release: v3.2.4

Fix category-skill-reminder to prioritize user-installed skills

AGENTS.md

@@ -1,7 +1,7 @@
 # PROJECT KNOWLEDGE BASE
 
-**Generated:** 2026-02-03T16:10:30+09:00
-**Commit:** d7679e14
+**Generated:** 2026-02-06T18:30:00+09:00
+**Commit:** c6c149e
 **Branch:** dev
 
 ---
@@ -120,40 +120,45 @@ This is an **international open-source project**. To ensure accessibility and ma
 
 ## OVERVIEW
 
-OpenCode plugin: multi-model agent orchestration (Claude Opus 4.5, GPT-5.2, Gemini 3 Flash). 34 lifecycle hooks, 20+ tools (LSP, AST-Grep, delegation), 11 specialized agents, full Claude Code compatibility. "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/         # 34 lifecycle hooks - see src/hooks/AGENTS.md
-│   ├── tools/         # 20+ tools - see src/tools/AGENTS.md
-│   ├── features/      # Background agents, Claude Code compat - see src/features/AGENTS.md
-│   ├── shared/        # 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, TypeScript types
-│   └── index.ts       # Main plugin entry (788 lines)
-├── script/            # build-schema.ts, build-binaries.ts
-├── packages/          # 11 platform-specific binaries
-└── dist/              # Build output (ESM + .d.ts)
+│   ├── 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 501 lines)
+│   ├── index.ts          # Main plugin entry (924 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` |
+| 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 index.ts |
+| Add MCP | `src/mcp/` | Create config, add to `createBuiltinMcps()` |
 | Add skill | `src/features/builtin-skills/` | Create dir with SKILL.md |
 | Add command | `src/features/builtin-commands/` | Add template + register in commands.ts |
 | Config schema | `src/config/schema.ts` | Zod schema, run `bun run build:schema` |
-| Background agents | `src/features/background-agent/` | manager.ts (1418 lines) |
-| Orchestrator | `src/hooks/atlas/` | Main orchestration hook (757 lines) |
+| Plugin config | `src/plugin-handlers/config-handler.ts` | JSONC loading, merging, migration |
+| 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)
 
@@ -165,7 +170,7 @@ oh-my-opencode/
 **Rules:**
 - NEVER write implementation before test
 - NEVER delete failing tests - fix the code
-- Test file: `*.test.ts` alongside source (100 test files)
+- Test file: `*.test.ts` alongside source (100+ test files)
 - BDD comments: `//#given`, `//#when`, `//#then`
 
 ## CONVENTIONS
@@ -175,7 +180,7 @@ oh-my-opencode/
 - **Build**: `bun build` (ESM) + `tsc --emitDeclarationOnly`
 - **Exports**: Barrel pattern via index.ts
 - **Naming**: kebab-case dirs, `createXXXHook`/`createXXXTool` factories
-- **Testing**: BDD comments, 100 test files
+- **Testing**: BDD comments, 100+ test files
 - **Temperature**: 0.1 for code agents, max 0.3
 
 ## ANTI-PATTERNS
@@ -204,14 +209,17 @@ oh-my-opencode/
 
 | Agent | Model | Purpose |
 |-------|-------|---------|
-| Sisyphus | anthropic/claude-opus-4-5 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro) |
-| Hephaestus | openai/gpt-5.2-codex | Autonomous deep worker, "The Legitimate Craftsman" (requires gpt-5.2-codex, no fallback) |
+| 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-4-5 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
+| 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
 
