fix: convert executeSyncTask to async prompt + polling pattern

Oracle agent (and all sync subagent tasks) fails with JSON Parse error in ACP environments because session.prompt() (blocking HTTP) returns empty/incomplete responses. Replace promptSyncWithModelSuggestionRetry with promptWithModelSuggestionRetry (async, fire-and-forget) and add polling loop to wait for response stability, matching the proven pattern from executeUnstableAgentTask. Fixes #1681
2026-02-09 10:03:54 +09:00
670 changed files with 21898 additions and 35442 deletions
--- a/.github/assets/elestyle.jpg
+++ b/.github/assets/elestyle.jpg
--- a/.github/workflows/cla.yml
+++ b/.github/workflows/cla.yml
@@ -25,7 +25,7 @@ jobs:
          path-to-signatures: 'signatures/cla.json'
          path-to-document: 'https://github.com/code-yeongyu/oh-my-opencode/blob/master/CLA.md'
          branch: 'dev'
-          allowlist: code-yeongyu,bot*,dependabot*,github-actions*,*[bot],sisyphus-dev-ai,web-flow
+          allowlist: code-yeongyu,bot*,dependabot*,github-actions*,*[bot],sisyphus-dev-ai
          custom-notsigned-prcomment: |
            Thank you for your contribution! Before we can merge this PR, we need you to sign our [Contributor License Agreement (CLA)](https://github.com/code-yeongyu/oh-my-opencode/blob/master/CLA.md).
            
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -1,7 +1,7 @@
 # PROJECT KNOWLEDGE BASE

-**Generated:** 2026-02-10T14:44:00+09:00
-**Commit:** b538806d
+**Generated:** 2026-02-08T16:45:00+09:00
+**Commit:** edee865f
 **Branch:** dev

 ---
@@ -27,14 +27,12 @@ feature branches (your work)
 | **ALL PRs → `dev`** | Every pull request MUST target the `dev` branch |
 | **NEVER PR → `master`** | PRs to `master` are **automatically rejected** by CI |
 | **"Create a PR" = target `dev`** | When asked to create a new PR, it ALWAYS means targeting `dev` |
-| **Merge commit ONLY** | Squash merge is **disabled** in this repo. Always use merge commit when merging PRs. |

 ### Why This Matters

 - `master` = production/published npm package
 - `dev` = integration branch where features are merged and tested
 - Feature branches → `dev` → (after testing) → `master`
- Squash merge is disabled at the repository level — attempting it will fail

 **If you create a PR targeting `master`, it WILL be rejected. No exceptions.**

@@ -77,6 +75,11 @@ Oh-My-OpenCode is a **plugin for OpenCode**. You will frequently need to examine
 | Debugging plugin issues | Fire `librarian` to find relevant OpenCode internals |
 | Answering "how does OpenCode do X?" | Fire `librarian` FIRST |

+**The `librarian` agent is specialized for:**
+- Searching remote codebases (GitHub)
+- Retrieving official documentation
+- Finding implementation examples in open source
+
 **DO NOT guess or hallucinate about OpenCode internals.** Always verify by examining actual source code via `librarian` or direct clone.

 ---
@@ -87,6 +90,8 @@ Oh-My-OpenCode is a **plugin for OpenCode**. You will frequently need to examine

 ### All Project Communications MUST Be in English

+This is an **international open-source project**. To ensure accessibility and maintainability:
+
 | Context | Language Requirement |
 |---------|---------------------|
 | **GitHub Issues** | English ONLY |
@@ -96,74 +101,64 @@ Oh-My-OpenCode is a **plugin for OpenCode**. You will frequently need to examine
 | **Documentation** | English ONLY |
 | **AGENTS.md files** | English ONLY |

-**If you're not comfortable writing in English, use translation tools. Broken English is fine. Non-English is not acceptable.**
+### Why This Matters
+
+- **Global Collaboration**: Contributors from all countries can participate
+- **Searchability**: English keywords are universally searchable
+- **AI Agent Compatibility**: AI tools work best with English content
+- **Consistency**: Mixed languages create confusion and fragmentation
+
+### Enforcement
+
+- Issues/PRs with non-English content may be closed with a request to resubmit in English
+- Commit messages must be in English - CI may reject non-English commits
+- Translated READMEs exist (README.ko.md, README.ja.md, etc.) but the primary docs are English
+
+**If you're not comfortable writing in English, use translation tools. Broken English is fine - we'll help fix it. Non-English is not acceptable.**

 ---

 ## OVERVIEW

-OpenCode plugin (v3.4.0): multi-model agent orchestration with 11 specialized agents (Claude Opus 4.6, GPT-5.3 Codex, Gemini 3 Flash, GLM-4.7, Grok). 41 lifecycle hooks across 7 event types, 25+ tools (LSP, AST-Grep, delegation, task management), full Claude Code compatibility layer. "oh-my-zsh" for OpenCode.
+OpenCode plugin: multi-model agent orchestration (Claude Opus 4.6, GPT-5.3 Codex, Gemini 3 Flash). 40+ lifecycle hooks, 25+ tools (LSP, AST-Grep, delegation), 11 specialized agents, full Claude Code compatibility. "oh-my-zsh" for OpenCode.

 ## STRUCTURE

 ```
 oh-my-opencode/
 ├── src/
-│   ├── agents/              # 11 AI agents - see src/agents/AGENTS.md
-│   ├── hooks/               # 41 lifecycle hooks - see src/hooks/AGENTS.md
-│   ├── tools/               # 25+ tools - see src/tools/AGENTS.md
-│   ├── features/            # Background agents, skills, CC compat - see src/features/AGENTS.md
-│   ├── shared/              # 84 cross-cutting utilities - see src/shared/AGENTS.md
-│   ├── cli/                 # CLI installer, doctor - see src/cli/AGENTS.md
-│   ├── mcp/                 # Built-in MCPs - see src/mcp/AGENTS.md
-│   ├── config/              # Zod schema - see src/config/AGENTS.md
-│   ├── plugin-handlers/     # Config loading - see src/plugin-handlers/AGENTS.md
-│   ├── plugin/              # Plugin interface composition (21 files)
-│   ├── index.ts             # Main plugin entry (88 lines)
-│   ├── create-hooks.ts      # Hook creation coordination (62 lines)
-│   ├── create-managers.ts   # Manager initialization (80 lines)
-│   ├── create-tools.ts      # Tool registry composition (54 lines)
-│   ├── plugin-interface.ts  # Plugin interface assembly (66 lines)
-│   ├── plugin-config.ts     # Config loading orchestration
-│   └── plugin-state.ts      # Model cache state
-├── script/                  # build-schema.ts, build-binaries.ts, publish.ts, generate-changelog.ts
-├── packages/                # 7 platform-specific binary packages
-└── dist/                    # Build output (ESM + .d.ts)
-```
-
-## INITIALIZATION FLOW
-
-```
-OhMyOpenCodePlugin(ctx)
-  1. injectServerAuthIntoClient(ctx.client)
-  2. startTmuxCheck()
-  3. loadPluginConfig(ctx.directory, ctx)      → OhMyOpenCodeConfig
-  4. createFirstMessageVariantGate()
-  5. createModelCacheState()
-  6. createManagers(ctx, config, tmux, cache)  → TmuxSessionManager, BackgroundManager, SkillMcpManager, ConfigHandler
-  7. createTools(ctx, config, managers)         → filteredTools, mergedSkills, availableSkills, availableCategories
-  8. createHooks(ctx, config, backgroundMgr)   → 41 hooks (core + continuation + skill)
-  9. createPluginInterface(...)                 → tool, chat.params, chat.message, event, tool.execute.before/after
- 10. Return plugin with experimental.session.compacting
+│   ├── agents/           # 11 AI agents - see src/agents/AGENTS.md
+│   ├── hooks/            # 40+ lifecycle hooks - see src/hooks/AGENTS.md
+│   ├── tools/            # 25+ tools - see src/tools/AGENTS.md
+│   ├── features/         # Background agents, skills, Claude Code compat - see src/features/AGENTS.md
+│   ├── shared/           # 66 cross-cutting utilities - see src/shared/AGENTS.md
+│   ├── cli/              # CLI installer, doctor - see src/cli/AGENTS.md
+│   ├── mcp/              # Built-in MCPs - see src/mcp/AGENTS.md
+│   ├── config/           # Zod schema (schema.ts 455 lines), TypeScript types
+│   ├── plugin-handlers/  # Plugin config loading (config-handler.ts 562 lines)
+│   ├── index.ts          # Main plugin entry (999 lines)
+│   ├── plugin-config.ts  # Config loading orchestration
+│   └── plugin-state.ts   # Model cache state
+├── script/               # build-schema.ts, build-binaries.ts, publish.ts
+├── packages/             # 11 platform-specific binaries
+└── dist/                 # Build output (ESM + .d.ts)
 ```

 ## WHERE TO LOOK

 | Task | Location | Notes |
 |------|----------|-------|
-| Add agent | `src/agents/` | Create .ts with factory, add to `agentSources` in builtin-agents/ |
-| Add hook | `src/hooks/` | Create dir, register in `src/plugin/hooks/create-*-hooks.ts` |
+| Add agent | `src/agents/` | Create .ts with factory, add to `agentSources` in utils.ts |
+| Add hook | `src/hooks/` | Create dir with `createXXXHook()`, register in index.ts |
 | Add tool | `src/tools/` | Dir with index/types/constants/tools.ts |
 | Add MCP | `src/mcp/` | Create config, add to `createBuiltinMcps()` |
-| Add skill | `src/features/builtin-skills/` | Create .ts in skills/ |
+| Add skill | `src/features/builtin-skills/` | Create dir with SKILL.md |
 | Add command | `src/features/builtin-commands/` | Add template + register in commands.ts |
-| Config schema | `src/config/schema/` | 21 schema component files, run `bun run build:schema` |
+| Config schema | `src/config/schema.ts` | Zod schema, run `bun run build:schema` |
 | Plugin config | `src/plugin-handlers/config-handler.ts` | JSONC loading, merging, migration |
-| Background agents | `src/features/background-agent/` | manager.ts (1646 lines) |
-| Orchestrator | `src/hooks/atlas/` | Main orchestration hook (1976 lines) |
-| Delegation | `src/tools/delegate-task/` | Category routing (constants.ts 569 lines) |
-| Task system | `src/features/claude-tasks/` | Task schema, storage, todo sync |
-| Plugin interface | `src/plugin/` | 21 files composing hooks, handlers, registries |
+| Background agents | `src/features/background-agent/` | manager.ts (1556 lines) |
+| Orchestrator | `src/hooks/atlas/` | Main orchestration hook (770 lines) |
+| Delegation | `src/tools/delegate-task/` | Category routing (executor.ts 983 lines) |

 ## TDD (Test-Driven Development)

@@ -175,7 +170,7 @@ OhMyOpenCodePlugin(ctx)
 **Rules:**
 - NEVER write implementation before test
 - NEVER delete failing tests - fix the code
- Test file: `*.test.ts` alongside source (176 test files)
+- Test file: `*.test.ts` alongside source (163 test files)
 - BDD comments: `//#given`, `//#when`, `//#then`

 ## CONVENTIONS
@@ -185,9 +180,8 @@ OhMyOpenCodePlugin(ctx)
 - **Build**: `bun build` (ESM) + `tsc --emitDeclarationOnly`
 - **Exports**: Barrel pattern via index.ts
 - **Naming**: kebab-case dirs, `createXXXHook`/`createXXXTool` factories
- **Testing**: BDD comments, 176 test files, 117k+ lines TypeScript
+- **Testing**: BDD comments, 163 test files
 - **Temperature**: 0.1 for code agents, max 0.3
- **Modular architecture**: 200 LOC hard limit per file (prompt strings exempt)

 ## ANTI-PATTERNS

@@ -210,57 +204,22 @@ OhMyOpenCodePlugin(ctx)
 | Git | Skip hooks (--no-verify), force push without request |
 | Bash | `sleep N` - use conditional waits |
 | Bash | `cd dir && cmd` - use workdir parameter |
-| Files | Catch-all utils.ts/helpers.ts - name by purpose |

 ## AGENT MODELS

-| Agent | Model | Temp | Purpose |
-|-------|-------|------|---------|
-| Sisyphus | anthropic/claude-opus-4-6 | 0.1 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.3-codex → gemini-3-pro) |
-| Hephaestus | openai/gpt-5.3-codex | 0.1 | Autonomous deep worker (NO fallback) |
-| Atlas | anthropic/claude-sonnet-4-5 | 0.1 | Master orchestrator (fallback: kimi-k2.5 → gpt-5.2) |
-| Prometheus | anthropic/claude-opus-4-6 | 0.1 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
-| oracle | openai/gpt-5.2 | 0.1 | Consultation, debugging (fallback: claude-opus-4-6) |
-| librarian | zai-coding-plan/glm-4.7 | 0.1 | Docs, GitHub search (fallback: glm-4.7-free) |
-| explore | xai/grok-code-fast-1 | 0.1 | Fast codebase grep (fallback: claude-haiku-4-5 → gpt-5-mini → gpt-5-nano) |
-| multimodal-looker | google/gemini-3-flash | 0.1 | PDF/image analysis |
-| Metis | anthropic/claude-opus-4-6 | 0.3 | Pre-planning analysis (fallback: kimi-k2.5 → gpt-5.2) |
-| Momus | openai/gpt-5.2 | 0.1 | Plan validation (fallback: claude-opus-4-6) |
-| Sisyphus-Junior | anthropic/claude-sonnet-4-5 | 0.1 | Category-spawned executor |
-
-## OPENCODE PLUGIN API
-
-Plugin SDK from `@opencode-ai/plugin` (v1.1.19). Plugin = `async (PluginInput) => Hooks`.
-
-| Hook | Purpose |
-|------|---------|
-| `tool` | Register custom tools (Record<string, ToolDefinition>) |
-| `chat.message` | Intercept user messages (can modify parts) |
-| `chat.params` | Modify LLM parameters (temperature, topP, options) |
-| `tool.execute.before` | Pre-tool interception (can modify args) |
-| `tool.execute.after` | Post-tool processing (can modify output) |
-| `event` | Session lifecycle events (session.created, session.stop, etc.) |
-| `config` | Config modification (register agents, MCPs, commands) |
-| `experimental.chat.messages.transform` | Transform message history |
-| `experimental.session.compacting` | Session compaction customization |
-
-## DEPENDENCIES
-
-| Package | Purpose |
-|---------|---------|
-| `@opencode-ai/plugin` + `sdk` | OpenCode integration SDK |
-| `@ast-grep/cli` + `napi` | AST pattern matching (search/replace) |
-| `@code-yeongyu/comment-checker` | AI comment detection/prevention |
-| `@modelcontextprotocol/sdk` | MCP client for remote HTTP servers |
-| `@clack/prompts` | Interactive CLI TUI |
-| `commander` | CLI argument parsing |
-| `zod` (v4) | Schema validation for config |
-| `jsonc-parser` | JSONC config with comments |
-| `picocolors` | Terminal colors |
-| `picomatch` | Glob pattern matching |
-| `vscode-jsonrpc` | LSP communication |
-| `js-yaml` | YAML parsing (tasks, skills) |
-| `detect-libc` | Platform binary selection |
+| Agent | Model | Purpose |
+|-------|-------|---------|
+| Sisyphus | anthropic/claude-opus-4-6 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.3-codex → gemini-3-pro) |
+| Hephaestus | openai/gpt-5.3-codex | Autonomous deep worker, "The Legitimate Craftsman" (requires gpt-5.3-codex, no fallback) |
+| Atlas | anthropic/claude-sonnet-4-5 | Master orchestrator (fallback: kimi-k2.5 → gpt-5.2) |
+| oracle | openai/gpt-5.2 | Consultation, debugging |
+| librarian | zai-coding-plan/glm-4.7 | Docs, GitHub search (fallback: glm-4.7-free) |
+| explore | xai/grok-code-fast-1 | Fast codebase grep (fallback: claude-haiku-4-5 → gpt-5-mini → gpt-5-nano) |
+| multimodal-looker | google/gemini-3-flash | PDF/image analysis |
+| Prometheus | anthropic/claude-opus-4-6 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
+| Metis | anthropic/claude-opus-4-6 | Pre-planning analysis (temp 0.3, fallback: kimi-k2.5 → gpt-5.2) |
+| Momus | openai/gpt-5.2 | Plan validation (temp 0.1, fallback: claude-opus-4-6) |
+| Sisyphus-Junior | anthropic/claude-sonnet-4-5 | Category-spawned executor (temp 0.1) |

