release: v3.1.9

🏆 test: optimize test suite with FakeTimers and race condition fixes (#1284 )
* fix: exclude prompt/permission from plan agent config plan agent should only inherit model settings from prometheus, not the prompt or permission. This ensures plan agent uses OpenCode's default behavior while only overriding the model. * test(todo-continuation-enforcer): use FakeTimers for 15x faster tests - Add custom FakeTimers implementation (~100 lines) - Replace all real setTimeout waits with fakeTimers.advanceBy() - Test time: 104.6s → 7.01s * test(callback-server): fix race conditions with Promise.all and Bun.fetch - Use Bun.fetch.bind(Bun) to avoid globalThis.fetch mock interference - Use Promise.all pattern for concurrent fetch/waitForCallback - Add Bun.sleep(10) in afterEach for port release * test(concurrency): replace placeholder assertions with getCount checks Replace 6 meaningless expect(true).toBe(true) assertions with actual getCount() verifications for test quality improvement * refactor(config-handler): simplify planDemoteConfig creation Remove unnecessary IIFE and destructuring, use direct spread instead * test(executor): use FakeTimeouts for faster tests - Add custom FakeTimeouts implementation - Replace setTimeout waits with fakeTimeouts.advanceBy() - Test time reduced from ~26s to ~6.8s * test: fix gemini model mock for artistry unstable mode * test: fix model list mock payload shape * test: mock provider models for artistry category --------- Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-30 14:15:54 +00:00 · 2026-01-30 22:10:52 +09:00 · 2026-01-30 09:56:07 +00:00 · 2026-01-30 08:51:59 +00:00 · 2026-01-30 16:57:21 +09:00 · 2026-01-30 07:33:44 +00:00
75 changed files with 2386 additions and 464 deletions
--- a/.github/workflows/publish-platform.yml
+++ b/.github/workflows/publish-platform.yml
@@ -28,16 +28,20 @@ permissions:
  id-token: write

 jobs:
-  publish-platform:
-    # Use windows-latest for Windows to avoid cross-compilation segfault (oven-sh/bun#18416)
-    # Fixes: #873, #844
+  # =============================================================================
+  # Job 1: Build binaries for all platforms
+  # - Windows builds on windows-latest (avoid bun cross-compile segfault)
+  # - All other platforms build on ubuntu-latest
+  # - Uploads compressed artifacts for the publish job
+  # =============================================================================
+  build:
    runs-on: ${{ matrix.platform == 'windows-x64' && 'windows-latest' || 'ubuntu-latest' }}
    defaults:
      run:
        shell: bash
    strategy:
      fail-fast: false
-      max-parallel: 2
+      max-parallel: 7
      matrix:
        platform: [darwin-arm64, darwin-x64, linux-x64, linux-arm64, linux-x64-musl, linux-arm64-musl, windows-x64]
    steps:
@@ -47,11 +51,6 @@ jobs:
        with:
          bun-version: latest

-      - uses: actions/setup-node@v4
-        with:
-          node-version: "24"
-          registry-url: "https://registry.npmjs.org"
-
      - name: Install dependencies
        run: bun install
        env:
@@ -63,15 +62,20 @@ jobs:
          PKG_NAME="oh-my-opencode-${{ matrix.platform }}"
          VERSION="${{ inputs.version }}"
          STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://registry.npmjs.org/${PKG_NAME}/${VERSION}")
+          # Convert platform name for output (replace - with _)
+          PLATFORM_KEY="${{ matrix.platform }}"
+          PLATFORM_KEY="${PLATFORM_KEY//-/_}"
          if [ "$STATUS" = "200" ]; then
            echo "skip=true" >> $GITHUB_OUTPUT
+            echo "skip_${PLATFORM_KEY}=true" >> $GITHUB_OUTPUT
            echo "✓ ${PKG_NAME}@${VERSION} already published"
          else
            echo "skip=false" >> $GITHUB_OUTPUT
+            echo "skip_${PLATFORM_KEY}=false" >> $GITHUB_OUTPUT
            echo "→ ${PKG_NAME}@${VERSION} needs publishing"
          fi

-      - name: Update version
+      - name: Update version in package.json
        if: steps.check.outputs.skip != 'true'
        run: |
          VERSION="${{ inputs.version }}"
@@ -99,15 +103,109 @@ jobs:
          fi
          
          bun build src/cli/index.ts --compile --minify --target=$TARGET --outfile=$OUTPUT
+          
+          echo "Built binary:"
+          ls -lh "$OUTPUT"
+
+      - name: Compress binary
+        if: steps.check.outputs.skip != 'true'
+        run: |
+          PLATFORM="${{ matrix.platform }}"
+          cd packages/${PLATFORM}
+          
+          if [ "$PLATFORM" = "windows-x64" ]; then
+            # Windows: use 7z (pre-installed on windows-latest)
+            7z a -tzip ../../binary-${PLATFORM}.zip bin/ package.json
+          else
+            # Unix: use tar.gz
+            tar -czvf ../../binary-${PLATFORM}.tar.gz bin/ package.json
+          fi
+          
+          cd ../..
+          echo "Compressed artifact:"
+          ls -lh binary-${PLATFORM}.*
+
+      - name: Upload artifact
+        if: steps.check.outputs.skip != 'true'
+        uses: actions/upload-artifact@v4
+        with:
+          name: binary-${{ matrix.platform }}
+          path: |
+            binary-${{ matrix.platform }}.tar.gz
+            binary-${{ matrix.platform }}.zip
+          retention-days: 1
+          if-no-files-found: error
+
+  # =============================================================================
+  # Job 2: Publish all platforms using OIDC/Provenance
+  # - Runs on ubuntu-latest for ALL platforms (just downloading artifacts)
+  # - Uses npm Trusted Publishing (OIDC) - no NODE_AUTH_TOKEN needed
+  # - Fresh OIDC token at publish time avoids timeout issues
+  # =============================================================================
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      max-parallel: 2
+      matrix:
+        platform: [darwin-arm64, darwin-x64, linux-x64, linux-arm64, linux-x64-musl, linux-arm64-musl, windows-x64]
+    steps:
+      - name: Check if already published
+        id: check
+        run: |
+          PKG_NAME="oh-my-opencode-${{ matrix.platform }}"
+          VERSION="${{ inputs.version }}"
+          STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://registry.npmjs.org/${PKG_NAME}/${VERSION}")
+          if [ "$STATUS" = "200" ]; then
+            echo "skip=true" >> $GITHUB_OUTPUT
+            echo "✓ ${PKG_NAME}@${VERSION} already published, skipping"
+          else
+            echo "skip=false" >> $GITHUB_OUTPUT
+            echo "→ ${PKG_NAME}@${VERSION} will be published"
+          fi
+
+      - name: Download artifact
+        if: steps.check.outputs.skip != 'true'
+        uses: actions/download-artifact@v4
+        with:
+          name: binary-${{ matrix.platform }}
+          path: .
+
+      - name: Extract artifact
+        if: steps.check.outputs.skip != 'true'
+        run: |
+          PLATFORM="${{ matrix.platform }}"
+          mkdir -p packages/${PLATFORM}
+          
+          if [ "$PLATFORM" = "windows-x64" ]; then
+            unzip binary-${PLATFORM}.zip -d packages/${PLATFORM}/
+          else
+            tar -xzvf binary-${PLATFORM}.tar.gz -C packages/${PLATFORM}/
+          fi
+          
+          echo "Extracted contents:"
+          ls -la packages/${PLATFORM}/
+          ls -la packages/${PLATFORM}/bin/
+
+      - uses: actions/setup-node@v4
+        if: steps.check.outputs.skip != 'true'
+        with:
+          node-version: "24"
+          registry-url: "https://registry.npmjs.org"

      - name: Publish ${{ matrix.platform }}
        if: steps.check.outputs.skip != 'true'
        run: |
          cd packages/${{ matrix.platform }}
+          
          TAG_ARG=""
          if [ -n "${{ inputs.dist_tag }}" ]; then
            TAG_ARG="--tag ${{ inputs.dist_tag }}"
          fi
-          npm publish --access public $TAG_ARG
+          
+          npm publish --access public --provenance $TAG_ARG
        env:
-          NPM_CONFIG_PROVENANCE: false
+          NODE_AUTH_TOKEN: ${{ secrets.NODE_AUTH_TOKEN }}
+          NPM_CONFIG_PROVENANCE: true
+        timeout-minutes: 15
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -98,13 +98,13 @@ oh-my-opencode/

 | Agent | Model | Purpose |
 |-------|-------|---------|
-| Sisyphus | anthropic/claude-opus-4-5 | Primary orchestrator |
-| Atlas | anthropic/claude-opus-4-5 | Master orchestrator |
+| Sisyphus | anthropic/claude-opus-4-5 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro) |
+| Atlas | anthropic/claude-sonnet-4-5 | Master orchestrator (fallback: kimi-k2.5 → gpt-5.2) |
 | oracle | openai/gpt-5.2 | Consultation, debugging |
-| librarian | opencode/big-pickle | Docs, GitHub search |
-| explore | opencode/gpt-5-nano | Fast codebase grep |
+| librarian | zai-coding-plan/glm-4.7 | Docs, GitHub search (fallback: glm-4.7-free) |
+| explore | anthropic/claude-haiku-4-5 | Fast codebase grep (fallback: gpt-5-mini → gpt-5-nano) |
 | multimodal-looker | google/gemini-3-flash | PDF/image analysis |
-| Prometheus | anthropic/claude-opus-4-5 | Strategic planning |
+| Prometheus | anthropic/claude-opus-4-5 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |

 ## COMMANDS

--- a/README.ja.md
+++ b/README.ja.md
@@ -189,7 +189,7 @@ Windows から Linux に初めて乗り換えた時のこと、自分の思い
  - Oracle: 設計、デバッグ (GPT 5.2 Medium)
  - Frontend UI/UX Engineer: フロントエンド開発 (Gemini 3 Pro)
  - Librarian: 公式ドキュメント、オープンソース実装、コードベース探索 (Claude Sonnet 4.5)
-  - Explore: 超高速コードベース探索 (Contextual Grep) (Grok Code)
+   - Explore: 超高速コードベース探索 (Contextual Grep) (Claude Haiku 4.5)
 - Full LSP / AstGrep Support: 決定的にリファクタリングしましょう。
 - Todo Continuation Enforcer: 途中で諦めたら、続行を強制します。これがシジフォスに岩を転がし続けさせる秘訣です。
 - Comment Checker: AIが過剰なコメントを付けないようにします。シジフォスが生成したコードは、人間が書いたものと区別がつかないべきです。
--- a/README.ko.md
+++ b/README.ko.md
@@ -197,7 +197,7 @@ Hey please read this readme and tell me why it is different from other agent har
  - Oracle: 디자인, 디버깅 (GPT 5.2 Medium)
  - Frontend UI/UX Engineer: 프론트엔드 개발 (Gemini 3 Pro)
  - Librarian: 공식 문서, 오픈 소스 구현, 코드베이스 탐색 (Claude Sonnet 4.5)
-  - Explore: 엄청나게 빠른 코드베이스 탐색 (Contextual Grep) (Grok Code)
+   - Explore: 엄청나게 빠른 코드베이스 탐색 (Contextual Grep) (Claude Haiku 4.5)
 - 완전한 LSP / AstGrep 지원: 결정적으로 리팩토링합니다.
 - TODO 연속 강제: 에이전트가 중간에 멈추면 계속하도록 강제합니다. **이것이 Sisyphus가 그 바위를 굴리게 하는 것입니다.**
 - 주석 검사기: AI가 과도한 주석을 추가하는 것을 방지합니다. Sisyphus가 생성한 코드는 인간이 작성한 것과 구별할 수 없어야 합니다.
--- a/README.md
+++ b/README.md
@@ -196,7 +196,7 @@ Meet our main agent: Sisyphus (Opus 4.5 High). Below are the tools Sisyphus uses
  - Oracle: Design, debugging (GPT 5.2 Medium)
  - Frontend UI/UX Engineer: Frontend development (Gemini 3 Pro)
  - Librarian: Official docs, open source implementations, codebase exploration (Claude Sonnet 4.5)
-  - Explore: Blazing fast codebase exploration (Contextual Grep) (Grok Code)
+  - Explore: Blazing fast codebase exploration (Contextual Grep) (Claude Haiku 4.5)
 - Full LSP / AstGrep Support: Refactor decisively.
 - Todo Continuation Enforcer: Forces the agent to continue if it quits halfway. **This is what keeps Sisyphus rolling that boulder.**
 - Comment Checker: Prevents AI from adding excessive comments. Code generated by Sisyphus should be indistinguishable from human-written code.
--- a/README.zh-cn.md
+++ b/README.zh-cn.md
@@ -193,7 +193,7 @@
  - Oracle：设计、调试 (GPT 5.2 Medium)
  - Frontend UI/UX Engineer：前端开发 (Gemini 3 Pro)
  - Librarian：官方文档、开源实现、代码库探索 (Claude Sonnet 4.5)
-  - Explore：极速代码库探索（上下文感知 Grep）(Grok Code)
+   - Explore：极速代码库探索（上下文感知 Grep）(Claude Haiku 4.5)
 - 完整 LSP / AstGrep 支持：果断重构。
 - Todo 继续执行器：如果智能体中途退出，强制它继续。**这就是让 Sisyphus 继续推动巨石的关键。**
 - 注释检查器：防止 AI 添加过多注释。Sisyphus 生成的代码应该与人类编写的代码无法区分。
--- a/docs/category-skill-guide.md
+++ b/docs/category-skill-guide.md
@@ -23,6 +23,7 @@ A Category is an agent configuration preset optimized for specific domains.
 |----------|---------------|-----------|
 | `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 |
+| `deep` | `openai/gpt-5.2-codex` (medium) | Goal-oriented autonomous problem-solving. Thorough research before action. For hairy problems requiring deep understanding. |
 | `artistry` | `google/gemini-3-pro` (max) | Highly creative/artistic tasks, novel ideas |
 | `quick` | `anthropic/claude-haiku-4-5` | Trivial tasks - single file changes, typo fixes, simple modifications |
 | `unspecified-low` | `anthropic/claude-sonnet-4-5` | Tasks that don't fit other categories, low effort required |
--- a/docs/configurations.md
+++ b/docs/configurations.md
@@ -894,15 +894,15 @@ Each agent has a defined provider priority chain. The system tries providers in

 | Agent | Model (no prefix) | Provider Priority Chain |
 |-------|-------------------|-------------------------|
-| **Sisyphus** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
-| **oracle** | `gpt-5.2` | openai → anthropic → google → github-copilot → opencode |
-| **librarian** | `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 |
-| **Atlas** | `claude-sonnet-4-5` | anthropic → github-copilot → opencode → antigravity → google |
+| **Sisyphus** | `claude-opus-4-5` | anthropic → kimi-for-coding → zai-coding-plan → openai → google |
+| **oracle** | `gpt-5.2` | openai → google → anthropic |
+| **librarian** | `glm-4.7` | zai-coding-plan → opencode → anthropic |
+| **explore** | `claude-haiku-4-5` | anthropic → github-copilot → opencode |
+| **multimodal-looker** | `gemini-3-flash` | google → openai → zai-coding-plan → kimi-for-coding → anthropic → opencode |
+| **Prometheus (Planner)** | `claude-opus-4-5` | anthropic → kimi-for-coding → openai → google |
+| **Metis (Plan Consultant)** | `claude-opus-4-5` | anthropic → kimi-for-coding → openai → google |
+| **Momus (Plan Reviewer)** | `gpt-5.2` | openai → anthropic → google |
+| **Atlas** | `claude-sonnet-4-5` | anthropic → kimi-for-coding → openai → google |

 ### Category Provider Chains

@@ -910,13 +910,14 @@ Categories follow the same resolution logic:

 | Category | Model (no prefix) | Provider Priority Chain |
 |----------|-------------------|-------------------------|
-| **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` | 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` | google → openai → anthropic → github-copilot → opencode |
+| **visual-engineering** | `gemini-3-pro` | google → anthropic → zai-coding-plan |
+| **ultrabrain** | `gpt-5.2-codex` | openai → google → anthropic |
+| **deep** | `gpt-5.2-codex` | openai → anthropic → google |
+| **artistry** | `gemini-3-pro` | google → anthropic → openai |
+| **quick** | `claude-haiku-4-5` | anthropic → google → opencode |
+| **unspecified-low** | `claude-sonnet-4-5` | anthropic → openai → google |
+| **unspecified-high** | `claude-opus-4-5` | anthropic → openai → google |
+| **writing** | `gemini-3-flash` | google → anthropic → zai-coding-plan → openai |

 ### Checking Your Configuration

--- a/docs/features.md
+++ b/docs/features.md
@@ -10,19 +10,19 @@ Oh-My-OpenCode provides 10 specialized AI agents. Each has distinct expertise, o

 | Agent | Model | Purpose |
 |-------|-------|---------|
-| **Sisyphus** | `anthropic/claude-opus-4-5` | **The default orchestrator.** Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). |
+| **Sisyphus** | `anthropic/claude-opus-4-5` | **The default orchestrator.** Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). Fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro. |
 | **oracle** | `openai/gpt-5.2` | Architecture decisions, code review, debugging. Read-only consultation - stellar logical reasoning and deep analysis. Inspired by AmpCode. |
-| **librarian** | `opencode/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. |
+| **librarian** | `zai-coding-plan/glm-4.7` | Multi-repo analysis, documentation lookup, OSS implementation examples. Deep codebase understanding with evidence-based answers. Fallback: glm-4.7-free → claude-sonnet-4-5. |
+| **explore** | `anthropic/claude-haiku-4-5` | Fast codebase exploration and contextual grep. Fallback: gpt-5-mini → gpt-5-nano. |
+| **multimodal-looker** | `google/gemini-3-flash` | Visual content specialist. Analyzes PDFs, images, diagrams to extract information. Fallback: gpt-5.2 → glm-4.6v → kimi-k2.5 → claude-haiku-4-5 → gpt-5-nano. |

 ### Planning Agents

 | Agent | Model | Purpose |
 |-------|-------|---------|
-| **Prometheus** | `anthropic/claude-opus-4-5` | Strategic planner with interview mode. Creates detailed work plans through iterative questioning. |
-| **Metis** | `anthropic/claude-sonnet-4-5` | Plan consultant - pre-planning analysis. Identifies hidden intentions, ambiguities, and AI failure points. |
-| **Momus** | `anthropic/claude-sonnet-4-5` | Plan reviewer - validates plans against clarity, verifiability, and completeness standards. |
+| **Prometheus** | `anthropic/claude-opus-4-5` | Strategic planner with interview mode. Creates detailed work plans through iterative questioning. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
+| **Metis** | `anthropic/claude-opus-4-5` | Plan consultant - pre-planning analysis. Identifies hidden intentions, ambiguities, and AI failure points. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
+| **Momus** | `openai/gpt-5.2` | Plan reviewer - validates plans against clarity, verifiability, and completeness standards. Fallback: gpt-5.2 → claude-opus-4-5 → gemini-3-pro. |

 ### Invoking Agents

--- a/docs/guide/installation.md
+++ b/docs/guide/installation.md
@@ -213,7 +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/gpt-5-nano`, and `opencode/big-pickle`.
+OpenCode Zen provides access to `opencode/` prefixed models including `opencode/claude-opus-4-5`, `opencode/gpt-5.2`, `opencode/gpt-5-nano`, and `opencode/glm-4.7-free`.

 When OpenCode Zen is the best available provider (no native or Copilot), these models are used:

@@ -222,7 +222,7 @@ When OpenCode Zen is the best available provider (no native or Copilot), these m
 | **Sisyphus**  | `opencode/claude-opus-4-5`       |
 | **Oracle**    | `opencode/gpt-5.2`               |
 | **Explore**   | `opencode/gpt-5-nano`             |
-| **Librarian** | `opencode/big-pickle`          |
+| **Librarian** | `opencode/glm-4.7-free`          |

 ##### Setup

@@ -278,7 +278,7 @@ After everything is set up and working, ask the user:

 If the user agrees, run:
 ```bash
-gh repo star code-yeongyu/oh-my-opencode
+gh api --silent --method PUT /user/starred/code-yeongyu/oh-my-opencode >/dev/null 2>&1 || true
 ```

 **Important**: Only run the command if the user explicitly says yes. Never run it automatically without consent.
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
  "name": "oh-my-opencode",
-  "version": "3.1.7",
+  "version": "3.1.9",
  "description": "The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools",
  "main": "dist/index.js",
  "types": "dist/index.d.ts",
@@ -74,13 +74,13 @@
    "typescript": "^5.7.3"
  },
  "optionalDependencies": {
-    "oh-my-opencode-darwin-arm64": "3.1.7",
-    "oh-my-opencode-darwin-x64": "3.1.7",
-    "oh-my-opencode-linux-arm64": "3.1.7",
-    "oh-my-opencode-linux-arm64-musl": "3.1.7",
-    "oh-my-opencode-linux-x64": "3.1.7",
-    "oh-my-opencode-linux-x64-musl": "3.1.7",
-    "oh-my-opencode-windows-x64": "3.1.7"
+    "oh-my-opencode-darwin-arm64": "3.1.9",
+    "oh-my-opencode-darwin-x64": "3.1.9",
+    "oh-my-opencode-linux-arm64": "3.1.9",
+    "oh-my-opencode-linux-arm64-musl": "3.1.9",
+    "oh-my-opencode-linux-x64": "3.1.9",
+    "oh-my-opencode-linux-x64-musl": "3.1.9",
+    "oh-my-opencode-windows-x64": "3.1.9"
  },
  "trustedDependencies": [
    "@ast-grep/cli",
--- a/packages/darwin-arm64/package.json
+++ b/packages/darwin-arm64/package.json
@@ -1,6 +1,6 @@
 {
  "name": "oh-my-opencode-darwin-arm64",
-  "version": "3.1.7",
+  "version": "3.1.9",
  "description": "Platform-specific binary for oh-my-opencode (darwin-arm64)",
  "license": "MIT",
  "repository": {
--- a/packages/darwin-x64/package.json
+++ b/packages/darwin-x64/package.json
@@ -1,6 +1,6 @@
 {
  "name": "oh-my-opencode-darwin-x64",
-  "version": "3.1.7",
+  "version": "3.1.9",
  "description": "Platform-specific binary for oh-my-opencode (darwin-x64)",
  "license": "MIT",
  "repository": {
--- a/packages/linux-arm64-musl/package.json
+++ b/packages/linux-arm64-musl/package.json
@@ -1,6 +1,6 @@
 {
  "name": "oh-my-opencode-linux-arm64-musl",
-  "version": "3.1.7",
+  "version": "3.1.9",
  "description": "Platform-specific binary for oh-my-opencode (linux-arm64-musl)",
  "license": "MIT",
  "repository": {
--- a/packages/linux-arm64/package.json
+++ b/packages/linux-arm64/package.json
@@ -1,6 +1,6 @@
 {
  "name": "oh-my-opencode-linux-arm64",
-  "version": "3.1.7",
+  "version": "3.1.9",
  "description": "Platform-specific binary for oh-my-opencode (linux-arm64)",
  "license": "MIT",
  "repository": {
--- a/packages/linux-x64-musl/package.json
+++ b/packages/linux-x64-musl/package.json
@@ -1,6 +1,6 @@
 {
  "name": "oh-my-opencode-linux-x64-musl",
-  "version": "3.1.7",
+  "version": "3.1.9",
  "description": "Platform-specific binary for oh-my-opencode (linux-x64-musl)",
  "license": "MIT",
  "repository": {
--- a/packages/linux-x64/package.json
+++ b/packages/linux-x64/package.json
@@ -1,6 +1,6 @@
 {
  "name": "oh-my-opencode-linux-x64",
-  "version": "3.1.7",
+  "version": "3.1.9",
  "description": "Platform-specific binary for oh-my-opencode (linux-x64)",
  "license": "MIT",
  "repository": {
--- a/packages/windows-x64/package.json
+++ b/packages/windows-x64/package.json
@@ -1,6 +1,6 @@
 {
  "name": "oh-my-opencode-windows-x64",
-  "version": "3.1.7",
+  "version": "3.1.9",
  "description": "Platform-specific binary for oh-my-opencode (windows-x64)",
  "license": "MIT",
  "repository": {
--- a/signatures/cla.json
+++ b/signatures/cla.json
@@ -967,6 +967,46 @@
      "created_at": "2026-01-29T09:00:28Z",
      "repoId": 1108837393,
      "pullRequestNo": 1241
+    },
+    {
+      "name": "LeekJay",
+      "id": 39609783,
+      "comment_id": 3819009761,
+      "created_at": "2026-01-29T17:03:24Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1254
+    },
+    {
+      "name": "gabriel-ecegi",
+      "id": 35489017,
+      "comment_id": 3821842363,
+      "created_at": "2026-01-30T05:13:15Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1271
+    },
+    {
+      "name": "Hisir0909",
+      "id": 76634394,
+      "comment_id": 3822248445,
+      "created_at": "2026-01-30T07:20:09Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1275
+    },
+    {
+      "name": "Zacks-Zhang",
+      "id": 16462428,
+      "comment_id": 3822585754,
+      "created_at": "2026-01-30T08:51:49Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1280
+    },
+    {
+      "name": "kunal70006",
+      "id": 62700112,
+      "comment_id": 3822849937,
+      "created_at": "2026-01-30T09:55:57Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1282
    }
  ]
 }
--- a/src/agents/AGENTS.md
+++ b/src/agents/AGENTS.md
@@ -25,15 +25,15 @@ agents/
 ## AGENT MODELS
 | Agent | Model | Temp | Purpose |
 |-------|-------|------|---------|
-| Sisyphus | anthropic/claude-opus-4-5 | 0.1 | Primary orchestrator |
-| Atlas | anthropic/claude-opus-4-5 | 0.1 | Master orchestrator |
+| Sisyphus | anthropic/claude-opus-4-5 | 0.1 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro) |
+| Atlas | anthropic/claude-sonnet-4-5 | 0.1 | Master orchestrator (fallback: kimi-k2.5 → gpt-5.2) |
 | oracle | openai/gpt-5.2 | 0.1 | Consultation, debugging |
-| librarian | opencode/big-pickle | 0.1 | Docs, GitHub search |
-| explore | opencode/gpt-5-nano | 0.1 | Fast contextual grep |
+| librarian | zai-coding-plan/glm-4.7 | 0.1 | Docs, GitHub search (fallback: glm-4.7-free) |
+| explore | anthropic/claude-haiku-4-5 | 0.1 | Fast contextual grep (fallback: gpt-5-mini → gpt-5-nano) |
 | multimodal-looker | google/gemini-3-flash | 0.1 | PDF/image analysis |
-| Prometheus | anthropic/claude-opus-4-5 | 0.1 | Strategic planning |
-| Metis | anthropic/claude-sonnet-4-5 | 0.3 | Pre-planning analysis |
-| Momus | anthropic/claude-sonnet-4-5 | 0.1 | Plan validation |
+| Prometheus | anthropic/claude-opus-4-5 | 0.1 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
+| Metis | anthropic/claude-opus-4-5 | 0.3 | Pre-planning analysis (fallback: kimi-k2.5 → gpt-5.2) |
+| Momus | openai/gpt-5.2 | 0.1 | Plan validation (fallback: claude-opus-4-5) |
 | Sisyphus-Junior | anthropic/claude-sonnet-4-5 | 0.1 | Category-spawned executor |