@@ -219,7 +227,7 @@ oh-my-opencode/
 bun run typecheck      # Type check
 bun run build          # ESM + declarations + schema
 bun run rebuild        # Clean + Build
-bun test               # 100 test files
+bun test               # 100+ test files
 ```
 
 ## DEPLOYMENT
@@ -233,30 +241,38 @@ bun test               # 100 test files
 
 | File | Lines | Description |
 |------|-------|-------------|
-| `src/features/builtin-skills/skills.ts` | 1729 | Skill definitions |
-| `src/features/background-agent/manager.ts` | 1418 | Task lifecycle, concurrency |
-| `src/agents/prometheus-prompt.ts` | 1283 | Planning agent prompt |
-| `src/tools/delegate-task/tools.ts` | 1135 | Category-based delegation |
-| `src/hooks/atlas/index.ts` | 757 | Orchestrator hook |
-| `src/index.ts` | 788 | Main plugin entry |
+| `src/features/background-agent/manager.ts` | 1556 | Task lifecycle, concurrency |
+| `src/features/builtin-skills/skills/git-master.ts` | 1107 | Git master skill definition |
+| `src/tools/delegate-task/executor.ts` | 983 | Category-based delegation executor |
+| `src/index.ts` | 924 | Main plugin entry |
+| `src/tools/lsp/client.ts` | 803 | LSP client operations |
+| `src/hooks/atlas/index.ts` | 770 | Orchestrator hook |
+| `src/tools/background-task/tools.ts` | 734 | Background task tools |
 | `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/tools/delegate-task/constants.ts` | 552 | Delegation constants |
+| `src/cli/install.ts` | 542 | Interactive CLI installer |
+| `src/agents/sisyphus.ts` | 530 | Main orchestrator agent |
 
 ## MCP ARCHITECTURE
 
 Three-tier system:
-1. **Built-in**: websearch (Exa), context7 (docs), grep_app (GitHub)
+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**: `src/config/schema.ts`
+- **Zod validation**: `src/config/schema.ts` (455 lines)
 - **JSONC support**: Comments, trailing commas
 - **Multi-level**: Project (`.opencode/`) → User (`~/.config/opencode/`)
+- **Loading**: `src/plugin-handlers/config-handler.ts` → merge → validate
 
 ## NOTES
 
 - **OpenCode**: Requires >= 1.0.150
 - **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

bun.lock

@@ -1,6 +1,6 @@
 {
   "lockfileVersion": 1,
-  "configVersion": 1,
+  "configVersion": 0,
   "workspaces": {
     "": {
       "name": "oh-my-opencode",
@@ -28,13 +28,13 @@
         "typescript": "^5.7.3",
       },
       "optionalDependencies": {
-        "oh-my-opencode-darwin-arm64": "3.2.2",
-        "oh-my-opencode-darwin-x64": "3.2.2",
-        "oh-my-opencode-linux-arm64": "3.2.2",
-        "oh-my-opencode-linux-arm64-musl": "3.2.2",
-        "oh-my-opencode-linux-x64": "3.2.2",
-        "oh-my-opencode-linux-x64-musl": "3.2.2",
-        "oh-my-opencode-windows-x64": "3.2.2",
+        "oh-my-opencode-darwin-arm64": "3.2.3",
+        "oh-my-opencode-darwin-x64": "3.2.3",
+        "oh-my-opencode-linux-arm64": "3.2.3",
+        "oh-my-opencode-linux-arm64-musl": "3.2.3",
+        "oh-my-opencode-linux-x64": "3.2.3",
+        "oh-my-opencode-linux-x64-musl": "3.2.3",
+        "oh-my-opencode-windows-x64": "3.2.3",
       },
     },
   },
@@ -44,41 +44,41 @@
     "@code-yeongyu/comment-checker",
   ],
   "packages": {
-    "@ast-grep/cli": ["@ast-grep/cli@0.40.5", "", { "dependencies": { "detect-libc": "2.1.2" }, "optionalDependencies": { "@ast-grep/cli-darwin-arm64": "0.40.5", "@ast-grep/cli-darwin-x64": "0.40.5", "@ast-grep/cli-linux-arm64-gnu": "0.40.5", "@ast-grep/cli-linux-x64-gnu": "0.40.5", "@ast-grep/cli-win32-arm64-msvc": "0.40.5", "@ast-grep/cli-win32-ia32-msvc": "0.40.5", "@ast-grep/cli-win32-x64-msvc": "0.40.5" }, "bin": { "sg": "sg", "ast-grep": "ast-grep" } }, "sha512-yVXL7Gz0WIHerQLf+MVaVSkhIhidtWReG5akNVr/JS9OVCVkSdz7gWm7H8jVv2M9OO1tauuG76K3UaRGBPu5lQ=="],
+    "@ast-grep/cli": ["@ast-grep/cli@0.40.0", "", { "dependencies": { "detect-libc": "2.1.2" }, "optionalDependencies": { "@ast-grep/cli-darwin-arm64": "0.40.0", "@ast-grep/cli-darwin-x64": "0.40.0", "@ast-grep/cli-linux-arm64-gnu": "0.40.0", "@ast-grep/cli-linux-x64-gnu": "0.40.0", "@ast-grep/cli-win32-arm64-msvc": "0.40.0", "@ast-grep/cli-win32-ia32-msvc": "0.40.0", "@ast-grep/cli-win32-x64-msvc": "0.40.0" }, "bin": { "sg": "sg", "ast-grep": "ast-grep" } }, "sha512-L8AkflsfI2ZP70yIdrwqvjR02ScCuRmM/qNGnJWUkOFck+e6gafNVJ4e4jjGQlEul+dNdBpx36+O2Op629t47A=="],
 
-    "@ast-grep/cli-darwin-arm64": ["@ast-grep/cli-darwin-arm64@0.40.5", "", { "os": "darwin", "cpu": "arm64" }, "sha512-T9CzwJ1GqQhnANdsu6c7iT1akpvTVMK+AZrxnhIPv33Ze5hrXUUkqan+j4wUAukRJDqU7u94EhXLSLD+5tcJ8g=="],
+    "@ast-grep/cli-darwin-arm64": ["@ast-grep/cli-darwin-arm64@0.40.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-UehY2MMUkdJbsriP7NKc6+uojrqPn7d1Cl0em+WAkee7Eij81VdyIjRsRxtZSLh440ZWQBHI3PALZ9RkOO8pKQ=="],
 
-    "@ast-grep/cli-darwin-x64": ["@ast-grep/cli-darwin-x64@0.40.5", "", { "os": "darwin", "cpu": "x64" }, "sha512-ez9b2zKvXU8f4ghhjlqYvbx6tWCKJTuVlNVqDDfjqwwhGeiTYfnzMlSVat4ElYRMd21gLtXZIMy055v2f21Ztg=="],
+    "@ast-grep/cli-darwin-x64": ["@ast-grep/cli-darwin-x64@0.40.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-RFDJ2ZxUbT0+grntNlOLJx7wa9/ciVCeaVtQpQy8WJJTvXvkY0etl8Qlh2TmO2x2yr+i0Z6aMJi4IG/Yx5ghTQ=="],
 
-    "@ast-grep/cli-linux-arm64-gnu": ["@ast-grep/cli-linux-arm64-gnu@0.40.5", "", { "os": "linux", "cpu": "arm64" }, "sha512-VXa2L1IEYD66AMb0GuG7VlMMbPmEGoJUySWDcwSZo/D9neiry3MJ41LQR5oTG2HyhIPBsf9umrXnmuRq66BviA=="],
+    "@ast-grep/cli-linux-arm64-gnu": ["@ast-grep/cli-linux-arm64-gnu@0.40.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-4p55gnTQ1mMFCyqjtM7bH9SB9r16mkwXtUcJQGX1YgFG4WD+QG8rC4GwSuNNZcdlYaOQuTWrgUEQ9z5K06UXfg=="],
 
-    "@ast-grep/cli-linux-x64-gnu": ["@ast-grep/cli-linux-x64-gnu@0.40.5", "", { "os": "linux", "cpu": "x64" }, "sha512-GQC5162eIOWXR2eQQ6Knzg7/8Trp5E1ODJkaErf0IubdQrZBGqj5AAcQPcWgPbbnmktjIp0H4NraPpOJ9eJ22A=="],
+    "@ast-grep/cli-linux-x64-gnu": ["@ast-grep/cli-linux-x64-gnu@0.40.0", "", { "os": "linux", "cpu": "x64" }, "sha512-u2MXFceuwvrO+OQ6zFGoJ6wbATXn46HWwW79j4UPrXYJzVl97jRyjJOIQTJOzTflsk02fjP98DQkfvbXt2dl3Q=="],
 
-    "@ast-grep/cli-win32-arm64-msvc": ["@ast-grep/cli-win32-arm64-msvc@0.40.5", "", { "os": "win32", "cpu": "arm64" }, "sha512-YiZdnQZsSlXQTMsZJop/Ux9MmUGfuRvC2x/UbFgrt5OBSYxND+yoiMc0WcA3WG+wU+tt4ZkB5HUea3r/IkOLYA=="],
+    "@ast-grep/cli-win32-arm64-msvc": ["@ast-grep/cli-win32-arm64-msvc@0.40.0", "", { "os": "win32", "cpu": "arm64" }, "sha512-E/I1xpF/RQL2fo1CQsQfTxyDLnChsbZ+ERrQHKuF1FI4WrkaPOBibpqda60QgVmUcgOGZyZ/GRb3iKEVWPsQNQ=="],
 
-    "@ast-grep/cli-win32-ia32-msvc": ["@ast-grep/cli-win32-ia32-msvc@0.40.5", "", { "os": "win32", "cpu": "ia32" }, "sha512-MHkCxCITVTr8sY9CcVqNKbfUzMa3Hc6IilGXad0Clnw2vNmPfWqSky+hU/UTerr5YHWwWfAVURH7ANZgirtx0Q=="],
+    "@ast-grep/cli-win32-ia32-msvc": ["@ast-grep/cli-win32-ia32-msvc@0.40.0", "", { "os": "win32", "cpu": "ia32" }, "sha512-9h12OQu1BR0GxHEtT+Z4QkJk3LLWLiKwjBkjXUGlASHYDPTyLcs85KwDLeFHs4BwarF8TDdF+KySvB9WPGl/nQ=="],
 
-    "@ast-grep/cli-win32-x64-msvc": ["@ast-grep/cli-win32-x64-msvc@0.40.5", "", { "os": "win32", "cpu": "x64" }, "sha512-/MJ5un7yxlClaaxou9eYl+Kr2xr/yTtYtTq5aLBWjPWA6dmmJ1nAJgx5zKHVuplFXFBrFDQk3paEgAETMTGcrA=="],
+    "@ast-grep/cli-win32-x64-msvc": ["@ast-grep/cli-win32-x64-msvc@0.40.0", "", { "os": "win32", "cpu": "x64" }, "sha512-n2+3WynEWFHhXg6KDgjwWQ0UEtIvqUITFbKEk5cDkUYrzYhg/A6kj0qauPwRbVMoJms49vtsNpLkzzqyunio5g=="],
 
-    "@ast-grep/napi": ["@ast-grep/napi@0.40.5", "", { "optionalDependencies": { "@ast-grep/napi-darwin-arm64": "0.40.5", "@ast-grep/napi-darwin-x64": "0.40.5", "@ast-grep/napi-linux-arm64-gnu": "0.40.5", "@ast-grep/napi-linux-arm64-musl": "0.40.5", "@ast-grep/napi-linux-x64-gnu": "0.40.5", "@ast-grep/napi-linux-x64-musl": "0.40.5", "@ast-grep/napi-win32-arm64-msvc": "0.40.5", "@ast-grep/napi-win32-ia32-msvc": "0.40.5", "@ast-grep/napi-win32-x64-msvc": "0.40.5" } }, "sha512-hJA62OeBKUQT68DD2gDyhOqJxZxycqg8wLxbqjgqSzYttCMSDL9tiAQ9abgekBYNHudbJosm9sWOEbmCDfpX2A=="],
+    "@ast-grep/napi": ["@ast-grep/napi@0.40.0", "", { "optionalDependencies": { "@ast-grep/napi-darwin-arm64": "0.40.0", "@ast-grep/napi-darwin-x64": "0.40.0", "@ast-grep/napi-linux-arm64-gnu": "0.40.0", "@ast-grep/napi-linux-arm64-musl": "0.40.0", "@ast-grep/napi-linux-x64-gnu": "0.40.0", "@ast-grep/napi-linux-x64-musl": "0.40.0", "@ast-grep/napi-win32-arm64-msvc": "0.40.0", "@ast-grep/napi-win32-ia32-msvc": "0.40.0", "@ast-grep/napi-win32-x64-msvc": "0.40.0" } }, "sha512-tq6nO/8KwUF/mHuk1ECaAOSOlz2OB/PmygnvprJzyAHGRVzdcffblaOOWe90M9sGz5MAasXoF+PTcayQj9TKKA=="],
 
-    "@ast-grep/napi-darwin-arm64": ["@ast-grep/napi-darwin-arm64@0.40.5", "", { "os": "darwin", "cpu": "arm64" }, "sha512-2F072fGN0WTq7KI3okuEnkGJVEHLbi56Bw1H6NAMf7j2mJJeQWsRyGOMcyNnUXZDeNdvoMH0OB2a5wwUegY/nQ=="],
+    "@ast-grep/napi-darwin-arm64": ["@ast-grep/napi-darwin-arm64@0.40.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-ZMjl5yLhKjxdwbqEEdMizgQdWH2NrWsM6Px+JuGErgCDe6Aedq9yurEPV7veybGdLVJQhOah6htlSflXxjHnYA=="],
 
-    "@ast-grep/napi-darwin-x64": ["@ast-grep/napi-darwin-x64@0.40.5", "", { "os": "darwin", "cpu": "x64" }, "sha512-dJMidHZhhxuLBYNi6/FKI812jQ7wcFPSKkVPwviez2D+KvYagapUMAV/4dJ7FCORfguVk8Y0jpPAlYmWRT5nvA=="],
+    "@ast-grep/napi-darwin-x64": ["@ast-grep/napi-darwin-x64@0.40.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-f9Ol5oQKNRMBkvDtzBK1WiNn2/3eejF2Pn9xwTj7PhXuSFseedOspPYllxQo0gbwUlw/DJqGFTce/jarhR/rBw=="],
 
-    "@ast-grep/napi-linux-arm64-gnu": ["@ast-grep/napi-linux-arm64-gnu@0.40.5", "", { "os": "linux", "cpu": "arm64" }, "sha512-nBRCbyoS87uqkaw4Oyfe5VO+SRm2B+0g0T8ME69Qry9ShMf41a2bTdpcQx9e8scZPogq+CTwDHo3THyBV71l9w=="],
+    "@ast-grep/napi-linux-arm64-gnu": ["@ast-grep/napi-linux-arm64-gnu@0.40.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-+tO+VW5GDhT9jGkKOK+3b8+ohKjC98WTzn7wSskd/myyhK3oYL1WTKqCm07WSYBZOJvb3z+WaX+wOUrc4bvtyQ=="],
 
-    "@ast-grep/napi-linux-arm64-musl": ["@ast-grep/napi-linux-arm64-musl@0.40.5", "", { "os": "linux", "cpu": "arm64" }, "sha512-/qKsmds5FMoaEj6FdNzepbmLMtlFuBLdrAn9GIWCqOIcVcYvM1Nka8+mncfeXB/MFZKOrzQsQdPTWqrrQzXLrA=="],
+    "@ast-grep/napi-linux-arm64-musl": ["@ast-grep/napi-linux-arm64-musl@0.40.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-MS9qalLRjUnF2PCzuTKTvCMVSORYHxxe3Qa0+SSaVULsXRBmuy5C/b1FeWwMFnwNnC0uie3VDet31Zujwi8q6A=="],
 
-    "@ast-grep/napi-linux-x64-gnu": ["@ast-grep/napi-linux-x64-gnu@0.40.5", "", { "os": "linux", "cpu": "x64" }, "sha512-DP4oDbq7f/1A2hRTFLhJfDFR6aI5mRWdEfKfHzRItmlKsR9WlcEl1qDJs/zX9R2EEtIDsSKRzuJNfJllY3/W8Q=="],
+    "@ast-grep/napi-linux-x64-gnu": ["@ast-grep/napi-linux-x64-gnu@0.40.0", "", { "os": "linux", "cpu": "x64" }, "sha512-BeHZVMNXhM3WV3XE2yghO0fRxhMOt8BTN972p5piYEQUvKeSHmS8oeGcs6Ahgx5znBclqqqq37ZfioYANiTqJA=="],
 
-    "@ast-grep/napi-linux-x64-musl": ["@ast-grep/napi-linux-x64-musl@0.40.5", "", { "os": "linux", "cpu": "x64" }, "sha512-BRZUvVBPUNpWPo6Ns8chXVzxHPY+k9gpsubGTHy92Q26ecZULd/dTkWWdnvfhRqttsSQ9Pe/XQdi5+hDQ6RYcg=="],
+    "@ast-grep/napi-linux-x64-musl": ["@ast-grep/napi-linux-x64-musl@0.40.0", "", { "os": "linux", "cpu": "x64" }, "sha512-rG1YujF7O+lszX8fd5u6qkFTuv4FwHXjWvt1CCvCxXwQLSY96LaCW88oVKg7WoEYQh54y++Fk57F+Wh9Gv9nVQ=="],
 
-    "@ast-grep/napi-win32-arm64-msvc": ["@ast-grep/napi-win32-arm64-msvc@0.40.5", "", { "os": "win32", "cpu": "arm64" }, "sha512-y95zSEwc7vhxmcrcH0GnK4ZHEBQrmrszRBNQovzaciF9GUqEcCACNLoBesn4V47IaOp4fYgD2/EhGRTIBFb2Ug=="],
+    "@ast-grep/napi-win32-arm64-msvc": ["@ast-grep/napi-win32-arm64-msvc@0.40.0", "", { "os": "win32", "cpu": "arm64" }, "sha512-9SqmnQqd4zTEUk6yx0TuW2ycZZs2+e569O/R0QnhSiQNpgwiJCYOe/yPS0BC9HkiaozQm6jjAcasWpFtz/dp+w=="],
 
-    "@ast-grep/napi-win32-ia32-msvc": ["@ast-grep/napi-win32-ia32-msvc@0.40.5", "", { "os": "win32", "cpu": "ia32" }, "sha512-K/u8De62iUnFCzVUs7FBdTZ2Jrgc5/DLHqjpup66KxZ7GIM9/HGME/O8aSoPkpcAeCD4TiTZ11C1i5p5H98hTg=="],
+    "@ast-grep/napi-win32-ia32-msvc": ["@ast-grep/napi-win32-ia32-msvc@0.40.0", "", { "os": "win32", "cpu": "ia32" }, "sha512-0JkdBZi5l9vZhGEO38A1way0LmLRDU5Vos6MXrLIOVkymmzDTDlCdY394J1LMmmsfwWcyJg6J7Yv2dw41MCxDQ=="],
 
-    "@ast-grep/napi-win32-x64-msvc": ["@ast-grep/napi-win32-x64-msvc@0.40.5", "", { "os": "win32", "cpu": "x64" }, "sha512-dqm5zg/o4Nh4VOQPEpMS23ot8HVd22gG0eg01t4CFcZeuzyuSgBlOL3N7xLbz3iH2sVkk7keuBwAzOIpTqziNQ=="],
+    "@ast-grep/napi-win32-x64-msvc": ["@ast-grep/napi-win32-x64-msvc@0.40.0", "", { "os": "win32", "cpu": "x64" }, "sha512-Hk2IwfPqMFGZt5SRxsoWmGLxBXxprow4LRp1eG6V8EEiJCNHxZ9ZiEaIc5bNvMDBjHVSnqZAXT22dROhrcSKQg=="],
 
     "@clack/core": ["@clack/core@0.5.0", "", { "dependencies": { "picocolors": "^1.0.0", "sisteransi": "^1.0.5" } }, "sha512-p3y0FIOwaYRUPRcMO7+dlmLh8PSRcrjuTndsiA0WAFbWES0mLZlrjVoBRZ9DzkPFJZG6KGkJmoEAY0ZcVWTkow=="],
 
@@ -86,17 +86,17 @@
 
     "@code-yeongyu/comment-checker": ["@code-yeongyu/comment-checker@0.6.1", "", { "os": [ "linux", "win32", "darwin", ], "cpu": [ "x64", "arm64", ], "bin": { "comment-checker": "bin/comment-checker" } }, "sha512-BBremX+Y5aW8sTzlhHrLsKParupYkPOVUYmq9STrlWvBvfAme6w5IWuZCLl6nHIQScRDdvGdrAjPycJC86EZFA=="],
 
-    "@hono/node-server": ["@hono/node-server@1.19.9", "", { "peerDependencies": { "hono": "^4" } }, "sha512-vHL6w3ecZsky+8P5MD+eFfaGTyCeOHUIFYMGpQGbrBTSmNNoxv0if69rEZ5giu36weC5saFuznL411gRX7bJDw=="],
+    "@hono/node-server": ["@hono/node-server@1.19.7", "", { "peerDependencies": { "hono": "^4" } }, "sha512-vUcD0uauS7EU2caukW8z5lJKtoGMokxNbJtBiwHgpqxEXokaHCBkQUmCHhjFB1VUTWdqj25QoMkMKzgjq+uhrw=="],
 
-    "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.25.3", "", { "dependencies": { "@hono/node-server": "^1.19.9", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.0.1", "express-rate-limit": "^7.5.0", "jose": "^6.1.1", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.0" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-vsAMBMERybvYgKbg/l4L1rhS7VXV1c0CtyJg72vwxONVX0l4ZfKVAnZEWTQixJGTzKnELjQ59e4NbdFDALRiAQ=="],
+    "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.25.1", "", { "dependencies": { "@hono/node-server": "^1.19.7", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.0.1", "express-rate-limit": "^7.5.0", "jose": "^6.1.1", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.0" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-yO28oVFFC7EBoiKdAn+VqRm+plcfv4v0xp6osG/VsCB0NlPZWi87ajbCZZ8f/RvOFLEu7//rSRmuZZ7lMoe3gQ=="],
 
-    "@opencode-ai/plugin": ["@opencode-ai/plugin@1.1.47", "", { "dependencies": { "@opencode-ai/sdk": "1.1.47", "zod": "4.1.8" } }, "sha512-gNMPz72altieDfLhUw3VAT1xbduKi3w3wZ57GLeS7qU9W474HdvdIiLBnt2Xq3U7Ko0/0tvK3nzCker6IIDqmQ=="],
+    "@opencode-ai/plugin": ["@opencode-ai/plugin@1.1.19", "", { "dependencies": { "@opencode-ai/sdk": "1.1.19", "zod": "4.1.8" } }, "sha512-Q6qBEjHb/dJMEw4BUqQxEswTMxCCHUpFMMb6jR8HTTs8X/28XRkKt5pHNPA82GU65IlSoPRph+zd8LReBDN53Q=="],
 
-    "@opencode-ai/sdk": ["@opencode-ai/sdk@1.1.47", "", {}, "sha512-s3PBHwk1sP6Zt/lJxIWSBWZ1TnrI1nFxSP97LCODUytouAQgbygZ1oDH7O2sGMBEuGdA8B1nNSPla0aRSN3IpA=="],
+    "@opencode-ai/sdk": ["@opencode-ai/sdk@1.1.19", "", {}, "sha512-XhZhFuvlLCqDpvNtUEjOsi/wvFj3YCXb1dySp+OONQRMuHlorNYnNa7P2A2ntKuhRdGT1Xt5na0nFzlUyNw+4A=="],
 
     "@types/js-yaml": ["@types/js-yaml@4.0.9", "", {}, "sha512-k4MGaQl5TGo/iipqb2UDG2UwjXziSWkh0uysQelTlJpX1qGlpUZYm8PnO4DxG1qBomtJUdYJ6qR6xdIah10JLg=="],
 
-    "@types/node": ["@types/node@25.1.0", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-t7frlewr6+cbx+9Ohpl0NOTKXZNV9xHRmNOvql47BFJKcEG1CxtxlPEEe+gR9uhVWM4DwhnvTF110mIL4yP9RA=="],
+    "@types/node": ["@types/node@24.10.1", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-GNWcUTRBgIRJD5zj+Tq0fKOJ5XZajIiBroOF0yvj2bSU1WvNdYS/dn9UxwsujGW4JX06dnHyjV2y9rRaybH0iQ=="],
 
     "@types/picomatch": ["@types/picomatch@3.0.2", "", {}, "sha512-n0i8TD3UDB7paoMMxA3Y65vUncFJXjcUf7lQY7YyKGl6031FNjfsLs6pdLFCy2GNFxItPJG8GvvpbZc2skH7WA=="],
 
@@ -108,7 +108,7 @@
 
     "argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],
 
-    "body-parser": ["body-parser@2.2.2", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^1.0.5", "debug": "^4.4.3", "http-errors": "^2.0.0", "iconv-lite": "^0.7.0", "on-finished": "^2.4.1", "qs": "^6.14.1", "raw-body": "^3.0.1", "type-is": "^2.0.1" } }, "sha512-oP5VkATKlNwcgvxi0vM0p/D3n2C3EReYVX+DNYs5TjZFn/oQt2j+4sVJtSMr18pdRr8wjTcBl6LoV+FUwzPmNA=="],
+    "body-parser": ["body-parser@2.2.1", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^1.0.5", "debug": "^4.4.3", "http-errors": "^2.0.0", "iconv-lite": "^0.7.0", "on-finished": "^2.4.1", "qs": "^6.14.0", "raw-body": "^3.0.1", "type-is": "^2.0.1" } }, "sha512-nfDwkulwiZYQIGwxdy0RUmowMhKcFVcYXUU7m4QlKYim1rUtg83xm2yjZ40QjDuc291AJjjeSc9b++AWHSgSHw=="],
 
     "bun-types": ["bun-types@1.3.6", "", { "dependencies": { "@types/node": "*" } }, "sha512-OlFwHcnNV99r//9v5IIOgQ9Uk37gZqrNMCcqEaExdkVq3Avwqok1bJFmvGMCkCE0FqzdY8VMOZpfpR3lwI+CsQ=="],
 
@@ -118,7 +118,7 @@
 
     "call-bound": ["call-bound@1.0.4", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.2", "get-intrinsic": "^1.3.0" } }, "sha512-+ys997U96po4Kx/ABpBCqhA9EuxJaQWDQg7295H4hBphv3IZg0boBKuwYpt4YXp6MZ5AmZQnU/tyMTlRpaSejg=="],
 
-    "commander": ["commander@14.0.3", "", {}, "sha512-H+y0Jo/T1RZ9qPP4Eh1pkcQcLRglraJaSLoyOtHxu6AapkjWVCy2Sit1QQ4x3Dng8qDlSsZEet7g5Pq06MvTgw=="],
+    "commander": ["commander@14.0.2", "", {}, "sha512-TywoWNNRbhoD0BXs1P3ZEScW8W5iKrnbithIl0YH+uCmBd0QpPOA8yc82DS3BIE5Ma6FnBVUsJ7wVUDz4dvOWQ=="],
 
     "content-disposition": ["content-disposition@1.0.1", "", {}, "sha512-oIXISMynqSqm241k6kcQ5UwttDILMK4BiurCfGEREw6+X9jkkpEe5T9FZaApyLGGOnFuyMWZpdolTXMtvEJ08Q=="],
 
@@ -128,7 +128,7 @@
 
     "cookie-signature": ["cookie-signature@1.2.2", "", {}, "sha512-D76uU73ulSXrD1UXF4KE2TMxVVwhsnCgfAyTg9k8P6KGZjlXKrOLe4dJQKI3Bxi5wjesZoFXJWElNWBjPZMbhg=="],
 
-    "cors": ["cors@2.8.6", "", { "dependencies": { "object-assign": "^4", "vary": "^1" } }, "sha512-tJtZBBHA6vjIAaF6EnIaq6laBBP9aq/Y3ouVJjEfoHbRBcHBAHYcMh/w8LDrk2PvIMMq8gmopa5D4V8RmbrxGw=="],
+    "cors": ["cors@2.8.5", "", { "dependencies": { "object-assign": "^4", "vary": "^1" } }, "sha512-KIHbLJqu73RGr/hnbrO9uBeixNGuvSQjul/jdFvS/KFSIH1hWVd1ng7zOHx+YrEfInLG7q4n6GHQ9cDtxv/P6g=="],
 
     "cross-spawn": ["cross-spawn@7.0.6", "", { "dependencies": { "path-key": "^3.1.0", "shebang-command": "^2.0.0", "which": "^2.0.1" } }, "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA=="],
 
@@ -184,11 +184,11 @@
 
     "hasown": ["hasown@2.0.2", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ=="],
 
-    "hono": ["hono@4.11.7", "", {}, "sha512-l7qMiNee7t82bH3SeyUCt9UF15EVmaBvsppY2zQtrbIhl/yzBTny+YUxsVjSjQ6gaqaeVtZmGocom8TzBlA4Yw=="],
+    "hono": ["hono@4.10.8", "", {}, "sha512-DDT0A0r6wzhe8zCGoYOmMeuGu3dyTAE40HHjwUsWFTEy5WxK1x2WDSsBPlEXgPbRIFY6miDualuUDbasPogIww=="],
 
     "http-errors": ["http-errors@2.0.1", "", { "dependencies": { "depd": "~2.0.0", "inherits": "~2.0.4", "setprototypeof": "~1.2.0", "statuses": "~2.0.2", "toidentifier": "~1.0.1" } }, "sha512-4FbRdAX+bSdmo4AUFuS0WNiPz8NgFt+r8ThgNWmlrjQjt1Q7ZR9+zTlce2859x4KSXrwIsaeTqDoKQmtP8pLmQ=="],
 
-    "iconv-lite": ["iconv-lite@0.7.2", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-im9DjEDQ55s9fL4EYzOAv0yMqmMBSZp6G0VvFyTMPKWxiSBHUj9NW/qqLmXUwXrrM7AvqSlTCfvqRb0cM8yYqw=="],
+    "iconv-lite": ["iconv-lite@0.7.1", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-2Tth85cXwGFHfvRgZWszZSvdo+0Xsqmw8k8ZwxScfcBneNUraK+dxRxRm24nszx80Y0TVio8kKLt5sLE7ZCLlw=="],
 
     "inherits": ["inherits@2.0.4", "", {}, "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="],
 
@@ -226,19 +226,19 @@
 
     "object-inspect": ["object-inspect@1.13.4", "", {}, "sha512-W67iLl4J2EXEGTbfeHCffrjDfitvLANg0UlX3wFUUSTx92KXRFegMHUVgSqE+wvhAbi4WqjGg9czysTV2Epbew=="],
 
-    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.2.2", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-KyfoWcANfcvpfanrrX+Wc8vH8vr9mvr7dJMHBe2bkvuhdtHnLHOG18hQwLg6jk4HhdoZAeBEmkolOsK2k4XajA=="],
+    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.2.3", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-Doc9xQCj5Jmx3PzouBIfvDwmfWM94Y9Q9IngFqOjrVpfBef9V/WIH0PlhJU6ps4BKGey8Nf2afFq3UE06Z63Hg=="],
 
-    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.2.2", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-ajZ1E36Ixwdz6rvSUKUI08M2xOaNIl1ZsdVjknZTrPRtct9xgS+BEFCoSCov9bnV/9DrZD3mlZtO/+FFDbseUg=="],
+    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.2.3", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-w7lO0Hn/AlLCHe33KPbje83Js2h5weDWVMuopEs6d3pi/1zkRDBEhCi63S4J0d0EKod9kEPQA6ojtdVJ4J39zQ=="],
 
-    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.2.2", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-ItJsYfigXcOa8/ejTjopC4qk5BCeYioMQ693kPTpeYHK3ByugTjJk8aamE7bHlVnmrdgWldz91QFzaP82yOAdg=="],
+    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.2.3", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-m1tS1jRLO2Svm5NuetK3BAgdAR8b2GkiIfMFoIYsLJTPmzIkXaigAYkFq+BXCs5JAbRmPmvjndz9cuCddnPADQ=="],
 
-    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.2.2", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-/TvjYe/Kb//ZSHnJzgRj0QPKpS5Y2nermVTSaMTGS2btObXQyQWzuphDhsVRu60SVrNLbflHzfuTdqb3avDjyA=="],
+    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.2.3", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-Q/0AGtOuUFGNGIX8F6iD5W8c2spbjrqVBPt0B7laQSwnScKs/BI+TvM6HRE37vhoWg+fzhAX3QYJ2H9Un9FYrg=="],
 
-    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.2.2", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-Ka5j+tjuQkNnpESVzcTzW5tZMlBhOfP9F12+UaR72cIcwFpSoLMBp84rV6R0vXM0zUcrrN7mPeW66DvQ6A0XQQ=="],
+    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.2.3", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-RIAyoj2XbT8vH++5fPUkdO+D1tfqxh+iWto7CqWr1TgbABbBJljGk91HJgS9xjnxyCQJEpFhTmO7NMHKJcZOWQ=="],
 
-    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.2.2", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-ISl0sTNShKCgPFO+rsDqEDsvVHQAMfOSAxO0KuWbHFKaH+KaRV4d3N/ihgxZ2M94CZjJLzZEuln+6kLZ93cvzQ=="],
+    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.2.3", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-nnQK3y7R4DrBvqdqRGbujL2oAAQnVVb23JHUbJPQ6YxrRRGWpLOVGvK5c16ykSFEUPl8eZDmi1ON/R4opKLOUw=="],
 
-    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.2.2", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-KeiJLQvJuZ+UYf/+eMsQXvCiHDRPk6tD15lL+qruLvU19va62JqMNvTuOv97732uF19iG0ZMiiVhqIMbSyVPqQ=="],
+    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.2.3", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-mt8E/TkpaCp04pvzwntT8x8TaqXDt3zCD5X2eA8ZZMrb5ofNr5HyG5G4SFXrUh+Ez3b/3YXpNWv6f6rnAlk1Dg=="],
 
     "on-finished": ["on-finished@2.4.1", "", { "dependencies": { "ee-first": "1.1.1" } }, "sha512-oVlzkg3ENAhCk2zdv7IJwd/QUD4z2RxRwpkcGY8psCVcCYZNq4wYnVWALHM+brtuJjePWiYF/ClmuDr8Ch5+kg=="],
 
@@ -310,10 +310,8 @@
 
     "wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="],
 
-    "zod": ["zod@4.3.6", "", {}, "sha512-rftlrkhHZOcjDwkGlnUtZZkvaPHCsDATp4pGpuOOMDaTdDDXF91wuVDJoWoPsKX/3YPQ5fHuF3STjcYyKr+Qhg=="],
+    "zod": ["zod@4.1.8", "", {}, "sha512-5R1P+WwQqmmMIEACyzSvo4JXHY5WiAFHRMg+zBZKgKS+Q1viRa0C1hmUKtHltoIFKtIdki3pRxkmpP74jnNYHQ=="],
 
     "zod-to-json-schema": ["zod-to-json-schema@3.25.1", "", { "peerDependencies": { "zod": "^3.25 || ^4" } }, "sha512-pM/SU9d3YAggzi6MtR4h7ruuQlqKtad8e9S0fmxcMi+ueAK5Korys/aWcV9LIIHTVbj01NdzxcnXSN+O74ZIVA=="],
-
-    "@opencode-ai/plugin/zod": ["zod@4.1.8", "", {}, "sha512-5R1P+WwQqmmMIEACyzSvo4JXHY5WiAFHRMg+zBZKgKS+Q1viRa0C1hmUKtHltoIFKtIdki3pRxkmpP74jnNYHQ=="],
   }
 }

docs/category-skill-guide.md

@@ -22,12 +22,12 @@ A Category is an agent configuration preset optimized for specific domains.
 | Category | Default Model | Use Cases |
 |----------|---------------|-----------|
 | `visual-engineering` | `google/gemini-3-pro` | Frontend, UI/UX, design, styling, animation |
-| `ultrabrain` | `openai/gpt-5.2-codex` (xhigh) | Deep logical reasoning, complex architecture decisions requiring extensive analysis |
-| `deep` | `openai/gpt-5.2-codex` (medium) | Goal-oriented autonomous problem-solving. Thorough research before action. For hairy problems requiring deep understanding. |
+| `ultrabrain` | `openai/gpt-5.3-codex` (xhigh) | Deep logical reasoning, complex architecture decisions requiring extensive analysis |
+| `deep` | `openai/gpt-5.3-codex` (medium) | Goal-oriented autonomous problem-solving. Thorough research before action. For hairy problems requiring deep understanding. |
 | `artistry` | `google/gemini-3-pro` (max) | Highly creative/artistic tasks, novel ideas |
 | `quick` | `anthropic/claude-haiku-4-5` | Trivial tasks - single file changes, typo fixes, simple modifications |
 | `unspecified-low` | `anthropic/claude-sonnet-4-5` | Tasks that don't fit other categories, low effort required |
-| `unspecified-high` | `anthropic/claude-opus-4-5` (max) | Tasks that don't fit other categories, high effort required |
+| `unspecified-high` | `anthropic/claude-opus-4-6` (max) | Tasks that don't fit other categories, high effort required |
 | `writing` | `google/gemini-3-flash` | Documentation, prose, technical writing |
 
 ### Usage
@@ -159,7 +159,7 @@ You can fine-tune categories in `oh-my-opencode.json`.
 | Field | Type | Description |
 |-------|------|-------------|
 | `description` | string | Human-readable description of the category's purpose. Shown in delegate_task prompt. |
-| `model` | string | AI model ID to use (e.g., `anthropic/claude-opus-4-5`) |
+| `model` | string | AI model ID to use (e.g., `anthropic/claude-opus-4-6`) |
 | `variant` | string | Model variant (e.g., `max`, `xhigh`) |
 | `temperature` | number | Creativity level (0.0 ~ 2.0). Lower is more deterministic. |
 | `top_p` | number | Nucleus sampling parameter (0.0 ~ 1.0) |
@@ -191,7 +191,7 @@ You can fine-tune categories in `oh-my-opencode.json`.
 
     // 3. Configure thinking model and restrict tools
     "deep-reasoning": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "thinking": {
         "type": "enabled",
         "budgetTokens": 32000

docs/configurations.md

@@ -693,7 +693,7 @@ Configure concurrency limits for background agent tasks. This controls how many
       "google": 10
     },
     "modelConcurrency": {
-      "anthropic/claude-opus-4-5": 2,
+      "anthropic/claude-opus-4-6": 2,
       "google/gemini-3-flash": 10
     }
   }
@@ -705,7 +705,7 @@ Configure concurrency limits for background agent tasks. This controls how many
 | `defaultConcurrency`  | -       | Default maximum concurrent background tasks for all providers/models                                                    |
 | `staleTimeoutMs`      | `180000` | Stale timeout in milliseconds - interrupt tasks with no activity for this duration (minimum: 60000 = 1 minute)             |
 | `providerConcurrency` | -       | Per-provider concurrency limits. Keys are provider names (e.g., `anthropic`, `openai`, `google`)                        |
-| `modelConcurrency`    | -       | Per-model concurrency limits. Keys are full model names (e.g., `anthropic/claude-opus-4-5`). Overrides provider limits. |
+| `modelConcurrency`    | -       | Per-model concurrency limits. Keys are full model names (e.g., `anthropic/claude-opus-4-6`). Overrides provider limits. |
 
 **Priority Order**: `modelConcurrency` > `providerConcurrency` > `defaultConcurrency`
 
@@ -725,11 +725,11 @@ All 7 categories come with optimal model defaults, but **you must configure them
 | Category             | Built-in Default Model             | Description                                                          |
 | -------------------- | ---------------------------------- | -------------------------------------------------------------------- |
 | `visual-engineering` | `google/gemini-3-pro-preview`      | Frontend, UI/UX, design, styling, animation                          |
-| `ultrabrain`         | `openai/gpt-5.2-codex` (xhigh)     | Deep logical reasoning, complex architecture decisions               |
+| `ultrabrain`         | `openai/gpt-5.3-codex` (xhigh)     | Deep logical reasoning, complex architecture decisions               |
 | `artistry`           | `google/gemini-3-pro-preview` (max)| Highly creative/artistic tasks, novel ideas                          |