 ## COMMANDS

@@ -268,8 +227,7 @@ Plugin SDK from `@opencode-ai/plugin` (v1.1.19). Plugin = `async (PluginInput) =
 bun run typecheck      # Type check
 bun run build          # ESM + declarations + schema
 bun run rebuild        # Clean + Build
-bun test               # 176 test files
-bun run build:schema   # Regenerate JSON schema
+bun test               # 100+ test files
 ```

 ## DEPLOYMENT
@@ -283,38 +241,41 @@ bun run build:schema   # Regenerate JSON schema

 | File | Lines | Description |
 |------|-------|-------------|
-| `src/features/background-agent/manager.ts` | 1646 | Task lifecycle, concurrency |
-| `src/hooks/anthropic-context-window-limit-recovery/` | 2232 | Multi-strategy context recovery |
-| `src/hooks/claude-code-hooks/` | 2110 | Claude Code settings.json compat |
-| `src/hooks/todo-continuation-enforcer/` | 2061 | Core boulder mechanism |
-| `src/hooks/atlas/` | 1976 | Session orchestration |
-| `src/hooks/ralph-loop/` | 1687 | Self-referential dev loop |
-| `src/hooks/keyword-detector/` | 1665 | Mode detection (ultrawork/search) |
-| `src/hooks/rules-injector/` | 1604 | Conditional rules injection |
-| `src/hooks/think-mode/` | 1365 | Model/variant switching |
-| `src/hooks/session-recovery/` | 1279 | Auto error recovery |
-| `src/features/builtin-skills/skills/git-master.ts` | 1111 | Git master skill |
-| `src/tools/delegate-task/constants.ts` | 569 | Category routing configs |
+| `src/features/background-agent/manager.ts` | 1642 | Task lifecycle, concurrency |
+| `src/features/builtin-skills/skills/git-master.ts` | 1107 | Git master skill definition |
+| `src/index.ts` | 999 | Main plugin entry |
+| `src/tools/delegate-task/executor.ts` | 969 | Category-based delegation executor |
+| `src/tools/lsp/client.ts` | 851 | LSP client operations |
+| `src/tools/background-task/tools.ts` | 757 | Background task tools |
+| `src/hooks/atlas/index.ts` | 697 | Orchestrator hook |
+| `src/cli/config-manager.ts` | 667 | JSONC config parsing |
+| `src/features/skill-mcp-manager/manager.ts` | 640 | MCP client lifecycle |
+| `src/features/builtin-commands/templates/refactor.ts` | 619 | Refactor command template |
+| `src/agents/hephaestus.ts` | 618 | Autonomous deep worker agent |
+| `src/agents/utils.ts` | 571 | Agent creation, model fallback resolution |
+| `src/plugin-handlers/config-handler.ts` | 562 | Plugin config loading |
+| `src/tools/delegate-task/constants.ts` | 552 | Delegation constants |
+| `src/cli/install.ts` | 542 | Interactive CLI installer |
+| `src/hooks/task-continuation-enforcer.ts` | 530 | Task completion enforcement |
+| `src/agents/sisyphus.ts` | 530 | Main orchestrator agent |

 ## MCP ARCHITECTURE

 Three-tier system:
-1. **Built-in** (src/mcp/): websearch (Exa/Tavily), context7 (docs), grep_app (GitHub)
-2. **Claude Code compat** (features/claude-code-mcp-loader/): .mcp.json with `${VAR}` expansion
-3. **Skill-embedded** (features/opencode-skill-loader/): YAML frontmatter in SKILL.md
+1. **Built-in**: websearch (Exa/Tavily), context7 (docs), grep_app (GitHub)
+2. **Claude Code compat**: .mcp.json with `${VAR}` expansion
+3. **Skill-embedded**: YAML frontmatter in skills

 ## CONFIG SYSTEM

- **Zod validation**: 21 schema component files in `src/config/schema/`
+- **Zod validation**: `src/config/schema.ts` (455 lines)
 - **JSONC support**: Comments, trailing commas
- **Multi-level**: Project (`.opencode/`) → User (`~/.config/opencode/`) → Defaults
- **Migration**: Legacy config auto-migration in `src/shared/migration/`
+- **Multi-level**: Project (`.opencode/`) → User (`~/.config/opencode/`)
+- **Loading**: `src/plugin-handlers/config-handler.ts` → merge → validate

 ## NOTES

 - **OpenCode**: Requires >= 1.0.150
- **1069 TypeScript files**, 176 test files, 117k+ lines
 - **Flaky tests**: ralph-loop (CI timeout), session-state (parallel pollution)
 - **Trusted deps**: @ast-grep/cli, @ast-grep/napi, @code-yeongyu/comment-checker
 - **No linter/formatter**: No ESLint, Prettier, or Biome configured
- **License**: SUL-1.0 (Sisyphus Use License)
--- a/README.ja.md
+++ b/README.ja.md
@@ -370,8 +370,6 @@ OpenCode が Debian / ArchLinux だとしたら、Oh My OpenCode は Ubuntu / [O
  - Making Spray - influencer marketing solution, vovushop - crossborder commerce platform, vreview - ai commerce review marketing solution
 - [Google](https://google.com)
 - [Microsoft](https://microsoft.com)
- [ELESTYLE](https://elestyle.jp)
-  - elepay - マルチモバイル決済ゲートウェイ、OneQR - キャッシュレスソリューション向けモバイルアプリケーションSaaS

 ## スポンサー
 - **Numman Ali** [GitHub](https://github.com/numman-ali) [X](https://x.com/nummanali)
--- a/README.ko.md
+++ b/README.ko.md
@@ -379,7 +379,5 @@ OpenCode가 Debian/Arch라면 Oh My OpenCode는 Ubuntu/[Omarchy](https://omarchy
  - Spray(인플루언서 마케팅 솔루션), vovushop(국가 간 상거래 플랫폼), vreview(AI 상거래 리뷰 마케팅 솔루션) 제작
 - [Google](https://google.com)
 - [Microsoft](https://microsoft.com)
- [ELESTYLE](https://elestyle.jp)
-  - elepay - 멀티 모바일 결제 게이트웨이, OneQR - 캐시리스 솔루션용 모바일 애플리케이션 SaaS

 *이 놀라운 히어로 이미지에 대해 [@junhoyeo](https://github.com/junhoyeo)에게 특별히 감사드립니다.*
--- a/README.md
+++ b/README.md
@@ -378,7 +378,5 @@ I have no affiliation with any project or model mentioned here. This is purely p
  - Making Spray - influencer marketing solution, vovushop - crossborder commerce platform, vreview - ai commerce review marketing solution
 - [Google](https://google.com)
 - [Microsoft](https://microsoft.com)
- [ELESTYLE](https://elestyle.jp)
-  - Making elepay - multi-mobile payment gateway, OneQR - mobile application SaaS for cashless solutions

 *Special thanks to [@junhoyeo](https://github.com/junhoyeo) for this amazing hero image.*
--- a/README.zh-cn.md
+++ b/README.zh-cn.md
@@ -376,8 +376,6 @@ curl -s https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/refs/heads
  - 制作 Spray - 网红营销解决方案、vovushop - 跨境电商平台、vreview - AI 电商评论营销解决方案
 - [Google](https://google.com)
 - [Microsoft](https://microsoft.com)
- [ELESTYLE](https://elestyle.jp)
-  - elepay - 多渠道移动支付网关、OneQR - 无现金解决方案移动应用 SaaS

 ## 赞助商
 - **Numman Ali** [GitHub](https://github.com/numman-ali) [X](https://x.com/nummanali)
--- a/bun.lock
+++ b/bun.lock
@@ -28,13 +28,13 @@
        "typescript": "^5.7.3",
      },
      "optionalDependencies": {
-        "oh-my-opencode-darwin-arm64": "3.5.1",
-        "oh-my-opencode-darwin-x64": "3.5.1",
-        "oh-my-opencode-linux-arm64": "3.5.1",
-        "oh-my-opencode-linux-arm64-musl": "3.5.1",
-        "oh-my-opencode-linux-x64": "3.5.1",
-        "oh-my-opencode-linux-x64-musl": "3.5.1",
-        "oh-my-opencode-windows-x64": "3.5.1",
+        "oh-my-opencode-darwin-arm64": "3.3.1",
+        "oh-my-opencode-darwin-x64": "3.3.1",
+        "oh-my-opencode-linux-arm64": "3.3.1",
+        "oh-my-opencode-linux-arm64-musl": "3.3.1",
+        "oh-my-opencode-linux-x64": "3.3.1",
+        "oh-my-opencode-linux-x64-musl": "3.3.1",
+        "oh-my-opencode-windows-x64": "3.3.1",
      },
    },
  },
@@ -226,19 +226,19 @@

    "object-inspect": ["object-inspect@1.13.4", "", {}, "sha512-W67iLl4J2EXEGTbfeHCffrjDfitvLANg0UlX3wFUUSTx92KXRFegMHUVgSqE+wvhAbi4WqjGg9czysTV2Epbew=="],

-    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.5.1", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-oH+c/+Z/ULIK+8T1jQFpzISHsvQPyYJfA6bceiD9sgFy1OY1NjRh4a3sFk8cXy6uRVKpivWDFOfbVTcZ2kbKWA=="],
+    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.3.1", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-R+o42Km6bsIaW6D3I8uu2HCF3BjIWqa/fg38W5y4hJEOw4mL0Q7uV4R+0vtrXRHo9crXTK9ag0fqVQUm+Y6iAQ=="],

-    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.5.1", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-wnBYQ9BZBLbzgSNIJZOIJS03zf+b4trAQeYmG+yCLn8y7FWXqw1KmjJ88/bbMXTuZ4RSMKWpXb1Afgdsred+DQ=="],
+    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.3.1", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-7VTbpR1vH3OEkoJxBKtYuxFPX8M3IbJKoeHWME9iK6FpT11W1ASsjyuhvzB1jcxSeqF8ddMnjitlG5ub6h5EVw=="],

-    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.5.1", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-19KNJex1LeU/S14IsJbumOvZa9O6F7X4BLIY7MfjtHtTk0dRFL+tbbXmlafecBMigEKlLdJ+HTW3TnQgp7Ih8A=="],
+    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.3.1", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-BZ/r/CFlvbOxkdZZrRoT16xFOjibRZHuwQnaE4f0JvOzgK6/HWp3zJI1+2/aX/oK5GA6lZxNWRrJC/SKUi8LEg=="],

-    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.5.1", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-mCCnym3nBTJP+xzK+AS4YPFQiT2sZWmjhOhOy7PjNY6Is4jkfT1C2e9ZrIU/2VoVLV6V5q7hQGh1jgleU+FxwQ=="],
+    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.3.1", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-U90Wruf21h+CJbtcrS7MeTAc/5VOF6RI+5jr7qj/cCxjXNJtjhyJdz/maehArjtgf304+lYCM/Mh1i+G2D3YFQ=="],

-    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.5.1", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-sDYt4adNuwb+p1RzHb7IR9zvbAnYYgZofjPvceirBorffp63f+aypYFxjFpfmbT87o/Eb/Hgzm4sHliJtd1UmQ=="],
+    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.3.1", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-sYzohSNdwsAhivbXcbhPdF1qqQi2CCI7FSgbmvvfBOMyZ8HAgqOFqYW2r3GPdmtywzkjOTvCzTG56FZwEjx15w=="],

-    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.5.1", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-tz/0QSS5AKIiKj6cMom5VQSnEYpMIP/SRTaP5WYNOYhnUkXMwXEncQ7FIcj2vovMCXuqA9a8ujVY0zTs7TeALw=="],
+    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.3.1", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-aG5pZ4eWS0YSGUicOnjMkUPrIqQV4poYF+d9SIvrfvlaMcK6WlQn7jXzgNCwJsfGn5lyhSmjshZBEU+v79Ua3w=="],

-    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.5.1", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-zfpRS6HIkSwE8btajJzSYxhqsE5kDkop896/XGS3LLIAAZt0RtCmT3C1plxVfI9oAABfgcaiveCxJ5f9AlKPcQ=="],
+    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.3.1", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-FGH7cnzBqNwjSkzCDglMsVttaq+MsykAxa7ehaFK+0dnBZArvllS3W13a3dGaANHMZzfK0vz8hNDUdVi7Z63cA=="],

    "on-finished": ["on-finished@2.4.1", "", { "dependencies": { "ee-first": "1.1.1" } }, "sha512-oVlzkg3ENAhCk2zdv7IJwd/QUD4z2RxRwpkcGY8psCVcCYZNq4wYnVWALHM+brtuJjePWiYF/ClmuDr8Ch5+kg=="],

--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
  "name": "oh-my-opencode",
-  "version": "3.5.1",
+  "version": "3.4.0",
  "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": "3.5.1",
-    "oh-my-opencode-darwin-x64": "3.5.1",
-    "oh-my-opencode-linux-arm64": "3.5.1",
-    "oh-my-opencode-linux-arm64-musl": "3.5.1",
-    "oh-my-opencode-linux-x64": "3.5.1",
-    "oh-my-opencode-linux-x64-musl": "3.5.1",
-    "oh-my-opencode-windows-x64": "3.5.1"
+    "oh-my-opencode-darwin-arm64": "3.4.0",
+    "oh-my-opencode-darwin-x64": "3.4.0",
+    "oh-my-opencode-linux-arm64": "3.4.0",
+    "oh-my-opencode-linux-arm64-musl": "3.4.0",
+    "oh-my-opencode-linux-x64": "3.4.0",
+    "oh-my-opencode-linux-x64-musl": "3.4.0",
+    "oh-my-opencode-windows-x64": "3.4.0"
  },
  "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": "3.5.1",
+  "version": "3.4.0",
  "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": "3.5.1",
+  "version": "3.4.0",
  "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": "3.5.1",
+  "version": "3.4.0",
  "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": "3.5.1",
+  "version": "3.4.0",
  "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": "3.5.1",
+  "version": "3.4.0",
  "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": "3.5.1",
+  "version": "3.4.0",
  "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": "3.5.1",
+  "version": "3.4.0",
  "description": "Platform-specific binary for oh-my-opencode (windows-x64)",
  "license": "MIT",
  "repository": {
--- a/signatures/cla.json
+++ b/signatures/cla.json
@@ -1263,102 +1263,6 @@
      "created_at": "2026-02-08T21:41:35Z",
      "repoId": 1108837393,
      "pullRequestNo": 1680
-    },
-    {
-      "name": "nianyi778",
-      "id": 23355645,
-      "comment_id": 3874840250,
-      "created_at": "2026-02-10T01:41:08Z",
-      "repoId": 1108837393,
-      "pullRequestNo": 1703
-    },
-    {
-      "name": "lxia1220",
-      "id": 43934024,
-      "comment_id": 3875675071,
-      "created_at": "2026-02-10T06:43:35Z",
-      "repoId": 1108837393,
-      "pullRequestNo": 1713
-    },
-    {
-      "name": "cyberprophet",
-      "id": 48705422,
-      "comment_id": 3877193956,
-      "created_at": "2026-02-10T12:06:03Z",
-      "repoId": 1108837393,
-      "pullRequestNo": 1717
-    },
-    {
-      "name": "materializerx",
-      "id": 96932157,
-      "comment_id": 3878329143,
-      "created_at": "2026-02-10T15:07:38Z",
-      "repoId": 1108837393,
-      "pullRequestNo": 1724
-    },
-    {
-      "name": "materializerx",
-      "id": 96932157,
-      "comment_id": 3878458939,
-      "created_at": "2026-02-10T15:21:04Z",
-      "repoId": 1108837393,
-      "pullRequestNo": 1724
-    },
-    {
-      "name": "RobertWsp",
-      "id": 67512895,
-      "comment_id": 3878518426,
-      "created_at": "2026-02-10T15:27:01Z",
-      "repoId": 1108837393,
-      "pullRequestNo": 1723
-    },
-    {
-      "name": "RobertWsp",
-      "id": 67512895,
-      "comment_id": 3878575833,
-      "created_at": "2026-02-10T15:32:31Z",
-      "repoId": 1108837393,
-      "pullRequestNo": 1723
-    },
-    {
-      "name": "sjawhar",
-      "id": 5074378,
-      "comment_id": 3879746658,
-      "created_at": "2026-02-10T17:43:47Z",
-      "repoId": 1108837393,
-      "pullRequestNo": 1727
-    },
-    {
-      "name": "marlon-costa-dc",
-      "id": 128386606,
-      "comment_id": 3879827362,
-      "created_at": "2026-02-10T17:59:06Z",
-      "repoId": 1108837393,
-      "pullRequestNo": 1726
-    },
-    {
-      "name": "marlon-costa-dc",
-      "id": 128386606,
-      "comment_id": 3879847814,
-      "created_at": "2026-02-10T18:03:41Z",
-      "repoId": 1108837393,
-      "pullRequestNo": 1726
-    },
-    {
-      "name": "danpung2",
-      "id": 75434746,
-      "comment_id": 3881834946,
-      "created_at": "2026-02-11T02:52:34Z",
-      "repoId": 1108837393,
-      "pullRequestNo": 1741
-    },
-    {
-      "name": "ojh102",
-      "id": 14901903,
-      "comment_id": 3882254163,
-      "created_at": "2026-02-11T05:29:51Z",
-      "repoId": 1108837393,
-      "pullRequestNo": 1750
    }
  ]
 }
--- a/src/AGENTS.md
+++ b/src/AGENTS.md
@@ -1,80 +1,128 @@
-# SRC KNOWLEDGE BASE
+# AGENTS KNOWLEDGE BASE

 ## OVERVIEW

-Main plugin entry point and orchestration layer. Plugin initialization, hook registration, tool composition, and lifecycle management.
+Main plugin entry point and orchestration layer. 1000+ lines of plugin initialization, hook registration, tool composition, and lifecycle management.
+
+**Core Responsibilities:**
+- Plugin initialization and configuration loading
+- 40+ lifecycle hooks orchestration  
+- 25+ tools composition and filtering
+- Background agent management
+- Session state coordination
+- MCP server lifecycle
+- Tmux integration
+- Claude Code compatibility layer

 ## STRUCTURE
 ```
 src/
-├── index.ts                          # Main plugin entry (88 lines) — OhMyOpenCodePlugin factory
-├── create-hooks.ts                   # Hook coordination: core, continuation, skill (62 lines)
-├── create-managers.ts                # Manager initialization: Tmux, Background, SkillMcp, Config (80 lines)
-├── create-tools.ts                   # Tool registry + skill context composition (54 lines)
-├── plugin-interface.ts               # Plugin interface assembly — 7 OpenCode hooks (66 lines)
-├── plugin-config.ts                  # Config loading orchestration (user + project merge)
-├── plugin-state.ts                   # Model cache state (context limits, anthropic 1M flag)
-├── agents/                           # 11 AI agents (32 files) - see agents/AGENTS.md
-├── cli/                              # CLI installer, doctor (107+ files) - see cli/AGENTS.md
-├── config/                           # Zod schema (21 component files) - see config/AGENTS.md
-├── features/                         # Background agents, skills, commands (18 dirs) - see features/AGENTS.md
-├── hooks/                            # 41 lifecycle hooks (36 dirs) - see hooks/AGENTS.md
-├── mcp/                              # Built-in MCPs (6 files) - see mcp/AGENTS.md
-├── plugin/                           # Plugin interface composition (21 files)
-├── plugin-handlers/                  # Config loading, plan inheritance (15 files) - see plugin-handlers/AGENTS.md
-├── shared/                           # Cross-cutting utilities (84 files) - see shared/AGENTS.md
-└── tools/                            # 25+ tools (14 dirs) - see tools/AGENTS.md
+├── index.ts                          # Main plugin entry (1000 lines) - orchestration layer
+├── index.compaction-model-agnostic.static.test.ts  # Compaction hook tests
+├── agents/                           # 11 AI agents (16 files)
+├── cli/                              # CLI commands (9 files) 
+├── config/                           # Schema validation (3 files)
+├── features/                         # Background features (20+ files)
+├── hooks/                            # 40+ lifecycle hooks (14 files)
+├── mcp/                              # MCP server configs (7 files)
+├── plugin-handlers/                  # Config loading (3 files)
+├── shared/                           # Utilities (70 files)
+└── tools/                            # 25+ tools (15 files)
 ```

-## PLUGIN INITIALIZATION (10 steps)
+## KEY COMPONENTS

-1. `injectServerAuthIntoClient(ctx.client)` — Auth injection
-2. `startTmuxCheck()` — Tmux availability
-3. `loadPluginConfig(ctx.directory, ctx)` — User + project config merge → Zod validation
-4. `createFirstMessageVariantGate()` — First message variant override gate
-5. `createModelCacheState()` — Model context limits cache
-6. `createManagers(...)` → 4 managers:
-   - `TmuxSessionManager` — Multi-pane tmux sessions
-   - `BackgroundManager` — Parallel subagent execution
-   - `SkillMcpManager` — MCP server lifecycle
-   - `ConfigHandler` — Plugin config API to OpenCode
-7. `createTools(...)` → `createSkillContext()` + `createAvailableCategories()` + `createToolRegistry()`
-8. `createHooks(...)` → `createCoreHooks()` + `createContinuationHooks()` + `createSkillHooks()`
-9. `createPluginInterface(...)` → 7 OpenCode hook handlers
-10. Return plugin with `experimental.session.compacting`
+**Plugin Initialization:**
+- `OhMyOpenCodePlugin()`: Main plugin factory (lines 124-841)
+- Configuration loading via `loadPluginConfig()`
+- Hook registration with safe creation patterns
+- Tool composition and disabled tool filtering

-## HOOK REGISTRATION (3 tiers)
+**Lifecycle Management:**
+- 40+ hooks: session recovery, continuation enforcers, compaction, context injection
+- Background agent coordination via `BackgroundManager`
+- Tmux session management for multi-pane workflows
+- MCP server lifecycle via `SkillMcpManager`

-**Core Hooks** (`create-core-hooks.ts`):
- Session (20): context-window-monitor, session-recovery, think-mode, ralph-loop, anthropic-effort, ...
- Tool Guard (8): comment-checker, tool-output-truncator, rules-injector, write-existing-file-guard, ...
- Transform (4): claude-code-hooks, keyword-detector, context-injector, thinking-block-validator
+**Tool Ecosystem:**
+- 25+ tools: LSP, AST-grep, delegation, background tasks, skills
+- Tool filtering based on agent permissions and user config
+- Metadata restoration for tool outputs

-**Continuation Hooks** (`create-continuation-hooks.ts`):
- 7 hooks: stop-continuation-guard, compaction-context-injector, todo-continuation-enforcer, atlas, ...
+**Integration Points:**
+- Claude Code compatibility hooks and commands
+- OpenCode SDK client interactions
+- Session state persistence and recovery
+- Model variant resolution and application

-**Skill Hooks** (`create-skill-hooks.ts`):
- 2 hooks: category-skill-reminder, auto-slash-command
-
-## PLUGIN INTERFACE (7 OpenCode handlers)
-
-| Handler | Source | Purpose |
-|---------|--------|---------|
-| `tool` | filteredTools | All registered tools |
-| `chat.params` | createChatParamsHandler | Anthropic effort level |
-| `chat.message` | createChatMessageHandler | First message variant, session setup |
-| `experimental.chat.messages.transform` | createMessagesTransformHandler | Context injection, keyword detection |
-| `config` | configHandler | Agent/MCP/command registration |
-| `event` | createEventHandler | Session lifecycle |
-| `tool.execute.before` | createToolExecuteBeforeHandler | Pre-tool hooks |
-| `tool.execute.after` | createToolExecuteAfterHandler | Post-tool hooks |
-
-## SAFE HOOK CREATION PATTERN
+## HOOK REGISTRATION PATTERNS

+**Safe Hook Creation:**
 ```typescript
 const hook = isHookEnabled("hook-name")
  ? safeCreateHook("hook-name", () => createHookFactory(ctx), { enabled: safeHookEnabled })
  : null;
 ```

-All hooks use this pattern for graceful degradation on failure.
+**Hook Categories:**
+- **Session Management**: recovery, notification, compaction
+- **Continuation**: todo/task enforcers, stop guards
+- **Context**: injection, rules, directory content
+- **Tool Enhancement**: output truncation, error recovery, validation
+- **Agent Coordination**: usage reminders, babysitting, delegation
+
+## TOOL COMPOSITION
+
+**Core Tools:**
+```typescript
+const allTools: Record<string, ToolDefinition> = {
+  ...builtinTools,           // Basic file/session operations
+  ...createGrepTools(ctx),   // Content search
+  ...createAstGrepTools(ctx), // AST-aware refactoring
+  task: delegateTask,        // Agent delegation
+  skill: skillTool,          // Skill execution
+  // ... 20+ more tools
+};
+```
+
+**Tool Filtering:**
+- Agent permission-based restrictions
+- User-configured disabled tools
+- Dynamic tool availability based on session state
+
+## SESSION LIFECYCLE
+
+**Session Events:**
+- `session.created`: Initialize session state, tmux setup
+- `session.deleted`: Cleanup resources, clear caches
+- `message.updated`: Update agent assignments
+- `session.error`: Trigger recovery mechanisms
+
+**Continuation Flow:**
+1. User message triggers agent selection
+2. Model/variant resolution applied
+3. Tools execute with hook interception
+4. Continuation enforcers monitor completion
+5. Session compaction preserves context
+
+## CONFIGURATION INTEGRATION
+
+**Plugin Config Loading:**
+- Project + user config merging
+- Schema validation via Zod
+- Migration support for legacy configs
+- Dynamic feature enablement
+
+**Runtime Configuration:**
+- Hook enablement based on `disabled_hooks`
+- Tool filtering via `disabled_tools`
+- Agent overrides and category definitions
+- Experimental feature toggles
+
+## ANTI-PATTERNS
+
+- **Direct hook exports**: All hooks created via factories for testability
+- **Global state pollution**: Session-scoped state management
+- **Synchronous blocking**: Async-first architecture with background coordination
+- **Tight coupling**: Plugin components communicate via events, not direct calls
+- **Memory leaks**: Proper cleanup on session deletion and plugin unload
--- a/src/agents/AGENTS.md
+++ b/src/agents/AGENTS.md
@@ -2,99 +2,88 @@

 ## OVERVIEW

-11 AI agents with factory functions, fallback chains, and model-specific prompt variants. Each agent has metadata (category, cost, triggers) and configurable tool restrictions.
+32 files containing AI agents and utilities for multi-model orchestration. Each agent has factory function + metadata + fallback chains.
+
+**Primary Agents** (respect UI model selection):
+- Sisyphus, Atlas, Prometheus
+
+**Subagents** (use own fallback chains):
+- Hephaestus, Oracle, Librarian, Explore, Multimodal-Looker, Metis, Momus, Sisyphus-Junior

 ## STRUCTURE
 ```
 agents/
-├── sisyphus.ts                 # Main orchestrator (530 lines)
-├── hephaestus.ts               # Autonomous deep worker (624 lines)
-├── oracle.ts                   # Strategic advisor (170 lines)
-├── librarian.ts                # Multi-repo research (328 lines)
-├── explore.ts                  # Fast codebase grep (124 lines)
-├── multimodal-looker.ts        # Media analyzer (58 lines)
-├── metis.ts                    # Pre-planning analysis (347 lines)
-├── momus.ts                    # Plan validator (244 lines)
-├── atlas/                      # Master orchestrator
-│   ├── agent.ts                # Atlas factory
-│   ├── default.ts              # Claude-optimized prompt
-│   ├── gpt.ts                  # GPT-optimized prompt
-│   └── utils.ts
-├── prometheus/                 # Planning agent
+├── atlas/                      # Master Orchestrator (holds todo list)
+│   ├── index.ts
+│   ├── default.ts              # Claude-optimized prompt (390 lines)
+│   ├── gpt.ts                  # GPT-optimized prompt (330 lines)
+│   └── utils.ts
+├── prometheus/                 # Planning Agent (Interview/Consultant mode)
 │   ├── index.ts
-│   ├── system-prompt.ts        # 6-section prompt assembly
 │   ├── plan-template.ts        # Work plan structure (423 lines)
 │   ├── interview-mode.ts       # Interview flow (335 lines)
 │   ├── plan-generation.ts
 │   ├── high-accuracy-mode.ts
 │   ├── identity-constraints.ts # Identity rules (301 lines)
 │   └── behavioral-summary.ts
-├── sisyphus-junior/            # Delegated task executor
-│   ├── agent.ts
-│   ├── default.ts              # Claude prompt
-│   └── gpt.ts                  # GPT prompt
+├── sisyphus-junior/            # Delegated task executor (category-spawned)
+│   ├── index.ts
+│   ├── default.ts
+│   └── gpt.ts
+├── sisyphus.ts                 # Main orchestrator prompt (530 lines)
+├── hephaestus.ts               # Autonomous deep worker (618 lines, GPT 5.3 Codex)
+├── oracle.ts                   # Strategic advisor (GPT-5.2)
+├── librarian.ts                # Multi-repo research (328 lines)
+├── explore.ts                  # Fast contextual grep
+├── multimodal-looker.ts        # Media analyzer (Gemini 3 Flash)
+├── metis.ts                    # Pre-planning analysis (347 lines)
+├── momus.ts                    # Plan reviewer
 ├── dynamic-agent-prompt-builder.ts  # Dynamic prompt generation (431 lines)
-├── builtin-agents/             # Agent registry (8 files)
-├── utils.ts                    # Agent creation, model fallback resolution (571 lines)
 ├── types.ts                    # AgentModelConfig, AgentPromptMetadata
-└── index.ts                    # Exports
+├── utils.ts                    # createBuiltinAgents(), resolveModelWithFallback() (485 lines)
+└── index.ts                    # builtinAgents export
 ```

 ## AGENT MODELS
-
-| Agent | Model | Temp | Fallback Chain | Cost |
-|-------|-------|------|----------------|------|
-| Sisyphus | claude-opus-4-6 | 0.1 | kimi-k2.5 → glm-4.7 → gpt-5.3-codex → gemini-3-pro | EXPENSIVE |
-| Hephaestus | gpt-5.3-codex | 0.1 | NONE (required) | EXPENSIVE |
-| Atlas | claude-sonnet-4-5 | 0.1 | kimi-k2.5 → gpt-5.2 | EXPENSIVE |
-| Prometheus | claude-opus-4-6 | 0.1 | kimi-k2.5 → gpt-5.2 | EXPENSIVE |
-| oracle | gpt-5.2 | 0.1 | claude-opus-4-6 | EXPENSIVE |
-| librarian | glm-4.7 | 0.1 | glm-4.7-free | CHEAP |
-| explore | grok-code-fast-1 | 0.1 | claude-haiku-4-5 → gpt-5-mini → gpt-5-nano | FREE |
-| multimodal-looker | gemini-3-flash | 0.1 | NONE | CHEAP |
-| Metis | claude-opus-4-6 | 0.3 | kimi-k2.5 → gpt-5.2 | EXPENSIVE |
-| Momus | gpt-5.2 | 0.1 | claude-opus-4-6 | EXPENSIVE |
-| Sisyphus-Junior | claude-sonnet-4-5 | 0.1 | (user-configurable) | EXPENSIVE |
-
-## TOOL RESTRICTIONS
-
-| Agent | Denied | Allowed |
-|-------|--------|---------|
-| oracle | write, edit, task, call_omo_agent | Read-only consultation |
-| librarian | write, edit, task, call_omo_agent | Research tools only |
-| explore | write, edit, task, call_omo_agent | Search tools only |
-| multimodal-looker | ALL except `read` | Vision-only |
-| Sisyphus-Junior | task | No delegation |
-| Atlas | task, call_omo_agent | Orchestration only |
-
-## THINKING / REASONING
-
-| Agent | Claude | GPT |
-|-------|--------|-----|
-| Sisyphus | 32k budget tokens | reasoningEffort: "medium" |
-| Hephaestus | — | reasoningEffort: "medium" |
-| Oracle | 32k budget tokens | reasoningEffort: "medium" |
-| Metis | 32k budget tokens | — |
-| Momus | 32k budget tokens | reasoningEffort: "medium" |
-| Sisyphus-Junior | 32k budget tokens | reasoningEffort: "medium" |
+| Agent | Model | Temp | Purpose |
+|-------|-------|------|---------|
+| Sisyphus | anthropic/claude-opus-4-6 | 0.1 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.3-codex → gemini-3-pro) |
+| Hephaestus | openai/gpt-5.3-codex | 0.1 | Autonomous deep worker, "The Legitimate Craftsman" (requires gpt-5.3-codex, no fallback) |
+| 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 | zai-coding-plan/glm-4.7 | 0.1 | Docs, GitHub search (fallback: glm-4.7-free) |
+| explore | xai/grok-code-fast-1 | 0.1 | Fast contextual grep (fallback: claude-haiku-4-5 → gpt-5-mini → gpt-5-nano) |
+| multimodal-looker | google/gemini-3-flash | 0.1 | PDF/image analysis |
+| Prometheus | anthropic/claude-opus-4-6 | 0.1 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
+| Metis | anthropic/claude-opus-4-6 | 0.3 | Pre-planning analysis (fallback: kimi-k2.5 → gpt-5.2) |
+| Momus | openai/gpt-5.2 | 0.1 | Plan validation (fallback: claude-opus-4-6) |
+| Sisyphus-Junior | anthropic/claude-sonnet-4-5 | 0.1 | Category-spawned executor |

 ## HOW TO ADD
+1. Create `src/agents/my-agent.ts` exporting factory + metadata.
+2. Add to `agentSources` in `src/agents/utils.ts`.
+3. Update `AgentNameSchema` in `src/config/schema.ts`.
+4. Register in `src/index.ts` initialization.

-1. Create `src/agents/my-agent.ts` exporting factory + metadata
-2. Add to `agentSources` in `src/agents/builtin-agents/`
-3. Update `AgentNameSchema` in `src/config/schema/agent-names.ts`
-4. Register in `src/plugin-handlers/agent-config-handler.ts`
+## TOOL RESTRICTIONS
+| Agent | Denied Tools |
+|-------|-------------|
+| oracle | write, edit, task, task |
+| librarian | write, edit, task, task, call_omo_agent |
+| explore | write, edit, task, task, call_omo_agent |
+| multimodal-looker | Allowlist: read only |
+| Sisyphus-Junior | task, task |
+| Atlas | task, call_omo_agent |

-## KEY PATTERNS
-
- **Factory**: `createXXXAgent(model): AgentConfig`
+## PATTERNS
+- **Factory**: `createXXXAgent(model: string): AgentConfig`
 - **Metadata**: `XXX_PROMPT_METADATA` with category, cost, triggers
- **Model-specific prompts**: Atlas, Sisyphus-Junior have GPT vs Claude variants
- **Dynamic prompts**: Sisyphus, Hephaestus use `dynamic-agent-prompt-builder.ts` to inject available tools/skills/categories
+- **Tool restrictions**: `createAgentToolRestrictions(tools)` or `createAgentToolAllowlist(tools)`
+- **Thinking**: 32k budget tokens for Sisyphus, Oracle, Prometheus, Atlas
+- **Model-specific routing**: Atlas, Sisyphus-Junior have GPT vs Claude prompt variants

 ## ANTI-PATTERNS
-
- **Trust agent self-reports**: NEVER — always verify outputs
- **High temperature**: Don't use >0.3 for code agents
+- **Trust reports**: NEVER trust "I'm done" - verify outputs
+- **High temp**: Don't use >0.3 for code agents
 - **Sequential calls**: Use `task` with `run_in_background` for exploration
- **Prometheus writing code**: Planner only — never implements
+- **Prometheus writing code**: Planner only - never implements
--- a/src/agents/agent-builder.ts
+++ b/src/agents/agent-builder.ts
@@ -1,50 +0,0 @@
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentFactory } from "./types"
-import type { CategoriesConfig, CategoryConfig, GitMasterConfig } from "../config/schema"
-import type { BrowserAutomationProvider } from "../config/schema"
-import { mergeCategories } from "../shared/merge-categories"
-import { resolveMultipleSkills } from "../features/opencode-skill-loader/skill-content"
-
-export type AgentSource = AgentFactory | AgentConfig
-
-export function isFactory(source: AgentSource): source is AgentFactory {
-  return typeof source === "function"
-}
-
-export function buildAgent(
-  source: AgentSource,
-  model: string,
-  categories?: CategoriesConfig,
-  gitMasterConfig?: GitMasterConfig,
-  browserProvider?: BrowserAutomationProvider,
-  disabledSkills?: Set<string>
-): AgentConfig {
-  const base = isFactory(source) ? source(model) : { ...source }
-  const categoryConfigs: Record<string, CategoryConfig> = mergeCategories(categories)
-
-  const agentWithCategory = base as AgentConfig & { category?: string; skills?: string[]; variant?: string }
-  if (agentWithCategory.category) {
-    const categoryConfig = categoryConfigs[agentWithCategory.category]
-    if (categoryConfig) {
-      if (!base.model) {
-        base.model = categoryConfig.model
-      }
-      if (base.temperature === undefined && categoryConfig.temperature !== undefined) {
-        base.temperature = categoryConfig.temperature
-      }
-      if (base.variant === undefined && categoryConfig.variant !== undefined) {
-        base.variant = categoryConfig.variant
-      }
-    }
-  }
-
-  if (agentWithCategory.skills?.length) {
-    const { resolved } = resolveMultipleSkills(agentWithCategory.skills, { gitMasterConfig, browserProvider, disabledSkills })
-    if (resolved.size > 0) {
-      const skillContent = Array.from(resolved.values()).join("\n\n")
-      base.prompt = skillContent + (base.prompt ? "\n\n" + base.prompt : "")
-    }
-  }
-
-  return base
-}
--- a/src/agents/atlas/agent.ts
+++ b/src/agents/atlas/agent.ts
@@ -1,142 +0,0 @@
-/**
- * Atlas - Master Orchestrator Agent
- *
- * Orchestrates work via task() to complete ALL tasks in a todo list until fully done.
- * You are the conductor of a symphony of specialized agents.
- *
- * Routing:
- * 1. GPT models (openai/*, github-copilot/gpt-*) → gpt.ts (GPT-5.2 optimized)
- * 2. Default (Claude, etc.) → default.ts (Claude-optimized)
- */
-
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentMode, AgentPromptMetadata } from "../types"
-import { isGptModel } from "../types"
-import type { AvailableAgent, AvailableSkill, AvailableCategory } from "../dynamic-agent-prompt-builder"
-import { buildCategorySkillsDelegationGuide } from "../dynamic-agent-prompt-builder"
-import type { CategoryConfig } from "../../config/schema"
-import { mergeCategories } from "../../shared/merge-categories"
-import { createAgentToolRestrictions } from "../../shared/permission-compat"
-
-import { getDefaultAtlasPrompt } from "./default"
-import { getGptAtlasPrompt } from "./gpt"
-import {
-  getCategoryDescription,
-  buildAgentSelectionSection,
-  buildCategorySection,
-  buildSkillsSection,
-  buildDecisionMatrix,
-} from "./prompt-section-builder"
-
-const MODE: AgentMode = "primary"
-
-export type AtlasPromptSource = "default" | "gpt"
-
-/**
- * Determines which Atlas prompt to use based on model.
- */
-export function getAtlasPromptSource(model?: string): AtlasPromptSource {
-  if (model && isGptModel(model)) {
-    return "gpt"
-  }
-  return "default"
-}
-
-export interface OrchestratorContext {
-  model?: string
-  availableAgents?: AvailableAgent[]
-  availableSkills?: AvailableSkill[]
-  userCategories?: Record<string, CategoryConfig>
-}
-
-/**
- * Gets the appropriate Atlas prompt based on model.
- */
-export function getAtlasPrompt(model?: string): string {
-  const source = getAtlasPromptSource(model)
-
-  switch (source) {
-    case "gpt":
-      return getGptAtlasPrompt()
-    case "default":
-    default:
-      return getDefaultAtlasPrompt()
-  }
-}
-
-function buildDynamicOrchestratorPrompt(ctx?: OrchestratorContext): string {
-  const agents = ctx?.availableAgents ?? []
-  const skills = ctx?.availableSkills ?? []
-  const userCategories = ctx?.userCategories
-  const model = ctx?.model
-
-  const allCategories = mergeCategories(userCategories)
-  const availableCategories: AvailableCategory[] = Object.entries(allCategories).map(([name]) => ({
-    name,
-    description: getCategoryDescription(name, userCategories),
-  }))
-
-  const categorySection = buildCategorySection(userCategories)
-  const agentSection = buildAgentSelectionSection(agents)
-  const decisionMatrix = buildDecisionMatrix(agents, userCategories)
-  const skillsSection = buildSkillsSection(skills)
-  const categorySkillsGuide = buildCategorySkillsDelegationGuide(availableCategories, skills)
-
-  const basePrompt = getAtlasPrompt(model)
-
-  return basePrompt
-    .replace("{CATEGORY_SECTION}", categorySection)
-    .replace("{AGENT_SECTION}", agentSection)
-    .replace("{DECISION_MATRIX}", decisionMatrix)
-    .replace("{SKILLS_SECTION}", skillsSection)
-    .replace("{{CATEGORY_SKILLS_DELEGATION_GUIDE}}", categorySkillsGuide)
-}
-
-export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
-  const restrictions = createAgentToolRestrictions([
-    "task",
-    "call_omo_agent",
-  ])
-
-  const baseConfig = {
-    description:
-      "Orchestrates work via task() to complete ALL tasks in a todo list until fully done. (Atlas - OhMyOpenCode)",
-    mode: MODE,
-    ...(ctx.model ? { model: ctx.model } : {}),
-    temperature: 0.1,
-    prompt: buildDynamicOrchestratorPrompt(ctx),
-    color: "#10B981",
-    ...restrictions,
-  }
-
-  return baseConfig as AgentConfig
-}
-createAtlasAgent.mode = MODE
-
-export const atlasPromptMetadata: AgentPromptMetadata = {
-  category: "advisor",
-  cost: "EXPENSIVE",
-  promptAlias: "Atlas",
-  triggers: [
-    {
-      domain: "Todo list orchestration",
-      trigger: "Complete ALL tasks in a todo list with verification",
-    },
-    {
-      domain: "Multi-agent coordination",
-      trigger: "Parallel task execution across specialized agents",
-    },
-  ],
-  useWhen: [
-    "User provides a todo list path (.sisyphus/plans/{name}.md)",
-    "Multiple tasks need to be completed in sequence or parallel",
-    "Work requires coordination across multiple specialized agents",
-  ],
-  avoidWhen: [
-    "Single simple task that doesn't require orchestration",
-    "Tasks that can be handled directly by one agent",
-    "When user wants to execute tasks manually",
-  ],
-  keyTrigger:
-    "Todo list path provided OR multiple tasks requiring multi-agent orchestration",
-}
--- a/src/agents/atlas/default.ts
+++ b/src/agents/atlas/default.ts
@@ -178,54 +178,34 @@ task(
 )
 \`\`\`

-### 3.4 Verify (MANDATORY — EVERY SINGLE DELEGATION)
+### 3.4 Verify (PROJECT-LEVEL QA)

-**You are the QA gate. Subagents lie. Automated checks alone are NOT enough.**
+**After EVERY delegation, YOU must verify:**

-After EVERY delegation, complete ALL of these steps — no shortcuts:
+1. **Project-level diagnostics**:
+   \`lsp_diagnostics(filePath="src/")\` or \`lsp_diagnostics(filePath=".")\`
+   MUST return ZERO errors

-#### A. Automated Verification
-1. \`lsp_diagnostics(filePath=".")\` → ZERO errors at project level
-2. \`bun run build\` or \`bun run typecheck\` → exit code 0
-3. \`bun test\` → ALL tests pass
+2. **Build verification**:
+   \`bun run build\` or \`bun run typecheck\`
+   Exit code MUST be 0

-#### B. Manual Code Review (NON-NEGOTIABLE — DO NOT SKIP)
+3. **Test verification**:
+   \`bun test\`
+   ALL tests MUST pass

-**This is the step you are most tempted to skip. DO NOT SKIP IT.**
+4. **Manual inspection**:
+   - Read changed files
+   - Confirm changes match requirements
+   - Check for regressions

-1. \`Read\` EVERY file the subagent created or modified — no exceptions
-2. For EACH file, check line by line:
-   - Does the logic actually implement the task requirement?
-   - Are there stubs, TODOs, placeholders, or hardcoded values?
-   - Are there logic errors or missing edge cases?
-   - Does it follow the existing codebase patterns?
-   - Are imports correct and complete?
-3. Cross-reference: compare what subagent CLAIMED vs what the code ACTUALLY does
-4. If anything doesn't match → resume session and fix immediately
-
-**If you cannot explain what the changed code does, you have not reviewed it.**
-
-#### C. Hands-On QA (if applicable)
-| Deliverable | Method | Tool |
-|-------------|--------|------|
-| Frontend/UI | Browser | \`/playwright\` |
-| TUI/CLI | Interactive | \`interactive_bash\` |
-| API/Backend | Real requests | curl |
-
-#### D. Check Boulder State Directly
-
-After verification, READ the plan file directly — every time, no exceptions:
+**Checklist:**
 \`\`\`
-Read(".sisyphus/tasks/{plan-name}.yaml")
-\`\`\`
-Count remaining \`- [ ]\` tasks. This is your ground truth for what comes next.
-
-**Checklist (ALL must be checked):**
-\`\`\`
-[ ] Automated: lsp_diagnostics clean, build passes, tests pass
-[ ] Manual: Read EVERY changed file, verified logic matches requirements
-[ ] Cross-check: Subagent claims match actual code
-[ ] Boulder: Read plan file, confirmed current progress
+[ ] lsp_diagnostics at project level - ZERO errors
+[ ] Build command - exit 0
+[ ] Test suite - all pass
+[ ] Files exist and match requirements
+[ ] No regressions
 \`\`\`

 **If verification fails**: Resume the SAME session with the ACTUAL error output:
@@ -345,25 +325,22 @@ task(category="quick", load_skills=[], run_in_background=false, prompt="Task 4..

 You are the QA gate. Subagents lie. Verify EVERYTHING.

-**After each delegation — BOTH automated AND manual verification are MANDATORY:**
-
-1. \`lsp_diagnostics\` at PROJECT level → ZERO errors
-2. Run build command → exit 0
-3. Run test suite → ALL pass
-4. **\`Read\` EVERY changed file line by line** → logic matches requirements
-5. **Cross-check**: subagent's claims vs actual code — do they match?
-6. **Check boulder state**: Read the plan file directly, count remaining tasks
+**After each delegation**:
+1. \`lsp_diagnostics\` at PROJECT level (not file level)
+2. Run build command
+3. Run test suite
+4. Read changed files manually
+5. Confirm requirements met

 **Evidence required**:
 | Action | Evidence |
 |--------|----------|
-| Code change | lsp_diagnostics clean + manual Read of every changed file |
+| Code change | lsp_diagnostics clean at project level |
 | Build | Exit code 0 |
 | Tests | All pass |
-| Logic correct | You read the code and can explain what it does |
-| Boulder state | Read plan file, confirmed progress |
+| Delegation | Verified independently |

-**No evidence = not complete. Skipping manual review = rubber-stamping broken work.**
+**No evidence = not complete.**
 </verification_rules>

 <boundaries>
--- a/src/agents/atlas/gpt.ts
+++ b/src/agents/atlas/gpt.ts
@@ -182,51 +182,19 @@ Extract wisdom → include in prompt.
 task(category="[cat]", load_skills=["[skills]"], run_in_background=false, prompt=\`[6-SECTION PROMPT]\`)
 \`\`\`

-### 3.4 Verify (MANDATORY — EVERY SINGLE DELEGATION)
+### 3.4 Verify (PROJECT-LEVEL QA)

-After EVERY delegation, complete ALL steps — no shortcuts:
-
-#### A. Automated Verification
+After EVERY delegation:
 1. \`lsp_diagnostics(filePath=".")\` → ZERO errors
 2. \`Bash("bun run build")\` → exit 0
 3. \`Bash("bun test")\` → all pass
+4. \`Read\` changed files → confirm requirements met

-#### B. Manual Code Review (NON-NEGOTIABLE)
-1. \`Read\` EVERY file the subagent touched — no exceptions
-2. For each file, verify line by line:
-
-| Check | What to Look For |
-|-------|------------------|
-| Logic correctness | Does implementation match task requirements? |
-| Completeness | No stubs, TODOs, placeholders, hardcoded values? |
-| Edge cases | Off-by-one, null checks, error paths handled? |
-| Patterns | Follows existing codebase conventions? |
-| Imports | Correct, complete, no unused? |
-
-3. Cross-check: subagent's claims vs actual code — do they match?
-4. If mismatch found → resume session with \`session_id\` and fix
-
-**If you cannot explain what the changed code does, you have not reviewed it.**
-
-#### C. Hands-On QA (if applicable)
-| Deliverable | Method | Tool |
-|-------------|--------|------|
-| Frontend/UI | Browser | \`/playwright\` |
-| TUI/CLI | Interactive | \`interactive_bash\` |
-| API/Backend | Real requests | curl |
-
-#### D. Check Boulder State Directly
-After verification, READ the plan file — every time:
-\`\`\`
-Read(".sisyphus/tasks/{plan-name}.yaml")
-\`\`\`
-Count remaining \`- [ ]\` tasks. This is your ground truth.
-
-Checklist (ALL required):
- [ ] Automated: diagnostics clean, build passes, tests pass
- [ ] Manual: Read EVERY changed file, logic matches requirements
- [ ] Cross-check: subagent claims match actual code
- [ ] Boulder: Read plan file, confirmed current progress
+Checklist:
+- [ ] lsp_diagnostics clean
+- [ ] Build passes
+- [ ] Tests pass
+- [ ] Files match requirements

 ### 3.5 Handle Failures

@@ -301,23 +269,15 @@ task(category="quick", load_skills=[], run_in_background=false, prompt="Task 3..
 <verification_rules>
 You are the QA gate. Subagents lie. Verify EVERYTHING.

-**After each delegation — BOTH automated AND manual verification are MANDATORY**:
-
+**After each delegation**:
 | Step | Tool | Expected |
 |------|------|----------|
 | 1 | \`lsp_diagnostics(".")\` | ZERO errors |
 | 2 | \`Bash("bun run build")\` | exit 0 |
 | 3 | \`Bash("bun test")\` | all pass |
-| 4 | \`Read\` EVERY changed file | logic matches requirements |
-| 5 | Cross-check claims vs code | subagent's report matches reality |
-| 6 | \`Read\` plan file | boulder state confirmed |
+| 4 | \`Read\` changed files | matches requirements |

-**Manual code review (Step 4) is NON-NEGOTIABLE:**
- Read every line of every changed file
- Verify logic correctness, completeness, edge cases
- If you can't explain what the code does, you haven't reviewed it
-
-**No evidence = not complete. Skipping manual review = rubber-stamping broken work.**
+**No evidence = not complete.**
 </verification_rules>

 <boundaries>
--- a/src/agents/atlas/index.ts
+++ b/src/agents/atlas/index.ts
@@ -1,3 +1,33 @@
+/**
+ * Atlas - Master Orchestrator Agent
+ *
+ * Orchestrates work via task() to complete ALL tasks in a todo list until fully done.
+ * You are the conductor of a symphony of specialized agents.
+ *
+ * Routing:
+ * 1. GPT models (openai/*, github-copilot/gpt-*) → gpt.ts (GPT-5.2 optimized)
+ * 2. Default (Claude, etc.) → default.ts (Claude-optimized)
+ */
+
+import type { AgentConfig } from "@opencode-ai/sdk"
+import type { AgentMode, AgentPromptMetadata } from "../types"
+import { isGptModel } from "../types"
+import type { AvailableAgent, AvailableSkill, AvailableCategory } from "../dynamic-agent-prompt-builder"
+import { buildCategorySkillsDelegationGuide } from "../dynamic-agent-prompt-builder"
+import type { CategoryConfig } from "../../config/schema"
+import { DEFAULT_CATEGORIES } from "../../tools/delegate-task/constants"
+import { createAgentToolRestrictions } from "../../shared/permission-compat"
+
+import { ATLAS_SYSTEM_PROMPT, getDefaultAtlasPrompt } from "./default"
+import { ATLAS_GPT_SYSTEM_PROMPT, getGptAtlasPrompt } from "./gpt"
+import {
+  getCategoryDescription,
+  buildAgentSelectionSection,
+  buildCategorySection,
+  buildSkillsSection,
+  buildDecisionMatrix,
+} from "./utils"
+
 export { ATLAS_SYSTEM_PROMPT, getDefaultAtlasPrompt } from "./default"