 ## HOW TO ADD
--- a/src/agents/atlas.ts
+++ b/src/agents/atlas.ts
@@ -1,5 +1,7 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
+
+const MODE: AgentMode = "primary"
 import type { AvailableAgent, AvailableSkill, AvailableCategory } from "./dynamic-agent-prompt-builder"
 import { buildCategorySkillsDelegationGuide } from "./dynamic-agent-prompt-builder"
 import type { CategoryConfig } from "../config/schema"
@@ -530,7 +532,7 @@ export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
  return {
    description:
      "Orchestrates work via delegate_task() to complete ALL tasks in a todo list until fully done. (Atlas - OhMyOpenCode)",
-    mode: "primary" as const,
+    mode: MODE,
    ...(ctx.model ? { model: ctx.model } : {}),
    temperature: 0.1,
    prompt: buildDynamicOrchestratorPrompt(ctx),
@@ -539,6 +541,7 @@ export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
    ...restrictions,
  } as AgentConfig
 }
+createAtlasAgent.mode = MODE

 export const atlasPromptMetadata: AgentPromptMetadata = {
  category: "advisor",
--- a/src/agents/explore.ts
+++ b/src/agents/explore.ts
@@ -1,7 +1,9 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { createAgentToolRestrictions } from "../shared/permission-compat"

+const MODE: AgentMode = "subagent"
+
 export const EXPLORE_PROMPT_METADATA: AgentPromptMetadata = {
  category: "exploration",
  cost: "FREE",
@@ -34,7 +36,7 @@ export function createExploreAgent(model: string): AgentConfig {
  return {
    description:
      'Contextual grep for codebases. Answers "Where is X?", "Which file has Y?", "Find the code that does Z". Fire multiple in parallel for broad searches. Specify thoroughness: "quick" for basic, "medium" for moderate, "very thorough" for comprehensive analysis. (Explore - OhMyOpenCode)',
-    mode: "subagent" as const,
+    mode: MODE,
    model,
    temperature: 0.1,
    ...restrictions,
@@ -119,4 +121,4 @@ Use the right tool for the job:
 Flood with parallel calls. Cross-validate findings across multiple tools.`,
  }
 }
-
+createExploreAgent.mode = MODE
--- a/src/agents/librarian.ts
+++ b/src/agents/librarian.ts
@@ -1,7 +1,9 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { createAgentToolRestrictions } from "../shared/permission-compat"

+const MODE: AgentMode = "subagent"
+
 export const LIBRARIAN_PROMPT_METADATA: AgentPromptMetadata = {
  category: "exploration",
  cost: "CHEAP",
@@ -31,7 +33,7 @@ export function createLibrarianAgent(model: string): AgentConfig {
  return {
    description:
      "Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search. MUST BE USED when users ask to look up code in remote repositories, explain library internals, or find usage examples in open source. (Librarian - OhMyOpenCode)",
-    mode: "subagent" as const,
+    mode: MODE,
    model,
    temperature: 0.1,
    ...restrictions,
@@ -323,4 +325,4 @@ grep_app_searchGitHub(query: "useQuery")
 `,
  }
 }
-
+createLibrarianAgent.mode = MODE
--- a/src/agents/metis.ts
+++ b/src/agents/metis.ts
@@ -1,7 +1,9 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { createAgentToolRestrictions } from "../shared/permission-compat"

+const MODE: AgentMode = "subagent"
+
 /**
 * Metis - Plan Consultant Agent
 *
@@ -311,7 +313,7 @@ export function createMetisAgent(model: string): AgentConfig {
  return {
    description:
      "Pre-planning consultant that analyzes requests to identify hidden intentions, ambiguities, and AI failure points. (Metis - OhMyOpenCode)",
-    mode: "subagent" as const,
+    mode: MODE,
    model,
    temperature: 0.3,
    ...metisRestrictions,
@@ -319,7 +321,7 @@ export function createMetisAgent(model: string): AgentConfig {
    thinking: { type: "enabled", budgetTokens: 32000 },
  } as AgentConfig
 }
-
+createMetisAgent.mode = MODE

 export const metisPromptMetadata: AgentPromptMetadata = {
  category: "advisor",
--- a/src/agents/momus.ts
+++ b/src/agents/momus.ts
@@ -1,8 +1,10 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { isGptModel } from "./types"
 import { createAgentToolRestrictions } from "../shared/permission-compat"

+const MODE: AgentMode = "subagent"
+
 /**
 * Momus - Plan Reviewer Agent
 *
@@ -400,7 +402,7 @@ export function createMomusAgent(model: string): AgentConfig {
  const base = {
    description:
      "Expert reviewer for evaluating work plans against rigorous clarity, verifiability, and completeness standards. (Momus - OhMyOpenCode)",
-    mode: "subagent" as const,
+    mode: MODE,
    model,
    temperature: 0.1,
    ...restrictions,
@@ -413,7 +415,7 @@ export function createMomusAgent(model: string): AgentConfig {

  return { ...base, thinking: { type: "enabled", budgetTokens: 32000 } } as AgentConfig
 }
-
+createMomusAgent.mode = MODE

 export const momusPromptMetadata: AgentPromptMetadata = {
  category: "advisor",
--- a/src/agents/multimodal-looker.ts
+++ b/src/agents/multimodal-looker.ts
@@ -1,7 +1,9 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { createAgentToolAllowlist } from "../shared/permission-compat"

+const MODE: AgentMode = "subagent"
+
 export const MULTIMODAL_LOOKER_PROMPT_METADATA: AgentPromptMetadata = {
  category: "utility",
  cost: "CHEAP",
@@ -15,7 +17,7 @@ export function createMultimodalLookerAgent(model: string): AgentConfig {
  return {
    description:
      "Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents. (Multimodal-Looker - OhMyOpenCode)",
-    mode: "subagent" as const,
+    mode: MODE,
    model,
    temperature: 0.1,
    ...restrictions,
@@ -53,4 +55,4 @@ Response rules:
 Your output goes straight to the main agent for continued work.`,
  }
 }
-
+createMultimodalLookerAgent.mode = MODE
--- a/src/agents/oracle.ts
+++ b/src/agents/oracle.ts
@@ -1,8 +1,10 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentPromptMetadata } from "./types"
+import type { AgentMode, AgentPromptMetadata } from "./types"
 import { isGptModel } from "./types"
 import { createAgentToolRestrictions } from "../shared/permission-compat"

+const MODE: AgentMode = "subagent"
+
 export const ORACLE_PROMPT_METADATA: AgentPromptMetadata = {
  category: "advisor",
  cost: "EXPENSIVE",
@@ -106,7 +108,7 @@ export function createOracleAgent(model: string): AgentConfig {
  const base = {
    description:
      "Read-only consultation agent. High-IQ reasoning specialist for debugging hard problems and high-difficulty architecture design. (Oracle - OhMyOpenCode)",
-    mode: "subagent" as const,
+    mode: MODE,
    model,
    temperature: 0.1,
    ...restrictions,
@@ -119,4 +121,5 @@ export function createOracleAgent(model: string): AgentConfig {

  return { ...base, thinking: { type: "enabled", budgetTokens: 32000 } } as AgentConfig
 }
+createOracleAgent.mode = MODE

--- a/src/agents/sisyphus-junior.ts
+++ b/src/agents/sisyphus-junior.ts
@@ -1,4 +1,5 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
+import type { AgentMode } from "./types"
 import { isGptModel } from "./types"
 import type { AgentOverrideConfig } from "../config/schema"
 import {
@@ -6,6 +7,8 @@ import {
  type PermissionValue,
 } from "../shared/permission-compat"

+const MODE: AgentMode = "subagent"
+
 const SISYPHUS_JUNIOR_PROMPT = `<Role>
 Sisyphus-Junior - Focused executor from OhMyOpenCode.
 Execute tasks directly. NEVER delegate or spawn other agents.
@@ -85,7 +88,7 @@ export function createSisyphusJuniorAgentWithOverrides(
  const base: AgentConfig = {
    description: override?.description ??
      "Focused task executor. Same discipline, no delegation. (Sisyphus-Junior - OhMyOpenCode)",
-    mode: "subagent" as const,
+    mode: MODE,
    model,
    temperature,
    maxTokens: 64000,
@@ -107,3 +110,5 @@ export function createSisyphusJuniorAgentWithOverrides(
    thinking: { type: "enabled", budgetTokens: 32000 },
  } as AgentConfig
 }
+
+createSisyphusJuniorAgentWithOverrides.mode = MODE
--- a/src/agents/sisyphus.ts
+++ b/src/agents/sisyphus.ts
@@ -1,5 +1,8 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
+import type { AgentMode } from "./types"
 import { isGptModel } from "./types"
+
+const MODE: AgentMode = "primary"
 import type { AvailableAgent, AvailableTool, AvailableSkill, AvailableCategory } from "./dynamic-agent-prompt-builder"
 import {
  buildKeyTriggersSection,
@@ -434,7 +437,7 @@ export function createSisyphusAgent(
  const base = {
    description:
      "Powerful AI orchestrator. Plans obsessively with todos, assesses search complexity before exploration, delegates strategically via category+skills combinations. Uses explore for internal code (parallel-friendly), librarian for external docs. (Sisyphus - OhMyOpenCode)",
-    mode: "primary" as const,
+    mode: MODE,
    model,
    maxTokens: 64000,
    prompt,
@@ -448,3 +451,4 @@ export function createSisyphusAgent(

  return { ...base, thinking: { type: "enabled", budgetTokens: 32000 } }
 }
+createSisyphusAgent.mode = MODE
--- a/src/agents/types.ts
+++ b/src/agents/types.ts
@@ -1,6 +1,20 @@
 import type { AgentConfig } from "@opencode-ai/sdk"

-export type AgentFactory = (model: string) => AgentConfig
+/**
+ * Agent mode determines UI model selection behavior:
+ * - "primary": Respects user's UI-selected model (sisyphus, atlas)
+ * - "subagent": Uses own fallback chain, ignores UI selection (oracle, explore, etc.)
+ * - "all": Available in both contexts (OpenCode compatibility)
+ */
+export type AgentMode = "primary" | "subagent" | "all"
+
+/**
+ * Agent factory function with static mode property.
+ * Mode is exposed as static property for pre-instantiation access.
+ */
+export type AgentFactory = ((model: string) => AgentConfig) & {
+  mode: AgentMode
+}

 /**
 * Agent category for grouping in Sisyphus prompt sections
--- a/src/agents/utils.ts
+++ b/src/agents/utils.ts
@@ -10,7 +10,7 @@ import { createMetisAgent } from "./metis"
 import { createAtlasAgent } from "./atlas"
 import { createMomusAgent } from "./momus"
 import type { AvailableAgent, AvailableCategory, AvailableSkill } from "./dynamic-agent-prompt-builder"
-import { deepMerge, fetchAvailableModels, resolveModelWithFallback, AGENT_MODEL_REQUIREMENTS, findCaseInsensitive, includesCaseInsensitive, readConnectedProvidersCache } from "../shared"
+import { deepMerge, fetchAvailableModels, resolveModelWithFallback, AGENT_MODEL_REQUIREMENTS, findCaseInsensitive, includesCaseInsensitive, readConnectedProvidersCache, isModelAvailable } from "../shared"
 import { DEFAULT_CATEGORIES, CATEGORY_DESCRIPTIONS } from "../tools/delegate-task/constants"
 import { resolveMultipleSkills } from "../features/opencode-skill-loader/skill-content"
 import { createBuiltinSkills } from "../features/builtin-skills"
@@ -222,11 +222,20 @@ export async function createBuiltinAgents(
     if (agentName === "atlas") continue
     if (includesCaseInsensitive(disabledAgents, agentName)) continue

-    const override = findCaseInsensitive(agentOverrides, agentName)
-    const requirement = AGENT_MODEL_REQUIREMENTS[agentName]
-    
-    const resolution = resolveModelWithFallback({
-      uiSelectedModel,
+     const override = findCaseInsensitive(agentOverrides, agentName)
+     const requirement = AGENT_MODEL_REQUIREMENTS[agentName]
+     
+     // Check if agent requires a specific model
+     if (requirement?.requiresModel && availableModels) {
+       if (!isModelAvailable(requirement.requiresModel, availableModels)) {
+         continue
+       }
+     }
+     
+     const isPrimaryAgent = isFactory(source) && source.mode === "primary"
+     
+     const resolution = resolveModelWithFallback({
+      uiSelectedModel: isPrimaryAgent ? uiSelectedModel : undefined,
      userModel: override?.model,
      fallbackChain: requirement?.fallbackChain,
      availableModels,
@@ -320,7 +329,7 @@ export async function createBuiltinAgents(
     const atlasRequirement = AGENT_MODEL_REQUIREMENTS["atlas"]
    
    const atlasResolution = resolveModelWithFallback({
-      uiSelectedModel,
+      // NOTE: Atlas does NOT use uiSelectedModel - respects its own fallbackChain (k2p5 primary)
      userModel: orchestratorOverride?.model,
      fallbackChain: atlasRequirement?.fallbackChain,
      availableModels,
--- a/src/cli/snapshots/model-fallback.test.ts.snap
+++ b/src/cli/snapshots/model-fallback.test.ts.snap
@@ -5,54 +5,57 @@ exports[`generateModelConfig no providers available returns ULTIMATE_FALLBACK fo
  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
  "agents": {
    "atlas": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "explore": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "librarian": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "metis": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "momus": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "multimodal-looker": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "oracle": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "prometheus": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "sisyphus": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
  },
  "categories": {
    "artistry": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
+    },
+    "deep": {
+      "model": "opencode/glm-4.7-free",
    },
    "quick": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "ultrabrain": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "unspecified-high": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "unspecified-low": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "visual-engineering": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "writing": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
  },
 }
@@ -77,6 +80,7 @@ exports[`generateModelConfig single native provider uses Claude models when only
    },
    "momus": {
      "model": "anthropic/claude-opus-4-5",
+      "variant": "max",
    },
    "multimodal-looker": {
      "model": "anthropic/claude-haiku-4-5",
@@ -98,6 +102,10 @@ exports[`generateModelConfig single native provider uses Claude models when only
      "model": "anthropic/claude-opus-4-5",
      "variant": "max",
    },
+    "deep": {
+      "model": "anthropic/claude-opus-4-5",
+      "variant": "max",
+    },
    "quick": {
      "model": "anthropic/claude-haiku-4-5",
    },
@@ -141,6 +149,7 @@ exports[`generateModelConfig single native provider uses Claude models with isMa
    },
    "momus": {
      "model": "anthropic/claude-opus-4-5",
+      "variant": "max",
    },
    "multimodal-looker": {
      "model": "anthropic/claude-haiku-4-5",
@@ -163,6 +172,10 @@ exports[`generateModelConfig single native provider uses Claude models with isMa
      "model": "anthropic/claude-opus-4-5",
      "variant": "max",
    },
+    "deep": {
+      "model": "anthropic/claude-opus-4-5",
+      "variant": "max",
+    },
    "quick": {
      "model": "anthropic/claude-haiku-4-5",
    },
@@ -199,7 +212,7 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
      "model": "opencode/gpt-5-nano",
    },
    "librarian": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "metis": {
      "model": "openai/gpt-5.2",
@@ -229,8 +242,12 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
    "artistry": {
      "model": "openai/gpt-5.2",
    },
+    "deep": {
+      "model": "openai/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "ultrabrain": {
      "model": "openai/gpt-5.2-codex",
@@ -245,8 +262,7 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
      "variant": "medium",
    },
    "visual-engineering": {
-      "model": "openai/gpt-5.2",
-      "variant": "high",
+      "model": "opencode/glm-4.7-free",
    },
    "writing": {
      "model": "openai/gpt-5.2",
@@ -266,7 +282,7 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
      "model": "opencode/gpt-5-nano",
    },
    "librarian": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "metis": {
      "model": "openai/gpt-5.2",
@@ -296,8 +312,12 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
    "artistry": {
      "model": "openai/gpt-5.2",
    },
+    "deep": {
+      "model": "openai/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "ultrabrain": {
      "model": "openai/gpt-5.2-codex",
@@ -312,8 +332,7 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
      "variant": "medium",
    },
    "visual-engineering": {
-      "model": "openai/gpt-5.2",
-      "variant": "high",
+      "model": "opencode/glm-4.7-free",
    },
    "writing": {
      "model": "openai/gpt-5.2",
@@ -333,7 +352,7 @@ exports[`generateModelConfig single native provider uses Gemini models when only
      "model": "opencode/gpt-5-nano",
    },
    "librarian": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "metis": {
      "model": "google/gemini-3-pro",
@@ -348,6 +367,7 @@ exports[`generateModelConfig single native provider uses Gemini models when only
    },
    "oracle": {
      "model": "google/gemini-3-pro",
+      "variant": "max",
    },
    "prometheus": {
      "model": "google/gemini-3-pro",
@@ -361,11 +381,16 @@ exports[`generateModelConfig single native provider uses Gemini models when only
      "model": "google/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "google/gemini-3-pro",
+      "variant": "max",
+    },
    "quick": {
      "model": "google/gemini-3-flash",
    },
    "ultrabrain": {
      "model": "google/gemini-3-pro",
+      "variant": "max",
    },
    "unspecified-high": {
      "model": "google/gemini-3-flash",
@@ -394,7 +419,7 @@ exports[`generateModelConfig single native provider uses Gemini models with isMa
      "model": "opencode/gpt-5-nano",
    },
    "librarian": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "metis": {
      "model": "google/gemini-3-pro",
@@ -409,6 +434,7 @@ exports[`generateModelConfig single native provider uses Gemini models with isMa
    },
    "oracle": {
      "model": "google/gemini-3-pro",
+      "variant": "max",
    },
    "prometheus": {
      "model": "google/gemini-3-pro",
@@ -422,11 +448,16 @@ exports[`generateModelConfig single native provider uses Gemini models with isMa
      "model": "google/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "google/gemini-3-pro",
+      "variant": "max",
+    },
    "quick": {
      "model": "google/gemini-3-flash",
    },
    "ultrabrain": {
      "model": "google/gemini-3-pro",
+      "variant": "max",
    },
    "unspecified-high": {
      "model": "google/gemini-3-pro",
@@ -485,6 +516,10 @@ exports[`generateModelConfig all native providers uses preferred models from fal
      "model": "google/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "openai/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
      "model": "anthropic/claude-haiku-4-5",
    },
@@ -550,6 +585,10 @@ exports[`generateModelConfig all native providers uses preferred models with isM
      "model": "google/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "openai/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
      "model": "anthropic/claude-haiku-4-5",
    },
@@ -579,13 +618,13 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
  "agents": {
    "atlas": {
-      "model": "opencode/claude-sonnet-4-5",
+      "model": "opencode/kimi-k2.5-free",
    },
    "explore": {
      "model": "opencode/claude-haiku-4-5",
    },
    "librarian": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "metis": {
      "model": "opencode/claude-opus-4-5",
@@ -615,6 +654,10 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
      "model": "opencode/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "opencode/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
      "model": "opencode/claude-haiku-4-5",
    },
@@ -643,13 +686,13 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
  "agents": {
    "atlas": {
-      "model": "opencode/claude-sonnet-4-5",
+      "model": "opencode/kimi-k2.5-free",
    },
    "explore": {
      "model": "opencode/claude-haiku-4-5",
    },
    "librarian": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "metis": {
      "model": "opencode/claude-opus-4-5",
@@ -680,6 +723,10 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
      "model": "opencode/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "opencode/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
      "model": "opencode/claude-haiku-4-5",
    },
@@ -745,6 +792,10 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models when
      "model": "github-copilot/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "github-copilot/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
      "model": "github-copilot/claude-haiku-4.5",
    },
@@ -810,6 +861,10 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models with
      "model": "github-copilot/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "github-copilot/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
      "model": "github-copilot/claude-haiku-4.5",
    },
@@ -839,7 +894,7 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian whe
  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
  "agents": {
    "atlas": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "explore": {
      "model": "opencode/gpt-5-nano",
@@ -848,42 +903,45 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian whe
      "model": "zai-coding-plan/glm-4.7",
    },
    "metis": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "momus": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "multimodal-looker": {
      "model": "zai-coding-plan/glm-4.6v",
    },
    "oracle": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "prometheus": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "sisyphus": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
  },
  "categories": {
    "artistry": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
+    },
+    "deep": {
+      "model": "opencode/glm-4.7-free",
    },
    "quick": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "ultrabrain": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "unspecified-high": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "unspecified-low": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "visual-engineering": {
-      "model": "opencode/big-pickle",
+      "model": "zai-coding-plan/glm-4.7",
    },
    "writing": {
      "model": "zai-coding-plan/glm-4.7",
@@ -897,7 +955,7 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian wit
  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
  "agents": {
    "atlas": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "explore": {
      "model": "opencode/gpt-5-nano",
@@ -906,19 +964,19 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian wit
      "model": "zai-coding-plan/glm-4.7",
    },
    "metis": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "momus": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "multimodal-looker": {
      "model": "zai-coding-plan/glm-4.6v",
    },
    "oracle": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "prometheus": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "sisyphus": {
      "model": "zai-coding-plan/glm-4.7",
@@ -926,22 +984,25 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian wit
  },
  "categories": {
    "artistry": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
+    },
+    "deep": {
+      "model": "opencode/glm-4.7-free",
    },
    "quick": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "ultrabrain": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "unspecified-high": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "unspecified-low": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "visual-engineering": {
-      "model": "opencode/big-pickle",
+      "model": "zai-coding-plan/glm-4.7",
    },
    "writing": {
      "model": "zai-coding-plan/glm-4.7",
@@ -955,13 +1016,13 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
  "agents": {
    "atlas": {
-      "model": "anthropic/claude-sonnet-4-5",
+      "model": "opencode/kimi-k2.5-free",
    },
    "explore": {
      "model": "anthropic/claude-haiku-4-5",
    },
    "librarian": {
-      "model": "opencode/big-pickle",
+      "model": "opencode/glm-4.7-free",
    },
    "metis": {
      "model": "anthropic/claude-opus-4-5",
@@ -991,6 +1052,10 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
      "model": "opencode/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "opencode/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
      "model": "anthropic/claude-haiku-4-5",
    },
@@ -1055,6 +1120,10 @@ exports[`generateModelConfig mixed provider scenarios uses OpenAI + Copilot comb
      "model": "github-copilot/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "openai/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
      "model": "github-copilot/claude-haiku-4.5",
    },
@@ -1097,6 +1166,7 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + ZAI combinat
    },
    "momus": {
      "model": "anthropic/claude-opus-4-5",
+      "variant": "max",
    },
    "multimodal-looker": {
      "model": "zai-coding-plan/glm-4.6v",
@@ -1118,6 +1188,10 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + ZAI combinat
      "model": "anthropic/claude-opus-4-5",
      "variant": "max",
    },
+    "deep": {
+      "model": "anthropic/claude-opus-4-5",
+      "variant": "max",
+    },
    "quick": {
      "model": "anthropic/claude-haiku-4-5",
    },
@@ -1161,12 +1235,13 @@ exports[`generateModelConfig mixed provider scenarios uses Gemini + Claude combi
    },
    "momus": {
      "model": "anthropic/claude-opus-4-5",
+      "variant": "max",
    },
    "multimodal-looker": {
      "model": "google/gemini-3-flash",
    },
    "oracle": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "google/gemini-3-pro",
      "variant": "max",
    },
    "prometheus": {
@@ -1182,11 +1257,15 @@ exports[`generateModelConfig mixed provider scenarios uses Gemini + Claude combi
      "model": "google/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "anthropic/claude-opus-4-5",
+      "variant": "max",
+    },
    "quick": {
      "model": "anthropic/claude-haiku-4-5",
    },
    "ultrabrain": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "google/gemini-3-pro",
      "variant": "max",
    },
    "unspecified-high": {
@@ -1210,7 +1289,7 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
  "agents": {
    "atlas": {
-      "model": "github-copilot/claude-sonnet-4.5",
+      "model": "opencode/kimi-k2.5-free",
    },
    "explore": {
      "model": "opencode/claude-haiku-4-5",
@@ -1246,6 +1325,10 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
      "model": "github-copilot/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "github-copilot/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
      "model": "github-copilot/claude-haiku-4.5",
    },
@@ -1274,7 +1357,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
  "agents": {
    "atlas": {
-      "model": "anthropic/claude-sonnet-4-5",
+      "model": "opencode/kimi-k2.5-free",
    },
    "explore": {
      "model": "anthropic/claude-haiku-4-5",
@@ -1310,6 +1393,10 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
      "model": "google/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "openai/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
      "model": "anthropic/claude-haiku-4-5",
    },
@@ -1338,7 +1425,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
  "agents": {
    "atlas": {
-      "model": "anthropic/claude-sonnet-4-5",
+      "model": "opencode/kimi-k2.5-free",
    },
    "explore": {
      "model": "anthropic/claude-haiku-4-5",
@@ -1375,6 +1462,10 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
      "model": "google/gemini-3-pro",
      "variant": "max",
    },
+    "deep": {
+      "model": "openai/gpt-5.2-codex",
+      "variant": "medium",
+    },
    "quick": {
      "model": "anthropic/claude-haiku-4-5",
    },
--- a/src/cli/config-manager.test.ts
+++ b/src/cli/config-manager.test.ts
@@ -250,6 +250,7 @@ describe("generateOmoConfig - model fallback system", () => {
      hasCopilot: false,
      hasOpencodeZen: false,
      hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
    }