 | `quick`              | `anthropic/claude-haiku-4-5`       | Trivial tasks - single file changes, typo fixes, simple modifications|
 | `unspecified-low`    | `anthropic/claude-sonnet-4-5`      | Tasks that don't fit other categories, low effort required           |
-| `unspecified-high`   | `anthropic/claude-opus-4-5` (max)  | Tasks that don't fit other categories, high effort required          |
+| `unspecified-high`   | `anthropic/claude-opus-4-6` (max)  | Tasks that don't fit other categories, high effort required          |
 | `writing`            | `google/gemini-3-flash-preview`    | Documentation, prose, technical writing                              |
 
 ### ⚠️ Critical: Model Resolution Priority
@@ -768,7 +768,7 @@ All 7 categories come with optimal model defaults, but **you must configure them
       "model": "google/gemini-3-pro-preview"
     },
     "ultrabrain": { 
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "xhigh"
     },
     "artistry": { 
@@ -782,7 +782,7 @@ All 7 categories come with optimal model defaults, but **you must configure them
       "model": "anthropic/claude-sonnet-4-5"
     },
     "unspecified-high": { 
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max"
     },
     "writing": { 
@@ -870,9 +870,9 @@ At runtime, Oh My OpenCode uses a 3-step resolution process to determine which m
 │   │ anthropic → github-copilot → opencode → antigravity     │   │
 │   │     │            │              │            │          │   │
 │   │     ▼            ▼              ▼            ▼          │   │
-│   │ Try: anthropic/claude-opus-4-5                          │   │
-│   │ Try: github-copilot/claude-opus-4-5                     │   │
-│   │ Try: opencode/claude-opus-4-5                           │   │
+│   │ Try: anthropic/claude-opus-4-6                          │   │
+│   │ Try: github-copilot/claude-opus-4-6                     │   │
+│   │ Try: opencode/claude-opus-4-6                           │   │
 │   │ ...                                                     │   │
 │   │                                                         │   │
 │   │ Found in available models? → Return matched model       │   │
@@ -894,13 +894,13 @@ Each agent has a defined provider priority chain. The system tries providers in
 
 | Agent | Model (no prefix) | Provider Priority Chain |
 |-------|-------------------|-------------------------|
-| **Sisyphus** | `claude-opus-4-5` | anthropic → kimi-for-coding → zai-coding-plan → openai → google |
+| **Sisyphus** | `claude-opus-4-6` | anthropic → kimi-for-coding → zai-coding-plan → openai → google |
 | **oracle** | `gpt-5.2` | openai → google → anthropic |
 | **librarian** | `glm-4.7` | zai-coding-plan → opencode → anthropic |
 | **explore** | `claude-haiku-4-5` | anthropic → github-copilot → opencode |
 | **multimodal-looker** | `gemini-3-flash` | google → openai → zai-coding-plan → kimi-for-coding → anthropic → opencode |
-| **Prometheus (Planner)** | `claude-opus-4-5` | anthropic → kimi-for-coding → openai → google |
-| **Metis (Plan Consultant)** | `claude-opus-4-5` | anthropic → kimi-for-coding → openai → google |
+| **Prometheus (Planner)** | `claude-opus-4-6` | anthropic → kimi-for-coding → openai → google |
+| **Metis (Plan Consultant)** | `claude-opus-4-6` | anthropic → kimi-for-coding → openai → google |
 | **Momus (Plan Reviewer)** | `gpt-5.2` | openai → anthropic → google |
 | **Atlas** | `claude-sonnet-4-5` | anthropic → kimi-for-coding → openai → google |
 
@@ -911,12 +911,12 @@ Categories follow the same resolution logic:
 | Category | Model (no prefix) | Provider Priority Chain |
 |----------|-------------------|-------------------------|
 | **visual-engineering** | `gemini-3-pro` | google → anthropic → zai-coding-plan |
-| **ultrabrain** | `gpt-5.2-codex` | openai → google → anthropic |
-| **deep** | `gpt-5.2-codex` | openai → anthropic → google |
+| **ultrabrain** | `gpt-5.3-codex` | openai → google → anthropic |
+| **deep** | `gpt-5.3-codex` | openai → anthropic → google |
 | **artistry** | `gemini-3-pro` | google → anthropic → openai |
 | **quick** | `claude-haiku-4-5` | anthropic → google → opencode |
 | **unspecified-low** | `claude-sonnet-4-5` | anthropic → openai → google |
-| **unspecified-high** | `claude-opus-4-5` | anthropic → openai → google |
+| **unspecified-high** | `claude-opus-4-6` | anthropic → openai → google |
 | **writing** | `gemini-3-flash` | google → anthropic → zai-coding-plan → openai |
 
 ### Checking Your Configuration
@@ -949,7 +949,7 @@ Override any agent or category model in `oh-my-opencode.json`:
   },
   "categories": {
     "visual-engineering": {
-      "model": "anthropic/claude-opus-4-5"
+      "model": "anthropic/claude-opus-4-6"
     }
   }
 }

docs/features.md

@@ -10,8 +10,8 @@ Oh-My-OpenCode provides 11 specialized AI agents. Each has distinct expertise, o
 
 | Agent | Model | Purpose |
 |-------|-------|---------|
-| **Sisyphus** | `anthropic/claude-opus-4-5` | **The default orchestrator.** Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). Fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro. |
-| **Hephaestus** | `openai/gpt-5.2-codex` | **The Legitimate Craftsman.** Autonomous deep worker inspired by AmpCode's deep mode. Goal-oriented execution with thorough research before action. Explores codebase patterns, completes tasks end-to-end without premature stopping. Named after the Greek god of forge and craftsmanship. Requires gpt-5.2-codex (no fallback - only activates when this model is available). |
+| **Sisyphus** | `anthropic/claude-opus-4-6` | **The default orchestrator.** Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). Fallback: kimi-k2.5 → glm-4.7 → gpt-5.3-codex → gemini-3-pro. |
+| **Hephaestus** | `openai/gpt-5.3-codex` | **The Legitimate Craftsman.** Autonomous deep worker inspired by AmpCode's deep mode. Goal-oriented execution with thorough research before action. Explores codebase patterns, completes tasks end-to-end without premature stopping. Named after the Greek god of forge and craftsmanship. Requires gpt-5.3-codex (no fallback - only activates when this model is available). |
 | **oracle** | `openai/gpt-5.2` | Architecture decisions, code review, debugging. Read-only consultation - stellar logical reasoning and deep analysis. Inspired by AmpCode. |
 | **librarian** | `zai-coding-plan/glm-4.7` | Multi-repo analysis, documentation lookup, OSS implementation examples. Deep codebase understanding with evidence-based answers. Fallback: glm-4.7-free → claude-sonnet-4-5. |
 | **explore** | `anthropic/claude-haiku-4-5` | Fast codebase exploration and contextual grep. Fallback: gpt-5-mini → gpt-5-nano. |
@@ -21,9 +21,9 @@ Oh-My-OpenCode provides 11 specialized AI agents. Each has distinct expertise, o
 
 | Agent | Model | Purpose |
 |-------|-------|---------|
-| **Prometheus** | `anthropic/claude-opus-4-5` | Strategic planner with interview mode. Creates detailed work plans through iterative questioning. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
-| **Metis** | `anthropic/claude-opus-4-5` | Plan consultant - pre-planning analysis. Identifies hidden intentions, ambiguities, and AI failure points. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
-| **Momus** | `openai/gpt-5.2` | Plan reviewer - validates plans against clarity, verifiability, and completeness standards. Fallback: gpt-5.2 → claude-opus-4-5 → gemini-3-pro. |
+| **Prometheus** | `anthropic/claude-opus-4-6` | Strategic planner with interview mode. Creates detailed work plans through iterative questioning. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
+| **Metis** | `anthropic/claude-opus-4-6` | Plan consultant - pre-planning analysis. Identifies hidden intentions, ambiguities, and AI failure points. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
+| **Momus** | `openai/gpt-5.2` | Plan reviewer - validates plans against clarity, verifiability, and completeness standards. Fallback: gpt-5.2 → claude-opus-4-6 → gemini-3-pro. |
 
 ### Invoking Agents
 

docs/guide/installation.md

@@ -196,7 +196,7 @@ When GitHub Copilot is the best available provider, oh-my-opencode uses these mo
 
 | Agent         | Model                            |
 | ------------- | -------------------------------- |
-| **Sisyphus**  | `github-copilot/claude-opus-4.5` |
+| **Sisyphus**  | `github-copilot/claude-opus-4.6` |
 | **Oracle**    | `github-copilot/gpt-5.2`         |
 | **Explore**   | `opencode/gpt-5-nano`              |
 | **Librarian** | `zai-coding-plan/glm-4.7` (if Z.ai available) or fallback |
@@ -218,13 +218,13 @@ If Z.ai is the only provider available, all agents will use GLM models:
 
 #### OpenCode Zen
 
-OpenCode Zen provides access to `opencode/` prefixed models including `opencode/claude-opus-4-5`, `opencode/gpt-5.2`, `opencode/gpt-5-nano`, and `opencode/glm-4.7-free`.
+OpenCode Zen provides access to `opencode/` prefixed models including `opencode/claude-opus-4-6`, `opencode/gpt-5.2`, `opencode/gpt-5-nano`, and `opencode/glm-4.7-free`.
 
 When OpenCode Zen is the best available provider (no native or Copilot), these models are used:
 
 | Agent         | Model                            |
 | ------------- | -------------------------------- |
-| **Sisyphus**  | `opencode/claude-opus-4-5`       |
+| **Sisyphus**  | `opencode/claude-opus-4-6`       |
 | **Oracle**    | `opencode/gpt-5.2`               |
 | **Explore**   | `opencode/gpt-5-nano`             |
 | **Librarian** | `opencode/glm-4.7-free`          |

docs/guide/understanding-orchestration-system.md

@@ -277,7 +277,7 @@ This "boulder pushing" mechanism is why the system is named after Sisyphus.
 ```typescript
 // OLD: Model name creates distributional bias
 delegate_task(agent="gpt-5.2", prompt="...")  // Model knows its limitations
-delegate_task(agent="claude-opus-4.5", prompt="...")  // Different self-perception
+delegate_task(agent="claude-opus-4.6", prompt="...")  // Different self-perception
 ```
 
 **The Solution: Semantic Categories:**

docs/orchestration-guide.md

@@ -275,7 +275,7 @@ flowchart TD
 
 ### 🔮 Prometheus (The Planner)
 
-- **Model**: `anthropic/claude-opus-4-5`
+- **Model**: `anthropic/claude-opus-4-6`
 - **Role**: Strategic planning, requirements interviews, work plan creation
 - **Constraint**: **READ-ONLY**. Can only create/modify markdown files within `.sisyphus/` directory.
 - **Characteristic**: Never writes code directly, focuses solely on "how to do it".

issue-1501-analysis.md

@@ -0,0 +1,357 @@
+# Issue #1501 분석 보고서: ULW Mode PLAN AGENT 무한루프
+
+## 📋 이슈 요약
+
+**증상:**
+- ULW (ultrawork) mode에서 PLAN AGENT가 무한루프에 빠짐
+- 분석/탐색 완료 후 plan만 계속 생성
+- 1분마다 매우 작은 토큰으로 요청 발생
+
+**예상 동작:**
+- 탐색 완료 후 solution document 생성
+
+---
+
+## 🔍 근본 원인 분석
+
+### 파일: `src/tools/delegate-task/constants.ts`
+
+#### 문제의 핵심
+
+`PLAN_AGENT_SYSTEM_PREPEND` (constants.ts 234-269행)에 구조적 결함이 있었습니다:
+
+1. **Interactive Mode 가정**
+   ```
+   2. After gathering context, ALWAYS present:
+      - Uncertainties: List of unclear points
+      - Clarifying Questions: Specific questions to resolve uncertainties
+   
+   3. ITERATE until ALL requirements are crystal clear:
+      - Do NOT proceed to planning until you have 100% clarity
+      - Ask the user to confirm your understanding
+   ```
+
+2. **종료 조건 없음**
+   - "100% clarity" 요구는 객관적 측정 불가능
+   - 사용자 확인 요청은 ULW mode에서 불가능
+   - 무한루프로 이어짐
+
+3. **ULW Mode 미감지**
+   - Subagent로 실행되는 경우를 구분하지 않음
+   - 항상 interactive mode로 동작 시도
+
+### 왜 무한루프가 발생했는가?
+
+```
+ULW Mode 시작
+  → Sisyphus가 Plan Agent 호출 (subagent)
+    → Plan Agent: "100% clarity 필요"
+      → Clarifying questions 생성
+        → 사용자 없음 (subagent)
+          → 다시 plan 생성 시도
+            → "여전히 unclear"
+              → 무한루프 반복
+```
+
+**핵심:** Plan Agent는 사용자와 대화하도록 설계되었지만, ULW mode에서는 사용자가 없는 subagent로 실행됨.
+
+---
+
+## ✅ 적용된 수정 방안
+
+### 수정 내용 (constants.ts)
+
+#### 1. SUBAGENT MODE DETECTION 섹션 추가
+
+```typescript
+SUBAGENT MODE DETECTION (CRITICAL):
+If you received a detailed prompt with gathered context from a parent orchestrator (e.g., Sisyphus):
+- You are running as a SUBAGENT
+- You CANNOT directly interact with the user
+- DO NOT ask clarifying questions - proceed with available information
+- Make reasonable assumptions for minor ambiguities
+- Generate the plan based on the provided context
+```
+
+#### 2. Context Gathering Protocol 수정
+
+```diff
+- 1. Launch background agents to gather context:
++ 1. Launch background agents to gather context (ONLY if not already provided):
+```
+
+**효과:** 이미 Sisyphus가 context를 수집한 경우 중복 방지
+
+#### 3. Clarifying Questions → Assumptions
+
+```diff
+- 2. After gathering context, ALWAYS present:
+-    - Uncertainties: List of unclear points
+-    - Clarifying Questions: Specific questions
++ 2. After gathering context, assess clarity:
++    - User Request Summary: Concise restatement
++    - Assumptions Made: List any assumptions for unclear points
+```
+
+**효과:** 질문 대신 가정 사항 문서화
+
+#### 4. 무한루프 방지 - 명확한 종료 조건
+
+```diff
+- 3. ITERATE until ALL requirements are crystal clear:
+-    - Do NOT proceed to planning until you have 100% clarity
+-    - Ask the user to confirm your understanding
+-    - Resolve every ambiguity before generating the work plan
++ 3. PROCEED TO PLAN GENERATION when:
++    - Core objective is understood (even if some details are ambiguous)
++    - You have gathered context via explore/librarian (or context was provided)
++    - You can make reasonable assumptions for remaining ambiguities
++    
++    DO NOT loop indefinitely waiting for perfect clarity.
++    DOCUMENT assumptions in the plan so they can be validated during execution.
+```
+
+**효과:**
+- "100% clarity" 요구 제거
+- 객관적인 진입 조건 제공
+- 무한루프 명시적 금지
+- Assumptions를 plan에 문서화하여 실행 중 검증 가능
+
+#### 5. 철학 변경
+
+```diff
+- REMEMBER: Vague requirements lead to failed implementations.
++ REMEMBER: A plan with documented assumptions is better than no plan.
+```
+
+**효과:** Perfectionism → Pragmatism
+
+---
+
+## 🎯 해결 메커니즘
+
+### Before (무한루프)
+
+```
+Plan Agent 시작
+  ↓
+Context gathering
+  ↓
+Requirements 명확한가?
+  ↓ NO
+Clarifying questions 생성
+  ↓
+사용자 응답 대기 (없음)
+  ↓
+다시 plan 시도
+  ↓
+(무한 반복)
+```
+
+### After (정상 종료)
+
+```
+Plan Agent 시작
+  ↓
+Subagent mode 감지?
+  ↓ YES
+Context 이미 있음? → YES
+  ↓
+Core objective 이해? → YES
+  ↓
+Reasonable assumptions 가능? → YES
+  ↓
+Plan 생성 (assumptions 문서화)
+  ↓
+완료 ✓
+```
+
+---
+
+## 📊 영향 분석
+
+### 해결되는 문제
+
+1. **ULW mode 무한루프** ✓
+2. **Sisyphus에서 Plan Agent 호출 시 블로킹** ✓
+3. **작은 토큰 반복 요청** ✓
+4. **1분마다 재시도** ✓
+
+### 부작용 없음
+
+- Interactive mode (사용자와 직접 대화)는 여전히 작동
+- Subagent mode일 때만 다르게 동작
+- Backward compatibility 유지
+
+### 추가 개선사항
+
+- Assumptions를 plan에 명시적으로 문서화
+- Execution 중 validation 가능
+- 더 pragmatic한 workflow
+
+---
+
+## 🧪 검증 방법
+
+### 테스트 시나리오
+
+1. **ULW mode에서 Plan Agent 호출**
+   ```bash
+   oh-my-opencode run "Complex task requiring planning. ulw"
+   ```
+   - 예상: Plan 생성 후 정상 종료
+   - 확인: 무한루프 없음
+
+2. **Interactive mode (변경 없어야 함)**
+   ```bash
+   oh-my-opencode run --agent prometheus "Design X"
+   ```
+   - 예상: Clarifying questions 여전히 가능
+   - 확인: 사용자와 대화 가능
+
+3. **Subagent context 제공 케이스**
+   - 예상: Context gathering skip
+   - 확인: 중복 탐색 없음
+
+---
+
+## 📝 수정된 파일
+
+```
+src/tools/delegate-task/constants.ts
+```
+
+### Diff Summary
+
+```diff
+@@ -234,22 +234,32 @@ export const PLAN_AGENT_SYSTEM_PREPEND = `<system>
++SUBAGENT MODE DETECTION (CRITICAL):
++[subagent 감지 및 처리 로직]
++
+ MANDATORY CONTEXT GATHERING PROTOCOL:
+-1. Launch background agents to gather context:
++1. Launch background agents (ONLY if not already provided):
+
+-2. After gathering context, ALWAYS present:
+-   - Uncertainties
+-   - Clarifying Questions
++2. After gathering context, assess clarity:
++   - Assumptions Made
+
+-3. ITERATE until ALL requirements are crystal clear:
+-   - Do NOT proceed until 100% clarity
+-   - Ask user to confirm
++3. PROCEED TO PLAN GENERATION when:
++   - Core objective understood
++   - Context gathered
++   - Reasonable assumptions possible
++   
++   DO NOT loop indefinitely.
++   DOCUMENT assumptions.
+```
+
+---
+
+## 🚀 권장 사항
+
+### Immediate Actions
+
+1. ✅ **수정 적용 완료** - constants.ts 업데이트됨
+2. ⏳ **테스트 수행** - ULW mode에서 동작 검증
+3. ⏳ **PR 생성** - code review 요청
+
+### Future Improvements
+
+1. **Subagent context 표준화**
+   - Subagent로 호출 시 명시적 플래그 전달
+   - `is_subagent: true` 파라미터 추가 고려
+
+2. **Assumptions validation workflow**
+   - Plan 실행 중 assumptions 검증 메커니즘
+   - Incorrect assumptions 감지 시 재계획
+
+3. **Timeout 메커니즘**
+   - Plan Agent가 X분 이상 걸리면 강제 종료
+   - Fallback plan 생성
+
+4. **Monitoring 추가**
+   - Plan Agent 실행 시간 측정
+   - Iteration 횟수 로깅
+   - 무한루프 조기 감지
+
+---
+
+## 📖 관련 코드 구조
+
+### Call Stack
+
+```
+Sisyphus (ULW mode)
+  ↓
+delegate_task(category="deep", ...)
+  ↓
+executor.ts: executeBackgroundContinuation()
+  ↓
+prompt-builder.ts: buildSystemContent()
+  ↓
+constants.ts: PLAN_AGENT_SYSTEM_PREPEND (문제 위치)
+  ↓
+Plan Agent 실행
+```
+
+### Key Functions
+
+1. **executor.ts:587** - `isPlanAgent()` 체크
+2. **prompt-builder.ts:11** - Plan Agent prepend 주입
+3. **constants.ts:234** - PLAN_AGENT_SYSTEM_PREPEND 정의
+
+---
+
+## 🎓 교훈
+
+### Design Lessons
+
+1. **Dual Mode Support**
+   - Interactive vs Autonomous mode 구분 필수
+   - Context 전달 방식 명확히
+
+2. **Avoid Perfectionism in Agents**
+   - "100% clarity" 같은 주관적 조건 지양
+   - 명확한 객관적 종료 조건 필요
+
+3. **Document Uncertainties**
+   - 불확실성을 숨기지 말고 문서화
+   - 실행 중 validation 가능하게
+
+4. **Infinite Loop Prevention**
+   - 모든 반복문에 명시적 종료 조건
+   - Timeout 또는 max iteration 설정
+
+---
+
+## 🔗 참고 자료
+
+- **Issue:** #1501 - [Bug]: ULW mode will 100% cause PLAN AGENT to get stuck
+- **Files Modified:** `src/tools/delegate-task/constants.ts`
+- **Related Concepts:** Ultrawork mode, Plan Agent, Subagent delegation
+- **Agent Architecture:** Sisyphus → Prometheus → Atlas workflow
+
+---
+
+## ✅ Conclusion
+
+**Root Cause:** Plan Agent가 interactive mode를 가정했으나 ULW mode에서는 subagent로 실행되어 사용자 상호작용 불가능. "100% clarity" 요구로 무한루프 발생.
+
+**Solution:** Subagent mode 감지 로직 추가, clarifying questions 제거, 명확한 종료 조건 제공, assumptions 문서화 방식 도입.
+
+**Result:** ULW mode에서 Plan Agent가 정상적으로 plan 생성 후 종료. 무한루프 해결.
+
+---
+
+**Status:** ✅ Fixed  
+**Tested:** ⏳ Pending  
+**Deployed:** ⏳ Pending  
+
+**Analyst:** Sisyphus (oh-my-opencode ultrawork mode)  
+**Date:** 2026-02-05  
+**Session:** fast-ember

package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "3.2.3",
+  "version": "3.2.4",
   "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": "3.2.3",
-    "oh-my-opencode-darwin-x64": "3.2.3",
-    "oh-my-opencode-linux-arm64": "3.2.3",
-    "oh-my-opencode-linux-arm64-musl": "3.2.3",
-    "oh-my-opencode-linux-x64": "3.2.3",
-    "oh-my-opencode-linux-x64-musl": "3.2.3",
-    "oh-my-opencode-windows-x64": "3.2.3"
+    "oh-my-opencode-darwin-arm64": "3.2.4",
+    "oh-my-opencode-darwin-x64": "3.2.4",
+    "oh-my-opencode-linux-arm64": "3.2.4",
+    "oh-my-opencode-linux-arm64-musl": "3.2.4",
+    "oh-my-opencode-linux-x64": "3.2.4",
+    "oh-my-opencode-linux-x64-musl": "3.2.4",
+    "oh-my-opencode-windows-x64": "3.2.4"
   },
   "trustedDependencies": [
     "@ast-grep/cli",

packages/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-arm64",
-  "version": "3.2.3",
+  "version": "3.2.4",
   "description": "Platform-specific binary for oh-my-opencode (darwin-arm64)",
   "license": "MIT",
   "repository": {

packages/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-x64",
-  "version": "3.2.3",
+  "version": "3.2.4",
   "description": "Platform-specific binary for oh-my-opencode (darwin-x64)",
   "license": "MIT",
   "repository": {

packages/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64-musl",
-  "version": "3.2.3",
+  "version": "3.2.4",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64",
-  "version": "3.2.3",
+  "version": "3.2.4",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64)",
   "license": "MIT",
   "repository": {

packages/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-musl",
-  "version": "3.2.3",
+  "version": "3.2.4",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64",
-  "version": "3.2.3",
+  "version": "3.2.4",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64)",
   "license": "MIT",
   "repository": {

packages/windows-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-windows-x64",
-  "version": "3.2.3",
+  "version": "3.2.4",
   "description": "Platform-specific binary for oh-my-opencode (windows-x64)",
   "license": "MIT",
   "repository": {

script/build-schema.ts

@@ -1,5 +1,6 @@
 #!/usr/bin/env bun
 import * as z from "zod"
+import { zodToJsonSchema } from "zod-to-json-schema"
 import { OhMyOpenCodeConfigSchema } from "../src/config/schema"
 
 const SCHEMA_OUTPUT_PATH = "assets/oh-my-opencode.schema.json"
@@ -7,9 +8,8 @@ const SCHEMA_OUTPUT_PATH = "assets/oh-my-opencode.schema.json"
 async function main() {
   console.log("Generating JSON Schema...")
 
-  const jsonSchema = z.toJSONSchema(OhMyOpenCodeConfigSchema, {
-    io: "input",
-    target: "draft-7",
+  const jsonSchema = zodToJsonSchema(OhMyOpenCodeConfigSchema, {
+    target: "draft7",
   })
 
   const finalSchema = {

signatures/cla.json

@@ -1183,6 +1183,30 @@
       "created_at": "2026-02-03T20:44:25Z",
       "repoId": 1108837393,
       "pullRequestNo": 1449
+    },
+    {
+      "name": "BowTiedSwan",
+      "id": 86532747,
+      "comment_id": 3742668781,
+      "created_at": "2026-01-13T08:05:00Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 741
+    },
+    {
+      "name": "Mang-Joo",
+      "id": 86056915,
+      "comment_id": 3855493558,
+      "created_at": "2026-02-05T18:41:49Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1526
+    },
+    {
+      "name": "shaunmorris",
+      "id": 579820,
+      "comment_id": 3858265174,
+      "created_at": "2026-02-06T06:23:24Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1541
     }
   ]
 }

sisyphus-prompt.md

@@ -7,7 +7,7 @@
 
 | Field | Value |
 |-------|-------|
-| Model | `anthropic/claude-opus-4-5` |
+| Model | `anthropic/claude-opus-4-6` |
 | Max Tokens | `64000` |
 | Mode | `primary` |
 | Thinking | Budget: 32000 |

src/agents/AGENTS.md

@@ -13,36 +13,50 @@
 ## STRUCTURE
 ```
 agents/
-├── atlas.ts                    # Master Orchestrator (holds todo list)
-├── sisyphus.ts                 # Main prompt (SF Bay Area engineer identity)
-├── hephaestus.ts               # Autonomous Deep Worker (GPT 5.2 Codex, "The Legitimate Craftsman")
-├── sisyphus-junior.ts          # Delegated task executor (category-spawned)
+├── 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
+│   ├── 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 (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 (GitHub CLI, Context7)
-├── explore.ts                  # Fast contextual grep (Grok Code Fast)
+├── librarian.ts                # Multi-repo research (328 lines)
+├── explore.ts                  # Fast contextual grep
 ├── multimodal-looker.ts        # Media analyzer (Gemini 3 Flash)
-├── prometheus-prompt.ts        # Planning (Interview/Consultant mode, 1283 lines)
-├── metis.ts                    # Pre-planning analysis (Gap detection)
-├── momus.ts                    # Plan reviewer (Ruthless fault-finding)
-├── dynamic-agent-prompt-builder.ts  # Dynamic prompt generation
+├── metis.ts                    # Pre-planning analysis (347 lines)
+├── momus.ts                    # Plan reviewer
+├── dynamic-agent-prompt-builder.ts  # Dynamic prompt generation (431 lines)
 ├── types.ts                    # AgentModelConfig, AgentPromptMetadata
-├── utils.ts                    # createBuiltinAgents(), resolveModelWithFallback()
+├── utils.ts                    # createBuiltinAgents(), resolveModelWithFallback() (485 lines)
 └── index.ts                    # builtinAgents export
 ```
 
 ## AGENT MODELS
 | Agent | Model | Temp | Purpose |
 |-------|-------|------|---------|
-| Sisyphus | anthropic/claude-opus-4-5 | 0.1 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro) |
-| Hephaestus | openai/gpt-5.2-codex | 0.1 | Autonomous deep worker, "The Legitimate Craftsman" (requires gpt-5.2-codex, no fallback) |
+| 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-4-5 | 0.1 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
-| Metis | anthropic/claude-opus-4-5 | 0.3 | Pre-planning analysis (fallback: kimi-k2.5 → gpt-5.2) |
-| Momus | openai/gpt-5.2 | 0.1 | Plan validation (fallback: claude-opus-4-5) |
+| 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
@@ -59,15 +73,17 @@ agents/
 | explore | write, edit, task, delegate_task, call_omo_agent |
 | multimodal-looker | Allowlist: read only |
 | Sisyphus-Junior | task, delegate_task |
+| Atlas | task, call_omo_agent |
 
 ## PATTERNS
 - **Factory**: `createXXXAgent(model: string): AgentConfig`
-- **Metadata**: `XXX_PROMPT_METADATA` with category, cost, triggers.
-- **Tool restrictions**: `createAgentToolRestrictions(tools)` or `createAgentToolAllowlist(tools)`.
-- **Thinking**: 32k budget tokens for Sisyphus, Oracle, Prometheus, Atlas.
+- **Metadata**: `XXX_PROMPT_METADATA` with category, cost, triggers
+- **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 reports**: NEVER trust "I'm done" - verify outputs.
-- **High temp**: Don't use >0.3 for code agents.
-- **Sequential calls**: Use `delegate_task` with `run_in_background` for exploration.
-- **Prometheus writing code**: Planner only - never implements.
+- **Trust reports**: NEVER trust "I'm done" - verify outputs
+- **High temp**: Don't use >0.3 for code agents
+- **Sequential calls**: Use `delegate_task` with `run_in_background` for exploration
+- **Prometheus writing code**: Planner only - never implements

src/agents/atlas/utils.ts

@@ -6,7 +6,7 @@
  */
 
 import type { CategoryConfig } from "../../config/schema"
-import type { AvailableAgent, AvailableSkill } from "../dynamic-agent-prompt-builder"
+import { formatCustomSkillsBlock, type AvailableAgent, type AvailableSkill } from "../dynamic-agent-prompt-builder"
 import { DEFAULT_CATEGORIES, CATEGORY_DESCRIPTIONS } from "../../tools/delegate-task/constants"
 
 export const getCategoryDescription = (name: string, userCategories?: Record<string, CategoryConfig>) =>
@@ -56,21 +56,48 @@ export function buildSkillsSection(skills: AvailableSkill[]): string {
     return ""
   }
 
-  const skillRows = skills.map((s) => {
+  const builtinSkills = skills.filter((s) => s.location === "plugin")
+  const customSkills = skills.filter((s) => s.location !== "plugin")
+
+  const builtinRows = builtinSkills.map((s) => {
     const shortDesc = s.description.split(".")[0] || s.description
     return `| \`${s.name}\` | ${shortDesc} |`
   })
 
+  const customRows = customSkills.map((s) => {
+    const shortDesc = s.description.split(".")[0] || s.description
+    const source = s.location === "project" ? "project" : "user"
+    return `| \`${s.name}\` | ${shortDesc} | ${source} |`
+  })
+
+  const customSkillBlock = formatCustomSkillsBlock(customRows, customSkills, "**")
+
+  let skillsTable: string
+
+  if (customSkills.length > 0 && builtinSkills.length > 0) {
+    skillsTable = `**Built-in Skills:**
+
+| Skill | When to Use |
+|-------|-------------|
+${builtinRows.join("\n")}
+
+${customSkillBlock}`
+  } else if (customSkills.length > 0) {
+    skillsTable = customSkillBlock
+  } else {
+    skillsTable = `| Skill | When to Use |
+|-------|-------------|
+${builtinRows.join("\n")}`
+  }
+
   return `
 #### 3.2.2: Skill Selection (PREPEND TO PROMPT)
 
 **Skills are specialized instructions that guide subagent behavior. Consider them alongside category selection.**
 
-| Skill | When to Use |
-|-------|-------------|
-${skillRows.join("\n")}
+${skillsTable}
 
-**MANDATORY: Evaluate ALL skills for relevance to your task.**
+**MANDATORY: Evaluate ALL skills (built-in AND user-installed) for relevance to your task.**
 
 Read each skill's description and ask: "Does this skill's domain overlap with my task?"
 - If YES: INCLUDE in load_skills=[...]

src/agents/dynamic-agent-prompt-builder.test.ts

