelSet
 	} catch (err) {
 		log("[fetchAvailableModels] error", { error: String(err) })
-		return new Set<string>()
+		return modelSet
 	}
 }
 
 export function __resetModelCache(): void {
 	cachedModels = null
 }
+
+export function isModelCacheAvailable(): boolean {
+	const cacheFile = join(getOpenCodeCacheDir(), "models.json")
+	return existsSync(cacheFile)
+}

src/shared/model-requirements.test.ts

@@ -23,9 +23,9 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     expect(primary.variant).toBe("high")
   })
 
-  test("Sisyphus has valid fallbackChain with claude-opus-4-5 as primary", () => {
-    // #given - Sisyphus agent requirement
-    const sisyphus = AGENT_MODEL_REQUIREMENTS["Sisyphus"]
+  test("sisyphus has valid fallbackChain with claude-opus-4-5 as primary", () => {
+    // #given - sisyphus agent requirement
+    const sisyphus = AGENT_MODEL_REQUIREMENTS["sisyphus"]
 
     // #when - accessing Sisyphus requirement
     // #then - fallbackChain exists with claude-opus-4-5 as first entry
@@ -54,39 +54,39 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     expect(primary.model).toBe("glm-4.7")
   })
 
-  test("explore has valid fallbackChain with gemini-3-flash-preview as primary", () => {
+  test("explore has valid fallbackChain with claude-haiku-4-5 as primary", () => {
     // #given - explore agent requirement
     const explore = AGENT_MODEL_REQUIREMENTS["explore"]
 
     // #when - accessing explore requirement
-    // #then - fallbackChain exists with gemini-3-flash-preview as first entry
+    // #then - fallbackChain exists with claude-haiku-4-5 as first entry
     expect(explore).toBeDefined()
     expect(explore.fallbackChain).toBeArray()
     expect(explore.fallbackChain.length).toBeGreaterThan(0)
 
     const primary = explore.fallbackChain[0]
-    expect(primary.providers).toContain("google")
-    expect(primary.model).toBe("gemini-3-flash-preview")
+    expect(primary.providers).toContain("anthropic")
+    expect(primary.model).toBe("claude-haiku-4-5")
   })
 
-  test("multimodal-looker has valid fallbackChain with gemini-3-flash-preview as primary", () => {
+  test("multimodal-looker has valid fallbackChain with gemini-3-flash as primary", () => {
     // #given - multimodal-looker agent requirement
     const multimodalLooker = AGENT_MODEL_REQUIREMENTS["multimodal-looker"]
 
     // #when - accessing multimodal-looker requirement
-    // #then - fallbackChain exists with gemini-3-flash-preview as first entry
+    // #then - fallbackChain exists with gemini-3-flash as first entry
     expect(multimodalLooker).toBeDefined()
     expect(multimodalLooker.fallbackChain).toBeArray()
     expect(multimodalLooker.fallbackChain.length).toBeGreaterThan(0)
 
     const primary = multimodalLooker.fallbackChain[0]
     expect(primary.providers[0]).toBe("google")
-    expect(primary.model).toBe("gemini-3-flash-preview")
+    expect(primary.model).toBe("gemini-3-flash")
   })
 
-  test("Prometheus (Planner) has valid fallbackChain with claude-opus-4-5 as primary", () => {
-    // #given - Prometheus agent requirement
-    const prometheus = AGENT_MODEL_REQUIREMENTS["Prometheus (Planner)"]
+  test("prometheus has valid fallbackChain with claude-opus-4-5 as primary", () => {
+    // #given - prometheus agent requirement
+    const prometheus = AGENT_MODEL_REQUIREMENTS["prometheus"]
 
     // #when - accessing Prometheus requirement
     // #then - fallbackChain exists with claude-opus-4-5 as first entry
@@ -100,9 +100,9 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     expect(primary.variant).toBe("max")
   })
 
-  test("Metis (Plan Consultant) has valid fallbackChain with claude-opus-4-5 as primary", () => {
-    // #given - Metis agent requirement
-    const metis = AGENT_MODEL_REQUIREMENTS["Metis (Plan Consultant)"]
+  test("metis has valid fallbackChain with claude-opus-4-5 as primary", () => {
+    // #given - metis agent requirement
+    const metis = AGENT_MODEL_REQUIREMENTS["metis"]
 
     // #when - accessing Metis requirement
     // #then - fallbackChain exists with claude-opus-4-5 as first entry
@@ -116,9 +116,9 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     expect(primary.variant).toBe("max")
   })
 