    // #when generating config
@@ -271,6 +272,7 @@ describe("generateOmoConfig - model fallback system", () => {
      hasCopilot: false,
      hasOpencodeZen: false,
      hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
    }

    // #when generating config
@@ -290,6 +292,7 @@ describe("generateOmoConfig - model fallback system", () => {
      hasCopilot: true,
      hasOpencodeZen: false,
      hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
    }

    // #when generating config
@@ -309,6 +312,7 @@ describe("generateOmoConfig - model fallback system", () => {
      hasCopilot: false,
      hasOpencodeZen: false,
      hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
    }

    // #when generating config
@@ -316,7 +320,7 @@ describe("generateOmoConfig - model fallback system", () => {

    // #then should use ultimate fallback for all agents
    expect(result.$schema).toBe("https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json")
-    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("opencode/big-pickle")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("opencode/glm-4.7-free")
  })

  test("uses zai-coding-plan/glm-4.7 for librarian when Z.ai available", () => {
@@ -329,6 +333,7 @@ describe("generateOmoConfig - model fallback system", () => {
      hasCopilot: false,
      hasOpencodeZen: false,
      hasZaiCodingPlan: true,
+      hasKimiForCoding: false,
    }

    // #when generating config
@@ -350,6 +355,7 @@ describe("generateOmoConfig - model fallback system", () => {
      hasCopilot: false,
      hasOpencodeZen: false,
      hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
    }

    // #when generating config
@@ -373,6 +379,7 @@ describe("generateOmoConfig - model fallback system", () => {
      hasCopilot: false,
      hasOpencodeZen: false,
      hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
    }

    // #when generating config
@@ -392,6 +399,7 @@ describe("generateOmoConfig - model fallback system", () => {
      hasCopilot: false,
      hasOpencodeZen: false,
      hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
    }

    // #when generating config
--- a/src/cli/config-manager.ts
+++ b/src/cli/config-manager.ts
@@ -598,27 +598,28 @@ export function addProviderConfig(config: InstallConfig): ConfigMergeResult {
  }
 }

-function detectProvidersFromOmoConfig(): { hasOpenAI: boolean; hasOpencodeZen: boolean; hasZaiCodingPlan: boolean } {
+function detectProvidersFromOmoConfig(): { hasOpenAI: boolean; hasOpencodeZen: boolean; hasZaiCodingPlan: boolean; hasKimiForCoding: boolean } {
  const omoConfigPath = getOmoConfig()
  if (!existsSync(omoConfigPath)) {
-    return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false }
+    return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
  }

  try {
    const content = readFileSync(omoConfigPath, "utf-8")
    const omoConfig = parseJsonc<Record<string, unknown>>(content)
    if (!omoConfig || typeof omoConfig !== "object") {
-      return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false }
+      return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
    }

    const configStr = JSON.stringify(omoConfig)
    const hasOpenAI = configStr.includes('"openai/')
    const hasOpencodeZen = configStr.includes('"opencode/')
    const hasZaiCodingPlan = configStr.includes('"zai-coding-plan/')
+    const hasKimiForCoding = configStr.includes('"kimi-for-coding/')

-    return { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan }
+    return { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan, hasKimiForCoding }
  } catch {
-    return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false }
+    return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
  }
 }

@@ -632,6 +633,7 @@ export function detectCurrentConfig(): DetectedConfig {
    hasCopilot: false,
    hasOpencodeZen: true,
    hasZaiCodingPlan: false,
+    hasKimiForCoding: false,
  }

  const { format, path } = detectConfigFormat()
@@ -655,10 +657,11 @@ export function detectCurrentConfig(): DetectedConfig {
  // Gemini auth plugin detection still works via plugin presence
  result.hasGemini = plugins.some((p) => p.startsWith("opencode-antigravity-auth"))

-  const { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan } = detectProvidersFromOmoConfig()
+  const { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan, hasKimiForCoding } = detectProvidersFromOmoConfig()
  result.hasOpenAI = hasOpenAI
  result.hasOpencodeZen = hasOpencodeZen
  result.hasZaiCodingPlan = hasZaiCodingPlan
+  result.hasKimiForCoding = hasKimiForCoding

  return result
 }
--- a/src/cli/index.ts
+++ b/src/cli/index.ts
@@ -30,6 +30,7 @@ program
  .option("--copilot <value>", "GitHub Copilot subscription: no, yes")
  .option("--opencode-zen <value>", "OpenCode Zen access: no, yes (default: no)")
  .option("--zai-coding-plan <value>", "Z.ai Coding Plan subscription: no, yes (default: no)")
+  .option("--kimi-for-coding <value>", "Kimi For Coding subscription: no, yes (default: no)")
  .option("--skip-auth", "Skip authentication setup hints")
  .addHelpText("after", `
 Examples:
@@ -37,13 +38,14 @@ Examples:
  $ bunx oh-my-opencode install --no-tui --claude=max20 --openai=yes --gemini=yes --copilot=no
  $ bunx oh-my-opencode install --no-tui --claude=no --gemini=no --copilot=yes --opencode-zen=yes

-Model Providers (Priority: Native > Copilot > OpenCode Zen > Z.ai):
+Model Providers (Priority: Native > Copilot > OpenCode Zen > Z.ai > Kimi):
  Claude        Native anthropic/ models (Opus, Sonnet, Haiku)
  OpenAI        Native openai/ models (GPT-5.2 for Oracle)
  Gemini        Native google/ models (Gemini 3 Pro, Flash)
  Copilot       github-copilot/ models (fallback)
  OpenCode Zen  opencode/ models (opencode/claude-opus-4-5, etc.)
  Z.ai          zai-coding-plan/glm-4.7 (Librarian priority)
+  Kimi          kimi-for-coding/k2p5 (Sisyphus/Prometheus fallback)
 `)
  .action(async (options) => {
    const args: InstallArgs = {
@@ -54,6 +56,7 @@ Model Providers (Priority: Native > Copilot > OpenCode Zen > Z.ai):
      copilot: options.copilot,
      opencodeZen: options.opencodeZen,
      zaiCodingPlan: options.zaiCodingPlan,
+      kimiForCoding: options.kimiForCoding,
      skipAuth: options.skipAuth ?? false,
    }
    const exitCode = await install(args)
--- a/src/cli/install.ts
+++ b/src/cli/install.ts
@@ -45,6 +45,7 @@ function formatConfigSummary(config: InstallConfig): string {
  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/Multimodal"))
+  lines.push(formatProvider("Kimi For Coding", config.hasKimiForCoding, "Sisyphus/Prometheus fallback"))

  lines.push("")
  lines.push(color.dim("─".repeat(40)))
@@ -141,6 +142,10 @@ function validateNonTuiArgs(args: InstallArgs): { valid: boolean; errors: string
    errors.push(`Invalid --zai-coding-plan value: ${args.zaiCodingPlan} (expected: no, yes)`)
  }

+  if (args.kimiForCoding !== undefined && !["no", "yes"].includes(args.kimiForCoding)) {
+    errors.push(`Invalid --kimi-for-coding value: ${args.kimiForCoding} (expected: no, yes)`)
+  }
+
  return { valid: errors.length === 0, errors }
 }

@@ -153,10 +158,11 @@ function argsToConfig(args: InstallArgs): InstallConfig {
    hasCopilot: args.copilot === "yes",
    hasOpencodeZen: args.opencodeZen === "yes",
    hasZaiCodingPlan: args.zaiCodingPlan === "yes",
+    hasKimiForCoding: args.kimiForCoding === "yes",
  }
 }

-function detectedToInitialValues(detected: DetectedConfig): { claude: ClaudeSubscription; openai: BooleanArg; gemini: BooleanArg; copilot: BooleanArg; opencodeZen: BooleanArg; zaiCodingPlan: BooleanArg } {
+function detectedToInitialValues(detected: DetectedConfig): { claude: ClaudeSubscription; openai: BooleanArg; gemini: BooleanArg; copilot: BooleanArg; opencodeZen: BooleanArg; zaiCodingPlan: BooleanArg; kimiForCoding: BooleanArg } {
  let claude: ClaudeSubscription = "no"
  if (detected.hasClaude) {
    claude = detected.isMax20 ? "max20" : "yes"
@@ -169,6 +175,7 @@ function detectedToInitialValues(detected: DetectedConfig): { claude: ClaudeSubs
    copilot: detected.hasCopilot ? "yes" : "no",
    opencodeZen: detected.hasOpencodeZen ? "yes" : "no",
    zaiCodingPlan: detected.hasZaiCodingPlan ? "yes" : "no",
+    kimiForCoding: detected.hasKimiForCoding ? "yes" : "no",
  }
 }

@@ -178,7 +185,7 @@ 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/big-pickle as fallback" },
+      { value: "no" as const, label: "No", hint: "Will use opencode/glm-4.7-free 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" },
    ],
@@ -260,6 +267,20 @@ async function runTuiMode(detected: DetectedConfig): Promise<InstallConfig | nul
    return null
  }

+  const kimiForCoding = await p.select({
+    message: "Do you have a Kimi For Coding subscription?",
+    options: [
+      { value: "no" as const, label: "No", hint: "Will use other configured providers" },
+      { value: "yes" as const, label: "Yes", hint: "Kimi K2.5 for Sisyphus/Prometheus fallback" },
+    ],
+    initialValue: initial.kimiForCoding,
+  })
+
+  if (p.isCancel(kimiForCoding)) {
+    p.cancel("Installation cancelled.")
+    return null
+  }
+
  return {
    hasClaude: claude !== "no",
    isMax20: claude === "max20",
@@ -268,6 +289,7 @@ async function runTuiMode(detected: DetectedConfig): Promise<InstallConfig | nul
    hasCopilot: copilot === "yes",
    hasOpencodeZen: opencodeZen === "yes",
    hasZaiCodingPlan: zaiCodingPlan === "yes",
+    hasKimiForCoding: kimiForCoding === "yes",
  }
 }

@@ -363,7 +385,7 @@ 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/big-pickle as fallback.")
+    printWarning("No model providers configured. Using opencode/glm-4.7-free as fallback.")
  }

  console.log(`${SYMBOLS.star} ${color.bold(color.green(isUpdate ? "Configuration updated!" : "Installation complete!"))}`)
@@ -378,7 +400,7 @@ async function runNonTuiInstall(args: InstallArgs): Promise<number> {
  )

  console.log(`${SYMBOLS.star} ${color.yellow("If you found this helpful, consider starring the repo!")}`)
-  console.log(`  ${color.dim("gh repo star code-yeongyu/oh-my-opencode")}`)
+  console.log(`  ${color.dim("gh api --silent --method PUT /user/starred/code-yeongyu/oh-my-opencode >/dev/null 2>&1 || true")}`)
  console.log()
  console.log(color.dim("oMoMoMoMo... Enjoy!"))
  console.log()
@@ -480,7 +502,7 @@ 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/big-pickle as fallback.")
+    p.log.warn("No model providers configured. Using opencode/glm-4.7-free as fallback.")
  }

  p.note(formatConfigSummary(config), isUpdate ? "Updated Configuration" : "Installation Complete")
@@ -496,7 +518,7 @@ export async function install(args: InstallArgs): Promise<number> {
  )

  p.log.message(`${color.yellow("★")} If you found this helpful, consider starring the repo!`)
-  p.log.message(`  ${color.dim("gh repo star code-yeongyu/oh-my-opencode")}`)
+  p.log.message(`  ${color.dim("gh api --silent --method PUT /user/starred/code-yeongyu/oh-my-opencode >/dev/null 2>&1 || true")}`)

  p.outro(color.green("oMoMoMoMo... Enjoy!"))

--- a/src/cli/model-fallback.test.ts
+++ b/src/cli/model-fallback.test.ts
@@ -12,6 +12,7 @@ function createConfig(overrides: Partial<InstallConfig> = {}): InstallConfig {
    hasCopilot: false,
    hasOpencodeZen: false,
    hasZaiCodingPlan: false,
+    hasKimiForCoding: false,
    ...overrides,
  }
 }
--- a/src/cli/model-fallback.ts
+++ b/src/cli/model-fallback.ts
@@ -14,6 +14,7 @@ interface ProviderAvailability {
  opencodeZen: boolean
  copilot: boolean
  zai: boolean
+  kimiForCoding: boolean
  isMaxPlan: boolean
 }

@@ -36,7 +37,7 @@ export interface GeneratedOmoConfig {

 const ZAI_MODEL = "zai-coding-plan/glm-4.7"

-const ULTIMATE_FALLBACK = "opencode/big-pickle"
+const ULTIMATE_FALLBACK = "opencode/glm-4.7-free"
 const SCHEMA_URL = "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json"

 function toProviderAvailability(config: InstallConfig): ProviderAvailability {
@@ -49,6 +50,7 @@ function toProviderAvailability(config: InstallConfig): ProviderAvailability {
    opencodeZen: config.hasOpencodeZen,
    copilot: config.hasCopilot,
    zai: config.hasZaiCodingPlan,
+    kimiForCoding: config.hasKimiForCoding,
    isMaxPlan: config.isMax20,
  }
 }
@@ -61,6 +63,7 @@ function isProviderAvailable(provider: string, avail: ProviderAvailability): boo
    "github-copilot": avail.copilot,
    opencode: avail.opencodeZen,
    "zai-coding-plan": avail.zai,
+    "kimi-for-coding": avail.kimiForCoding,
  }
  return mapping[provider] ?? false
 }
@@ -102,6 +105,8 @@ function getSisyphusFallbackChain(isMaxPlan: boolean): FallbackEntry[] {
  // For non-max plan, use sonnet instead of opus
  return [
    { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" },
+    { providers: ["kimi-for-coding"], model: "k2p5" },
+    { providers: ["opencode"], model: "kimi-k2.5-free" },
    { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
    { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
  ]
@@ -115,7 +120,8 @@ export function generateModelConfig(config: InstallConfig): GeneratedOmoConfig {
    avail.native.gemini ||
    avail.opencodeZen ||
    avail.copilot ||
-    avail.zai
+    avail.zai ||
+    avail.kimiForCoding

  if (!hasAnyProvider) {
    return {
--- a/src/cli/run/events.test.ts
+++ b/src/cli/run/events.test.ts
@@ -82,6 +82,7 @@ describe("createEventState", () => {
    expect(state.lastOutput).toBe("")
    expect(state.lastPartText).toBe("")
    expect(state.currentTool).toBe(null)
+    expect(state.hasReceivedMeaningfulWork).toBe(false)
  })
 })

@@ -126,6 +127,119 @@ describe("event handling", () => {
    expect(state.mainSessionIdle).toBe(false)
  })

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

    const payload: EventPayload = {
--- a/src/cli/run/events.ts
+++ b/src/cli/run/events.ts
@@ -63,6 +63,8 @@ export interface EventState {
  lastOutput: string
  lastPartText: string
  currentTool: string | null
+  /** Set to true when the main session has produced meaningful work (text, tool call, or tool result) */
+  hasReceivedMeaningfulWork: boolean
 }

 export function createEventState(): EventState {
@@ -73,6 +75,7 @@ export function createEventState(): EventState {
    lastOutput: "",
    lastPartText: "",
    currentTool: null,
+    hasReceivedMeaningfulWork: false,
  }
 }

@@ -113,7 +116,9 @@ function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
  const isMainSession = sessionID === ctx.sessionID
  const sessionTag = isMainSession
    ? pc.green("[MAIN]")
-    : pc.yellow(`[${String(sessionID).slice(0, 8)}]`)
+    : sessionID
+      ? pc.yellow(`[${String(sessionID).slice(0, 8)}]`)
+      : pc.dim("[system]")

  switch (payload.type) {
    case "session.idle":
@@ -124,8 +129,6 @@ function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
    }

    case "message.part.updated": {
-      // Skip verbose logging for partial message updates
-      // Only log tool invocation state changes, not text streaming
      const partProps = props as MessagePartUpdatedProps | undefined
      const part = partProps?.part
      if (part?.type === "tool-invocation") {
@@ -133,6 +136,11 @@ function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
        console.error(
          pc.dim(`${sessionTag} message.part (tool): ${toolPart.toolName} [${toolPart.state}]`)
        )
+      } else if (part?.type === "text" && part.text) {
+        const preview = part.text.slice(0, 80).replace(/\n/g, "\\n")
+        console.error(
+          pc.dim(`${sessionTag} message.part (text): "${preview}${part.text.length > 80 ? "..." : ""}"`)
+        )
      }
      break
    }
@@ -140,11 +148,10 @@ function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
    case "message.updated": {
      const msgProps = props as MessageUpdatedProps | undefined
      const role = msgProps?.info?.role ?? "unknown"
-      const content = msgProps?.content ?? ""
-      const preview = content.slice(0, 100).replace(/\n/g, "\\n")
-      console.error(
-        pc.dim(`${sessionTag} message.updated (${role}): "${preview}${content.length > 100 ? "..." : ""}"`)
-      )
+      const model = msgProps?.info?.modelID
+      const agent = msgProps?.info?.agent
+      const details = [role, agent, model].filter(Boolean).join(", ")
+      console.error(pc.dim(`${sessionTag} message.updated (${details})`))
      break
    }

@@ -241,6 +248,7 @@ function handleMessagePartUpdated(
    const newText = part.text.slice(state.lastPartText.length)
    if (newText) {
      process.stdout.write(newText)
+      state.hasReceivedMeaningfulWork = true
    }
    state.lastPartText = part.text
  }
@@ -257,16 +265,7 @@ function handleMessageUpdated(
  if (props?.info?.sessionID !== ctx.sessionID) return
  if (props?.info?.role !== "assistant") return

-  const content = props.content
-  if (!content || content === state.lastOutput) return
-
-  if (state.lastPartText.length === 0) {
-    const newContent = content.slice(state.lastOutput.length)
-    if (newContent) {
-      process.stdout.write(newContent)
-    }
-  }
-  state.lastOutput = content
+  state.hasReceivedMeaningfulWork = true
 }

 function handleToolExecute(
@@ -296,6 +295,7 @@ function handleToolExecute(
    }
  }

+  state.hasReceivedMeaningfulWork = true
  process.stdout.write(`\n${pc.cyan(">")} ${pc.bold(toolName)}${inputPreview}\n`)
 }

--- a/src/cli/run/runner.ts
+++ b/src/cli/run/runner.ts
@@ -143,6 +143,14 @@ export async function run(options: RunOptions): Promise<number> {
          process.exit(1)
        }

+        // Guard against premature completion: don't check completion until the
+        // session has produced meaningful work (text output, tool call, or tool result).
+        // Without this, a session that goes busy->idle before the LLM responds
+        // would exit immediately because 0 todos + 0 children = "complete".
+        if (!eventState.hasReceivedMeaningfulWork) {
+          continue
+        }
+
        const shouldExit = await checkCompletionConditions(ctx)
        if (shouldExit) {
          console.log(pc.green("\n\nAll tasks completed."))
--- a/src/cli/run/types.ts
+++ b/src/cli/run/types.ts
@@ -44,8 +44,13 @@ export interface SessionStatusProps {
 }

 export interface MessageUpdatedProps {
-  info?: { sessionID?: string; role?: string }
-  content?: string
+  info?: {
+    sessionID?: string
+    role?: string
+    modelID?: string
+    providerID?: string
+    agent?: string
+  }
 }

 export interface MessagePartUpdatedProps {
--- a/src/cli/types.ts
+++ b/src/cli/types.ts
@@ -9,6 +9,7 @@ export interface InstallArgs {
  copilot?: BooleanArg
  opencodeZen?: BooleanArg
  zaiCodingPlan?: BooleanArg
+  kimiForCoding?: BooleanArg
  skipAuth?: boolean
 }

@@ -20,6 +21,7 @@ export interface InstallConfig {
  hasCopilot: boolean
  hasOpencodeZen: boolean
  hasZaiCodingPlan: boolean
+  hasKimiForCoding: boolean
 }

 export interface ConfigMergeResult {
@@ -37,4 +39,5 @@ export interface DetectedConfig {
  hasCopilot: boolean
  hasOpencodeZen: boolean
  hasZaiCodingPlan: boolean
+  hasKimiForCoding: boolean
 }
--- a/src/config/schema.ts
+++ b/src/config/schema.ts
@@ -187,6 +187,7 @@ export const CategoryConfigSchema = z.object({
 export const BuiltinCategoryNameSchema = z.enum([
  "visual-engineering",
  "ultrabrain",
+  "deep",
  "artistry",
  "quick",
  "unspecified-low",
--- a/src/features/background-agent/concurrency.test.ts
+++ b/src/features/background-agent/concurrency.test.ts
@@ -176,8 +176,8 @@ describe("ConcurrencyManager.acquire/release", () => {
    await manager.acquire("model-a")
    await manager.acquire("model-a")

-    // #then - both resolved without waiting
-    expect(true).toBe(true)
+    // #then - both resolved without waiting, count should be 2
+    expect(manager.getCount("model-a")).toBe(2)
  })

  test("should allow acquires up to default limit of 5", async () => {
@@ -190,8 +190,8 @@ describe("ConcurrencyManager.acquire/release", () => {
    await manager.acquire("model-a")
    await manager.acquire("model-a")

-    // #then - all 5 resolved
-    expect(true).toBe(true)
+    // #then - all 5 resolved, count should be 5
+    expect(manager.getCount("model-a")).toBe(5)
  })

  test("should queue when limit reached", async () => {
@@ -276,8 +276,8 @@ describe("ConcurrencyManager.acquire/release", () => {
    manager.release("model-a")
    await manager.acquire("model-a")

-    // #then
-    expect(true).toBe(true)
+    // #then - count should be 1 after re-acquiring
+    expect(manager.getCount("model-a")).toBe(1)
  })

  test("should handle release when no acquire", () => {
@@ -288,21 +288,21 @@ describe("ConcurrencyManager.acquire/release", () => {
    // #when - release without acquire
    manager.release("model-a")

-    // #then - should not throw
-    expect(true).toBe(true)
+    // #then - count should be 0 (no negative count)
+    expect(manager.getCount("model-a")).toBe(0)
  })

  test("should handle release when no prior acquire", () => {
    // #given - default config

-    // #when - release without acquire
-    manager.release("model-a")
+     // #when - release without acquire
+     manager.release("model-a")

-    // #then - should not throw
-    expect(true).toBe(true)
-  })
+     // #then - count should be 0 (no negative count)
+     expect(manager.getCount("model-a")).toBe(0)
+   })

-  test("should handle multiple acquires and releases correctly", async () => {
+   test("should handle multiple acquires and releases correctly", async () => {
    // #given
    const config: BackgroundTaskConfig = { defaultConcurrency: 3 }
    manager = new ConcurrencyManager(config)
@@ -317,11 +317,11 @@ describe("ConcurrencyManager.acquire/release", () => {
    manager.release("model-a")
    manager.release("model-a")

-    // Should be able to acquire again
-    await manager.acquire("model-a")
+     // Should be able to acquire again
+     await manager.acquire("model-a")

-    // #then
-    expect(true).toBe(true)
+     // #then - count should be 1 after re-acquiring
+     expect(manager.getCount("model-a")).toBe(1)
  })

  test("should use model-specific limit for acquire", async () => {
--- a/src/features/background-agent/manager.ts
+++ b/src/features/background-agent/manager.ts
@@ -5,7 +5,7 @@ import type {
  LaunchInput,
  ResumeInput,
 } from "./types"
-import { log, getAgentToolRestrictions } from "../../shared"
+import { log, getAgentToolRestrictions, promptWithModelSuggestionRetry } from "../../shared"
 import { ConcurrencyManager } from "./concurrency"
 import type { BackgroundTaskConfig, TmuxConfig } from "../../config/schema"
 import { isInsideTmux } from "../../shared/tmux"
@@ -307,7 +307,7 @@ export class BackgroundManager {
      : undefined
    const launchVariant = input.model?.variant

-    this.client.session.prompt({
+    promptWithModelSuggestionRetry(this.client, {
      path: { id: sessionID },
      body: {
        agent: input.agent,
--- a/src/features/builtin-commands/commands.ts
+++ b/src/features/builtin-commands/commands.ts
@@ -55,6 +55,7 @@ ${REFACTOR_TEMPLATE}
  },
  "start-work": {
    description: "(builtin) Start Sisyphus work session from Prometheus plan",
+    agent: "atlas",
    template: `<command-instruction>
 ${START_WORK_TEMPLATE}
 </command-instruction>
--- a/src/features/hook-message-injector/injector.ts
+++ b/src/features/hook-message-injector/injector.ts
@@ -2,6 +2,7 @@ import { existsSync, mkdirSync, readFileSync, readdirSync, writeFileSync } from
 import { join } from "node:path"
 import { MESSAGE_STORAGE, PART_STORAGE } from "./constants"
 import type { MessageMeta, OriginalMessageContext, TextPart, ToolPermission } from "./types"
+import { log } from "../../shared/logger"

 export interface StoredMessage {
  agent?: string
@@ -117,7 +118,7 @@ export function injectHookMessage(
 ): boolean {
  // Validate hook content to prevent empty message injection
  if (!hookContent || hookContent.trim().length === 0) {
-    console.warn("[hook-message-injector] Attempted to inject empty hook content, skipping injection", {
+    log("[hook-message-injector] Attempted to inject empty hook content, skipping injection", {
      sessionID,
      hasAgent: !!originalMessage.agent,
      hasModel: !!(originalMessage.model?.providerID && originalMessage.model?.modelID)
--- a/src/features/mcp-oauth/callback-server.test.ts
+++ b/src/features/mcp-oauth/callback-server.test.ts
@@ -1,6 +1,8 @@
 import { afterEach, describe, expect, it } from "bun:test"
 import { findAvailablePort, startCallbackServer, type CallbackServer } from "./callback-server"