 export { ATLAS_GPT_SYSTEM_PROMPT, getGptAtlasPrompt } from "./gpt"
 export {
@@ -6,9 +36,118 @@ export {
  buildCategorySection,
  buildSkillsSection,
  buildDecisionMatrix,
-} from "./prompt-section-builder"
+} from "./utils"
+export { isGptModel }

-export { createAtlasAgent, getAtlasPromptSource, getAtlasPrompt, atlasPromptMetadata } from "./agent"
-export type { AtlasPromptSource, OrchestratorContext } from "./agent"
+const MODE: AgentMode = "primary"

-export { isGptModel } from "../types"
+export type AtlasPromptSource = "default" | "gpt"
+
+/**
+ * Determines which Atlas prompt to use based on model.
+ */
+export function getAtlasPromptSource(model?: string): AtlasPromptSource {
+  if (model && isGptModel(model)) {
+    return "gpt"
+  }
+  return "default"
+}
+
+export interface OrchestratorContext {
+  model?: string
+  availableAgents?: AvailableAgent[]
+  availableSkills?: AvailableSkill[]
+  userCategories?: Record<string, CategoryConfig>
+}
+
+/**
+ * Gets the appropriate Atlas prompt based on model.
+ */
+export function getAtlasPrompt(model?: string): string {
+  const source = getAtlasPromptSource(model)
+
+  switch (source) {
+    case "gpt":
+      return getGptAtlasPrompt()
+    case "default":
+    default:
+      return getDefaultAtlasPrompt()
+  }
+}
+
+function buildDynamicOrchestratorPrompt(ctx?: OrchestratorContext): string {
+  const agents = ctx?.availableAgents ?? []
+  const skills = ctx?.availableSkills ?? []
+  const userCategories = ctx?.userCategories
+  const model = ctx?.model
+
+  const allCategories = { ...DEFAULT_CATEGORIES, ...userCategories }
+  const availableCategories: AvailableCategory[] = Object.entries(allCategories).map(([name]) => ({
+    name,
+    description: getCategoryDescription(name, userCategories),
+  }))
+
+  const categorySection = buildCategorySection(userCategories)
+  const agentSection = buildAgentSelectionSection(agents)
+  const decisionMatrix = buildDecisionMatrix(agents, userCategories)
+  const skillsSection = buildSkillsSection(skills)
+  const categorySkillsGuide = buildCategorySkillsDelegationGuide(availableCategories, skills)
+
+  const basePrompt = getAtlasPrompt(model)
+
+  return basePrompt
+    .replace("{CATEGORY_SECTION}", categorySection)
+    .replace("{AGENT_SECTION}", agentSection)
+    .replace("{DECISION_MATRIX}", decisionMatrix)
+    .replace("{SKILLS_SECTION}", skillsSection)
+    .replace("{{CATEGORY_SKILLS_DELEGATION_GUIDE}}", categorySkillsGuide)
+}
+
+export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
+  const restrictions = createAgentToolRestrictions([
+    "task",
+    "call_omo_agent",
+  ])
+
+  const baseConfig = {
+    description:
+      "Orchestrates work via task() to complete ALL tasks in a todo list until fully done. (Atlas - OhMyOpenCode)",
+    mode: MODE,
+    ...(ctx.model ? { model: ctx.model } : {}),
+    temperature: 0.1,
+    prompt: buildDynamicOrchestratorPrompt(ctx),
+    color: "#10B981",
+    ...restrictions,
+  }
+
+  return baseConfig as AgentConfig
+}
+createAtlasAgent.mode = MODE
+
+export const atlasPromptMetadata: AgentPromptMetadata = {
+  category: "advisor",
+  cost: "EXPENSIVE",
+  promptAlias: "Atlas",
+  triggers: [
+    {
+      domain: "Todo list orchestration",
+      trigger: "Complete ALL tasks in a todo list with verification",
+    },
+    {
+      domain: "Multi-agent coordination",
+      trigger: "Parallel task execution across specialized agents",
+    },
+  ],
+  useWhen: [
+    "User provides a todo list path (.sisyphus/plans/{name}.md)",
+    "Multiple tasks need to be completed in sequence or parallel",
+    "Work requires coordination across multiple specialized agents",
+  ],
+  avoidWhen: [
+    "Single simple task that doesn't require orchestration",
+    "Tasks that can be handled directly by one agent",
+    "When user wants to execute tasks manually",
+  ],
+  keyTrigger:
+    "Todo list path provided OR multiple tasks requiring multi-agent orchestration",
+}
--- a/src/agents/atlas/prompt-section-builder.ts
+++ b/src/agents/atlas/prompt-section-builder.ts
@@ -7,8 +7,7 @@

 import type { CategoryConfig } from "../../config/schema"
 import { formatCustomSkillsBlock, type AvailableAgent, type AvailableSkill } from "../dynamic-agent-prompt-builder"
-import { CATEGORY_DESCRIPTIONS } from "../../tools/delegate-task/constants"
-import { mergeCategories } from "../../shared/merge-categories"
+import { DEFAULT_CATEGORIES, CATEGORY_DESCRIPTIONS } from "../../tools/delegate-task/constants"
 import { truncateDescription } from "../../shared/truncate-description"

 export const getCategoryDescription = (name: string, userCategories?: Record<string, CategoryConfig>) =>
@@ -34,7 +33,7 @@ ${rows.join("\n")}`
 }

 export function buildCategorySection(userCategories?: Record<string, CategoryConfig>): string {
-  const allCategories = mergeCategories(userCategories)
+  const allCategories = { ...DEFAULT_CATEGORIES, ...userCategories }
  const categoryRows = Object.entries(allCategories).map(([name, config]) => {
    const temp = config.temperature ?? 0.5
    return `| \`${name}\` | ${temp} | ${getCategoryDescription(name, userCategories)} |`
@@ -117,7 +116,7 @@ task(category="[category]", load_skills=["skill-1", "skill-2"], run_in_backgroun
 }

 export function buildDecisionMatrix(agents: AvailableAgent[], userCategories?: Record<string, CategoryConfig>): string {
-  const allCategories = mergeCategories(userCategories)
+  const allCategories = { ...DEFAULT_CATEGORIES, ...userCategories }

  const categoryRows = Object.entries(allCategories).map(([name]) =>
    `| ${getCategoryDescription(name, userCategories)} | \`category="${name}", load_skills=[...]\` |`
--- a/src/agents/builtin-agents.ts
+++ b/src/agents/builtin-agents.ts
@@ -1,181 +0,0 @@
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { BuiltinAgentName, AgentOverrides, AgentFactory, AgentPromptMetadata } from "./types"
-import type { CategoriesConfig, GitMasterConfig } from "../config/schema"
-import type { LoadedSkill } from "../features/opencode-skill-loader/types"
-import type { BrowserAutomationProvider } from "../config/schema"
-import { createSisyphusAgent } from "./sisyphus"
-import { createOracleAgent, ORACLE_PROMPT_METADATA } from "./oracle"
-import { createLibrarianAgent, LIBRARIAN_PROMPT_METADATA } from "./librarian"
-import { createExploreAgent, EXPLORE_PROMPT_METADATA } from "./explore"
-import { createMultimodalLookerAgent, MULTIMODAL_LOOKER_PROMPT_METADATA } from "./multimodal-looker"
-import { createMetisAgent, metisPromptMetadata } from "./metis"
-import { createAtlasAgent, atlasPromptMetadata } from "./atlas"
-import { createMomusAgent, momusPromptMetadata } from "./momus"
-import { createHephaestusAgent } from "./hephaestus"
-import type { AvailableCategory } from "./dynamic-agent-prompt-builder"
-import { fetchAvailableModels, readConnectedProvidersCache } from "../shared"
-import { CATEGORY_DESCRIPTIONS } from "../tools/delegate-task/constants"
-import { mergeCategories } from "../shared/merge-categories"
-import { buildAvailableSkills } from "./builtin-agents/available-skills"
-import { collectPendingBuiltinAgents } from "./builtin-agents/general-agents"
-import { maybeCreateSisyphusConfig } from "./builtin-agents/sisyphus-agent"
-import { maybeCreateHephaestusConfig } from "./builtin-agents/hephaestus-agent"
-import { maybeCreateAtlasConfig } from "./builtin-agents/atlas-agent"
-import { buildCustomAgentMetadata, parseRegisteredAgentSummaries } from "./custom-agent-summaries"
-
-type AgentSource = AgentFactory | AgentConfig
-
-const agentSources: Record<BuiltinAgentName, AgentSource> = {
-  sisyphus: createSisyphusAgent,
-  hephaestus: createHephaestusAgent,
-  oracle: createOracleAgent,
-  librarian: createLibrarianAgent,
-  explore: createExploreAgent,
-  "multimodal-looker": createMultimodalLookerAgent,
-  metis: createMetisAgent,
-  momus: createMomusAgent,
-  // Note: Atlas is handled specially in createBuiltinAgents()
-  // because it needs OrchestratorContext, not just a model string
-  atlas: createAtlasAgent as AgentFactory,
-}
-
-/**
- * Metadata for each agent, used to build Sisyphus's dynamic prompt sections
- * (Delegation Table, Tool Selection, Key Triggers, etc.)
- */
-const agentMetadata: Partial<Record<BuiltinAgentName, AgentPromptMetadata>> = {
-  oracle: ORACLE_PROMPT_METADATA,
-  librarian: LIBRARIAN_PROMPT_METADATA,
-  explore: EXPLORE_PROMPT_METADATA,
-  "multimodal-looker": MULTIMODAL_LOOKER_PROMPT_METADATA,
-  metis: metisPromptMetadata,
-  momus: momusPromptMetadata,
-  atlas: atlasPromptMetadata,
-}
-
-export async function createBuiltinAgents(
-  disabledAgents: string[] = [],
-  agentOverrides: AgentOverrides = {},
-  directory?: string,
-  systemDefaultModel?: string,
-  categories?: CategoriesConfig,
-  gitMasterConfig?: GitMasterConfig,
-  discoveredSkills: LoadedSkill[] = [],
-  customAgentSummaries?: unknown,
-  browserProvider?: BrowserAutomationProvider,
-  uiSelectedModel?: string,
-  disabledSkills?: Set<string>,
-  useTaskSystem = false
-): Promise<Record<string, AgentConfig>> {
-  const connectedProviders = readConnectedProvidersCache()
-  // IMPORTANT: Do NOT call OpenCode client APIs during plugin initialization.
-  // This function is called from config handler, and calling client API causes deadlock.
-  // See: https://github.com/code-yeongyu/oh-my-opencode/issues/1301
-  const availableModels = await fetchAvailableModels(undefined, {
-    connectedProviders: connectedProviders ?? undefined,
-  })
-  const isFirstRunNoCache =
-    availableModels.size === 0 && (!connectedProviders || connectedProviders.length === 0)
-
-  const result: Record<string, AgentConfig> = {}
-
-  const mergedCategories = mergeCategories(categories)
-
-  const availableCategories: AvailableCategory[] = Object.entries(mergedCategories).map(([name]) => ({
-    name,
-    description: categories?.[name]?.description ?? CATEGORY_DESCRIPTIONS[name] ?? "General tasks",
-  }))
-
-  const availableSkills = buildAvailableSkills(discoveredSkills, browserProvider, disabledSkills)
-
-  // Collect general agents first (for availableAgents), but don't add to result yet
-  const { pendingAgentConfigs, availableAgents } = collectPendingBuiltinAgents({
-    agentSources,
-    agentMetadata,
-    disabledAgents,
-    agentOverrides,
-    directory,
-    systemDefaultModel,
-    mergedCategories,
-    gitMasterConfig,
-    browserProvider,
-    uiSelectedModel,
-    availableModels,
-    disabledSkills,
-  })
-
-  const registeredAgents = parseRegisteredAgentSummaries(customAgentSummaries)
-  const builtinAgentNames = new Set(Object.keys(agentSources).map((name) => name.toLowerCase()))
-  const disabledAgentNames = new Set(disabledAgents.map((name) => name.toLowerCase()))
-
-  for (const agent of registeredAgents) {
-    const lowerName = agent.name.toLowerCase()
-    if (builtinAgentNames.has(lowerName)) continue
-    if (disabledAgentNames.has(lowerName)) continue
-    if (availableAgents.some((availableAgent) => availableAgent.name.toLowerCase() === lowerName)) continue
-
-    availableAgents.push({
-      name: agent.name,
-      description: agent.description,
-      metadata: buildCustomAgentMetadata(agent.name, agent.description),
-    })
-  }
-
-  const sisyphusConfig = maybeCreateSisyphusConfig({
-    disabledAgents,
-    agentOverrides,
-    uiSelectedModel,
-    availableModels,
-    systemDefaultModel,
-    isFirstRunNoCache,
-    availableAgents,
-    availableSkills,
-    availableCategories,
-    mergedCategories,
-    directory,
-    userCategories: categories,
-    useTaskSystem,
-  })
-  if (sisyphusConfig) {
-    result["sisyphus"] = sisyphusConfig
-  }
-
-  const hephaestusConfig = maybeCreateHephaestusConfig({
-    disabledAgents,
-    agentOverrides,
-    availableModels,
-    systemDefaultModel,
-    isFirstRunNoCache,
-    availableAgents,
-    availableSkills,
-    availableCategories,
-    mergedCategories,
-    directory,
-    useTaskSystem,
-  })
-  if (hephaestusConfig) {
-    result["hephaestus"] = hephaestusConfig
-  }
-
-  // Add pending agents after sisyphus and hephaestus to maintain order
-  for (const [name, config] of pendingAgentConfigs) {
-    result[name] = config
-  }
-
-  const atlasConfig = maybeCreateAtlasConfig({
-    disabledAgents,
-    agentOverrides,
-    uiSelectedModel,
-    availableModels,
-    systemDefaultModel,
-    availableAgents,
-    availableSkills,
-    mergedCategories,
-    userCategories: categories,
-  })
-  if (atlasConfig) {
-    result["atlas"] = atlasConfig
-  }
-
-  return result
-}
--- a/src/agents/builtin-agents/agent-overrides.ts
+++ b/src/agents/builtin-agents/agent-overrides.ts
@@ -1,65 +0,0 @@
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentOverrideConfig } from "../types"
-import type { CategoryConfig } from "../../config/schema"
-import { deepMerge, migrateAgentConfig } from "../../shared"
-
-/**
- * Expands a category reference from an agent override into concrete config properties.
- * Category properties are applied unconditionally (overwriting factory defaults),
- * because the user's chosen category should take priority over factory base values.
- * Direct override properties applied later via mergeAgentConfig() will supersede these.
- */
-export function applyCategoryOverride(
-  config: AgentConfig,
-  categoryName: string,
-  mergedCategories: Record<string, CategoryConfig>
-): AgentConfig {
-  const categoryConfig = mergedCategories[categoryName]
-  if (!categoryConfig) return config
-
-  const result = { ...config } as AgentConfig & Record<string, unknown>
-  if (categoryConfig.model) result.model = categoryConfig.model
-  if (categoryConfig.variant !== undefined) result.variant = categoryConfig.variant
-  if (categoryConfig.temperature !== undefined) result.temperature = categoryConfig.temperature
-  if (categoryConfig.reasoningEffort !== undefined) result.reasoningEffort = categoryConfig.reasoningEffort
-  if (categoryConfig.textVerbosity !== undefined) result.textVerbosity = categoryConfig.textVerbosity
-  if (categoryConfig.thinking !== undefined) result.thinking = categoryConfig.thinking
-  if (categoryConfig.top_p !== undefined) result.top_p = categoryConfig.top_p
-  if (categoryConfig.maxTokens !== undefined) result.maxTokens = categoryConfig.maxTokens
-
-  if (categoryConfig.prompt_append && typeof result.prompt === "string") {
-    result.prompt = result.prompt + "\n" + categoryConfig.prompt_append
-  }
-
-  return result as AgentConfig
-}
-
-export function mergeAgentConfig(base: AgentConfig, override: AgentOverrideConfig): AgentConfig {
-  const migratedOverride = migrateAgentConfig(override as Record<string, unknown>) as AgentOverrideConfig
-  const { prompt_append, ...rest } = migratedOverride
-  const merged = deepMerge(base, rest as Partial<AgentConfig>)
-
-  if (prompt_append && merged.prompt) {
-    merged.prompt = merged.prompt + "\n" + prompt_append
-  }
-
-  return merged
-}
-
-export function applyOverrides(
-  config: AgentConfig,
-  override: AgentOverrideConfig | undefined,
-  mergedCategories: Record<string, CategoryConfig>
-): AgentConfig {
-  let result = config
-  const overrideCategory = (override as Record<string, unknown> | undefined)?.category as string | undefined
-  if (overrideCategory) {
-    result = applyCategoryOverride(result, overrideCategory, mergedCategories)
-  }
-
-  if (override) {
-    result = mergeAgentConfig(result, override)
-  }
-
-  return result
-}
--- a/src/agents/builtin-agents/atlas-agent.ts
+++ b/src/agents/builtin-agents/atlas-agent.ts
@@ -1,64 +0,0 @@
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentOverrides } from "../types"
-import type { CategoriesConfig, CategoryConfig } from "../../config/schema"
-import type { AvailableAgent, AvailableSkill } from "../dynamic-agent-prompt-builder"
-import { AGENT_MODEL_REQUIREMENTS } from "../../shared"
-import { applyOverrides } from "./agent-overrides"
-import { applyModelResolution } from "./model-resolution"
-import { createAtlasAgent } from "../atlas"
-
-export function maybeCreateAtlasConfig(input: {
-  disabledAgents: string[]
-  agentOverrides: AgentOverrides
-  uiSelectedModel?: string
-  availableModels: Set<string>
-  systemDefaultModel?: string
-  availableAgents: AvailableAgent[]
-  availableSkills: AvailableSkill[]
-  mergedCategories: Record<string, CategoryConfig>
-  userCategories?: CategoriesConfig
-  useTaskSystem?: boolean
-}): AgentConfig | undefined {
-  const {
-    disabledAgents,
-    agentOverrides,
-    uiSelectedModel,
-    availableModels,
-    systemDefaultModel,
-    availableAgents,
-    availableSkills,
-    mergedCategories,
-    userCategories,
-  } = input
-
-  if (disabledAgents.includes("atlas")) return undefined
-
-  const orchestratorOverride = agentOverrides["atlas"]
-  const atlasRequirement = AGENT_MODEL_REQUIREMENTS["atlas"]
-
-  const atlasResolution = applyModelResolution({
-    uiSelectedModel: orchestratorOverride?.model ? undefined : uiSelectedModel,
-    userModel: orchestratorOverride?.model,
-    requirement: atlasRequirement,
-    availableModels,
-    systemDefaultModel,
-  })
-
-  if (!atlasResolution) return undefined
-  const { model: atlasModel, variant: atlasResolvedVariant } = atlasResolution
-
-  let orchestratorConfig = createAtlasAgent({
-    model: atlasModel,
-    availableAgents,
-    availableSkills,
-    userCategories,
-  })
-
-  if (atlasResolvedVariant) {
-    orchestratorConfig = { ...orchestratorConfig, variant: atlasResolvedVariant }
-  }
-
-  orchestratorConfig = applyOverrides(orchestratorConfig, orchestratorOverride, mergedCategories)
-
-  return orchestratorConfig
-}
--- a/src/agents/builtin-agents/available-skills.ts
+++ b/src/agents/builtin-agents/available-skills.ts
@@ -1,35 +0,0 @@
-import type { AvailableSkill } from "../dynamic-agent-prompt-builder"
-import type { BrowserAutomationProvider } from "../../config/schema"
-import type { LoadedSkill, SkillScope } from "../../features/opencode-skill-loader/types"
-import { createBuiltinSkills } from "../../features/builtin-skills"
-
-function mapScopeToLocation(scope: SkillScope): AvailableSkill["location"] {
-  if (scope === "user" || scope === "opencode") return "user"
-  if (scope === "project" || scope === "opencode-project") return "project"
-  return "plugin"
-}
-
-export function buildAvailableSkills(
-  discoveredSkills: LoadedSkill[],
-  browserProvider?: BrowserAutomationProvider,
-  disabledSkills?: Set<string>
-): AvailableSkill[] {
-  const builtinSkills = createBuiltinSkills({ browserProvider, disabledSkills })
-  const builtinSkillNames = new Set(builtinSkills.map(s => s.name))
-
-  const builtinAvailable: AvailableSkill[] = builtinSkills.map((skill) => ({
-    name: skill.name,
-    description: skill.description,
-    location: "plugin" as const,
-  }))
-
-  const discoveredAvailable: AvailableSkill[] = discoveredSkills
-    .filter(s => !builtinSkillNames.has(s.name) && !disabledSkills?.has(s.name))
-    .map((skill) => ({
-      name: skill.name,
-      description: skill.definition.description ?? "",
-      location: mapScopeToLocation(skill.scope),
-    }))
-
-  return [...builtinAvailable, ...discoveredAvailable]
-}
--- a/src/agents/builtin-agents/environment-context.ts
+++ b/src/agents/builtin-agents/environment-context.ts
@@ -1,8 +0,0 @@
-import type { AgentConfig } from "@opencode-ai/sdk"
-import { createEnvContext } from "../env-context"
-
-export function applyEnvironmentContext(config: AgentConfig, directory?: string): AgentConfig {
-  if (!directory || !config.prompt) return config
-  const envContext = createEnvContext()
-  return { ...config, prompt: config.prompt + envContext }
-}
--- a/src/agents/builtin-agents/general-agents.ts
+++ b/src/agents/builtin-agents/general-agents.ts
@@ -1,103 +0,0 @@
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { BuiltinAgentName, AgentOverrides, AgentPromptMetadata } from "../types"
-import type { CategoryConfig, GitMasterConfig } from "../../config/schema"
-import type { BrowserAutomationProvider } from "../../config/schema"
-import type { AvailableAgent } from "../dynamic-agent-prompt-builder"
-import { AGENT_MODEL_REQUIREMENTS, isModelAvailable } from "../../shared"
-import { buildAgent, isFactory } from "../agent-builder"
-import { applyOverrides } from "./agent-overrides"
-import { applyEnvironmentContext } from "./environment-context"
-import { applyModelResolution } from "./model-resolution"
-
-export function collectPendingBuiltinAgents(input: {
-  agentSources: Record<BuiltinAgentName, import("../agent-builder").AgentSource>
-  agentMetadata: Partial<Record<BuiltinAgentName, AgentPromptMetadata>>
-  disabledAgents: string[]
-  agentOverrides: AgentOverrides
-  directory?: string
-  systemDefaultModel?: string
-  mergedCategories: Record<string, CategoryConfig>
-  gitMasterConfig?: GitMasterConfig
-  browserProvider?: BrowserAutomationProvider
-  uiSelectedModel?: string
-  availableModels: Set<string>
-  disabledSkills?: Set<string>
-  useTaskSystem?: boolean
-}): { pendingAgentConfigs: Map<string, AgentConfig>; availableAgents: AvailableAgent[] } {
-  const {
-    agentSources,
-    agentMetadata,
-    disabledAgents,
-    agentOverrides,
-    directory,
-    systemDefaultModel,
-    mergedCategories,
-    gitMasterConfig,
-    browserProvider,
-    uiSelectedModel,
-    availableModels,
-    disabledSkills,
-  } = input
-
-  const availableAgents: AvailableAgent[] = []
-  const pendingAgentConfigs: Map<string, AgentConfig> = new Map()
-
-  for (const [name, source] of Object.entries(agentSources)) {
-    const agentName = name as BuiltinAgentName
-
-    if (agentName === "sisyphus") continue
-    if (agentName === "hephaestus") continue
-    if (agentName === "atlas") continue
-    if (disabledAgents.some((name) => name.toLowerCase() === agentName.toLowerCase())) continue
-
-    const override = agentOverrides[agentName]
-      ?? Object.entries(agentOverrides).find(([key]) => key.toLowerCase() === agentName.toLowerCase())?.[1]
-    const requirement = AGENT_MODEL_REQUIREMENTS[agentName]
-
-    // Check if agent requires a specific model
-    if (requirement?.requiresModel && availableModels) {
-      if (!isModelAvailable(requirement.requiresModel, availableModels)) {
-        continue
-      }
-    }
-
-    const isPrimaryAgent = isFactory(source) && source.mode === "primary"
-
-    const resolution = applyModelResolution({
-      uiSelectedModel: (isPrimaryAgent && !override?.model) ? uiSelectedModel : undefined,
-      userModel: override?.model,
-      requirement,
-      availableModels,
-      systemDefaultModel,
-    })
-    if (!resolution) continue
-    const { model, variant: resolvedVariant } = resolution
-
-    let config = buildAgent(source, model, mergedCategories, gitMasterConfig, browserProvider, disabledSkills)
-
-    // Apply resolved variant from model fallback chain
-    if (resolvedVariant) {
-      config = { ...config, variant: resolvedVariant }
-    }
-
-    if (agentName === "librarian") {
-      config = applyEnvironmentContext(config, directory)
-    }
-
-    config = applyOverrides(config, override, mergedCategories)
-
-    // Store for later - will be added after sisyphus and hephaestus
-    pendingAgentConfigs.set(name, config)
-
-    const metadata = agentMetadata[agentName]
-    if (metadata) {
-      availableAgents.push({
-        name: agentName,
-        description: config.description ?? "",
-        metadata,
-      })
-    }
-  }
-
-  return { pendingAgentConfigs, availableAgents }
-}
--- a/src/agents/builtin-agents/hephaestus-agent.ts
+++ b/src/agents/builtin-agents/hephaestus-agent.ts
@@ -1,91 +0,0 @@
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentOverrides } from "../types"
-import type { CategoryConfig } from "../../config/schema"
-import type { AvailableAgent, AvailableCategory, AvailableSkill } from "../dynamic-agent-prompt-builder"
-import { AGENT_MODEL_REQUIREMENTS, isAnyProviderConnected } from "../../shared"
-import { createHephaestusAgent } from "../hephaestus"
-import { createEnvContext } from "../env-context"
-import { applyCategoryOverride, mergeAgentConfig } from "./agent-overrides"
-import { applyModelResolution, getFirstFallbackModel } from "./model-resolution"
-
-export function maybeCreateHephaestusConfig(input: {
-  disabledAgents: string[]
-  agentOverrides: AgentOverrides
-  availableModels: Set<string>
-  systemDefaultModel?: string
-  isFirstRunNoCache: boolean
-  availableAgents: AvailableAgent[]
-  availableSkills: AvailableSkill[]
-  availableCategories: AvailableCategory[]
-  mergedCategories: Record<string, CategoryConfig>
-  directory?: string
-  useTaskSystem: boolean
-}): AgentConfig | undefined {
-  const {
-    disabledAgents,
-    agentOverrides,
-    availableModels,
-    systemDefaultModel,
-    isFirstRunNoCache,
-    availableAgents,
-    availableSkills,
-    availableCategories,
-    mergedCategories,
-    directory,
-    useTaskSystem,
-  } = input
-
-  if (disabledAgents.includes("hephaestus")) return undefined
-
-  const hephaestusOverride = agentOverrides["hephaestus"]
-  const hephaestusRequirement = AGENT_MODEL_REQUIREMENTS["hephaestus"]
-  const hasHephaestusExplicitConfig = hephaestusOverride !== undefined
-
-  const hasRequiredProvider =
-    !hephaestusRequirement?.requiresProvider ||
-    hasHephaestusExplicitConfig ||
-    isFirstRunNoCache ||
-    isAnyProviderConnected(hephaestusRequirement.requiresProvider, availableModels)
-
-  if (!hasRequiredProvider) return undefined
-
-  let hephaestusResolution = applyModelResolution({
-    userModel: hephaestusOverride?.model,
-    requirement: hephaestusRequirement,
-    availableModels,
-    systemDefaultModel,
-  })
-
-  if (isFirstRunNoCache && !hephaestusOverride?.model) {
-    hephaestusResolution = getFirstFallbackModel(hephaestusRequirement)
-  }
-
-  if (!hephaestusResolution) return undefined
-  const { model: hephaestusModel, variant: hephaestusResolvedVariant } = hephaestusResolution
-
-  let hephaestusConfig = createHephaestusAgent(
-    hephaestusModel,
-    availableAgents,
-    undefined,
-    availableSkills,
-    availableCategories,
-    useTaskSystem
-  )
-
-  hephaestusConfig = { ...hephaestusConfig, variant: hephaestusResolvedVariant ?? "medium" }
-
-  const hepOverrideCategory = (hephaestusOverride as Record<string, unknown> | undefined)?.category as string | undefined
-  if (hepOverrideCategory) {
-    hephaestusConfig = applyCategoryOverride(hephaestusConfig, hepOverrideCategory, mergedCategories)
-  }
-
-  if (directory && hephaestusConfig.prompt) {
-    const envContext = createEnvContext()
-    hephaestusConfig = { ...hephaestusConfig, prompt: hephaestusConfig.prompt + envContext }
-  }
-
-  if (hephaestusOverride) {
-    hephaestusConfig = mergeAgentConfig(hephaestusConfig, hephaestusOverride)
-  }
-  return hephaestusConfig
-}
--- a/src/agents/builtin-agents/model-resolution.ts
+++ b/src/agents/builtin-agents/model-resolution.ts
@@ -1,28 +0,0 @@
-import { resolveModelPipeline } from "../../shared"
-
-export function applyModelResolution(input: {
-  uiSelectedModel?: string
-  userModel?: string
-  requirement?: { fallbackChain?: { providers: string[]; model: string; variant?: string }[] }
-  availableModels: Set<string>
-  systemDefaultModel?: string
-}) {
-  const { uiSelectedModel, userModel, requirement, availableModels, systemDefaultModel } = input
-  return resolveModelPipeline({
-    intent: { uiSelectedModel, userModel },
-    constraints: { availableModels },
-    policy: { fallbackChain: requirement?.fallbackChain, systemDefaultModel },
-  })
-}
-
-export function getFirstFallbackModel(requirement?: {
-  fallbackChain?: { providers: string[]; model: string; variant?: string }[]
-}) {
-  const entry = requirement?.fallbackChain?.[0]
-  if (!entry || entry.providers.length === 0) return undefined
-  return {
-    model: `${entry.providers[0]}/${entry.model}`,
-    provenance: "provider-fallback" as const,
-    variant: entry.variant,
-  }
-}
--- a/src/agents/builtin-agents/sisyphus-agent.ts
+++ b/src/agents/builtin-agents/sisyphus-agent.ts
@@ -1,84 +0,0 @@
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentOverrides } from "../types"
-import type { CategoriesConfig, CategoryConfig } from "../../config/schema"
-import type { AvailableAgent, AvailableCategory, AvailableSkill } from "../dynamic-agent-prompt-builder"
-import { AGENT_MODEL_REQUIREMENTS, isAnyFallbackModelAvailable } from "../../shared"
-import { applyEnvironmentContext } from "./environment-context"
-import { applyOverrides } from "./agent-overrides"
-import { applyModelResolution, getFirstFallbackModel } from "./model-resolution"
-import { createSisyphusAgent } from "../sisyphus"
-
-export function maybeCreateSisyphusConfig(input: {
-  disabledAgents: string[]
-  agentOverrides: AgentOverrides
-  uiSelectedModel?: string
-  availableModels: Set<string>
-  systemDefaultModel?: string
-  isFirstRunNoCache: boolean
-  availableAgents: AvailableAgent[]
-  availableSkills: AvailableSkill[]
-  availableCategories: AvailableCategory[]
-  mergedCategories: Record<string, CategoryConfig>
-  directory?: string
-  userCategories?: CategoriesConfig
-  useTaskSystem: boolean
-}): AgentConfig | undefined {
-  const {
-    disabledAgents,
-    agentOverrides,
-    uiSelectedModel,
-    availableModels,
-    systemDefaultModel,
-    isFirstRunNoCache,
-    availableAgents,
-    availableSkills,
-    availableCategories,
-    mergedCategories,
-    directory,
-    useTaskSystem,
-  } = input
-
-  const sisyphusOverride = agentOverrides["sisyphus"]
-  const sisyphusRequirement = AGENT_MODEL_REQUIREMENTS["sisyphus"]
-  const hasSisyphusExplicitConfig = sisyphusOverride !== undefined
-  const meetsSisyphusAnyModelRequirement =
-    !sisyphusRequirement?.requiresAnyModel ||
-    hasSisyphusExplicitConfig ||
-    isFirstRunNoCache ||
-    isAnyFallbackModelAvailable(sisyphusRequirement.fallbackChain, availableModels)
-
-  if (disabledAgents.includes("sisyphus") || !meetsSisyphusAnyModelRequirement) return undefined
-
-  let sisyphusResolution = applyModelResolution({
-    uiSelectedModel: sisyphusOverride?.model ? undefined : uiSelectedModel,
-    userModel: sisyphusOverride?.model,
-    requirement: sisyphusRequirement,
-    availableModels,
-    systemDefaultModel,
-  })
-
-  if (isFirstRunNoCache && !sisyphusOverride?.model && !uiSelectedModel) {
-    sisyphusResolution = getFirstFallbackModel(sisyphusRequirement)
-  }
-
-  if (!sisyphusResolution) return undefined
-  const { model: sisyphusModel, variant: sisyphusResolvedVariant } = sisyphusResolution
-
-  let sisyphusConfig = createSisyphusAgent(
-    sisyphusModel,
-    availableAgents,
-    undefined,
-    availableSkills,
-    availableCategories,
-    useTaskSystem
-  )
-
-  if (sisyphusResolvedVariant) {
-    sisyphusConfig = { ...sisyphusConfig, variant: sisyphusResolvedVariant }
-  }
-
-  sisyphusConfig = applyOverrides(sisyphusConfig, sisyphusOverride, mergedCategories)
-  sisyphusConfig = applyEnvironmentContext(sisyphusConfig, directory)
-
-  return sisyphusConfig
-}
--- a/src/agents/custom-agent-summaries.ts
+++ b/src/agents/custom-agent-summaries.ts
@@ -1,61 +0,0 @@
-import type { AgentPromptMetadata } from "./types"
-import { truncateDescription } from "../shared/truncate-description"
-
-type RegisteredAgentSummary = {
-  name: string
-  description: string
-}
-
-function sanitizeMarkdownTableCell(value: string): string {
-  return value
-    .replace(/\r?\n/g, " ")
-    .replace(/\|/g, "\\|")
-    .replace(/\s+/g, " ")
-    .trim()
-}
-
-function isRecord(value: unknown): value is Record<string, unknown> {
-  return typeof value === "object" && value !== null
-}
-
-export function parseRegisteredAgentSummaries(input: unknown): RegisteredAgentSummary[] {
-  if (!Array.isArray(input)) return []
-
-  const result: RegisteredAgentSummary[] = []
-  for (const item of input) {
-    if (!isRecord(item)) continue
-
-    const name = typeof item.name === "string" ? item.name : undefined
-    if (!name) continue
-
-    const hidden = item.hidden
-    if (hidden === true) continue
-
-    const disabled = item.disabled
-    if (disabled === true) continue
-
-    const enabled = item.enabled
-    if (enabled === false) continue
-
-    const description = typeof item.description === "string" ? item.description : ""
-    result.push({ name: sanitizeMarkdownTableCell(name), description: sanitizeMarkdownTableCell(description) })
-  }
-
-  return result
-}
-
-export function buildCustomAgentMetadata(agentName: string, description: string): AgentPromptMetadata {
-  const shortDescription = sanitizeMarkdownTableCell(truncateDescription(description))
-  const safeAgentName = sanitizeMarkdownTableCell(agentName)
-
-  return {
-    category: "specialist",
-    cost: "CHEAP",
-    triggers: [
-      {
-        domain: `Custom agent: ${safeAgentName}`,
-        trigger: shortDescription || "Use when this agent's description matches the task",
-      },
-    ],
-  }
-}
--- a/src/agents/env-context.ts
+++ b/src/agents/env-context.ts
@@ -1,33 +0,0 @@
-/**
- * Creates OmO-specific environment context (time, timezone, locale).
- * Note: Working directory, platform, and date are already provided by OpenCode's system.ts,
- * so we only include fields that OpenCode doesn't provide to avoid duplication.
- * See: https://github.com/code-yeongyu/oh-my-opencode/issues/379
- */
-export function createEnvContext(): string {
-  const now = new Date()
-  const timezone = Intl.DateTimeFormat().resolvedOptions().timeZone
-  const locale = Intl.DateTimeFormat().resolvedOptions().locale
-
-  const dateStr = now.toLocaleDateString(locale, {
-    weekday: "short",
-    year: "numeric",
-    month: "short",
-    day: "numeric",
-  })
-
-  const timeStr = now.toLocaleTimeString(locale, {
-    hour: "2-digit",
-    minute: "2-digit",
-    second: "2-digit",
-    hour12: true,
-  })
-
-  return `
-<omo-env>
-  Current date: ${dateStr}
-  Current time: ${timeStr}
-  Timezone: ${timezone}
-  Locale: ${locale}
-</omo-env>`
-}
--- a/src/agents/hephaestus.ts
+++ b/src/agents/hephaestus.ts
@@ -278,19 +278,13 @@ ${librarianSection}

 \`\`\`typescript
 // CORRECT: Always background, always parallel
-// Prompt structure (each field should be substantive, not a single sentence):
-//   [CONTEXT]: What task I'm working on, which files/modules are involved, and what approach I'm taking
-//   [GOAL]: The specific outcome I need — what decision or action the results will unblock
-//   [DOWNSTREAM]: How I will use the results — what I'll build/decide based on what's found
-//   [REQUEST]: Concrete search instructions — what to find, what format to return, and what to SKIP
-
+// Prompt structure: [CONTEXT: what I'm doing] + [GOAL: what I'm trying to achieve] + [QUESTION: what I need to know] + [REQUEST: what to find]
 // Contextual Grep (internal)
-task(subagent_type="explore", run_in_background=true, load_skills=[], description="Find auth implementations", prompt="I'm implementing JWT auth for the REST API in src/api/routes/. I need to match existing auth conventions so my code fits seamlessly. I'll use this to decide middleware structure and token flow. Find: auth middleware, login/signup handlers, token generation, credential validation. Focus on src/ — skip tests. Return file paths with pattern descriptions.")
-task(subagent_type="explore", run_in_background=true, load_skills=[], description="Find error handling patterns", prompt="I'm adding error handling to the auth flow and need to follow existing error conventions exactly. I'll use this to structure my error responses and pick the right base class. Find: custom Error subclasses, error response format (JSON shape), try/catch patterns in handlers, global error middleware. Skip test files. Return the error class hierarchy and response format.")
-
+task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="I'm implementing user authentication for our API. I need to understand how auth is currently structured in this codebase. Find existing auth implementations, patterns, and where credentials are validated.")
+task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="I'm adding error handling to the auth flow. I want to follow existing project conventions for consistency. Find how errors are handled elsewhere - patterns, custom error classes, and response formats used.")
 // Reference Grep (external)
-task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find JWT security docs", prompt="I'm implementing JWT auth and need current security best practices to choose token storage (httpOnly cookies vs localStorage) and set expiration policy. Find: OWASP auth guidelines, recommended token lifetimes, refresh token rotation strategies, common JWT vulnerabilities. Skip 'what is JWT' tutorials — production security guidance only.")
-task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find Express auth patterns", prompt="I'm building Express auth middleware and need production-quality patterns to structure my middleware chain. Find how established Express apps (1000+ stars) handle: middleware ordering, token refresh, role-based access control, auth error propagation. Skip basic tutorials — I need battle-tested patterns with proper error handling.")
+task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="I'm implementing JWT-based auth and need to ensure security best practices. Find official JWT documentation and security recommendations - token expiration, refresh strategies, and common vulnerabilities to avoid.")
+task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="I'm building Express middleware for auth and want production-quality patterns. Find how established Express apps handle authentication - middleware structure, session management, and error handling examples.")
 // Continue immediately - collect results when needed

 // WRONG: Sequential or blocking - NEVER DO THIS
--- a/src/agents/index.ts
+++ b/src/agents/index.ts
@@ -1,5 +1,5 @@
 export * from "./types"
-export { createBuiltinAgents } from "./builtin-agents"
+export { createBuiltinAgents } from "./utils"
 export type { AvailableAgent, AvailableCategory, AvailableSkill } from "./dynamic-agent-prompt-builder"
 export { createSisyphusAgent } from "./sisyphus"
 export { createOracleAgent, ORACLE_PROMPT_METADATA } from "./oracle"
--- a/src/agents/prometheus/index.ts
+++ b/src/agents/prometheus/index.ts
@@ -1,4 +1,50 @@
-export { PROMETHEUS_SYSTEM_PROMPT, PROMETHEUS_PERMISSION } from "./system-prompt"
+/**
+ * Prometheus Planner System Prompt
+ *
+ * Named after the Titan who gave fire (knowledge/foresight) to humanity.
+ * Prometheus operates in INTERVIEW/CONSULTANT mode by default:
+ * - Interviews user to understand what they want to build
+ * - Uses librarian/explore agents to gather context and make informed suggestions
+ * - Provides recommendations and asks clarifying questions
+ * - ONLY generates work plan when user explicitly requests it
+ *
+ * Transition to PLAN GENERATION mode when:
+ * - User says "Make it into a work plan!" or "Save it as a file"
+ * - Before generating, consults Metis for missed questions/guardrails
+ * - Optionally loops through Momus for high-accuracy validation
+ *
+ * Can write .md files only (enforced by prometheus-md-only hook).
+ */
+
+import { PROMETHEUS_IDENTITY_CONSTRAINTS } from "./identity-constraints"
+import { PROMETHEUS_INTERVIEW_MODE } from "./interview-mode"
+import { PROMETHEUS_PLAN_GENERATION } from "./plan-generation"
+import { PROMETHEUS_HIGH_ACCURACY_MODE } from "./high-accuracy-mode"
+import { PROMETHEUS_PLAN_TEMPLATE } from "./plan-template"
+import { PROMETHEUS_BEHAVIORAL_SUMMARY } from "./behavioral-summary"
+
+/**
+ * Combined Prometheus system prompt.
+ * Assembled from modular sections for maintainability.
+ */
+export const PROMETHEUS_SYSTEM_PROMPT = `${PROMETHEUS_IDENTITY_CONSTRAINTS}
+${PROMETHEUS_INTERVIEW_MODE}
+${PROMETHEUS_PLAN_GENERATION}
+${PROMETHEUS_HIGH_ACCURACY_MODE}
+${PROMETHEUS_PLAN_TEMPLATE}
+${PROMETHEUS_BEHAVIORAL_SUMMARY}`
+
+/**
+ * Prometheus planner permission configuration.
+ * Allows write/edit for plan files (.md only, enforced by prometheus-md-only hook).
+ * Question permission allows agent to ask user questions via OpenCode's QuestionTool.
+ */
+export const PROMETHEUS_PERMISSION = {
+  edit: "allow" as const,
+  bash: "allow" as const,
+  webfetch: "allow" as const,
+  question: "allow" as const,
+}

 // Re-export individual sections for granular access
 export { PROMETHEUS_IDENTITY_CONSTRAINTS } from "./identity-constraints"
--- a/src/agents/prometheus/interview-mode.ts
+++ b/src/agents/prometheus/interview-mode.ts
@@ -65,13 +65,9 @@ Or should I just note down this single fix?"

 **Research First:**
 \`\`\`typescript
-// Prompt structure (each field substantive):
-//   [CONTEXT]: Task, files/modules involved, approach
-//   [GOAL]: Specific outcome needed — what decision/action results will unblock
-//   [DOWNSTREAM]: How results will be used
-//   [REQUEST]: What to find, return format, what to SKIP
-task(subagent_type="explore", load_skills=[], prompt="I'm refactoring [target] and need to map its full impact scope before making changes. I'll use this to build a safe refactoring plan. Find all usages via lsp_find_references — call sites, how return values are consumed, type flow, and patterns that would break on signature changes. Also check for dynamic access that lsp_find_references might miss. Return: file path, usage pattern, risk level (high/medium/low) per call site.", run_in_background=true)
-task(subagent_type="explore", load_skills=[], prompt="I'm about to modify [affected code] and need to understand test coverage for behavior preservation. I'll use this to decide whether to add tests first. Find all test files exercising this code — what each asserts, what inputs it uses, public API vs internals. Identify coverage gaps: behaviors used in production but untested. Return a coverage map: tested vs untested behaviors.", run_in_background=true)
+// Prompt structure: CONTEXT (what I'm doing) + GOAL (what I'm trying to achieve) + QUESTION (what I need to know) + REQUEST (what to find)
+task(subagent_type="explore", load_skills=[], prompt="I'm refactoring [target] and need to understand its impact scope before making changes. Find all usages via lsp_find_references - show calling code, patterns of use, and potential breaking points.", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="I'm about to modify [affected code] and need to ensure behavior preservation. Find existing test coverage - which tests exercise this code, what assertions exist, and any gaps in coverage.", run_in_background=true)
 \`\`\`

 **Interview Focus:**
@@ -94,10 +90,10 @@ task(subagent_type="explore", load_skills=[], prompt="I'm about to modify [affec
 **Pre-Interview Research (MANDATORY):**
 \`\`\`typescript
 // Launch BEFORE asking user questions
-// Prompt structure: [CONTEXT] + [GOAL] + [DOWNSTREAM] + [REQUEST]
-task(subagent_type="explore", load_skills=[], prompt="I'm building a new [feature] from scratch and need to match existing codebase conventions exactly. I'll use this to copy the right file structure and patterns. Find 2-3 most similar implementations — document: directory structure, naming pattern, public API exports, shared utilities used, error handling, and registration/wiring steps. Return concrete file paths and patterns, not abstract descriptions.", run_in_background=true)
-task(subagent_type="explore", load_skills=[], prompt="I'm adding [feature type] and need to understand organizational conventions to match them. I'll use this to determine directory layout and naming scheme. Find how similar features are organized: nesting depth, index.ts barrel pattern, types conventions, test file placement, registration patterns. Compare 2-3 feature directories. Return the canonical structure as a file tree.", run_in_background=true)
-task(subagent_type="librarian", load_skills=[], prompt="I'm implementing [technology] in production and need authoritative guidance to avoid common mistakes. I'll use this for setup and configuration decisions. Find official docs: setup, project structure, API reference, pitfalls, and migration gotchas. Also find 1-2 production-quality OSS examples (not tutorials). Skip beginner guides — I need production patterns only.", run_in_background=true)
+// Prompt structure: CONTEXT + GOAL + QUESTION + REQUEST
+task(subagent_type="explore", load_skills=[], prompt="I'm building a new [feature] and want to maintain codebase consistency. Find similar implementations in this project - their structure, patterns used, and conventions to follow.", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="I'm adding [feature type] to the project and need to understand existing conventions. Find how similar features are organized - file structure, naming patterns, and architectural approach.", run_in_background=true)
+task(subagent_type="librarian", load_skills=[], prompt="I'm implementing [technology] and want to follow established best practices. Find official documentation and community recommendations - setup patterns, common pitfalls, and production-ready examples.", run_in_background=true)
 \`\`\`

 **Interview Focus** (AFTER research):
@@ -136,7 +132,7 @@ Based on your stack, I'd recommend NextAuth.js - it integrates well with Next.js

 Run this check:
 \`\`\`typescript
-task(subagent_type="explore", load_skills=[], prompt="I'm assessing test infrastructure before planning TDD work. I'll use this to decide whether to include test setup tasks. Find: 1) Test framework — package.json scripts, config files (jest/vitest/bun/pytest), test dependencies. 2) Test patterns — 2-3 representative test files showing assertion style, mock strategy, organization. 3) Coverage config and test-to-source ratio. 4) CI integration — test commands in .github/workflows. Return structured report: YES/NO per capability with examples.", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="I'm assessing this project's test setup before planning work that may require TDD. I need to understand what testing capabilities exist. Find test infrastructure: package.json test scripts, config files (jest.config, vitest.config, pytest.ini), and existing test files. Report: 1) Does test infra exist? 2) What framework? 3) Example test patterns.", run_in_background=true)
 \`\`\`

 #### Step 2: Ask the Test Question (MANDATORY)
@@ -234,8 +230,8 @@ Add to draft immediately:

 **Research First:**
 \`\`\`typescript
-task(subagent_type="explore", load_skills=[], prompt="I'm planning architectural changes and need to understand current system design. I'll use this to identify safe-to-change vs load-bearing boundaries. Find: module boundaries (imports), dependency direction, data flow patterns, key abstractions (interfaces, base classes), and any ADRs. Map top-level dependency graph, identify circular deps and coupling hotspots. Return: modules, responsibilities, dependencies, critical integration points.", run_in_background=true)