@@ -0,0 +1,205 @@
+/// <reference types="bun-types" />
+
+import { describe, it, expect } from "bun:test"
+import {
+  buildCategorySkillsDelegationGuide,
+  buildUltraworkSection,
+  formatCustomSkillsBlock,
+  type AvailableSkill,
+  type AvailableCategory,
+  type AvailableAgent,
+} from "./dynamic-agent-prompt-builder"
+
+describe("buildCategorySkillsDelegationGuide", () => {
+  const categories: AvailableCategory[] = [
+    { name: "visual-engineering", description: "Frontend, UI/UX" },
+    { name: "quick", description: "Trivial tasks" },
+  ]
+
+  const builtinSkills: AvailableSkill[] = [
+    { name: "playwright", description: "Browser automation via Playwright", location: "plugin" },
+    { name: "frontend-ui-ux", description: "Designer-turned-developer", location: "plugin" },
+  ]
+
+  const customUserSkills: AvailableSkill[] = [
+    { name: "react-19", description: "React 19 patterns and best practices", location: "user" },
+    { name: "tailwind-4", description: "Tailwind CSS v4 utilities", location: "user" },
+  ]
+
+  const customProjectSkills: AvailableSkill[] = [
+    { name: "our-design-system", description: "Internal design system components", location: "project" },
+  ]
+
+  it("should separate builtin and custom skills into distinct sections", () => {
+    //#given: mix of builtin and custom skills
+    const allSkills = [...builtinSkills, ...customUserSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: should have separate sections
+    expect(result).toContain("Built-in Skills")
+    expect(result).toContain("User-Installed Skills")
+    expect(result).toContain("HIGH PRIORITY")
+  })
+
+  it("should include custom skill names in CRITICAL warning", () => {
+    //#given: custom skills installed
+    const allSkills = [...builtinSkills, ...customUserSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: should mention custom skills by name in the warning
+    expect(result).toContain('"react-19"')
+    expect(result).toContain('"tailwind-4"')
+    expect(result).toContain("CRITICAL")
+  })
+
+  it("should show source column for custom skills (user vs project)", () => {
+    //#given: both user and project custom skills
+    const allSkills = [...builtinSkills, ...customUserSkills, ...customProjectSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: should show source for each custom skill
+    expect(result).toContain("| user |")
+    expect(result).toContain("| project |")
+  })
+
+  it("should not show custom skill section when only builtin skills exist", () => {
+    //#given: only builtin skills
+    const allSkills = [...builtinSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: should not contain custom skill emphasis
+    expect(result).not.toContain("User-Installed Skills")
+    expect(result).not.toContain("HIGH PRIORITY")
+    expect(result).toContain("Available Skills")
+  })
+
+  it("should handle only custom skills (no builtins)", () => {
+    //#given: only custom skills, no builtins
+    const allSkills = [...customUserSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: should show custom skills with emphasis, no builtin section
+    expect(result).toContain("User-Installed Skills")
+    expect(result).toContain("HIGH PRIORITY")
+    expect(result).not.toContain("Built-in Skills")
+  })
+
+  it("should include priority note for custom skills in evaluation step", () => {
+    //#given: custom skills present
+    const allSkills = [...builtinSkills, ...customUserSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: evaluation section should mention user-installed priority
+    expect(result).toContain("User-installed skills get PRIORITY")
+    expect(result).toContain("INCLUDE it rather than omit it")
+  })
+
+  it("should NOT include priority note when no custom skills", () => {
+    //#given: only builtin skills
+    const allSkills = [...builtinSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: no priority note for custom skills
+    expect(result).not.toContain("User-installed skills get PRIORITY")
+  })
+
+  it("should return empty string when no categories and no skills", () => {
+    //#given: no categories and no skills
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide([], [])
+
+    //#then: should return empty string
+    expect(result).toBe("")
+  })
+})
+
+describe("buildUltraworkSection", () => {
+  const agents: AvailableAgent[] = []
+
+  it("should separate builtin and custom skills", () => {
+    //#given: mix of builtin and custom skills
+    const skills: AvailableSkill[] = [
+      { name: "playwright", description: "Browser automation", location: "plugin" },
+      { name: "react-19", description: "React 19 patterns", location: "user" },
+    ]
+
+    //#when: building ultrawork section
+    const result = buildUltraworkSection(agents, [], skills)
+
+    //#then: should have separate sections
+    expect(result).toContain("Built-in Skills")
+    expect(result).toContain("User-Installed Skills")
+    expect(result).toContain("HIGH PRIORITY")
+  })
+
+  it("should not separate when only builtin skills", () => {
+    //#given: only builtin skills
+    const skills: AvailableSkill[] = [
+      { name: "playwright", description: "Browser automation", location: "plugin" },
+    ]
+
+    //#when: building ultrawork section
+    const result = buildUltraworkSection(agents, [], skills)
+
+    //#then: should have single section
+    expect(result).toContain("Built-in Skills")
+    expect(result).not.toContain("User-Installed Skills")
+  })
+})
+
+describe("formatCustomSkillsBlock", () => {
+  const customSkills: AvailableSkill[] = [
+    { name: "react-19", description: "React 19 patterns", location: "user" },
+    { name: "tailwind-4", description: "Tailwind v4", location: "project" },
+  ]
+
+  const customRows = customSkills.map((s) => {
+    const source = s.location === "project" ? "project" : "user"
+    return `| \`${s.name}\` | ${s.description} | ${source} |`
+  })
+
+  it("should produce consistent output used by both builders", () => {
+    //#given: custom skills and rows
+    //#when: formatting with default header level
+    const result = formatCustomSkillsBlock(customRows, customSkills)
+
+    //#then: contains all expected elements
+    expect(result).toContain("User-Installed Skills (HIGH PRIORITY)")
+    expect(result).toContain("CRITICAL")
+    expect(result).toContain('"react-19"')
+    expect(result).toContain('"tailwind-4"')
+    expect(result).toContain("| user |")
+    expect(result).toContain("| project |")
+  })
+
+  it("should use #### header by default", () => {
+    //#given: default header level
+    const result = formatCustomSkillsBlock(customRows, customSkills)
+
+    //#then: uses markdown h4
+    expect(result).toContain("#### User-Installed Skills")
+  })
+
+  it("should use bold header when specified", () => {
+    //#given: bold header level (used by Atlas)
+    const result = formatCustomSkillsBlock(customRows, customSkills, "**")
+
+    //#then: uses bold instead of h4
+    expect(result).toContain("**User-Installed Skills (HIGH PRIORITY):**")
+    expect(result).not.toContain("#### User-Installed Skills")
+  })
+})

src/agents/dynamic-agent-prompt-builder.ts

@@ -20,6 +20,7 @@ export interface AvailableSkill {
 export interface AvailableCategory {
   name: string
   description: string
+  model?: string
 }
 
 export function categorizeTools(toolNames: string[]): AvailableTool[] {
@@ -166,6 +167,33 @@ export function buildDelegationTable(agents: AvailableAgent[]): string {
   return rows.join("\n")
 }
 
+/**
+ * Renders the "User-Installed Skills (HIGH PRIORITY)" block used across multiple agent prompts.
+ * Extracted to avoid duplication between buildCategorySkillsDelegationGuide, buildSkillsSection, etc.
+ */
+export function formatCustomSkillsBlock(
+  customRows: string[],
+  customSkills: AvailableSkill[],
+  headerLevel: "####" | "**" = "####"
+): string {
+  const customSkillNames = customSkills.map((s) => `"${s.name}"`).join(", ")
+  const header = headerLevel === "####"
+    ? `#### User-Installed Skills (HIGH PRIORITY)`
+    : `**User-Installed Skills (HIGH PRIORITY):**`
+
+  return `${header}
+
+**The user has installed these custom skills. They MUST be evaluated for EVERY delegation.**
+Subagents are STATELESS — they lose all custom knowledge unless you pass these skills via \`load_skills\`.
+
+| Skill | Expertise Domain | Source |
+|-------|------------------|--------|
+${customRows.join("\n")}
+
+> **CRITICAL**: Ignoring user-installed skills when they match the task domain is a failure.
+> The user installed ${customSkillNames} for a reason — USE THEM when the task overlaps with their domain.`
+}
+
 export function buildCategorySkillsDelegationGuide(categories: AvailableCategory[], skills: AvailableSkill[]): string {
   if (categories.length === 0 && skills.length === 0) return ""
 
@@ -174,11 +202,44 @@ export function buildCategorySkillsDelegationGuide(categories: AvailableCategory
     return `| \`${c.name}\` | ${desc} |`
   })
 
-  const skillRows = skills.map((s) => {
+  const builtinSkills = skills.filter((s) => s.location === "plugin")
+  const customSkills = skills.filter((s) => s.location !== "plugin")
+
+  const builtinRows = builtinSkills.map((s) => {
     const desc = s.description.split(".")[0] || s.description
     return `| \`${s.name}\` | ${desc} |`
   })
 
+  const customRows = customSkills.map((s) => {
+    const desc = s.description.split(".")[0] || s.description
+    const source = s.location === "project" ? "project" : "user"
+    return `| \`${s.name}\` | ${desc} | ${source} |`
+  })
+
+  const customSkillBlock = formatCustomSkillsBlock(customRows, customSkills)
+
+  let skillsSection: string
+
+  if (customSkills.length > 0 && builtinSkills.length > 0) {
+    skillsSection = `#### Built-in Skills
+
+| Skill | Expertise Domain |
+|-------|------------------|
+${builtinRows.join("\n")}
+
+${customSkillBlock}`
+  } else if (customSkills.length > 0) {
+    skillsSection = customSkillBlock
+  } else {
+    skillsSection = `#### Available Skills (Domain Expertise Injection)
+
+Skills inject specialized instructions into the subagent. Read the description to understand when each skill applies.
+
+| Skill | Expertise Domain |
+|-------|------------------|
+${builtinRows.join("\n")}`
+  }
+
   return `### Category + Skills Delegation System
 
 **delegate_task() combines categories and skills for optimal task execution.**
@@ -191,13 +252,7 @@ Each category is configured with a model optimized for that domain. Read the des
 |----------|-------------------|
 ${categoryRows.join("\n")}
 
-#### Available Skills (Domain Expertise Injection)
-
-Skills inject specialized instructions into the subagent. Read the description to understand when each skill applies.
-
-| Skill | Expertise Domain |
-|-------|------------------|
-${skillRows.join("\n")}
+${skillsSection}
 
 ---
 
@@ -208,12 +263,15 @@ ${skillRows.join("\n")}
 - Match task requirements to category domain
 - Select the category whose domain BEST fits the task
 
-**STEP 2: Evaluate ALL Skills**
+**STEP 2: Evaluate ALL Skills (Built-in AND User-Installed)**
 For EVERY skill listed above, ask yourself:
 > "Does this skill's expertise domain overlap with my task?"
 
 - If YES → INCLUDE in \`load_skills=[...]\`
 - If NO → You MUST justify why (see below)
+${customSkills.length > 0 ? `
+> **User-installed skills get PRIORITY.** The user explicitly installed them for their workflow.
+> When in doubt about a user-installed skill, INCLUDE it rather than omit it.` : ""}
 
 **STEP 3: Justify Omissions**
 
@@ -240,7 +298,7 @@ SKILL EVALUATION for "[skill-name]":
 \`\`\`typescript
 delegate_task(
   category="[selected-category]",
-  load_skills=["skill-1", "skill-2"],  // Include ALL relevant skills
+  load_skills=["skill-1", "skill-2"],  // Include ALL relevant skills — ESPECIALLY user-installed ones
   prompt="..."
 )
 \`\`\`
@@ -328,12 +386,26 @@ export function buildUltraworkSection(
   }
 
   if (skills.length > 0) {
-    lines.push("**Skills** (combine with categories - EVALUATE ALL for relevance):")
-    for (const skill of skills) {
-      const shortDesc = skill.description.split(".")[0] || skill.description
-      lines.push(`- \`${skill.name}\`: ${shortDesc}`)
+    const builtinSkills = skills.filter((s) => s.location === "plugin")
+    const customSkills = skills.filter((s) => s.location !== "plugin")
+
+    if (builtinSkills.length > 0) {
+      lines.push("**Built-in Skills** (combine with categories):")
+      for (const skill of builtinSkills) {
+        const shortDesc = skill.description.split(".")[0] || skill.description
+        lines.push(`- \`${skill.name}\`: ${shortDesc}`)
+      }
+      lines.push("")
+    }
+
+    if (customSkills.length > 0) {
+      lines.push("**User-Installed Skills** (HIGH PRIORITY - user installed these for their workflow):")
+      for (const skill of customSkills) {
+        const shortDesc = skill.description.split(".")[0] || skill.description
+        lines.push(`- \`${skill.name}\`: ${shortDesc}`)
+      }
+      lines.push("")
     }
-    lines.push("")
   }
 
   if (agents.length > 0) {

src/agents/hephaestus.ts

@@ -142,6 +142,19 @@ You operate as a **Senior Staff Engineer** with deep expertise in:
 
 You do not guess. You verify. You do not stop early. You complete.
 
+## Core Principle (HIGHEST PRIORITY)
+
+**KEEP GOING. SOLVE PROBLEMS. ASK ONLY WHEN TRULY IMPOSSIBLE.**
+
+When blocked:
+1. Try a different approach (there's always another way)
+2. Decompose the problem into smaller pieces
+3. Challenge your assumptions
+4. Explore how others solved similar problems
+
+Asking the user is the LAST resort after exhausting creative alternatives.
+Your job is to SOLVE problems, not report them.
+
 ## Hard Constraints (MUST READ FIRST - GPT 5.2 Constraint-First)
 
 ${hardBlocks}
@@ -404,6 +417,13 @@ Only terminate your turn when you are SURE the problem is SOLVED.
 Autonomously resolve the query to the BEST of your ability.
 Do NOT guess. Do NOT ask unnecessary questions. Do NOT stop early.
 
+**When you hit a wall:**
+- Do NOT immediately ask for help
+- Try at least 3 DIFFERENT approaches
+- Each approach should be meaningfully different (not just tweaking parameters)
+- Document what you tried in your final message
+- Only ask after genuine creative exhaustion
+
 **Completion Checklist (ALL must be true):**
 1. User asked for X → X is FULLY implemented (not partial, not "basic version")
 2. X passes lsp_diagnostics (zero errors on ALL modified files)
@@ -459,9 +479,9 @@ Do NOT guess. Do NOT ask unnecessary questions. Do NOT stop early.
 - Each update must include concrete outcome ("Found X", "Updated Y")
 
 **Scope:**
-- Implement EXACTLY what user requests
-- No extra features, no embellishments
-- Simplest valid interpretation for ambiguous instructions
+- Implement what user requests
+- When blocked, autonomously try alternative approaches before asking
+- No unnecessary features, but solve blockers creatively
 </output_contract>
 
 ## Response Compaction (LONG CONTEXT HANDLING)
@@ -545,21 +565,27 @@ When working on long sessions or complex multi-file tasks:
 2. Re-verify after EVERY fix attempt
 3. Never shotgun debug
 
-### After 3 Consecutive Failures
+### After Failure (AUTONOMOUS RECOVERY)
+
+1. **Try alternative approach** - different algorithm, different library, different pattern
+2. **Decompose** - break into smaller, independently solvable steps
+3. **Challenge assumptions** - what if your initial interpretation was wrong?
+4. **Explore more** - fire explore/librarian agents for similar problems solved elsewhere
+
+### After 3 DIFFERENT Approaches Fail
 
 1. **STOP** all edits
 2. **REVERT** to last working state
-3. **DOCUMENT** what failed
+3. **DOCUMENT** what you tried (all 3 approaches)
 4. **CONSULT** Oracle with full context
-5. If unresolved, **ASK USER**
+5. If Oracle cannot help, **ASK USER** with clear explanation of attempts
 
 **Never**: Leave code broken, delete failing tests, continue hoping
 
 ## Soft Guidelines
 
 - Prefer existing libraries over new dependencies
-- Prefer small, focused changes over large refactors
-- When uncertain about scope, ask`
+- Prefer small, focused changes over large refactors`
 }
 
 export function createHephaestusAgent(

src/agents/utils.test.ts

@@ -6,14 +6,14 @@ import * as connectedProvidersCache from "../shared/connected-providers-cache"
 import * as modelAvailability from "../shared/model-availability"
 import * as shared from "../shared"
 
-const TEST_DEFAULT_MODEL = "anthropic/claude-opus-4-5"
+const TEST_DEFAULT_MODEL = "anthropic/claude-opus-4-6"
 
 describe("createBuiltinAgents with model overrides", () => {
   test("Sisyphus with default model has thinking config when all models available", async () => {
     // #given
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
       new Set([
-        "anthropic/claude-opus-4-5",
+        "anthropic/claude-opus-4-6",
         "kimi-for-coding/k2p5",
         "opencode/kimi-k2.5-free",
         "zai-coding-plan/glm-4.7",
@@ -26,7 +26,7 @@ describe("createBuiltinAgents with model overrides", () => {
       const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], {})
 
       // #then
-      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
+      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-6")
       expect(agents.sisyphus.thinking).toEqual({ type: "enabled", budgetTokens: 32000 })
       expect(agents.sisyphus.reasoningEffort).toBeUndefined()
     } finally {
@@ -81,7 +81,7 @@ describe("createBuiltinAgents with model overrides", () => {
 
   test("Sisyphus is created on first run when no availableModels or cache exist", async () => {
     // #given
-    const systemDefaultModel = "anthropic/claude-opus-4-5"
+    const systemDefaultModel = "anthropic/claude-opus-4-6"
     const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(new Set())
 
@@ -91,7 +91,7 @@ describe("createBuiltinAgents with model overrides", () => {
 
       // #then
       expect(agents.sisyphus).toBeDefined()
-      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
+      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-6")
     } finally {
       cacheSpy.mockRestore()
       fetchSpy.mockRestore()
@@ -218,7 +218,7 @@ describe("createBuiltinAgents without systemDefaultModel", () => {
     ])
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
       new Set([
-        "anthropic/claude-opus-4-5",
+        "anthropic/claude-opus-4-6",
         "kimi-for-coding/k2p5",
         "opencode/kimi-k2.5-free",
         "zai-coding-plan/glm-4.7",
@@ -232,7 +232,7 @@ describe("createBuiltinAgents without systemDefaultModel", () => {
 
       // #then
       expect(agents.sisyphus).toBeDefined()
-      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
+      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-6")
     } finally {
       cacheSpy.mockRestore()
       fetchSpy.mockRestore()
@@ -240,12 +240,13 @@ describe("createBuiltinAgents without systemDefaultModel", () => {
   })
 })
 
-describe("createBuiltinAgents with requiresModel gating", () => {
-  test("hephaestus is not created when gpt-5.2-codex is unavailable", async () => {
-    // #given
+describe("createBuiltinAgents with requiresProvider gating (hephaestus)", () => {
+  test("hephaestus is not created when no required provider is connected", async () => {
+    // #given - only anthropic models available, not in hephaestus requiresProvider
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
-      new Set(["anthropic/claude-opus-4-5"])
+      new Set(["anthropic/claude-opus-4-6"])
     )
+    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["anthropic"])
 
     try {
       // #when
@@ -255,13 +256,48 @@ describe("createBuiltinAgents with requiresModel gating", () => {
       expect(agents.hephaestus).toBeUndefined()
     } finally {
       fetchSpy.mockRestore()
+      cacheSpy.mockRestore()
     }
   })
 
-  test("hephaestus is created when gpt-5.2-codex is available", async () => {
-    // #given
+  test("hephaestus is created when openai provider is connected", async () => {
+    // #given - openai provider has models available
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
-      new Set(["openai/gpt-5.2-codex"])
+      new Set(["openai/gpt-5.3-codex"])
+    )
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], {})
+
+      // #then
+      expect(agents.hephaestus).toBeDefined()
+    } finally {
+      fetchSpy.mockRestore()
+    }
+  })
+
+  test("hephaestus is created when github-copilot provider is connected", async () => {
+    // #given - github-copilot provider has models available
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set(["github-copilot/gpt-5.3-codex"])
+    )
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], {})
+
+      // #then
+      expect(agents.hephaestus).toBeDefined()
+    } finally {
+      fetchSpy.mockRestore()
+    }
+  })
+
+  test("hephaestus is created when opencode provider is connected", async () => {
+    // #given - opencode provider has models available
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set(["opencode/gpt-5.3-codex"])
     )
 
     try {
@@ -286,20 +322,20 @@ describe("createBuiltinAgents with requiresModel gating", () => {
 
       // #then
       expect(agents.hephaestus).toBeDefined()
-      expect(agents.hephaestus.model).toBe("openai/gpt-5.2-codex")
+      expect(agents.hephaestus.model).toBe("openai/gpt-5.3-codex")
     } finally {
       cacheSpy.mockRestore()
       fetchSpy.mockRestore()
     }
   })
 
-  test("hephaestus is created when explicit config provided even if model unavailable", async () => {
+  test("hephaestus is created when explicit config provided even if provider unavailable", async () => {
     // #given
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
-      new Set(["anthropic/claude-opus-4-5"])
+      new Set(["anthropic/claude-opus-4-6"])
     )
     const overrides = {
-      hephaestus: { model: "anthropic/claude-opus-4-5" },
+      hephaestus: { model: "anthropic/claude-opus-4-6" },
     }
 
     try {
@@ -318,7 +354,7 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
   test("sisyphus is created when at least one fallback model is available", async () => {
     // #given
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
-      new Set(["anthropic/claude-opus-4-5"])
+      new Set(["anthropic/claude-opus-4-6"])
     )
 
     try {
@@ -343,7 +379,7 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
 
       // #then
       expect(agents.sisyphus).toBeDefined()
-      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
+      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-6")
     } finally {
       cacheSpy.mockRestore()
       fetchSpy.mockRestore()
@@ -354,7 +390,7 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
     // #given
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(new Set())
     const overrides = {
-      sisyphus: { model: "anthropic/claude-opus-4-5" },
+      sisyphus: { model: "anthropic/claude-opus-4-6" },
     }
 
     try {
@@ -368,11 +404,12 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
     }
   })
 
-  test("sisyphus is not created when no fallback model is available (unrelated model only)", async () => {
+  test("sisyphus is not created when no fallback model is available and provider not connected", async () => {
     // #given - only openai/gpt-5.2 available, not in sisyphus fallback chain
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
       new Set(["openai/gpt-5.2"])
     )
+    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue([])
 
     try {
       // #when
@@ -382,13 +419,14 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
       expect(agents.sisyphus).toBeUndefined()
     } finally {
       fetchSpy.mockRestore()
+      cacheSpy.mockRestore()
     }
   })
 })
 
 describe("buildAgent with category and skills", () => {
   const { buildAgent } = require("./utils")
-  const TEST_MODEL = "anthropic/claude-opus-4-5"
+  const TEST_MODEL = "anthropic/claude-opus-4-6"
 
   beforeEach(() => {
     clearSkillCache()
@@ -534,7 +572,7 @@ describe("buildAgent with category and skills", () => {
     const agent = buildAgent(source["test-agent"], TEST_MODEL)
 
     // #then - category's built-in model and skills are applied
-    expect(agent.model).toBe("openai/gpt-5.2-codex")
+    expect(agent.model).toBe("openai/gpt-5.3-codex")
     expect(agent.variant).toBe("xhigh")
     expect(agent.prompt).toContain("Role: Designer-Turned-Developer")
     expect(agent.prompt).toContain("Task description")
@@ -647,9 +685,9 @@ describe("override.category expansion in createBuiltinAgents", () => {
     // #when
     const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
 
-    // #then - ultrabrain category: model=openai/gpt-5.2-codex, variant=xhigh
+    // #then - ultrabrain category: model=openai/gpt-5.3-codex, variant=xhigh
     expect(agents.oracle).toBeDefined()
-    expect(agents.oracle.model).toBe("openai/gpt-5.2-codex")
+    expect(agents.oracle.model).toBe("openai/gpt-5.3-codex")
     expect(agents.oracle.variant).toBe("xhigh")
   })
 
@@ -716,9 +754,9 @@ describe("override.category expansion in createBuiltinAgents", () => {
     // #when
     const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
 
-    // #then - ultrabrain category: model=openai/gpt-5.2-codex, variant=xhigh
+    // #then - ultrabrain category: model=openai/gpt-5.3-codex, variant=xhigh
     expect(agents.sisyphus).toBeDefined()
-    expect(agents.sisyphus.model).toBe("openai/gpt-5.2-codex")
+    expect(agents.sisyphus.model).toBe("openai/gpt-5.3-codex")
     expect(agents.sisyphus.variant).toBe("xhigh")
   })
 
@@ -731,9 +769,9 @@ describe("override.category expansion in createBuiltinAgents", () => {
     // #when
     const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
 
-    // #then - ultrabrain category: model=openai/gpt-5.2-codex, variant=xhigh
+    // #then - ultrabrain category: model=openai/gpt-5.3-codex, variant=xhigh
     expect(agents.atlas).toBeDefined()
-    expect(agents.atlas.model).toBe("openai/gpt-5.2-codex")
+    expect(agents.atlas.model).toBe("openai/gpt-5.3-codex")
     expect(agents.atlas.variant).toBe("xhigh")
   })
 

src/agents/utils.ts

@@ -11,7 +11,7 @@ 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, migrateAgentConfig } from "../shared"
+import { deepMerge, fetchAvailableModels, resolveModelPipeline, AGENT_MODEL_REQUIREMENTS, readConnectedProvidersCache, isModelAvailable, isAnyFallbackModelAvailable, isAnyProviderConnected, migrateAgentConfig } 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"
@@ -394,13 +394,13 @@ export async function createBuiltinAgents(
     const hephaestusRequirement = AGENT_MODEL_REQUIREMENTS["hephaestus"]
     const hasHephaestusExplicitConfig = hephaestusOverride !== undefined
 
-    const hasRequiredModel =
-      !hephaestusRequirement?.requiresModel ||
+    const hasRequiredProvider =
+      !hephaestusRequirement?.requiresProvider ||
       hasHephaestusExplicitConfig ||
       isFirstRunNoCache ||
-      (availableModels.size > 0 && isModelAvailable(hephaestusRequirement.requiresModel, availableModels))
+      isAnyProviderConnected(hephaestusRequirement.requiresProvider, availableModels)
 
-    if (hasRequiredModel) {
+    if (hasRequiredProvider) {
       let hephaestusResolution = applyModelResolution({
         userModel: hephaestusOverride?.model,
         requirement: hephaestusRequirement,

src/cli/AGENTS.md

@@ -2,25 +2,25 @@
 
 ## OVERVIEW
 
-CLI entry: `bunx oh-my-opencode`. 4 commands with Commander.js + @clack/prompts TUI.
+CLI entry: `bunx oh-my-opencode`. 5 commands with Commander.js + @clack/prompts TUI.
 
-**Commands**: install (interactive setup), doctor (14 health checks), run (session launcher), get-local-version
+**Commands**: install (interactive setup), doctor (14 health checks), run (session launcher), get-local-version, mcp-oauth
 
 ## STRUCTURE
 