+const nativeFetch = Bun.fetch.bind(Bun)
+
 describe("findAvailablePort", () => {
  it("returns the start port when it is available", async () => {
    //#given
@@ -34,9 +36,11 @@ describe("findAvailablePort", () => {
 describe("startCallbackServer", () => {
  let server: CallbackServer | null = null

-  afterEach(() => {
+  afterEach(async () => {
    server?.close()
    server = null
+    // Allow time for port to be released before next test
+    await Bun.sleep(10)
  })

  it("starts server and returns port", async () => {
@@ -57,9 +61,12 @@ describe("startCallbackServer", () => {
    const callbackUrl = `http://127.0.0.1:${server.port}/oauth/callback?code=test-code&state=test-state`

    //#when
-    const fetchPromise = fetch(callbackUrl)
-    const result = await server.waitForCallback()
-    const response = await fetchPromise
+    // Use Promise.all to ensure fetch and waitForCallback run concurrently
+    // This prevents race condition where waitForCallback blocks before fetch starts
+    const [result, response] = await Promise.all([
+      server.waitForCallback(),
+      nativeFetch(callbackUrl)
+    ])

    //#then
    expect(result).toEqual({ code: "test-code", state: "test-state" })
@@ -73,7 +80,7 @@ describe("startCallbackServer", () => {
    server = await startCallbackServer()

    //#when
-    const response = await fetch(`http://127.0.0.1:${server.port}/other`)
+    const response = await nativeFetch(`http://127.0.0.1:${server.port}/other`)

    //#then
    expect(response.status).toBe(404)
@@ -85,7 +92,7 @@ describe("startCallbackServer", () => {
    const callbackRejection = server.waitForCallback().catch((e: Error) => e)

    //#when
-    const response = await fetch(`http://127.0.0.1:${server.port}/oauth/callback?state=s`)
+    const response = await nativeFetch(`http://127.0.0.1:${server.port}/oauth/callback?state=s`)

    //#then
    expect(response.status).toBe(400)
@@ -100,7 +107,7 @@ describe("startCallbackServer", () => {
    const callbackRejection = server.waitForCallback().catch((e: Error) => e)

    //#when
-    const response = await fetch(`http://127.0.0.1:${server.port}/oauth/callback?code=c`)
+    const response = await nativeFetch(`http://127.0.0.1:${server.port}/oauth/callback?code=c`)

    //#then
    expect(response.status).toBe(400)
@@ -120,7 +127,7 @@ describe("startCallbackServer", () => {

    //#then
    try {
-      await fetch(`http://127.0.0.1:${port}/oauth/callback?code=c&state=s`)
+      await nativeFetch(`http://127.0.0.1:${port}/oauth/callback?code=c&state=s`)
      expect(true).toBe(false)
    } catch (error) {
      expect(error).toBeDefined()
--- a/src/features/tmux-subagent/manager.test.ts
+++ b/src/features/tmux-subagent/manager.test.ts
@@ -2,6 +2,7 @@ import { describe, test, expect, mock, beforeEach } from 'bun:test'
 import type { TmuxConfig } from '../../config/schema'
 import type { WindowState, PaneAction } from './types'
 import type { ActionResult, ExecuteContext } from './action-executor'
+import type { TmuxUtilDeps } from './manager'

 type ExecuteActionsResult = {
  success: boolean
@@ -33,6 +34,11 @@ const mockExecuteAction = mock<(
 const mockIsInsideTmux = mock<() => boolean>(() => true)
 const mockGetCurrentPaneId = mock<() => string | undefined>(() => '%0')

+const mockTmuxDeps: TmuxUtilDeps = {
+  isInsideTmux: mockIsInsideTmux,
+  getCurrentPaneId: mockGetCurrentPaneId,
+}
+
 mock.module('./pane-state-querier', () => ({
  queryWindowState: mockQueryWindowState,
  paneExists: mockPaneExists,
@@ -51,15 +57,19 @@ mock.module('./action-executor', () => ({
  executeAction: mockExecuteAction,
 }))

-mock.module('../../shared/tmux', () => ({
-  isInsideTmux: mockIsInsideTmux,
-  getCurrentPaneId: mockGetCurrentPaneId,
-  POLL_INTERVAL_BACKGROUND_MS: 2000,
-  SESSION_TIMEOUT_MS: 600000,
-  SESSION_MISSING_GRACE_MS: 6000,
-  SESSION_READY_POLL_INTERVAL_MS: 100,
-  SESSION_READY_TIMEOUT_MS: 500,
-}))
+mock.module('../../shared/tmux', () => {
+  const { isInsideTmux, getCurrentPaneId } = require('../../shared/tmux/tmux-utils')
+  const { POLL_INTERVAL_BACKGROUND_MS, SESSION_TIMEOUT_MS, SESSION_MISSING_GRACE_MS } = require('../../shared/tmux/constants')
+  return {
+    isInsideTmux,
+    getCurrentPaneId,
+    POLL_INTERVAL_BACKGROUND_MS,
+    SESSION_TIMEOUT_MS,
+    SESSION_MISSING_GRACE_MS,
+    SESSION_READY_POLL_INTERVAL_MS: 100,
+    SESSION_READY_TIMEOUT_MS: 500,
+  }
+})

 const trackedSessions = new Set<string>()

@@ -148,7 +158,7 @@ describe('TmuxSessionManager', () => {
      }

      //#when
-      const manager = new TmuxSessionManager(ctx, config)
+      const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)

      //#then
      expect(manager).toBeDefined()
@@ -168,7 +178,7 @@ describe('TmuxSessionManager', () => {
      }

      //#when
-      const manager = new TmuxSessionManager(ctx, config)
+      const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)

      //#then
      expect(manager).toBeDefined()
@@ -188,7 +198,7 @@ describe('TmuxSessionManager', () => {
      }

      //#when
-      const manager = new TmuxSessionManager(ctx, config)
+      const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)

      //#then
      expect(manager).toBeDefined()
@@ -210,7 +220,7 @@ describe('TmuxSessionManager', () => {
        main_pane_min_width: 80,
        agent_pane_min_width: 40,
      }
-      const manager = new TmuxSessionManager(ctx, config)
+      const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
      const event = createSessionCreatedEvent(
        'ses_child',
        'ses_parent',
@@ -271,7 +281,7 @@ describe('TmuxSessionManager', () => {
        main_pane_min_width: 80,
        agent_pane_min_width: 40,
      }
-      const manager = new TmuxSessionManager(ctx, config)
+      const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)

      //#when - first agent
      await manager.onSessionCreated(
@@ -305,7 +315,7 @@ describe('TmuxSessionManager', () => {
        main_pane_min_width: 80,
        agent_pane_min_width: 40,
      }
-      const manager = new TmuxSessionManager(ctx, config)
+      const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
      const event = createSessionCreatedEvent('ses_root', undefined, 'Root Session')

      //#when
@@ -327,7 +337,7 @@ describe('TmuxSessionManager', () => {
        main_pane_min_width: 80,
        agent_pane_min_width: 40,
      }
-      const manager = new TmuxSessionManager(ctx, config)
+      const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
      const event = createSessionCreatedEvent(
        'ses_child',
        'ses_parent',
@@ -353,7 +363,7 @@ describe('TmuxSessionManager', () => {
        main_pane_min_width: 80,
        agent_pane_min_width: 40,
      }
-      const manager = new TmuxSessionManager(ctx, config)
+      const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
      const event = {
        type: 'session.deleted',
        properties: {
@@ -398,7 +408,7 @@ describe('TmuxSessionManager', () => {
        main_pane_min_width: 120,
        agent_pane_min_width: 40,
      }
-      const manager = new TmuxSessionManager(ctx, config)
+      const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)

      //#when
      await manager.onSessionCreated(
@@ -450,7 +460,7 @@ describe('TmuxSessionManager', () => {
        main_pane_min_width: 80,
        agent_pane_min_width: 40,
      }
-      const manager = new TmuxSessionManager(ctx, config)
+      const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)

      await manager.onSessionCreated(
        createSessionCreatedEvent(
@@ -487,7 +497,7 @@ describe('TmuxSessionManager', () => {
        main_pane_min_width: 80,
        agent_pane_min_width: 40,
      }
-      const manager = new TmuxSessionManager(ctx, config)
+      const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)

      //#when
      await manager.onSessionDeleted({ sessionID: 'ses_unknown' })
@@ -521,7 +531,7 @@ describe('TmuxSessionManager', () => {
        main_pane_min_width: 80,
        agent_pane_min_width: 40,
      }
-      const manager = new TmuxSessionManager(ctx, config)
+      const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)

      await manager.onSessionCreated(
        createSessionCreatedEvent('ses_1', 'ses_parent', 'Task 1')
--- a/src/features/tmux-subagent/manager.ts
+++ b/src/features/tmux-subagent/manager.ts
@@ -2,8 +2,8 @@ import type { PluginInput } from "@opencode-ai/plugin"
 import type { TmuxConfig } from "../../config/schema"
 import type { TrackedSession, CapacityConfig } from "./types"
 import {
-  isInsideTmux,
-  getCurrentPaneId,
+  isInsideTmux as defaultIsInsideTmux,
+  getCurrentPaneId as defaultGetCurrentPaneId,
  POLL_INTERVAL_BACKGROUND_MS,
  SESSION_MISSING_GRACE_MS,
  SESSION_READY_POLL_INTERVAL_MS,
@@ -21,6 +21,16 @@ interface SessionCreatedEvent {
  properties?: { info?: { id?: string; parentID?: string; title?: string } }
 }

+export interface TmuxUtilDeps {
+  isInsideTmux: () => boolean
+  getCurrentPaneId: () => string | undefined
+}
+
+const defaultTmuxDeps: TmuxUtilDeps = {
+  isInsideTmux: defaultIsInsideTmux,
+  getCurrentPaneId: defaultGetCurrentPaneId,
+}
+
 const SESSION_TIMEOUT_MS = 10 * 60 * 1000

 /**
@@ -43,13 +53,15 @@ export class TmuxSessionManager {
  private sessions = new Map<string, TrackedSession>()
  private pendingSessions = new Set<string>()
  private pollInterval?: ReturnType<typeof setInterval>
+  private deps: TmuxUtilDeps

-  constructor(ctx: PluginInput, tmuxConfig: TmuxConfig) {
+  constructor(ctx: PluginInput, tmuxConfig: TmuxConfig, deps: TmuxUtilDeps = defaultTmuxDeps) {
    this.client = ctx.client
    this.tmuxConfig = tmuxConfig
+    this.deps = deps
    const defaultPort = process.env.OPENCODE_PORT ?? "4096"
    this.serverUrl = ctx.serverUrl?.toString() ?? `http://localhost:${defaultPort}`
-    this.sourcePaneId = getCurrentPaneId()
+    this.sourcePaneId = deps.getCurrentPaneId()

    log("[tmux-session-manager] initialized", {
      configEnabled: this.tmuxConfig.enabled,
@@ -60,7 +72,7 @@ export class TmuxSessionManager {
  }

  private isEnabled(): boolean {
-    return this.tmuxConfig.enabled && isInsideTmux()
+    return this.tmuxConfig.enabled && this.deps.isInsideTmux()
  }

  private getCapacityConfig(): CapacityConfig {
@@ -113,7 +125,7 @@ export class TmuxSessionManager {
    log("[tmux-session-manager] onSessionCreated called", {
      enabled,
      tmuxConfigEnabled: this.tmuxConfig.enabled,
-      isInsideTmux: isInsideTmux(),
+      isInsideTmux: this.deps.isInsideTmux(),
      eventType: event.type,
      infoId: event.properties?.info?.id,
      infoParentID: event.properties?.info?.parentID,
--- a/src/hooks/anthropic-context-window-limit-recovery/executor.test.ts
+++ b/src/hooks/anthropic-context-window-limit-recovery/executor.test.ts
@@ -1,11 +1,83 @@
-import { describe, test, expect, mock, beforeEach, spyOn } from "bun:test"
+import { afterEach, beforeEach, describe, expect, mock, spyOn, test } from "bun:test"
 import { executeCompact } from "./executor"
 import type { AutoCompactState } from "./types"
 import * as storage from "./storage"

+type TimerCallback = (...args: any[]) => void
+
+interface FakeTimeouts {
+  advanceBy: (ms: number) => Promise<void>
+  restore: () => void
+}
+
+function createFakeTimeouts(): FakeTimeouts {
+  let now = 0
+  let nextId = 1
+  const timers = new Map<number, { id: number; time: number; callback: TimerCallback; args: any[] }>()
+  const cleared = new Set<number>()
+
+  const original = {
+    setTimeout: globalThis.setTimeout,
+    clearTimeout: globalThis.clearTimeout,
+  }
+
+  const normalizeDelay = (delay?: number) => {
+    if (typeof delay !== "number" || !Number.isFinite(delay)) return 0
+    return delay < 0 ? 0 : delay
+  }
+
+  globalThis.setTimeout = ((callback: TimerCallback, delay?: number, ...args: any[]) => {
+    const id = nextId++
+    timers.set(id, {
+      id,
+      time: now + normalizeDelay(delay),
+      callback,
+      args,
+    })
+    return id as unknown as ReturnType<typeof setTimeout>
+  }) as typeof setTimeout
+
+  globalThis.clearTimeout = ((id?: number) => {
+    if (typeof id !== "number") return
+    cleared.add(id)
+    timers.delete(id)
+  }) as typeof clearTimeout
+
+  const advanceBy = async (ms: number) => {
+    const target = now + Math.max(0, ms)
+    while (true) {
+      let next: { id: number; time: number; callback: TimerCallback; args: any[] } | undefined
+      for (const timer of timers.values()) {
+        if (timer.time <= target && (!next || timer.time < next.time)) {
+          next = timer
+        }
+      }
+      if (!next) break
+
+      now = next.time
+      timers.delete(next.id)
+      if (!cleared.has(next.id)) {
+        next.callback(...next.args)
+      }
+      cleared.delete(next.id)
+      await Promise.resolve()
+    }
+    now = target
+    await Promise.resolve()
+  }
+
+  const restore = () => {
+    globalThis.setTimeout = original.setTimeout
+    globalThis.clearTimeout = original.clearTimeout
+  }
+
+  return { advanceBy, restore }
+}
+
 describe("executeCompact lock management", () => {
  let autoCompactState: AutoCompactState
  let mockClient: any
+  let fakeTimeouts: FakeTimeouts
  const sessionID = "test-session-123"
  const directory = "/test/dir"
  const msg = { providerID: "anthropic", modelID: "claude-opus-4-5" }
@@ -32,6 +104,12 @@ describe("executeCompact lock management", () => {
        showToast: mock(() => Promise.resolve()),
      },
    }
+
+    fakeTimeouts = createFakeTimeouts()
+  })
+
+  afterEach(() => {
+    fakeTimeouts.restore()
  })

  test("clears lock on successful summarize completion", async () => {
@@ -216,7 +294,7 @@ describe("executeCompact lock management", () => {
    await executeCompact(sessionID, msg, autoCompactState, mockClient, directory)

    // Wait for setTimeout callback
-    await new Promise((resolve) => setTimeout(resolve, 600))
+    await fakeTimeouts.advanceBy(600)

    // #then: Lock should be cleared
    // The continuation happens in setTimeout, but lock is cleared in finally before that
@@ -288,7 +366,7 @@ describe("executeCompact lock management", () => {
    await executeCompact(sessionID, msg, autoCompactState, mockClient, directory)

    // Wait for setTimeout callback
-    await new Promise((resolve) => setTimeout(resolve, 600))
+    await fakeTimeouts.advanceBy(600)

    // #then: Truncation was attempted
    expect(truncateSpy).toHaveBeenCalled()
--- a/src/hooks/comment-checker/downloader.ts
+++ b/src/hooks/comment-checker/downloader.ts
@@ -4,6 +4,7 @@ import { join } from "path"
 import { homedir, tmpdir } from "os"
 import { createRequire } from "module"
 import { extractZip } from "../../shared"
+import { log } from "../../shared/logger"

 const DEBUG = process.env.COMMENT_CHECKER_DEBUG === "1"
 const DEBUG_FILE = join(tmpdir(), "comment-checker-debug.log")
@@ -127,7 +128,7 @@ export async function downloadCommentChecker(): Promise<string | null> {
  const downloadUrl = `https://github.com/${REPO}/releases/download/v${version}/${assetName}`
  
  debugLog(`Downloading from: ${downloadUrl}`)
-  console.log(`[oh-my-opencode] Downloading comment-checker binary...`)
+  log(`[oh-my-opencode] Downloading comment-checker binary...`)
  
  try {
    // Ensure cache directory exists
@@ -166,14 +167,14 @@ export async function downloadCommentChecker(): Promise<string | null> {
    }
    
    debugLog(`Successfully downloaded binary to: ${binaryPath}`)
-    console.log(`[oh-my-opencode] comment-checker binary ready.`)
+    log(`[oh-my-opencode] comment-checker binary ready.`)
    
    return binaryPath
    
  } catch (err) {
    debugLog(`Failed to download: ${err}`)
-    console.error(`[oh-my-opencode] Failed to download comment-checker: ${err instanceof Error ? err.message : err}`)
-    console.error(`[oh-my-opencode] Comment checking disabled.`)
+    log(`[oh-my-opencode] Failed to download comment-checker: ${err instanceof Error ? err.message : err}`)
+    log(`[oh-my-opencode] Comment checking disabled.`)
    return null
  }
 }
--- a/src/hooks/keyword-detector/constants.ts
+++ b/src/hooks/keyword-detector/constants.ts
@@ -180,7 +180,9 @@ ${ULTRAWORK_PLANNER_SECTION}

 1. **THINK DEEPLY** - What is the user's TRUE intent? What problem are they REALLY trying to solve?
 2. **EXPLORE THOROUGHLY** - Fire explore/librarian agents to gather ALL relevant context
-3. **CONSULT ORACLE** - For architecture decisions, complex logic, or when you're stuck
+3. **CONSULT SPECIALISTS** - For hard/complex tasks, DO NOT struggle alone. Delegate:
+   - **Oracle**: Conventional problems - architecture, debugging, complex logic
+   - **Artistry**: Non-conventional problems - different approach needed, unusual constraints
 4. **ASK THE USER** - If ambiguity remains after exploration, ASK. Don't guess.

 **SIGNS YOU ARE NOT READY TO IMPLEMENT:**
@@ -194,7 +196,10 @@ ${ULTRAWORK_PLANNER_SECTION}
 \`\`\`
 delegate_task(agent="explore", prompt="Find [X] patterns in codebase", background=true)
 delegate_task(agent="librarian", prompt="Find docs/examples for [Y]", background=true)
-delegate_task(agent="oracle", prompt="Review my approach: [describe plan]")
+
+// Hard problem? DON'T struggle alone:
+delegate_task(agent="oracle", prompt="...")         // conventional: architecture, debugging
+delegate_task(category="artistry", prompt="...")    // non-conventional: needs different approach
 \`\`\`

 **ONLY AFTER YOU HAVE:**
@@ -229,7 +234,7 @@ delegate_task(agent="oracle", prompt="Review my approach: [describe plan]")
 **IF YOU ENCOUNTER A BLOCKER:**
 1. **DO NOT** give up
 2. **DO NOT** deliver a compromised version
-3. **DO** consult oracle for solutions
+3. **DO** consult specialists (oracle for conventional, artistry for non-conventional)
 4. **DO** ask the user for guidance
 5. **DO** explore alternative approaches

@@ -298,7 +303,8 @@ delegate_task(session_id="ses_abc123", prompt="Here's my answer to your question
 | Codebase exploration | delegate_task(subagent_type="explore", run_in_background=true) | Parallel, context-efficient |
 | Documentation lookup | delegate_task(subagent_type="librarian", run_in_background=true) | Specialized knowledge |
 | Planning | delegate_task(subagent_type="plan") | Parallel task graph + structured TODO list |
-| Architecture/Debugging | delegate_task(subagent_type="oracle") | High-IQ reasoning |
+| Hard problem (conventional) | delegate_task(subagent_type="oracle") | Architecture, debugging, complex logic |
+| Hard problem (non-conventional) | delegate_task(category="artistry", load_skills=[...]) | Different approach needed |
 | Implementation | delegate_task(category="...", load_skills=[...]) | Domain-optimized models |

 **CATEGORY + SKILL DELEGATION:**
@@ -490,8 +496,9 @@ CONTEXT GATHERING (parallel):
 - 1-2 librarian agents (if external library involved)
 - Direct tools: Grep, AST-grep, LSP for targeted searches

-IF COMPLEX (architecture, multi-system, debugging after 2+ failures):
- Consult oracle for strategic guidance
+IF COMPLEX - DO NOT STRUGGLE ALONE. Consult specialists:
+- **Oracle**: Conventional problems (architecture, debugging, complex logic)
+- **Artistry**: Non-conventional problems (different approach needed)

 SYNTHESIZE findings before proceeding.`,
  },
--- a/src/hooks/session-recovery/index.ts
+++ b/src/hooks/session-recovery/index.ts
@@ -16,6 +16,7 @@ import {
  stripThinkingParts,
 } from "./storage"
 import type { MessageData, ResumeConfig } from "./types"
+import { log } from "../../shared/logger"

 export interface SessionRecoveryOptions {
  experimental?: ExperimentalConfig
@@ -414,7 +415,7 @@ export function createSessionRecoveryHook(ctx: PluginInput, options?: SessionRec

      return success
  } catch (err) {
-    console.error("[session-recovery] Recovery failed:", err)
+    log("[session-recovery] Recovery failed:", err)
    return false
  } finally {
    processingErrors.delete(assistantMsgID)
--- a/src/hooks/todo-continuation-enforcer.test.ts
+++ b/src/hooks/todo-continuation-enforcer.test.ts
@@ -4,9 +4,123 @@ import type { BackgroundManager } from "../features/background-agent"
 import { setMainSession, subagentSessions, _resetForTesting } from "../features/claude-code-session-state"
 import { createTodoContinuationEnforcer } from "./todo-continuation-enforcer"

+type TimerCallback = (...args: any[]) => void
+
+interface FakeTimers {
+  advanceBy: (ms: number, advanceClock?: boolean) => Promise<void>
+  restore: () => void
+}
+
+function createFakeTimers(): FakeTimers {
+  const originalNow = Date.now()
+  let clockNow = originalNow
+  let timerNow = 0
+  let nextId = 1
+  const timers = new Map<number, { id: number; time: number; interval: number | null; callback: TimerCallback; args: any[] }>()
+  const cleared = new Set<number>()
+
+  const original = {
+    setTimeout: globalThis.setTimeout,
+    clearTimeout: globalThis.clearTimeout,
+    setInterval: globalThis.setInterval,
+    clearInterval: globalThis.clearInterval,
+    dateNow: Date.now,
+  }
+
+  const normalizeDelay = (delay?: number) => {
+    if (typeof delay !== "number" || !Number.isFinite(delay)) return 0
+    return delay < 0 ? 0 : delay
+  }
+
+  const schedule = (callback: TimerCallback, delay: number | undefined, interval: number | null, args: any[]) => {
+    const id = nextId++
+    timers.set(id, {
+      id,
+      time: timerNow + normalizeDelay(delay),
+      interval,
+      callback,
+      args,
+    })
+    return id
+  }
+
+  const clear = (id: number | undefined) => {
+    if (typeof id !== "number") return
+    cleared.add(id)
+    timers.delete(id)
+  }
+
+  globalThis.setTimeout = ((callback: TimerCallback, delay?: number, ...args: any[]) => {
+    return schedule(callback, delay, null, args) as unknown as ReturnType<typeof setTimeout>
+  }) as typeof setTimeout
+
+  globalThis.setInterval = ((callback: TimerCallback, delay?: number, ...args: any[]) => {
+    const interval = normalizeDelay(delay)
+    return schedule(callback, delay, interval, args) as unknown as ReturnType<typeof setInterval>
+  }) as typeof setInterval
+
+  globalThis.clearTimeout = ((id?: number) => {
+    clear(id)
+  }) as typeof clearTimeout
+
+  globalThis.clearInterval = ((id?: number) => {
+    clear(id)
+  }) as typeof clearInterval
+
+  Date.now = () => clockNow
+
+  const advanceBy = async (ms: number, advanceClock: boolean = false) => {
+    const clamped = Math.max(0, ms)
+    const target = timerNow + clamped
+    if (advanceClock) {
+      clockNow += clamped
+    }
+    while (true) {
+      let next: { id: number; time: number; interval: number | null; callback: TimerCallback; args: any[] } | undefined
+      for (const timer of timers.values()) {
+        if (timer.time <= target && (!next || timer.time < next.time)) {
+          next = timer
+        }
+      }
+      if (!next) break
+
+      timerNow = next.time
+      timers.delete(next.id)
+      next.callback(...next.args)
+
+      if (next.interval !== null && !cleared.has(next.id)) {
+        timers.set(next.id, {
+          id: next.id,
+          time: timerNow + next.interval,
+          interval: next.interval,
+          callback: next.callback,
+          args: next.args,
+        })
+      } else {
+        cleared.delete(next.id)
+      }
+
+      await Promise.resolve()
+    }
+    timerNow = target
+    await Promise.resolve()
+  }
+
+  const restore = () => {
+    globalThis.setTimeout = original.setTimeout
+    globalThis.clearTimeout = original.clearTimeout
+    globalThis.setInterval = original.setInterval
+    globalThis.clearInterval = original.clearInterval
+    Date.now = original.dateNow
+  }
+
+  return { advanceBy, restore }
+}
+
 describe("todo-continuation-enforcer", () => {
  let promptCalls: Array<{ sessionID: string; agent?: string; model?: { providerID?: string; modelID?: string }; text: string }>
  let toastCalls: Array<{ title: string; message: string }>
+  let fakeTimers: FakeTimers

  interface MockMessage {
    info: {
@@ -60,6 +174,7 @@ describe("todo-continuation-enforcer", () => {
  }

  beforeEach(() => {
+    fakeTimers = createFakeTimers()
    _resetForTesting()
    promptCalls = []
    toastCalls = []
@@ -67,6 +182,7 @@ describe("todo-continuation-enforcer", () => {
  })

  afterEach(() => {
+    fakeTimers.restore()
    _resetForTesting()
  })