-task(subagent_type="librarian", load_skills=[], prompt="I'm designing architecture for [domain] and need to evaluate trade-offs before committing. I'll use this to present concrete options to the user. Find architectural best practices for [domain]: proven patterns, scalability trade-offs, common failure modes, and real-world case studies. Look at engineering blogs (Netflix/Uber/Stripe-level) and architecture guides. Skip generic pattern catalogs — I need domain-specific guidance.", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="I'm planning architectural changes and need to understand the current system design. Find existing architecture: module boundaries, dependency patterns, data flow, and key abstractions used.", run_in_background=true)
+task(subagent_type="librarian", load_skills=[], prompt="I'm designing architecture for [domain] and want to make informed decisions. Find architectural best practices - proven patterns, trade-offs, and lessons learned from similar systems.", run_in_background=true)
 \`\`\`

 **Oracle Consultation** (recommend when stakes are high):
@@ -257,9 +253,9 @@ task(subagent_type="oracle", load_skills=[], prompt="Architecture consultation n

 **Parallel Investigation:**
 \`\`\`typescript
-task(subagent_type="explore", load_skills=[], prompt="I'm researching [feature] to decide whether to extend or replace the current approach. I'll use this to recommend a strategy. Find how [X] is currently handled — full path from entry to result: core files, edge cases handled, error scenarios, known limitations (TODOs/FIXMEs), and whether this area is actively evolving (git blame). Return: what works, what's fragile, what's missing.", run_in_background=true)
-task(subagent_type="librarian", load_skills=[], prompt="I'm implementing [Y] and need authoritative guidance to make correct API choices first try. I'll use this to follow intended patterns, not anti-patterns. Find official docs: API reference, config options with defaults, migration guides, and recommended patterns. Check for 'common mistakes' sections and GitHub issues for gotchas. Return: key API signatures, recommended config, pitfalls.", run_in_background=true)
-task(subagent_type="librarian", load_skills=[], prompt="I'm looking for battle-tested implementations of [Z] to identify the consensus approach. I'll use this to avoid reinventing the wheel. Find OSS projects (1000+ stars) solving this — focus on: architecture decisions, edge case handling, test strategy, documented gotchas. Compare 2-3 implementations for common vs project-specific patterns. Skip tutorials — production code only.", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="I'm researching how to implement [feature] and need to understand current approach. Find how X is currently handled in this codebase - implementation details, edge cases covered, and any known limitations.", run_in_background=true)
+task(subagent_type="librarian", load_skills=[], prompt="I'm implementing Y and need authoritative guidance. Find official documentation - API reference, configuration options, and recommended usage patterns.", run_in_background=true)
+task(subagent_type="librarian", load_skills=[], prompt="I'm looking for battle-tested implementations of Z. Find open source projects that solve this - focus on production-quality code, how they handle edge cases, and any gotchas documented.", run_in_background=true)
 \`\`\`

 **Interview Focus:**
@@ -285,17 +281,17 @@ task(subagent_type="librarian", load_skills=[], prompt="I'm looking for battle-t

 **For Understanding Codebase:**
 \`\`\`typescript
-task(subagent_type="explore", load_skills=[], prompt="I'm working on [topic] and need to understand how it's organized before making changes. I'll use this to match existing conventions. Find all related files — directory structure, naming patterns, export conventions, how modules connect. Compare 2-3 similar modules to identify the canonical pattern. Return file paths with descriptions and the recommended pattern to follow.", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="I'm working on [topic] and need to understand how it's organized in this project. Find all related files - show the structure, patterns used, and conventions I should follow.", run_in_background=true)
 \`\`\`

 **For External Knowledge:**
 \`\`\`typescript
-task(subagent_type="librarian", load_skills=[], prompt="I'm integrating [library] and need to understand [specific feature] for correct first-try implementation. I'll use this to follow recommended patterns. Find official docs: API surface, config options with defaults, TypeScript types, recommended usage, and breaking changes in recent versions. Check changelog if our version differs from latest. Return: API signatures, config snippets, pitfalls.", run_in_background=true)
+task(subagent_type="librarian", load_skills=[], prompt="I'm integrating [library] and need to understand [specific feature]. Find official documentation - API details, configuration options, and recommended best practices.", run_in_background=true)
 \`\`\`

 **For Implementation Examples:**
 \`\`\`typescript
-task(subagent_type="librarian", load_skills=[], prompt="I'm implementing [feature] and want to learn from production OSS before designing our approach. I'll use this to identify consensus patterns. Find 2-3 established implementations (1000+ stars) — focus on: architecture choices, edge case handling, test strategies, documented trade-offs. Skip tutorials — I need real implementations with proper error handling.", run_in_background=true)
+task(subagent_type="librarian", load_skills=[], prompt="I'm implementing [feature] and want to learn from existing solutions. Find open source implementations - focus on production-quality code, architecture decisions, and common patterns.", run_in_background=true)
 \`\`\`

 ## Interview Mode Anti-Patterns
--- a/src/agents/prometheus/system-prompt.ts
+++ b/src/agents/prometheus/system-prompt.ts
@@ -1,29 +0,0 @@
-import { PROMETHEUS_IDENTITY_CONSTRAINTS } from "./identity-constraints"
-import { PROMETHEUS_INTERVIEW_MODE } from "./interview-mode"
-import { PROMETHEUS_PLAN_GENERATION } from "./plan-generation"
-import { PROMETHEUS_HIGH_ACCURACY_MODE } from "./high-accuracy-mode"
-import { PROMETHEUS_PLAN_TEMPLATE } from "./plan-template"
-import { PROMETHEUS_BEHAVIORAL_SUMMARY } from "./behavioral-summary"
-
-/**
- * Combined Prometheus system prompt.
- * Assembled from modular sections for maintainability.
- */
-export const PROMETHEUS_SYSTEM_PROMPT = `${PROMETHEUS_IDENTITY_CONSTRAINTS}
-${PROMETHEUS_INTERVIEW_MODE}
-${PROMETHEUS_PLAN_GENERATION}
-${PROMETHEUS_HIGH_ACCURACY_MODE}
-${PROMETHEUS_PLAN_TEMPLATE}
-${PROMETHEUS_BEHAVIORAL_SUMMARY}`
-
-/**
- * Prometheus planner permission configuration.
- * Allows write/edit for plan files (.md only, enforced by prometheus-md-only hook).
- * Question permission allows agent to ask user questions via OpenCode's QuestionTool.
- */
-export const PROMETHEUS_PERMISSION = {
-  edit: "allow" as const,
-  bash: "allow" as const,
-  webfetch: "allow" as const,
-  question: "allow" as const,
-}
--- a/src/agents/sisyphus-junior/agent.ts
+++ b/src/agents/sisyphus-junior/agent.ts
@@ -1,119 +0,0 @@
-/**
- * Sisyphus-Junior - Focused Task Executor
- *
- * Executes delegated tasks directly without spawning other agents.
- * Category-spawned executor with domain-specific configurations.
- *
- * Routing:
- * 1. GPT models (openai/*, github-copilot/gpt-*) -> gpt.ts (GPT-5.2 optimized)
- * 2. Default (Claude, etc.) -> default.ts (Claude-optimized)
- */
-
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentMode } from "../types"
-import { isGptModel } from "../types"
-import type { AgentOverrideConfig } from "../../config/schema"
-import {
-  createAgentToolRestrictions,
-  type PermissionValue,
-} from "../../shared/permission-compat"
-
-import { buildDefaultSisyphusJuniorPrompt } from "./default"
-import { buildGptSisyphusJuniorPrompt } from "./gpt"
-
-const MODE: AgentMode = "subagent"
-
-// Core tools that Sisyphus-Junior must NEVER have access to
-// Note: call_omo_agent is ALLOWED so subagents can spawn explore/librarian
-const BLOCKED_TOOLS = ["task"]
-
-export const SISYPHUS_JUNIOR_DEFAULTS = {
-  model: "anthropic/claude-sonnet-4-5",
-  temperature: 0.1,
-} as const
-
-export type SisyphusJuniorPromptSource = "default" | "gpt"
-
-/**
- * Determines which Sisyphus-Junior prompt to use based on model.
- */
-export function getSisyphusJuniorPromptSource(model?: string): SisyphusJuniorPromptSource {
-  if (model && isGptModel(model)) {
-    return "gpt"
-  }
-  return "default"
-}
-
-/**
- * Builds the appropriate Sisyphus-Junior prompt based on model.
- */
-export function buildSisyphusJuniorPrompt(
-  model: string | undefined,
-  useTaskSystem: boolean,
-  promptAppend?: string
-): string {
-  const source = getSisyphusJuniorPromptSource(model)
-
-  switch (source) {
-    case "gpt":
-      return buildGptSisyphusJuniorPrompt(useTaskSystem, promptAppend)
-    case "default":
-    default:
-      return buildDefaultSisyphusJuniorPrompt(useTaskSystem, promptAppend)
-  }
-}
-
-export function createSisyphusJuniorAgentWithOverrides(
-  override: AgentOverrideConfig | undefined,
-  systemDefaultModel?: string,
-  useTaskSystem = false
-): AgentConfig {
-  if (override?.disable) {
-    override = undefined
-  }
-
-  const overrideModel = (override as { model?: string } | undefined)?.model
-  const model = overrideModel ?? systemDefaultModel ?? SISYPHUS_JUNIOR_DEFAULTS.model
-  const temperature = override?.temperature ?? SISYPHUS_JUNIOR_DEFAULTS.temperature
-
-  const promptAppend = override?.prompt_append
-  const prompt = buildSisyphusJuniorPrompt(model, useTaskSystem, promptAppend)
-
-  const baseRestrictions = createAgentToolRestrictions(BLOCKED_TOOLS)
-
-  const userPermission = (override?.permission ?? {}) as Record<string, PermissionValue>
-  const basePermission = baseRestrictions.permission
-  const merged: Record<string, PermissionValue> = { ...userPermission }
-  for (const tool of BLOCKED_TOOLS) {
-    merged[tool] = "deny"
-  }
-  merged.call_omo_agent = "allow"
-  const toolsConfig = { permission: { ...merged, ...basePermission } }
-
-  const base: AgentConfig = {
-    description: override?.description ??
-      "Focused task executor. Same discipline, no delegation. (Sisyphus-Junior - OhMyOpenCode)",
-    mode: MODE,
-    model,
-    temperature,
-    maxTokens: 64000,
-    prompt,
-    color: override?.color ?? "#20B2AA",
-    ...toolsConfig,
-  }
-
-  if (override?.top_p !== undefined) {
-    base.top_p = override.top_p
-  }
-
-  if (isGptModel(model)) {
-    return { ...base, reasoningEffort: "medium" } as AgentConfig
-  }
-
-  return {
-    ...base,
-    thinking: { type: "enabled", budgetTokens: 32000 },
-  } as AgentConfig
-}
-
-createSisyphusJuniorAgentWithOverrides.mode = MODE
--- a/src/agents/sisyphus-junior/default.ts
+++ b/src/agents/sisyphus-junior/default.ts
@@ -12,7 +12,6 @@ export function buildDefaultSisyphusJuniorPrompt(
  promptAppend?: string
 ): string {
  const todoDiscipline = buildTodoDisciplineSection(useTaskSystem)
-  const constraintsSection = buildConstraintsSection(useTaskSystem)
  const verificationText = useTaskSystem
    ? "All tasks marked completed"
    : "All todos marked completed"
@@ -22,7 +21,13 @@ Sisyphus-Junior - Focused executor from OhMyOpenCode.
 Execute tasks directly. NEVER delegate or spawn other agents.
 </Role>

-${constraintsSection}
+<Critical_Constraints>
+BLOCKED ACTIONS (will fail if attempted):
+- task tool: BLOCKED
+
+ALLOWED: call_omo_agent - You CAN spawn explore/librarian agents for research.
+You work ALONE for implementation. No delegation of implementation tasks.
+</Critical_Constraints>

 ${todoDiscipline}

@@ -43,29 +48,6 @@ Task NOT complete without:
  return prompt + "\n\n" + promptAppend
 }

-function buildConstraintsSection(useTaskSystem: boolean): string {
-  if (useTaskSystem) {
-    return `<Critical_Constraints>
-BLOCKED ACTIONS (will fail if attempted):
- task (agent delegation tool): BLOCKED — you cannot delegate work to other agents
-
-ALLOWED tools:
- call_omo_agent: You CAN spawn explore/librarian agents for research
- task_create, task_update, task_list, task_get: ALLOWED — use these for tracking your work
-
-You work ALONE for implementation. No delegation of implementation tasks.
-</Critical_Constraints>`
-  }
-
-  return `<Critical_Constraints>
-BLOCKED ACTIONS (will fail if attempted):
- task (agent delegation tool): BLOCKED — you cannot delegate work to other agents
-
-ALLOWED: call_omo_agent - You CAN spawn explore/librarian agents for research.
-You work ALONE for implementation. No delegation of implementation tasks.
-</Critical_Constraints>`
-}
-
 function buildTodoDisciplineSection(useTaskSystem: boolean): string {
  if (useTaskSystem) {
    return `<Task_Discipline>
--- a/src/agents/sisyphus-junior/gpt.ts
+++ b/src/agents/sisyphus-junior/gpt.ts
@@ -21,7 +21,6 @@ export function buildGptSisyphusJuniorPrompt(
  promptAppend?: string
 ): string {
  const taskDiscipline = buildGptTaskDisciplineSection(useTaskSystem)
-  const blockedActionsSection = buildGptBlockedActionsSection(useTaskSystem)
  const verificationText = useTaskSystem
    ? "All tasks marked completed"
    : "All todos marked completed"
@@ -46,7 +45,19 @@ Role: Execute tasks directly. You work ALONE.
 - Do NOT expand task boundaries beyond what's written.
 </scope_and_design_constraints>

-${blockedActionsSection}
+<blocked_actions>
+BLOCKED (will fail if attempted):
+| Tool | Status |
+|------|--------|
+| task | BLOCKED |
+
+ALLOWED:
+| Tool | Usage |
+|------|-------|
+| call_omo_agent | Spawn explore/librarian for research ONLY |
+
+You work ALONE for implementation. No delegation.
+</blocked_actions>

 <uncertainty_and_ambiguity>
 - If a task is ambiguous or underspecified:
@@ -88,42 +99,6 @@ Task NOT complete without evidence:
  return prompt + "\n\n" + promptAppend
 }

-function buildGptBlockedActionsSection(useTaskSystem: boolean): string {
-  if (useTaskSystem) {
-    return `<blocked_actions>
-BLOCKED (will fail if attempted):
-| Tool | Status | Description |
-|------|--------|-------------|
-| task | BLOCKED | Agent delegation tool — you cannot spawn other agents |
-
-ALLOWED:
-| Tool | Usage |
-|------|-------|
-| call_omo_agent | Spawn explore/librarian for research ONLY |
-| task_create | Create tasks to track your work |
-| task_update | Update task status (in_progress, completed) |
-| task_list | List active tasks |
-| task_get | Get task details by ID |
-
-You work ALONE for implementation. No delegation.
-</blocked_actions>`
-  }
-
-  return `<blocked_actions>
-BLOCKED (will fail if attempted):
-| Tool | Status | Description |
-|------|--------|-------------|
-| task | BLOCKED | Agent delegation tool — you cannot spawn other agents |
-
-ALLOWED:
-| Tool | Usage |
-|------|-------|
-| call_omo_agent | Spawn explore/librarian for research ONLY |
-
-You work ALONE for implementation. No delegation.
-</blocked_actions>`
-}
-
 function buildGptTaskDisciplineSection(useTaskSystem: boolean): string {
  if (useTaskSystem) {
    return `<task_discipline_spec>
--- a/src/agents/sisyphus-junior/index.test.ts
+++ b/src/agents/sisyphus-junior/index.test.ts
@@ -200,88 +200,6 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
    })
  })

-  describe("useTaskSystem integration", () => {
-    test("useTaskSystem=true produces Task_Discipline prompt for Claude", () => {
-      //#given
-      const override = { model: "anthropic/claude-sonnet-4-5" }
-
-      //#when
-      const result = createSisyphusJuniorAgentWithOverrides(override, undefined, true)
-
-      //#then
-      expect(result.prompt).toContain("TaskCreate")
-      expect(result.prompt).toContain("TaskUpdate")
-      expect(result.prompt).not.toContain("todowrite")
-    })
-
-    test("useTaskSystem=true produces task_discipline_spec prompt for GPT", () => {
-      //#given
-      const override = { model: "openai/gpt-5.2" }
-
-      //#when
-      const result = createSisyphusJuniorAgentWithOverrides(override, undefined, true)
-
-      //#then
-      expect(result.prompt).toContain("<task_discipline_spec>")
-      expect(result.prompt).toContain("TaskCreate")
-      expect(result.prompt).not.toContain("<todo_discipline_spec>")
-    })
-
-    test("useTaskSystem=false (default) produces Todo_Discipline prompt", () => {
-      //#given
-      const override = {}
-
-      //#when
-      const result = createSisyphusJuniorAgentWithOverrides(override)
-
-      //#then
-      expect(result.prompt).toContain("todowrite")
-      expect(result.prompt).not.toContain("TaskCreate")
-    })
-
-    test("useTaskSystem=true explicitly lists task management tools as ALLOWED for Claude", () => {
-      //#given
-      const override = { model: "anthropic/claude-sonnet-4-5" }
-
-      //#when
-      const result = createSisyphusJuniorAgentWithOverrides(override, undefined, true)
-
-      //#then - prompt must disambiguate: delegation tool blocked, management tools allowed
-      expect(result.prompt).toContain("task_create")
-      expect(result.prompt).toContain("task_update")
-      expect(result.prompt).toContain("task_list")
-      expect(result.prompt).toContain("task_get")
-      expect(result.prompt).toContain("agent delegation tool")
-    })
-
-    test("useTaskSystem=true explicitly lists task management tools as ALLOWED for GPT", () => {
-      //#given
-      const override = { model: "openai/gpt-5.2" }
-
-      //#when
-      const result = createSisyphusJuniorAgentWithOverrides(override, undefined, true)
-
-      //#then - prompt must disambiguate: delegation tool blocked, management tools allowed
-      expect(result.prompt).toContain("task_create")
-      expect(result.prompt).toContain("task_update")
-      expect(result.prompt).toContain("task_list")
-      expect(result.prompt).toContain("task_get")
-      expect(result.prompt).toContain("Agent delegation tool")
-    })
-
-    test("useTaskSystem=false does NOT list task management tools in constraints", () => {
-      //#given - Claude model without task system
-      const override = { model: "anthropic/claude-sonnet-4-5" }
-
-      //#when
-      const result = createSisyphusJuniorAgentWithOverrides(override, undefined, false)
-
-      //#then - no task management tool references in constraints section
-      expect(result.prompt).not.toContain("task_create")
-      expect(result.prompt).not.toContain("task_update")
-    })
-  })
-
  describe("prompt composition", () => {
    test("base prompt contains discipline constraints", () => {
      // given
--- a/src/agents/sisyphus-junior/index.ts
+++ b/src/agents/sisyphus-junior/index.ts
@@ -1,10 +1,121 @@
+/**
+ * Sisyphus-Junior - Focused Task Executor
+ *
+ * Executes delegated tasks directly without spawning other agents.
+ * Category-spawned executor with domain-specific configurations.
+ *
+ * Routing:
+ * 1. GPT models (openai/*, github-copilot/gpt-*) -> gpt.ts (GPT-5.2 optimized)
+ * 2. Default (Claude, etc.) -> default.ts (Claude-optimized)
+ */
+
+import type { AgentConfig } from "@opencode-ai/sdk"
+import type { AgentMode } from "../types"
+import { isGptModel } from "../types"
+import type { AgentOverrideConfig } from "../../config/schema"
+import {
+  createAgentToolRestrictions,
+  type PermissionValue,
+} from "../../shared/permission-compat"
+
+import { buildDefaultSisyphusJuniorPrompt } from "./default"
+import { buildGptSisyphusJuniorPrompt } from "./gpt"
+
 export { buildDefaultSisyphusJuniorPrompt } from "./default"
 export { buildGptSisyphusJuniorPrompt } from "./gpt"

-export {
-  SISYPHUS_JUNIOR_DEFAULTS,
-  getSisyphusJuniorPromptSource,
-  buildSisyphusJuniorPrompt,
-  createSisyphusJuniorAgentWithOverrides,
-} from "./agent"
-export type { SisyphusJuniorPromptSource } from "./agent"
+const MODE: AgentMode = "subagent"
+
+// Core tools that Sisyphus-Junior must NEVER have access to
+// Note: call_omo_agent is ALLOWED so subagents can spawn explore/librarian
+const BLOCKED_TOOLS = ["task"]
+
+export const SISYPHUS_JUNIOR_DEFAULTS = {
+  model: "anthropic/claude-sonnet-4-5",
+  temperature: 0.1,
+} as const
+
+export type SisyphusJuniorPromptSource = "default" | "gpt"
+
+/**
+ * Determines which Sisyphus-Junior prompt to use based on model.
+ */
+export function getSisyphusJuniorPromptSource(model?: string): SisyphusJuniorPromptSource {
+  if (model && isGptModel(model)) {
+    return "gpt"
+  }
+  return "default"
+}
+
+/**
+ * Builds the appropriate Sisyphus-Junior prompt based on model.
+ */
+export function buildSisyphusJuniorPrompt(
+  model: string | undefined,
+  useTaskSystem: boolean,
+  promptAppend?: string
+): string {
+  const source = getSisyphusJuniorPromptSource(model)
+
+  switch (source) {
+    case "gpt":
+      return buildGptSisyphusJuniorPrompt(useTaskSystem, promptAppend)
+    case "default":
+    default:
+      return buildDefaultSisyphusJuniorPrompt(useTaskSystem, promptAppend)
+  }
+}
+
+export function createSisyphusJuniorAgentWithOverrides(
+  override: AgentOverrideConfig | undefined,
+  systemDefaultModel?: string,
+  useTaskSystem = false
+): AgentConfig {
+  if (override?.disable) {
+    override = undefined
+  }
+
+  const model = override?.model ?? systemDefaultModel ?? SISYPHUS_JUNIOR_DEFAULTS.model
+  const temperature = override?.temperature ?? SISYPHUS_JUNIOR_DEFAULTS.temperature
+
+  const promptAppend = override?.prompt_append
+  const prompt = buildSisyphusJuniorPrompt(model, useTaskSystem, promptAppend)
+
+  const baseRestrictions = createAgentToolRestrictions(BLOCKED_TOOLS)
+
+  const userPermission = (override?.permission ?? {}) as Record<string, PermissionValue>
+  const basePermission = baseRestrictions.permission
+  const merged: Record<string, PermissionValue> = { ...userPermission }
+  for (const tool of BLOCKED_TOOLS) {
+    merged[tool] = "deny"
+  }
+  merged.call_omo_agent = "allow"
+  const toolsConfig = { permission: { ...merged, ...basePermission } }
+
+  const base: AgentConfig = {
+    description: override?.description ??
+      "Focused task executor. Same discipline, no delegation. (Sisyphus-Junior - OhMyOpenCode)",
+    mode: MODE,
+    model,
+    temperature,
+    maxTokens: 64000,
+    prompt,
+    color: override?.color ?? "#20B2AA",
+    ...toolsConfig,
+  }
+
+  if (override?.top_p !== undefined) {
+    base.top_p = override.top_p
+  }
+
+  if (isGptModel(model)) {
+    return { ...base, reasoningEffort: "medium" } as AgentConfig
+  }
+
+  return {
+    ...base,
+    thinking: { type: "enabled", budgetTokens: 32000 },
+  } as AgentConfig
+}
+
+createSisyphusJuniorAgentWithOverrides.mode = MODE
--- a/src/agents/sisyphus.ts
+++ b/src/agents/sisyphus.ts
@@ -275,19 +275,13 @@ ${librarianSection}

 \`\`\`typescript
 // CORRECT: Always background, always parallel
-// Prompt structure (each field should be substantive, not a single sentence):
-//   [CONTEXT]: What task I'm working on, which files/modules are involved, and what approach I'm taking
-//   [GOAL]: The specific outcome I need — what decision or action the results will unblock
-//   [DOWNSTREAM]: How I will use the results — what I'll build/decide based on what's found
-//   [REQUEST]: Concrete search instructions — what to find, what format to return, and what to SKIP
-
+// Prompt structure: [CONTEXT: what I'm doing] + [GOAL: what I'm trying to achieve] + [QUESTION: what I need to know] + [REQUEST: what to find]
 // Contextual Grep (internal)
-task(subagent_type="explore", run_in_background=true, load_skills=[], description="Find auth implementations", prompt="I'm implementing JWT auth for the REST API in src/api/routes/. I need to match existing auth conventions so my code fits seamlessly. I'll use this to decide middleware structure and token flow. Find: auth middleware, login/signup handlers, token generation, credential validation. Focus on src/ — skip tests. Return file paths with pattern descriptions.")
-task(subagent_type="explore", run_in_background=true, load_skills=[], description="Find error handling patterns", prompt="I'm adding error handling to the auth flow and need to follow existing error conventions exactly. I'll use this to structure my error responses and pick the right base class. Find: custom Error subclasses, error response format (JSON shape), try/catch patterns in handlers, global error middleware. Skip test files. Return the error class hierarchy and response format.")
-
+task(subagent_type="explore", run_in_background=true, load_skills=[], description="Find auth implementations", prompt="I'm implementing user authentication for our API. I need to understand how auth is currently structured in this codebase. Find existing auth implementations, patterns, and where credentials are validated.")
+task(subagent_type="explore", run_in_background=true, load_skills=[], description="Find error handling patterns", prompt="I'm adding error handling to the auth flow. I want to follow existing project conventions for consistency. Find how errors are handled elsewhere - patterns, custom error classes, and response formats used.")
 // Reference Grep (external)
-task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find JWT security docs", prompt="I'm implementing JWT auth and need current security best practices to choose token storage (httpOnly cookies vs localStorage) and set expiration policy. Find: OWASP auth guidelines, recommended token lifetimes, refresh token rotation strategies, common JWT vulnerabilities. Skip 'what is JWT' tutorials — production security guidance only.")
-task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find Express auth patterns", prompt="I'm building Express auth middleware and need production-quality patterns to structure my middleware chain. Find how established Express apps (1000+ stars) handle: middleware ordering, token refresh, role-based access control, auth error propagation. Skip basic tutorials — I need battle-tested patterns with proper error handling.")
+task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find JWT security docs", prompt="I'm implementing JWT-based auth and need to ensure security best practices. Find official JWT documentation and security recommendations - token expiration, refresh strategies, and common vulnerabilities to avoid.")
+task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find Express auth patterns", prompt="I'm building Express middleware for auth and want production-quality patterns. Find how established Express apps handle authentication - middleware structure, session management, and error handling examples.")
 // Continue working immediately. Collect with background_output when needed.

 // WRONG: Sequential or blocking
--- a/src/agents/utils.test.ts
+++ b/src/agents/utils.test.ts
@@ -1,7 +1,5 @@
-/// <reference types="bun-types" />
-
 import { describe, test, expect, beforeEach, afterEach, spyOn } from "bun:test"
-import { createBuiltinAgents } from "./builtin-agents"
+import { createBuiltinAgents } from "./utils"
 import type { AgentConfig } from "@opencode-ai/sdk"
 import { clearSkillCache } from "../features/opencode-skill-loader/skill-content"
 import * as connectedProvidersCache from "../shared/connected-providers-cache"
@@ -761,7 +759,7 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
 })

 describe("buildAgent with category and skills", () => {
-  const { buildAgent } = require("./agent-builder")
+  const { buildAgent } = require("./utils")
  const TEST_MODEL = "anthropic/claude-opus-4-6"

  beforeEach(() => {
--- a/src/agents/utils.ts
+++ b/src/agents/utils.ts
@@ -0,0 +1,571 @@
+import type { AgentConfig } from "@opencode-ai/sdk"
+import type { BuiltinAgentName, AgentOverrideConfig, AgentOverrides, AgentFactory, AgentPromptMetadata } from "./types"
+import type { CategoriesConfig, CategoryConfig, GitMasterConfig } from "../config/schema"
+import { createSisyphusAgent } from "./sisyphus"
+import { createOracleAgent, ORACLE_PROMPT_METADATA } from "./oracle"
+import { createLibrarianAgent, LIBRARIAN_PROMPT_METADATA } from "./librarian"
+import { createExploreAgent, EXPLORE_PROMPT_METADATA } from "./explore"
+import { createMultimodalLookerAgent, MULTIMODAL_LOOKER_PROMPT_METADATA } from "./multimodal-looker"
+import { createMetisAgent, metisPromptMetadata } from "./metis"
+import { createAtlasAgent, atlasPromptMetadata } from "./atlas"
+import { createMomusAgent, momusPromptMetadata } from "./momus"
+import { createHephaestusAgent } from "./hephaestus"
+import type { AvailableAgent, AvailableCategory, AvailableSkill } from "./dynamic-agent-prompt-builder"
+import {
+  deepMerge,
+  fetchAvailableModels,
+  resolveModelPipeline,
+  AGENT_MODEL_REQUIREMENTS,
+  readConnectedProvidersCache,
+  isModelAvailable,
+  isAnyFallbackModelAvailable,
+  isAnyProviderConnected,
+  migrateAgentConfig,
+  truncateDescription,
+} from "../shared"
+import { DEFAULT_CATEGORIES, CATEGORY_DESCRIPTIONS } from "../tools/delegate-task/constants"
+import { resolveMultipleSkills } from "../features/opencode-skill-loader/skill-content"
+import { createBuiltinSkills } from "../features/builtin-skills"
+import type { LoadedSkill, SkillScope } from "../features/opencode-skill-loader/types"
+import type { BrowserAutomationProvider } from "../config/schema"
+
+type AgentSource = AgentFactory | AgentConfig
+
+const agentSources: Record<BuiltinAgentName, AgentSource> = {
+  sisyphus: createSisyphusAgent,
+  hephaestus: createHephaestusAgent,
+  oracle: createOracleAgent,
+  librarian: createLibrarianAgent,
+  explore: createExploreAgent,
+  "multimodal-looker": createMultimodalLookerAgent,
+  metis: createMetisAgent,
+  momus: createMomusAgent,
+  // Note: Atlas is handled specially in createBuiltinAgents()
+  // because it needs OrchestratorContext, not just a model string
+  atlas: createAtlasAgent as unknown as AgentFactory,
+}
+
+/**
+ * Metadata for each agent, used to build Sisyphus's dynamic prompt sections
+ * (Delegation Table, Tool Selection, Key Triggers, etc.)
+ */
+const agentMetadata: Partial<Record<BuiltinAgentName, AgentPromptMetadata>> = {
+  oracle: ORACLE_PROMPT_METADATA,
+  librarian: LIBRARIAN_PROMPT_METADATA,
+  explore: EXPLORE_PROMPT_METADATA,
+  "multimodal-looker": MULTIMODAL_LOOKER_PROMPT_METADATA,
+  metis: metisPromptMetadata,
+  momus: momusPromptMetadata,
+  atlas: atlasPromptMetadata,
+}
+
+function isFactory(source: AgentSource): source is AgentFactory {
+  return typeof source === "function"
+}
+
+type RegisteredAgentSummary = {
+  name: string
+  description: string
+}
+
+function sanitizeMarkdownTableCell(value: string): string {
+  return value
+    .replace(/\r?\n/g, " ")
+    .replace(/\|/g, "\\|")
+    .replace(/\s+/g, " ")
+    .trim()
+}
+
+function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === "object" && value !== null
+}
+
+function parseRegisteredAgentSummaries(input: unknown): RegisteredAgentSummary[] {
+  if (!Array.isArray(input)) return []
+
+  const result: RegisteredAgentSummary[] = []
+  for (const item of input) {
+    if (!isRecord(item)) continue
+
+    const name = typeof item.name === "string" ? item.name : undefined
+    if (!name) continue
+
+    const hidden = item.hidden
+    if (hidden === true) continue
+
+    const disabled = item.disabled
+    if (disabled === true) continue
+
+    const enabled = item.enabled
+    if (enabled === false) continue
+
+    const description = typeof item.description === "string" ? item.description : ""
+    result.push({ name, description: sanitizeMarkdownTableCell(description) })
+  }
+
+  return result
+}
+
+function buildCustomAgentMetadata(agentName: string, description: string): AgentPromptMetadata {
+  const shortDescription = sanitizeMarkdownTableCell(truncateDescription(description))
+  const safeAgentName = sanitizeMarkdownTableCell(agentName)
+  return {
+    category: "specialist",
+    cost: "CHEAP",
+    triggers: [
+      {
+        domain: `Custom agent: ${safeAgentName}`,
+        trigger: shortDescription || "Use when this agent's description matches the task",
+      },
+    ],
+  }
+}
+
+export function buildAgent(
+  source: AgentSource,
+  model: string,
+  categories?: CategoriesConfig,
+  gitMasterConfig?: GitMasterConfig,
+  browserProvider?: BrowserAutomationProvider,
+  disabledSkills?: Set<string>
+): AgentConfig {
+  const base = isFactory(source) ? source(model) : source
+  const categoryConfigs: Record<string, CategoryConfig> = categories
+    ? { ...DEFAULT_CATEGORIES, ...categories }
+    : DEFAULT_CATEGORIES
+
+  const agentWithCategory = base as AgentConfig & { category?: string; skills?: string[]; variant?: string }
+  if (agentWithCategory.category) {
+    const categoryConfig = categoryConfigs[agentWithCategory.category]
+    if (categoryConfig) {
+      if (!base.model) {
+        base.model = categoryConfig.model
+      }
+      if (base.temperature === undefined && categoryConfig.temperature !== undefined) {
+        base.temperature = categoryConfig.temperature
+      }
+      if (base.variant === undefined && categoryConfig.variant !== undefined) {
+        base.variant = categoryConfig.variant
+      }
+    }
+  }
+
+  if (agentWithCategory.skills?.length) {
+    const { resolved } = resolveMultipleSkills(agentWithCategory.skills, { gitMasterConfig, browserProvider, disabledSkills })
+    if (resolved.size > 0) {
+      const skillContent = Array.from(resolved.values()).join("\n\n")
+      base.prompt = skillContent + (base.prompt ? "\n\n" + base.prompt : "")
+    }
+  }
+
+  return base
+}
+
+/**
+ * Creates OmO-specific environment context (time, timezone, locale).
+ * Note: Working directory, platform, and date are already provided by OpenCode's system.ts,
+ * so we only include fields that OpenCode doesn't provide to avoid duplication.
+ * See: https://github.com/code-yeongyu/oh-my-opencode/issues/379
+ */
+export function createEnvContext(): string {
+  const now = new Date()
+  const timezone = Intl.DateTimeFormat().resolvedOptions().timeZone
+  const locale = Intl.DateTimeFormat().resolvedOptions().locale
+
+  const dateStr = now.toLocaleDateString(locale, {
+    weekday: "short",
+    year: "numeric",
+    month: "short",
+    day: "numeric",
+  })
+
+  const timeStr = now.toLocaleTimeString(locale, {
+    hour: "2-digit",
+    minute: "2-digit",
+    second: "2-digit",
+    hour12: true,
+  })
+
+  return `
+<omo-env>
+  Current date: ${dateStr}
+  Current time: ${timeStr}
+  Timezone: ${timezone}
+  Locale: ${locale}
+</omo-env>`
+}
+
+/**
+ * Expands a category reference from an agent override into concrete config properties.
+ * Category properties are applied unconditionally (overwriting factory defaults),
+ * because the user's chosen category should take priority over factory base values.
+ * Direct override properties applied later via mergeAgentConfig() will supersede these.
+ */
+function applyCategoryOverride(
+  config: AgentConfig,
+  categoryName: string,
+  mergedCategories: Record<string, CategoryConfig>
+): AgentConfig {
+  const categoryConfig = mergedCategories[categoryName]
+  if (!categoryConfig) return config
+
+  const result = { ...config } as AgentConfig & Record<string, unknown>
+  if (categoryConfig.model) result.model = categoryConfig.model
+  if (categoryConfig.variant !== undefined) result.variant = categoryConfig.variant
+  if (categoryConfig.temperature !== undefined) result.temperature = categoryConfig.temperature
+  if (categoryConfig.reasoningEffort !== undefined) result.reasoningEffort = categoryConfig.reasoningEffort
+  if (categoryConfig.textVerbosity !== undefined) result.textVerbosity = categoryConfig.textVerbosity
+  if (categoryConfig.thinking !== undefined) result.thinking = categoryConfig.thinking
+  if (categoryConfig.top_p !== undefined) result.top_p = categoryConfig.top_p
+  if (categoryConfig.maxTokens !== undefined) result.maxTokens = categoryConfig.maxTokens
+
+  return result as AgentConfig
+}
+
+function applyModelResolution(input: {
+  uiSelectedModel?: string
+  userModel?: string
+  requirement?: { fallbackChain?: { providers: string[]; model: string; variant?: string }[] }
+  availableModels: Set<string>
+  systemDefaultModel?: string
+}) {
+  const { uiSelectedModel, userModel, requirement, availableModels, systemDefaultModel } = input
+  return resolveModelPipeline({
+    intent: { uiSelectedModel, userModel },
+    constraints: { availableModels },
+    policy: { fallbackChain: requirement?.fallbackChain, systemDefaultModel },
+  })
+}
+
+function getFirstFallbackModel(requirement?: {
+  fallbackChain?: { providers: string[]; model: string; variant?: string }[]
+}) {
+  const entry = requirement?.fallbackChain?.[0]
+  if (!entry || entry.providers.length === 0) return undefined
+  return {
+    model: `${entry.providers[0]}/${entry.model}`,
+    provenance: "provider-fallback" as const,
+    variant: entry.variant,
+  }
+}
+
+function applyEnvironmentContext(config: AgentConfig, directory?: string): AgentConfig {
+  if (!directory || !config.prompt) return config
+  const envContext = createEnvContext()
+  return { ...config, prompt: config.prompt + envContext }
+}
+
+function applyOverrides(
+  config: AgentConfig,
+  override: AgentOverrideConfig | undefined,
+  mergedCategories: Record<string, CategoryConfig>
+): AgentConfig {
+  let result = config
+  const overrideCategory = (override as Record<string, unknown> | undefined)?.category as string | undefined
+  if (overrideCategory) {
+    result = applyCategoryOverride(result, overrideCategory, mergedCategories)
+  }
+
+  if (override) {
+    result = mergeAgentConfig(result, override)
+  }
+
+  return result
+}
+
+function mergeAgentConfig(
+  base: AgentConfig,
+  override: AgentOverrideConfig
+): AgentConfig {
+  const migratedOverride = migrateAgentConfig(override as Record<string, unknown>) as AgentOverrideConfig
+  const { prompt_append, ...rest } = migratedOverride
+  const merged = deepMerge(base, rest as Partial<AgentConfig>)
+
+  if (prompt_append && merged.prompt) {
+    merged.prompt = merged.prompt + "\n" + prompt_append
+  }
+
+  return merged
+}
+
+function mapScopeToLocation(scope: SkillScope): AvailableSkill["location"] {
+  if (scope === "user" || scope === "opencode") return "user"
+  if (scope === "project" || scope === "opencode-project") return "project"
+  return "plugin"
+}
+
+export async function createBuiltinAgents(
+  disabledAgents: string[] = [],
+  agentOverrides: AgentOverrides = {},
+  directory?: string,
+  systemDefaultModel?: string,
+  categories?: CategoriesConfig,
+  gitMasterConfig?: GitMasterConfig,
+  discoveredSkills: LoadedSkill[] = [],
+  customAgentSummaries?: unknown,
+  browserProvider?: BrowserAutomationProvider,
+  uiSelectedModel?: string,
+  disabledSkills?: Set<string>
+): Promise<Record<string, AgentConfig>> {
+  const connectedProviders = readConnectedProvidersCache()
+  // IMPORTANT: Do NOT call OpenCode client APIs during plugin initialization.
+  // This function is called from config handler, and calling client API causes deadlock.
+  // See: https://github.com/code-yeongyu/oh-my-opencode/issues/1301
+  const availableModels = await fetchAvailableModels(undefined, {
+    connectedProviders: connectedProviders ?? undefined,
+  })
+  const isFirstRunNoCache =
+    availableModels.size === 0 && (!connectedProviders || connectedProviders.length === 0)
+
+  const result: Record<string, AgentConfig> = {}
+  const availableAgents: AvailableAgent[] = []
+
+  const mergedCategories = categories
+    ? { ...DEFAULT_CATEGORIES, ...categories }
+    : DEFAULT_CATEGORIES
+
+  const availableCategories: AvailableCategory[] = Object.entries(mergedCategories).map(([name]) => ({
+    name,
+    description: categories?.[name]?.description ?? CATEGORY_DESCRIPTIONS[name] ?? "General tasks",
+  }))
+
+  const builtinSkills = createBuiltinSkills({ browserProvider, disabledSkills })
+  const builtinSkillNames = new Set(builtinSkills.map(s => s.name))
+
+  const builtinAvailable: AvailableSkill[] = builtinSkills.map((skill) => ({
+    name: skill.name,
+    description: skill.description,
+    location: "plugin" as const,
+  }))
+
+  const discoveredAvailable: AvailableSkill[] = discoveredSkills
+    .filter(s => !builtinSkillNames.has(s.name))
+    .map((skill) => ({
+      name: skill.name,
+      description: skill.definition.description ?? "",
+      location: mapScopeToLocation(skill.scope),
+    }))
+
+  const availableSkills: AvailableSkill[] = [...builtinAvailable, ...discoveredAvailable]
+
+  const registeredAgents = parseRegisteredAgentSummaries(customAgentSummaries)
+  const builtinAgentNames = new Set(Object.keys(agentSources).map((n) => n.toLowerCase()))
+  const disabledAgentNames = new Set(disabledAgents.map((n) => n.toLowerCase()))
+
+  // Collect general agents first (for availableAgents), but don't add to result yet
+  const pendingAgentConfigs: Map<string, AgentConfig> = new Map()
+
+   for (const [name, source] of Object.entries(agentSources)) {
+     const agentName = name as BuiltinAgentName
+
+     if (agentName === "sisyphus") continue
+     if (agentName === "hephaestus") continue
+     if (agentName === "atlas") continue
+     if (disabledAgents.some((name) => name.toLowerCase() === agentName.toLowerCase())) continue
+
+     const override = agentOverrides[agentName]
+       ?? Object.entries(agentOverrides).find(([key]) => key.toLowerCase() === agentName.toLowerCase())?.[1]
+     const requirement = AGENT_MODEL_REQUIREMENTS[agentName]
+
+     // Check if agent requires a specific model
+     if (requirement?.requiresModel && availableModels) {
+       if (!isModelAvailable(requirement.requiresModel, availableModels)) {
+         continue
+       }
+     }
+
+     const isPrimaryAgent = isFactory(source) && source.mode === "primary"
+
+    const resolution = applyModelResolution({
+      uiSelectedModel: (isPrimaryAgent && !override?.model) ? uiSelectedModel : undefined,
+      userModel: override?.model,
+      requirement,
+      availableModels,
+      systemDefaultModel,
+    })
+    if (!resolution) continue
+    const { model, variant: resolvedVariant } = resolution
+
+    let config = buildAgent(source, model, mergedCategories, gitMasterConfig, browserProvider, disabledSkills)
+    
+    // Apply resolved variant from model fallback chain
+    if (resolvedVariant) {
+      config = { ...config, variant: resolvedVariant }
+    }
+
+    // Expand override.category into concrete properties (higher priority than factory/resolved)
+    const overrideCategory = (override as Record<string, unknown> | undefined)?.category as string | undefined
+    if (overrideCategory) {
+      config = applyCategoryOverride(config, overrideCategory, mergedCategories)
+    }
+
+    if (agentName === "librarian") {
+      config = applyEnvironmentContext(config, directory)
+    }
+
+    config = applyOverrides(config, override, mergedCategories)
+
+    // Store for later - will be added after sisyphus and hephaestus
+    pendingAgentConfigs.set(name, config)
+
+     const metadata = agentMetadata[agentName]
+     if (metadata) {
+       availableAgents.push({
+         name: agentName,
+         description: config.description ?? "",
+         metadata,
+       })
+     }
+   }
+
+  for (const agent of registeredAgents) {
+    const lowerName = agent.name.toLowerCase()
+    if (builtinAgentNames.has(lowerName)) continue
+    if (disabledAgentNames.has(lowerName)) continue
+    if (availableAgents.some((a) => a.name.toLowerCase() === lowerName)) continue
+
+    availableAgents.push({
+      name: agent.name,
+      description: agent.description,
+      metadata: buildCustomAgentMetadata(agent.name, agent.description),
+    })
+  }
+
+   const sisyphusOverride = agentOverrides["sisyphus"]
+   const sisyphusRequirement = AGENT_MODEL_REQUIREMENTS["sisyphus"]
+   const hasSisyphusExplicitConfig = sisyphusOverride !== undefined
+   const meetsSisyphusAnyModelRequirement =
+     !sisyphusRequirement?.requiresAnyModel ||
+     hasSisyphusExplicitConfig ||
+     isFirstRunNoCache ||
+     isAnyFallbackModelAvailable(sisyphusRequirement.fallbackChain, availableModels)
+
+   if (!disabledAgents.includes("sisyphus") && meetsSisyphusAnyModelRequirement) {
+    let sisyphusResolution = applyModelResolution({
+      uiSelectedModel: sisyphusOverride?.model ? undefined : uiSelectedModel,
+      userModel: sisyphusOverride?.model,
+      requirement: sisyphusRequirement,
+      availableModels,
+      systemDefaultModel,
+    })
+
+    if (isFirstRunNoCache && !sisyphusOverride?.model && !uiSelectedModel) {
+      sisyphusResolution = getFirstFallbackModel(sisyphusRequirement)
+    }
+
+    if (sisyphusResolution) {
+      const { model: sisyphusModel, variant: sisyphusResolvedVariant } = sisyphusResolution
+
+      let sisyphusConfig = createSisyphusAgent(
+        sisyphusModel,
+        availableAgents,
+        undefined,
+        availableSkills,
+        availableCategories
+      )
+
+      if (sisyphusResolvedVariant) {
+        sisyphusConfig = { ...sisyphusConfig, variant: sisyphusResolvedVariant }
+      }
+
+      sisyphusConfig = applyOverrides(sisyphusConfig, sisyphusOverride, mergedCategories)
+      sisyphusConfig = applyEnvironmentContext(sisyphusConfig, directory)
+
+      result["sisyphus"] = sisyphusConfig
+    }
+   }
+
+  if (!disabledAgents.includes("hephaestus")) {
+    const hephaestusOverride = agentOverrides["hephaestus"]
+    const hephaestusRequirement = AGENT_MODEL_REQUIREMENTS["hephaestus"]
+    const hasHephaestusExplicitConfig = hephaestusOverride !== undefined
+
+    const hasRequiredProvider =
+      !hephaestusRequirement?.requiresProvider ||
+      hasHephaestusExplicitConfig ||
+      isFirstRunNoCache ||
+      isAnyProviderConnected(hephaestusRequirement.requiresProvider, availableModels)
+
+    if (hasRequiredProvider) {
+      let hephaestusResolution = applyModelResolution({
+        userModel: hephaestusOverride?.model,
+        requirement: hephaestusRequirement,
+        availableModels,
+        systemDefaultModel,
+      })
+
+      if (isFirstRunNoCache && !hephaestusOverride?.model) {
+        hephaestusResolution = getFirstFallbackModel(hephaestusRequirement)
+      }
+
+      if (hephaestusResolution) {
+        const { model: hephaestusModel, variant: hephaestusResolvedVariant } = hephaestusResolution
+
+        let hephaestusConfig = createHephaestusAgent(
+          hephaestusModel,
+          availableAgents,
+          undefined,
+          availableSkills,
+          availableCategories
+        )
+
+        if (!hephaestusOverride?.variant) {
+          hephaestusConfig = { ...hephaestusConfig, variant: hephaestusResolvedVariant ?? "medium" }
+        }
+        const hepOverrideCategory = (hephaestusOverride as Record<string, unknown> | undefined)?.category as string | undefined
+        if (hepOverrideCategory) {
+          hephaestusConfig = applyCategoryOverride(hephaestusConfig, hepOverrideCategory, mergedCategories)