 ```
 cli/
-├── index.ts              # Commander.js entry (4 commands)
+├── index.ts              # Commander.js entry (5 commands)
 ├── install.ts            # Interactive TUI (542 lines)
 ├── config-manager.ts     # JSONC parsing (667 lines)
-├── types.ts              # InstallArgs, InstallConfig
 ├── 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 (114 lines)
+│   ├── types.ts          # CheckResult, CheckDefinition
 │   └── checks/           # 14 checks, 23 files
 │       ├── version.ts    # OpenCode + plugin version
 │       ├── config.ts     # JSONC validity, Zod
@@ -28,10 +28,11 @@ cli/
 │       ├── dependencies.ts # AST-Grep, Comment Checker
 │       ├── lsp.ts        # LSP connectivity
 │       ├── mcp.ts        # MCP validation
-│       ├── model-resolution.ts # Model resolution check
+│       ├── model-resolution.ts # Model resolution check (323 lines)
 │       └── gh.ts         # GitHub CLI
 ├── run/
-│   └── index.ts          # Session launcher
+│   ├── index.ts          # Session launcher
+│   └── events.ts         # CLI run events (325 lines)
 ├── mcp-oauth/
 │   └── index.ts          # MCP OAuth flow
 └── get-local-version/
@@ -46,6 +47,7 @@ cli/
 | `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 CATEGORIES (14 Checks)
 