@@ -85,12 +201,12 @@ describe("todo-continuation-enforcer", () => {
    })

    // #then - countdown toast shown
-    await new Promise(r => setTimeout(r, 100))
+    await fakeTimers.advanceBy(100)
    expect(toastCalls.length).toBeGreaterThanOrEqual(1)
    expect(toastCalls[0].title).toBe("Todo Continuation")

    // #then - after countdown, continuation injected
-    await new Promise(r => setTimeout(r, 2500))
+    await fakeTimers.advanceBy(2500)
    expect(promptCalls.length).toBe(1)
    expect(promptCalls[0].text).toContain("TODO CONTINUATION")
  })
@@ -112,7 +228,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation injected
    expect(promptCalls).toHaveLength(0)
@@ -132,7 +248,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation injected
    expect(promptCalls).toHaveLength(0)
@@ -150,7 +266,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID: otherSession } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation injected
    expect(promptCalls).toHaveLength(0)
@@ -170,7 +286,7 @@ describe("todo-continuation-enforcer", () => {
    })

    // #then - continuation injected for background task session
-    await new Promise(r => setTimeout(r, 2500))
+    await fakeTimers.advanceBy(2500)
    expect(promptCalls.length).toBe(1)
    expect(promptCalls[0].sessionID).toBe(bgTaskSession)
  })
@@ -190,7 +306,7 @@ describe("todo-continuation-enforcer", () => {
    })

    // #when - wait past grace period (500ms), then user sends message
-    await new Promise(r => setTimeout(r, 600))
+    await fakeTimers.advanceBy(600, true)
    await hook.handler({
      event: {
        type: "message.updated",
@@ -199,7 +315,7 @@ describe("todo-continuation-enforcer", () => {
    })

    // #then - wait past countdown time and verify no injection (countdown was cancelled)
-    await new Promise(r => setTimeout(r, 2500))
+    await fakeTimers.advanceBy(2500)
    expect(promptCalls).toHaveLength(0)
  })

@@ -223,9 +339,9 @@ describe("todo-continuation-enforcer", () => {
      },
    })

-    // #then - countdown should continue (message was ignored)
+     // #then - countdown should continue (message was ignored)
    // wait past 2s countdown and verify injection happens
-    await new Promise(r => setTimeout(r, 2500))
+    await fakeTimers.advanceBy(2500)
    expect(promptCalls).toHaveLength(1)
  })

@@ -242,7 +358,7 @@ describe("todo-continuation-enforcer", () => {
    })

    // #when - assistant starts responding
-    await new Promise(r => setTimeout(r, 500))
+    await fakeTimers.advanceBy(500)
    await hook.handler({
      event: {
        type: "message.part.updated",
@@ -250,7 +366,7 @@ describe("todo-continuation-enforcer", () => {
      },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation injected (cancelled)
    expect(promptCalls).toHaveLength(0)
@@ -269,12 +385,12 @@ describe("todo-continuation-enforcer", () => {
    })

    // #when - tool starts executing
-    await new Promise(r => setTimeout(r, 500))
+    await fakeTimers.advanceBy(500)
    await hook.handler({
      event: { type: "tool.execute.before", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation injected (cancelled)
    expect(promptCalls).toHaveLength(0)
@@ -295,7 +411,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation injected
    expect(promptCalls).toHaveLength(0)
@@ -317,7 +433,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - continuation injected
    expect(promptCalls.length).toBe(1)
@@ -336,12 +452,12 @@ describe("todo-continuation-enforcer", () => {
    })

    // #when - session is deleted during countdown
-    await new Promise(r => setTimeout(r, 500))
+    await fakeTimers.advanceBy(500)
    await hook.handler({
      event: { type: "session.deleted", properties: { info: { id: sessionID } } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation injected (cleaned up)
    expect(promptCalls).toHaveLength(0)
@@ -362,7 +478,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 100))
+    await fakeTimers.advanceBy(100)
    expect(toastCalls.length).toBeGreaterThanOrEqual(1)
  })

@@ -379,7 +495,7 @@ describe("todo-continuation-enforcer", () => {
    })

    // #then - multiple toast updates during countdown (2s countdown = 2 toasts: "2s" and "1s")
-    await new Promise(r => setTimeout(r, 2500))
+    await fakeTimers.advanceBy(2500)
    expect(toastCalls.length).toBeGreaterThanOrEqual(2)
    expect(toastCalls[0].message).toContain("2s")
  })
@@ -395,7 +511,7 @@ describe("todo-continuation-enforcer", () => {
    await hook.handler({
      event: { type: "session.idle", properties: { sessionID } },
    })
-    await new Promise(r => setTimeout(r, 3500))
+    await fakeTimers.advanceBy(3500)

    // #then - first injection happened
    expect(promptCalls.length).toBe(1)
@@ -404,7 +520,7 @@ describe("todo-continuation-enforcer", () => {
    await hook.handler({
      event: { type: "session.idle", properties: { sessionID } },
    })
-    await new Promise(r => setTimeout(r, 3500))
+    await fakeTimers.advanceBy(3500)

    // #then - second injection also happened (no throttle blocking)
    expect(promptCalls.length).toBe(2)
@@ -439,7 +555,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 2500))
+    await fakeTimers.advanceBy(2500)

    // #then - continuation injected (non-abort errors don't block)
    expect(promptCalls.length).toBe(1)
@@ -472,7 +588,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation (last message was aborted)
    expect(promptCalls).toHaveLength(0)
@@ -490,12 +606,12 @@ describe("todo-continuation-enforcer", () => {

    const hook = createTodoContinuationEnforcer(createMockPluginInput(), {})

-    // #when - session goes idle
+     // #when - session goes idle
    await hook.handler({
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - continuation injected (no abort)
    expect(promptCalls.length).toBe(1)
@@ -518,7 +634,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - continuation injected (last message is user, not aborted assistant)
    expect(promptCalls.length).toBe(1)
@@ -541,7 +657,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation (abort error detected)
    expect(promptCalls).toHaveLength(0)
@@ -566,12 +682,12 @@ describe("todo-continuation-enforcer", () => {
      },
    })

-    // #when - session goes idle immediately after
+     // #when - session goes idle immediately after
    await hook.handler({
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation (abort detected via event)
    expect(promptCalls).toHaveLength(0)
@@ -601,7 +717,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation (abort detected via event)
    expect(promptCalls).toHaveLength(0)
@@ -627,13 +743,13 @@ describe("todo-continuation-enforcer", () => {
    })

    // #when - wait >3s then idle fires
-    await new Promise(r => setTimeout(r, 3100))
+    await fakeTimers.advanceBy(3100, true)

    await hook.handler({
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - continuation injected (abort flag is stale)
    expect(promptCalls.length).toBeGreaterThan(0)
@@ -659,7 +775,7 @@ describe("todo-continuation-enforcer", () => {
    })

    // #when - user sends new message (clears abort flag)
-    await new Promise(r => setTimeout(r, 600))
+    await fakeTimers.advanceBy(600)
    await hook.handler({
      event: {
        type: "message.updated",
@@ -672,7 +788,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - continuation injected (abort flag was cleared by user activity)
    expect(promptCalls.length).toBeGreaterThan(0)
@@ -710,7 +826,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - continuation injected (abort flag was cleared by assistant activity)
    expect(promptCalls.length).toBeGreaterThan(0)
@@ -748,7 +864,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - continuation injected (abort flag was cleared by tool execution)
    expect(promptCalls.length).toBeGreaterThan(0)
@@ -778,7 +894,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation (event-based detection wins over API)
    expect(promptCalls).toHaveLength(0)
@@ -800,7 +916,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation (API fallback detected the abort)
    expect(promptCalls).toHaveLength(0)
@@ -820,7 +936,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 2500))
+    await fakeTimers.advanceBy(2500)

    // #then - prompt call made, model is undefined when no context (expected behavior)
    expect(promptCalls.length).toBe(1)
@@ -867,7 +983,7 @@ describe("todo-continuation-enforcer", () => {

    // #when - session goes idle
    await hook.handler({ event: { type: "session.idle", properties: { sessionID } } })
-    await new Promise(r => setTimeout(r, 2500))
+    await fakeTimers.advanceBy(2500)

    // #then - model should be extracted from assistant message's flat modelID/providerID
    expect(promptCalls.length).toBe(1)
@@ -919,7 +1035,7 @@ describe("todo-continuation-enforcer", () => {

    // #when - session goes idle
    await hook.handler({ event: { type: "session.idle", properties: { sessionID } } })
-    await new Promise(r => setTimeout(r, 2500))
+    await fakeTimers.advanceBy(2500)

    // #then - continuation uses Sisyphus (skipped compaction agent)
    expect(promptCalls.length).toBe(1)
@@ -964,7 +1080,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation (compaction is in default skipAgents)
    expect(promptCalls).toHaveLength(0)
@@ -1010,7 +1126,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - no continuation (prometheus found after filtering compaction, prometheus is in skipAgents)
    expect(promptCalls).toHaveLength(0)
@@ -1057,7 +1173,7 @@ describe("todo-continuation-enforcer", () => {
      event: { type: "session.idle", properties: { sessionID } },
    })

-    await new Promise(r => setTimeout(r, 3000))
+    await fakeTimers.advanceBy(3000)

    // #then - continuation injected (no agents to skip)
    expect(promptCalls.length).toBe(1)
--- a/src/index.ts
+++ b/src/index.ts
@@ -118,7 +118,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
    
    if (externalNotifier.detected && !forceEnable) {
      // External notification plugin detected - skip our notification to avoid conflicts
-      console.warn(getNotificationConflictWarning(externalNotifier.pluginName!));
+      log(getNotificationConflictWarning(externalNotifier.pluginName!));
      log("session-notification disabled due to external notifier conflict", {
        detected: externalNotifier.pluginName,
        allPlugins: externalNotifier.allPlugins,
--- a/src/shared/agent-config-integration.test.ts
+++ b/src/shared/agent-config-integration.test.ts
@@ -46,7 +46,7 @@ describe("Agent Config Integration", () => {
      const config = {
        sisyphus: { model: "anthropic/claude-opus-4-5" },
        oracle: { model: "openai/gpt-5.2" },
-        librarian: { model: "opencode/big-pickle" },
+        librarian: { model: "opencode/glm-4.7-free" },
      }

      // #when - migration is applied
@@ -65,7 +65,7 @@ describe("Agent Config Integration", () => {
        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" },
+        librarian: { model: "opencode/glm-4.7-free" },
      }

      // #when - migration is applied
--- a/src/shared/connected-providers-cache.ts
+++ b/src/shared/connected-providers-cache.ts
@@ -159,13 +159,13 @@ export async function updateConnectedProvidersCache(client: {

 		writeConnectedProvidersCache(connected)

-		// Also update provider-models cache if model.list is available
+		// Always update provider-models cache (overwrite with fresh data)
+		let modelsByProvider: Record<string, string[]> = {}
 		if (client.model?.list) {
 			try {
 				const modelsResult = await client.model.list()
 				const models = modelsResult.data ?? []

-				const modelsByProvider: Record<string, string[]> = {}
 				for (const model of models) {
 					if (!modelsByProvider[model.provider]) {
 						modelsByProvider[model.provider] = []
@@ -173,19 +173,21 @@ export async function updateConnectedProvidersCache(client: {
 					modelsByProvider[model.provider].push(model.id)
 				}

-				writeProviderModelsCache({
-					models: modelsByProvider,
-					connected,
-				})
-
-				log("[connected-providers-cache] Provider-models cache updated", {
+				log("[connected-providers-cache] Fetched models from API", {
 					providerCount: Object.keys(modelsByProvider).length,
 					totalModels: models.length,
 				})
 			} catch (modelErr) {
-				log("[connected-providers-cache] Error fetching models", { error: String(modelErr) })
+				log("[connected-providers-cache] Error fetching models, writing empty cache", { error: String(modelErr) })
 			}
+		} else {
+			log("[connected-providers-cache] client.model.list not available, writing empty cache")
 		}
+
+		writeProviderModelsCache({
+			models: modelsByProvider,
+			connected,
+		})
 	} catch (err) {
 		log("[connected-providers-cache] Error updating cache", { error: String(err) })
 	}
--- a/src/shared/index.ts
+++ b/src/shared/index.ts
@@ -32,3 +32,4 @@ export * from "./connected-providers-cache"
 export * from "./case-insensitive"
 export * from "./session-utils"
 export * from "./tmux"
+export * from "./model-suggestion-retry"
--- a/src/shared/model-availability.test.ts
+++ b/src/shared/model-availability.test.ts
@@ -2,7 +2,7 @@ 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, getConnectedProviders, __resetModelCache } from "./model-availability"
+import { fetchAvailableModels, fuzzyMatchModel, getConnectedProviders, __resetModelCache, isModelAvailable } from "./model-availability"

 describe("fetchAvailableModels", () => {
  let tempDir: string
@@ -59,6 +59,28 @@ describe("fetchAvailableModels", () => {
    expect(result.size).toBe(0)
  })

+  it("#given connectedProviders unknown but client can list #when fetchAvailableModels called with client #then returns models from API filtered by connected providers", async () => {
+    const client = {
+      provider: {
+        list: async () => ({ data: { connected: ["openai"] } }),
+      },
+      model: {
+        list: async () => ({
+          data: [
+            { id: "gpt-5.2-codex", provider: "openai" },
+            { id: "gemini-3-pro", provider: "google" },
+          ],
+        }),
+      },
+    }
+
+    const result = await fetchAvailableModels(client)
+
+    expect(result).toBeInstanceOf(Set)
+    expect(result.has("openai/gpt-5.2-codex")).toBe(true)
+    expect(result.has("google/gemini-3-pro")).toBe(false)
+  })
+
  it("#given cache file not found #when fetchAvailableModels called with connectedProviders #then returns empty Set", async () => {
    const result = await fetchAvailableModels(undefined, { connectedProviders: ["openai"] })

@@ -66,6 +88,28 @@ describe("fetchAvailableModels", () => {
    expect(result.size).toBe(0)
  })

+  it("#given cache missing but client can list #when fetchAvailableModels called with connectedProviders #then returns models from API", async () => {
+    const client = {
+      provider: {
+        list: async () => ({ data: { connected: ["openai", "google"] } }),
+      },
+      model: {
+        list: async () => ({
+          data: [
+            { id: "gpt-5.2-codex", provider: "openai" },
+            { id: "gemini-3-pro", provider: "google" },
+          ],
+        }),
+      },
+    }
+
+    const result = await fetchAvailableModels(client, { connectedProviders: ["openai", "google"] })
+
+    expect(result).toBeInstanceOf(Set)
+    expect(result.has("openai/gpt-5.2-codex")).toBe(true)
+    expect(result.has("google/gemini-3-pro")).toBe(true)
+  })
+
  it("#given cache read twice #when second call made with same providers #then reads fresh each time", async () => {
    writeModelsCache({
      openai: { id: "openai", models: { "gpt-5.2": { id: "gpt-5.2" } } },
@@ -122,6 +166,19 @@ describe("fuzzyMatchModel", () => {
 		expect(result).toBe("openai/gpt-5.2")
 	})

+	// #given available model with preview suffix
+	// #when searching with provider-prefixed base model
+	// #then return preview model
+	it("should match preview suffix for gemini-3-flash", () => {
+		const available = new Set(["google/gemini-3-flash-preview"])
+		const result = fuzzyMatchModel(
+			"google/gemini-3-flash",
+			available,
+			["google"],
+		)
+		expect(result).toBe("google/gemini-3-flash-preview")
+	})
+
 	// #given available models with partial matches
 	// #when searching for a substring
 	// #then return exact match if it exists
@@ -547,13 +604,13 @@ describe("fetchAvailableModels with provider-models cache (whitelist-filtered)",
 	it("should prefer provider-models cache over models.json", async () => {
 		writeProviderModelsCache({
 			models: {
-				opencode: ["big-pickle", "gpt-5-nano"],
+				opencode: ["glm-4.7-free", "gpt-5-nano"],
 				anthropic: ["claude-opus-4-5"]
 			},
 			connected: ["opencode", "anthropic"]
 		})
 		writeModelsCache({
-			opencode: { models: { "big-pickle": {}, "gpt-5-nano": {}, "gpt-5.2": {} } },
+			opencode: { models: { "glm-4.7-free": {}, "gpt-5-nano": {}, "gpt-5.2": {} } },
 			anthropic: { models: { "claude-opus-4-5": {}, "claude-sonnet-4-5": {} } }
 		})

@@ -562,19 +619,40 @@ describe("fetchAvailableModels with provider-models cache (whitelist-filtered)",
 		})

 		expect(result.size).toBe(3)
-		expect(result.has("opencode/big-pickle")).toBe(true)
+		expect(result.has("opencode/glm-4.7-free")).toBe(true)
 		expect(result.has("opencode/gpt-5-nano")).toBe(true)
 		expect(result.has("anthropic/claude-opus-4-5")).toBe(true)
 		expect(result.has("opencode/gpt-5.2")).toBe(false)
 		expect(result.has("anthropic/claude-sonnet-4-5")).toBe(false)
 	})

+	//#given provider-models cache exists but has no models (API failure)
+	//#when fetchAvailableModels called
+	//#then falls back to models.json so fuzzy matching can still work
+	it("should fall back to models.json when provider-models cache is empty", async () => {
+		writeProviderModelsCache({
+			models: {
+			},
+			connected: ["google"],
+		})
+		writeModelsCache({
+			google: { models: { "gemini-3-flash-preview": {} } },
+		})
+
+		const availableModels = await fetchAvailableModels(undefined, {
+			connectedProviders: ["google"],
+		})
+		const match = fuzzyMatchModel("google/gemini-3-flash", availableModels, ["google"])
+
+		expect(match).toBe("google/gemini-3-flash-preview")
+	})
+
 	//#given only models.json exists (no provider-models cache)
 	//#when fetchAvailableModels called
 	//#then falls back to models.json (no whitelist filtering)
 	it("should fallback to models.json when provider-models cache not found", async () => {
 		writeModelsCache({
-			opencode: { models: { "big-pickle": {}, "gpt-5-nano": {}, "gpt-5.2": {} } },
+			opencode: { models: { "glm-4.7-free": {}, "gpt-5-nano": {}, "gpt-5.2": {} } },
 		})

 		const result = await fetchAvailableModels(undefined, {
@@ -582,7 +660,7 @@ describe("fetchAvailableModels with provider-models cache (whitelist-filtered)",
 		})

 		expect(result.size).toBe(3)
-		expect(result.has("opencode/big-pickle")).toBe(true)
+		expect(result.has("opencode/glm-4.7-free")).toBe(true)
 		expect(result.has("opencode/gpt-5-nano")).toBe(true)
 		expect(result.has("opencode/gpt-5.2")).toBe(true)
 	})
@@ -593,7 +671,7 @@ describe("fetchAvailableModels with provider-models cache (whitelist-filtered)",
 	it("should filter by connectedProviders even with provider-models cache", async () => {
 		writeProviderModelsCache({
 			models: {
-				opencode: ["big-pickle"],
+				opencode: ["glm-4.7-free"],
 				anthropic: ["claude-opus-4-5"],
 				google: ["gemini-3-pro"]
 			},
@@ -605,8 +683,43 @@ describe("fetchAvailableModels with provider-models cache (whitelist-filtered)",
 		})

 		expect(result.size).toBe(1)
-		expect(result.has("opencode/big-pickle")).toBe(true)
+		expect(result.has("opencode/glm-4.7-free")).toBe(true)
 		expect(result.has("anthropic/claude-opus-4-5")).toBe(false)
 		expect(result.has("google/gemini-3-pro")).toBe(false)
 	})
 })
+
+describe("isModelAvailable", () => {
+	it("returns true when model exists via fuzzy match", () => {
+		// #given
+		const available = new Set(["openai/gpt-5.2-codex", "anthropic/claude-opus-4-5"])
+
+		// #when
+		const result = isModelAvailable("gpt-5.2-codex", available)
+
+		// #then
+		expect(result).toBe(true)
+	})
+
+	it("returns false when model not found", () => {
+		// #given
+		const available = new Set(["anthropic/claude-opus-4-5"])
+
+		// #when
+		const result = isModelAvailable("gpt-5.2-codex", available)
+
+		// #then
+		expect(result).toBe(false)
+	})
+
+	it("returns false for empty available set", () => {
+		// #given
+		const available = new Set<string>()
+
+		// #when
+		const result = isModelAvailable("gpt-5.2-codex", available)
+
+		// #then
+		expect(result).toBe(false)
+	})
+})
--- a/src/shared/model-availability.ts
+++ b/src/shared/model-availability.ts
@@ -87,6 +87,20 @@ export function fuzzyMatchModel(
 	return result
 }

+/**
+ * Check if a target model is available (fuzzy match by model name, no provider filtering)
+ * 
+ * @param targetModel - Model name to check (e.g., "gpt-5.2-codex")
+ * @param availableModels - Set of available models in "provider/model" format
+ * @returns true if model is available, false otherwise
+ */
+export function isModelAvailable(
+	targetModel: string,
+	availableModels: Set<string>,
+): boolean {
+	return fuzzyMatchModel(targetModel, availableModels) !== null
+}
+
 export async function getConnectedProviders(client: any): Promise<string[]> {
 	if (!client?.provider?.list) {
 		log("[getConnectedProviders] client.provider.list not available")
@@ -105,85 +119,144 @@ export async function getConnectedProviders(client: any): Promise<string[]> {
 }

 export async function fetchAvailableModels(
-	_client?: any,
+	client?: any,
 	options?: { connectedProviders?: string[] | null }
 ): Promise<Set<string>> {
-	const connectedProvidersUnknown = options?.connectedProviders === null || options?.connectedProviders === undefined
+	let connectedProviders = options?.connectedProviders ?? null
+	let connectedProvidersUnknown = connectedProviders === null

 	log("[fetchAvailableModels] CALLED", { 
 		connectedProvidersUnknown,
 		connectedProviders: options?.connectedProviders 
 	})

+	if (connectedProvidersUnknown && client) {
+		const liveConnected = await getConnectedProviders(client)
+		if (liveConnected.length > 0) {
+			connectedProviders = liveConnected
+			connectedProvidersUnknown = false
+			log("[fetchAvailableModels] connected providers fetched from client", { count: liveConnected.length })
+		}
+	}
+
 	if (connectedProvidersUnknown) {
+		if (client?.model?.list) {
+			const modelSet = new Set<string>()
+			try {
+				const modelsResult = await client.model.list()
+				const models = modelsResult.data ?? []
+				for (const model of models) {
+					if (model?.provider && model?.id) {
+						modelSet.add(`${model.provider}/${model.id}`)
+					}
+				}
+				log("[fetchAvailableModels] fetched models from client without provider filter", {
+					count: modelSet.size,
+				})
+				return modelSet
+			} catch (err) {
+				log("[fetchAvailableModels] client.model.list error", { error: String(err) })
+			}
+		}
 		log("[fetchAvailableModels] connected providers unknown, returning empty set for fallback resolution")
 		return new Set<string>()
 	}

-	const connectedProviders = options!.connectedProviders!
-	const connectedSet = new Set(connectedProviders)
+	const connectedProvidersList = connectedProviders ?? []
+	const connectedSet = new Set(connectedProvidersList)
 	const modelSet = new Set<string>()

 	const providerModelsCache = readProviderModelsCache()
 	if (providerModelsCache) {
-		log("[fetchAvailableModels] using provider-models cache (whitelist-filtered)")
-		
-		for (const [providerId, modelIds] of Object.entries(providerModelsCache.models)) {
-			if (!connectedSet.has(providerId)) {
-				continue
+		const providerCount = Object.keys(providerModelsCache.models).length
+		if (providerCount === 0) {
+			log("[fetchAvailableModels] provider-models cache empty, falling back to models.json")
+		} else {
+			log("[fetchAvailableModels] using provider-models cache (whitelist-filtered)")
+			
+			for (const [providerId, modelIds] of Object.entries(providerModelsCache.models)) {
+				if (!connectedSet.has(providerId)) {
+					continue
+				}
+				for (const modelId of modelIds) {
+					modelSet.add(`${providerId}/${modelId}`)
+				}
 			}
-			for (const modelId of modelIds) {
-				modelSet.add(`${providerId}/${modelId}`)
+
+			log("[fetchAvailableModels] parsed from provider-models cache", {
+				count: modelSet.size,
+				connectedProviders: connectedProvidersList.slice(0, 5)
+			})
+
+			if (modelSet.size > 0) {
+				return modelSet
 			}
+			log("[fetchAvailableModels] provider-models cache produced no models for connected providers, falling back to models.json")
 		}
-
-		log("[fetchAvailableModels] parsed from provider-models cache", {
-			count: modelSet.size,
-			connectedProviders: connectedProviders.slice(0, 5)
-		})
-
-		return modelSet
 	}

 	log("[fetchAvailableModels] provider-models cache not found, falling back to models.json")
 	const cacheFile = join(getOpenCodeCacheDir(), "models.json")

 	if (!existsSync(cacheFile)) {
-		log("[fetchAvailableModels] models.json cache file not found, returning empty set")
-		return modelSet
-	}
+		log("[fetchAvailableModels] models.json cache file not found, falling back to client")
+	} else {
+		try {
+			const content = readFileSync(cacheFile, "utf-8")
+			const data = JSON.parse(content) as Record<string, { id?: string; models?: Record<string, { id?: string }> }>

-	try {
-		const content = readFileSync(cacheFile, "utf-8")
-		const data = JSON.parse(content) as Record<string, { id?: string; models?: Record<string, { id?: string }> }>
+			const providerIds = Object.keys(data)
+			log("[fetchAvailableModels] providers found in models.json", { count: providerIds.length, providers: providerIds.slice(0, 10) })

-		const providerIds = Object.keys(data)
-		log("[fetchAvailableModels] providers found in models.json", { count: providerIds.length, providers: providerIds.slice(0, 10) })
+			for (const providerId of providerIds) {
+				if (!connectedSet.has(providerId)) {
+					continue
+				}

-		for (const providerId of providerIds) {
-			if (!connectedSet.has(providerId)) {
-				continue
+				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}`)
+				}
 			}