+        }
+        if (directory && hephaestusConfig.prompt) {
+          const envContext = createEnvContext()
+          hephaestusConfig = { ...hephaestusConfig, prompt: hephaestusConfig.prompt + envContext }
+        }
+
+        if (hephaestusOverride) {
+          hephaestusConfig = mergeAgentConfig(hephaestusConfig, hephaestusOverride)
+        }
+
+        result["hephaestus"] = hephaestusConfig
+      }
+    }
+   }
+
+   // Add pending agents after sisyphus and hephaestus to maintain order
+   for (const [name, config] of pendingAgentConfigs) {
+     result[name] = config
+   }
+
+    if (!disabledAgents.includes("atlas")) {
+      const orchestratorOverride = agentOverrides["atlas"]
+      const atlasRequirement = AGENT_MODEL_REQUIREMENTS["atlas"]
+
+      const atlasResolution = applyModelResolution({
+        uiSelectedModel: orchestratorOverride?.model ? undefined : uiSelectedModel,
+        userModel: orchestratorOverride?.model,
+        requirement: atlasRequirement,
+        availableModels,
+        systemDefaultModel,
+      })
+    
+    if (atlasResolution) {
+      const { model: atlasModel, variant: atlasResolvedVariant } = atlasResolution
+
+      let orchestratorConfig = createAtlasAgent({
+        model: atlasModel,
+        availableAgents,
+        availableSkills,
+        userCategories: categories,
+      })
+
+      if (atlasResolvedVariant) {
+        orchestratorConfig = { ...orchestratorConfig, variant: atlasResolvedVariant }
+      }
+
+      orchestratorConfig = applyOverrides(orchestratorConfig, orchestratorOverride, mergedCategories)
+
+      result["atlas"] = orchestratorConfig
+    }
+   }
+
+   return result
+ }
--- a/src/cli/AGENTS.md
+++ b/src/cli/AGENTS.md
@@ -2,71 +2,79 @@

 ## OVERVIEW

-CLI entry: `bunx oh-my-opencode`. 107+ files with Commander.js + @clack/prompts TUI.
+CLI entry: `bunx oh-my-opencode`. 70 CLI utilities and commands with Commander.js + @clack/prompts TUI.

-**Commands**: install, run, doctor, get-local-version, mcp-oauth
+**Commands**: install (interactive setup), doctor (14 health checks), run (session launcher), get-local-version, mcp-oauth

 ## STRUCTURE
+
 ```
 cli/
-├── index.ts                 # Entry point (5 lines)
-├── cli-program.ts           # Commander.js program (150+ lines, 5 commands)
-├── install.ts               # TTY routing (TUI or CLI installer)
-├── cli-installer.ts         # Non-interactive installer (164 lines)
-├── tui-installer.ts         # Interactive TUI with @clack/prompts (140 lines)
-├── config-manager/          # 17 config utilities
-│   ├── add-plugin-to-opencode-config.ts  # Plugin registration
-│   ├── add-provider-config.ts            # Provider setup
-│   ├── detect-current-config.ts          # Project vs user config
-│   ├── write-omo-config.ts               # JSONC writing
-│   └── ...
-├── doctor/                  # 14 health checks
-│   ├── runner.ts            # Check orchestration
-│   ├── formatter.ts         # Colored output
-│   └── checks/              # 29 files: auth, config, dependencies, gh, lsp, mcp, opencode, plugin, version, model-resolution (6 sub-checks)
-├── run/                     # Session launcher (24 files)
-│   ├── runner.ts            # Run orchestration (126 lines)
-│   ├── agent-resolver.ts    # Agent selection: flag → env → config → fallback
-│   ├── session-resolver.ts  # Session creation or resume
-│   ├── event-handlers.ts    # Event processing (125 lines)
-│   ├── completion.ts        # Completion detection
-│   └── poll-for-completion.ts # Polling with timeout
-├── mcp-oauth/               # OAuth token management (login, logout, status)
-├── get-local-version/       # Version detection + update check
-├── model-fallback.ts        # Model fallback configuration
-└── provider-availability.ts # Provider availability checks
+├── index.ts              # Commander.js entry (5 commands)
+├── install.ts            # Interactive TUI (542 lines)
+├── config-manager.ts     # JSONC parsing (667 lines)
+├── model-fallback.ts     # Model fallback configuration
+├── types.ts              # InstallArgs, InstallConfig
+├── doctor/
+│   ├── index.ts          # Doctor entry
+│   ├── runner.ts         # Check orchestration
+│   ├── formatter.ts      # Colored output
+│   ├── constants.ts      # Check IDs, symbols
+│   ├── types.ts          # CheckResult, CheckDefinition
+│   └── checks/           # 14 checks, 23 files
+│       ├── version.ts    # OpenCode + plugin version
+│       ├── config.ts     # JSONC validity, Zod
+│       ├── auth.ts       # Anthropic, OpenAI, Google
+│       ├── dependencies.ts # AST-Grep, Comment Checker
+│       ├── lsp.ts        # LSP connectivity
+│       ├── mcp.ts        # MCP validation
+│       ├── model-resolution.ts # Model resolution check (323 lines)
+│       └── gh.ts         # GitHub CLI
+├── run/
+│   ├── index.ts          # Session launcher
+│   └── events.ts         # CLI run events (325 lines)
+├── mcp-oauth/
+│   └── index.ts          # MCP OAuth flow
+└── get-local-version/
+    └── index.ts          # Version detection
 ```

 ## COMMANDS

-| Command | Purpose | Key Logic |
-|---------|---------|-----------|
-| `install` | Interactive setup | Provider selection → config generation → plugin registration |
-| `run` | Session launcher | Agent: flag → env → config → Sisyphus. Enforces todo completion. |
-| `doctor` | 14 health checks | installation, config, auth, deps, tools, updates |
-| `get-local-version` | Version check | Detects installed, compares with npm latest |
-| `mcp-oauth` | OAuth tokens | login (PKCE flow), logout, status |
+| Command | Purpose |
+|---------|---------|
+| `install` | Interactive setup with provider selection |
+| `doctor` | 14 health checks for diagnostics |
+| `run` | Launch session with todo enforcement |
+| `get-local-version` | Version detection and update check |
+| `mcp-oauth` | MCP OAuth authentication flow |

-## DOCTOR CHECK CATEGORIES
+## DOCTOR CATEGORIES (14 Checks)

 | Category | Checks |
 |----------|--------|
 | installation | opencode, plugin |
-| configuration | config validity, Zod, model-resolution (6 sub-checks) |
+| configuration | config validity, Zod, model-resolution |
 | authentication | anthropic, openai, google |
 | dependencies | ast-grep, comment-checker, gh-cli |
-| tools | LSP, MCP, MCP-OAuth |
+| tools | LSP, MCP |
 | updates | version comparison |

 ## HOW TO ADD CHECK

 1. Create `src/cli/doctor/checks/my-check.ts`
-2. Export `getXXXCheckDefinition()` returning `CheckDefinition`
+2. Export `getXXXCheckDefinition()` factory returning `CheckDefinition`
 3. Add to `getAllCheckDefinitions()` in `checks/index.ts`

+## TUI FRAMEWORK
+
+- **@clack/prompts**: `select()`, `spinner()`, `intro()`, `outro()`
+- **picocolors**: Terminal colors for status and headers
+- **Symbols**: ✓ (pass), ✗ (fail), ⚠ (warn), ℹ (info)
+
 ## ANTI-PATTERNS

- **Blocking in non-TTY**: Check `process.stdout.isTTY`
- **Direct JSON.parse**: Use `parseJsonc()` from shared
- **Silent failures**: Return `warn` or `fail` in doctor, don't throw
- **Hardcoded paths**: Use `getOpenCodeConfigPaths()` from config-manager
+- **Blocking in non-TTY**: Always check `process.stdout.isTTY`
+- **Direct JSON.parse**: Use `parseJsonc()` from shared utils
+- **Silent failures**: Return `warn` or `fail` in doctor instead of throwing
+- **Hardcoded paths**: Use `getOpenCodeConfigPaths()` from `config-manager.ts`
--- a/src/cli/cli-installer.ts
+++ b/src/cli/cli-installer.ts
@@ -1,164 +0,0 @@
-import color from "picocolors"
-import type { InstallArgs } from "./types"
-import {
-  addAuthPlugins,
-  addPluginToOpenCodeConfig,
-  addProviderConfig,
-  detectCurrentConfig,
-  getOpenCodeVersion,
-  isOpenCodeInstalled,
-  writeOmoConfig,
-} from "./config-manager"
-import {
-  SYMBOLS,
-  argsToConfig,
-  detectedToInitialValues,
-  formatConfigSummary,
-  printBox,
-  printError,
-  printHeader,
-  printInfo,
-  printStep,
-  printSuccess,
-  printWarning,
-  validateNonTuiArgs,
-} from "./install-validators"
-
-export async function runCliInstaller(args: InstallArgs, version: string): Promise<number> {
-  const validation = validateNonTuiArgs(args)
-  if (!validation.valid) {
-    printHeader(false)
-    printError("Validation failed:")
-    for (const err of validation.errors) {
-      console.log(`  ${SYMBOLS.bullet} ${err}`)
-    }
-    console.log()
-    printInfo(
-      "Usage: bunx oh-my-opencode install --no-tui --claude=<no|yes|max20> --gemini=<no|yes> --copilot=<no|yes>",
-    )
-    console.log()
-    return 1
-  }
-
-  const detected = detectCurrentConfig()
-  const isUpdate = detected.isInstalled
-
-  printHeader(isUpdate)
-
-  const totalSteps = 6
-  let step = 1
-
-  printStep(step++, totalSteps, "Checking OpenCode installation...")
-  const installed = await isOpenCodeInstalled()
-  const openCodeVersion = await getOpenCodeVersion()
-  if (!installed) {
-    printWarning(
-      "OpenCode binary not found. Plugin will be configured, but you'll need to install OpenCode to use it.",
-    )
-    printInfo("Visit https://opencode.ai/docs for installation instructions")
-  } else {
-    printSuccess(`OpenCode ${openCodeVersion ?? ""} detected`)
-  }
-
-  if (isUpdate) {
-    const initial = detectedToInitialValues(detected)
-    printInfo(`Current config: Claude=${initial.claude}, Gemini=${initial.gemini}`)
-  }
-
-  const config = argsToConfig(args)
-
-  printStep(step++, totalSteps, "Adding oh-my-opencode plugin...")
-  const pluginResult = await addPluginToOpenCodeConfig(version)
-  if (!pluginResult.success) {
-    printError(`Failed: ${pluginResult.error}`)
-    return 1
-  }
-  printSuccess(
-    `Plugin ${isUpdate ? "verified" : "added"} ${SYMBOLS.arrow} ${color.dim(pluginResult.configPath)}`,
-  )
-
-  if (config.hasGemini) {
-    printStep(step++, totalSteps, "Adding auth plugins...")
-    const authResult = await addAuthPlugins(config)
-    if (!authResult.success) {
-      printError(`Failed: ${authResult.error}`)
-      return 1
-    }
-    printSuccess(`Auth plugins configured ${SYMBOLS.arrow} ${color.dim(authResult.configPath)}`)
-
-    printStep(step++, totalSteps, "Adding provider configurations...")
-    const providerResult = addProviderConfig(config)
-    if (!providerResult.success) {
-      printError(`Failed: ${providerResult.error}`)
-      return 1
-    }
-    printSuccess(`Providers configured ${SYMBOLS.arrow} ${color.dim(providerResult.configPath)}`)
-  } else {
-    step += 2
-  }
-
-  printStep(step++, totalSteps, "Writing oh-my-opencode configuration...")
-  const omoResult = writeOmoConfig(config)
-  if (!omoResult.success) {
-    printError(`Failed: ${omoResult.error}`)
-    return 1
-  }
-  printSuccess(`Config written ${SYMBOLS.arrow} ${color.dim(omoResult.configPath)}`)
-
-  printBox(formatConfigSummary(config), isUpdate ? "Updated Configuration" : "Installation Complete")
-
-  if (!config.hasClaude) {
-    console.log()
-    console.log(color.bgRed(color.white(color.bold(" CRITICAL WARNING "))))
-    console.log()
-    console.log(color.red(color.bold("  Sisyphus agent is STRONGLY optimized for Claude Opus 4.5.")))
-    console.log(color.red("  Without Claude, you may experience significantly degraded performance:"))
-    console.log(color.dim("    • Reduced orchestration quality"))
-    console.log(color.dim("    • Weaker tool selection and delegation"))
-    console.log(color.dim("    • Less reliable task completion"))
-    console.log()
-    console.log(color.yellow("  Consider subscribing to Claude Pro/Max for the best experience."))
-    console.log()
-  }
-
-  if (
-    !config.hasClaude &&
-    !config.hasOpenAI &&
-    !config.hasGemini &&
-    !config.hasCopilot &&
-    !config.hasOpencodeZen
-  ) {
-    printWarning("No model providers configured. Using opencode/glm-4.7-free as fallback.")
-  }
-
-  console.log(`${SYMBOLS.star} ${color.bold(color.green(isUpdate ? "Configuration updated!" : "Installation complete!"))}`)
-  console.log(`  Run ${color.cyan("opencode")} to start!`)
-  console.log()
-
-  printBox(
-    `${color.bold("Pro Tip:")} Include ${color.cyan("ultrawork")} (or ${color.cyan("ulw")}) in your prompt.\n` +
-      `All features work like magic—parallel agents, background tasks,\n` +
-      `deep exploration, and relentless execution until completion.`,
-    "The Magic Word",
-  )
-
-  console.log(`${SYMBOLS.star} ${color.yellow("If you found this helpful, consider starring the repo!")}`)
-  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()
-
-  if ((config.hasClaude || config.hasGemini || config.hasCopilot) && !args.skipAuth) {
-    printBox(
-      `Run ${color.cyan("opencode auth login")} and select your provider:\n` +
-        (config.hasClaude ? `  ${SYMBOLS.bullet} Anthropic ${color.gray("→ Claude Pro/Max")}\n` : "") +
-        (config.hasGemini ? `  ${SYMBOLS.bullet} Google ${color.gray("→ OAuth with Antigravity")}\n` : "") +
-        (config.hasCopilot ? `  ${SYMBOLS.bullet} GitHub ${color.gray("→ Copilot")}` : ""),
-      "Authenticate Your Providers",
-    )
-  }
-
-  return 0
-}
--- a/src/cli/cli-program.ts
+++ b/src/cli/cli-program.ts
@@ -1,191 +0,0 @@
-import { Command } from "commander"
-import { install } from "./install"
-import { run } from "./run"
-import { getLocalVersion } from "./get-local-version"
-import { doctor } from "./doctor"
-import { createMcpOAuthCommand } from "./mcp-oauth"
-import type { InstallArgs } from "./types"
-import type { RunOptions } from "./run"
-import type { GetLocalVersionOptions } from "./get-local-version/types"
-import type { DoctorOptions } from "./doctor"
-import packageJson from "../../package.json" with { type: "json" }
-
-const VERSION = packageJson.version
-
-const program = new Command()
-
-program
-  .name("oh-my-opencode")
-  .description("The ultimate OpenCode plugin - multi-model orchestration, LSP tools, and more")
-  .version(VERSION, "-v, --version", "Show version number")
-  .enablePositionalOptions()
-
-program
-  .command("install")
-  .description("Install and configure oh-my-opencode with interactive setup")
-  .option("--no-tui", "Run in non-interactive mode (requires all options)")
-  .option("--claude <value>", "Claude subscription: no, yes, max20")
-  .option("--openai <value>", "OpenAI/ChatGPT subscription: no, yes (default: no)")
-  .option("--gemini <value>", "Gemini integration: no, yes")
-  .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:
-  $ bunx oh-my-opencode install
-  $ 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 > 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-4-6, 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 = {
-      tui: options.tui !== false,
-      claude: options.claude,
-      openai: options.openai,
-      gemini: options.gemini,
-      copilot: options.copilot,
-      opencodeZen: options.opencodeZen,
-      zaiCodingPlan: options.zaiCodingPlan,
-      kimiForCoding: options.kimiForCoding,
-      skipAuth: options.skipAuth ?? false,
-    }
-    const exitCode = await install(args)
-    process.exit(exitCode)
-  })
-
-program
-   .command("run <message>")
-   .allowUnknownOption()
-   .passThroughOptions()
-   .description("Run opencode with todo/background task completion enforcement")
-  .option("-a, --agent <name>", "Agent to use (default: from CLI/env/config, fallback: Sisyphus)")
-  .option("-d, --directory <path>", "Working directory")
-  .option("-t, --timeout <ms>", "Timeout in milliseconds (default: 30 minutes)", parseInt)
-  .option("-p, --port <port>", "Server port (attaches if port already in use)", parseInt)
-  .option("--attach <url>", "Attach to existing opencode server URL")
-  .option("--on-complete <command>", "Shell command to run after completion")
-  .option("--json", "Output structured JSON result to stdout")
-  .option("--session-id <id>", "Resume existing session instead of creating new one")
-  .addHelpText("after", `
-Examples:
-  $ bunx oh-my-opencode run "Fix the bug in index.ts"
-  $ bunx oh-my-opencode run --agent Sisyphus "Implement feature X"
-  $ bunx oh-my-opencode run --timeout 3600000 "Large refactoring task"
-  $ bunx oh-my-opencode run --port 4321 "Fix the bug"
-  $ bunx oh-my-opencode run --attach http://127.0.0.1:4321 "Fix the bug"
-  $ bunx oh-my-opencode run --json "Fix the bug" | jq .sessionId
-  $ bunx oh-my-opencode run --on-complete "notify-send Done" "Fix the bug"
-  $ bunx oh-my-opencode run --session-id ses_abc123 "Continue the work"
-
-Agent resolution order:
-  1) --agent flag
-  2) OPENCODE_DEFAULT_AGENT
-  3) oh-my-opencode.json "default_run_agent"
-  4) Sisyphus (fallback)
-
-Available core agents:
-  Sisyphus, Hephaestus, Prometheus, Atlas
-
-Unlike 'opencode run', this command waits until:
-  - All todos are completed or cancelled
-  - All child sessions (background tasks) are idle
-`)
-  .action(async (message: string, options) => {
-    if (options.port && options.attach) {
-      console.error("Error: --port and --attach are mutually exclusive")
-      process.exit(1)
-    }
-    const runOptions: RunOptions = {
-      message,
-      agent: options.agent,
-      directory: options.directory,
-      timeout: options.timeout,
-      port: options.port,
-      attach: options.attach,
-      onComplete: options.onComplete,
-      json: options.json ?? false,
-      sessionId: options.sessionId,
-    }
-    const exitCode = await run(runOptions)
-    process.exit(exitCode)
-  })
-
-program
-  .command("get-local-version")
-  .description("Show current installed version and check for updates")
-  .option("-d, --directory <path>", "Working directory to check config from")
-  .option("--json", "Output in JSON format for scripting")
-  .addHelpText("after", `
-Examples:
-  $ bunx oh-my-opencode get-local-version
-  $ bunx oh-my-opencode get-local-version --json
-  $ bunx oh-my-opencode get-local-version --directory /path/to/project
-
-This command shows:
-  - Current installed version
-  - Latest available version on npm
-  - Whether you're up to date
-  - Special modes (local dev, pinned version)
-`)
-  .action(async (options) => {
-    const versionOptions: GetLocalVersionOptions = {
-      directory: options.directory,
-      json: options.json ?? false,
-    }
-    const exitCode = await getLocalVersion(versionOptions)
-    process.exit(exitCode)
-  })
-
-program
-  .command("doctor")
-  .description("Check oh-my-opencode installation health and diagnose issues")
-  .option("--verbose", "Show detailed diagnostic information")
-  .option("--json", "Output results in JSON format")
-  .option("--category <category>", "Run only specific category")
-  .addHelpText("after", `
-Examples:
-  $ bunx oh-my-opencode doctor
-  $ bunx oh-my-opencode doctor --verbose
-  $ bunx oh-my-opencode doctor --json
-  $ bunx oh-my-opencode doctor --category authentication
-
-Categories:
-  installation     Check OpenCode and plugin installation
-  configuration    Validate configuration files
-  authentication   Check auth provider status
-  dependencies     Check external dependencies
-  tools            Check LSP and MCP servers
-  updates          Check for version updates
-`)
-  .action(async (options) => {
-    const doctorOptions: DoctorOptions = {
-      verbose: options.verbose ?? false,
-      json: options.json ?? false,
-      category: options.category,
-    }
-    const exitCode = await doctor(doctorOptions)
-    process.exit(exitCode)
-  })
-
-program
-  .command("version")
-  .description("Show version information")
-  .action(() => {
-    console.log(`oh-my-opencode v${VERSION}`)
-  })
-
-program.addCommand(createMcpOAuthCommand())
-
-export function runCli(): void {
-  program.parse()
-}
--- a/src/cli/config-manager.ts
+++ b/src/cli/config-manager.ts
@@ -1,23 +1,667 @@
-export type { ConfigContext } from "./config-manager/config-context"
-export {
-  initConfigContext,
-  getConfigContext,
-  resetConfigContext,
-} from "./config-manager/config-context"
+import { existsSync, mkdirSync, readFileSync, writeFileSync, statSync } from "node:fs"
+import {
+  parseJsonc,
+  getOpenCodeConfigPaths,
+  type OpenCodeBinaryType,
+  type OpenCodeConfigPaths,
+} from "../shared"
+import type { ConfigMergeResult, DetectedConfig, InstallConfig } from "./types"
+import { generateModelConfig } from "./model-fallback"

-export { fetchNpmDistTags } from "./config-manager/npm-dist-tags"
-export { getPluginNameWithVersion } from "./config-manager/plugin-name-with-version"
-export { addPluginToOpenCodeConfig } from "./config-manager/add-plugin-to-opencode-config"
+const OPENCODE_BINARIES = ["opencode", "opencode-desktop"] as const

-export { generateOmoConfig } from "./config-manager/generate-omo-config"
-export { writeOmoConfig } from "./config-manager/write-omo-config"
+interface ConfigContext {
+  binary: OpenCodeBinaryType
+  version: string | null
+  paths: OpenCodeConfigPaths
+}

-export { isOpenCodeInstalled, getOpenCodeVersion } from "./config-manager/opencode-binary"
+let configContext: ConfigContext | null = null

-export { fetchLatestVersion, addAuthPlugins } from "./config-manager/auth-plugins"
-export { ANTIGRAVITY_PROVIDER_CONFIG } from "./config-manager/antigravity-provider-configuration"
-export { addProviderConfig } from "./config-manager/add-provider-config"
-export { detectCurrentConfig } from "./config-manager/detect-current-config"
+export function initConfigContext(binary: OpenCodeBinaryType, version: string | null): void {
+  const paths = getOpenCodeConfigPaths({ binary, version })
+  configContext = { binary, version, paths }
+}

-export type { BunInstallResult } from "./config-manager/bun-install"
-export { runBunInstall, runBunInstallWithDetails } from "./config-manager/bun-install"
+export function getConfigContext(): ConfigContext {
+  if (!configContext) {
+    const paths = getOpenCodeConfigPaths({ binary: "opencode", version: null })
+    configContext = { binary: "opencode", version: null, paths }
+  }
+  return configContext
+}
+
+export function resetConfigContext(): void {
+  configContext = null
+}
+
+function getConfigDir(): string {
+  return getConfigContext().paths.configDir
+}
+
+function getConfigJson(): string {
+  return getConfigContext().paths.configJson
+}
+
+function getConfigJsonc(): string {
+  return getConfigContext().paths.configJsonc
+}
+
+function getPackageJson(): string {
+  return getConfigContext().paths.packageJson
+}
+
+function getOmoConfig(): string {
+  return getConfigContext().paths.omoConfig
+}
+
+const BUN_INSTALL_TIMEOUT_SECONDS = 60
+const BUN_INSTALL_TIMEOUT_MS = BUN_INSTALL_TIMEOUT_SECONDS * 1000
+
+interface NodeError extends Error {
+  code?: string
+}
+
+function isPermissionError(err: unknown): boolean {
+  const nodeErr = err as NodeError
+  return nodeErr?.code === "EACCES" || nodeErr?.code === "EPERM"
+}
+
+function isFileNotFoundError(err: unknown): boolean {
+  const nodeErr = err as NodeError
+  return nodeErr?.code === "ENOENT"
+}
+
+function formatErrorWithSuggestion(err: unknown, context: string): string {
+  if (isPermissionError(err)) {
+    return `Permission denied: Cannot ${context}. Try running with elevated permissions or check file ownership.`
+  }
+
+  if (isFileNotFoundError(err)) {
+    return `File not found while trying to ${context}. The file may have been deleted or moved.`
+  }
+
+  if (err instanceof SyntaxError) {
+    return `JSON syntax error while trying to ${context}: ${err.message}. Check for missing commas, brackets, or invalid characters.`
+  }
+
+  const message = err instanceof Error ? err.message : String(err)
+
+  if (message.includes("ENOSPC")) {
+    return `Disk full: Cannot ${context}. Free up disk space and try again.`
+  }
+
+  if (message.includes("EROFS")) {
+    return `Read-only filesystem: Cannot ${context}. Check if the filesystem is mounted read-only.`
+  }
+
+  return `Failed to ${context}: ${message}`
+}
+
+export async function fetchLatestVersion(packageName: string): Promise<string | null> {
+  try {
+    const res = await fetch(`https://registry.npmjs.org/${packageName}/latest`)
+    if (!res.ok) return null
+    const data = await res.json() as { version: string }
+    return data.version
+  } catch {
+    return null
+  }
+}
+
+interface NpmDistTags {
+  latest?: string
+  beta?: string
+  next?: string
+  [tag: string]: string | undefined
+}
+
+const NPM_FETCH_TIMEOUT_MS = 5000
+
+export async function fetchNpmDistTags(packageName: string): Promise<NpmDistTags | null> {
+  try {
+    const res = await fetch(`https://registry.npmjs.org/-/package/${packageName}/dist-tags`, {
+      signal: AbortSignal.timeout(NPM_FETCH_TIMEOUT_MS),
+    })
+    if (!res.ok) return null
+    const data = await res.json() as NpmDistTags
+    return data
+  } catch {
+    return null
+  }
+}
+
+const PACKAGE_NAME = "oh-my-opencode"
+
+const PRIORITIZED_TAGS = ["latest", "beta", "next"] as const
+
+export async function getPluginNameWithVersion(currentVersion: string): Promise<string> {
+  const distTags = await fetchNpmDistTags(PACKAGE_NAME)
+
+  if (distTags) {
+    const allTags = new Set([...PRIORITIZED_TAGS, ...Object.keys(distTags)])
+    for (const tag of allTags) {
+      if (distTags[tag] === currentVersion) {
+        return `${PACKAGE_NAME}@${tag}`
+      }
+    }
+  }
+
+  return `${PACKAGE_NAME}@${currentVersion}`
+}
+
+type ConfigFormat = "json" | "jsonc" | "none"
+
+interface OpenCodeConfig {
+  plugin?: string[]
+  [key: string]: unknown
+}
+
+export function detectConfigFormat(): { format: ConfigFormat; path: string } {
+  const configJsonc = getConfigJsonc()
+  const configJson = getConfigJson()
+
+  if (existsSync(configJsonc)) {
+    return { format: "jsonc", path: configJsonc }
+  }
+  if (existsSync(configJson)) {
+    return { format: "json", path: configJson }
+  }
+  return { format: "none", path: configJson }
+}
+
+interface ParseConfigResult {
+  config: OpenCodeConfig | null
+  error?: string
+}
+
+function isEmptyOrWhitespace(content: string): boolean {
+  return content.trim().length === 0
+}
+
+function parseConfig(path: string, _isJsonc: boolean): OpenCodeConfig | null {
+  const result = parseConfigWithError(path)
+  return result.config
+}
+
+function parseConfigWithError(path: string): ParseConfigResult {
+  try {
+    const stat = statSync(path)
+    if (stat.size === 0) {
+      return { config: null, error: `Config file is empty: ${path}. Delete it or add valid JSON content.` }
+    }
+
+    const content = readFileSync(path, "utf-8")
+
+    if (isEmptyOrWhitespace(content)) {
+      return { config: null, error: `Config file contains only whitespace: ${path}. Delete it or add valid JSON content.` }
+    }
+
+    const config = parseJsonc<OpenCodeConfig>(content)
+
+    if (config === null || config === undefined) {
+      return { config: null, error: `Config file parsed to null/undefined: ${path}. Ensure it contains valid JSON.` }
+    }
+
+    if (typeof config !== "object" || Array.isArray(config)) {
+      return { config: null, error: `Config file must contain a JSON object, not ${Array.isArray(config) ? "an array" : typeof config}: ${path}` }
+    }
+
+    return { config }
+  } catch (err) {
+    return { config: null, error: formatErrorWithSuggestion(err, `parse config file ${path}`) }
+  }
+}
+
+function ensureConfigDir(): void {
+  const configDir = getConfigDir()
+  if (!existsSync(configDir)) {
+    mkdirSync(configDir, { recursive: true })
+  }
+}
+
+export async function addPluginToOpenCodeConfig(currentVersion: string): Promise<ConfigMergeResult> {
+  try {
+    ensureConfigDir()
+  } catch (err) {
+    return { success: false, configPath: getConfigDir(), error: formatErrorWithSuggestion(err, "create config directory") }
+  }
+
+  const { format, path } = detectConfigFormat()
+  const pluginEntry = await getPluginNameWithVersion(currentVersion)
+
+  try {
+    if (format === "none") {
+      const config: OpenCodeConfig = { plugin: [pluginEntry] }
+      writeFileSync(path, JSON.stringify(config, null, 2) + "\n")
+      return { success: true, configPath: path }
+    }
+
+    const parseResult = parseConfigWithError(path)
+    if (!parseResult.config) {
+      return { success: false, configPath: path, error: parseResult.error ?? "Failed to parse config file" }
+    }
+
+    const config = parseResult.config
+    const plugins = config.plugin ?? []
+    const existingIndex = plugins.findIndex((p) => p === PACKAGE_NAME || p.startsWith(`${PACKAGE_NAME}@`))
+
+    if (existingIndex !== -1) {
+      if (plugins[existingIndex] === pluginEntry) {
+        return { success: true, configPath: path }
+      }
+      plugins[existingIndex] = pluginEntry
+    } else {
+      plugins.push(pluginEntry)
+    }
+
+    config.plugin = plugins
+
+    if (format === "jsonc") {
+      const content = readFileSync(path, "utf-8")
+      const pluginArrayRegex = /"plugin"\s*:\s*\[([\s\S]*?)\]/
+      const match = content.match(pluginArrayRegex)
+
+      if (match) {
+        const formattedPlugins = plugins.map((p) => `"${p}"`).join(",\n    ")
+        const newContent = content.replace(pluginArrayRegex, `"plugin": [\n    ${formattedPlugins}\n  ]`)
+        writeFileSync(path, newContent)
+      } else {
+        const newContent = content.replace(/^(\s*\{)/, `$1\n  "plugin": ["${pluginEntry}"],`)
+        writeFileSync(path, newContent)
+      }
+    } else {
+      writeFileSync(path, JSON.stringify(config, null, 2) + "\n")
+    }
+
+    return { success: true, configPath: path }
+  } catch (err) {
+    return { success: false, configPath: path, error: formatErrorWithSuggestion(err, "update opencode config") }
+  }
+}
+
+function deepMerge<T extends Record<string, unknown>>(target: T, source: Partial<T>): T {
+  const result = { ...target }
+
+  for (const key of Object.keys(source) as Array<keyof T>) {
+    const sourceValue = source[key]
+    const targetValue = result[key]
+
+    if (
+      sourceValue !== null &&
+      typeof sourceValue === "object" &&
+      !Array.isArray(sourceValue) &&
+      targetValue !== null &&
+      typeof targetValue === "object" &&
+      !Array.isArray(targetValue)
+    ) {
+      result[key] = deepMerge(
+        targetValue as Record<string, unknown>,
+        sourceValue as Record<string, unknown>
+      ) as T[keyof T]
+    } else if (sourceValue !== undefined) {
+      result[key] = sourceValue as T[keyof T]
+    }
+  }
+
+  return result
+}
+
+export function generateOmoConfig(installConfig: InstallConfig): Record<string, unknown> {
+  return generateModelConfig(installConfig)
+}
+
+export function writeOmoConfig(installConfig: InstallConfig): ConfigMergeResult {
+  try {
+    ensureConfigDir()
+  } catch (err) {
+    return { success: false, configPath: getConfigDir(), error: formatErrorWithSuggestion(err, "create config directory") }
+  }
+
+  const omoConfigPath = getOmoConfig()
+
+  try {
+    const newConfig = generateOmoConfig(installConfig)
+
+    if (existsSync(omoConfigPath)) {
+      try {
+        const stat = statSync(omoConfigPath)
+        const content = readFileSync(omoConfigPath, "utf-8")
+
+        if (stat.size === 0 || isEmptyOrWhitespace(content)) {
+          writeFileSync(omoConfigPath, JSON.stringify(newConfig, null, 2) + "\n")
+          return { success: true, configPath: omoConfigPath }
+        }
+
+        const existing = parseJsonc<Record<string, unknown>>(content)
+        if (!existing || typeof existing !== "object" || Array.isArray(existing)) {
+          writeFileSync(omoConfigPath, JSON.stringify(newConfig, null, 2) + "\n")
+          return { success: true, configPath: omoConfigPath }
+        }
+
+        const merged = deepMerge(existing, newConfig)
+        writeFileSync(omoConfigPath, JSON.stringify(merged, null, 2) + "\n")
+      } catch (parseErr) {
+        if (parseErr instanceof SyntaxError) {
+          writeFileSync(omoConfigPath, JSON.stringify(newConfig, null, 2) + "\n")
+          return { success: true, configPath: omoConfigPath }
+        }
+        throw parseErr
+      }
+    } else {
+      writeFileSync(omoConfigPath, JSON.stringify(newConfig, null, 2) + "\n")
+    }
+
+    return { success: true, configPath: omoConfigPath }
+  } catch (err) {
+    return { success: false, configPath: omoConfigPath, error: formatErrorWithSuggestion(err, "write oh-my-opencode config") }
+  }
+}
+
+interface OpenCodeBinaryResult {
+  binary: OpenCodeBinaryType
+  version: string
+}
+
+async function findOpenCodeBinaryWithVersion(): Promise<OpenCodeBinaryResult | null> {
+  for (const binary of OPENCODE_BINARIES) {
+    try {
+      const proc = Bun.spawn([binary, "--version"], {
+        stdout: "pipe",
+        stderr: "pipe",
+      })
+      const output = await new Response(proc.stdout).text()
+      await proc.exited
+      if (proc.exitCode === 0) {
+        const version = output.trim()
+        initConfigContext(binary, version)
+        return { binary, version }
+      }
+    } catch {
+      continue
+    }
+  }
+  return null
+}
+
+export async function isOpenCodeInstalled(): Promise<boolean> {
+  const result = await findOpenCodeBinaryWithVersion()
+  return result !== null
+}
+
+export async function getOpenCodeVersion(): Promise<string | null> {
+  const result = await findOpenCodeBinaryWithVersion()
+  return result?.version ?? null
+}
+
+export async function addAuthPlugins(config: InstallConfig): Promise<ConfigMergeResult> {
+  try {
+    ensureConfigDir()
+  } catch (err) {
+    return { success: false, configPath: getConfigDir(), error: formatErrorWithSuggestion(err, "create config directory") }
+  }
+
+  const { format, path } = detectConfigFormat()
+
+  try {
+    let existingConfig: OpenCodeConfig | null = null
+    if (format !== "none") {
+      const parseResult = parseConfigWithError(path)
+      if (parseResult.error && !parseResult.config) {
+        existingConfig = {}
+      } else {
+        existingConfig = parseResult.config
+      }
+    }
+
+    const plugins: string[] = existingConfig?.plugin ?? []
+
+    if (config.hasGemini) {
+      const version = await fetchLatestVersion("opencode-antigravity-auth")
+      const pluginEntry = version ? `opencode-antigravity-auth@${version}` : "opencode-antigravity-auth"
+      if (!plugins.some((p) => p.startsWith("opencode-antigravity-auth"))) {
+        plugins.push(pluginEntry)
+      }
+    }
+
+
+
+    const newConfig = { ...(existingConfig ?? {}), plugin: plugins }
+    writeFileSync(path, JSON.stringify(newConfig, null, 2) + "\n")
+    return { success: true, configPath: path }
+  } catch (err) {
+    return { success: false, configPath: path, error: formatErrorWithSuggestion(err, "add auth plugins to config") }
+  }
+}
+
+export interface BunInstallResult {
+  success: boolean
+  timedOut?: boolean
+  error?: string
+}
+
+export async function runBunInstall(): Promise<boolean> {
+  const result = await runBunInstallWithDetails()
+  return result.success
+}
+
+export async function runBunInstallWithDetails(): Promise<BunInstallResult> {
+  try {
+    const proc = Bun.spawn(["bun", "install"], {
+      cwd: getConfigDir(),
+      stdout: "pipe",
+      stderr: "pipe",
+    })
+
+    const timeoutPromise = new Promise<"timeout">((resolve) =>
+      setTimeout(() => resolve("timeout"), BUN_INSTALL_TIMEOUT_MS)
+    )
+
+    const exitPromise = proc.exited.then(() => "completed" as const)
+
+    const result = await Promise.race([exitPromise, timeoutPromise])
+
+    if (result === "timeout") {
+      try {
+        proc.kill()
+      } catch {
+        /* intentionally empty - process may have already exited */
+      }
+      return {
+        success: false,
+        timedOut: true,
+        error: `bun install timed out after ${BUN_INSTALL_TIMEOUT_SECONDS} seconds. Try running manually: cd ~/.config/opencode && bun i`,
+      }
+    }
+
+    if (proc.exitCode !== 0) {
+      const stderr = await new Response(proc.stderr).text()
+      return {
+        success: false,
+        error: stderr.trim() || `bun install failed with exit code ${proc.exitCode}`,
+      }
+    }
+
+    return { success: true }
+  } catch (err) {
+    const message = err instanceof Error ? err.message : String(err)
+    return {
+      success: false,
+      error: `bun install failed: ${message}. Is bun installed? Try: curl -fsSL https://bun.sh/install | bash`,
+    }
+  }
+}
+
+/**
+ * Antigravity Provider Configuration
+ *
+ * IMPORTANT: Model names MUST use `antigravity-` prefix for stability.
+ *
+ * Since opencode-antigravity-auth v1.3.0, models use a variant system:
+ * - `antigravity-gemini-3-pro` with variants: low, high
+ * - `antigravity-gemini-3-flash` with variants: minimal, low, medium, high
+ *
+ * Legacy tier-suffixed names (e.g., `antigravity-gemini-3-pro-high`) still work
+ * but variants are the recommended approach.
+ *
+ * @see https://github.com/NoeFabris/opencode-antigravity-auth#models
+ */
+export const ANTIGRAVITY_PROVIDER_CONFIG = {
+  google: {
+    name: "Google",
+    models: {
+      "antigravity-gemini-3-pro": {
+        name: "Gemini 3 Pro (Antigravity)",
+        limit: { context: 1048576, output: 65535 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          low: { thinkingLevel: "low" },
+          high: { thinkingLevel: "high" },
+        },
+      },
+      "antigravity-gemini-3-flash": {
+        name: "Gemini 3 Flash (Antigravity)",
+        limit: { context: 1048576, output: 65536 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          minimal: { thinkingLevel: "minimal" },
+          low: { thinkingLevel: "low" },
+          medium: { thinkingLevel: "medium" },
+          high: { thinkingLevel: "high" },
+        },
+      },
+      "antigravity-claude-sonnet-4-5": {
+        name: "Claude Sonnet 4.5 (Antigravity)",
+        limit: { context: 200000, output: 64000 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+      },
+      "antigravity-claude-sonnet-4-5-thinking": {
+        name: "Claude Sonnet 4.5 Thinking (Antigravity)",
+        limit: { context: 200000, output: 64000 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          low: { thinkingConfig: { thinkingBudget: 8192 } },
+          max: { thinkingConfig: { thinkingBudget: 32768 } },
+        },
+      },
+      "antigravity-claude-opus-4-5-thinking": {
+        name: "Claude Opus 4.5 Thinking (Antigravity)",
+        limit: { context: 200000, output: 64000 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          low: { thinkingConfig: { thinkingBudget: 8192 } },
+          max: { thinkingConfig: { thinkingBudget: 32768 } },
+        },
+      },
+    },
+  },
+}
+
+
+
+export function addProviderConfig(config: InstallConfig): ConfigMergeResult {
+  try {
+    ensureConfigDir()
+  } catch (err) {
+    return { success: false, configPath: getConfigDir(), error: formatErrorWithSuggestion(err, "create config directory") }
+  }
+
+  const { format, path } = detectConfigFormat()
+
+  try {
+    let existingConfig: OpenCodeConfig | null = null
+    if (format !== "none") {
+      const parseResult = parseConfigWithError(path)
+      if (parseResult.error && !parseResult.config) {
+        existingConfig = {}
+      } else {
+        existingConfig = parseResult.config
+      }
+    }
+
+    const newConfig = { ...(existingConfig ?? {}) }
+
+    const providers = (newConfig.provider ?? {}) as Record<string, unknown>
+
+    if (config.hasGemini) {
+      providers.google = ANTIGRAVITY_PROVIDER_CONFIG.google
+    }
+
+    if (Object.keys(providers).length > 0) {
+      newConfig.provider = providers
+    }
+
+    writeFileSync(path, JSON.stringify(newConfig, null, 2) + "\n")
+    return { success: true, configPath: path }
+  } catch (err) {
+    return { success: false, configPath: path, error: formatErrorWithSuggestion(err, "add provider config") }
+  }
+}
+
+function detectProvidersFromOmoConfig(): { hasOpenAI: boolean; hasOpencodeZen: boolean; hasZaiCodingPlan: boolean; hasKimiForCoding: boolean } {
+  const omoConfigPath = getOmoConfig()
+  if (!existsSync(omoConfigPath)) {
+    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, 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, hasKimiForCoding }
+  } catch {
+    return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
+  }
+}
+
+export function detectCurrentConfig(): DetectedConfig {
+  const result: DetectedConfig = {
+    isInstalled: false,
+    hasClaude: true,
+    isMax20: true,
+    hasOpenAI: true,
+    hasGemini: false,
+    hasCopilot: false,
+    hasOpencodeZen: true,
+    hasZaiCodingPlan: false,
+    hasKimiForCoding: false,
+  }
+
+  const { format, path } = detectConfigFormat()
+  if (format === "none") {
+    return result
+  }
+
+  const parseResult = parseConfigWithError(path)
+  if (!parseResult.config) {
+    return result
+  }
+
+  const openCodeConfig = parseResult.config
+  const plugins = openCodeConfig.plugin ?? []
+  result.isInstalled = plugins.some((p) => p.startsWith("oh-my-opencode"))
+
+  if (!result.isInstalled) {
+    return result
+  }
+
+  // Gemini auth plugin detection still works via plugin presence
+  result.hasGemini = plugins.some((p) => p.startsWith("opencode-antigravity-auth"))
+
+  const { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan, hasKimiForCoding } = detectProvidersFromOmoConfig()
+  result.hasOpenAI = hasOpenAI
+  result.hasOpencodeZen = hasOpencodeZen
+  result.hasZaiCodingPlan = hasZaiCodingPlan
+  result.hasKimiForCoding = hasKimiForCoding
+
+  return result
+}
--- a/src/cli/config-manager/add-plugin-to-opencode-config.ts
+++ b/src/cli/config-manager/add-plugin-to-opencode-config.ts
@@ -1,82 +0,0 @@
-import { readFileSync, writeFileSync } from "node:fs"
-import type { ConfigMergeResult } from "../types"
-import { getConfigDir } from "./config-context"
-import { ensureConfigDirectoryExists } from "./ensure-config-directory-exists"
-import { formatErrorWithSuggestion } from "./format-error-with-suggestion"
-import { detectConfigFormat } from "./opencode-config-format"
-import { parseOpenCodeConfigFileWithError, type OpenCodeConfig } from "./parse-opencode-config-file"
-import { getPluginNameWithVersion } from "./plugin-name-with-version"
-
-const PACKAGE_NAME = "oh-my-opencode"
-
-export async function addPluginToOpenCodeConfig(currentVersion: string): Promise<ConfigMergeResult> {
-  try {
-    ensureConfigDirectoryExists()
-  } catch (err) {
-    return {
-      success: false,
-      configPath: getConfigDir(),
-      error: formatErrorWithSuggestion(err, "create config directory"),
-    }
-  }
-
-  const { format, path } = detectConfigFormat()
-  const pluginEntry = await getPluginNameWithVersion(currentVersion)
-
-  try {
-    if (format === "none") {
-      const config: OpenCodeConfig = { plugin: [pluginEntry] }
-      writeFileSync(path, JSON.stringify(config, null, 2) + "\n")
-      return { success: true, configPath: path }
-    }
-
-    const parseResult = parseOpenCodeConfigFileWithError(path)
-    if (!parseResult.config) {
-      return {
-        success: false,
-        configPath: path,
-        error: parseResult.error ?? "Failed to parse config file",
-      }
-    }
-
-    const config = parseResult.config
-    const plugins = config.plugin ?? []
-    const existingIndex = plugins.findIndex((p) => p === PACKAGE_NAME || p.startsWith(`${PACKAGE_NAME}@`))
-
-    if (existingIndex !== -1) {
-      if (plugins[existingIndex] === pluginEntry) {
-        return { success: true, configPath: path }
-      }
-      plugins[existingIndex] = pluginEntry
-    } else {
-      plugins.push(pluginEntry)
-    }
-
-    config.plugin = plugins
-
-    if (format === "jsonc") {
-      const content = readFileSync(path, "utf-8")
-      const pluginArrayRegex = /"plugin"\s*:\s*\[([\s\S]*?)\]/
-      const match = content.match(pluginArrayRegex)
-
-      if (match) {
-        const formattedPlugins = plugins.map((p) => `"${p}"`).join(",\n    ")
-        const newContent = content.replace(pluginArrayRegex, `"plugin": [\n    ${formattedPlugins}\n  ]`)
-        writeFileSync(path, newContent)
-      } else {
-        const newContent = content.replace(/(\{)/, `$1\n  "plugin": ["${pluginEntry}"],`)
-        writeFileSync(path, newContent)
-      }
-    } else {
-      writeFileSync(path, JSON.stringify(config, null, 2) + "\n")
-    }
-
-    return { success: true, configPath: path }
-  } catch (err) {
-    return {
-      success: false,
-      configPath: path,
-      error: formatErrorWithSuggestion(err, "update opencode config"),
-    }
-  }
-}
--- a/src/cli/config-manager/add-provider-config.test.ts
+++ b/src/cli/config-manager/add-provider-config.test.ts
@@ -1,205 +0,0 @@
-import { describe, expect, it } from "bun:test"
-import { modifyProviderInJsonc } from "./jsonc-provider-editor"
-import { parseJsonc } from "../../shared/jsonc-parser"
-
-describe("modifyProviderInJsonc", () => {
-  describe("Test 1: Basic JSONC with existing provider", () => {
-    it("replaces provider value, preserves comments and other keys", () => {
-      // given
-      const content = `{
-  // my config
-  "provider": { "openai": {} },
-  "plugin": ["foo"]
-}`
-      const newProviderValue = { google: { name: "Google" } }
-
-      // when
-      const result = modifyProviderInJsonc(content, newProviderValue)
-
-      // then
-      expect(result).toContain('"google"')
-      expect(result).toContain('"plugin": ["foo"]')
-      expect(result).toContain('// my config')
-
-      // Post-write validation
-      const parsed = parseJsonc<Record<string, unknown>>(result)
-      expect(parsed).toHaveProperty('plugin')
-      expect(parsed).toHaveProperty('provider')
-    })
-  })
-
-  describe("Test 2: Comment containing '}' inside provider block", () => {
-    it("must NOT corrupt file", () => {
-      // given
-      const content = `{
-  "provider": {
-    // } this brace should be ignored
-    "openai": {}
-  },
-  "other": 1
-}`
-      const newProviderValue = { google: { name: "Google" } }
-
-      // when
-      const result = modifyProviderInJsonc(content, newProviderValue)
-
-      // then
-      expect(result).toContain('"other"')
-
-      // Post-write validation
-      const parsed = parseJsonc<Record<string, unknown>>(result)
-      expect(parsed).toHaveProperty('other')
-      expect(parsed.other).toBe(1)
-    })
-  })
-
-  describe("Test 3: Comment containing '\"provider\"' before real key", () => {
-    it("must NOT match wrong location", () => {
-      // given
-      const content = `{
-  // "provider": { "example": true }
-  "provider": { "openai": {} },
-  "other": 1
-}`
-      const newProviderValue = { google: { name: "Google" } }
-
-      // when
-      const result = modifyProviderInJsonc(content, newProviderValue)
-
-      // then
-      expect(result).toContain('"other"')
-
-      // Post-write validation
-      const parsed = parseJsonc<Record<string, unknown>>(result)
-      expect(parsed).toHaveProperty('other')
-      expect(parsed.other).toBe(1)
-      expect(parsed.provider).toHaveProperty('google')
-    })
-  })
-
-  describe("Test 4: Comment containing '{' inside provider", () => {
-    it("must NOT mess up depth", () => {