src/cli/__snapshots__/model-fallback.test.ts.snap

@@ -75,26 +75,26 @@ exports[`generateModelConfig single native provider uses Claude models when only
       "model": "anthropic/claude-sonnet-4-5",
     },
     "metis": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "momus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "multimodal-looker": {
       "model": "anthropic/claude-haiku-4-5",
     },
     "oracle": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "prometheus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
   },
@@ -103,7 +103,7 @@ exports[`generateModelConfig single native provider uses Claude models when only
       "model": "anthropic/claude-haiku-4-5",
     },
     "ultrabrain": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "unspecified-high": {
@@ -113,7 +113,7 @@ exports[`generateModelConfig single native provider uses Claude models when only
       "model": "anthropic/claude-sonnet-4-5",
     },
     "visual-engineering": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "writing": {
@@ -137,26 +137,26 @@ exports[`generateModelConfig single native provider uses Claude models with isMa
       "model": "anthropic/claude-sonnet-4-5",
     },
     "metis": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "momus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "multimodal-looker": {
       "model": "anthropic/claude-haiku-4-5",
     },
     "oracle": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "prometheus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
   },
@@ -165,18 +165,18 @@ exports[`generateModelConfig single native provider uses Claude models with isMa
       "model": "anthropic/claude-haiku-4-5",
     },
     "ultrabrain": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "unspecified-high": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "unspecified-low": {
       "model": "anthropic/claude-sonnet-4-5",
     },
     "visual-engineering": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "writing": {
@@ -197,7 +197,7 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
       "model": "opencode/gpt-5-nano",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
@@ -225,22 +225,22 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
   },
   "categories": {
     "deep": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "opencode/glm-4.7-free",
     },
     "ultrabrain": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "unspecified-low": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "visual-engineering": {
@@ -264,7 +264,7 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
       "model": "opencode/gpt-5-nano",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
@@ -292,14 +292,14 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
   },
   "categories": {
     "deep": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "opencode/glm-4.7-free",
     },
     "ultrabrain": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
@@ -307,7 +307,7 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
       "variant": "high",
     },
     "unspecified-low": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "visual-engineering": {
@@ -451,14 +451,14 @@ exports[`generateModelConfig all native providers uses preferred models from fal
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
       "model": "anthropic/claude-sonnet-4-5",
     },
     "metis": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "momus": {
@@ -473,11 +473,11 @@ exports[`generateModelConfig all native providers uses preferred models from fal
       "variant": "high",
     },
     "prometheus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
   },
@@ -487,14 +487,14 @@ exports[`generateModelConfig all native providers uses preferred models from fal
       "variant": "high",
     },
     "deep": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "anthropic/claude-haiku-4-5",
     },
     "ultrabrain": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
@@ -524,14 +524,14 @@ exports[`generateModelConfig all native providers uses preferred models with isM
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
       "model": "anthropic/claude-sonnet-4-5",
     },
     "metis": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "momus": {
@@ -546,11 +546,11 @@ exports[`generateModelConfig all native providers uses preferred models with isM
       "variant": "high",
     },
     "prometheus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
   },
@@ -560,18 +560,18 @@ exports[`generateModelConfig all native providers uses preferred models with isM
       "variant": "high",
     },
     "deep": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "anthropic/claude-haiku-4-5",
     },
     "ultrabrain": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "unspecified-low": {
@@ -598,14 +598,14 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
       "model": "opencode/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "opencode/gpt-5.2-codex",
+      "model": "opencode/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
       "model": "opencode/glm-4.7-free",
     },
     "metis": {
-      "model": "opencode/claude-opus-4-5",
+      "model": "opencode/claude-opus-4-6",
       "variant": "max",
     },
     "momus": {
@@ -620,11 +620,11 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
       "variant": "high",
     },
     "prometheus": {
-      "model": "opencode/claude-opus-4-5",
+      "model": "opencode/claude-opus-4-6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "opencode/claude-opus-4-5",
+      "model": "opencode/claude-opus-4-6",
       "variant": "max",
     },
   },
@@ -634,14 +634,14 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
       "variant": "high",
     },
     "deep": {
-      "model": "opencode/gpt-5.2-codex",
+      "model": "opencode/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "opencode/claude-haiku-4-5",
     },
     "ultrabrain": {
-      "model": "opencode/gpt-5.2-codex",
+      "model": "opencode/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
@@ -671,14 +671,14 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
       "model": "opencode/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "opencode/gpt-5.2-codex",
+      "model": "opencode/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
       "model": "opencode/glm-4.7-free",
     },
     "metis": {
-      "model": "opencode/claude-opus-4-5",
+      "model": "opencode/claude-opus-4-6",
       "variant": "max",
     },
     "momus": {
@@ -693,11 +693,11 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
       "variant": "high",
     },
     "prometheus": {
-      "model": "opencode/claude-opus-4-5",
+      "model": "opencode/claude-opus-4-6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "opencode/claude-opus-4-5",
+      "model": "opencode/claude-opus-4-6",
       "variant": "max",
     },
   },
@@ -707,18 +707,18 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
       "variant": "high",
     },
     "deep": {
-      "model": "opencode/gpt-5.2-codex",
+      "model": "opencode/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "opencode/claude-haiku-4-5",
     },
     "ultrabrain": {
-      "model": "opencode/gpt-5.2-codex",
+      "model": "opencode/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
-      "model": "opencode/claude-opus-4-5",
+      "model": "opencode/claude-opus-4-6",
       "variant": "max",
     },
     "unspecified-low": {
@@ -745,14 +745,14 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models when
       "model": "github-copilot/gpt-5-mini",
     },
     "hephaestus": {
-      "model": "github-copilot/gpt-5.2-codex",
+      "model": "github-copilot/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
       "model": "github-copilot/claude-sonnet-4.5",
     },
     "metis": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
     "momus": {
@@ -767,11 +767,11 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models when
       "variant": "high",
     },
     "prometheus": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
   },
@@ -781,14 +781,14 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models when
       "variant": "high",
     },
     "deep": {
-      "model": "github-copilot/gpt-5.2-codex",
+      "model": "github-copilot/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "github-copilot/claude-haiku-4.5",
     },
     "ultrabrain": {
-      "model": "github-copilot/gpt-5.2-codex",
+      "model": "github-copilot/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
@@ -818,14 +818,14 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models with
       "model": "github-copilot/gpt-5-mini",
     },
     "hephaestus": {
-      "model": "github-copilot/gpt-5.2-codex",
+      "model": "github-copilot/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
       "model": "github-copilot/claude-sonnet-4.5",
     },
     "metis": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
     "momus": {
@@ -840,11 +840,11 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models with
       "variant": "high",
     },
     "prometheus": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
   },
@@ -854,18 +854,18 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models with
       "variant": "high",
     },
     "deep": {
-      "model": "github-copilot/gpt-5.2-codex",
+      "model": "github-copilot/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "github-copilot/claude-haiku-4.5",
     },
     "ultrabrain": {
-      "model": "github-copilot/gpt-5.2-codex",
+      "model": "github-copilot/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
     "unspecified-low": {
@@ -1002,14 +1002,14 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "opencode/gpt-5.2-codex",
+      "model": "opencode/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
       "model": "opencode/glm-4.7-free",
     },
     "metis": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "momus": {
@@ -1024,11 +1024,11 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
       "variant": "high",
     },
     "prometheus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
   },
@@ -1038,14 +1038,14 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
       "variant": "high",
     },
     "deep": {
-      "model": "opencode/gpt-5.2-codex",
+      "model": "opencode/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "anthropic/claude-haiku-4-5",
     },
     "ultrabrain": {
-      "model": "opencode/gpt-5.2-codex",
+      "model": "opencode/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
@@ -1075,14 +1075,14 @@ exports[`generateModelConfig mixed provider scenarios uses OpenAI + Copilot comb
       "model": "github-copilot/gpt-5-mini",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
       "model": "github-copilot/claude-sonnet-4.5",
     },
     "metis": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
     "momus": {
@@ -1097,11 +1097,11 @@ exports[`generateModelConfig mixed provider scenarios uses OpenAI + Copilot comb
       "variant": "high",
     },
     "prometheus": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
   },
@@ -1111,14 +1111,14 @@ exports[`generateModelConfig mixed provider scenarios uses OpenAI + Copilot comb
       "variant": "high",
     },
     "deep": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "github-copilot/claude-haiku-4.5",
     },
     "ultrabrain": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
@@ -1151,26 +1151,26 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + ZAI combinat
       "model": "zai-coding-plan/glm-4.7",
     },
     "metis": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "momus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "multimodal-looker": {
       "model": "zai-coding-plan/glm-4.6v",
     },
     "oracle": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "prometheus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
   },
@@ -1179,7 +1179,7 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + ZAI combinat
       "model": "anthropic/claude-haiku-4-5",
     },
     "ultrabrain": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "unspecified-high": {
@@ -1189,7 +1189,7 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + ZAI combinat
       "model": "anthropic/claude-sonnet-4-5",
     },
     "visual-engineering": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "writing": {
@@ -1213,11 +1213,11 @@ exports[`generateModelConfig mixed provider scenarios uses Gemini + Claude combi
       "model": "anthropic/claude-sonnet-4-5",
     },
     "metis": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "momus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "multimodal-looker": {
@@ -1228,11 +1228,11 @@ exports[`generateModelConfig mixed provider scenarios uses Gemini + Claude combi
       "variant": "high",
     },
     "prometheus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
   },
@@ -1275,14 +1275,14 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
       "model": "opencode/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "github-copilot/gpt-5.2-codex",
+      "model": "github-copilot/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
       "model": "zai-coding-plan/glm-4.7",
     },
     "metis": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
     "momus": {
@@ -1297,11 +1297,11 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
       "variant": "high",
     },
     "prometheus": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "github-copilot/claude-opus-4.5",
+      "model": "github-copilot/claude-opus-4.6",
       "variant": "max",
     },
   },
@@ -1311,14 +1311,14 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
       "variant": "high",
     },
     "deep": {
-      "model": "github-copilot/gpt-5.2-codex",
+      "model": "github-copilot/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "github-copilot/claude-haiku-4.5",
     },
     "ultrabrain": {
-      "model": "github-copilot/gpt-5.2-codex",
+      "model": "github-copilot/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
@@ -1348,14 +1348,14 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
       "model": "zai-coding-plan/glm-4.7",
     },
     "metis": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "momus": {
@@ -1370,11 +1370,11 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
       "variant": "high",
     },
     "prometheus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
   },
@@ -1384,14 +1384,14 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
       "variant": "high",
     },
     "deep": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "anthropic/claude-haiku-4-5",
     },
     "ultrabrain": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
@@ -1421,14 +1421,14 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
       "model": "zai-coding-plan/glm-4.7",
     },
     "metis": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "momus": {
@@ -1443,11 +1443,11 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
       "variant": "high",
     },
     "prometheus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "sisyphus": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
   },
@@ -1457,18 +1457,18 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
       "variant": "high",
     },
     "deep": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "anthropic/claude-haiku-4-5",
     },
     "ultrabrain": {
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max",
     },
     "unspecified-low": {

src/cli/config-manager.test.ts

@@ -259,7 +259,7 @@ describe("generateOmoConfig - model fallback system", () => {
     // #then Sisyphus uses Claude (OR logic - at least one provider available)
     expect(result.$schema).toBe("https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json")
     expect(result.agents).toBeDefined()
-    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-5")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-6")
   })
 
   test("generates native opus models when Claude max20 subscription", () => {
@@ -279,7 +279,7 @@ describe("generateOmoConfig - model fallback system", () => {
     const result = generateOmoConfig(config)
 
     // #then Sisyphus uses Claude (OR logic - at least one provider available)
-    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-5")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-6")
   })
 
   test("uses github-copilot sonnet fallback when only copilot available", () => {
@@ -298,8 +298,8 @@ describe("generateOmoConfig - model fallback system", () => {
     // #when generating config
     const result = generateOmoConfig(config)
 
-    // #then Sisyphus uses Copilot (OR logic - copilot is in claude-opus-4-5 providers)
-    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("github-copilot/claude-opus-4.5")
+    // #then Sisyphus uses Copilot (OR logic - copilot is in claude-opus-4-6 providers)
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("github-copilot/claude-opus-4.6")
   })
 
   test("uses ultimate fallback when no providers configured", () => {
@@ -342,7 +342,7 @@ describe("generateOmoConfig - model fallback system", () => {
     // #then librarian should use zai-coding-plan/glm-4.7
     expect((result.agents as Record<string, { model: string }>).librarian.model).toBe("zai-coding-plan/glm-4.7")
     // #then Sisyphus uses Claude (OR logic)
-    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-5")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-6")
   })
 
   test("uses native OpenAI models when only ChatGPT available", () => {

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

@@ -14,9 +14,8 @@ describe("model-resolution check", () => {
       // then: Should have agent entries
       const sisyphus = info.agents.find((a) => a.name === "sisyphus")
       expect(sisyphus).toBeDefined()
-      expect(sisyphus!.requirement.fallbackChain[0]?.model).toBe("claude-opus-4-5")
+      expect(sisyphus!.requirement.fallbackChain[0]?.model).toBe("claude-opus-4-6")
       expect(sisyphus!.requirement.fallbackChain[0]?.providers).toContain("anthropic")
-      expect(sisyphus!.requirement.fallbackChain[0]?.providers).toContain("github-copilot")
     })
 
     it("returns category requirements with provider chains", async () => {
@@ -43,7 +42,7 @@ describe("model-resolution check", () => {
       // given: User has override for oracle agent
       const mockConfig = {
         agents: {
-          oracle: { model: "anthropic/claude-opus-4-5" },
+          oracle: { model: "anthropic/claude-opus-4-6" },
         },
       }
 