-			const provider = data[providerId]
-			const models = provider?.models
-			if (!models || typeof models !== "object") continue
+			log("[fetchAvailableModels] parsed models from models.json (NO whitelist filtering)", {
+				count: modelSet.size,
+				connectedProviders: connectedProvidersList.slice(0, 5)
+			})

-			for (const modelKey of Object.keys(models)) {
-				modelSet.add(`${providerId}/${modelKey}`)
+			if (modelSet.size > 0) {
+				return modelSet
 			}
+		} catch (err) {
+			log("[fetchAvailableModels] error", { error: String(err) })
 		}
-
-		log("[fetchAvailableModels] parsed models from models.json (NO whitelist filtering)", {
-			count: modelSet.size,
-			connectedProviders: connectedProviders.slice(0, 5)
-		})
-
-		return modelSet
-	} catch (err) {
-		log("[fetchAvailableModels] error", { error: String(err) })
-		return modelSet
 	}
+
+	if (client?.model?.list) {
+		try {
+			const modelsResult = await client.model.list()
+			const models = modelsResult.data ?? []
+
+			for (const model of models) {
+				if (!model?.provider || !model?.id) continue
+				if (connectedSet.has(model.provider)) {
+					modelSet.add(`${model.provider}/${model.id}`)
+				}
+			}
+
+			log("[fetchAvailableModels] fetched models from client (filtered)", {
+				count: modelSet.size,
+				connectedProviders: connectedProvidersList.slice(0, 5),
+			})
+		} catch (err) {
+			log("[fetchAvailableModels] client.model.list error", { error: String(err) })
+		}
+	}
+
+	return modelSet
 }

 export function __resetModelCache(): void {}
--- a/src/shared/model-requirements.test.ts
+++ b/src/shared/model-requirements.test.ts
@@ -141,19 +141,19 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
    expect(primary.providers[0]).toBe("openai")
  })

-  test("atlas has valid fallbackChain with claude-sonnet-4-5 as primary", () => {
+  test("atlas has valid fallbackChain with k2p5 as primary (kimi-for-coding prioritized)", () => {
    // #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
+    // #then - fallbackChain exists with k2p5 as first entry (kimi-for-coding prioritized)
    expect(atlas).toBeDefined()
    expect(atlas.fallbackChain).toBeArray()
    expect(atlas.fallbackChain.length).toBeGreaterThan(0)

    const primary = atlas.fallbackChain[0]
-    expect(primary.model).toBe("claude-sonnet-4-5")
-    expect(primary.providers[0]).toBe("anthropic")
+    expect(primary.model).toBe("k2p5")
+    expect(primary.providers[0]).toBe("kimi-for-coding")
  })

  test("all 9 builtin agents have valid fallbackChain arrays", () => {
@@ -208,6 +208,22 @@ describe("CATEGORY_MODEL_REQUIREMENTS", () => {
    expect(primary.providers[0]).toBe("openai")
  })

+  test("deep has valid fallbackChain with gpt-5.2-codex as primary", () => {
+    // #given - deep category requirement
+    const deep = CATEGORY_MODEL_REQUIREMENTS["deep"]
+
+    // #when - accessing deep requirement
+    // #then - fallbackChain exists with gpt-5.2-codex as first entry, medium variant
+    expect(deep).toBeDefined()
+    expect(deep.fallbackChain).toBeArray()
+    expect(deep.fallbackChain.length).toBeGreaterThan(0)
+
+    const primary = deep.fallbackChain[0]
+    expect(primary.variant).toBe("medium")
+    expect(primary.model).toBe("gpt-5.2-codex")
+    expect(primary.providers[0]).toBe("openai")
+  })
+
  test("visual-engineering has valid fallbackChain with gemini-3-pro as primary", () => {
    // #given - visual-engineering category requirement
    const visualEngineering = CATEGORY_MODEL_REQUIREMENTS["visual-engineering"]
@@ -300,11 +316,12 @@ describe("CATEGORY_MODEL_REQUIREMENTS", () => {
    expect(primary.providers[0]).toBe("google")
  })

-  test("all 7 categories have valid fallbackChain arrays", () => {
-    // #given - list of 7 category names
+  test("all 8 categories have valid fallbackChain arrays", () => {
+    // #given - list of 8 category names
    const expectedCategories = [
      "visual-engineering",
      "ultrabrain",
+      "deep",
      "artistry",
      "quick",
      "unspecified-low",
@@ -316,7 +333,7 @@ describe("CATEGORY_MODEL_REQUIREMENTS", () => {
    const definedCategories = Object.keys(CATEGORY_MODEL_REQUIREMENTS)

    // #then - all categories present with valid fallbackChain
-    expect(definedCategories).toHaveLength(7)
+    expect(definedCategories).toHaveLength(8)
    for (const category of expectedCategories) {
      const requirement = CATEGORY_MODEL_REQUIREMENTS[category]
      expect(requirement).toBeDefined()
@@ -353,7 +370,7 @@ describe("FallbackEntry type", () => {
    // #given - a FallbackEntry without variant
    const entry: FallbackEntry = {
      providers: ["opencode", "anthropic"],
-      model: "big-pickle",
+      model: "glm-4.7-free",
    }

    // #when - accessing variant
@@ -383,7 +400,7 @@ describe("ModelRequirement type", () => {
  test("ModelRequirement variant is optional", () => {
    // #given - a ModelRequirement without top-level variant
    const requirement: ModelRequirement = {
-      fallbackChain: [{ providers: ["opencode"], model: "big-pickle" }],
+      fallbackChain: [{ providers: ["opencode"], model: "glm-4.7-free" }],
    }

    // #when - accessing variant
@@ -407,20 +424,38 @@ describe("ModelRequirement type", () => {
    }
  })

-  test("all fallbackChain entries have non-empty providers array", () => {
-    // #given - all agent and category requirements
-    const allRequirements = [
-      ...Object.values(AGENT_MODEL_REQUIREMENTS),
-      ...Object.values(CATEGORY_MODEL_REQUIREMENTS),
-    ]
+   test("all fallbackChain entries have non-empty providers array", () => {
+     // #given - all agent and category requirements
+     const allRequirements = [
+       ...Object.values(AGENT_MODEL_REQUIREMENTS),
+       ...Object.values(CATEGORY_MODEL_REQUIREMENTS),
+     ]

-    // #when - checking each entry in fallbackChain
-    // #then - all have non-empty providers array
-    for (const req of allRequirements) {
-      for (const entry of req.fallbackChain) {
-        expect(entry.providers).toBeArray()
-        expect(entry.providers.length).toBeGreaterThan(0)
-      }
-    }
+     // #when - checking each entry in fallbackChain
+     // #then - all have non-empty providers array
+     for (const req of allRequirements) {
+       for (const entry of req.fallbackChain) {
+         expect(entry.providers).toBeArray()
+         expect(entry.providers.length).toBeGreaterThan(0)
+       }
+     }
+   })
+})
+
+describe("requiresModel field in categories", () => {
+  test("deep category has requiresModel set to gpt-5.2-codex", () => {
+    // #given
+    const deep = CATEGORY_MODEL_REQUIREMENTS["deep"]
+
+    // #when / #then
+    expect(deep.requiresModel).toBe("gpt-5.2-codex")
+  })
+
+  test("artistry category has requiresModel set to gemini-3-pro", () => {
+    // #given
+    const artistry = CATEGORY_MODEL_REQUIREMENTS["artistry"]
+
+    // #when / #then
+    expect(artistry.requiresModel).toBe("gemini-3-pro")
  })
 })
--- a/src/shared/model-requirements.ts
+++ b/src/shared/model-requirements.ts
@@ -7,12 +7,15 @@ export type FallbackEntry = {
 export type ModelRequirement = {
  fallbackChain: FallbackEntry[]
  variant?: string // Default variant (used when entry doesn't specify one)
+  requiresModel?: string // If set, only activates when this model is available (fuzzy match)
 }

 export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
  sisyphus: {
    fallbackChain: [
      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+      { providers: ["kimi-for-coding"], model: "k2p5" },
+      { providers: ["opencode"], model: "kimi-k2.5-free" },
      { 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" },
@@ -21,14 +24,14 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
  oracle: {
    fallbackChain: [
      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "max" },
      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
-      { 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: ["opencode"], model: "glm-4.7-free" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" },
     ],
   },
@@ -44,6 +47,8 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
      { 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: ["kimi-for-coding"], model: "k2p5" },
+      { providers: ["opencode"], model: "kimi-k2.5-free" },
      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-haiku-4-5" },
      { providers: ["opencode"], model: "gpt-5-nano" },
    ],
@@ -51,6 +56,8 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
  prometheus: {
    fallbackChain: [
      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+      { providers: ["kimi-for-coding"], model: "k2p5" },
+      { providers: ["opencode"], model: "kimi-k2.5-free" },
      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
    ],
@@ -58,6 +65,8 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
  metis: {
    fallbackChain: [
      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+      { providers: ["kimi-for-coding"], model: "k2p5" },
+      { providers: ["opencode"], model: "kimi-k2.5-free" },
      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "max" },
    ],
@@ -65,12 +74,14 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
  momus: {
    fallbackChain: [
      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "medium" },
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "max" },
    ],
  },
  atlas: {
    fallbackChain: [
+      { providers: ["kimi-for-coding"], model: "k2p5" },
+      { providers: ["opencode"], model: "kimi-k2.5-free" },
      { 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" },
@@ -83,23 +94,32 @@ export const CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
    fallbackChain: [
      { 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" },
+      { providers: ["zai-coding-plan"], model: "glm-4.7" },
    ],
  },
  ultrabrain: {
    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" },
-    ],
-  },
-  artistry: {
-    fallbackChain: [
      { 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" },
    ],
  },
+   deep: {
+     fallbackChain: [
+       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2-codex", variant: "medium" },
+       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "max" },
+     ],
+     requiresModel: "gpt-5.2-codex",
+   },
+   artistry: {
+     fallbackChain: [
+       { 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" },
+     ],
+     requiresModel: "gemini-3-pro",
+   },
  quick: {
    fallbackChain: [
      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-haiku-4-5" },
--- a/src/shared/model-resolver.test.ts
+++ b/src/shared/model-resolver.test.ts
@@ -388,6 +388,85 @@ describe("resolveModelWithFallback", () => {
      expect(result!.model).toBe("anthropic/claude-opus-4-5")
      expect(result!.source).toBe("provider-fallback")
    })
+
+    test("cross-provider fuzzy match when preferred provider unavailable (librarian scenario)", () => {
+      // #given - glm-4.7 is defined for zai-coding-plan, but only opencode has it
+      const input: ExtendedModelResolutionInput = {
+        fallbackChain: [
+          { providers: ["zai-coding-plan"], model: "glm-4.7" },
+          { providers: ["anthropic"], model: "claude-sonnet-4-5" },
+        ],
+        availableModels: new Set(["opencode/glm-4.7", "anthropic/claude-sonnet-4-5"]),
+        systemDefaultModel: "google/gemini-3-pro",
+      }
+
+      // #when
+      const result = resolveModelWithFallback(input)
+
+      // #then - should find glm-4.7 from opencode via cross-provider fuzzy match
+      expect(result!.model).toBe("opencode/glm-4.7")
+      expect(result!.source).toBe("provider-fallback")
+      expect(logSpy).toHaveBeenCalledWith("Model resolved via fallback chain (cross-provider fuzzy match)", {
+        model: "glm-4.7",
+        match: "opencode/glm-4.7",
+        variant: undefined,
+      })
+    })
+
+    test("prefers specified provider over cross-provider match", () => {
+      // #given - both zai-coding-plan and opencode have glm-4.7
+      const input: ExtendedModelResolutionInput = {
+        fallbackChain: [
+          { providers: ["zai-coding-plan"], model: "glm-4.7" },
+        ],
+        availableModels: new Set(["zai-coding-plan/glm-4.7", "opencode/glm-4.7"]),
+        systemDefaultModel: "google/gemini-3-pro",
+      }
+
+      // #when
+      const result = resolveModelWithFallback(input)
+
+      // #then - should prefer zai-coding-plan (specified provider) over opencode
+      expect(result!.model).toBe("zai-coding-plan/glm-4.7")
+      expect(result!.source).toBe("provider-fallback")
+    })
+
+    test("cross-provider match preserves variant from entry", () => {
+      // #given - entry has variant, model found via cross-provider
+      const input: ExtendedModelResolutionInput = {
+        fallbackChain: [
+          { providers: ["zai-coding-plan"], model: "glm-4.7", variant: "high" },
+        ],
+        availableModels: new Set(["opencode/glm-4.7"]),
+        systemDefaultModel: "google/gemini-3-pro",
+      }
+
+      // #when
+      const result = resolveModelWithFallback(input)
+
+      // #then - variant should be preserved
+      expect(result!.model).toBe("opencode/glm-4.7")
+      expect(result!.variant).toBe("high")
+    })
+
+    test("cross-provider match tries next entry if no match found anywhere", () => {
+      // #given - first entry model not available anywhere, second entry available
+      const input: ExtendedModelResolutionInput = {
+        fallbackChain: [
+          { providers: ["zai-coding-plan"], model: "nonexistent-model" },
+          { providers: ["anthropic"], model: "claude-sonnet-4-5" },
+        ],
+        availableModels: new Set(["anthropic/claude-sonnet-4-5"]),
+        systemDefaultModel: "google/gemini-3-pro",
+      }
+
+      // #when
+      const result = resolveModelWithFallback(input)
+
+      // #then - should fall through to second entry
+      expect(result!.model).toBe("anthropic/claude-sonnet-4-5")
+      expect(result!.source).toBe("provider-fallback")
+    })
  })

  describe("Step 4: System default fallback (no availability match)", () => {
@@ -626,6 +705,103 @@ describe("resolveModelWithFallback", () => {
    })
  })

+  describe("categoryDefaultModel (fuzzy matching for category defaults)", () => {
+    test("applies fuzzy matching to categoryDefaultModel when userModel not provided", () => {
+      // #given - gemini-3-pro is the category default, but only gemini-3-pro-preview is available
+      const input: ExtendedModelResolutionInput = {
+        categoryDefaultModel: "google/gemini-3-pro",
+        fallbackChain: [
+          { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
+        ],
+        availableModels: new Set(["google/gemini-3-pro-preview", "anthropic/claude-opus-4-5"]),
+        systemDefaultModel: "anthropic/claude-sonnet-4-5",
+      }
+
+      // #when
+      const result = resolveModelWithFallback(input)
+
+      // #then - should fuzzy match gemini-3-pro → gemini-3-pro-preview
+      expect(result!.model).toBe("google/gemini-3-pro-preview")
+      expect(result!.source).toBe("category-default")
+    })
+
+    test("categoryDefaultModel uses exact match when available", () => {
+      // #given - exact match exists
+      const input: ExtendedModelResolutionInput = {
+        categoryDefaultModel: "google/gemini-3-pro",
+        fallbackChain: [
+          { providers: ["google"], model: "gemini-3-pro" },
+        ],
+        availableModels: new Set(["google/gemini-3-pro", "google/gemini-3-pro-preview"]),
+        systemDefaultModel: "anthropic/claude-sonnet-4-5",
+      }
+
+      // #when
+      const result = resolveModelWithFallback(input)
+
+      // #then - should use exact match
+      expect(result!.model).toBe("google/gemini-3-pro")
+      expect(result!.source).toBe("category-default")
+    })
+
+    test("categoryDefaultModel falls through to fallbackChain when no match in availableModels", () => {
+      // #given - categoryDefaultModel has no match, but fallbackChain does
+      const input: ExtendedModelResolutionInput = {
+        categoryDefaultModel: "google/gemini-3-pro",
+        fallbackChain: [
+          { providers: ["anthropic"], model: "claude-opus-4-5" },
+        ],
+        availableModels: new Set(["anthropic/claude-opus-4-5"]),
+        systemDefaultModel: "system/default",
+      }
+
+      // #when
+      const result = resolveModelWithFallback(input)
+
+      // #then - should fall through to fallbackChain
+      expect(result!.model).toBe("anthropic/claude-opus-4-5")
+      expect(result!.source).toBe("provider-fallback")
+    })
+
+    test("userModel takes priority over categoryDefaultModel", () => {
+      // #given - both userModel and categoryDefaultModel provided
+      const input: ExtendedModelResolutionInput = {
+        userModel: "anthropic/claude-opus-4-5",
+        categoryDefaultModel: "google/gemini-3-pro",
+        fallbackChain: [
+          { providers: ["google"], model: "gemini-3-pro" },
+        ],
+        availableModels: new Set(["google/gemini-3-pro-preview", "anthropic/claude-opus-4-5"]),
+        systemDefaultModel: "system/default",
+      }
+
+      // #when
+      const result = resolveModelWithFallback(input)
+
+      // #then - userModel wins
+      expect(result!.model).toBe("anthropic/claude-opus-4-5")
+      expect(result!.source).toBe("override")
+    })
+
+    test("categoryDefaultModel works when availableModels is empty but connected provider exists", () => {
+      // #given - no availableModels but connected provider cache exists
+      const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["google"])
+      const input: ExtendedModelResolutionInput = {
+        categoryDefaultModel: "google/gemini-3-pro",
+        availableModels: new Set(),
+        systemDefaultModel: "anthropic/claude-sonnet-4-5",
+      }
+
+      // #when
+      const result = resolveModelWithFallback(input)
+
+      // #then - should use categoryDefaultModel since google is connected
+      expect(result!.model).toBe("google/gemini-3-pro")
+      expect(result!.source).toBe("category-default")
+      cacheSpy.mockRestore()
+    })
+  })
+
  describe("Optional systemDefaultModel", () => {
    test("returns undefined when systemDefaultModel is undefined and no fallback found", () => {
      // #given
--- a/src/shared/model-resolver.ts
+++ b/src/shared/model-resolver.ts
@@ -11,6 +11,7 @@ export type ModelResolutionInput = {

 export type ModelSource =
 	| "override"
+	| "category-default"
 	| "provider-fallback"
 	| "system-default"

@@ -23,6 +24,7 @@ export type ModelResolutionResult = {
 export type ExtendedModelResolutionInput = {
 	uiSelectedModel?: string
 	userModel?: string
+	categoryDefaultModel?: string
 	fallbackChain?: FallbackEntry[]
 	availableModels: Set<string>
 	systemDefaultModel?: string
@@ -44,7 +46,7 @@ export function resolveModel(input: ModelResolutionInput): string | undefined {
 export function resolveModelWithFallback(
 	input: ExtendedModelResolutionInput,
 ): ModelResolutionResult | undefined {
-	const { uiSelectedModel, userModel, fallbackChain, availableModels, systemDefaultModel } = input
+	const { uiSelectedModel, userModel, categoryDefaultModel, fallbackChain, availableModels, systemDefaultModel } = input

 	// Step 1: UI Selection (highest priority - respects user's model choice in OpenCode UI)
 	const normalizedUiModel = normalizeModel(uiSelectedModel)
@@ -53,14 +55,43 @@ export function resolveModelWithFallback(
 		return { model: normalizedUiModel, source: "override" }
 	}

-	// Step 2: Config Override (from oh-my-opencode.json)
+	// Step 2: Config Override (from oh-my-opencode.json user config)
 	const normalizedUserModel = normalizeModel(userModel)
 	if (normalizedUserModel) {
 		log("Model resolved via config override", { model: normalizedUserModel })
 		return { model: normalizedUserModel, source: "override" }
 	}

-	// Step 3: Provider fallback chain (with availability check)
+	// Step 2.5: Category Default Model (from DEFAULT_CATEGORIES, with fuzzy matching)
+	const normalizedCategoryDefault = normalizeModel(categoryDefaultModel)
+	if (normalizedCategoryDefault) {
+		if (availableModels.size > 0) {
+			const parts = normalizedCategoryDefault.split("/")
+			const providerHint = parts.length >= 2 ? [parts[0]] : undefined
+			const match = fuzzyMatchModel(normalizedCategoryDefault, availableModels, providerHint)
+			if (match) {
+				log("Model resolved via category default (fuzzy matched)", { original: normalizedCategoryDefault, matched: match })
+				return { model: match, source: "category-default" }
+			}
+		} else {
+			const connectedProviders = readConnectedProvidersCache()
+			if (connectedProviders === null) {
+				log("Model resolved via category default (no cache, first run)", { model: normalizedCategoryDefault })
+				return { model: normalizedCategoryDefault, source: "category-default" }
+			}
+			const parts = normalizedCategoryDefault.split("/")
+			if (parts.length >= 2) {
+				const provider = parts[0]
+				if (connectedProviders.includes(provider)) {
+					log("Model resolved via category default (connected provider)", { model: normalizedCategoryDefault })
+					return { model: normalizedCategoryDefault, source: "category-default" }
+				}
+			}
+		}
+		log("Category default model not available, falling through to fallback chain", { model: normalizedCategoryDefault })
+	}
+
+	// Step 3: Provider fallback chain (exact match → fuzzy match → next provider)
 	if (fallbackChain && fallbackChain.length > 0) {
 		if (availableModels.size === 0) {
 			const connectedProviders = readConnectedProvidersCache()
@@ -73,7 +104,7 @@ export function resolveModelWithFallback(
 					for (const provider of entry.providers) {
 						if (connectedSet.has(provider)) {
 							const model = `${provider}/${entry.model}`
-							log("Model resolved via fallback chain (no model cache, using connected provider)", { 
+							log("Model resolved via fallback chain (connected provider)", { 
 								provider, 
 								model: entry.model, 
 								variant: entry.variant,
@@ -84,19 +115,31 @@ export function resolveModelWithFallback(
 				}
 				log("No connected provider found in fallback chain, falling through to system default")
 			}
-		}
+		} else {
+			for (const entry of fallbackChain) {
+				// Step 1: Try with provider filter (preferred providers first)
+				for (const provider of entry.providers) {
+					const fullModel = `${provider}/${entry.model}`
+					const match = fuzzyMatchModel(fullModel, availableModels, [provider])
+					if (match) {
+						log("Model resolved via fallback chain (availability confirmed)", { provider, model: entry.model, match, variant: entry.variant })
+						return { model: match, source: "provider-fallback", variant: entry.variant }
+					}
+				}

-		for (const entry of fallbackChain) {
-			for (const provider of entry.providers) {
-				const fullModel = `${provider}/${entry.model}`
-				const match = fuzzyMatchModel(fullModel, availableModels, [provider])
-				if (match) {
-					log("Model resolved via fallback chain (availability confirmed)", { provider, model: entry.model, match, variant: entry.variant })
-					return { model: match, source: "provider-fallback", variant: entry.variant }
+				// Step 2: Try without provider filter (cross-provider fuzzy match)
+				const crossProviderMatch = fuzzyMatchModel(entry.model, availableModels)
+				if (crossProviderMatch) {
+					log("Model resolved via fallback chain (cross-provider fuzzy match)", {
+						model: entry.model,
+						match: crossProviderMatch,
+						variant: entry.variant,
+					})
+					return { model: crossProviderMatch, source: "provider-fallback", variant: entry.variant }
 				}
 			}
+			log("No available model found in fallback chain, falling through to system default")
 		}
-		log("No available model found in fallback chain, falling through to system default")
 	}