-      // given
-      const content = `{
-  "provider": {
-    // { unmatched brace in comment
-    "openai": {}
-  },
-  "other": 1
-}`
-      const newProviderValue = { google: { name: "Google" } }
-
-      // when
-      const result = modifyProviderInJsonc(content, newProviderValue)
-
-      // then
-      expect(result).toContain('"other"')
-
-      // Post-write validation
-      const parsed = parseJsonc<Record<string, unknown>>(result)
-      expect(parsed).toHaveProperty('other')
-      expect(parsed.other).toBe(1)
-    })
-  })
-
-  describe("Test 5: No existing provider key", () => {
-    it("inserts provider without corrupting", () => {
-      // given
-      const content = `{
-  // config comment
-  "plugin": ["foo"]
-}`
-      const newProviderValue = { google: { name: "Google" } }
-
-      // when
-      const result = modifyProviderInJsonc(content, newProviderValue)
-
-      // then
-      expect(result).toContain('"provider"')
-      expect(result).toContain('"plugin"')
-      expect(result).toContain('foo')
-      expect(result).toContain('// config comment')
-
-      // Post-write validation
-      const parsed = parseJsonc<Record<string, unknown>>(result)
-      expect(parsed).toHaveProperty('provider')
-      expect(parsed).toHaveProperty('plugin')
-      expect(parsed.plugin).toEqual(['foo'])
-    })
-  })
-
-  describe("Test 6: String value exactly 'provider' before real key", () => {
-    it("must NOT match wrong location", () => {
-      // given
-      const content = `{
-  "note": "provider",
-  "provider": { "openai": {} },
-  "other": 1
-}`
-      const newProviderValue = { google: { name: "Google" } }
-
-      // when
-      const result = modifyProviderInJsonc(content, newProviderValue)
-
-      // then
-      expect(result).toContain('"other"')
-      expect(result).toContain('"note": "provider"')
-
-      // Post-write validation
-      const parsed = parseJsonc<Record<string, unknown>>(result)
-      expect(parsed).toHaveProperty('other')
-      expect(parsed.other).toBe(1)
-      expect(parsed.note).toBe('provider')
-    })
-  })
-
-  describe("Test 7: Post-write validation", () => {
-    it("result file must be valid JSONC for all cases", () => {
-      // Test Case 1
-      const content1 = `{
-  "provider": { "openai": {} },
-  "plugin": ["foo"]
-}`
-      const result1 = modifyProviderInJsonc(content1, { google: {} })
-      expect(() => parseJsonc(result1)).not.toThrow()
-
-      // Test Case 2
-      const content2 = `{
-  "provider": {
-    // } comment
-    "openai": {}
-  }
-}`
-      const result2 = modifyProviderInJsonc(content2, { google: {} })
-      expect(() => parseJsonc(result2)).not.toThrow()
-
-      // Test Case 3
-      const content3 = `{
-  "plugin": ["foo"]
-}`
-      const result3 = modifyProviderInJsonc(content3, { google: {} })
-      expect(() => parseJsonc(result3)).not.toThrow()
-    })
-  })
-
-  describe("Test 8: Trailing commas preserved", () => {
-    it("file is valid JSONC with trailing commas", () => {
-      // given
-      const content = `{
-  "provider": { "openai": {}, },
-  "plugin": ["foo",],
-}`
-      const newProviderValue = { google: { name: "Google" } }
-
-      // when
-      const result = modifyProviderInJsonc(content, newProviderValue)
-
-      // then
-      expect(() => parseJsonc(result)).not.toThrow()
-
-      const parsed = parseJsonc<Record<string, unknown>>(result)
-      expect(parsed).toHaveProperty('plugin')
-      expect(parsed.plugin).toEqual(['foo'])
-    })
-  })
-})
--- a/src/cli/config-manager/add-provider-config.ts
+++ b/src/cli/config-manager/add-provider-config.ts
@@ -1,82 +0,0 @@
-import { readFileSync, writeFileSync, copyFileSync } from "node:fs"
-import type { ConfigMergeResult, InstallConfig } from "../types"
-import { getConfigDir } from "./config-context"
-import { ensureConfigDirectoryExists } from "./ensure-config-directory-exists"
-import { formatErrorWithSuggestion } from "./format-error-with-suggestion"
-import { detectConfigFormat } from "./opencode-config-format"
-import { parseOpenCodeConfigFileWithError, type OpenCodeConfig } from "./parse-opencode-config-file"
-import { ANTIGRAVITY_PROVIDER_CONFIG } from "./antigravity-provider-configuration"
-import { modifyProviderInJsonc } from "./jsonc-provider-editor"
-import { parseJsonc } from "../../shared/jsonc-parser"
-
-export function addProviderConfig(config: InstallConfig): ConfigMergeResult {
-  try {
-    ensureConfigDirectoryExists()
-  } catch (err) {
-    return {
-      success: false,
-      configPath: getConfigDir(),
-      error: formatErrorWithSuggestion(err, "create config directory"),
-    }
-  }
-
-  const { format, path } = detectConfigFormat()
-
-  try {
-    let existingConfig: OpenCodeConfig | null = null
-    if (format !== "none") {
-      const parseResult = parseOpenCodeConfigFileWithError(path)
-      if (parseResult.error && !parseResult.config) {
-        return {
-          success: false,
-          configPath: path,
-          error: `Failed to parse config file: ${parseResult.error}`,
-        }
-      }
-      existingConfig = parseResult.config
-    }
-
-    const newConfig = { ...(existingConfig ?? {}) }
-    const providers = (newConfig.provider ?? {}) as Record<string, unknown>
-
-    if (config.hasGemini) {
-      providers.google = ANTIGRAVITY_PROVIDER_CONFIG.google
-    }
-
-    if (Object.keys(providers).length > 0) {
-      newConfig.provider = providers
-    }
-
-    if (format === "jsonc") {
-      const content = readFileSync(path, "utf-8")
-
-      // Backup original file
-      copyFileSync(path, `${path}.bak`)
-
-      const providerValue = (newConfig.provider ?? {}) as Record<string, unknown>
-      const newContent = modifyProviderInJsonc(content, providerValue)
-
-      // Post-write validation
-      try {
-        parseJsonc(newContent)
-      } catch (error) {
-        return {
-          success: false,
-          configPath: path,
-          error: `Generated JSONC is invalid: ${error instanceof Error ? error.message : String(error)}`,
-        }
-      }
-
-      writeFileSync(path, newContent)
-    } else {
-      writeFileSync(path, JSON.stringify(newConfig, null, 2) + "\n")
-    }
-    return { success: true, configPath: path }
-  } catch (err) {
-    return {
-      success: false,
-      configPath: path,
-      error: formatErrorWithSuggestion(err, "add provider config"),
-    }
-  }
-}
--- a/src/cli/config-manager/antigravity-provider-configuration.ts
+++ b/src/cli/config-manager/antigravity-provider-configuration.ts
@@ -1,64 +0,0 @@
-/**
- * Antigravity Provider Configuration
- *
- * IMPORTANT: Model names MUST use `antigravity-` prefix for stability.
- *
- * Since opencode-antigravity-auth v1.3.0, models use a variant system:
- * - `antigravity-gemini-3-pro` with variants: low, high
- * - `antigravity-gemini-3-flash` with variants: minimal, low, medium, high
- *
- * Legacy tier-suffixed names (e.g., `antigravity-gemini-3-pro-high`) still work
- * but variants are the recommended approach.
- *
- * @see https://github.com/NoeFabris/opencode-antigravity-auth#models
- */
-export const ANTIGRAVITY_PROVIDER_CONFIG = {
-  google: {
-    name: "Google",
-    models: {
-      "antigravity-gemini-3-pro": {
-        name: "Gemini 3 Pro (Antigravity)",
-        limit: { context: 1048576, output: 65535 },
-        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
-        variants: {
-          low: { thinkingLevel: "low" },
-          high: { thinkingLevel: "high" },
-        },
-      },
-      "antigravity-gemini-3-flash": {
-        name: "Gemini 3 Flash (Antigravity)",
-        limit: { context: 1048576, output: 65536 },
-        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
-        variants: {
-          minimal: { thinkingLevel: "minimal" },
-          low: { thinkingLevel: "low" },
-          medium: { thinkingLevel: "medium" },
-          high: { thinkingLevel: "high" },
-        },
-      },
-      "antigravity-claude-sonnet-4-5": {
-        name: "Claude Sonnet 4.5 (Antigravity)",
-        limit: { context: 200000, output: 64000 },
-        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
-      },
-      "antigravity-claude-sonnet-4-5-thinking": {
-        name: "Claude Sonnet 4.5 Thinking (Antigravity)",
-        limit: { context: 200000, output: 64000 },
-        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
-        variants: {
-          low: { thinkingConfig: { thinkingBudget: 8192 } },
-          max: { thinkingConfig: { thinkingBudget: 32768 } },
-        },
-      },
-      "antigravity-claude-opus-4-5-thinking": {
-        name: "Claude Opus 4.5 Thinking (Antigravity)",
-        limit: { context: 200000, output: 64000 },
-        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
-        variants: {
-          low: { thinkingConfig: { thinkingBudget: 8192 } },
-          max: { thinkingConfig: { thinkingBudget: 32768 } },
-        },
-      },
-    },
-  },
-}
--- a/src/cli/config-manager/auth-plugins.test.ts
+++ b/src/cli/config-manager/auth-plugins.test.ts
@@ -1,224 +0,0 @@
-import { describe, expect, it, beforeEach, afterEach, spyOn } from "bun:test"
-import { tmpdir } from "node:os"
-import { join } from "node:path"
-import { writeFileSync, readFileSync, existsSync, rmSync, mkdirSync } from "node:fs"
-import { parseJsonc } from "../../shared/jsonc-parser"
-import type { InstallConfig } from "../types"
-import { resetConfigContext } from "./config-context"
-
-let testConfigPath: string
-let testConfigDir: string
-let testCounter = 0
-let fetchVersionSpy: unknown
-
-beforeEach(async () => {
-  testCounter++
-  testConfigDir = join(tmpdir(), `test-opencode-${Date.now()}-${testCounter}`)
-  testConfigPath = join(testConfigDir, "opencode.jsonc")
-  mkdirSync(testConfigDir, { recursive: true })
-
-  process.env.OPENCODE_CONFIG_DIR = testConfigDir
-  resetConfigContext()
-
-  const module = await import("./auth-plugins")
-  fetchVersionSpy = spyOn(module, "fetchLatestVersion").mockResolvedValue("1.2.3")
-})
-
-afterEach(() => {
-  try {
-    rmSync(testConfigDir, { recursive: true, force: true })
-  } catch {}
-})
-
-const testConfig: InstallConfig = {
-  hasClaude: false,
-  isMax20: false,
-  hasOpenAI: false,
-  hasGemini: true,
-  hasCopilot: false,
-  hasOpencodeZen: false,
-  hasZaiCodingPlan: false,
-  hasKimiForCoding: false,
-}
-
-describe("addAuthPlugins", () => {
-  describe("Test 1: JSONC with commented plugin line", () => {
-    it("preserves comment, updates actual plugin array", async () => {
-      const content = `{
-  // "plugin": ["old-plugin"]
-  "plugin": ["existing-plugin"],
-  "provider": {}
-}`
-      writeFileSync(testConfigPath, content, "utf-8")
-
-      const { addAuthPlugins } = await import("./auth-plugins")
-      const result = await addAuthPlugins(testConfig)
-
-      expect(result.success).toBe(true)
-
-      const newContent = readFileSync(result.configPath, "utf-8")
-      expect(newContent).toContain('// "plugin": ["old-plugin"]')
-      expect(newContent).toContain('existing-plugin')
-      expect(newContent).toContain('opencode-antigravity-auth')
-
-      const parsed = parseJsonc<Record<string, unknown>>(newContent)
-      const plugins = parsed.plugin as string[]
-      expect(plugins).toContain('existing-plugin')
-      expect(plugins.some((p) => p.startsWith('opencode-antigravity-auth'))).toBe(true)
-    })
-  })
-
-  describe("Test 2: Plugin array already contains antigravity", () => {
-    it("does not add duplicate", async () => {
-      const content = `{
-  "plugin": ["existing-plugin", "opencode-antigravity-auth"],
-  "provider": {}
-}`
-      writeFileSync(testConfigPath, content, "utf-8")
-
-      const { addAuthPlugins } = await import("./auth-plugins")
-      const result = await addAuthPlugins(testConfig)
-
-      expect(result.success).toBe(true)
-
-      const newContent = readFileSync(testConfigPath, "utf-8")
-      const parsed = parseJsonc<Record<string, unknown>>(newContent)
-      const plugins = parsed.plugin as string[]
-
-      const antigravityCount = plugins.filter((p) => p.startsWith('opencode-antigravity-auth')).length
-      expect(antigravityCount).toBe(1)
-    })
-  })
-
-  describe("Test 3: Backup created before write", () => {
-    it("creates .bak file", async () => {
-      const originalContent = `{
-  "plugin": ["existing-plugin"],
-  "provider": {}
-}`
-      writeFileSync(testConfigPath, originalContent, "utf-8")
-      readFileSync(testConfigPath, "utf-8")
-
-      const { addAuthPlugins } = await import("./auth-plugins")
-      const result = await addAuthPlugins(testConfig)
-
-      expect(result.success).toBe(true)
-      expect(existsSync(`${result.configPath}.bak`)).toBe(true)
-
-      const backupContent = readFileSync(`${result.configPath}.bak`, "utf-8")
-      expect(backupContent).toBe(originalContent)
-    })
-  })
-
-  describe("Test 4: Comment with } character", () => {
-    it("preserves comments with special characters", async () => {
-      const content = `{
-  // This comment has } special characters
-  "plugin": ["existing-plugin"],
-  "provider": {}
-}`
-      writeFileSync(testConfigPath, content, "utf-8")
-
-      const { addAuthPlugins } = await import("./auth-plugins")
-      const result = await addAuthPlugins(testConfig)
-
-      expect(result.success).toBe(true)
-
-      const newContent = readFileSync(testConfigPath, "utf-8")
-      expect(newContent).toContain('// This comment has } special characters')
-
-      expect(() => parseJsonc(newContent)).not.toThrow()
-    })
-  })
-
-  describe("Test 5: Comment containing 'plugin' string", () => {
-    it("must NOT match comment location", async () => {
-      const content = `{
-  // "plugin": ["fake"]
-  "plugin": ["existing-plugin"],
-  "provider": {}
-}`
-      writeFileSync(testConfigPath, content, "utf-8")
-
-      const { addAuthPlugins } = await import("./auth-plugins")
-      const result = await addAuthPlugins(testConfig)
-
-      expect(result.success).toBe(true)
-
-      const newContent = readFileSync(testConfigPath, "utf-8")
-      expect(newContent).toContain('// "plugin": ["fake"]')
-
-      const parsed = parseJsonc<Record<string, unknown>>(newContent)
-      const plugins = parsed.plugin as string[]
-      expect(plugins).toContain('existing-plugin')
-      expect(plugins).not.toContain('fake')
-    })
-  })
-
-  describe("Test 6: No existing plugin array", () => {
-    it("creates plugin array when none exists", async () => {
-      const content = `{
-  "provider": {}
-}`
-      writeFileSync(testConfigPath, content, "utf-8")
-
-      const { addAuthPlugins } = await import("./auth-plugins")
-      const result = await addAuthPlugins(testConfig)
-
-      expect(result.success).toBe(true)
-
-      const newContent = readFileSync(result.configPath, "utf-8")
-
-      const parsed = parseJsonc<Record<string, unknown>>(newContent)
-      expect(parsed).toHaveProperty('plugin')
-      const plugins = parsed.plugin as string[]
-      expect(plugins.some((p) => p.startsWith('opencode-antigravity-auth'))).toBe(true)
-    })
-  })
-
-  describe("Test 7: Post-write validation ensures valid JSONC", () => {
-    it("result file must be valid JSONC", async () => {
-      const content = `{
-  "plugin": ["existing-plugin"],
-  "provider": {}
-}`
-      writeFileSync(testConfigPath, content, "utf-8")
-
-      const { addAuthPlugins } = await import("./auth-plugins")
-      const result = await addAuthPlugins(testConfig)
-
-      expect(result.success).toBe(true)
-
-      const newContent = readFileSync(testConfigPath, "utf-8")
-      expect(() => parseJsonc(newContent)).not.toThrow()
-
-      const parsed = parseJsonc<Record<string, unknown>>(newContent)
-      expect(parsed).toHaveProperty('plugin')
-      expect(parsed).toHaveProperty('provider')
-    })
-  })
-
-  describe("Test 8: Multiple plugins in array", () => {
-    it("appends to existing plugins", async () => {
-      const content = `{
-  "plugin": ["plugin-1", "plugin-2", "plugin-3"],
-  "provider": {}
-}`
-      writeFileSync(testConfigPath, content, "utf-8")
-
-      const { addAuthPlugins } = await import("./auth-plugins")
-      const result = await addAuthPlugins(testConfig)
-
-      expect(result.success).toBe(true)
-
-      const newContent = readFileSync(result.configPath, "utf-8")
-      const parsed = parseJsonc<Record<string, unknown>>(newContent)
-      const plugins = parsed.plugin as string[]
-
-      expect(plugins).toContain('plugin-1')
-      expect(plugins).toContain('plugin-2')
-      expect(plugins).toContain('plugin-3')
-      expect(plugins.some((p) => p.startsWith('opencode-antigravity-auth'))).toBe(true)
-    })
-  })
-})
--- a/src/cli/config-manager/auth-plugins.ts
+++ b/src/cli/config-manager/auth-plugins.ts
@@ -1,145 +0,0 @@
-import { readFileSync, writeFileSync, copyFileSync, existsSync } from "node:fs"
-import { modify, applyEdits } from "jsonc-parser"
-import type { ConfigMergeResult, InstallConfig } from "../types"
-import { getConfigDir } from "./config-context"
-import { ensureConfigDirectoryExists } from "./ensure-config-directory-exists"
-import { formatErrorWithSuggestion } from "./format-error-with-suggestion"
-import { detectConfigFormat } from "./opencode-config-format"
-import { parseOpenCodeConfigFileWithError, type OpenCodeConfig } from "./parse-opencode-config-file"
-import { parseJsonc } from "../../shared/jsonc-parser"
-
-export async function fetchLatestVersion(packageName: string): Promise<string | null> {
-  try {
-    const res = await fetch(`https://registry.npmjs.org/${encodeURIComponent(packageName)}/latest`)
-    if (!res.ok) return null
-    const data = (await res.json()) as { version: string }
-    return data.version
-  } catch {
-    return null
-  }
-}
-
-export async function addAuthPlugins(config: InstallConfig): Promise<ConfigMergeResult> {
-  try {
-    ensureConfigDirectoryExists()
-  } catch (err) {
-    return {
-      success: false,
-      configPath: getConfigDir(),
-      error: formatErrorWithSuggestion(err, "create config directory"),
-    }
-  }
-
-  const { format, path } = detectConfigFormat()
-  const backupPath = `${path}.bak`
-
-  try {
-    let existingConfig: OpenCodeConfig | null = null
-    if (format !== "none") {
-      const parseResult = parseOpenCodeConfigFileWithError(path)
-      if (parseResult.error && !parseResult.config) {
-        return {
-          success: false,
-          configPath: path,
-          error: `Failed to parse config file: ${parseResult.error}`,
-        }
-      }
-      existingConfig = parseResult.config
-    }
-
-    const rawPlugins = existingConfig?.plugin
-    const plugins: string[] = Array.isArray(rawPlugins) ? rawPlugins : []
-
-    if (config.hasGemini) {
-      const version = await fetchLatestVersion("opencode-antigravity-auth")
-      const pluginEntry = version ? `opencode-antigravity-auth@${version}` : "opencode-antigravity-auth"
-      if (!plugins.some((p) => p.startsWith("opencode-antigravity-auth"))) {
-        plugins.push(pluginEntry)
-      }
-    }
-
-    const newConfig = { ...(existingConfig ?? {}), plugin: plugins }
-
-    if (format !== "none" && existsSync(path)) {
-      copyFileSync(path, backupPath)
-    }
-
-    if (format === "jsonc") {
-      const content = readFileSync(path, "utf-8")
-
-      const newContent = applyEdits(
-        content,
-        modify(content, ["plugin"], plugins, {
-          formattingOptions: { tabSize: 2, insertSpaces: true },
-        })
-      )
-
-      try {
-        parseJsonc(newContent)
-      } catch (error) {
-        if (existsSync(backupPath)) {
-          copyFileSync(backupPath, path)
-        }
-        throw new Error(`Generated JSONC is invalid: ${error instanceof Error ? error.message : String(error)}`)
-      }
-
-      try {
-        writeFileSync(path, newContent)
-      } catch (error) {
-        const hasBackup = existsSync(backupPath)
-        try {
-          if (hasBackup) {
-            copyFileSync(backupPath, path)
-          }
-        } catch (restoreError) {
-          return {
-            success: false,
-            configPath: path,
-            error: `Failed to write config file, and restore from backup failed: ${String(error)}; restore error: ${String(restoreError)}`,
-          }
-        }
-
-        return {
-          success: false,
-          configPath: path,
-          error: hasBackup
-            ? `Failed to write config file. Restored from backup: ${String(error)}`
-            : `Failed to write config file. No backup was available: ${String(error)}`,
-        }
-      }
-    } else {
-      const nextContent = JSON.stringify(newConfig, null, 2) + "\n"
-      try {
-        writeFileSync(path, nextContent)
-      } catch (error) {
-        const hasBackup = existsSync(backupPath)
-        try {
-          if (hasBackup) {
-            copyFileSync(backupPath, path)
-          }
-        } catch (restoreError) {
-          return {
-            success: false,
-            configPath: path,
-            error: `Failed to write config file, and restore from backup failed: ${String(error)}; restore error: ${String(restoreError)}`,
-          }
-        }
-
-        return {
-          success: false,
-          configPath: path,
-          error: hasBackup
-            ? `Failed to write config file. Restored from backup: ${String(error)}`
-            : `Failed to write config file. No backup was available: ${String(error)}`,
-        }
-      }
-    }
-    return { success: true, configPath: path }
-  } catch (err) {
-    return {
-      success: false,
-      configPath: path,
-      error: formatErrorWithSuggestion(err, "add auth plugins to config"),
-    }
-  }
-}
--- a/src/cli/config-manager/bun-install.ts
+++ b/src/cli/config-manager/bun-install.ts
@@ -1,61 +0,0 @@
-import { getConfigDir } from "./config-context"
-
-const BUN_INSTALL_TIMEOUT_SECONDS = 60
-const BUN_INSTALL_TIMEOUT_MS = BUN_INSTALL_TIMEOUT_SECONDS * 1000
-
-export interface BunInstallResult {
-  success: boolean
-  timedOut?: boolean
-  error?: string
-}
-
-export async function runBunInstall(): Promise<boolean> {
-  const result = await runBunInstallWithDetails()
-  return result.success
-}
-
-export async function runBunInstallWithDetails(): Promise<BunInstallResult> {
-  try {
-    const proc = Bun.spawn(["bun", "install"], {
-      cwd: getConfigDir(),
-      stdout: "inherit",
-      stderr: "inherit",
-    })
-
-    let timeoutId: ReturnType<typeof setTimeout>
-    const timeoutPromise = new Promise<"timeout">((resolve) => {
-      timeoutId = setTimeout(() => resolve("timeout"), BUN_INSTALL_TIMEOUT_MS)
-    })
-    const exitPromise = proc.exited.then(() => "completed" as const)
-    const result = await Promise.race([exitPromise, timeoutPromise])
-    clearTimeout(timeoutId!)
-
-    if (result === "timeout") {
-      try {
-        proc.kill()
-      } catch {
-        /* intentionally empty - process may have already exited */
-      }
-      return {
-        success: false,
-        timedOut: true,
-        error: `bun install timed out after ${BUN_INSTALL_TIMEOUT_SECONDS} seconds. Try running manually: cd ${getConfigDir()} && bun i`,
-      }
-    }
-
-    if (proc.exitCode !== 0) {
-      return {
-        success: false,
-        error: `bun install failed with exit code ${proc.exitCode}`,
-      }
-    }
-
-    return { success: true }
-  } catch (err) {
-    const message = err instanceof Error ? err.message : String(err)
-    return {
-      success: false,
-      error: `bun install failed: ${message}. Is bun installed? Try: curl -fsSL https://bun.sh/install | bash`,
-    }
-  }
-}
--- a/src/cli/config-manager/config-context.ts
+++ b/src/cli/config-manager/config-context.ts
@@ -1,49 +0,0 @@
-import { getOpenCodeConfigPaths } from "../../shared"
-import type {
-  OpenCodeBinaryType,
-  OpenCodeConfigPaths,
-} from "../../shared/opencode-config-dir-types"
-
-export interface ConfigContext {
-  binary: OpenCodeBinaryType
-  version: string | null
-  paths: OpenCodeConfigPaths
-}
-
-let configContext: ConfigContext | null = null
-
-export function initConfigContext(binary: OpenCodeBinaryType, version: string | null): void {
-  const paths = getOpenCodeConfigPaths({ binary, version })
-  configContext = { binary, version, paths }
-}
-
-export function getConfigContext(): ConfigContext {
-  if (!configContext) {
-    if (process.env.NODE_ENV !== "production") {
-      console.warn("[config-context] getConfigContext() called before initConfigContext(); defaulting to CLI paths.")
-    }
-    const paths = getOpenCodeConfigPaths({ binary: "opencode", version: null })
-    configContext = { binary: "opencode", version: null, paths }
-  }
-  return configContext
-}
-
-export function resetConfigContext(): void {
-  configContext = null
-}
-
-export function getConfigDir(): string {
-  return getConfigContext().paths.configDir
-}
-
-export function getConfigJson(): string {
-  return getConfigContext().paths.configJson
-}
-
-export function getConfigJsonc(): string {
-  return getConfigContext().paths.configJsonc
-}
-
-export function getOmoConfigPath(): string {
-  return getConfigContext().paths.omoConfig
-}
--- a/src/cli/config-manager/deep-merge-record.ts
+++ b/src/cli/config-manager/deep-merge-record.ts
@@ -1,30 +0,0 @@
-export function deepMergeRecord<TTarget extends Record<string, unknown>>(
-  target: TTarget,
-  source: Partial<TTarget>
-): TTarget {
-  const result: TTarget = { ...target }
-
-  for (const key of Object.keys(source) as Array<keyof TTarget>) {
-    if (key === "__proto__" || key === "constructor" || key === "prototype") continue
-    const sourceValue = source[key]
-    const targetValue = result[key]
-
-    if (
-      sourceValue !== null &&
-      typeof sourceValue === "object" &&
-      !Array.isArray(sourceValue) &&
-      targetValue !== null &&
-      typeof targetValue === "object" &&
-      !Array.isArray(targetValue)
-    ) {
-      result[key] = deepMergeRecord(
-        targetValue as Record<string, unknown>,
-        sourceValue as Record<string, unknown>
-      ) as TTarget[keyof TTarget]
-    } else if (sourceValue !== undefined) {
-      result[key] = sourceValue as TTarget[keyof TTarget]
-    }
-  }
-
-  return result
-}
--- a/src/cli/config-manager/detect-current-config.ts
+++ b/src/cli/config-manager/detect-current-config.ts
@@ -1,78 +0,0 @@
-import { existsSync, readFileSync } from "node:fs"
-import { parseJsonc } from "../../shared"
-import type { DetectedConfig } from "../types"
-import { getOmoConfigPath } from "./config-context"
-import { detectConfigFormat } from "./opencode-config-format"
-import { parseOpenCodeConfigFileWithError } from "./parse-opencode-config-file"
-
-function detectProvidersFromOmoConfig(): {
-  hasOpenAI: boolean
-  hasOpencodeZen: boolean
-  hasZaiCodingPlan: boolean
-  hasKimiForCoding: boolean
-} {
-  const omoConfigPath = getOmoConfigPath()
-  if (!existsSync(omoConfigPath)) {
-    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, 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, hasKimiForCoding }
-  } catch {
-    return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
-  }
-}
-
-export function detectCurrentConfig(): DetectedConfig {
-  const result: DetectedConfig = {
-    isInstalled: false,
-    hasClaude: true,
-    isMax20: true,
-    hasOpenAI: true,
-    hasGemini: false,
-    hasCopilot: false,
-    hasOpencodeZen: true,
-    hasZaiCodingPlan: false,
-    hasKimiForCoding: false,
-  }
-
-  const { format, path } = detectConfigFormat()
-  if (format === "none") {
-    return result
-  }
-
-  const parseResult = parseOpenCodeConfigFileWithError(path)
-  if (!parseResult.config) {
-    return result
-  }
-
-  const openCodeConfig = parseResult.config
-  const plugins = openCodeConfig.plugin ?? []
-  result.isInstalled = plugins.some((p) => p.startsWith("oh-my-opencode"))
-
-  if (!result.isInstalled) {
-    return result
-  }
-
-  result.hasGemini = plugins.some((p) => p.startsWith("opencode-antigravity-auth"))
-
-  const { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan, hasKimiForCoding } = detectProvidersFromOmoConfig()
-  result.hasOpenAI = hasOpenAI
-  result.hasOpencodeZen = hasOpencodeZen
-  result.hasZaiCodingPlan = hasZaiCodingPlan
-  result.hasKimiForCoding = hasKimiForCoding
-
-  return result
-}
--- a/src/cli/config-manager/ensure-config-directory-exists.ts
+++ b/src/cli/config-manager/ensure-config-directory-exists.ts
@@ -1,9 +0,0 @@
-import { existsSync, mkdirSync } from "node:fs"
-import { getConfigDir } from "./config-context"
-
-export function ensureConfigDirectoryExists(): void {
-  const configDir = getConfigDir()
-  if (!existsSync(configDir)) {
-    mkdirSync(configDir, { recursive: true })
-  }
-}
--- a/src/cli/config-manager/format-error-with-suggestion.ts
+++ b/src/cli/config-manager/format-error-with-suggestion.ts
@@ -1,39 +0,0 @@
-interface NodeError extends Error {
-  code?: string
-}
-
-function isPermissionError(err: unknown): boolean {
-  const nodeErr = err as NodeError
-  return nodeErr?.code === "EACCES" || nodeErr?.code === "EPERM"
-}
-
-function isFileNotFoundError(err: unknown): boolean {
-  const nodeErr = err as NodeError
-  return nodeErr?.code === "ENOENT"
-}
-
-export function formatErrorWithSuggestion(err: unknown, context: string): string {
-  if (isPermissionError(err)) {
-    return `Permission denied: Cannot ${context}. Try running with elevated permissions or check file ownership.`
-  }
-
-  if (isFileNotFoundError(err)) {
-    return `File not found while trying to ${context}. The file may have been deleted or moved.`
-  }
-
-  if (err instanceof SyntaxError) {
-    return `JSON syntax error while trying to ${context}: ${err.message}. Check for missing commas, brackets, or invalid characters.`
-  }
-
-  const message = err instanceof Error ? err.message : String(err)
-
-  if (message.includes("ENOSPC")) {
-    return `Disk full: Cannot ${context}. Free up disk space and try again.`
-  }
-
-  if (message.includes("EROFS")) {
-    return `Read-only filesystem: Cannot ${context}. Check if the filesystem is mounted read-only.`
-  }
-
-  return `Failed to ${context}: ${message}`
-}
--- a/src/cli/config-manager/generate-omo-config.ts
+++ b/src/cli/config-manager/generate-omo-config.ts
@@ -1,6 +0,0 @@
-import type { InstallConfig } from "../types"
-import { generateModelConfig } from "../model-fallback"
-
-export function generateOmoConfig(installConfig: InstallConfig): Record<string, unknown> {
-  return generateModelConfig(installConfig)
-}
--- a/src/cli/config-manager/jsonc-provider-editor.ts
+++ b/src/cli/config-manager/jsonc-provider-editor.ts
@@ -1,11 +0,0 @@
-import { modify, applyEdits } from "jsonc-parser"
-
-export function modifyProviderInJsonc(
-  content: string,
-  newProviderValue: Record<string, unknown>
-): string {
-  const edits = modify(content, ["provider"], newProviderValue, {
-    formattingOptions: { tabSize: 2, insertSpaces: true },
-  })
-  return applyEdits(content, edits)
-}
--- a/src/cli/config-manager/npm-dist-tags.ts
+++ b/src/cli/config-manager/npm-dist-tags.ts
@@ -1,21 +0,0 @@
-export interface NpmDistTags {
-  latest?: string
-  beta?: string
-  next?: string
-  [tag: string]: string | undefined
-}
-
-const NPM_FETCH_TIMEOUT_MS = 5000
-
-export async function fetchNpmDistTags(packageName: string): Promise<NpmDistTags | null> {
-  try {
-    const res = await fetch(`https://registry.npmjs.org/-/package/${encodeURIComponent(packageName)}/dist-tags`, {
-      signal: AbortSignal.timeout(NPM_FETCH_TIMEOUT_MS),
-    })
-    if (!res.ok) return null
-    const data = (await res.json()) as NpmDistTags
-    return data
-  } catch {
-    return null
-  }
-}
--- a/src/cli/config-manager/opencode-binary.ts
+++ b/src/cli/config-manager/opencode-binary.ts
@@ -1,40 +0,0 @@
-import type { OpenCodeBinaryType } from "../../shared/opencode-config-dir-types"
-import { initConfigContext } from "./config-context"
-
-const OPENCODE_BINARIES = ["opencode", "opencode-desktop"] as const
-
-interface OpenCodeBinaryResult {
-  binary: OpenCodeBinaryType
-  version: string
-}
-
-async function findOpenCodeBinaryWithVersion(): Promise<OpenCodeBinaryResult | null> {
-  for (const binary of OPENCODE_BINARIES) {
-    try {
-      const proc = Bun.spawn([binary, "--version"], {
-        stdout: "pipe",
-        stderr: "pipe",
-      })
-      const output = await new Response(proc.stdout).text()
-      await proc.exited
-      if (proc.exitCode === 0) {
-        const version = output.trim()
-        initConfigContext(binary, version)
-        return { binary, version }
-      }
-    } catch {
-      continue
-    }
-  }
-  return null
-}
-
-export async function isOpenCodeInstalled(): Promise<boolean> {
-  const result = await findOpenCodeBinaryWithVersion()
-  return result !== null
-}
-
-export async function getOpenCodeVersion(): Promise<string | null> {
-  const result = await findOpenCodeBinaryWithVersion()
-  return result?.version ?? null
-}
--- a/src/cli/config-manager/opencode-config-format.ts
+++ b/src/cli/config-manager/opencode-config-format.ts
@@ -1,17 +0,0 @@
-import { existsSync } from "node:fs"
-import { getConfigJson, getConfigJsonc } from "./config-context"
-
-export type ConfigFormat = "json" | "jsonc" | "none"
-
-export function detectConfigFormat(): { format: ConfigFormat; path: string } {
-  const configJsonc = getConfigJsonc()
-  const configJson = getConfigJson()
-
-  if (existsSync(configJsonc)) {
-    return { format: "jsonc", path: configJsonc }
-  }
-  if (existsSync(configJson)) {
-    return { format: "json", path: configJson }
-  }
-  return { format: "none", path: configJson }
-}
--- a/src/cli/config-manager/parse-opencode-config-file.ts
+++ b/src/cli/config-manager/parse-opencode-config-file.ts
@@ -1,48 +0,0 @@
-import { readFileSync, statSync } from "node:fs"
-import { parseJsonc } from "../../shared"
-import { formatErrorWithSuggestion } from "./format-error-with-suggestion"
-
-interface ParseConfigResult {
-  config: OpenCodeConfig | null
-  error?: string
-}
-
-export interface OpenCodeConfig {
-  plugin?: string[]
-  [key: string]: unknown
-}
-
-function isEmptyOrWhitespace(content: string): boolean {
-  return content.trim().length === 0
-}
-
-export function parseOpenCodeConfigFileWithError(path: string): ParseConfigResult {
-  try {
-    const stat = statSync(path)
-    if (stat.size === 0) {
-      return { config: null, error: `Config file is empty: ${path}. Delete it or add valid JSON content.` }
-    }
-
-    const content = readFileSync(path, "utf-8")
-    if (isEmptyOrWhitespace(content)) {
-      return { config: null, error: `Config file contains only whitespace: ${path}. Delete it or add valid JSON content.` }
-    }
-
-    const config = parseJsonc<OpenCodeConfig>(content)
-
-    if (config === null || config === undefined) {
-      return { config: null, error: `Config file parsed to null/undefined: ${path}. Ensure it contains valid JSON.` }
-    }
-
-    if (typeof config !== "object" || Array.isArray(config)) {
-      return {
-        config: null,
-        error: `Config file must contain a JSON object, not ${Array.isArray(config) ? "an array" : typeof config}: ${path}`,
-      }
-    }
-
-    return { config }
-  } catch (err) {
-    return { config: null, error: formatErrorWithSuggestion(err, `parse config file ${path}`) }
-  }
-}
--- a/src/cli/config-manager/plugin-name-with-version.ts
+++ b/src/cli/config-manager/plugin-name-with-version.ts
@@ -1,19 +0,0 @@
-import { fetchNpmDistTags } from "./npm-dist-tags"
-
-const PACKAGE_NAME = "oh-my-opencode"
-const PRIORITIZED_TAGS = ["latest", "beta", "next"] as const
-
-export async function getPluginNameWithVersion(currentVersion: string): Promise<string> {
-  const distTags = await fetchNpmDistTags(PACKAGE_NAME)
-
-  if (distTags) {
-    const allTags = new Set([...PRIORITIZED_TAGS, ...Object.keys(distTags)])
-    for (const tag of allTags) {
-      if (distTags[tag] === currentVersion) {
-        return `${PACKAGE_NAME}@${tag}`
-      }
-    }
-  }
-
-  return `${PACKAGE_NAME}@${currentVersion}`
-}
--- a/src/cli/config-manager/write-omo-config.ts
+++ b/src/cli/config-manager/write-omo-config.ts
@@ -1,67 +0,0 @@
-import { existsSync, readFileSync, statSync, writeFileSync } from "node:fs"
-import { parseJsonc } from "../../shared"
-import type { ConfigMergeResult, InstallConfig } from "../types"
-import { getConfigDir, getOmoConfigPath } from "./config-context"
-import { deepMergeRecord } from "./deep-merge-record"
-import { ensureConfigDirectoryExists } from "./ensure-config-directory-exists"
-import { formatErrorWithSuggestion } from "./format-error-with-suggestion"
-import { generateOmoConfig } from "./generate-omo-config"
-
-function isEmptyOrWhitespace(content: string): boolean {
-  return content.trim().length === 0
-}
-
-export function writeOmoConfig(installConfig: InstallConfig): ConfigMergeResult {
-  try {
-    ensureConfigDirectoryExists()
-  } catch (err) {
-    return {
-      success: false,
-      configPath: getConfigDir(),
-      error: formatErrorWithSuggestion(err, "create config directory"),
-    }
-  }
-
-  const omoConfigPath = getOmoConfigPath()
-
-  try {
-    const newConfig = generateOmoConfig(installConfig)
-
-    if (existsSync(omoConfigPath)) {
-      try {
-        const stat = statSync(omoConfigPath)
-        const content = readFileSync(omoConfigPath, "utf-8")
-
-        if (stat.size === 0 || isEmptyOrWhitespace(content)) {
-          writeFileSync(omoConfigPath, JSON.stringify(newConfig, null, 2) + "\n")
-          return { success: true, configPath: omoConfigPath }
-        }
-
-        const existing = parseJsonc<Record<string, unknown>>(content)
-        if (!existing || typeof existing !== "object" || Array.isArray(existing)) {
-          writeFileSync(omoConfigPath, JSON.stringify(newConfig, null, 2) + "\n")
-          return { success: true, configPath: omoConfigPath }
-        }
-
-        const merged = deepMergeRecord(existing, newConfig)
-        writeFileSync(omoConfigPath, JSON.stringify(merged, null, 2) + "\n")
-      } catch (parseErr) {
-        if (parseErr instanceof SyntaxError) {
-          writeFileSync(omoConfigPath, JSON.stringify(newConfig, null, 2) + "\n")
-          return { success: true, configPath: omoConfigPath }
-        }
-        throw parseErr
-      }
-    } else {
-      writeFileSync(omoConfigPath, JSON.stringify(newConfig, null, 2) + "\n")
-    }
-
-    return { success: true, configPath: omoConfigPath }
-  } catch (err) {
-    return {
-      success: false,
-      configPath: omoConfigPath,
-      error: formatErrorWithSuggestion(err, "write oh-my-opencode config"),
-    }
-  }
-}
--- a/src/cli/doctor/checks/index.ts
+++ b/src/cli/doctor/checks/index.ts
@@ -15,12 +15,6 @@ export * from "./opencode"
 export * from "./plugin"
 export * from "./config"
 export * from "./model-resolution"
-export * from "./model-resolution-types"
-export * from "./model-resolution-cache"
-export * from "./model-resolution-config"
-export * from "./model-resolution-effective-model"
-export * from "./model-resolution-variant"
-export * from "./model-resolution-details"
 export * from "./auth"
 export * from "./dependencies"
 export * from "./gh"
--- a/src/cli/doctor/checks/model-resolution-cache.ts
+++ b/src/cli/doctor/checks/model-resolution-cache.ts
@@ -1,37 +0,0 @@
-import { existsSync, readFileSync } from "node:fs"
-import { homedir } from "node:os"
-import { join } from "node:path"
-import { parseJsonc } from "../../../shared"
-import type { AvailableModelsInfo } from "./model-resolution-types"
-
-function getOpenCodeCacheDir(): string {
-  const xdgCache = process.env.XDG_CACHE_HOME
-  if (xdgCache) return join(xdgCache, "opencode")
-  return join(homedir(), ".cache", "opencode")
-}
-
-export function loadAvailableModelsFromCache(): AvailableModelsInfo {
-  const cacheFile = join(getOpenCodeCacheDir(), "models.json")
-
-  if (!existsSync(cacheFile)) {
-    return { providers: [], modelCount: 0, cacheExists: false }
-  }
-
-  try {
-    const content = readFileSync(cacheFile, "utf-8")
-    const data = parseJsonc<Record<string, { models?: Record<string, unknown> }>>(content)
-
-    const providers = Object.keys(data)
-    let modelCount = 0
-    for (const providerId of providers) {
-      const models = data[providerId]?.models
-      if (models && typeof models === "object") {
-        modelCount += Object.keys(models).length
-      }
-    }
-
-    return { providers, modelCount, cacheExists: true }
-  } catch {
-    return { providers: [], modelCount: 0, cacheExists: false }
-  }
-}
--- a/src/cli/doctor/checks/model-resolution-config.ts
+++ b/src/cli/doctor/checks/model-resolution-config.ts
@@ -1,35 +0,0 @@
-import { readFileSync } from "node:fs"
-import { join } from "node:path"
-import { detectConfigFile, getOpenCodeConfigPaths, parseJsonc } from "../../../shared"
-import type { OmoConfig } from "./model-resolution-types"
-
-const PACKAGE_NAME = "oh-my-opencode"
-const USER_CONFIG_BASE = join(
-  getOpenCodeConfigPaths({ binary: "opencode", version: null }).configDir,
-  PACKAGE_NAME
-)
-const PROJECT_CONFIG_BASE = join(process.cwd(), ".opencode", PACKAGE_NAME)
-
-export function loadOmoConfig(): OmoConfig | null {
-  const projectDetected = detectConfigFile(PROJECT_CONFIG_BASE)
-  if (projectDetected.format !== "none") {
-    try {
-      const content = readFileSync(projectDetected.path, "utf-8")
-      return parseJsonc<OmoConfig>(content)
-    } catch {
-      return null
-    }
-  }
-
-  const userDetected = detectConfigFile(USER_CONFIG_BASE)
-  if (userDetected.format !== "none") {
-    try {
-      const content = readFileSync(userDetected.path, "utf-8")
-      return parseJsonc<OmoConfig>(content)
-    } catch {
-      return null
-    }
-  }
-
-  return null
-}
--- a/src/cli/doctor/checks/model-resolution-details.ts
+++ b/src/cli/doctor/checks/model-resolution-details.ts
@@ -1,56 +0,0 @@
-import { join } from "node:path"
-
-import { getOpenCodeCacheDir } from "../../../shared"
-import type { AvailableModelsInfo, ModelResolutionInfo, OmoConfig } from "./model-resolution-types"
-import { formatModelWithVariant, getCategoryEffectiveVariant, getEffectiveVariant } from "./model-resolution-variant"
-
-export function buildModelResolutionDetails(options: {
-  info: ModelResolutionInfo
-  available: AvailableModelsInfo
-  config: OmoConfig
-}): string[] {
-  const details: string[] = []
-  const cacheFile = join(getOpenCodeCacheDir(), "models.json")
-
-  details.push("═══ Available Models (from cache) ═══")
-  details.push("")
-  if (options.available.cacheExists) {
-    details.push(`  Providers in cache: ${options.available.providers.length}`)
-    details.push(
-      `  Sample: ${options.available.providers.slice(0, 6).join(", ")}${options.available.providers.length > 6 ? "..." : ""}`
-    )
-    details.push(`  Total models: ${options.available.modelCount}`)
-    details.push(`  Cache: ${cacheFile}`)
-    details.push(`  ℹ Runtime: only connected providers used`)
-    details.push(`  Refresh: opencode models --refresh`)
-  } else {
-    details.push("  ⚠ Cache not found. Run 'opencode' to populate.")
-  }
-  details.push("")
-
-  details.push("═══ Configured Models ═══")
-  details.push("")
-  details.push("Agents:")
-  for (const agent of options.info.agents) {
-    const marker = agent.userOverride ? "●" : "○"
-    const display = formatModelWithVariant(
-      agent.effectiveModel,
-      getEffectiveVariant(agent.name, agent.requirement, options.config)
-    )
-    details.push(`  ${marker} ${agent.name}: ${display}`)
-  }
-  details.push("")
-  details.push("Categories:")
-  for (const category of options.info.categories) {
-    const marker = category.userOverride ? "●" : "○"
-    const display = formatModelWithVariant(
-      category.effectiveModel,
-      getCategoryEffectiveVariant(category.name, category.requirement, options.config)
-    )
-    details.push(`  ${marker} ${category.name}: ${display}`)
-  }
-  details.push("")
-  details.push("● = user override, ○ = provider fallback")
-
-  return details
-}
--- a/src/cli/doctor/checks/model-resolution-effective-model.ts
+++ b/src/cli/doctor/checks/model-resolution-effective-model.ts
@@ -1,27 +0,0 @@
-import type { ModelRequirement } from "../../../shared/model-requirements"
-
-function formatProviderChain(providers: string[]): string {
-  return providers.join(" → ")
-}
-
-export function getEffectiveModel(requirement: ModelRequirement, userOverride?: string): string {
-  if (userOverride) {
-    return userOverride
-  }
-  const firstEntry = requirement.fallbackChain[0]
-  if (!firstEntry) {
-    return "unknown"
-  }
-  return `${firstEntry.providers[0]}/${firstEntry.model}`
-}
-
-export function buildEffectiveResolution(requirement: ModelRequirement, userOverride?: string): string {
-  if (userOverride) {
-    return `User override: ${userOverride}`
-  }
-  const firstEntry = requirement.fallbackChain[0]
-  if (!firstEntry) {
-    return "No fallback chain defined"
-  }
-  return `Provider fallback: ${formatProviderChain(firstEntry.providers)} → ${firstEntry.model}`
-}
--- a/src/cli/doctor/checks/model-resolution-types.ts
+++ b/src/cli/doctor/checks/model-resolution-types.ts
@@ -1,35 +0,0 @@
-import type { ModelRequirement } from "../../../shared/model-requirements"
-
-export interface AgentResolutionInfo {
-  name: string
-  requirement: ModelRequirement
-  userOverride?: string
-  userVariant?: string
-  effectiveModel: string
-  effectiveResolution: string
-}
-
-export interface CategoryResolutionInfo {
-  name: string
-  requirement: ModelRequirement
-  userOverride?: string
-  userVariant?: string
-  effectiveModel: string
-  effectiveResolution: string
-}
-
-export interface ModelResolutionInfo {
-  agents: AgentResolutionInfo[]
-  categories: CategoryResolutionInfo[]
-}
-
-export interface OmoConfig {
-  agents?: Record<string, { model?: string; variant?: string; category?: string }>
-  categories?: Record<string, { model?: string; variant?: string }>
-}
-
-export interface AvailableModelsInfo {
-  providers: string[]
-  modelCount: number
-  cacheExists: boolean
-}
--- a/src/cli/doctor/checks/model-resolution-variant.ts
+++ b/src/cli/doctor/checks/model-resolution-variant.ts
@@ -1,55 +0,0 @@
-import type { ModelRequirement } from "../../../shared/model-requirements"
-import type { OmoConfig } from "./model-resolution-types"
-
-export function formatModelWithVariant(model: string, variant?: string): string {
-  return variant ? `${model} (${variant})` : model
-}
-
-function getAgentOverride(
-  agentName: string,
-  config: OmoConfig
-): { variant?: string; category?: string } | undefined {
-  const agentOverrides = config.agents
-  if (!agentOverrides) return undefined
-
-  return (
-    agentOverrides[agentName] ??
-    Object.entries(agentOverrides).find(([key]) => key.toLowerCase() === agentName.toLowerCase())?.[1]
-  )
-}
-
-export function getEffectiveVariant(