-  test("Momus (Plan Reviewer) has valid fallbackChain with gpt-5.2 as primary", () => {
-    // #given - Momus agent requirement
-    const momus = AGENT_MODEL_REQUIREMENTS["Momus (Plan Reviewer)"]
+  test("momus has valid fallbackChain with gpt-5.2 as primary", () => {
+    // #given - momus agent requirement
+    const momus = AGENT_MODEL_REQUIREMENTS["momus"]
 
     // #when - accessing Momus requirement
     // #then - fallbackChain exists with gpt-5.2 as first entry, variant medium
@@ -132,9 +132,9 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     expect(primary.providers[0]).toBe("openai")
   })
 
-  test("Atlas has valid fallbackChain with claude-sonnet-4-5 as primary", () => {
-    // #given - Atlas agent requirement
-    const atlas = AGENT_MODEL_REQUIREMENTS["Atlas"]
+  test("atlas has valid fallbackChain with claude-sonnet-4-5 as primary", () => {
+    // #given - atlas agent requirement
+    const atlas = AGENT_MODEL_REQUIREMENTS["atlas"]
 
     // #when - accessing Atlas requirement
     // #then - fallbackChain exists with claude-sonnet-4-5 as first entry
@@ -150,15 +150,15 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
   test("all 9 builtin agents have valid fallbackChain arrays", () => {
     // #given - list of 9 agent names
     const expectedAgents = [
-      "Sisyphus",
+      "sisyphus",
       "oracle",
       "librarian",
       "explore",
       "multimodal-looker",
-      "Prometheus (Planner)",
-      "Metis (Plan Consultant)",
-      "Momus (Plan Reviewer)",
-      "Atlas",
+      "prometheus",
+      "metis",
+      "momus",
+      "atlas",
     ]
 
     // #when - checking AGENT_MODEL_REQUIREMENTS
@@ -199,19 +199,19 @@ describe("CATEGORY_MODEL_REQUIREMENTS", () => {
     expect(primary.providers[0]).toBe("openai")
   })
 
-  test("visual-engineering has valid fallbackChain with gemini-3-pro-preview as primary", () => {
+  test("visual-engineering has valid fallbackChain with gemini-3-pro as primary", () => {
     // #given - visual-engineering category requirement
     const visualEngineering = CATEGORY_MODEL_REQUIREMENTS["visual-engineering"]
 
     // #when - accessing visual-engineering requirement
-    // #then - fallbackChain exists with gemini-3-pro-preview as first entry
+    // #then - fallbackChain exists with gemini-3-pro as first entry
     expect(visualEngineering).toBeDefined()
     expect(visualEngineering.fallbackChain).toBeArray()
     expect(visualEngineering.fallbackChain.length).toBeGreaterThan(0)
 
     const primary = visualEngineering.fallbackChain[0]
     expect(primary.providers[0]).toBe("google")
-    expect(primary.model).toBe("gemini-3-pro-preview")
+    expect(primary.model).toBe("gemini-3-pro")
   })
 
   test("quick has valid fallbackChain with claude-haiku-4-5 as primary", () => {
@@ -260,34 +260,34 @@ describe("CATEGORY_MODEL_REQUIREMENTS", () => {
     expect(primary.providers[0]).toBe("anthropic")
   })
 
-  test("artistry has valid fallbackChain with gemini-3-pro-preview as primary", () => {
+  test("artistry has valid fallbackChain with gemini-3-pro as primary", () => {
     // #given - artistry category requirement
     const artistry = CATEGORY_MODEL_REQUIREMENTS["artistry"]
 
     // #when - accessing artistry requirement
-    // #then - fallbackChain exists with gemini-3-pro-preview as first entry
+    // #then - fallbackChain exists with gemini-3-pro as first entry
     expect(artistry).toBeDefined()
     expect(artistry.fallbackChain).toBeArray()
     expect(artistry.fallbackChain.length).toBeGreaterThan(0)
 
     const primary = artistry.fallbackChain[0]
-    expect(primary.model).toBe("gemini-3-pro-preview")
+    expect(primary.model).toBe("gemini-3-pro")
     expect(primary.variant).toBe("max")
     expect(primary.providers[0]).toBe("google")
   })
 