@@ -52,8 +51,8 @@ describe("model-resolution check", () => {
       // then: Oracle should show the override
       const oracle = info.agents.find((a) => a.name === "oracle")
       expect(oracle).toBeDefined()
-      expect(oracle!.userOverride).toBe("anthropic/claude-opus-4-5")
-      expect(oracle!.effectiveResolution).toBe("User override: anthropic/claude-opus-4-5")
+      expect(oracle!.userOverride).toBe("anthropic/claude-opus-4-6")
+      expect(oracle!.effectiveResolution).toBe("User override: anthropic/claude-opus-4-6")
     })
 
     it("shows user override for category when configured", async () => {
@@ -90,6 +89,46 @@ describe("model-resolution check", () => {
       expect(sisyphus!.effectiveResolution).toContain("Provider fallback:")
       expect(sisyphus!.effectiveResolution).toContain("anthropic")
     })
+
+    it("captures user variant for agent when configured", async () => {
+      const { getModelResolutionInfoWithOverrides } = await import("./model-resolution")
+
+      //#given User has model with variant override for oracle agent
+      const mockConfig = {
+        agents: {
+          oracle: { model: "openai/gpt-5.2", variant: "xhigh" },
+        },
+      }
+
+      //#when getting resolution info with config
+      const info = getModelResolutionInfoWithOverrides(mockConfig)
+
+      //#then Oracle should have userVariant set
+      const oracle = info.agents.find((a) => a.name === "oracle")
+      expect(oracle).toBeDefined()
+      expect(oracle!.userOverride).toBe("openai/gpt-5.2")
+      expect(oracle!.userVariant).toBe("xhigh")
+    })
+
+    it("captures user variant for category when configured", async () => {
+      const { getModelResolutionInfoWithOverrides } = await import("./model-resolution")
+
+      //#given User has model with variant override for visual-engineering category
+      const mockConfig = {
+        categories: {
+          "visual-engineering": { model: "google/gemini-3-flash-preview", variant: "high" },
+        },
+      }
+
+      //#when getting resolution info with config
+      const info = getModelResolutionInfoWithOverrides(mockConfig)
+
+      //#then visual-engineering should have userVariant set
+      const visual = info.categories.find((c) => c.name === "visual-engineering")
+      expect(visual).toBeDefined()
+      expect(visual!.userOverride).toBe("google/gemini-3-flash-preview")
+      expect(visual!.userVariant).toBe("high")
+    })
   })
 
   describe("checkModelResolution", () => {

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

@@ -51,6 +51,7 @@ export interface AgentResolutionInfo {
   name: string
   requirement: ModelRequirement
   userOverride?: string
+  userVariant?: string
   effectiveModel: string
   effectiveResolution: string
 }
@@ -59,6 +60,7 @@ export interface CategoryResolutionInfo {
   name: string
   requirement: ModelRequirement
   userOverride?: string
+  userVariant?: string
   effectiveModel: string
   effectiveResolution: string
 }
@@ -152,10 +154,12 @@ export function getModelResolutionInfoWithOverrides(config: OmoConfig): ModelRes
   const agents: AgentResolutionInfo[] = Object.entries(AGENT_MODEL_REQUIREMENTS).map(
     ([name, requirement]) => {
       const userOverride = config.agents?.[name]?.model
+      const userVariant = config.agents?.[name]?.variant
       return {
         name,
         requirement,
         userOverride,
+        userVariant,
         effectiveModel: getEffectiveModel(requirement, userOverride),
         effectiveResolution: buildEffectiveResolution(requirement, userOverride),
       }
@@ -165,10 +169,12 @@ export function getModelResolutionInfoWithOverrides(config: OmoConfig): ModelRes
   const categories: CategoryResolutionInfo[] = Object.entries(CATEGORY_MODEL_REQUIREMENTS).map(
     ([name, requirement]) => {
       const userOverride = config.categories?.[name]?.model
+      const userVariant = config.categories?.[name]?.variant
       return {
         name,
         requirement,
         userOverride,
+        userVariant,
         effectiveModel: getEffectiveModel(requirement, userOverride),
         effectiveResolution: buildEffectiveResolution(requirement, userOverride),
       }

src/cli/index.ts

@@ -43,7 +43,7 @@ Model Providers (Priority: Native > Copilot > OpenCode Zen > Z.ai > Kimi):
   OpenAI        Native openai/ models (GPT-5.2 for Oracle)
   Gemini        Native google/ models (Gemini 3 Pro, Flash)
   Copilot       github-copilot/ models (fallback)
-  OpenCode Zen  opencode/ models (opencode/claude-opus-4-5, etc.)
+  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)
 `)

src/cli/install.ts

@@ -243,7 +243,7 @@ async function runTuiMode(detected: DetectedConfig): Promise<InstallConfig | nul
     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-4-5, opencode/gpt-5.2, etc." },
+      { value: "yes" as const, label: "Yes", hint: "opencode/claude-opus-4-6, opencode/gpt-5.2, etc." },
     ],
     initialValue: initial.opencodeZen,
   })

src/cli/model-fallback.test.ts

@@ -376,7 +376,7 @@ describe("generateModelConfig", () => {
       const result = generateModelConfig(config)
 
       // #then
-      expect(result.agents?.sisyphus?.model).toBe("anthropic/claude-opus-4-5")
+      expect(result.agents?.sisyphus?.model).toBe("anthropic/claude-opus-4-6")
     })
 
     test("Sisyphus is created when multiple fallback providers are available", () => {
@@ -393,7 +393,7 @@ describe("generateModelConfig", () => {
       const result = generateModelConfig(config)
 
       // #then
-      expect(result.agents?.sisyphus?.model).toBe("anthropic/claude-opus-4-5")
+      expect(result.agents?.sisyphus?.model).toBe("anthropic/claude-opus-4-6")
     })
 
     test("Sisyphus is omitted when no fallback provider is available (OpenAI not in chain)", () => {
@@ -409,7 +409,7 @@ describe("generateModelConfig", () => {
   })
 
   describe("Hephaestus agent special cases", () => {
-    test("Hephaestus is created when OpenAI is available (has gpt-5.2-codex)", () => {
+    test("Hephaestus is created when OpenAI is available (openai provider connected)", () => {
       // #given
       const config = createConfig({ hasOpenAI: true })
 
@@ -417,11 +417,11 @@ describe("generateModelConfig", () => {
       const result = generateModelConfig(config)
 
       // #then
-      expect(result.agents?.hephaestus?.model).toBe("openai/gpt-5.2-codex")
+      expect(result.agents?.hephaestus?.model).toBe("openai/gpt-5.3-codex")
       expect(result.agents?.hephaestus?.variant).toBe("medium")
     })
 
-    test("Hephaestus is created when Copilot is available (has gpt-5.2-codex)", () => {
+    test("Hephaestus is created when Copilot is available (github-copilot provider connected)", () => {
       // #given
       const config = createConfig({ hasCopilot: true })
 
@@ -429,11 +429,11 @@ describe("generateModelConfig", () => {
       const result = generateModelConfig(config)
 
       // #then
-      expect(result.agents?.hephaestus?.model).toBe("github-copilot/gpt-5.2-codex")
+      expect(result.agents?.hephaestus?.model).toBe("github-copilot/gpt-5.3-codex")
       expect(result.agents?.hephaestus?.variant).toBe("medium")
     })
 
-    test("Hephaestus is created when OpenCode Zen is available (has gpt-5.2-codex)", () => {
+    test("Hephaestus is created when OpenCode Zen is available (opencode provider connected)", () => {
       // #given
       const config = createConfig({ hasOpencodeZen: true })
 
@@ -441,11 +441,11 @@ describe("generateModelConfig", () => {
       const result = generateModelConfig(config)
 
       // #then
-      expect(result.agents?.hephaestus?.model).toBe("opencode/gpt-5.2-codex")
+      expect(result.agents?.hephaestus?.model).toBe("opencode/gpt-5.3-codex")
       expect(result.agents?.hephaestus?.variant).toBe("medium")
     })
 
-    test("Hephaestus is omitted when only Claude is available (no gpt-5.2-codex)", () => {
+    test("Hephaestus is omitted when only Claude is available (no required provider connected)", () => {
       // #given
       const config = createConfig({ hasClaude: true })
 
@@ -456,7 +456,7 @@ describe("generateModelConfig", () => {
       expect(result.agents?.hephaestus).toBeUndefined()
     })
 
-    test("Hephaestus is omitted when only Gemini is available (no gpt-5.2-codex)", () => {
+    test("Hephaestus is omitted when only Gemini is available (no required provider connected)", () => {
       // #given
       const config = createConfig({ hasGemini: true })
 
@@ -467,7 +467,7 @@ describe("generateModelConfig", () => {
       expect(result.agents?.hephaestus).toBeUndefined()
     })
 
-    test("Hephaestus is omitted when only ZAI is available (no gpt-5.2-codex)", () => {
+    test("Hephaestus is omitted when only ZAI is available (no required provider connected)", () => {
       // #given
       const config = createConfig({ hasZaiCodingPlan: true })
 

src/cli/model-fallback.ts

@@ -71,7 +71,7 @@ function isProviderAvailable(provider: string, avail: ProviderAvailability): boo
 function transformModelForProvider(provider: string, model: string): string {
   if (provider === "github-copilot") {
     return model
-      .replace("claude-opus-4-5", "claude-opus-4.5")
+      .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")
@@ -122,6 +122,13 @@ function isRequiredModelAvailable(
   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)
   const hasAnyProvider =
@@ -185,6 +192,9 @@ export function generateModelConfig(config: InstallConfig): GeneratedOmoConfig {
     if (req.requiresModel && !isRequiredModelAvailable(req.requiresModel, req.fallbackChain, avail)) {
       continue
     }
+    if (req.requiresProvider && !isRequiredProviderAvailable(req.requiresProvider, avail)) {
+      continue
+    }
 
     const resolved = resolveModelFromChain(req.fallbackChain, avail)
     if (resolved) {
@@ -205,6 +215,9 @@ export function generateModelConfig(config: InstallConfig): GeneratedOmoConfig {
     if (req.requiresModel && !isRequiredModelAvailable(req.requiresModel, req.fallbackChain, avail)) {
       continue
     }
+    if (req.requiresProvider && !isRequiredProviderAvailable(req.requiresProvider, avail)) {
+      continue
+    }
 
     const resolved = resolveModelFromChain(fallbackChain, avail)
     if (resolved) {

src/cli/run/runner.ts

@@ -5,6 +5,7 @@ import { checkCompletionConditions } from "./completion"
 import { createEventState, processEvents, serializeError } from "./events"
 import type { OhMyOpenCodeConfig } from "../../config"
 import { loadPluginConfig } from "../../plugin-config"
+import { getAvailableServerPort, DEFAULT_SERVER_PORT } from "../../shared/port-utils"
 
 const POLL_INTERVAL_MS = 500
 const DEFAULT_TIMEOUT_MS = 0
@@ -89,7 +90,7 @@ export async function run(options: RunOptions): Promise<number> {
   const pluginConfig = loadPluginConfig(directory, { command: "run" })
   const resolvedAgent = resolveRunAgent(options, pluginConfig)
 
-  console.log(pc.cyan("Starting opencode server..."))
+  console.log(pc.cyan("Starting opencode server (auto port selection enabled)..."))
 
   const abortController = new AbortController()
   let timeoutId: ReturnType<typeof setTimeout> | null = null
@@ -103,18 +104,24 @@ export async function run(options: RunOptions): Promise<number> {
   }
 
   try {
-    // Support custom OpenCode server port via environment variable
-    // This allows Open Agent and other orchestrators to run multiple
-    // concurrent missions without port conflicts
-    const serverPort = process.env.OPENCODE_SERVER_PORT
+    const envPort = process.env.OPENCODE_SERVER_PORT
       ? parseInt(process.env.OPENCODE_SERVER_PORT, 10)
       : undefined
-    const serverHostname = process.env.OPENCODE_SERVER_HOSTNAME || undefined
+    const serverHostname = process.env.OPENCODE_SERVER_HOSTNAME || "127.0.0.1"
+    const preferredPort = envPort && !isNaN(envPort) ? envPort : DEFAULT_SERVER_PORT
+
+    const { port: serverPort, wasAutoSelected } = await getAvailableServerPort(preferredPort, serverHostname)
+
+    if (wasAutoSelected) {
+      console.log(pc.yellow(`Port ${preferredPort} is busy, using port ${serverPort} instead`))
+    } else {
+      console.log(pc.dim(`Using port ${serverPort}`))
+    }
 
     const { client, server } = await createOpencode({
       signal: abortController.signal,
-      ...(serverPort && !isNaN(serverPort) ? { port: serverPort } : {}),
-      ...(serverHostname ? { hostname: serverHostname } : {}),
+      port: serverPort,
+      hostname: serverHostname,
     })
 
     const cleanup = () => {

src/config/schema.ts

@@ -32,6 +32,7 @@ export const BuiltinAgentNameSchema = z.enum([
 export const BuiltinSkillNameSchema = z.enum([
   "playwright",
   "agent-browser",
+  "dev-browser",
   "frontend-ui-ux",
   "git-master",
 ])
@@ -63,10 +64,12 @@ export const HookNameSchema = z.enum([
   "comment-checker",
   "grep-output-truncator",
   "tool-output-truncator",
+  "question-label-truncator",
   "directory-agents-injector",
   "directory-readme-injector",
   "empty-task-response-detector",
   "think-mode",
+  "subagent-question-blocker",
   "anthropic-context-window-limit-recovery",
   "preemptive-compaction",
   "rules-injector",
@@ -92,13 +95,21 @@ export const HookNameSchema = z.enum([
   "start-work",
   "atlas",
   "unstable-agent-babysitter",
+  "task-reminder",
+  "task-resume-info",
   "stop-continuation-guard",
   "tasks-todowrite-disabler",
+  "write-existing-file-guard",
 ])
 
 export const BuiltinCommandNameSchema = z.enum([
   "init-deep",
+  "ralph-loop",
+  "ulw-loop",
+  "cancel-ralph",
+  "refactor",
   "start-work",
+  "stop-continuation",
 ])
 
 export const AgentOverrideConfigSchema = z.object({
@@ -368,8 +379,10 @@ export const TmuxConfigSchema = z.object({
 })
 
 export const SisyphusTasksConfigSchema = z.object({
-  /** Storage path for tasks (default: .sisyphus/tasks) */
-  storage_path: z.string().default(".sisyphus/tasks"),
+  /** Absolute or relative storage path override. When set, bypasses global config dir. */
+  storage_path: z.string().optional(),
+  /** Force task list ID (alternative to env ULTRAWORK_TASK_LIST_ID) */
+  task_list_id: z.string().optional(),
   /** Enable Claude Code path compatibility mode */
   claude_code_compat: z.boolean().default(false),
 })

src/features/AGENTS.md

@@ -2,7 +2,7 @@
 
 ## OVERVIEW
 
-20 feature modules: background agents, skill MCPs, builtin skills/commands, Claude Code compatibility layer.
+17 feature modules: background agents, skill MCPs, builtin skills/commands, Claude Code compatibility layer, task management.
 
 **Feature Types**: Task orchestration, Skill definitions, Command templates, Claude Code loaders, Supporting utilities
 
@@ -10,27 +10,25 @@
 
 ```
 features/
-├── background-agent/           # Task lifecycle (1418 lines)
+├── background-agent/           # Task lifecycle (1556 lines)
 │   ├── manager.ts              # Launch → poll → complete
 │   └── concurrency.ts          # Per-provider limits
-├── builtin-skills/             # Core skills (1729 lines)
-│   └── skills.ts               # playwright, dev-browser, frontend-ui-ux, git-master, typescript-programmer
+├── builtin-skills/             # Core skills
+│   └── skills/                 # playwright, agent-browser, frontend-ui-ux, git-master, dev-browser
 ├── builtin-commands/           # ralph-loop, refactor, ulw-loop, init-deep, start-work, cancel-ralph, stop-continuation
 ├── claude-code-agent-loader/   # ~/.claude/agents/*.md
 ├── claude-code-command-loader/ # ~/.claude/commands/*.md
 ├── claude-code-mcp-loader/     # .mcp.json with ${VAR} expansion
-├── claude-code-plugin-loader/  # installed_plugins.json
+├── claude-code-plugin-loader/  # installed_plugins.json (486 lines)
 ├── claude-code-session-state/  # Session persistence
-├── opencode-skill-loader/      # Skills from 6 directories
+├── opencode-skill-loader/      # Skills from 6 directories (loader.ts 311 lines)
 ├── context-injector/           # AGENTS.md/README.md injection
 ├── boulder-state/              # Todo state persistence
 ├── hook-message-injector/      # Message injection
 ├── task-toast-manager/         # Background task notifications
-├── skill-mcp-manager/          # MCP client lifecycle (617 lines)
-├── tmux-subagent/              # Tmux session management
+├── skill-mcp-manager/          # MCP client lifecycle (640 lines)
+├── tmux-subagent/              # Tmux session management (472 lines)
 ├── mcp-oauth/                  # MCP OAuth handling
-├── sisyphus-swarm/             # Swarm coordination
-├── sisyphus-tasks/             # Task tracking
 └── claude-tasks/               # Task schema/storage - see AGENTS.md
 ```
 

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

@@ -94,7 +94,7 @@ describe("ConcurrencyManager.getConcurrencyLimit", () => {
 
     // when
     const modelLimit = manager.getConcurrencyLimit("anthropic/claude-sonnet-4-5")
-    const providerLimit = manager.getConcurrencyLimit("anthropic/claude-opus-4-5")
+    const providerLimit = manager.getConcurrencyLimit("anthropic/claude-opus-4-6")
     const defaultLimit = manager.getConcurrencyLimit("google/gemini-3-pro")
 
     // then

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

@@ -783,7 +783,7 @@ describe("BackgroundManager.notifyParentSession - dynamic message lookup", () =>
     }
     const currentMessage: CurrentMessage = {
       agent: "sisyphus",
-      model: { providerID: "anthropic", modelID: "claude-opus-4-5" },
+      model: { providerID: "anthropic", modelID: "claude-opus-4-6" },
     }
 
     // when
@@ -791,7 +791,7 @@ describe("BackgroundManager.notifyParentSession - dynamic message lookup", () =>
 
     // then - uses currentMessage values, not task.parentModel/parentAgent
     expect(promptBody.agent).toBe("sisyphus")
-    expect(promptBody.model).toEqual({ providerID: "anthropic", modelID: "claude-opus-4-5" })
+    expect(promptBody.model).toEqual({ providerID: "anthropic", modelID: "claude-opus-4-6" })
   })
 
   test("should fallback to parentAgent when currentMessage.agent is undefined", async () => {
@@ -875,6 +875,90 @@ describe("BackgroundManager.notifyParentSession - dynamic message lookup", () =>
   })
 })
 
+describe("BackgroundManager.notifyParentSession - aborted parent", () => {
+  test("should skip notification when parent session is aborted", async () => {
+    //#given
+    let promptCalled = false
+    const client = {
+      session: {
+        prompt: async () => {
+          promptCalled = true
+          return {}
+        },
+        abort: async () => ({}),
+        messages: async () => {
+          const error = new Error("User aborted")
+          error.name = "MessageAbortedError"
+          throw error
+        },
+      },
+    }
+    const manager = new BackgroundManager({ client, directory: tmpdir() } as unknown as PluginInput)
+    const task: BackgroundTask = {
+      id: "task-aborted-parent",
+      sessionID: "session-child",
+      parentSessionID: "session-parent",
+      parentMessageID: "msg-parent",
+      description: "task aborted parent",
+      prompt: "test",
+      agent: "explore",
+      status: "completed",
+      startedAt: new Date(),
+      completedAt: new Date(),
+    }
+    getPendingByParent(manager).set("session-parent", new Set([task.id, "task-remaining"]))
+
+    //#when
+    await (manager as unknown as { notifyParentSession: (task: BackgroundTask) => Promise<void> })
+      .notifyParentSession(task)
+
+    //#then
+    expect(promptCalled).toBe(false)
+
+    manager.shutdown()
+  })
+
+  test("should swallow aborted error from prompt", async () => {
+    //#given
+    let promptCalled = false
+    const client = {
+      session: {
+        prompt: async () => {
+          promptCalled = true
+          const error = new Error("User aborted")
+          error.name = "MessageAbortedError"
+          throw error
+        },
+        abort: async () => ({}),
+        messages: async () => ({ data: [] }),
+      },
+    }
+    const manager = new BackgroundManager({ client, directory: tmpdir() } as unknown as PluginInput)
+    const task: BackgroundTask = {
+      id: "task-aborted-prompt",
+      sessionID: "session-child",
+      parentSessionID: "session-parent",
+      parentMessageID: "msg-parent",
+      description: "task aborted prompt",
+      prompt: "test",
+      agent: "explore",
+      status: "completed",
+      startedAt: new Date(),
+      completedAt: new Date(),
+    }
+    getPendingByParent(manager).set("session-parent", new Set([task.id]))
+
+    //#when
+    await (manager as unknown as { notifyParentSession: (task: BackgroundTask) => Promise<void> })
+      .notifyParentSession(task)
+
+    //#then
+    expect(promptCalled).toBe(true)
+
+    manager.shutdown()
+  })
+})
+
 function buildNotificationPromptBody(
   task: BackgroundTask,
   currentMessage: CurrentMessage | null
@@ -913,7 +997,7 @@ describe("BackgroundManager.tryCompleteTask", () => {
 
   test("should release concurrency and clear key on completion", async () => {
     // given
-    const concurrencyKey = "anthropic/claude-opus-4-5"
+    const concurrencyKey = "anthropic/claude-opus-4-6"
     const concurrencyManager = getConcurrencyManager(manager)
     await concurrencyManager.acquire(concurrencyKey)
 