-  agentName: string,
-  requirement: ModelRequirement,
-  config: OmoConfig
-): string | undefined {
-  const agentOverride = getAgentOverride(agentName, config)
-
-  if (agentOverride?.variant) {
-    return agentOverride.variant
-  }
-
-  const categoryName = agentOverride?.category
-  if (categoryName) {
-    const categoryVariant = config.categories?.[categoryName]?.variant
-    if (categoryVariant) {
-      return categoryVariant
-    }
-  }
-
-  const firstEntry = requirement.fallbackChain[0]
-  return firstEntry?.variant ?? requirement.variant
-}
-
-export function getCategoryEffectiveVariant(
-  categoryName: string,
-  requirement: ModelRequirement,
-  config: OmoConfig
-): string | undefined {
-  const categoryVariant = config.categories?.[categoryName]?.variant
-  if (categoryVariant) {
-    return categoryVariant
-  }
-  const firstEntry = requirement.fallbackChain[0]
-  return firstEntry?.variant ?? requirement.variant
-}
--- a/src/cli/doctor/checks/model-resolution.ts
+++ b/src/cli/doctor/checks/model-resolution.ts
@@ -1,14 +1,132 @@
+import { readFileSync, existsSync } from "node:fs"
 import type { CheckResult, CheckDefinition } from "../types"
 import { CHECK_IDS, CHECK_NAMES } from "../constants"
+import { parseJsonc, detectConfigFile } from "../../../shared"
 import {
  AGENT_MODEL_REQUIREMENTS,
  CATEGORY_MODEL_REQUIREMENTS,
+  type ModelRequirement,
 } from "../../../shared/model-requirements"
-import type { OmoConfig, ModelResolutionInfo, AgentResolutionInfo, CategoryResolutionInfo } from "./model-resolution-types"
-import { loadAvailableModelsFromCache } from "./model-resolution-cache"
-import { loadOmoConfig } from "./model-resolution-config"
-import { buildEffectiveResolution, getEffectiveModel } from "./model-resolution-effective-model"
-import { buildModelResolutionDetails } from "./model-resolution-details"
+import { homedir } from "node:os"
+import { join } from "node:path"
+
+function getOpenCodeCacheDir(): string {
+  const xdgCache = process.env.XDG_CACHE_HOME
+  if (xdgCache) return join(xdgCache, "opencode")
+  return join(homedir(), ".cache", "opencode")
+}
+
+function loadAvailableModels(): { providers: string[]; modelCount: number; cacheExists: boolean } {
+  const cacheFile = join(getOpenCodeCacheDir(), "models.json")
+  
+  if (!existsSync(cacheFile)) {
+    return { providers: [], modelCount: 0, cacheExists: false }
+  }
+
+  try {
+    const content = readFileSync(cacheFile, "utf-8")
+    const data = JSON.parse(content) as Record<string, { models?: Record<string, unknown> }>
+    
+    const providers = Object.keys(data)
+    let modelCount = 0
+    for (const providerId of providers) {
+      const models = data[providerId]?.models
+      if (models && typeof models === "object") {
+        modelCount += Object.keys(models).length
+      }
+    }
+    
+    return { providers, modelCount, cacheExists: true }
+  } catch {
+    return { providers: [], modelCount: 0, cacheExists: false }
+  }
+}
+
+const PACKAGE_NAME = "oh-my-opencode"
+const USER_CONFIG_DIR = join(homedir(), ".config", "opencode")
+const USER_CONFIG_BASE = join(USER_CONFIG_DIR, PACKAGE_NAME)
+const PROJECT_CONFIG_BASE = join(process.cwd(), ".opencode", PACKAGE_NAME)
+
+export interface AgentResolutionInfo {
+  name: string
+  requirement: ModelRequirement
+  userOverride?: string
+  userVariant?: string
+  effectiveModel: string
+  effectiveResolution: string
+}
+
+export interface CategoryResolutionInfo {
+  name: string
+  requirement: ModelRequirement
+  userOverride?: string
+  userVariant?: string
+  effectiveModel: string
+  effectiveResolution: string
+}
+
+export interface ModelResolutionInfo {
+  agents: AgentResolutionInfo[]
+  categories: CategoryResolutionInfo[]
+}
+
+interface OmoConfig {
+  agents?: Record<string, { model?: string; variant?: string; category?: string }>
+  categories?: Record<string, { model?: string; variant?: string }>
+}
+
+function loadConfig(): OmoConfig | null {
+  const projectDetected = detectConfigFile(PROJECT_CONFIG_BASE)
+  if (projectDetected.format !== "none") {
+    try {
+      const content = readFileSync(projectDetected.path, "utf-8")
+      return parseJsonc<OmoConfig>(content)
+    } catch {
+      return null
+    }
+  }
+
+  const userDetected = detectConfigFile(USER_CONFIG_BASE)
+  if (userDetected.format !== "none") {
+    try {
+      const content = readFileSync(userDetected.path, "utf-8")
+      return parseJsonc<OmoConfig>(content)
+    } catch {
+      return null
+    }
+  }
+
+  return null
+}
+
+function formatProviderChain(providers: string[]): string {
+  return providers.join(" → ")
+}
+
+function getEffectiveModel(requirement: ModelRequirement, userOverride?: string): string {
+  if (userOverride) {
+    return userOverride
+  }
+  const firstEntry = requirement.fallbackChain[0]
+  if (!firstEntry) {
+    return "unknown"
+  }
+  return `${firstEntry.providers[0]}/${firstEntry.model}`
+}
+
+function buildEffectiveResolution(
+  requirement: ModelRequirement,
+  userOverride?: string,
+): string {
+  if (userOverride) {
+    return `User override: ${userOverride}`
+  }
+  const firstEntry = requirement.fallbackChain[0]
+  if (!firstEntry) {
+    return "No fallback chain defined"
+  }
+  return `Provider fallback: ${formatProviderChain(firstEntry.providers)} → ${firstEntry.model}`
+}

 export function getModelResolutionInfo(): ModelResolutionInfo {
  const agents: AgentResolutionInfo[] = Object.entries(AGENT_MODEL_REQUIREMENTS).map(
@@ -66,10 +184,116 @@ export function getModelResolutionInfoWithOverrides(config: OmoConfig): ModelRes
  return { agents, categories }
 }

+function formatModelWithVariant(model: string, variant?: string): string {
+  return variant ? `${model} (${variant})` : model
+}
+
+function getAgentOverride(
+  agentName: string,
+  config: OmoConfig,
+): { variant?: string; category?: string } | undefined {
+  const agentOverrides = config.agents
+  if (!agentOverrides) return undefined
+
+  // Direct lookup first, then case-insensitive lookup (matches agent-variant.ts)
+  return (
+    agentOverrides[agentName] ??
+    Object.entries(agentOverrides).find(
+      ([key]) => key.toLowerCase() === agentName.toLowerCase()
+    )?.[1]
+  )
+}
+
+function getEffectiveVariant(
+  name: string,
+  requirement: ModelRequirement,
+  config: OmoConfig,
+): string | undefined {
+  const agentOverride = getAgentOverride(name, config)
+
+  // Priority 1: Agent's direct variant override
+  if (agentOverride?.variant) {
+    return agentOverride.variant
+  }
+
+  // Priority 2: Agent's category -> category's variant (matches agent-variant.ts)
+  const categoryName = agentOverride?.category
+  if (categoryName) {
+    const categoryVariant = config.categories?.[categoryName]?.variant
+    if (categoryVariant) {
+      return categoryVariant
+    }
+  }
+
+  // Priority 3: Fall back to requirement's fallback chain
+  const firstEntry = requirement.fallbackChain[0]
+  return firstEntry?.variant ?? requirement.variant
+}
+
+interface AvailableModelsInfo {
+  providers: string[]
+  modelCount: number
+  cacheExists: boolean
+}
+
+function getCategoryEffectiveVariant(
+  categoryName: string,
+  requirement: ModelRequirement,
+  config: OmoConfig,
+): string | undefined {
+  const categoryVariant = config.categories?.[categoryName]?.variant
+  if (categoryVariant) {
+    return categoryVariant
+  }
+  const firstEntry = requirement.fallbackChain[0]
+  return firstEntry?.variant ?? requirement.variant
+}
+
+function buildDetailsArray(info: ModelResolutionInfo, available: AvailableModelsInfo, config: OmoConfig): string[] {
+  const details: string[] = []
+
+  details.push("═══ Available Models (from cache) ═══")
+  details.push("")
+  if (available.cacheExists) {
+    details.push(`  Providers in cache: ${available.providers.length}`)
+    details.push(`  Sample: ${available.providers.slice(0, 6).join(", ")}${available.providers.length > 6 ? "..." : ""}`)
+    details.push(`  Total models: ${available.modelCount}`)
+    details.push(`  Cache: ~/.cache/opencode/models.json`)
+    details.push(`  ℹ Runtime: only connected providers used`)
+    details.push(`  Refresh: opencode models --refresh`)
+  } else {
+    details.push("  ⚠ Cache not found. Run 'opencode' to populate.")
+  }
+  details.push("")
+
+  details.push("═══ Configured Models ═══")
+  details.push("")
+  details.push("Agents:")
+  for (const agent of info.agents) {
+    const marker = agent.userOverride ? "●" : "○"
+    const display = formatModelWithVariant(agent.effectiveModel, getEffectiveVariant(agent.name, agent.requirement, config))
+    details.push(`  ${marker} ${agent.name}: ${display}`)
+  }
+  details.push("")
+  details.push("Categories:")
+  for (const category of info.categories) {
+    const marker = category.userOverride ? "●" : "○"
+    const display = formatModelWithVariant(
+      category.effectiveModel,
+      getCategoryEffectiveVariant(category.name, category.requirement, config)
+    )
+    details.push(`  ${marker} ${category.name}: ${display}`)
+  }
+  details.push("")
+  details.push("● = user override, ○ = provider fallback")
+
+  return details
+}
+
 export async function checkModelResolution(): Promise<CheckResult> {
-  const config = loadOmoConfig() ?? {}
+  const config = loadConfig() ?? {}
  const info = getModelResolutionInfoWithOverrides(config)
-  const available = loadAvailableModelsFromCache()
+  const available = loadAvailableModels()

  const agentCount = info.agents.length
  const categoryCount = info.categories.length
@@ -84,7 +308,7 @@ export async function checkModelResolution(): Promise<CheckResult> {
    name: CHECK_NAMES[CHECK_IDS.MODEL_RESOLUTION],
    status: available.cacheExists ? "pass" : "warn",
    message: `${agentCount} agents, ${categoryCount} categories${overrideNote}${cacheNote}`,
-    details: buildModelResolutionDetails({ info, available, config }),
+    details: buildDetailsArray(info, available, config),
  }
 }

--- a/src/cli/fallback-chain-resolution.ts
+++ b/src/cli/fallback-chain-resolution.ts
@@ -1,55 +0,0 @@
-import {
-	AGENT_MODEL_REQUIREMENTS,
-	type FallbackEntry,
-} from "../shared/model-requirements"
-import type { ProviderAvailability } from "./model-fallback-types"
-import { isProviderAvailable } from "./provider-availability"
-import { transformModelForProvider } from "./provider-model-id-transform"
-
-export function resolveModelFromChain(
-	fallbackChain: FallbackEntry[],
-	availability: ProviderAvailability
-): { model: string; variant?: string } | null {
-	for (const entry of fallbackChain) {
-		for (const provider of entry.providers) {
-			if (isProviderAvailable(provider, availability)) {
-				const transformedModel = transformModelForProvider(provider, entry.model)
-				return {
-					model: `${provider}/${transformedModel}`,
-					variant: entry.variant,
-				}
-			}
-		}
-	}
-	return null
-}
-
-export function getSisyphusFallbackChain(): FallbackEntry[] {
-	return AGENT_MODEL_REQUIREMENTS.sisyphus.fallbackChain
-}
-
-export function isAnyFallbackEntryAvailable(
-	fallbackChain: FallbackEntry[],
-	availability: ProviderAvailability
-): boolean {
-	return fallbackChain.some((entry) =>
-		entry.providers.some((provider) => isProviderAvailable(provider, availability))
-	)
-}
-
-export function isRequiredModelAvailable(
-	requiresModel: string,
-	fallbackChain: FallbackEntry[],
-	availability: ProviderAvailability
-): boolean {
-	const matchingEntry = fallbackChain.find((entry) => entry.model === requiresModel)
-	if (!matchingEntry) return false
-	return matchingEntry.providers.some((provider) => isProviderAvailable(provider, availability))
-}
-
-export function isRequiredProviderAvailable(
-	requiredProviders: string[],
-	availability: ProviderAvailability
-): boolean {
-	return requiredProviders.some((provider) => isProviderAvailable(provider, availability))
-}
--- a/src/cli/get-local-version/get-local-version.ts
+++ b/src/cli/get-local-version/get-local-version.ts
@@ -1,112 +0,0 @@
-import {
-  findPluginEntry,
-  getCachedVersion,
-  getLatestVersion,
-  getLocalDevVersion,
-  isLocalDevMode,
-} from "../../hooks/auto-update-checker/checker"
-
-import type { GetLocalVersionOptions, VersionInfo } from "./types"
-import { formatJsonOutput, formatVersionOutput } from "./formatter"
-
-export async function getLocalVersion(
-  options: GetLocalVersionOptions = {}
-): Promise<number> {
-  const directory = options.directory ?? process.cwd()
-
-  try {
-    if (isLocalDevMode(directory)) {
-      const currentVersion = getLocalDevVersion(directory) ?? getCachedVersion()
-      const info: VersionInfo = {
-        currentVersion,
-        latestVersion: null,
-        isUpToDate: false,
-        isLocalDev: true,
-        isPinned: false,
-        pinnedVersion: null,
-        status: "local-dev",
-      }
-
-      console.log(options.json ? formatJsonOutput(info) : formatVersionOutput(info))
-      return 0
-    }
-
-    const pluginInfo = findPluginEntry(directory)
-    if (pluginInfo?.isPinned) {
-      const info: VersionInfo = {
-        currentVersion: pluginInfo.pinnedVersion,
-        latestVersion: null,
-        isUpToDate: false,
-        isLocalDev: false,
-        isPinned: true,
-        pinnedVersion: pluginInfo.pinnedVersion,
-        status: "pinned",
-      }
-
-      console.log(options.json ? formatJsonOutput(info) : formatVersionOutput(info))
-      return 0
-    }
-
-    const currentVersion = getCachedVersion()
-    if (!currentVersion) {
-      const info: VersionInfo = {
-        currentVersion: null,
-        latestVersion: null,
-        isUpToDate: false,
-        isLocalDev: false,
-        isPinned: false,
-        pinnedVersion: null,
-        status: "unknown",
-      }
-
-      console.log(options.json ? formatJsonOutput(info) : formatVersionOutput(info))
-      return 1
-    }
-
-    const { extractChannel } = await import("../../hooks/auto-update-checker/index")
-    const channel = extractChannel(pluginInfo?.pinnedVersion ?? currentVersion)
-    const latestVersion = await getLatestVersion(channel)
-
-    if (!latestVersion) {
-      const info: VersionInfo = {
-        currentVersion,
-        latestVersion: null,
-        isUpToDate: false,
-        isLocalDev: false,
-        isPinned: false,
-        pinnedVersion: null,
-        status: "error",
-      }
-
-      console.log(options.json ? formatJsonOutput(info) : formatVersionOutput(info))
-      return 0
-    }
-
-    const isUpToDate = currentVersion === latestVersion
-    const info: VersionInfo = {
-      currentVersion,
-      latestVersion,
-      isUpToDate,
-      isLocalDev: false,
-      isPinned: false,
-      pinnedVersion: null,
-      status: isUpToDate ? "up-to-date" : "outdated",
-    }
-
-    console.log(options.json ? formatJsonOutput(info) : formatVersionOutput(info))
-    return 0
-  } catch (error) {
-    const info: VersionInfo = {
-      currentVersion: null,
-      latestVersion: null,
-      isUpToDate: false,
-      isLocalDev: false,
-      isPinned: false,
-      pinnedVersion: null,
-      status: "error",
-    }
-
-    console.log(options.json ? formatJsonOutput(info) : formatVersionOutput(info))
-    return 1
-  }
-}
--- a/src/cli/get-local-version/index.ts
+++ b/src/cli/get-local-version/index.ts
@@ -1,2 +1,106 @@
-export { getLocalVersion } from "./get-local-version"
+import { getCachedVersion, getLatestVersion, isLocalDevMode, findPluginEntry } from "../../hooks/auto-update-checker/checker"
+import type { GetLocalVersionOptions, VersionInfo } from "./types"
+import { formatVersionOutput, formatJsonOutput } from "./formatter"
+
+export async function getLocalVersion(options: GetLocalVersionOptions = {}): Promise<number> {
+  const directory = options.directory ?? process.cwd()
+  
+  try {
+    if (isLocalDevMode(directory)) {
+      const currentVersion = getCachedVersion()
+      const info: VersionInfo = {
+        currentVersion,
+        latestVersion: null,
+        isUpToDate: false,
+        isLocalDev: true,
+        isPinned: false,
+        pinnedVersion: null,
+        status: "local-dev",
+      }
+      
+      console.log(options.json ? formatJsonOutput(info) : formatVersionOutput(info))
+      return 0
+    }
+
+    const pluginInfo = findPluginEntry(directory)
+    if (pluginInfo?.isPinned) {
+      const info: VersionInfo = {
+        currentVersion: pluginInfo.pinnedVersion,
+        latestVersion: null,
+        isUpToDate: false,
+        isLocalDev: false,
+        isPinned: true,
+        pinnedVersion: pluginInfo.pinnedVersion,
+        status: "pinned",
+      }
+      
+      console.log(options.json ? formatJsonOutput(info) : formatVersionOutput(info))
+      return 0
+    }
+
+    const currentVersion = getCachedVersion()
+    if (!currentVersion) {
+      const info: VersionInfo = {
+        currentVersion: null,
+        latestVersion: null,
+        isUpToDate: false,
+        isLocalDev: false,
+        isPinned: false,
+        pinnedVersion: null,
+        status: "unknown",
+      }
+      
+      console.log(options.json ? formatJsonOutput(info) : formatVersionOutput(info))
+      return 1
+    }
+
+    const { extractChannel } = await import("../../hooks/auto-update-checker/index")
+    const channel = extractChannel(pluginInfo?.pinnedVersion ?? currentVersion)
+    const latestVersion = await getLatestVersion(channel)
+    
+    if (!latestVersion) {
+      const info: VersionInfo = {
+        currentVersion,
+        latestVersion: null,
+        isUpToDate: false,
+        isLocalDev: false,
+        isPinned: false,
+        pinnedVersion: null,
+        status: "error",
+      }
+      
+      console.log(options.json ? formatJsonOutput(info) : formatVersionOutput(info))
+      return 0
+    }
+
+    const isUpToDate = currentVersion === latestVersion
+    const info: VersionInfo = {
+      currentVersion,
+      latestVersion,
+      isUpToDate,
+      isLocalDev: false,
+      isPinned: false,
+      pinnedVersion: null,
+      status: isUpToDate ? "up-to-date" : "outdated",
+    }
+
+    console.log(options.json ? formatJsonOutput(info) : formatVersionOutput(info))
+    return 0
+
+  } catch (error) {
+    const info: VersionInfo = {
+      currentVersion: null,
+      latestVersion: null,
+      isUpToDate: false,
+      isLocalDev: false,
+      isPinned: false,
+      pinnedVersion: null,
+      status: "error",
+    }
+    
+    console.log(options.json ? formatJsonOutput(info) : formatVersionOutput(info))
+    return 1
+  }
+}
+
 export * from "./types"
--- a/src/cli/index.ts
+++ b/src/cli/index.ts
@@ -1,4 +1,190 @@
 #!/usr/bin/env bun
-import { runCli } from "./cli-program"
+import { Command } from "commander"
+import { install } from "./install"
+import { run } from "./run"
+import { getLocalVersion } from "./get-local-version"
+import { doctor } from "./doctor"
+import { createMcpOAuthCommand } from "./mcp-oauth"
+import type { InstallArgs } from "./types"
+import type { RunOptions } from "./run"
+import type { GetLocalVersionOptions } from "./get-local-version/types"
+import type { DoctorOptions } from "./doctor"
+import packageJson from "../../package.json" with { type: "json" }

-runCli()
+const VERSION = packageJson.version
+
+const program = new Command()
+
+program
+  .name("oh-my-opencode")
+  .description("The ultimate OpenCode plugin - multi-model orchestration, LSP tools, and more")
+  .version(VERSION, "-v, --version", "Show version number")
+  .enablePositionalOptions()
+
+program
+  .command("install")
+  .description("Install and configure oh-my-opencode with interactive setup")
+  .option("--no-tui", "Run in non-interactive mode (requires all options)")
+  .option("--claude <value>", "Claude subscription: no, yes, max20")
+  .option("--openai <value>", "OpenAI/ChatGPT subscription: no, yes (default: no)")
+  .option("--gemini <value>", "Gemini integration: no, yes")
+  .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:
+  $ bunx oh-my-opencode install
+  $ 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 > 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-4-6, 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 = {
+      tui: options.tui !== false,
+      claude: options.claude,
+      openai: options.openai,
+      gemini: options.gemini,
+      copilot: options.copilot,
+      opencodeZen: options.opencodeZen,
+      zaiCodingPlan: options.zaiCodingPlan,
+      kimiForCoding: options.kimiForCoding,
+      skipAuth: options.skipAuth ?? false,
+    }
+    const exitCode = await install(args)
+    process.exit(exitCode)
+  })
+
+program
+   .command("run <message>")
+   .allowUnknownOption()
+   .passThroughOptions()
+   .description("Run opencode with todo/background task completion enforcement")
+  .option("-a, --agent <name>", "Agent to use (default: from CLI/env/config, fallback: Sisyphus)")
+  .option("-d, --directory <path>", "Working directory")
+  .option("-t, --timeout <ms>", "Timeout in milliseconds (default: 30 minutes)", parseInt)
+  .option("-p, --port <port>", "Server port (attaches if port already in use)", parseInt)
+  .option("--attach <url>", "Attach to existing opencode server URL")
+  .option("--on-complete <command>", "Shell command to run after completion")
+  .option("--json", "Output structured JSON result to stdout")
+  .option("--session-id <id>", "Resume existing session instead of creating new one")
+  .addHelpText("after", `
+Examples:
+  $ bunx oh-my-opencode run "Fix the bug in index.ts"
+  $ bunx oh-my-opencode run --agent Sisyphus "Implement feature X"
+  $ bunx oh-my-opencode run --timeout 3600000 "Large refactoring task"
+  $ bunx oh-my-opencode run --port 4321 "Fix the bug"
+  $ bunx oh-my-opencode run --attach http://127.0.0.1:4321 "Fix the bug"
+  $ bunx oh-my-opencode run --json "Fix the bug" | jq .sessionId
+  $ bunx oh-my-opencode run --on-complete "notify-send Done" "Fix the bug"
+  $ bunx oh-my-opencode run --session-id ses_abc123 "Continue the work"
+
+Agent resolution order:
+  1) --agent flag
+  2) OPENCODE_DEFAULT_AGENT
+  3) oh-my-opencode.json "default_run_agent"
+  4) Sisyphus (fallback)
+
+Available core agents:
+  Sisyphus, Hephaestus, Prometheus, Atlas
+
+Unlike 'opencode run', this command waits until:
+  - All todos are completed or cancelled
+  - All child sessions (background tasks) are idle
+`)
+  .action(async (message: string, options) => {
+    if (options.port && options.attach) {
+      console.error("Error: --port and --attach are mutually exclusive")
+      process.exit(1)
+    }
+    const runOptions: RunOptions = {
+      message,
+      agent: options.agent,
+      directory: options.directory,
+      timeout: options.timeout,
+      port: options.port,
+      attach: options.attach,
+      onComplete: options.onComplete,
+      json: options.json ?? false,
+      sessionId: options.sessionId,
+    }
+    const exitCode = await run(runOptions)
+    process.exit(exitCode)
+  })
+
+program
+  .command("get-local-version")
+  .description("Show current installed version and check for updates")
+  .option("-d, --directory <path>", "Working directory to check config from")
+  .option("--json", "Output in JSON format for scripting")
+  .addHelpText("after", `
+Examples:
+  $ bunx oh-my-opencode get-local-version
+  $ bunx oh-my-opencode get-local-version --json
+  $ bunx oh-my-opencode get-local-version --directory /path/to/project
+
+This command shows:
+  - Current installed version
+  - Latest available version on npm
+  - Whether you're up to date
+  - Special modes (local dev, pinned version)
+`)
+  .action(async (options) => {
+    const versionOptions: GetLocalVersionOptions = {
+      directory: options.directory,
+      json: options.json ?? false,
+    }
+    const exitCode = await getLocalVersion(versionOptions)
+    process.exit(exitCode)
+  })
+
+program
+  .command("doctor")
+  .description("Check oh-my-opencode installation health and diagnose issues")
+  .option("--verbose", "Show detailed diagnostic information")
+  .option("--json", "Output results in JSON format")
+  .option("--category <category>", "Run only specific category")
+  .addHelpText("after", `
+Examples:
+  $ bunx oh-my-opencode doctor
+  $ bunx oh-my-opencode doctor --verbose
+  $ bunx oh-my-opencode doctor --json
+  $ bunx oh-my-opencode doctor --category authentication
+
+Categories:
+  installation     Check OpenCode and plugin installation
+  configuration    Validate configuration files
+  authentication   Check auth provider status
+  dependencies     Check external dependencies
+  tools            Check LSP and MCP servers
+  updates          Check for version updates
+`)
+  .action(async (options) => {
+    const doctorOptions: DoctorOptions = {
+      verbose: options.verbose ?? false,
+      json: options.json ?? false,
+      category: options.category,
+    }
+    const exitCode = await doctor(doctorOptions)
+    process.exit(exitCode)
+  })
+
+program
+  .command("version")
+  .description("Show version information")
+  .action(() => {
+    console.log(`oh-my-opencode v${VERSION}`)
+  })
+
+program.addCommand(createMcpOAuthCommand())
+
+program.parse()
--- a/src/cli/install-validators.ts
+++ b/src/cli/install-validators.ts
@@ -1,189 +0,0 @@
-import color from "picocolors"
-import type {
-  BooleanArg,
-  ClaudeSubscription,
-  DetectedConfig,
-  InstallArgs,
-  InstallConfig,
-} from "./types"
-
-export const SYMBOLS = {
-  check: color.green("[OK]"),
-  cross: color.red("[X]"),
-  arrow: color.cyan("->"),
-  bullet: color.dim("*"),
-  info: color.blue("[i]"),
-  warn: color.yellow("[!]"),
-  star: color.yellow("*"),
-}
-
-function formatProvider(name: string, enabled: boolean, detail?: string): string {
-  const status = enabled ? SYMBOLS.check : color.dim("○")
-  const label = enabled ? color.white(name) : color.dim(name)
-  const suffix = detail ? color.dim(` (${detail})`) : ""
-  return `  ${status} ${label}${suffix}`
-}
-
-export function formatConfigSummary(config: InstallConfig): string {
-  const lines: string[] = []
-
-  lines.push(color.bold(color.white("Configuration Summary")))
-  lines.push("")
-
-  const claudeDetail = config.hasClaude ? (config.isMax20 ? "max20" : "standard") : undefined
-  lines.push(formatProvider("Claude", config.hasClaude, claudeDetail))
-  lines.push(formatProvider("OpenAI/ChatGPT", config.hasOpenAI, "GPT-5.2 for Oracle"))
-  lines.push(formatProvider("Gemini", config.hasGemini))
-  lines.push(formatProvider("GitHub Copilot", config.hasCopilot, "fallback"))
-  lines.push(formatProvider("OpenCode Zen", config.hasOpencodeZen, "opencode/ models"))
-  lines.push(formatProvider("Z.ai Coding Plan", config.hasZaiCodingPlan, "Librarian/Multimodal"))
-  lines.push(formatProvider("Kimi For Coding", config.hasKimiForCoding, "Sisyphus/Prometheus fallback"))
-
-  lines.push("")
-  lines.push(color.dim("─".repeat(40)))
-  lines.push("")
-
-  lines.push(color.bold(color.white("Model Assignment")))
-  lines.push("")
-  lines.push(`  ${SYMBOLS.info} Models auto-configured based on provider priority`)
-  lines.push(`  ${SYMBOLS.bullet} Priority: Native > Copilot > OpenCode Zen > Z.ai`)
-
-  return lines.join("\n")
-}
-
-export function printHeader(isUpdate: boolean): void {
-  const mode = isUpdate ? "Update" : "Install"
-  console.log()
-  console.log(color.bgMagenta(color.white(` oMoMoMoMo... ${mode} `)))
-  console.log()
-}
-
-export function printStep(step: number, total: number, message: string): void {
-  const progress = color.dim(`[${step}/${total}]`)
-  console.log(`${progress} ${message}`)
-}
-
-export function printSuccess(message: string): void {
-  console.log(`${SYMBOLS.check} ${message}`)
-}
-
-export function printError(message: string): void {
-  console.log(`${SYMBOLS.cross} ${color.red(message)}`)
-}
-
-export function printInfo(message: string): void {
-  console.log(`${SYMBOLS.info} ${message}`)
-}
-
-export function printWarning(message: string): void {
-  console.log(`${SYMBOLS.warn} ${color.yellow(message)}`)
-}
-
-export function printBox(content: string, title?: string): void {
-  const lines = content.split("\n")
-  const maxWidth =
-    Math.max(
-      ...lines.map((line) => line.replace(/\x1b\[[0-9;]*m/g, "").length),
-      title?.length ?? 0,
-    ) + 4
-  const border = color.dim("─".repeat(maxWidth))
-
-  console.log()
-  if (title) {
-    console.log(
-      color.dim("┌─") +
-        color.bold(` ${title} `) +
-        color.dim("─".repeat(maxWidth - title.length - 4)) +
-        color.dim("┐"),
-    )
-  } else {
-    console.log(color.dim("┌") + border + color.dim("┐"))
-  }
-
-  for (const line of lines) {
-    const stripped = line.replace(/\x1b\[[0-9;]*m/g, "")
-    const padding = maxWidth - stripped.length
-    console.log(color.dim("│") + ` ${line}${" ".repeat(padding - 1)}` + color.dim("│"))
-  }
-
-  console.log(color.dim("└") + border + color.dim("┘"))
-  console.log()
-}
-
-export function validateNonTuiArgs(args: InstallArgs): { valid: boolean; errors: string[] } {
-  const errors: string[] = []
-
-  if (args.claude === undefined) {
-    errors.push("--claude is required (values: no, yes, max20)")
-  } else if (!["no", "yes", "max20"].includes(args.claude)) {
-    errors.push(`Invalid --claude value: ${args.claude} (expected: no, yes, max20)`)
-  }
-
-  if (args.gemini === undefined) {
-    errors.push("--gemini is required (values: no, yes)")
-  } else if (!["no", "yes"].includes(args.gemini)) {
-    errors.push(`Invalid --gemini value: ${args.gemini} (expected: no, yes)`)
-  }
-
-  if (args.copilot === undefined) {
-    errors.push("--copilot is required (values: no, yes)")
-  } else if (!["no", "yes"].includes(args.copilot)) {
-    errors.push(`Invalid --copilot value: ${args.copilot} (expected: no, yes)`)
-  }
-
-  if (args.openai !== undefined && !["no", "yes"].includes(args.openai)) {
-    errors.push(`Invalid --openai value: ${args.openai} (expected: no, yes)`)
-  }
-
-  if (args.opencodeZen !== undefined && !["no", "yes"].includes(args.opencodeZen)) {
-    errors.push(`Invalid --opencode-zen value: ${args.opencodeZen} (expected: no, yes)`)
-  }
-
-  if (args.zaiCodingPlan !== undefined && !["no", "yes"].includes(args.zaiCodingPlan)) {
-    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 }
-}
-
-export function argsToConfig(args: InstallArgs): InstallConfig {
-  return {
-    hasClaude: args.claude !== "no",
-    isMax20: args.claude === "max20",
-    hasOpenAI: args.openai === "yes",
-    hasGemini: args.gemini === "yes",
-    hasCopilot: args.copilot === "yes",
-    hasOpencodeZen: args.opencodeZen === "yes",
-    hasZaiCodingPlan: args.zaiCodingPlan === "yes",
-    hasKimiForCoding: args.kimiForCoding === "yes",
-  }
-}
-
-export 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"
-  }
-
-  return {
-    claude,
-    openai: detected.hasOpenAI ? "yes" : "no",
-    gemini: detected.hasGemini ? "yes" : "no",
-    copilot: detected.hasCopilot ? "yes" : "no",
-    opencodeZen: detected.hasOpencodeZen ? "yes" : "no",
-    zaiCodingPlan: detected.hasZaiCodingPlan ? "yes" : "no",
-    kimiForCoding: detected.hasKimiForCoding ? "yes" : "no",
-  }
-}
--- a/src/cli/install.ts
+++ b/src/cli/install.ts
@@ -1,10 +1,542 @@
+import * as p from "@clack/prompts"
+import color from "picocolors"
+import type { InstallArgs, InstallConfig, ClaudeSubscription, BooleanArg, DetectedConfig } from "./types"
+import {
+  addPluginToOpenCodeConfig,
+  writeOmoConfig,
+  isOpenCodeInstalled,
+  getOpenCodeVersion,
+  addAuthPlugins,
+  addProviderConfig,
+  detectCurrentConfig,
+} from "./config-manager"
+import { shouldShowChatGPTOnlyWarning } from "./model-fallback"
 import packageJson from "../../package.json" with { type: "json" }
-import type { InstallArgs } from "./types"
-import { runCliInstaller } from "./cli-installer"
-import { runTuiInstaller } from "./tui-installer"

 const VERSION = packageJson.version

-export async function install(args: InstallArgs): Promise<number> {
-  return args.tui ? runTuiInstaller(args, VERSION) : runCliInstaller(args, VERSION)
+const SYMBOLS = {
+  check: color.green("[OK]"),
+  cross: color.red("[X]"),
+  arrow: color.cyan("->"),
+  bullet: color.dim("*"),
+  info: color.blue("[i]"),
+  warn: color.yellow("[!]"),
+  star: color.yellow("*"),
+}
+
+function formatProvider(name: string, enabled: boolean, detail?: string): string {
+  const status = enabled ? SYMBOLS.check : color.dim("○")
+  const label = enabled ? color.white(name) : color.dim(name)
+  const suffix = detail ? color.dim(` (${detail})`) : ""
+  return `  ${status} ${label}${suffix}`
+}
+
+function formatConfigSummary(config: InstallConfig): string {
+  const lines: string[] = []
+
+  lines.push(color.bold(color.white("Configuration Summary")))
+  lines.push("")
+
+  const claudeDetail = config.hasClaude ? (config.isMax20 ? "max20" : "standard") : undefined
+  lines.push(formatProvider("Claude", config.hasClaude, claudeDetail))
+  lines.push(formatProvider("OpenAI/ChatGPT", config.hasOpenAI, "GPT-5.2 for Oracle"))
+  lines.push(formatProvider("Gemini", config.hasGemini))
+  lines.push(formatProvider("GitHub Copilot", config.hasCopilot, "fallback"))
+  lines.push(formatProvider("OpenCode Zen", config.hasOpencodeZen, "opencode/ models"))
+  lines.push(formatProvider("Z.ai Coding Plan", config.hasZaiCodingPlan, "Librarian/Multimodal"))
+  lines.push(formatProvider("Kimi For Coding", config.hasKimiForCoding, "Sisyphus/Prometheus fallback"))
+
+  lines.push("")
+  lines.push(color.dim("─".repeat(40)))
+  lines.push("")
+
+  lines.push(color.bold(color.white("Model Assignment")))
+  lines.push("")
+  lines.push(`  ${SYMBOLS.info} Models auto-configured based on provider priority`)
+  lines.push(`  ${SYMBOLS.bullet} Priority: Native > Copilot > OpenCode Zen > Z.ai`)
+
+  return lines.join("\n")
+}
+
+function printHeader(isUpdate: boolean): void {
+  const mode = isUpdate ? "Update" : "Install"
+  console.log()
+  console.log(color.bgMagenta(color.white(` oMoMoMoMo... ${mode} `)))
+  console.log()
+}
+
+function printStep(step: number, total: number, message: string): void {
+  const progress = color.dim(`[${step}/${total}]`)
+  console.log(`${progress} ${message}`)
+}
+
+function printSuccess(message: string): void {
+  console.log(`${SYMBOLS.check} ${message}`)
+}
+
+function printError(message: string): void {
+  console.log(`${SYMBOLS.cross} ${color.red(message)}`)
+}
+
+function printInfo(message: string): void {
+  console.log(`${SYMBOLS.info} ${message}`)
+}
+
+function printWarning(message: string): void {
+  console.log(`${SYMBOLS.warn} ${color.yellow(message)}`)
+}
+
+function printBox(content: string, title?: string): void {
+  const lines = content.split("\n")
+  const maxWidth = Math.max(...lines.map(l => l.replace(/\x1b\[[0-9;]*m/g, "").length), title?.length ?? 0) + 4
+  const border = color.dim("─".repeat(maxWidth))
+
+  console.log()
+  if (title) {
+    console.log(color.dim("┌─") + color.bold(` ${title} `) + color.dim("─".repeat(maxWidth - title.length - 4)) + color.dim("┐"))
+  } else {
+    console.log(color.dim("┌") + border + color.dim("┐"))
+  }
+
+  for (const line of lines) {
+    const stripped = line.replace(/\x1b\[[0-9;]*m/g, "")
+    const padding = maxWidth - stripped.length
+    console.log(color.dim("│") + ` ${line}${" ".repeat(padding - 1)}` + color.dim("│"))
+  }
+
+  console.log(color.dim("└") + border + color.dim("┘"))
+  console.log()
+}
+
+function validateNonTuiArgs(args: InstallArgs): { valid: boolean; errors: string[] } {
+  const errors: string[] = []
+
+  if (args.claude === undefined) {
+    errors.push("--claude is required (values: no, yes, max20)")
+  } else if (!["no", "yes", "max20"].includes(args.claude)) {
+    errors.push(`Invalid --claude value: ${args.claude} (expected: no, yes, max20)`)
+  }
+
+  if (args.gemini === undefined) {
+    errors.push("--gemini is required (values: no, yes)")
+  } else if (!["no", "yes"].includes(args.gemini)) {
+    errors.push(`Invalid --gemini value: ${args.gemini} (expected: no, yes)`)
+  }
+
+  if (args.copilot === undefined) {
+    errors.push("--copilot is required (values: no, yes)")
+  } else if (!["no", "yes"].includes(args.copilot)) {
+    errors.push(`Invalid --copilot value: ${args.copilot} (expected: no, yes)`)
+  }
+
+  if (args.openai !== undefined && !["no", "yes"].includes(args.openai)) {
+    errors.push(`Invalid --openai value: ${args.openai} (expected: no, yes)`)
+  }
+
+  if (args.opencodeZen !== undefined && !["no", "yes"].includes(args.opencodeZen)) {
+    errors.push(`Invalid --opencode-zen value: ${args.opencodeZen} (expected: no, yes)`)
+  }
+
+  if (args.zaiCodingPlan !== undefined && !["no", "yes"].includes(args.zaiCodingPlan)) {
+    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 }
+}
+
+function argsToConfig(args: InstallArgs): InstallConfig {
+  return {
+    hasClaude: args.claude !== "no",
+    isMax20: args.claude === "max20",
+    hasOpenAI: args.openai === "yes",
+    hasGemini: args.gemini === "yes",
+    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; kimiForCoding: BooleanArg } {
+  let claude: ClaudeSubscription = "no"
+  if (detected.hasClaude) {
+    claude = detected.isMax20 ? "max20" : "yes"
+  }
+
+  return {
+    claude,
+    openai: detected.hasOpenAI ? "yes" : "no",
+    gemini: detected.hasGemini ? "yes" : "no",
+    copilot: detected.hasCopilot ? "yes" : "no",
+    opencodeZen: detected.hasOpencodeZen ? "yes" : "no",
+    zaiCodingPlan: detected.hasZaiCodingPlan ? "yes" : "no",
+    kimiForCoding: detected.hasKimiForCoding ? "yes" : "no",
+  }
+}
+
+async function runTuiMode(detected: DetectedConfig): Promise<InstallConfig | null> {
+  const initial = detectedToInitialValues(detected)
+
+  const claude = await p.select({
+    message: "Do you have a Claude Pro/Max subscription?",
+    options: [
+      { value: "no" as const, label: "No", hint: "Will use opencode/glm-4.7-free as fallback" },
+      { value: "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" },
+    ],
+    initialValue: initial.claude,
+  })
+
+  if (p.isCancel(claude)) {
+    p.cancel("Installation cancelled.")
+    return null
+  }
+
+  const openai = await p.select({
+    message: "Do you have an OpenAI/ChatGPT Plus subscription?",
+    options: [
+      { value: "no" as const, label: "No", hint: "Oracle will use fallback models" },
+      { value: "yes" as const, label: "Yes", hint: "GPT-5.2 for Oracle (high-IQ debugging)" },
+    ],
+    initialValue: initial.openai,
+  })
+
+  if (p.isCancel(openai)) {
+    p.cancel("Installation cancelled.")
+    return null
+  }
+
+  const gemini = await p.select({
+    message: "Will you integrate Google Gemini?",
+    options: [
+      { value: "no" as const, label: "No", hint: "Frontend/docs agents will use fallback" },
+      { value: "yes" as const, label: "Yes", hint: "Beautiful UI generation with Gemini 3 Pro" },
+    ],
+    initialValue: initial.gemini,
+  })
+
+  if (p.isCancel(gemini)) {
+    p.cancel("Installation cancelled.")
+    return null
+  }
+
+  const copilot = await p.select({
+    message: "Do you have a GitHub Copilot subscription?",
+    options: [
+      { value: "no" as const, label: "No", hint: "Only native providers will be used" },
+      { value: "yes" as const, label: "Yes", hint: "Fallback option when native providers unavailable" },
+    ],
+    initialValue: initial.copilot,
+  })
+
+  if (p.isCancel(copilot)) {
+    p.cancel("Installation cancelled.")
+    return null
+  }
+
+  const opencodeZen = await p.select({
+    message: "Do you have access to OpenCode Zen (opencode/ models)?",
+    options: [
+      { value: "no" as const, label: "No", hint: "Will use other configured providers" },
+      { value: "yes" as const, label: "Yes", hint: "opencode/claude-opus-4-6, opencode/gpt-5.2, etc." },
+    ],
+    initialValue: initial.opencodeZen,
+  })
+
+  if (p.isCancel(opencodeZen)) {
+    p.cancel("Installation cancelled.")
+    return null
+  }
+
+  const zaiCodingPlan = await p.select({
+    message: "Do you have a Z.ai Coding Plan subscription?",
+    options: [
+      { value: "no" as const, label: "No", hint: "Will use other configured providers" },
+      { value: "yes" as const, label: "Yes", hint: "Fallback for Librarian and Multimodal Looker" },
+    ],
+    initialValue: initial.zaiCodingPlan,
+  })
+
+  if (p.isCancel(zaiCodingPlan)) {
+    p.cancel("Installation cancelled.")
+    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",
+    hasOpenAI: openai === "yes",
+    hasGemini: gemini === "yes",
+    hasCopilot: copilot === "yes",
+    hasOpencodeZen: opencodeZen === "yes",
+    hasZaiCodingPlan: zaiCodingPlan === "yes",
+    hasKimiForCoding: kimiForCoding === "yes",
+  }
+}
+
+async function runNonTuiInstall(args: InstallArgs): Promise<number> {
+  const validation = validateNonTuiArgs(args)
+  if (!validation.valid) {
+    printHeader(false)
+    printError("Validation failed:")
+    for (const err of validation.errors) {
+      console.log(`  ${SYMBOLS.bullet} ${err}`)
+    }
+    console.log()
+    printInfo("Usage: bunx oh-my-opencode install --no-tui --claude=<no|yes|max20> --gemini=<no|yes> --copilot=<no|yes>")
+    console.log()
+    return 1
+  }
+
+  const detected = detectCurrentConfig()
+  const isUpdate = detected.isInstalled
+
+  printHeader(isUpdate)
+
+  const totalSteps = 6
+  let step = 1
+
+  printStep(step++, totalSteps, "Checking OpenCode installation...")
+  const installed = await isOpenCodeInstalled()
+  const version = await getOpenCodeVersion()
+  if (!installed) {
+    printWarning("OpenCode binary not found. Plugin will be configured, but you'll need to install OpenCode to use it.")
+    printInfo("Visit https://opencode.ai/docs for installation instructions")
+  } else {
+    printSuccess(`OpenCode ${version ?? ""} detected`)
+  }
+
+  if (isUpdate) {
+    const initial = detectedToInitialValues(detected)
+    printInfo(`Current config: Claude=${initial.claude}, Gemini=${initial.gemini}`)
+  }
+
+  const config = argsToConfig(args)
+
+  printStep(step++, totalSteps, "Adding oh-my-opencode plugin...")
+  const pluginResult = await addPluginToOpenCodeConfig(VERSION)
+  if (!pluginResult.success) {
+    printError(`Failed: ${pluginResult.error}`)
+    return 1
+  }
+  printSuccess(`Plugin ${isUpdate ? "verified" : "added"} ${SYMBOLS.arrow} ${color.dim(pluginResult.configPath)}`)
+
+  if (config.hasGemini) {
+    printStep(step++, totalSteps, "Adding auth plugins...")
+    const authResult = await addAuthPlugins(config)
+    if (!authResult.success) {
+      printError(`Failed: ${authResult.error}`)
+      return 1
+    }
+    printSuccess(`Auth plugins configured ${SYMBOLS.arrow} ${color.dim(authResult.configPath)}`)
+
+    printStep(step++, totalSteps, "Adding provider configurations...")
+    const providerResult = addProviderConfig(config)
+    if (!providerResult.success) {
+      printError(`Failed: ${providerResult.error}`)
+      return 1
+    }
+    printSuccess(`Providers configured ${SYMBOLS.arrow} ${color.dim(providerResult.configPath)}`)
+  } else {
+    step += 2
+  }
+
+  printStep(step++, totalSteps, "Writing oh-my-opencode configuration...")
+  const omoResult = writeOmoConfig(config)
+  if (!omoResult.success) {
+    printError(`Failed: ${omoResult.error}`)
+    return 1
+  }
+  printSuccess(`Config written ${SYMBOLS.arrow} ${color.dim(omoResult.configPath)}`)
+
+  printBox(formatConfigSummary(config), isUpdate ? "Updated Configuration" : "Installation Complete")
+
+  if (!config.hasClaude) {
+    console.log()
+    console.log(color.bgRed(color.white(color.bold(" CRITICAL WARNING "))))
+    console.log()
+    console.log(color.red(color.bold("  Sisyphus agent is STRONGLY optimized for Claude Opus 4.5.")))
+    console.log(color.red("  Without Claude, you may experience significantly degraded performance:"))
+    console.log(color.dim("    • Reduced orchestration quality"))
+    console.log(color.dim("    • Weaker tool selection and delegation"))
+    console.log(color.dim("    • Less reliable task completion"))
+    console.log()
+    console.log(color.yellow("  Consider subscribing to Claude Pro/Max for the best experience."))
+    console.log()
+  }
+
+  if (!config.hasClaude && !config.hasOpenAI && !config.hasGemini && !config.hasCopilot && !config.hasOpencodeZen) {
+    printWarning("No model providers configured. Using opencode/glm-4.7-free as fallback.")
+  }
+
+  console.log(`${SYMBOLS.star} ${color.bold(color.green(isUpdate ? "Configuration updated!" : "Installation complete!"))}`)
+  console.log(`  Run ${color.cyan("opencode")} to start!`)
+  console.log()
+
+  printBox(
+    `${color.bold("Pro Tip:")} Include ${color.cyan("ultrawork")} (or ${color.cyan("ulw")}) in your prompt.\n` +
+    `All features work like magic—parallel agents, background tasks,\n` +
+    `deep exploration, and relentless execution until completion.`,
+    "The Magic Word"
+  )
+
+  console.log(`${SYMBOLS.star} ${color.yellow("If you found this helpful, consider starring the repo!")}`)
+  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()
+
+  if ((config.hasClaude || config.hasGemini || config.hasCopilot) && !args.skipAuth) {
+    printBox(
+      `Run ${color.cyan("opencode auth login")} and select your provider:\n` +
+      (config.hasClaude ? `  ${SYMBOLS.bullet} Anthropic ${color.gray("→ Claude Pro/Max")}\n` : "") +
+      (config.hasGemini ? `  ${SYMBOLS.bullet} Google ${color.gray("→ OAuth with Antigravity")}\n` : "") +
+      (config.hasCopilot ? `  ${SYMBOLS.bullet} GitHub ${color.gray("→ Copilot")}` : ""),
+      "Authenticate Your Providers"
+    )
+  }
+
+  return 0
+}
+
+export async function install(args: InstallArgs): Promise<number> {
+  if (!args.tui) {
+    return runNonTuiInstall(args)
+  }
+
+  const detected = detectCurrentConfig()
+  const isUpdate = detected.isInstalled
+
+  p.intro(color.bgMagenta(color.white(isUpdate ? " oMoMoMoMo... Update " : " oMoMoMoMo... ")))
+
+  if (isUpdate) {
+    const initial = detectedToInitialValues(detected)
+    p.log.info(`Existing configuration detected: Claude=${initial.claude}, Gemini=${initial.gemini}`)
+  }
+
+  const s = p.spinner()
+  s.start("Checking OpenCode installation")
+
+  const installed = await isOpenCodeInstalled()
+  const version = await getOpenCodeVersion()
+  if (!installed) {
+    s.stop(`OpenCode binary not found ${color.yellow("[!]")}`)
+    p.log.warn("OpenCode binary not found. Plugin will be configured, but you'll need to install OpenCode to use it.")
+    p.note("Visit https://opencode.ai/docs for installation instructions", "Installation Guide")
+  } else {
+    s.stop(`OpenCode ${version ?? "installed"} ${color.green("[OK]")}`)
+  }
+
+  const config = await runTuiMode(detected)
+  if (!config) return 1
+
+  s.start("Adding oh-my-opencode to OpenCode config")
+  const pluginResult = await addPluginToOpenCodeConfig(VERSION)
+  if (!pluginResult.success) {
+    s.stop(`Failed to add plugin: ${pluginResult.error}`)
+    p.outro(color.red("Installation failed."))
+    return 1
+  }