-  test("writing has valid fallbackChain with gemini-3-flash-preview as primary", () => {
+  test("writing has valid fallbackChain with gemini-3-flash as primary", () => {
     // #given - writing category requirement
     const writing = CATEGORY_MODEL_REQUIREMENTS["writing"]
 
     // #when - accessing writing requirement
-    // #then - fallbackChain exists with gemini-3-flash-preview as first entry
+    // #then - fallbackChain exists with gemini-3-flash as first entry
     expect(writing).toBeDefined()
     expect(writing.fallbackChain).toBeArray()
     expect(writing.fallbackChain.length).toBeGreaterThan(0)
 
     const primary = writing.fallbackChain[0]
-    expect(primary.model).toBe("gemini-3-flash-preview")
+    expect(primary.model).toBe("gemini-3-flash")
     expect(primary.providers[0]).toBe("google")
   })
 
@@ -344,7 +344,7 @@ describe("FallbackEntry type", () => {
     // #given - a FallbackEntry without variant
     const entry: FallbackEntry = {
       providers: ["opencode", "anthropic"],
-      model: "glm-4.7-free",
+      model: "big-pickle",
     }
 
     // #when - accessing variant
@@ -374,7 +374,7 @@ describe("ModelRequirement type", () => {
   test("ModelRequirement variant is optional", () => {
     // #given - a ModelRequirement without top-level variant
     const requirement: ModelRequirement = {
-      fallbackChain: [{ providers: ["opencode"], model: "glm-4.7-free" }],
+      fallbackChain: [{ providers: ["opencode"], model: "big-pickle" }],
     }
 
     // #when - accessing variant

src/shared/model-requirements.ts

@@ -10,67 +10,69 @@ export type ModelRequirement = {
 }
 
 export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
-  Sisyphus: {
+  sisyphus: {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro-preview" },
+      { providers: ["zai-coding-plan"], model: "glm-4.7" },
+      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2-codex", variant: "medium" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
     ],
   },
   oracle: {
     fallbackChain: [
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro-preview" },
-    ],
-  },
-  librarian: {
-    fallbackChain: [
-      { providers: ["zai-coding-plan"], model: "glm-4.7" },
-      { providers: ["opencode"], model: "glm-4.7-free" },
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
     ],
   },
+   librarian: {
+     fallbackChain: [
+       { providers: ["zai-coding-plan"], model: "glm-4.7" },
+       { providers: ["opencode"], model: "big-pickle" },
+       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" },
+     ],
+   },
   explore: {
     fallbackChain: [
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash-preview" },
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-haiku-4-5" },
-      { providers: ["opencode", "github-copilot"], model: "grok-code" },
+      { providers: ["anthropic", "opencode"], model: "claude-haiku-4-5" },
+      { providers: ["opencode"], model: "gpt-5-nano" },
     ],
   },
   "multimodal-looker": {
     fallbackChain: [
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash-preview" },
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-haiku-4-5" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
+      { providers: ["zai-coding-plan"], model: "glm-4.6v" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-haiku-4-5" },
+      { providers: ["opencode"], model: "gpt-5-nano" },
     ],
   },
-  "Prometheus (Planner)": {
+  prometheus: {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
       { 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" },
     ],
   },
-  "Metis (Plan Consultant)": {
+  metis: {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
       { 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", variant: "max" },
     ],
   },
-  "Momus (Plan Reviewer)": {
+  momus: {
     fallbackChain: [
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "medium" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro-preview" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "max" },
     ],
   },
-  Atlas: {
+  atlas: {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro-preview" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
     ],
   },
 }
@@ -78,7 +80,7 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
 export const CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   "visual-engineering": {
     fallbackChain: [
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro-preview" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
     ],
@@ -87,12 +89,12 @@ export const CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
     fallbackChain: [
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2-codex", variant: "xhigh" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro-preview" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
     ],
   },
   artistry: {
     fallbackChain: [
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro-preview", variant: "max" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "max" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
     ],
@@ -100,28 +102,29 @@ export const CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   quick: {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-haiku-4-5" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash-preview" },
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.1-codex-mini" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" },
+      { providers: ["opencode"], model: "gpt-5-nano" },
     ],
   },
   "unspecified-low": {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" },
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash-preview" },
+      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2-codex", variant: "medium" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" },
     ],
   },
   "unspecified-high": {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
       { 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" },
     ],
   },
   writing: {
     fallbackChain: [
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash-preview" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" },
+      { providers: ["zai-coding-plan"], model: "glm-4.7" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
     ],
   },