 	// Step 4: System default (if provided)
--- a/src/shared/model-suggestion-retry.test.ts
+++ b/src/shared/model-suggestion-retry.test.ts
@@ -0,0 +1,401 @@
+import { describe, it, expect, mock } from "bun:test"
+import { parseModelSuggestion, promptWithModelSuggestionRetry } from "./model-suggestion-retry"
+
+describe("parseModelSuggestion", () => {
+  describe("structured NamedError format", () => {
+    it("should extract suggestion from ProviderModelNotFoundError", () => {
+      //#given a structured NamedError with suggestions
+      const error = {
+        name: "ProviderModelNotFoundError",
+        data: {
+          providerID: "anthropic",
+          modelID: "claude-sonet-4",
+          suggestions: ["claude-sonnet-4", "claude-sonnet-4-5"],
+        },
+      }
+
+      //#when parsing the error
+      const result = parseModelSuggestion(error)
+
+      //#then should return the first suggestion
+      expect(result).toEqual({
+        providerID: "anthropic",
+        modelID: "claude-sonet-4",
+        suggestion: "claude-sonnet-4",
+      })
+    })
+
+    it("should return null when suggestions array is empty", () => {
+      //#given a NamedError with empty suggestions
+      const error = {
+        name: "ProviderModelNotFoundError",
+        data: {
+          providerID: "anthropic",
+          modelID: "claude-sonet-4",
+          suggestions: [],
+        },
+      }
+
+      //#when parsing the error
+      const result = parseModelSuggestion(error)
+
+      //#then should return null
+      expect(result).toBeNull()
+    })
+
+    it("should return null when suggestions field is missing", () => {
+      //#given a NamedError without suggestions
+      const error = {
+        name: "ProviderModelNotFoundError",
+        data: {
+          providerID: "anthropic",
+          modelID: "claude-sonet-4",
+        },
+      }
+
+      //#when parsing the error
+      const result = parseModelSuggestion(error)
+
+      //#then should return null
+      expect(result).toBeNull()
+    })
+  })
+
+  describe("nested error format", () => {
+    it("should extract suggestion from nested data.error", () => {
+      //#given an error with nested NamedError in data field
+      const error = {
+        data: {
+          name: "ProviderModelNotFoundError",
+          data: {
+            providerID: "openai",
+            modelID: "gpt-5",
+            suggestions: ["gpt-5.2"],
+          },
+        },
+      }
+
+      //#when parsing the error
+      const result = parseModelSuggestion(error)
+
+      //#then should extract from nested structure
+      expect(result).toEqual({
+        providerID: "openai",
+        modelID: "gpt-5",
+        suggestion: "gpt-5.2",
+      })
+    })
+
+    it("should extract suggestion from nested error field", () => {
+      //#given an error with nested NamedError in error field
+      const error = {
+        error: {
+          name: "ProviderModelNotFoundError",
+          data: {
+            providerID: "google",
+            modelID: "gemini-3-flsh",
+            suggestions: ["gemini-3-flash"],
+          },
+        },
+      }
+
+      //#when parsing the error
+      const result = parseModelSuggestion(error)
+
+      //#then should extract from nested error field
+      expect(result).toEqual({
+        providerID: "google",
+        modelID: "gemini-3-flsh",
+        suggestion: "gemini-3-flash",
+      })
+    })
+  })
+
+  describe("string message format", () => {
+    it("should parse suggestion from error message string", () => {
+      //#given an Error with model-not-found message and suggestion
+      const error = new Error(
+        "Model not found: anthropic/claude-sonet-4. Did you mean: claude-sonnet-4, claude-sonnet-4-5?"
+      )
+
+      //#when parsing the error
+      const result = parseModelSuggestion(error)
+
+      //#then should extract from message string
+      expect(result).toEqual({
+        providerID: "anthropic",
+        modelID: "claude-sonet-4",
+        suggestion: "claude-sonnet-4",
+      })
+    })
+
+    it("should parse from plain string error", () => {
+      //#given a plain string error message
+      const error =
+        "Model not found: openai/gtp-5. Did you mean: gpt-5?"
+
+      //#when parsing the error
+      const result = parseModelSuggestion(error)
+
+      //#then should extract from string
+      expect(result).toEqual({
+        providerID: "openai",
+        modelID: "gtp-5",
+        suggestion: "gpt-5",
+      })
+    })
+
+    it("should parse from object with message property", () => {
+      //#given an object with message property
+      const error = {
+        message: "Model not found: google/gemini-3-flsh. Did you mean: gemini-3-flash?",
+      }
+
+      //#when parsing the error
+      const result = parseModelSuggestion(error)
+
+      //#then should extract from message property
+      expect(result).toEqual({
+        providerID: "google",
+        modelID: "gemini-3-flsh",
+        suggestion: "gemini-3-flash",
+      })
+    })
+
+    it("should return null when message has no suggestion", () => {
+      //#given an error without Did you mean
+      const error = new Error("Model not found: anthropic/nonexistent.")
+
+      //#when parsing the error
+      const result = parseModelSuggestion(error)
+
+      //#then should return null
+      expect(result).toBeNull()
+    })
+  })
+
+  describe("edge cases", () => {
+    it("should return null for null error", () => {
+      //#given null
+      //#when parsing
+      const result = parseModelSuggestion(null)
+      //#then should return null
+      expect(result).toBeNull()
+    })
+
+    it("should return null for undefined error", () => {
+      //#given undefined
+      //#when parsing
+      const result = parseModelSuggestion(undefined)
+      //#then should return null
+      expect(result).toBeNull()
+    })
+
+    it("should return null for unrelated error", () => {
+      //#given an unrelated error
+      const error = new Error("Connection timeout")
+      //#when parsing
+      const result = parseModelSuggestion(error)
+      //#then should return null
+      expect(result).toBeNull()
+    })
+
+    it("should return null for empty object", () => {
+      //#given empty object
+      //#when parsing
+      const result = parseModelSuggestion({})
+      //#then should return null
+      expect(result).toBeNull()
+    })
+  })
+})
+
+describe("promptWithModelSuggestionRetry", () => {
+  it("should succeed on first try without retry", async () => {
+    //#given a client where prompt succeeds
+    const promptMock = mock(() => Promise.resolve())
+    const client = { session: { prompt: promptMock } }
+
+    //#when calling promptWithModelSuggestionRetry
+    await promptWithModelSuggestionRetry(client as any, {
+      path: { id: "session-1" },
+      body: {
+        parts: [{ type: "text", text: "hello" }],
+        model: { providerID: "anthropic", modelID: "claude-sonnet-4" },
+      },
+    })
+
+    //#then should call prompt exactly once
+    expect(promptMock).toHaveBeenCalledTimes(1)
+  })
+
+  it("should retry with suggestion on model-not-found error", async () => {
+    //#given a client that fails first with model-not-found, then succeeds
+    const promptMock = mock()
+      .mockRejectedValueOnce({
+        name: "ProviderModelNotFoundError",
+        data: {
+          providerID: "anthropic",
+          modelID: "claude-sonet-4",
+          suggestions: ["claude-sonnet-4"],
+        },
+      })
+      .mockResolvedValueOnce(undefined)
+    const client = { session: { prompt: promptMock } }
+
+    //#when calling promptWithModelSuggestionRetry
+    await promptWithModelSuggestionRetry(client as any, {
+      path: { id: "session-1" },
+      body: {
+        agent: "explore",
+        parts: [{ type: "text", text: "hello" }],
+        model: { providerID: "anthropic", modelID: "claude-sonet-4" },
+      },
+    })
+
+    //#then should call prompt twice - first with original, then with suggestion
+    expect(promptMock).toHaveBeenCalledTimes(2)
+    const retryCall = promptMock.mock.calls[1][0]
+    expect(retryCall.body.model).toEqual({
+      providerID: "anthropic",
+      modelID: "claude-sonnet-4",
+    })
+  })
+
+  it("should throw original error when no suggestion available", async () => {
+    //#given a client that fails with a non-model-not-found error
+    const originalError = new Error("Connection refused")
+    const promptMock = mock().mockRejectedValueOnce(originalError)
+    const client = { session: { prompt: promptMock } }
+
+    //#when calling promptWithModelSuggestionRetry
+    //#then should throw the original error
+    await expect(
+      promptWithModelSuggestionRetry(client as any, {
+        path: { id: "session-1" },
+        body: {
+          parts: [{ type: "text", text: "hello" }],
+          model: { providerID: "anthropic", modelID: "claude-sonnet-4" },
+        },
+      })
+    ).rejects.toThrow("Connection refused")
+
+    expect(promptMock).toHaveBeenCalledTimes(1)
+  })
+
+  it("should throw original error when retry also fails", async () => {
+    //#given a client that fails with model-not-found, retry also fails
+    const modelNotFoundError = {
+      name: "ProviderModelNotFoundError",
+      data: {
+        providerID: "anthropic",
+        modelID: "claude-sonet-4",
+        suggestions: ["claude-sonnet-4"],
+      },
+    }
+    const retryError = new Error("Still not found")
+    const promptMock = mock()
+      .mockRejectedValueOnce(modelNotFoundError)
+      .mockRejectedValueOnce(retryError)
+    const client = { session: { prompt: promptMock } }
+
+    //#when calling promptWithModelSuggestionRetry
+    //#then should throw the retry error (not the original)
+    await expect(
+      promptWithModelSuggestionRetry(client as any, {
+        path: { id: "session-1" },
+        body: {
+          parts: [{ type: "text", text: "hello" }],
+          model: { providerID: "anthropic", modelID: "claude-sonet-4" },
+        },
+      })
+    ).rejects.toThrow("Still not found")
+
+    expect(promptMock).toHaveBeenCalledTimes(2)
+  })
+
+  it("should preserve other body fields during retry", async () => {
+    //#given a client that fails first with model-not-found
+    const promptMock = mock()
+      .mockRejectedValueOnce({
+        name: "ProviderModelNotFoundError",
+        data: {
+          providerID: "anthropic",
+          modelID: "claude-sonet-4",
+          suggestions: ["claude-sonnet-4"],
+        },
+      })
+      .mockResolvedValueOnce(undefined)
+    const client = { session: { prompt: promptMock } }
+
+    //#when calling with additional body fields
+    await promptWithModelSuggestionRetry(client as any, {
+      path: { id: "session-1" },
+      body: {
+        agent: "explore",
+        system: "You are a helpful agent",
+        tools: { task: false },
+        parts: [{ type: "text", text: "hello" }],
+        model: { providerID: "anthropic", modelID: "claude-sonet-4" },
+        variant: "max",
+      },
+    })
+
+    //#then retry call should preserve all fields except corrected model
+    const retryCall = promptMock.mock.calls[1][0]
+    expect(retryCall.body.agent).toBe("explore")
+    expect(retryCall.body.system).toBe("You are a helpful agent")
+    expect(retryCall.body.tools).toEqual({ task: false })
+    expect(retryCall.body.variant).toBe("max")
+    expect(retryCall.body.model).toEqual({
+      providerID: "anthropic",
+      modelID: "claude-sonnet-4",
+    })
+  })
+
+  it("should handle string error message with suggestion", async () => {
+    //#given a client that fails with a string error containing suggestion
+    const promptMock = mock()
+      .mockRejectedValueOnce(
+        new Error("Model not found: anthropic/claude-sonet-4. Did you mean: claude-sonnet-4?")
+      )
+      .mockResolvedValueOnce(undefined)
+    const client = { session: { prompt: promptMock } }
+
+    //#when calling promptWithModelSuggestionRetry
+    await promptWithModelSuggestionRetry(client as any, {
+      path: { id: "session-1" },
+      body: {
+        parts: [{ type: "text", text: "hello" }],
+        model: { providerID: "anthropic", modelID: "claude-sonet-4" },
+      },
+    })
+
+    //#then should retry with suggested model
+    expect(promptMock).toHaveBeenCalledTimes(2)
+    const retryCall = promptMock.mock.calls[1][0]
+    expect(retryCall.body.model.modelID).toBe("claude-sonnet-4")
+  })
+
+  it("should not retry when no model in original request", async () => {
+    //#given a client that fails with model-not-found but original has no model param
+    const modelNotFoundError = new Error(
+      "Model not found: anthropic/claude-sonet-4. Did you mean: claude-sonnet-4?"
+    )
+    const promptMock = mock().mockRejectedValueOnce(modelNotFoundError)
+    const client = { session: { prompt: promptMock } }
+
+    //#when calling without model in body
+    //#then should throw without retrying
+    await expect(
+      promptWithModelSuggestionRetry(client as any, {
+        path: { id: "session-1" },
+        body: {
+          parts: [{ type: "text", text: "hello" }],
+        },
+      })
+    ).rejects.toThrow()
+
+    expect(promptMock).toHaveBeenCalledTimes(1)
+  })
+})
--- a/src/shared/model-suggestion-retry.ts
+++ b/src/shared/model-suggestion-retry.ts
@@ -0,0 +1,111 @@
+import type { createOpencodeClient } from "@opencode-ai/sdk"
+import { log } from "./logger"
+
+type Client = ReturnType<typeof createOpencodeClient>
+
+export interface ModelSuggestionInfo {
+  providerID: string
+  modelID: string
+  suggestion: string
+}
+
+function extractMessage(error: unknown): string {
+  if (typeof error === "string") return error
+  if (error instanceof Error) return error.message
+  if (typeof error === "object" && error !== null) {
+    const obj = error as Record<string, unknown>
+    if (typeof obj.message === "string") return obj.message
+    try {
+      return JSON.stringify(error)
+    } catch {
+      return ""
+    }
+  }
+  return String(error)
+}
+
+export function parseModelSuggestion(error: unknown): ModelSuggestionInfo | null {
+  if (!error) return null
+
+  if (typeof error === "object") {
+    const errObj = error as Record<string, unknown>
+
+    if (errObj.name === "ProviderModelNotFoundError" && typeof errObj.data === "object" && errObj.data !== null) {
+      const data = errObj.data as Record<string, unknown>
+      const suggestions = data.suggestions
+      if (Array.isArray(suggestions) && suggestions.length > 0 && typeof suggestions[0] === "string") {
+        return {
+          providerID: String(data.providerID ?? ""),
+          modelID: String(data.modelID ?? ""),
+          suggestion: suggestions[0],
+        }
+      }
+      return null
+    }
+
+    for (const key of ["data", "error", "cause"] as const) {
+      const nested = errObj[key]
+      if (nested && typeof nested === "object") {
+        const result = parseModelSuggestion(nested)
+        if (result) return result
+      }
+    }
+  }
+
+  const message = extractMessage(error)
+  if (!message) return null
+
+  const modelMatch = message.match(/model not found:\s*([^/\s]+)\s*\/\s*([^.\s]+)/i)
+  const suggestionMatch = message.match(/did you mean:\s*([^,?]+)/i)
+
+  if (modelMatch && suggestionMatch) {
+    return {
+      providerID: modelMatch[1].trim(),
+      modelID: modelMatch[2].trim(),
+      suggestion: suggestionMatch[1].trim(),
+    }
+  }
+
+  return null
+}
+
+interface PromptBody {
+  model?: { providerID: string; modelID: string }
+  [key: string]: unknown
+}
+
+interface PromptArgs {
+  path: { id: string }
+  body: PromptBody
+  [key: string]: unknown
+}
+
+export async function promptWithModelSuggestionRetry(
+  client: Client,
+  args: PromptArgs,
+): Promise<void> {
+  try {
+    await client.session.prompt(args as Parameters<typeof client.session.prompt>[0])
+  } catch (error) {
+    const suggestion = parseModelSuggestion(error)
+    if (!suggestion || !args.body.model) {
+      throw error
+    }
+
+    log("[model-suggestion-retry] Model not found, retrying with suggestion", {
+      original: `${suggestion.providerID}/${suggestion.modelID}`,
+      suggested: suggestion.suggestion,
+    })
+
+    await client.session.prompt({
+      ...args,
+      body: {
+        ...args.body,
+        model: {
+          providerID: suggestion.providerID,
+          modelID: suggestion.suggestion,
+        },
+      },
+    } as Parameters<typeof client.session.prompt>[0])
+  }
+}
--- a/src/tools/ast-grep/downloader.ts
+++ b/src/tools/ast-grep/downloader.ts
@@ -3,6 +3,7 @@ import { join } from "path"
 import { homedir } from "os"
 import { createRequire } from "module"
 import { extractZip } from "../../shared"
+import { log } from "../../shared/logger"

 const REPO = "ast-grep/ast-grep"

@@ -63,7 +64,7 @@ export async function downloadAstGrep(version: string = DEFAULT_VERSION): Promis
  const platformInfo = PLATFORM_MAP[platformKey]

  if (!platformInfo) {
-    console.error(`[oh-my-opencode] Unsupported platform for ast-grep: ${platformKey}`)
+    log(`[oh-my-opencode] Unsupported platform for ast-grep: ${platformKey}`)
    return null
  }

@@ -79,7 +80,7 @@ export async function downloadAstGrep(version: string = DEFAULT_VERSION): Promis
  const assetName = `app-${arch}-${os}.zip`
  const downloadUrl = `https://github.com/${REPO}/releases/download/${version}/${assetName}`

-  console.log(`[oh-my-opencode] Downloading ast-grep binary...`)
+  log(`[oh-my-opencode] Downloading ast-grep binary...`)

  try {
    if (!existsSync(cacheDir)) {
@@ -106,11 +107,11 @@ export async function downloadAstGrep(version: string = DEFAULT_VERSION): Promis
      chmodSync(binaryPath, 0o755)
    }

-    console.log(`[oh-my-opencode] ast-grep binary ready.`)
+    log(`[oh-my-opencode] ast-grep binary ready.`)

    return binaryPath
  } catch (err) {
-    console.error(
+    log(
      `[oh-my-opencode] Failed to download ast-grep: ${err instanceof Error ? err.message : err}`
    )
    return null
--- a/src/tools/delegate-task/constants.ts
+++ b/src/tools/delegate-task/constants.ts
@@ -14,8 +14,14 @@ Design-first mindset:
 AVOID: Generic fonts, purple gradients on white, predictable layouts, cookie-cutter patterns.
 </Category_Context>`

-export const STRATEGIC_CATEGORY_PROMPT_APPEND = `<Category_Context>
-You are working on BUSINESS LOGIC / ARCHITECTURE tasks.
+export const ULTRABRAIN_CATEGORY_PROMPT_APPEND = `<Category_Context>
+You are working on DEEP LOGICAL REASONING / COMPLEX ARCHITECTURE tasks.
+
+**CRITICAL - CODE STYLE REQUIREMENTS (NON-NEGOTIABLE)**:
+1. BEFORE writing ANY code, SEARCH the existing codebase to find similar patterns/styles
+2. Your code MUST match the project's existing conventions - blend in seamlessly
+3. Write READABLE code that humans can easily understand - no clever tricks
+4. If unsure about style, explore more files until you find the pattern

 Strategic advisor mindset:
 - Bias toward simplicity: least complex solution that fulfills requirements
@@ -153,11 +159,43 @@ Approach:
 - Documentation, READMEs, articles, technical writing
 </Category_Context>`

+export const DEEP_CATEGORY_PROMPT_APPEND = `<Category_Context>
+You are working on GOAL-ORIENTED AUTONOMOUS tasks.
+
+**CRITICAL - AUTONOMOUS EXECUTION MINDSET (NON-NEGOTIABLE)**:
+You are NOT an interactive assistant. You are an autonomous problem-solver.
+
+**BEFORE making ANY changes**:
+1. SILENTLY explore the codebase extensively (5-15 minutes of reading is normal)
+2. Read related files, trace dependencies, understand the full context
+3. Build a complete mental model of the problem space
+4. DO NOT ask clarifying questions - the goal is already defined
+
+**Autonomous executor mindset**:
+- You receive a GOAL, not step-by-step instructions
+- Figure out HOW to achieve the goal yourself
+- Thorough research before any action
+- Fix hairy problems that require deep understanding
+- Work independently without frequent check-ins
+
+**Approach**:
+- Explore extensively, understand deeply, then act decisively
+- Prefer comprehensive solutions over quick patches
+- If the goal is unclear, make reasonable assumptions and proceed
+- Document your reasoning in code comments only when non-obvious
+
+**Response format**:
+- Minimal status updates (user trusts your autonomy)
+- Focus on results, not play-by-play progress
+- Report completion with summary of changes made
+</Category_Context>`
+


 export const DEFAULT_CATEGORIES: Record<string, CategoryConfig> = {
  "visual-engineering": { model: "google/gemini-3-pro" },
  ultrabrain: { model: "openai/gpt-5.2-codex", variant: "xhigh" },
+  deep: { model: "openai/gpt-5.2-codex", variant: "medium" },
  artistry: { model: "google/gemini-3-pro", variant: "max" },
  quick: { model: "anthropic/claude-haiku-4-5" },
  "unspecified-low": { model: "anthropic/claude-sonnet-4-5" },
@@ -167,7 +205,8 @@ export const DEFAULT_CATEGORIES: Record<string, CategoryConfig> = {

 export const CATEGORY_PROMPT_APPENDS: Record<string, string> = {
  "visual-engineering": VISUAL_CATEGORY_PROMPT_APPEND,
-  ultrabrain: STRATEGIC_CATEGORY_PROMPT_APPEND,
+  ultrabrain: ULTRABRAIN_CATEGORY_PROMPT_APPEND,
+  deep: DEEP_CATEGORY_PROMPT_APPEND,
  artistry: ARTISTRY_CATEGORY_PROMPT_APPEND,
  quick: QUICK_CATEGORY_PROMPT_APPEND,
  "unspecified-low": UNSPECIFIED_LOW_CATEGORY_PROMPT_APPEND,
@@ -177,8 +216,9 @@ export const CATEGORY_PROMPT_APPENDS: Record<string, string> = {

 export const CATEGORY_DESCRIPTIONS: Record<string, string> = {
  "visual-engineering": "Frontend, UI/UX, design, styling, animation",
-  ultrabrain: "Deep logical reasoning, complex architecture decisions requiring extensive analysis",
-  artistry: "Highly creative/artistic tasks, novel ideas",
+  ultrabrain: "Use ONLY for genuinely hard, logic-heavy tasks. Give clear goals only, not step-by-step instructions.",
+  deep: "Goal-oriented autonomous problem-solving. Thorough research before action. For hairy problems requiring deep understanding.",
+  artistry: "Complex problem-solving with unconventional, creative approaches - beyond standard patterns",
  quick: "Trivial tasks - single file changes, typo fixes, simple modifications",
  "unspecified-low": "Tasks that don't fit other categories, low effort required",
  "unspecified-high": "Tasks that don't fit other categories, high effort required",
--- a/src/tools/delegate-task/tools.test.ts
+++ b/src/tools/delegate-task/tools.test.ts
@@ -51,6 +51,16 @@ describe("sisyphus-task", () => {
      expect(category.model).toBe("openai/gpt-5.2-codex")
      expect(category.variant).toBe("xhigh")
    })
+
+    test("deep category has model and variant config", () => {
+      // #given
+      const category = DEFAULT_CATEGORIES["deep"]
+
+      // #when / #then
+      expect(category).toBeDefined()
+      expect(category.model).toBe("openai/gpt-5.2-codex")
+      expect(category.variant).toBe("medium")
+    })
  })

  describe("CATEGORY_PROMPT_APPENDS", () => {
@@ -63,14 +73,23 @@ describe("sisyphus-task", () => {
      expect(promptAppend).toContain("Design-first")
    })

-    test("ultrabrain category has strategic prompt", () => {
+    test("ultrabrain category has deep logical reasoning prompt", () => {
      // #given
      const promptAppend = CATEGORY_PROMPT_APPENDS["ultrabrain"]

      // #when / #then
-      expect(promptAppend).toContain("BUSINESS LOGIC")
+      expect(promptAppend).toContain("DEEP LOGICAL REASONING")
      expect(promptAppend).toContain("Strategic advisor")
    })
+
+    test("deep category has goal-oriented autonomous prompt", () => {
+      // #given
+      const promptAppend = CATEGORY_PROMPT_APPENDS["deep"]
+
+      // #when / #then
+      expect(promptAppend).toContain("GOAL-ORIENTED")
+      expect(promptAppend).toContain("autonomous")
+    })
  })

  describe("CATEGORY_DESCRIPTIONS", () => {
@@ -283,6 +302,36 @@ describe("sisyphus-task", () => {
      expect(result).toBeNull()
    })

+    test("blocks requiresModel when availability is known and missing the required model", () => {
+      // #given
+      const categoryName = "deep"
+      const availableModels = new Set<string>(["anthropic/claude-opus-4-5"])
+
+      // #when
+      const result = resolveCategoryConfig(categoryName, {
+        systemDefaultModel: SYSTEM_DEFAULT_MODEL,
+        availableModels,
+      })
+
+      // #then
+      expect(result).toBeNull()
+    })
+
+    test("blocks requiresModel when availability is empty", () => {
+      // #given
+      const categoryName = "deep"
+      const availableModels = new Set<string>()
+
+      // #when
+      const result = resolveCategoryConfig(categoryName, {
+        systemDefaultModel: SYSTEM_DEFAULT_MODEL,
+        availableModels,
+      })
+
+      // #then
+      expect(result).toBeNull()
+    })
+
    test("returns default model from DEFAULT_CATEGORIES for builtin category", () => {
      // #given
      const categoryName = "visual-engineering"
@@ -1110,7 +1159,7 @@ describe("sisyphus-task", () => {
      const mockClient = {
        app: { agents: async () => ({ data: [] }) },
        config: { get: async () => ({ data: { model: SYSTEM_DEFAULT_MODEL } }) },
-        model: { list: async () => [{ id: "google/gemini-3-pro" }] },
+        model: { list: async () => ({ data: [{ provider: "google", id: "gemini-3-pro" }] }) },
        session: {
          get: async () => ({ data: { directory: "/project" } }),
          create: async () => ({ data: { id: "ses_unstable_gemini" } }),
@@ -1276,6 +1325,13 @@ describe("sisyphus-task", () => {
    test("artistry category (gemini) with run_in_background=false should force background but wait for result", async () => {
      // #given - artistry also uses gemini model
      const { createDelegateTask } = require("./tools")
+      const providerModelsSpy = spyOn(connectedProvidersCache, "readProviderModelsCache").mockReturnValue({
+        connected: ["anthropic", "google", "openai"],
+        updatedAt: new Date().toISOString(),
+        models: {
+          google: ["gemini-3-pro", "gemini-3-flash"],
+        },
+      })
      let launchCalled = false
      
      const mockManager = {
@@ -1294,7 +1350,7 @@ describe("sisyphus-task", () => {
      const mockClient = {
        app: { agents: async () => ({ data: [] }) },
        config: { get: async () => ({ data: { model: SYSTEM_DEFAULT_MODEL } }) },
-        model: { list: async () => [{ id: "google/gemini-3-pro" }] },
+        model: { list: async () => ({ data: [{ provider: "google", id: "gemini-3-pro" }] }) },
        session: {
          get: async () => ({ data: { directory: "/project" } }),
          create: async () => ({ data: { id: "ses_artistry_gemini" } }),
@@ -1336,6 +1392,7 @@ describe("sisyphus-task", () => {
      expect(launchCalled).toBe(true)
      expect(result).toContain("SUPERVISED TASK COMPLETED")
      expect(result).toContain("Artistry result here")
+      providerModelsSpy.mockRestore()
    }, { timeout: 20000 })

    test("writing category (gemini-flash) with run_in_background=false should force background but wait for result", async () => {
@@ -1474,6 +1531,73 @@ describe("sisyphus-task", () => {
    }, { timeout: 20000 })
  })