+  s.stop(`Plugin added to ${color.cyan(pluginResult.configPath)}`)
+
+  if (config.hasGemini) {
+    s.start("Adding auth plugins (fetching latest versions)")
+    const authResult = await addAuthPlugins(config)
+    if (!authResult.success) {
+      s.stop(`Failed to add auth plugins: ${authResult.error}`)
+      p.outro(color.red("Installation failed."))
+      return 1
+    }
+    s.stop(`Auth plugins added to ${color.cyan(authResult.configPath)}`)
+
+    s.start("Adding provider configurations")
+    const providerResult = addProviderConfig(config)
+    if (!providerResult.success) {
+      s.stop(`Failed to add provider config: ${providerResult.error}`)
+      p.outro(color.red("Installation failed."))
+      return 1
+    }
+    s.stop(`Provider config added to ${color.cyan(providerResult.configPath)}`)
+  }
+
+  s.start("Writing oh-my-opencode configuration")
+  const omoResult = writeOmoConfig(config)
+  if (!omoResult.success) {
+    s.stop(`Failed to write config: ${omoResult.error}`)
+    p.outro(color.red("Installation failed."))
+    return 1
+  }
+  s.stop(`Config written to ${color.cyan(omoResult.configPath)}`)
+
+  if (!config.hasClaude) {
+    console.log()
+    console.log(color.bgRed(color.white(color.bold(" CRITICAL WARNING "))))
+    console.log()
+    console.log(color.red(color.bold("  Sisyphus agent is STRONGLY optimized for Claude Opus 4.5.")))
+    console.log(color.red("  Without Claude, you may experience significantly degraded performance:"))
+    console.log(color.dim("    • Reduced orchestration quality"))
+    console.log(color.dim("    • Weaker tool selection and delegation"))
+    console.log(color.dim("    • Less reliable task completion"))
+    console.log()
+    console.log(color.yellow("  Consider subscribing to Claude Pro/Max for the best experience."))
+    console.log()
+  }
+
+  if (!config.hasClaude && !config.hasOpenAI && !config.hasGemini && !config.hasCopilot && !config.hasOpencodeZen) {
+    p.log.warn("No model providers configured. Using opencode/glm-4.7-free as fallback.")
+  }
+
+  p.note(formatConfigSummary(config), isUpdate ? "Updated Configuration" : "Installation Complete")
+
+  p.log.success(color.bold(isUpdate ? "Configuration updated!" : "Installation complete!"))
+  p.log.message(`Run ${color.cyan("opencode")} to start!`)
+
+  p.note(
+    `Include ${color.cyan("ultrawork")} (or ${color.cyan("ulw")}) in your prompt.\n` +
+    `All features work like magic—parallel agents, background tasks,\n` +
+    `deep exploration, and relentless execution until completion.`,
+    "The Magic Word"
+  )
+
+  p.log.message(`${color.yellow("★")} If you found this helpful, consider starring the repo!`)
+  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!"))
+
+  if ((config.hasClaude || config.hasGemini || config.hasCopilot) && !args.skipAuth) {
+    const providers: string[] = []
+    if (config.hasClaude) providers.push(`Anthropic ${color.gray("→ Claude Pro/Max")}`)
+    if (config.hasGemini) providers.push(`Google ${color.gray("→ OAuth with Antigravity")}`)
+    if (config.hasCopilot) providers.push(`GitHub ${color.gray("→ Copilot")}`)
+
+    console.log()
+    console.log(color.bold("Authenticate Your Providers"))
+    console.log()
+    console.log(`   Run ${color.cyan("opencode auth login")} and select:`)
+    for (const provider of providers) {
+      console.log(`   ${SYMBOLS.bullet} ${provider}`)
+    }
+    console.log()
+  }
+
+  return 0
 }
--- a/src/cli/model-fallback-types.ts
+++ b/src/cli/model-fallback-types.ts
@@ -1,29 +0,0 @@
-export interface ProviderAvailability {
-	native: {
-		claude: boolean
-		openai: boolean
-		gemini: boolean
-	}
-	opencodeZen: boolean
-	copilot: boolean
-	zai: boolean
-	kimiForCoding: boolean
-	isMaxPlan: boolean
-}
-
-export interface AgentConfig {
-	model: string
-	variant?: string
-}
-
-export interface CategoryConfig {
-	model: string
-	variant?: string
-}
-
-export interface GeneratedOmoConfig {
-	$schema: string
-	agents?: Record<string, AgentConfig>
-	categories?: Record<string, CategoryConfig>
-	[key: string]: unknown
-}
--- a/src/cli/model-fallback.ts
+++ b/src/cli/model-fallback.ts
@@ -1,27 +1,133 @@
 import {
-	AGENT_MODEL_REQUIREMENTS,
-	CATEGORY_MODEL_REQUIREMENTS,
+  AGENT_MODEL_REQUIREMENTS,
+  CATEGORY_MODEL_REQUIREMENTS,
+  type FallbackEntry,
 } from "../shared/model-requirements"
 import type { InstallConfig } from "./types"

-import type { AgentConfig, CategoryConfig, GeneratedOmoConfig } from "./model-fallback-types"
-import { toProviderAvailability } from "./provider-availability"
-import {
-	getSisyphusFallbackChain,
-	isAnyFallbackEntryAvailable,
-	isRequiredModelAvailable,
-	isRequiredProviderAvailable,
-	resolveModelFromChain,
-} from "./fallback-chain-resolution"
+interface ProviderAvailability {
+  native: {
+    claude: boolean
+    openai: boolean
+    gemini: boolean
+  }
+  opencodeZen: boolean
+  copilot: boolean
+  zai: boolean
+  kimiForCoding: boolean
+  isMaxPlan: boolean
+}

-export type { GeneratedOmoConfig } from "./model-fallback-types"
+interface AgentConfig {
+  model: string
+  variant?: string
+}
+
+interface CategoryConfig {
+  model: string
+  variant?: string
+}
+
+export interface GeneratedOmoConfig {
+  $schema: string
+  agents?: Record<string, AgentConfig>
+  categories?: Record<string, CategoryConfig>
+  [key: string]: unknown
+}

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

 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 {
+  return {
+    native: {
+      claude: config.hasClaude,
+      openai: config.hasOpenAI,
+      gemini: config.hasGemini,
+    },
+    opencodeZen: config.hasOpencodeZen,
+    copilot: config.hasCopilot,
+    zai: config.hasZaiCodingPlan,
+    kimiForCoding: config.hasKimiForCoding,
+    isMaxPlan: config.isMax20,
+  }
+}

+function isProviderAvailable(provider: string, avail: ProviderAvailability): boolean {
+  const mapping: Record<string, boolean> = {
+    anthropic: avail.native.claude,
+    openai: avail.native.openai,
+    google: avail.native.gemini,
+    "github-copilot": avail.copilot,
+    opencode: avail.opencodeZen,
+    "zai-coding-plan": avail.zai,
+    "kimi-for-coding": avail.kimiForCoding,
+  }
+  return mapping[provider] ?? false
+}
+
+function transformModelForProvider(provider: string, model: string): string {
+  if (provider === "github-copilot") {
+    return model
+      .replace("claude-opus-4-6", "claude-opus-4.6")
+      .replace("claude-sonnet-4-5", "claude-sonnet-4.5")
+      .replace("claude-haiku-4-5", "claude-haiku-4.5")
+      .replace("claude-sonnet-4", "claude-sonnet-4")
+      .replace("gemini-3-pro", "gemini-3-pro-preview")
+      .replace("gemini-3-flash", "gemini-3-flash-preview")
+  }
+  return model
+}
+
+function resolveModelFromChain(
+  fallbackChain: FallbackEntry[],
+  avail: ProviderAvailability
+): { model: string; variant?: string } | null {
+  for (const entry of fallbackChain) {
+    for (const provider of entry.providers) {
+      if (isProviderAvailable(provider, avail)) {
+        const transformedModel = transformModelForProvider(provider, entry.model)
+        return {
+          model: `${provider}/${transformedModel}`,
+          variant: entry.variant,
+        }
+      }
+    }
+  }
+  return null
+}
+
+function getSisyphusFallbackChain(): FallbackEntry[] {
+  return AGENT_MODEL_REQUIREMENTS.sisyphus.fallbackChain
+}
+
+function isAnyFallbackEntryAvailable(
+  fallbackChain: FallbackEntry[],
+  avail: ProviderAvailability
+): boolean {
+  return fallbackChain.some((entry) =>
+    entry.providers.some((provider) => isProviderAvailable(provider, avail))
+  )
+}
+
+function isRequiredModelAvailable(
+  requiresModel: string,
+  fallbackChain: FallbackEntry[],
+  avail: ProviderAvailability
+): boolean {
+  const matchingEntry = fallbackChain.find((entry) => entry.model === requiresModel)
+  if (!matchingEntry) return false
+  return matchingEntry.providers.some((provider) => isProviderAvailable(provider, avail))
+}
+
+function isRequiredProviderAvailable(
+  requiredProviders: string[],
+  avail: ProviderAvailability
+): boolean {
+  return requiredProviders.some((provider) => isProviderAvailable(provider, avail))
+}

 export function generateModelConfig(config: InstallConfig): GeneratedOmoConfig {
  const avail = toProviderAvailability(config)
--- a/src/cli/provider-availability.ts
+++ b/src/cli/provider-availability.ts
@@ -1,30 +0,0 @@
-import type { InstallConfig } from "./types"
-import type { ProviderAvailability } from "./model-fallback-types"
-
-export function toProviderAvailability(config: InstallConfig): ProviderAvailability {
-	return {
-		native: {
-			claude: config.hasClaude,
-			openai: config.hasOpenAI,
-			gemini: config.hasGemini,
-		},
-		opencodeZen: config.hasOpencodeZen,
-		copilot: config.hasCopilot,
-		zai: config.hasZaiCodingPlan,
-		kimiForCoding: config.hasKimiForCoding,
-		isMaxPlan: config.isMax20,
-	}
-}
-
-export function isProviderAvailable(provider: string, availability: ProviderAvailability): boolean {
-	const mapping: Record<string, boolean> = {
-		anthropic: availability.native.claude,
-		openai: availability.native.openai,
-		google: availability.native.gemini,
-		"github-copilot": availability.copilot,
-		opencode: availability.opencodeZen,
-		"zai-coding-plan": availability.zai,
-		"kimi-for-coding": availability.kimiForCoding,
-	}
-	return mapping[provider] ?? false
-}
--- a/src/cli/provider-model-id-transform.ts
+++ b/src/cli/provider-model-id-transform.ts
@@ -1,12 +0,0 @@
-export function transformModelForProvider(provider: string, model: string): string {
-	if (provider === "github-copilot") {
-		return model
-			.replace("claude-opus-4-6", "claude-opus-4.6")
-			.replace("claude-sonnet-4-5", "claude-sonnet-4.5")
-			.replace("claude-haiku-4-5", "claude-haiku-4.5")
-			.replace("claude-sonnet-4", "claude-sonnet-4")
-			.replace("gemini-3-pro", "gemini-3-pro-preview")
-			.replace("gemini-3-flash", "gemini-3-flash-preview")
-	}
-	return model
-}
--- a/src/cli/run/event-formatting.ts
+++ b/src/cli/run/event-formatting.ts
@@ -1,140 +0,0 @@
-import pc from "picocolors"
-import type {
-  RunContext,
-  EventPayload,
-  MessageUpdatedProps,
-  MessagePartUpdatedProps,
-  ToolExecuteProps,
-  ToolResultProps,
-  SessionErrorProps,
-} from "./types"
-
-export function serializeError(error: unknown): string {
-  if (!error) return "Unknown error"
-
-  if (error instanceof Error) {
-    const parts = [error.message]
-    if (error.cause) {
-      parts.push(`Cause: ${serializeError(error.cause)}`)
-    }
-    return parts.join(" | ")
-  }
-
-  if (typeof error === "string") {
-    return error
-  }
-
-  if (typeof error === "object") {
-    const obj = error as Record<string, unknown>
-
-    const messagePaths = [
-      obj.message,
-      obj.error,
-      (obj.data as Record<string, unknown>)?.message,
-      (obj.data as Record<string, unknown>)?.error,
-      (obj.error as Record<string, unknown>)?.message,
-    ]
-
-    for (const msg of messagePaths) {
-      if (typeof msg === "string" && msg.length > 0) {
-        return msg
-      }
-    }
-
-    try {
-      const json = JSON.stringify(error, null, 2)
-      if (json !== "{}") {
-        return json
-      }
-    } catch (_) {
-      void _
-    }
-  }
-
-  return String(error)
-}
-
-function getSessionTag(ctx: RunContext, payload: EventPayload): string {
-  const props = payload.properties as Record<string, unknown> | undefined
-  const info = props?.info as Record<string, unknown> | undefined
-  const sessionID = props?.sessionID ?? info?.sessionID
-  const isMainSession = sessionID === ctx.sessionID
-  if (isMainSession) return pc.green("[MAIN]")
-  if (sessionID) return pc.yellow(`[${String(sessionID).slice(0, 8)}]`)
-  return pc.dim("[system]")
-}
-
-export function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
-  const sessionTag = getSessionTag(ctx, payload)
-  const props = payload.properties as Record<string, unknown> | undefined
-
-  switch (payload.type) {
-    case "session.idle":
-    case "session.status": {
-      const status = (props?.status as { type?: string })?.type ?? "idle"
-      console.error(pc.dim(`${sessionTag} ${payload.type}: ${status}`))
-      break
-    }
-
-    case "message.part.updated": {
-      const partProps = props as MessagePartUpdatedProps | undefined
-      const part = partProps?.part
-      if (part?.type === "tool-invocation") {
-        const toolPart = part as { toolName?: string; state?: string }
-        console.error(pc.dim(`${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}${part.text.length > 80 ? "..." : ""}"`))
-      }
-      break
-    }
-
-    case "message.updated": {
-      const msgProps = props as MessageUpdatedProps | undefined
-      const role = msgProps?.info?.role ?? "unknown"
-      const model = msgProps?.info?.modelID
-      const agent = msgProps?.info?.agent
-      const details = [role, agent, model].filter(Boolean).join(", ")
-      console.error(pc.dim(`${sessionTag} message.updated (${details})`))
-      break
-    }
-
-    case "tool.execute": {
-      const toolProps = props as ToolExecuteProps | undefined
-      const toolName = toolProps?.name ?? "unknown"
-      const input = toolProps?.input ?? {}
-      let inputStr: string
-      try {
-        inputStr = JSON.stringify(input)
-      } catch {
-        try {
-          inputStr = String(input)
-        } catch {
-          inputStr = "[unserializable]"
-        }
-      }
-      const inputPreview = inputStr.slice(0, 150)
-      console.error(pc.cyan(`${sessionTag} TOOL.EXECUTE: ${pc.bold(toolName)}`))
-      console.error(pc.dim(`   input: ${inputPreview}${inputStr.length >= 150 ? "..." : ""}`))
-      break
-    }
-
-    case "tool.result": {
-      const resultProps = props as ToolResultProps | undefined
-      const output = resultProps?.output ?? ""
-      const preview = output.slice(0, 200).replace(/\n/g, "\\n")
-      console.error(pc.green(`${sessionTag} TOOL.RESULT: "${preview}${output.length > 200 ? "..." : ""}"`))
-      break
-    }
-
-    case "session.error": {
-      const errorProps = props as SessionErrorProps | undefined
-      const errorMsg = serializeError(errorProps?.error)
-      console.error(pc.red(`${sessionTag} SESSION.ERROR: ${errorMsg}`))
-      break
-    }
-
-    default:
-      console.error(pc.dim(`${sessionTag} ${payload.type}`))
-  }
-}
--- a/src/cli/run/event-handlers.test.ts
+++ b/src/cli/run/event-handlers.test.ts
@@ -1,73 +0,0 @@
-import { describe, it, expect } from "bun:test"
-import type { RunContext } from "./types"
-import { createEventState } from "./events"
-import { handleSessionStatus } from "./event-handlers"
-
-const createMockContext = (sessionID: string = "test-session"): RunContext => ({
-  sessionID,
-} as RunContext)
-
-describe("handleSessionStatus", () => {
-  it("recognizes idle from session.status event (not just deprecated session.idle)", () => {
-    //#given - state with mainSessionIdle=false
-    const ctx = createMockContext("test-session")
-    const state = createEventState()
-    state.mainSessionIdle = false
-
-    const payload = {
-      type: "session.status",
-      properties: {
-        sessionID: "test-session",
-        status: { type: "idle" as const },
-      },
-    }
-
-    //#when - handleSessionStatus called with idle status
-    handleSessionStatus(ctx, payload as any, state)
-
-    //#then - state.mainSessionIdle === true
-    expect(state.mainSessionIdle).toBe(true)
-  })
-
-  it("handleSessionStatus sets idle=false on busy", () => {
-    //#given - state with mainSessionIdle=true
-    const ctx = createMockContext("test-session")
-    const state = createEventState()
-    state.mainSessionIdle = true
-
-    const payload = {
-      type: "session.status",
-      properties: {
-        sessionID: "test-session",
-        status: { type: "busy" as const },
-      },
-    }
-
-    //#when - handleSessionStatus called with busy status
-    handleSessionStatus(ctx, payload as any, state)
-
-    //#then - state.mainSessionIdle === false
-    expect(state.mainSessionIdle).toBe(false)
-  })
-
-  it("does nothing for different session ID", () => {
-    //#given - state with mainSessionIdle=true
-    const ctx = createMockContext("test-session")
-    const state = createEventState()
-    state.mainSessionIdle = true
-
-    const payload = {
-      type: "session.status",
-      properties: {
-        sessionID: "other-session",
-        status: { type: "idle" as const },
-      },
-    }
-
-    //#when - handleSessionStatus called with different session ID
-    handleSessionStatus(ctx, payload as any, state)
-
-    //#then - state.mainSessionIdle remains unchanged
-    expect(state.mainSessionIdle).toBe(true)
-  })
-})
--- a/src/cli/run/event-handlers.ts
+++ b/src/cli/run/event-handlers.ts
@@ -1,127 +0,0 @@
-import pc from "picocolors"
-import type {
-  RunContext,
-  EventPayload,
-  SessionIdleProps,
-  SessionStatusProps,
-  SessionErrorProps,
-  MessageUpdatedProps,
-  MessagePartUpdatedProps,
-  ToolExecuteProps,
-  ToolResultProps,
-} from "./types"
-import type { EventState } from "./event-state"
-import { serializeError } from "./event-formatting"
-
-export function handleSessionIdle(ctx: RunContext, payload: EventPayload, state: EventState): void {
-  if (payload.type !== "session.idle") return
-
-  const props = payload.properties as SessionIdleProps | undefined
-  if (props?.sessionID === ctx.sessionID) {
-    state.mainSessionIdle = true
-  }
-}
-
-export function handleSessionStatus(ctx: RunContext, payload: EventPayload, state: EventState): void {
-  if (payload.type !== "session.status") return
-
-  const props = payload.properties as SessionStatusProps | undefined
-  if (props?.sessionID !== ctx.sessionID) return
-
-  if (props?.status?.type === "busy") {
-    state.mainSessionIdle = false
-  } else if (props?.status?.type === "idle") {
-    state.mainSessionIdle = true
-  } else if (props?.status?.type === "retry") {
-    state.mainSessionIdle = false
-  }
-}
-
-export function handleSessionError(ctx: RunContext, payload: EventPayload, state: EventState): void {
-  if (payload.type !== "session.error") return
-
-  const props = payload.properties as SessionErrorProps | undefined
-  if (props?.sessionID === ctx.sessionID) {
-    state.mainSessionError = true
-    state.lastError = serializeError(props?.error)
-    console.error(pc.red(`\n[session.error] ${state.lastError}`))
-  }
-}
-
-export function handleMessagePartUpdated(ctx: RunContext, payload: EventPayload, state: EventState): void {
-  if (payload.type !== "message.part.updated") return
-
-  const props = payload.properties as MessagePartUpdatedProps | undefined
-  if (props?.info?.sessionID !== ctx.sessionID) return
-  if (props?.info?.role !== "assistant") return
-
-  const part = props.part
-  if (!part) return
-
-  if (part.type === "text" && part.text) {
-    const newText = part.text.slice(state.lastPartText.length)
-    if (newText) {
-      process.stdout.write(newText)
-      state.hasReceivedMeaningfulWork = true
-    }
-    state.lastPartText = part.text
-  }
-}
-
-export function handleMessageUpdated(ctx: RunContext, payload: EventPayload, state: EventState): void {
-  if (payload.type !== "message.updated") return
-
-  const props = payload.properties as MessageUpdatedProps | undefined
-  if (props?.info?.sessionID !== ctx.sessionID) return
-  if (props?.info?.role !== "assistant") return
-
-  state.hasReceivedMeaningfulWork = true
-  state.messageCount++
-  state.lastPartText = ""
-}
-
-export function handleToolExecute(ctx: RunContext, payload: EventPayload, state: EventState): void {
-  if (payload.type !== "tool.execute") return
-
-  const props = payload.properties as ToolExecuteProps | undefined
-  if (props?.sessionID !== ctx.sessionID) return
-
-  const toolName = props?.name || "unknown"
-  state.currentTool = toolName
-
-  let inputPreview = ""
-  if (props?.input) {
-    const input = props.input
-    if (input.command) {
-      inputPreview = ` ${pc.dim(String(input.command).slice(0, 60))}`
-    } else if (input.pattern) {
-      inputPreview = ` ${pc.dim(String(input.pattern).slice(0, 40))}`
-    } else if (input.filePath) {
-      inputPreview = ` ${pc.dim(String(input.filePath))}`
-    } else if (input.query) {
-      inputPreview = ` ${pc.dim(String(input.query).slice(0, 40))}`
-    }
-  }
-
-  state.hasReceivedMeaningfulWork = true
-  process.stdout.write(`\n${pc.cyan(">")} ${pc.bold(toolName)}${inputPreview}\n`)
-}
-
-export function handleToolResult(ctx: RunContext, payload: EventPayload, state: EventState): void {
-  if (payload.type !== "tool.result") return
-
-  const props = payload.properties as ToolResultProps | undefined
-  if (props?.sessionID !== ctx.sessionID) return
-
-  const output = props?.output || ""
-  const maxLen = 200
-  const preview = output.length > maxLen ? output.slice(0, maxLen) + "..." : output
-
-  if (preview.trim()) {
-    const lines = preview.split("\n").slice(0, 3)
-    process.stdout.write(pc.dim(`   └─ ${lines.join("\n      ")}\n`))
-  }
-
-  state.currentTool = null
-  state.lastPartText = ""
-}
--- a/src/cli/run/event-state.ts
+++ b/src/cli/run/event-state.ts
@@ -1,25 +0,0 @@
-export interface EventState {
-  mainSessionIdle: boolean
-  mainSessionError: boolean
-  lastError: string | null
-  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
-  /** Count of assistant messages for the main session */
-  messageCount: number
-}
-
-export function createEventState(): EventState {
-  return {
-    mainSessionIdle: false,
-    mainSessionError: false,
-    lastError: null,
-    lastOutput: "",
-    lastPartText: "",
-    currentTool: null,
-    hasReceivedMeaningfulWork: false,
-    messageCount: 0,
-  }
-}
--- a/src/cli/run/event-stream-processor.ts
+++ b/src/cli/run/event-stream-processor.ts
@@ -1,43 +0,0 @@
-import pc from "picocolors"
-import type { RunContext, EventPayload } from "./types"
-import type { EventState } from "./event-state"
-import { logEventVerbose } from "./event-formatting"
-import {
-  handleSessionError,
-  handleSessionIdle,
-  handleSessionStatus,
-  handleMessagePartUpdated,
-  handleMessageUpdated,
-  handleToolExecute,
-  handleToolResult,
-} from "./event-handlers"
-
-export async function processEvents(
-  ctx: RunContext,
-  stream: AsyncIterable<unknown>,
-  state: EventState
-): Promise<void> {
-  for await (const event of stream) {
-    if (ctx.abortController.signal.aborted) break
-
-    try {
-      const payload = event as EventPayload
-      if (!payload?.type) {
-        console.error(pc.dim(`[event] no type: ${JSON.stringify(event)}`))
-        continue
-      }
-
-      logEventVerbose(ctx, payload)
-
-      handleSessionError(ctx, payload, state)
-      handleSessionIdle(ctx, payload, state)
-      handleSessionStatus(ctx, payload, state)
-      handleMessagePartUpdated(ctx, payload, state)
-      handleMessageUpdated(ctx, payload, state)
-      handleToolExecute(ctx, payload, state)
-      handleToolResult(ctx, payload, state)
-    } catch (err) {
-      console.error(pc.red(`[event error] ${err}`))
-    }
-  }
-}
--- a/src/cli/run/events.ts
+++ b/src/cli/run/events.ts
@@ -1,4 +1,329 @@
-export type { EventState } from "./event-state"
-export { createEventState } from "./event-state"
-export { serializeError } from "./event-formatting"
-export { processEvents } from "./event-stream-processor"
+import pc from "picocolors"
+import type {
+  RunContext,
+  EventPayload,
+  SessionIdleProps,
+  SessionStatusProps,
+  SessionErrorProps,
+  MessageUpdatedProps,
+  MessagePartUpdatedProps,
+  ToolExecuteProps,
+  ToolResultProps,
+} from "./types"
+
+export function serializeError(error: unknown): string {
+  if (!error) return "Unknown error"
+
+  if (error instanceof Error) {
+    const parts = [error.message]
+    if (error.cause) {
+      parts.push(`Cause: ${serializeError(error.cause)}`)
+    }
+    return parts.join(" | ")
+  }
+
+  if (typeof error === "string") {
+    return error
+  }
+
+  if (typeof error === "object") {
+    const obj = error as Record<string, unknown>
+
+    const messagePaths = [
+      obj.message,
+      obj.error,
+      (obj.data as Record<string, unknown>)?.message,
+      (obj.data as Record<string, unknown>)?.error,
+      (obj.error as Record<string, unknown>)?.message,
+    ]
+
+    for (const msg of messagePaths) {
+      if (typeof msg === "string" && msg.length > 0) {
+        return msg
+      }
+    }
+
+    try {
+      const json = JSON.stringify(error, null, 2)
+      if (json !== "{}") {
+        return json
+      }
+    } catch (_) {
+      void _
+    }
+  }
+
+  return String(error)
+}
+
+export interface EventState {
+  mainSessionIdle: boolean
+  mainSessionError: boolean
+  lastError: string | null
+  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
+  /** Count of assistant messages for the main session */
+  messageCount: number
+}
+
+export function createEventState(): EventState {
+  return {
+    mainSessionIdle: false,
+    mainSessionError: false,
+    lastError: null,
+    lastOutput: "",
+    lastPartText: "",
+    currentTool: null,
+    hasReceivedMeaningfulWork: false,
+    messageCount: 0,
+  }
+}
+
+export async function processEvents(
+  ctx: RunContext,
+  stream: AsyncIterable<unknown>,
+  state: EventState
+): Promise<void> {
+  for await (const event of stream) {
+    if (ctx.abortController.signal.aborted) break
+
+    try {
+      const payload = event as EventPayload
+      if (!payload?.type) {
+        console.error(pc.dim(`[event] no type: ${JSON.stringify(event)}`))
+        continue
+      }
+
+      logEventVerbose(ctx, payload)
+
+      handleSessionError(ctx, payload, state)
+      handleSessionIdle(ctx, payload, state)
+      handleSessionStatus(ctx, payload, state)
+      handleMessagePartUpdated(ctx, payload, state)
+      handleMessageUpdated(ctx, payload, state)
+      handleToolExecute(ctx, payload, state)
+      handleToolResult(ctx, payload, state)
+    } catch (err) {
+      console.error(pc.red(`[event error] ${err}`))
+    }
+  }
+}
+
+function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
+  const props = payload.properties as Record<string, unknown> | undefined
+  const info = props?.info as Record<string, unknown> | undefined
+  const sessionID = props?.sessionID ?? info?.sessionID
+  const isMainSession = sessionID === ctx.sessionID
+  const sessionTag = isMainSession
+    ? pc.green("[MAIN]")
+    : sessionID
+      ? pc.yellow(`[${String(sessionID).slice(0, 8)}]`)
+      : pc.dim("[system]")
+
+  switch (payload.type) {
+    case "session.idle":
+    case "session.status": {
+      const status = (props?.status as { type?: string })?.type ?? "idle"
+      console.error(pc.dim(`${sessionTag} ${payload.type}: ${status}`))
+      break
+    }
+
+    case "message.part.updated": {
+      const partProps = props as MessagePartUpdatedProps | undefined
+      const part = partProps?.part
+      if (part?.type === "tool-invocation") {
+        const toolPart = part as { toolName?: string; state?: string }
+        console.error(
+          pc.dim(`${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}${part.text.length > 80 ? "..." : ""}"`)
+        )
+      }
+      break
+    }
+
+    case "message.updated": {
+      const msgProps = props as MessageUpdatedProps | undefined
+      const role = msgProps?.info?.role ?? "unknown"
+      const model = msgProps?.info?.modelID
+      const agent = msgProps?.info?.agent
+      const details = [role, agent, model].filter(Boolean).join(", ")
+      console.error(pc.dim(`${sessionTag} message.updated (${details})`))
+      break
+    }
+
+    case "tool.execute": {
+      const toolProps = props as ToolExecuteProps | undefined
+      const toolName = toolProps?.name ?? "unknown"
+      const input = toolProps?.input ?? {}
+      const inputStr = JSON.stringify(input).slice(0, 150)
+      console.error(
+        pc.cyan(`${sessionTag} TOOL.EXECUTE: ${pc.bold(toolName)}`)
+      )
+      console.error(pc.dim(`   input: ${inputStr}${inputStr.length >= 150 ? "..." : ""}`))
+      break
+    }
+
+    case "tool.result": {
+      const resultProps = props as ToolResultProps | undefined
+      const output = resultProps?.output ?? ""
+      const preview = output.slice(0, 200).replace(/\n/g, "\\n")
+      console.error(
+        pc.green(`${sessionTag} TOOL.RESULT: "${preview}${output.length > 200 ? "..." : ""}"`)
+      )
+      break
+    }
+
+    case "session.error": {
+      const errorProps = props as SessionErrorProps | undefined
+      const errorMsg = serializeError(errorProps?.error)
+      console.error(pc.red(`${sessionTag} SESSION.ERROR: ${errorMsg}`))
+      break
+    }
+
+    default:
+      console.error(pc.dim(`${sessionTag} ${payload.type}`))
+  }
+}
+
+function handleSessionIdle(
+  ctx: RunContext,
+  payload: EventPayload,
+  state: EventState
+): void {
+  if (payload.type !== "session.idle") return
+
+  const props = payload.properties as SessionIdleProps | undefined
+  if (props?.sessionID === ctx.sessionID) {
+    state.mainSessionIdle = true
+  }
+}
+
+function handleSessionStatus(
+  ctx: RunContext,
+  payload: EventPayload,
+  state: EventState
+): void {
+  if (payload.type !== "session.status") return
+
+  const props = payload.properties as SessionStatusProps | undefined
+  if (props?.sessionID === ctx.sessionID && props?.status?.type === "busy") {
+    state.mainSessionIdle = false
+  }
+}
+
+function handleSessionError(
+  ctx: RunContext,
+  payload: EventPayload,
+  state: EventState
+): void {
+  if (payload.type !== "session.error") return
+
+  const props = payload.properties as SessionErrorProps | undefined
+  if (props?.sessionID === ctx.sessionID) {
+    state.mainSessionError = true
+    state.lastError = serializeError(props?.error)
+    console.error(pc.red(`\n[session.error] ${state.lastError}`))
+  }
+}
+
+function handleMessagePartUpdated(
+  ctx: RunContext,
+  payload: EventPayload,
+  state: EventState
+): void {
+  if (payload.type !== "message.part.updated") return
+
+  const props = payload.properties as MessagePartUpdatedProps | undefined
+  if (props?.info?.sessionID !== ctx.sessionID) return
+  if (props?.info?.role !== "assistant") return
+
+  const part = props.part
+  if (!part) return
+
+  if (part.type === "text" && part.text) {
+    const newText = part.text.slice(state.lastPartText.length)
+    if (newText) {
+      process.stdout.write(newText)
+      state.hasReceivedMeaningfulWork = true
+    }
+    state.lastPartText = part.text
+  }
+}
+
+function handleMessageUpdated(
+  ctx: RunContext,
+  payload: EventPayload,
+  state: EventState
+): void {
+  if (payload.type !== "message.updated") return
+
+  const props = payload.properties as MessageUpdatedProps | undefined
+  if (props?.info?.sessionID !== ctx.sessionID) return
+  if (props?.info?.role !== "assistant") return
+
+  state.hasReceivedMeaningfulWork = true
+  state.messageCount++
+}
+
+function handleToolExecute(
+  ctx: RunContext,
+  payload: EventPayload,
+  state: EventState
+): void {
+  if (payload.type !== "tool.execute") return
+
+  const props = payload.properties as ToolExecuteProps | undefined
+  if (props?.sessionID !== ctx.sessionID) return
+
+  const toolName = props?.name || "unknown"
+  state.currentTool = toolName
+
+  let inputPreview = ""
+  if (props?.input) {
+    const input = props.input
+    if (input.command) {
+      inputPreview = ` ${pc.dim(String(input.command).slice(0, 60))}`
+    } else if (input.pattern) {
+      inputPreview = ` ${pc.dim(String(input.pattern).slice(0, 40))}`
+    } else if (input.filePath) {
+      inputPreview = ` ${pc.dim(String(input.filePath))}`
+    } else if (input.query) {
+      inputPreview = ` ${pc.dim(String(input.query).slice(0, 40))}`
+    }
+  }
+
+  state.hasReceivedMeaningfulWork = true
+  process.stdout.write(`\n${pc.cyan(">")} ${pc.bold(toolName)}${inputPreview}\n`)
+}
+
+function handleToolResult(
+  ctx: RunContext,
+  payload: EventPayload,
+  state: EventState
+): void {
+  if (payload.type !== "tool.result") return
+
+  const props = payload.properties as ToolResultProps | undefined
+  if (props?.sessionID !== ctx.sessionID) return
+
+  const output = props?.output || ""
+  const maxLen = 200
+  const preview = output.length > maxLen 
+    ? output.slice(0, maxLen) + "..." 
+    : output
+  
+  if (preview.trim()) {
+    const lines = preview.split("\n").slice(0, 3)
+    process.stdout.write(pc.dim(`   └─ ${lines.join("\n      ")}\n`))
+  }
+
+  state.currentTool = null
+  state.lastPartText = ""
+}
--- a/src/cli/run/index.ts
+++ b/src/cli/run/index.ts
@@ -4,6 +4,4 @@ export { createServerConnection } from "./server-connection"
 export { resolveSession } from "./session-resolver"
 export { createJsonOutputManager } from "./json-output"
 export { executeOnCompleteHook } from "./on-complete-hook"
-export { createEventState, processEvents, serializeError } from "./events"
-export type { EventState } from "./events"
 export type { RunOptions, RunContext, RunResult, ServerConnection } from "./types"
--- a/src/cli/run/poll-for-completion.test.ts
+++ b/src/cli/run/poll-for-completion.test.ts
@@ -1,292 +0,0 @@
-import { describe, it, expect, mock, spyOn } from "bun:test"
-import type { RunContext, Todo, ChildSession, SessionStatus } from "./types"
-import { createEventState } from "./events"
-import { pollForCompletion } from "./poll-for-completion"
-
-const createMockContext = (overrides: {
-  todo?: Todo[]
-  childrenBySession?: Record<string, ChildSession[]>
-  statuses?: Record<string, SessionStatus>
-} = {}): RunContext => {
-  const {
-    todo = [],
-    childrenBySession = { "test-session": [] },
-    statuses = {},
-  } = overrides
-
-  return {
-    client: {
-      session: {
-        todo: mock(() => Promise.resolve({ data: todo })),
-        children: mock((opts: { path: { id: string } }) =>
-          Promise.resolve({ data: childrenBySession[opts.path.id] ?? [] })
-        ),
-        status: mock(() => Promise.resolve({ data: statuses })),
-      },
-    } as unknown as RunContext["client"],
-    sessionID: "test-session",
-    directory: "/test",
-    abortController: new AbortController(),
-  }
-}
-
-describe("pollForCompletion", () => {
-  it("requires consecutive stability checks before exiting - not immediate", async () => {
-    //#given - 0 todos, 0 children, session idle, meaningful work done
-    spyOn(console, "log").mockImplementation(() => {})
-    spyOn(console, "error").mockImplementation(() => {})
-    const ctx = createMockContext()
-    const eventState = createEventState()
-    eventState.mainSessionIdle = true
-    eventState.hasReceivedMeaningfulWork = true
-    const abortController = new AbortController()
-
-    //#when
-    const result = await pollForCompletion(ctx, eventState, abortController, {
-      pollIntervalMs: 10,
-      requiredConsecutive: 3,
-      minStabilizationMs: 0,
-    })
-
-    //#then - exits with 0 but only after 3 consecutive checks
-    expect(result).toBe(0)
-    const todoCallCount = (ctx.client.session.todo as ReturnType<typeof mock>).mock.calls.length
-    expect(todoCallCount).toBeGreaterThanOrEqual(3)
-  })
-
-  it("does not check completion during stabilization period after first meaningful work", async () => {
-    //#given - 0 todos, 0 children, session idle, meaningful work done, short stabilization
-    spyOn(console, "log").mockImplementation(() => {})
-    spyOn(console, "error").mockImplementation(() => {})
-    const ctx = createMockContext()
-    const eventState = createEventState()
-    eventState.mainSessionIdle = true
-    eventState.hasReceivedMeaningfulWork = true
-    const abortController = new AbortController()
-
-    //#when - abort before stabilization period ends
-    setTimeout(() => abortController.abort(), 50)
-    const result = await pollForCompletion(ctx, eventState, abortController, {
-      pollIntervalMs: 10,
-      requiredConsecutive: 3,
-      minStabilizationMs: 200,
-    })
-
-    //#then - should be aborted (130) because stabilization hadn't elapsed yet
-    expect(result).toBe(130)
-    const todoCallCount = (ctx.client.session.todo as ReturnType<typeof mock>).mock.calls.length
-    expect(todoCallCount).toBe(0)
-  })
-
-  it("does not exit when currentTool is set - resets consecutive counter", async () => {
-    //#given
-    spyOn(console, "log").mockImplementation(() => {})
-    spyOn(console, "error").mockImplementation(() => {})
-    const ctx = createMockContext()
-    const eventState = createEventState()
-    eventState.mainSessionIdle = true
-    eventState.hasReceivedMeaningfulWork = true
-    eventState.currentTool = "task"
-    const abortController = new AbortController()
-
-    //#when - abort after enough time to verify it didn't exit
-    setTimeout(() => abortController.abort(), 100)
-    const result = await pollForCompletion(ctx, eventState, abortController, {
-      pollIntervalMs: 10,
-      requiredConsecutive: 3,
-    })
-
-    //#then - should be aborted, not completed (tool blocked exit)
-    expect(result).toBe(130)
-    const todoCallCount = (ctx.client.session.todo as ReturnType<typeof mock>).mock.calls.length
-    expect(todoCallCount).toBe(0)
-  })
-
-  it("resets consecutive counter when session becomes busy between checks", async () => {
-    //#given
-    spyOn(console, "log").mockImplementation(() => {})
-    spyOn(console, "error").mockImplementation(() => {})
-    const ctx = createMockContext()
-    const eventState = createEventState()
-    eventState.mainSessionIdle = true
-    eventState.hasReceivedMeaningfulWork = true
-    const abortController = new AbortController()
-    let todoCallCount = 0
-    let busyInserted = false
-
-    ;(ctx.client.session as any).todo = mock(async () => {
-      todoCallCount++
-      if (todoCallCount === 1 && !busyInserted) {
-        busyInserted = true
-        eventState.mainSessionIdle = false
-        setTimeout(() => { eventState.mainSessionIdle = true }, 15)
-      }
-      return { data: [] }
-    })
-    ;(ctx.client.session as any).children = mock(() =>
-      Promise.resolve({ data: [] })
-    )
-    ;(ctx.client.session as any).status = mock(() =>
-      Promise.resolve({ data: {} })
-    )
-
-    //#when
-    const startMs = Date.now()
-    const result = await pollForCompletion(ctx, eventState, abortController, {
-      pollIntervalMs: 10,
-      requiredConsecutive: 3,
-      minStabilizationMs: 0,
-    })
-    const elapsedMs = Date.now() - startMs
-
-    //#then - took longer than 3 polls because busy interrupted the streak
-    expect(result).toBe(0)
-    expect(elapsedMs).toBeGreaterThan(30)
-  })
-
-  it("returns 1 on session error", async () => {
-    //#given
-    spyOn(console, "log").mockImplementation(() => {})
-    spyOn(console, "error").mockImplementation(() => {})
-    const ctx = createMockContext()
-    const eventState = createEventState()
-    eventState.mainSessionIdle = true
-    eventState.mainSessionError = true
-    eventState.lastError = "Test error"
-    const abortController = new AbortController()
-
-    //#when
-    const result = await pollForCompletion(ctx, eventState, abortController, {
-      pollIntervalMs: 10,
-      requiredConsecutive: 3,
-    })
-
-    //#then
-    expect(result).toBe(1)
-  })
-
-  it("returns 130 when aborted", async () => {
-    //#given
-    spyOn(console, "log").mockImplementation(() => {})
-    spyOn(console, "error").mockImplementation(() => {})
-    const ctx = createMockContext()
-    const eventState = createEventState()
-    const abortController = new AbortController()
-
-    //#when
-    setTimeout(() => abortController.abort(), 50)
-    const result = await pollForCompletion(ctx, eventState, abortController, {
-      pollIntervalMs: 10,
-      requiredConsecutive: 3,
-    })
-
-    //#then
-    expect(result).toBe(130)
-  })
-
-  it("does not check completion when hasReceivedMeaningfulWork is false", async () => {
-    //#given
-    spyOn(console, "log").mockImplementation(() => {})
-    spyOn(console, "error").mockImplementation(() => {})
-    const ctx = createMockContext()
-    const eventState = createEventState()
-    eventState.mainSessionIdle = true
-    eventState.hasReceivedMeaningfulWork = false
-    const abortController = new AbortController()
-
-    //#when
-    setTimeout(() => abortController.abort(), 100)
-    const result = await pollForCompletion(ctx, eventState, abortController, {
-      pollIntervalMs: 10,
-      requiredConsecutive: 3,
-    })
-
-    //#then
-    expect(result).toBe(130)
-    const todoCallCount = (ctx.client.session.todo as ReturnType<typeof mock>).mock.calls.length
-    expect(todoCallCount).toBe(0)
-  })
-
-  it("simulates race condition: brief idle with 0 todos does not cause immediate exit", async () => {
-    //#given - simulate Sisyphus outputting text, session goes idle briefly, then tool fires
-    spyOn(console, "log").mockImplementation(() => {})
-    spyOn(console, "error").mockImplementation(() => {})
-    const ctx = createMockContext()
-    const eventState = createEventState()
-    eventState.mainSessionIdle = true
-    eventState.hasReceivedMeaningfulWork = true
-    const abortController = new AbortController()
-    let pollTick = 0
-
-    ;(ctx.client.session as any).todo = mock(async () => {
-      pollTick++
-      if (pollTick === 2) {
-        eventState.currentTool = "task"
-      }
-      return { data: [] }
-    })
-    ;(ctx.client.session as any).children = mock(() =>
-      Promise.resolve({ data: [] })
-    )
-    ;(ctx.client.session as any).status = mock(() =>
-      Promise.resolve({ data: {} })
-    )
-
-    //#when - abort after tool stays in-flight
-    setTimeout(() => abortController.abort(), 200)
-    const result = await pollForCompletion(ctx, eventState, abortController, {
-      pollIntervalMs: 10,
-      requiredConsecutive: 3,
-    })
-
-    //#then - should NOT have exited with 0 (tool blocked it, then aborted)
-    expect(result).toBe(130)
-  })
-
-  it("returns 1 when session errors while not idle (error not masked by idle gate)", async () => {
-    //#given - mainSessionIdle=false, mainSessionError=true, lastError="crash"
-    spyOn(console, "log").mockImplementation(() => {})
-    spyOn(console, "error").mockImplementation(() => {})
-    const ctx = createMockContext()
-    const eventState = createEventState()
-    eventState.mainSessionIdle = false
-    eventState.mainSessionError = true
-    eventState.lastError = "crash"
-    eventState.hasReceivedMeaningfulWork = true
-    const abortController = new AbortController()
-
-    //#when - pollForCompletion runs
-    const result = await pollForCompletion(ctx, eventState, abortController, {
-      pollIntervalMs: 10,
-      requiredConsecutive: 3,
-    })
-
-    //#then - returns 1 (not 130/timeout), error message printed
-    expect(result).toBe(1)
-    const errorCalls = (console.error as ReturnType<typeof mock>).mock.calls
-    expect(errorCalls.some((call) => call[0]?.includes("Session ended with error"))).toBe(true)
-  })
-
-  it("returns 1 when session errors while tool is active (error not masked by tool gate)", async () => {
-    //#given - mainSessionIdle=true, currentTool="bash", mainSessionError=true
-    spyOn(console, "log").mockImplementation(() => {})
-    spyOn(console, "error").mockImplementation(() => {})
-    const ctx = createMockContext()
-    const eventState = createEventState()
-    eventState.mainSessionIdle = true
-    eventState.currentTool = "bash"
-    eventState.mainSessionError = true
-    eventState.lastError = "error during tool"
-    eventState.hasReceivedMeaningfulWork = true
-    const abortController = new AbortController()
-
-    //#when
-    const result = await pollForCompletion(ctx, eventState, abortController, {
-      pollIntervalMs: 10,
-      requiredConsecutive: 3,
-    })
-
-    //#then - returns 1
-    expect(result).toBe(1)
-  })
-})
--- a/src/cli/run/poll-for-completion.ts
+++ b/src/cli/run/poll-for-completion.ts
@@ -1,96 +0,0 @@
-import pc from "picocolors"
-import type { RunContext } from "./types"
-import type { EventState } from "./events"
-import { checkCompletionConditions } from "./completion"
-
-const DEFAULT_POLL_INTERVAL_MS = 500
-const DEFAULT_REQUIRED_CONSECUTIVE = 3
-const ERROR_GRACE_CYCLES = 3
-const MIN_STABILIZATION_MS = 10_000
-
-export interface PollOptions {
-  pollIntervalMs?: number
-  requiredConsecutive?: number
-  minStabilizationMs?: number
-}
-
-export async function pollForCompletion(
-  ctx: RunContext,
-  eventState: EventState,
-  abortController: AbortController,
-  options: PollOptions = {}
-): Promise<number> {
-  const pollIntervalMs = options.pollIntervalMs ?? DEFAULT_POLL_INTERVAL_MS
-  const requiredConsecutive =
-    options.requiredConsecutive ?? DEFAULT_REQUIRED_CONSECUTIVE
-  const minStabilizationMs =
-    options.minStabilizationMs ?? MIN_STABILIZATION_MS
-  let consecutiveCompleteChecks = 0
-  let errorCycleCount = 0
-  let firstWorkTimestamp: number | null = null
-
-  while (!abortController.signal.aborted) {
-    await new Promise((resolve) => setTimeout(resolve, pollIntervalMs))
-
-    // ERROR CHECK FIRST — errors must not be masked by other gates
-    if (eventState.mainSessionError) {
-      errorCycleCount++
-      if (errorCycleCount >= ERROR_GRACE_CYCLES) {
-        console.error(
-          pc.red(`\n\nSession ended with error: ${eventState.lastError}`)
-        )
-        console.error(
-          pc.yellow("Check if todos were completed before the error.")
-        )
-        return 1
-      }
-      // Continue polling during grace period to allow recovery
-      continue
-    } else {
-      // Reset error counter when error clears (recovery succeeded)
-      errorCycleCount = 0
-    }
-
-    if (!eventState.mainSessionIdle) {
-      consecutiveCompleteChecks = 0
-      continue
-    }
-
-    if (eventState.currentTool !== null) {
-      consecutiveCompleteChecks = 0
-      continue
-    }
-
-    if (!eventState.hasReceivedMeaningfulWork) {
-      consecutiveCompleteChecks = 0
-      continue
-    }
-
-    // Track when first meaningful work was received
-    if (firstWorkTimestamp === null) {
-      firstWorkTimestamp = Date.now()
-    }
-
-    // Don't check completion until stabilization period has elapsed.
-    // Agents need time to set up todos and spawn child sessions after
-    // their first output. Without this, empty todos + no children
-    // triggers a false "all complete" within ~1.5s of starting.
-    if (Date.now() - firstWorkTimestamp < minStabilizationMs) {
-      consecutiveCompleteChecks = 0
-      continue
-    }
-
-    const shouldExit = await checkCompletionConditions(ctx)
-    if (shouldExit) {
-      consecutiveCompleteChecks++
-      if (consecutiveCompleteChecks >= requiredConsecutive) {
-        console.log(pc.green("\n\nAll tasks completed."))
-        return 0
-      }
-    } else {
-      consecutiveCompleteChecks = 0
-    }
-  }
-
-  return 130
-}
--- a/Show More
+++ b/Show More