+  describe("category model resolution fallback", () => {
+    test("category uses resolved.model when connectedProvidersCache is null and availableModels is empty", async () => {
+      // #given - connectedProvidersCache returns null (simulates missing cache file)
+      // This is a regression test for PR #1227 which removed resolved.model from userModel chain
+      cacheSpy.mockReturnValue(null)
+
+      const { createDelegateTask } = require("./tools")
+      let launchInput: any
+
+      const mockManager = {
+        launch: async (input: any) => {
+          launchInput = input
+          return {
+            id: "task-fallback",
+            sessionID: "ses_fallback_test",
+            description: "Fallback test task",
+            agent: "sisyphus-junior",
+            status: "running",
+          }
+        },
+      }
+
+      const mockClient = {
+        app: { agents: async () => ({ data: [] }) },
+        config: { get: async () => ({ data: { model: SYSTEM_DEFAULT_MODEL } }) },
+        model: { list: async () => [] },
+        session: {
+          create: async () => ({ data: { id: "test-session" } }),
+          prompt: async () => ({ data: {} }),
+          messages: async () => ({ data: [] }),
+        },
+      }
+
+      // NO userCategories override, NO sisyphusJuniorModel
+      const tool = createDelegateTask({
+        manager: mockManager,
+        client: mockClient,
+        // userCategories: undefined - use DEFAULT_CATEGORIES only
+        // sisyphusJuniorModel: undefined
+      })
+
+      const toolContext = {
+        sessionID: "parent-session",
+        messageID: "parent-message",
+        agent: "sisyphus",
+        abort: new AbortController().signal,
+      }
+
+      // #when - using "quick" category which should use "anthropic/claude-haiku-4-5"
+      await tool.execute(
+        {
+          description: "Test category fallback",
+          prompt: "Do something quick",
+          category: "quick",
+          run_in_background: true,
+          load_skills: [],
+        },
+        toolContext
+      )
+
+      // #then - model should be anthropic/claude-haiku-4-5 from DEFAULT_CATEGORIES
+      //         NOT anthropic/claude-sonnet-4-5 (system default)
+      expect(launchInput.model.providerID).toBe("anthropic")
+      expect(launchInput.model.modelID).toBe("claude-haiku-4-5")
+    })
+  })
+
  describe("browserProvider propagation", () => {
    test("should resolve agent-browser skill when browserProvider is passed", async () => {
      // #given - delegate_task configured with browserProvider: "agent-browser"
--- a/src/tools/delegate-task/tools.ts
+++ b/src/tools/delegate-task/tools.ts
@@ -12,8 +12,8 @@ import { discoverSkills } from "../../features/opencode-skill-loader"
 import { getTaskToastManager } from "../../features/task-toast-manager"
 import type { ModelFallbackInfo } from "../../features/task-toast-manager/types"
 import { subagentSessions, getSessionAgent } from "../../features/claude-code-session-state"
-import { log, getAgentToolRestrictions, resolveModel, getOpenCodeConfigPaths, findByNameCaseInsensitive, equalsIgnoreCase } from "../../shared"
-import { fetchAvailableModels } from "../../shared/model-availability"
+import { log, getAgentToolRestrictions, resolveModel, getOpenCodeConfigPaths, findByNameCaseInsensitive, equalsIgnoreCase, promptWithModelSuggestionRetry } from "../../shared"
+import { fetchAvailableModels, isModelAvailable } from "../../shared/model-availability"
 import { readConnectedProvidersCache } from "../../shared/connected-providers-cache"
 import { resolveModelWithFallback } from "../../shared/model-resolver"
 import { CATEGORY_MODEL_REQUIREMENTS } from "../../shared/model-requirements"
@@ -117,9 +117,20 @@ export function resolveCategoryConfig(
    userCategories?: CategoriesConfig
    inheritedModel?: string
    systemDefaultModel?: string
+    availableModels?: Set<string>
  }
 ): { config: CategoryConfig; promptAppend: string; model: string | undefined } | null {
-  const { userCategories, inheritedModel, systemDefaultModel } = options
+  const { userCategories, inheritedModel, systemDefaultModel, availableModels } = options
+
+  // Check if category requires a specific model
+  const categoryReq = CATEGORY_MODEL_REQUIREMENTS[categoryName]
+  if (categoryReq?.requiresModel && availableModels) {
+    if (!isModelAvailable(categoryReq.requiresModel, availableModels)) {
+      log(`[resolveCategoryConfig] Category ${categoryName} requires ${categoryReq.requiresModel} but not available`)
+      return null
+    }
+  }
+
  const defaultConfig = DEFAULT_CATEGORIES[categoryName]
  const userConfig = userCategories?.[categoryName]
  const defaultPromptAppend = CATEGORY_PROMPT_APPENDS[categoryName] ?? ""
@@ -522,11 +533,12 @@ To continue this session: session_id="${args.session_id}"`
            connectedProviders: connectedProviders ?? undefined
          })

-         const resolved = resolveCategoryConfig(args.category, {
-           userCategories,
-           inheritedModel,
-           systemDefaultModel,
-         })
+          const resolved = resolveCategoryConfig(args.category, {
+            userCategories,
+            inheritedModel,
+            systemDefaultModel,
+            availableModels,
+          })
         if (!resolved) {
           return `Unknown category: "${args.category}". Available: ${Object.keys({ ...DEFAULT_CATEGORIES, ...userCategories }).join(", ")}`
         }
@@ -541,7 +553,8 @@ To continue this session: session_id="${args.session_id}"`
           }
          } else {
          const resolution = resolveModelWithFallback({
-              userModel: userCategories?.[args.category]?.model ?? sisyphusJuniorModel,
+              userModel: userCategories?.[args.category]?.model,
+              categoryDefaultModel: resolved.model ?? sisyphusJuniorModel,
              fallbackChain: requirement.fallbackChain,
              availableModels,
              systemDefaultModel,
@@ -555,18 +568,19 @@ To continue this session: session_id="${args.session_id}"`
               return `Invalid model format "${actualModel}". Expected "provider/model" format (e.g., "anthropic/claude-sonnet-4-5").`
             }

-             let type: "user-defined" | "inherited" | "category-default" | "system-default"
-             switch (source) {
-                case "override":
-                  type = "user-defined"
-                  break
-                case "provider-fallback":
-                  type = "category-default"
-                  break
-                case "system-default":
-                  type = "system-default"
-                  break
-             }
+              let type: "user-defined" | "inherited" | "category-default" | "system-default"
+              switch (source) {
+                 case "override":
+                   type = "user-defined"
+                   break
+                 case "category-default":
+                 case "provider-fallback":
+                   type = "category-default"
+                   break
+                 case "system-default":
+                   type = "system-default"
+                   break
+              }

             modelInfo = { model: actualModel, type, source }
             
@@ -819,12 +833,6 @@ Create the work plan directly - that's your job as the planning agent.`
          // If we can't fetch agents, proceed anyway - the session.prompt will fail with a clearer error
        }

-        // When using subagent_type directly, inherit parent model so agents don't default
-        // to their hardcoded models (like grok-code) which may not be available
-        if (parentModel) {
-          categoryModel = parentModel
-          modelInfo = { model: `${parentModel.providerID}/${parentModel.modelID}`, type: "inherited" }
-        }
      }

      const systemContent = buildSystemContent({ skillContent, categoryPromptAppend, agentName: agentToUse })
@@ -953,7 +961,7 @@ To continue this session: session_id="${task.sessionID}"`

        try {
          const allowDelegateTask = isPlanAgent(agentToUse)
-          await client.session.prompt({
+          await promptWithModelSuggestionRetry(client, {
            path: { id: sessionID },
            body: {
              agent: agentToUse,
--- a/src/tools/look-at/tools.test.ts
+++ b/src/tools/look-at/tools.test.ts
@@ -146,4 +146,62 @@ describe("look-at tool", () => {
      expect(result).toContain("Network connection failed")
    })
  })
+
+  describe("createLookAt model passthrough", () => {
+    // #given multimodal-looker agent has resolved model info
+    // #when LookAt 도구 실행
+    // #then session.prompt에 model 정보가 전달되어야 함
+    test("passes multimodal-looker model to session.prompt when available", async () => {
+      let promptBody: any
+
+      const mockClient = {
+        app: {
+          agents: async () => ({
+            data: [
+              {
+                name: "multimodal-looker",
+                mode: "subagent",
+                model: { providerID: "google", modelID: "gemini-3-flash" },
+              },
+            ],
+          }),
+        },
+        session: {
+          get: async () => ({ data: { directory: "/project" } }),
+          create: async () => ({ data: { id: "ses_model_passthrough" } }),
+          prompt: async (input: any) => {
+            promptBody = input.body
+            return { data: {} }
+          },
+          messages: async () => ({
+            data: [
+              { info: { role: "assistant", time: { created: 1 } }, parts: [{ type: "text", text: "done" }] },
+            ],
+          }),
+        },
+      }
+
+      const tool = createLookAt({
+        client: mockClient,
+        directory: "/project",
+      } as any)
+
+      const toolContext = {
+        sessionID: "parent-session",
+        messageID: "parent-message",
+        agent: "sisyphus",
+        abort: new AbortController().signal,
+      }
+
+      await tool.execute(
+        { file_path: "/test/file.png", goal: "analyze image" },
+        toolContext
+      )
+
+      expect(promptBody.model).toEqual({
+        providerID: "google",
+        modelID: "gemini-3-flash",
+      })
+    })
+  })
 })
--- a/src/tools/look-at/tools.ts
+++ b/src/tools/look-at/tools.ts
@@ -3,7 +3,7 @@ import { pathToFileURL } from "node:url"
 import { tool, type PluginInput, type ToolDefinition } from "@opencode-ai/plugin"
 import { LOOK_AT_DESCRIPTION, MULTIMODAL_LOOKER_AGENT } from "./constants"
 import type { LookAtArgs } from "./types"
-import { log } from "../../shared/logger"
+import { findByNameCaseInsensitive, log, promptWithModelSuggestionRetry } from "../../shared"

 interface LookAtArgsWithAlias extends LookAtArgs {
  path?: string
@@ -130,9 +130,34 @@ Original error: ${createResult.error}`
      const sessionID = createResult.data.id
      log(`[look_at] Created session: ${sessionID}`)

+      let agentModel: { providerID: string; modelID: string } | undefined
+      let agentVariant: string | undefined
+
+      try {
+        const agentsResult = await ctx.client.app?.agents?.()
+        type AgentInfo = {
+          name: string
+          mode?: "subagent" | "primary" | "all"
+          model?: { providerID: string; modelID: string }
+          variant?: string
+        }
+        const agents = ((agentsResult as { data?: AgentInfo[] })?.data ?? agentsResult) as AgentInfo[] | undefined
+        if (agents?.length) {
+          const matchedAgent = findByNameCaseInsensitive(agents, MULTIMODAL_LOOKER_AGENT)
+          if (matchedAgent?.model) {
+            agentModel = matchedAgent.model
+          }
+          if (matchedAgent?.variant) {
+            agentVariant = matchedAgent.variant
+          }
+        }
+      } catch (error) {
+        log("[look_at] Failed to resolve multimodal-looker model info", error)
+      }
+
      log(`[look_at] Sending prompt with file passthrough to session ${sessionID}`)
      try {
-        await ctx.client.session.prompt({
+        await promptWithModelSuggestionRetry(ctx.client, {
          path: { id: sessionID },
          body: {
            agent: MULTIMODAL_LOOKER_AGENT,
@@ -146,6 +171,8 @@ Original error: ${createResult.error}`
              { type: "text", text: prompt },
              { type: "file", mime: mimeType, url: pathToFileURL(args.file_path).href, filename },
            ],
+            ...(agentModel ? { model: { providerID: agentModel.providerID, modelID: agentModel.modelID } } : {}),
+            ...(agentVariant ? { variant: agentVariant } : {}),
          },
        })
      } catch (promptError) {
--- a/src/tools/lsp/client.ts
+++ b/src/tools/lsp/client.ts
@@ -11,6 +11,7 @@ import {
 } from "vscode-jsonrpc/node"
 import { getLanguageId } from "./config"
 import type { Diagnostic, ResolvedServer } from "./types"
+import { log } from "../../shared/logger"

 interface ManagedClient {
  client: LSPClient
@@ -306,7 +307,7 @@ export class LSPClient {
    })

    this.connection.onError((error) => {
-      console.error("LSP connection error:", error)
+      log("LSP connection error:", error)
    })

    this.connection.listen()
Author	SHA1	Message	Date
github-actions[bot]	c77c9ceb53	release: v3.1.9	2026-01-30 14:15:54 +00:00
YeonGyu-Kim	8c2625cfb0	🏆 test: optimize test suite with FakeTimers and race condition fixes (#1284 ) * fix: exclude prompt/permission from plan agent config plan agent should only inherit model settings from prometheus, not the prompt or permission. This ensures plan agent uses OpenCode's default behavior while only overriding the model. * test(todo-continuation-enforcer): use FakeTimers for 15x faster tests - Add custom FakeTimers implementation (~100 lines) - Replace all real setTimeout waits with fakeTimers.advanceBy() - Test time: 104.6s → 7.01s * test(callback-server): fix race conditions with Promise.all and Bun.fetch - Use Bun.fetch.bind(Bun) to avoid globalThis.fetch mock interference - Use Promise.all pattern for concurrent fetch/waitForCallback - Add Bun.sleep(10) in afterEach for port release * test(concurrency): replace placeholder assertions with getCount checks Replace 6 meaningless expect(true).toBe(true) assertions with actual getCount() verifications for test quality improvement * refactor(config-handler): simplify planDemoteConfig creation Remove unnecessary IIFE and destructuring, use direct spread instead * test(executor): use FakeTimeouts for faster tests - Add custom FakeTimeouts implementation - Replace setTimeout waits with fakeTimeouts.advanceBy() - Test time reduced from ~26s to ~6.8s * test: fix gemini model mock for artistry unstable mode * test: fix model list mock payload shape * test: mock provider models for artistry category --------- Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>	2026-01-30 22:10:52 +09:00
github-actions[bot]	3ced20d1ab	@kunal70006 has signed the CLA in code-yeongyu/oh-my-opencode#1282	2026-01-30 09:56:07 +00:00
github-actions[bot]	fb02cc9e95	@Zacks-Zhang has signed the CLA in code-yeongyu/oh-my-opencode#1280	2026-01-30 08:51:59 +00:00
justsisyphus	80ee52fe3b	fix: improve model resolution with client API fallback and explicit model passing - fetchAvailableModels now falls back to client.model.list() when cache is empty - provider-models cache empty → models.json → client API (3-tier fallback) - look-at tool explicitly passes registered agent's model to session.prompt - Ensures multimodal-looker uses correctly resolved model (e.g., gemini-3-flash-preview) - Add comprehensive tests for fuzzy matching and fallback scenarios	2026-01-30 16:57:21 +09:00
github-actions[bot]	2f7e188cb5	@Hisir0909 has signed the CLA in code-yeongyu/oh-my-opencode#1275	2026-01-30 07:33:44 +00:00
justsisyphus	f8be01c6dd	test: update Atlas fallback test and misc code improvements - Update Atlas fallback test to expect k2p5 as primary (kimi-for-coding) - Minor improvements to connected-providers-cache and utils Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>	2026-01-30 16:19:02 +09:00
justsisyphus	0dbec08923	feat(cli): add kimi-for-coding provider to model fallback - Add kimiForCoding field to ProviderAvailability interface - Add kimi-for-coding provider mapping in isProviderAvailable - Include kimi-for-coding in Sisyphus fallback chain for non-max plan Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>	2026-01-30 16:19:02 +09:00
justsisyphus	691fa8b815	refactor(sisyphus-junior): extract MODE constant and add export - Add AgentMode type import and MODE constant - Export mode on createSisyphusJuniorAgentWithOverrides function Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>	2026-01-30 16:19:02 +09:00
justsisyphus	a73d806d4e	docs: update explore agent model and category descriptions - Change explore agent from Grok Code to Claude Haiku 4.5 - Update deep category description for clarity - Fix Momus fallback chain order Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>	2026-01-30 16:19:02 +09:00
justsisyphus	a424f81cd5	docs: update Sisyphus fallback chain across all documentation Update Sisyphus fallback chain to include gpt-5.2-codex and gemini-3-pro Files: AGENTS.md, README*.md, src/agents/AGENTS.md Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>	2026-01-30 16:19:02 +09:00
justsisyphus	1187a02020	fix: Atlas respects fallbackChain, always refresh provider-models cache - Remove uiSelectedModel from Atlas model resolution (use k2p5 as primary) - Always overwrite provider-models.json on session start to prevent stale cache	2026-01-30 16:19:02 +09:00
Junho Yeo	3074434887	fix: use correct gh api command for starring repo (#1274 ) `gh repo star` is not a valid GitHub CLI command. Use `gh api --silent --method PUT /user/starred/OWNER/REPO` instead.	2026-01-30 15:58:56 +09:00
justsisyphus	6bb2854162	Merge branch 'omo-avail' into dev	2026-01-30 15:28:20 +09:00
justsisyphus	e08904a27a	feat: add artistry category to ultrawork-mode specialist delegation - Add oracle vs artistry distinction in MANDATORY CERTAINTY PROTOCOL - Update WHEN IN DOUBT examples with both delegation options - Add artistry to IF YOU ENCOUNTER A BLOCKER section - Add 'Hard problem (non-conventional)' row to AGENTS UTILIZATION table - Update analyze-mode message with artistry specialist option Oracle: conventional problems (architecture, debugging, complex logic) Artistry: non-conventional problems (different approach needed)	2026-01-30 15:19:38 +09:00
justsisyphus	0188d69233	test: add requiresModel and isModelAvailable tests	2026-01-30 15:11:32 +09:00
justsisyphus	2c74f608f0	feat(delegate-task, agents): check requiresModel for conditional activation	2026-01-30 15:11:27 +09:00
justsisyphus	baefd16b3f	feat(shared): add requiresModel field and isModelAvailable helper	2026-01-30 15:11:19 +09:00
justsisyphus	b1b4578906	feat: add opencode/kimi-k2.5-free fallback and prioritize kimi for atlas	2026-01-30 15:10:38 +09:00
justsisyphus	9d20a5b11c	feat: add kimi-for-coding provider to installer and fix model ID to k2p5	2026-01-30 15:08:26 +09:00
justsisyphus	d2d8d1a782	feat: add kimi-k2.5 to agent fallback chains and update model catalog - sisyphus: opus → kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro - atlas: sonnet-4-5 → kimi-k2.5 → gpt-5.2 → gemini-3-pro - prometheus/metis: opus → kimi-k2.5 → gpt-5.2 → gemini-3-pro - multimodal-looker: gemini-flash → gpt-5.2 → glm-4.6v → kimi-k2.5 → haiku → gpt-5-nano - visual-engineering: remove gpt-5.2 from chain - ultrabrain: reorder to gpt-5.2-codex → gemini-3-pro → opus - Add cross-provider fuzzy match for model resolution - Update all documentation (AGENTS.md, features.md, configurations.md, category-skill-guide.md)	2026-01-30 14:53:50 +09:00
justsisyphus	10bdb6c694	chore: update artistry category description for creative problem-solving	2026-01-30 14:53:50 +09:00
justsisyphus	5f243e2d3a	chore: add glm-4.7 to visual-engineering fallback chain	2026-01-30 14:53:50 +09:00
justsisyphus	82a47ff928	chore: add code style requirements to ultrabrain prompt - MUST search existing codebase for patterns before writing code - MUST match project's existing conventions - MUST write readable, human-friendly code	2026-01-30 14:53:50 +09:00
justsisyphus	c06f38693e	refactor: revamp ultrabrain category with deep work mindset - Add variant: max to ultrabrain's gemini-3-pro fallback entry - Rename STRATEGIC_CATEGORY_PROMPT_APPEND to ULTRABRAIN_CATEGORY_PROMPT_APPEND - Keep original strategic advisor prompt content (no micromanagement instructions) - Update description: use only for genuinely hard tasks, give clear goals only - Update tests to match renamed constant	2026-01-30 14:53:50 +09:00
justsisyphus	6e9cb7ecd8	chore: add variant max to momus opus-4-5 fallback entry	2026-01-30 14:53:50 +09:00
justsisyphus	b731399edf	chore: prioritize gemini-3-pro over opus in oracle fallback chain - Move gemini-3-pro above claude-opus-4-5 in oracle's fallbackChain - Add variant: "max" to gemini-3-pro entry	2026-01-30 14:53:50 +09:00
github-actions[bot]	0a28f6a790	@gabriel-ecegi has signed the CLA in code-yeongyu/oh-my-opencode#1271	2026-01-30 05:13:19 +00:00
justsisyphus	4e529b74e0	revert: remove unnecessary NODE_AUTH_TOKEN from publish.yml (OIDC works)	2026-01-30 13:54:46 +09:00
justsisyphus	90eec0a369	fix: add NODE_AUTH_TOKEN env to main publish workflow	2026-01-30 13:50:55 +09:00
justsisyphus	3b5d18e6bf	fix(agents): exclude subagents from UI model selection override Subagents (explore, librarian, oracle, etc.) now use their own fallback chain instead of inheriting the UI-selected model. This fixes the issue where explore agent was incorrectly using Opus instead of Haiku. - Add AgentMode type and static mode property to AgentFactory - Each agent declares its own mode via factory.mode = MODE pattern - createBuiltinAgents() checks source.mode before passing uiSelectedModel	2026-01-30 13:49:40 +09:00
justsisyphus	67aeb9cb8c	chore: replace big-pickle model with glm-4.7-free	2026-01-30 13:44:04 +09:00
justsisyphus	b1c1f02172	fix: add NODE_AUTH_TOKEN env to publish step	2026-01-30 13:36:20 +09:00
justsisyphus	2b39d119cd	fix: restore registry-url for npm auth with new granular token	2026-01-30 13:21:35 +09:00
justsisyphus	afa2ece847	fix: remove registry-url from setup-node to enable OIDC auth	2026-01-30 13:11:44 +09:00
justsisyphus	390c25197f	fix: manually create .npmrc without token for OIDC setup-node with registry-url injects NODE_AUTH_TOKEN secret which is revoked. Create .npmrc manually with empty _authToken to force OIDC authentication.	2026-01-30 12:57:15 +09:00
justsisyphus	9e07b143df	fix: match main workflow's OIDC setup exactly Main workflow works with registry-url + NPM_CONFIG_PROVENANCE. Removed all extra env vars and debugging - simplify to match working pattern.	2026-01-30 12:52:57 +09:00
justsisyphus	ad95880198	fix(start-work): restore atlas agent and proper model fallback chain - Restore agent: 'atlas' in start-work command (removed by PR #1201) - Fix model-resolver to properly iterate through fallback chain providers - Remove broken parent model inheritance that bypassed fallback logic - Add model-suggestion-retry for runtime API failures (cherry-pick 800846c1) Fixes #1200	2026-01-30 12:52:46 +09:00
justsisyphus	86088d3a6e	fix: remove registry-url to enable npm OIDC auto-detection - Remove registry-url from setup-node (was injecting NODE_AUTH_TOKEN) - Add npm version check and auto-upgrade for OIDC support (11.5.1+) - Add explicit --registry flag to npm publish - Remove empty NODE_AUTH_TOKEN/NPM_CONFIG_USERCONFIG env vars that were breaking OIDC	2026-01-30 12:47:15 +09:00
justsisyphus	ae8a6c5eb8	refactor: replace console.log/warn/error with file-based log() for silent logging Replace all console output with shared logger to write to /tmp/oh-my-opencode.log instead of stdout/stderr. Files changed: - index.ts: console.warn → log() - hook-message-injector/injector.ts: console.warn → log() - lsp/client.ts: console.error → log() - ast-grep/downloader.ts: console.log/error → log() - session-recovery/index.ts: console.error → log() - comment-checker/downloader.ts: console.log/error → log() CLI tools (install.ts, doctor, etc.) retain console output for UX.	2026-01-30 12:45:37 +09:00
justsisyphus	db538c7e6b	fix(ci): override env vars to disable token auth, force OIDC	2026-01-30 12:41:00 +09:00
justsisyphus	dfed2abd3e	fix(ci): also remove NPM_CONFIG_USERCONFIG .npmrc and unset tokens for OIDC	2026-01-30 12:37:12 +09:00
justsisyphus	300a3fdc14	fix(ci): remove .npmrc to enable pure OIDC auth for npm publish	2026-01-30 12:33:51 +09:00
justsisyphus	c993cf007f	fix(ci): remove registry-url to use pure OIDC auth for npm publish	2026-01-30 12:29:33 +09:00
justsisyphus	3d7de0a050	fix(publish-platform): use 7z on Windows, simplify skip logic	2026-01-30 12:25:30 +09:00
justsisyphus	8e19ffdce4	ci(publish-platform): separate build/publish jobs with OIDC provenance - Split into two jobs: build (compile binaries) and publish (npm publish) - Build job uploads compressed artifacts (tar.gz/zip) - Publish job downloads artifacts and uses OIDC Trusted Publishing - Removes NODE_AUTH_TOKEN dependency, uses npm provenance instead - Increased timeout for large binary uploads (40-120MB) - Build parallelism increased to 7 (all platforms simultaneously) - Fixes npm classic token deprecation issue Benefits: - Fresh OIDC token at publish time avoids timeout issues - No token rotation needed (OIDC is ephemeral) - Build failures isolated from publish failures - Artifacts can be reused if publish fails	2026-01-30 12:21:24 +09:00
github-actions[bot]	456d9cea65	release: v3.1.8	2026-01-30 02:58:12 +00:00
justsisyphus	30f893b766	fix(cli/run): fix [undefine] tag and add text preview to verbose log - Fix sessionTag showing '[undefine]' when sessionID is undefined - System events now display as '[system]' instead - Fix message.updated expecting non-existent 'content' field - SDK's EventMessageUpdated only contains info metadata, not content - Content is streamed via message.part.updated events - Add text preview to message.part.updated verbose logging - Update MessageUpdatedProps type to match SDK structure - Update tests to reflect actual SDK behavior	2026-01-30 11:45:58 +09:00
justsisyphus	c905e1cb7a	fix(delegate-task): restore resolved.model to category userModel chain (#1227 ) PR #1227 incorrectly removed resolved.model from the userModel chain, assuming it was bypassing the fallback chain. However, resolved.model contained the category's DEFAULT_CATEGORIES model (e.g., quick -> claude-haiku-4-5), not the main session model. Without resolved.model, when connectedProvidersCache is null and availableModels is empty, category model resolution falls through to systemDefaultModel (opus) instead of using the category's default. This fix restores the original priority: 1. User category model override 2. Category default model (from resolved.model) 3. sisyphusJuniorModel 4. Fallback chain 5. System default	2026-01-30 11:45:19 +09:00
YeonGyu-Kim	d3e2b36e3d	refactor(tmux-subagent): introduce dependency injection for testability (#1267 ) Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>	2026-01-30 10:59:54 +09:00
YeonGyu-Kim	5f0b6d49f5	fix(run): prevent premature exit on idle before meaningful work (#1263 ) The run command's completion check had a race condition: when a session transitions busy->idle before the LLM generates any output (empty response or API delay), checkCompletionConditions() returns true because 0 incomplete todos + 0 busy children = complete. This caused the runner to exit with 'All tasks completed' before any work was done. Fix: - Add hasReceivedMeaningfulWork flag to EventState - Set flag on: assistant text content, tool execution, or message update with actual content (all scoped to main session only) - Guard completion check in runner poll loop: skip if no meaningful work has been observed yet This ensures the runner waits until the session has produced at least one observable output before considering completion conditions. Adds 6 new test cases covering the race condition scenarios.	2026-01-30 09:10:24 +09:00
github-actions[bot]	b45408dd9c	@LeekJay has signed the CLA in code-yeongyu/oh-my-opencode#1254	2026-01-29 17:03:39 +00:00