@@ -942,7 +1026,7 @@ describe("BackgroundManager.tryCompleteTask", () => {
 
   test("should prevent double completion and double release", async () => {
     // given
-    const concurrencyKey = "anthropic/claude-opus-4-5"
+    const concurrencyKey = "anthropic/claude-opus-4-6"
     const concurrencyManager = getConcurrencyManager(manager)
     await concurrencyManager.acquire(concurrencyKey)
 
@@ -1573,7 +1657,7 @@ describe("BackgroundManager - Non-blocking Queue Integration", () => {
         description: "Task 1",
         prompt: "Do something",
         agent: "test-agent",
-        model: { providerID: "anthropic", modelID: "claude-opus-4-5" },
+        model: { providerID: "anthropic", modelID: "claude-opus-4-6" },
         parentSessionID: "parent-session",
         parentMessageID: "parent-message",
       }

src/features/background-agent/manager.ts

@@ -1123,7 +1123,14 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
           break
         }
       }
-    } catch {
+    } catch (error) {
+      if (this.isAbortedSessionError(error)) {
+        log("[background-agent] Parent session aborted, skipping notification:", {
+          taskId: task.id,
+          parentSessionID: task.parentSessionID,
+        })
+        return
+      }
       const messageDir = getMessageDir(task.parentSessionID)
       const currentMessage = messageDir ? findNearestMessageWithFields(messageDir) : null
       agent = currentMessage?.agent ?? task.parentAgent
@@ -1154,6 +1161,13 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
         noReply: !allComplete,
       })
     } catch (error) {
+      if (this.isAbortedSessionError(error)) {
+        log("[background-agent] Parent session aborted, skipping notification:", {
+          taskId: task.id,
+          parentSessionID: task.parentSessionID,
+        })
+        return
+      }
       log("[background-agent] Failed to send notification:", error)
     }
 
@@ -1192,6 +1206,28 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
     return `${seconds}s`
   }
 
+  private isAbortedSessionError(error: unknown): boolean {
+    const message = this.getErrorText(error)
+    return message.toLowerCase().includes("aborted")
+  }
+
+  private getErrorText(error: unknown): string {
+    if (!error) return ""
+    if (typeof error === "string") return error
+    if (error instanceof Error) {
+      return `${error.name}: ${error.message}`
+    }
+    if (typeof error === "object" && error !== null) {
+      if ("message" in error && typeof error.message === "string") {
+        return error.message
+      }
+      if ("name" in error && typeof error.name === "string") {
+        return error.name
+      }
+    }
+    return ""
+  }
+
   private hasRunningTasks(): boolean {
     for (const task of this.tasks.values()) {
       if (task.status === "running") return true

src/features/boulder-state/storage.test.ts

@@ -246,5 +246,33 @@ describe("boulder-state", () => {
       expect(state.plan_name).toBe("auth-refactor")
       expect(state.started_at).toBeDefined()
     })
+
+    test("should include agent field when provided", () => {
+      //#given - plan path, session id, and agent type
+      const planPath = "/path/to/feature.md"
+      const sessionId = "ses-xyz789"
+      const agent = "atlas"
+
+      //#when - createBoulderState is called with agent
+      const state = createBoulderState(planPath, sessionId, agent)
+
+      //#then - state should include the agent field
+      expect(state.agent).toBe("atlas")
+      expect(state.active_plan).toBe(planPath)
+      expect(state.session_ids).toEqual([sessionId])
+      expect(state.plan_name).toBe("feature")
+    })
+
+    test("should allow agent to be undefined", () => {
+      //#given - plan path and session id without agent
+      const planPath = "/path/to/legacy.md"
+      const sessionId = "ses-legacy"
+
+      //#when - createBoulderState is called without agent
+      const state = createBoulderState(planPath, sessionId)
+
+      //#then - state should not have agent field (backward compatible)
+      expect(state.agent).toBeUndefined()
+    })
   })
 })

src/features/boulder-state/storage.ts

@@ -139,12 +139,14 @@ export function getPlanName(planPath: string): string {
  */
 export function createBoulderState(
   planPath: string,
-  sessionId: string
+  sessionId: string,
+  agent?: string
 ): BoulderState {
   return {
     active_plan: planPath,
     started_at: new Date().toISOString(),
     session_ids: [sessionId],
     plan_name: getPlanName(planPath),
+    ...(agent !== undefined ? { agent } : {}),
   }
 }

src/features/boulder-state/types.ts

@@ -14,6 +14,8 @@ export interface BoulderState {
   session_ids: string[]
   /** Plan name derived from filename */
   plan_name: string
+  /** Agent type to use when resuming (e.g., 'atlas') */
+  agent?: string
 }
 
 export interface PlanProgress {

src/features/claude-tasks/AGENTS.md

@@ -12,6 +12,7 @@ claude-tasks/
 ├── types.test.ts     # Schema validation tests (8 tests)
 ├── storage.ts        # File operations
 ├── storage.test.ts   # Storage tests (14 tests)
+├── todo-sync.ts      # Task → Todo synchronization
 └── index.ts          # Barrel exports
 ```
 
@@ -44,67 +45,21 @@ interface Task {
 
 ## TODO SYNC
 
-The task system includes a sync layer (`todo-sync.ts`) that automatically mirrors task state to the project's Todo system.
+Task system includes sync layer (`todo-sync.ts`) that automatically mirrors task state to the project's Todo system.
 
-- **Creation**: Creating a task via `task_create` adds a corresponding item to the Todo list.
-- **Updates**: Updating a task's `status` or `subject` via `task_update` reflects in the Todo list.
-- **Completion**: Marking a task as `completed` automatically marks the Todo item as done.
+- **Creation**: `task_create` adds corresponding Todo item
+- **Updates**: `task_update` reflects in Todo list
+- **Completion**: `completed` status marks Todo item done
 
 ## STORAGE UTILITIES
 
-### getTaskDir(config)
-
-Returns: `.sisyphus/tasks` (or custom path from config)
-
-### readJsonSafe(filePath, schema)
-
-- Returns parsed & validated data or `null`
-- Safe for missing files, invalid JSON, schema violations
-
-### writeJsonAtomic(filePath, data)
-
-- Atomic write via temp file + rename
-- Creates parent directories automatically
-- Cleans up temp file on error
-
-### acquireLock(dirPath)
-
-- File-based lock: `.lock` file with timestamp
-- 30-second stale threshold
-- Returns `{ acquired: boolean, release: () => void }`
-
-## TESTING
-
-**types.test.ts** (8 tests):
-- Valid status enum values
-- Required vs optional fields
-- Array validation (blocks, blockedBy)
-- Schema rejection for invalid data
-
-**storage.test.ts** (14 tests):
-- Path construction
-- Safe JSON reading (missing files, invalid JSON, schema failures)
-- Atomic writes (directory creation, overwrites)
-- Lock acquisition (fresh locks, stale locks, release)
-
-## USAGE
-
-```typescript
-import { TaskSchema, getTaskDir, readJsonSafe, writeJsonAtomic, acquireLock } from "./features/claude-tasks"
-
-const taskDir = getTaskDir(config)
-const lock = acquireLock(taskDir)
-
-try {
-  const task = readJsonSafe(join(taskDir, "1.json"), TaskSchema)
-  if (task) {
-    task.status = "completed"
-    writeJsonAtomic(join(taskDir, "1.json"), task)
-  }
-} finally {
-  lock.release()
-}
-```
+| Function | Purpose |
+|----------|---------|
+| `getTaskDir(config)` | Returns task storage directory path |
+| `resolveTaskListId(config)` | Resolves task list ID (env → config → cwd basename) |
+| `readJsonSafe(path, schema)` | Parse + validate, returns null on failure |
+| `writeJsonAtomic(path, data)` | Atomic write via temp file + rename |
+| `acquireLock(dirPath)` | File-based lock with 30s stale threshold |
 
 ## ANTI-PATTERNS
 

src/features/claude-tasks/storage.test.ts

@@ -1,26 +1,99 @@
 import { describe, test, expect, beforeEach, afterEach } from "bun:test"
 import { existsSync, mkdirSync, rmSync, writeFileSync } from "fs"
-import { join } from "path"
+import { join, basename } from "path"
 import { z } from "zod"
-import { getTaskDir, readJsonSafe, writeJsonAtomic, acquireLock, generateTaskId, listTaskFiles } from "./storage"
+import { getOpenCodeConfigDir } from "../../shared/opencode-config-dir"
+import {
+  getTaskDir,
+  readJsonSafe,
+  writeJsonAtomic,
+  acquireLock,
+  generateTaskId,
+  listTaskFiles,
+  resolveTaskListId,
+  sanitizePathSegment,
+} from "./storage"
 import type { OhMyOpenCodeConfig } from "../../config/schema"
 
 const TEST_DIR = ".test-claude-tasks"
 const TEST_DIR_ABS = join(process.cwd(), TEST_DIR)
 
 describe("getTaskDir", () => {
-  test("returns correct path for default config", () => {
+  const originalTaskListId = process.env.ULTRAWORK_TASK_LIST_ID
+
+  beforeEach(() => {
+    if (originalTaskListId === undefined) {
+      delete process.env.ULTRAWORK_TASK_LIST_ID
+    } else {
+      process.env.ULTRAWORK_TASK_LIST_ID = originalTaskListId
+    }
+  })
+
+  afterEach(() => {
+    if (originalTaskListId === undefined) {
+      delete process.env.ULTRAWORK_TASK_LIST_ID
+    } else {
+      process.env.ULTRAWORK_TASK_LIST_ID = originalTaskListId
+    }
+  })
+
+  test("returns global config path for default config", () => {
     //#given
     const config: Partial<OhMyOpenCodeConfig> = {}
+    const configDir = getOpenCodeConfigDir({ binary: "opencode" })
+    const expectedListId = sanitizePathSegment(basename(process.cwd()))
 
     //#when
     const result = getTaskDir(config)
 
     //#then
-    expect(result).toBe(join(process.cwd(), ".sisyphus/tasks"))
+    expect(result).toBe(join(configDir, "tasks", expectedListId))
   })
 
-  test("returns correct path with custom storage_path", () => {
+  test("respects ULTRAWORK_TASK_LIST_ID env var", () => {
+    //#given
+    process.env.ULTRAWORK_TASK_LIST_ID = "custom list/id"
+    const configDir = getOpenCodeConfigDir({ binary: "opencode" })
+
+    //#when
+    const result = getTaskDir()
+
+    //#then
+    expect(result).toBe(join(configDir, "tasks", "custom-list-id"))
+  })
+
+  test("falls back to sanitized cwd basename when env var not set", () => {
+    //#given
+    delete process.env.ULTRAWORK_TASK_LIST_ID
+    const configDir = getOpenCodeConfigDir({ binary: "opencode" })
+    const expectedListId = sanitizePathSegment(basename(process.cwd()))
+
+    //#when
+    const result = getTaskDir()
+
+    //#then
+    expect(result).toBe(join(configDir, "tasks", expectedListId))
+  })
+
+  test("returns absolute storage_path without joining cwd", () => {
+    //#given
+    const config: Partial<OhMyOpenCodeConfig> = {
+      sisyphus: {
+        tasks: {
+          storage_path: "/tmp/custom-task-path",
+          claude_code_compat: false,
+        },
+      },
+    }
+
+    //#when
+    const result = getTaskDir(config)
+
+    //#then
+    expect(result).toBe("/tmp/custom-task-path")
+  })
+
+  test("joins relative storage_path with cwd", () => {
     //#given
     const config: Partial<OhMyOpenCodeConfig> = {
       sisyphus: {
@@ -37,13 +110,59 @@ describe("getTaskDir", () => {
     //#then
     expect(result).toBe(join(process.cwd(), ".custom/tasks"))
   })
+})
+
+describe("resolveTaskListId", () => {
+  const originalTaskListId = process.env.ULTRAWORK_TASK_LIST_ID
+
+  beforeEach(() => {
+    if (originalTaskListId === undefined) {
+      delete process.env.ULTRAWORK_TASK_LIST_ID
+    } else {
+      process.env.ULTRAWORK_TASK_LIST_ID = originalTaskListId
+    }
+  })
+
+  afterEach(() => {
+    if (originalTaskListId === undefined) {
+      delete process.env.ULTRAWORK_TASK_LIST_ID
+    } else {
+      process.env.ULTRAWORK_TASK_LIST_ID = originalTaskListId
+    }
+  })
+
+  test("returns env var when set", () => {
+    //#given
+    process.env.ULTRAWORK_TASK_LIST_ID = "custom-list"
 
-  test("returns correct path with default config parameter", () => {
     //#when
-    const result = getTaskDir()
+    const result = resolveTaskListId()
 
     //#then
-    expect(result).toBe(join(process.cwd(), ".sisyphus/tasks"))
+    expect(result).toBe("custom-list")
+  })
+
+  test("sanitizes special characters", () => {
+    //#given
+    process.env.ULTRAWORK_TASK_LIST_ID = "custom list/id"
+
+    //#when
+    const result = resolveTaskListId()
+
+    //#then
+    expect(result).toBe("custom-list-id")
+  })
+
+  test("returns sanitized cwd basename when env var not set", () => {
+    //#given
+    delete process.env.ULTRAWORK_TASK_LIST_ID
+    const expected = sanitizePathSegment(basename(process.cwd()))
+
+    //#when
+    const result = resolveTaskListId()
+
+    //#then
+    expect(result).toBe(expected)
   })
 })
 

src/features/claude-tasks/storage.ts

@@ -1,13 +1,35 @@
-import { join, dirname } from "path"
+import { join, dirname, basename, isAbsolute } from "path"
 import { existsSync, mkdirSync, readFileSync, writeFileSync, renameSync, unlinkSync, readdirSync } from "fs"
 import { randomUUID } from "crypto"
+import { getOpenCodeConfigDir } from "../../shared/opencode-config-dir"
 import type { z } from "zod"
 import type { OhMyOpenCodeConfig } from "../../config/schema"
 
 export function getTaskDir(config: Partial<OhMyOpenCodeConfig> = {}): string {
   const tasksConfig = config.sisyphus?.tasks
-  const storagePath = tasksConfig?.storage_path ?? ".sisyphus/tasks"
-  return join(process.cwd(), storagePath)
+  const storagePath = tasksConfig?.storage_path
+
+  if (storagePath) {
+    return isAbsolute(storagePath) ? storagePath : join(process.cwd(), storagePath)
+  }
+
+  const configDir = getOpenCodeConfigDir({ binary: "opencode" })
+  const listId = resolveTaskListId(config)
+  return join(configDir, "tasks", listId)
+}
+
+export function sanitizePathSegment(value: string): string {
+  return value.replace(/[^a-zA-Z0-9_-]/g, "-") || "default"
+}
+
+export function resolveTaskListId(config: Partial<OhMyOpenCodeConfig> = {}): string {
+  const envId = process.env.ULTRAWORK_TASK_LIST_ID?.trim()
+  if (envId) return sanitizePathSegment(envId)
+
+  const configId = config.sisyphus?.tasks?.task_list_id?.trim()
+  if (configId) return sanitizePathSegment(configId)
+
+  return sanitizePathSegment(basename(process.cwd()))
 }
 
 export function ensureDir(dirPath: string): void {

src/features/opencode-skill-loader/loader.test.ts

@@ -388,169 +388,175 @@ Skill body.
     })
   })
 
-  describe("nested skill discovery", () => {
-    it("discovers skills in nested directories (superpowers pattern)", async () => {
-      // #given - simulate superpowers structure: skills/superpowers/brainstorming/SKILL.md
-      const nestedDir = join(SKILLS_DIR, "superpowers", "brainstorming")
-      mkdirSync(nestedDir, { recursive: true })
-      const skillContent = `---
-name: brainstorming
-description: A nested skill for brainstorming
+  describe("deduplication", () => {
+    it("deduplicates skills by name across scopes, keeping higher priority (opencode-project > opencode > project)", async () => {
+      const originalCwd = process.cwd()
+      const originalOpenCodeConfigDir = process.env.OPENCODE_CONFIG_DIR
+      const originalClaudeConfigDir = process.env.CLAUDE_CONFIG_DIR
+
+      // given: same skill name in multiple scopes
+      const opencodeProjectSkillsDir = join(TEST_DIR, ".opencode", "skills")
+      const opencodeConfigDir = join(TEST_DIR, "opencode-global")
+      const opencodeGlobalSkillsDir = join(opencodeConfigDir, "skills")
+      const projectClaudeSkillsDir = join(TEST_DIR, ".claude", "skills")
+
+      process.env.OPENCODE_CONFIG_DIR = opencodeConfigDir
+      process.env.CLAUDE_CONFIG_DIR = join(TEST_DIR, "claude-user")
+
+      mkdirSync(join(opencodeProjectSkillsDir, "duplicate-skill"), { recursive: true })
+      mkdirSync(join(opencodeGlobalSkillsDir, "duplicate-skill"), { recursive: true })
+      mkdirSync(join(projectClaudeSkillsDir, "duplicate-skill"), { recursive: true })
+
+      writeFileSync(
+        join(opencodeProjectSkillsDir, "duplicate-skill", "SKILL.md"),
+        `---
+name: duplicate-skill
+description: From opencode-project (highest priority)
 ---
-This is a nested skill.
+opencode-project body.
 `
-      writeFileSync(join(nestedDir, "SKILL.md"), skillContent)
+      )
 
-      // #when
+      writeFileSync(
+        join(opencodeGlobalSkillsDir, "duplicate-skill", "SKILL.md"),
+        `---
+name: duplicate-skill
+description: From opencode-global (middle priority)
+---
+opencode-global body.
+`
+      )
+
+      writeFileSync(
+        join(projectClaudeSkillsDir, "duplicate-skill", "SKILL.md"),
+        `---
+name: duplicate-skill
+description: From claude project (lowest priority among these)
+---
+claude project body.
+`
+      )
+
+      // when
       const { discoverSkills } = await import("./loader")
-      const originalCwd = process.cwd()
       process.chdir(TEST_DIR)
 
       try {
-        const skills = await discoverSkills({ includeClaudeCodePaths: false })
-        const skill = skills.find(s => s.name === "superpowers/brainstorming")
+        const skills = await discoverSkills()
+        const duplicates = skills.filter(s => s.name === "duplicate-skill")
 
-        // #then
-        expect(skill).toBeDefined()
-        expect(skill?.name).toBe("superpowers/brainstorming")
-        expect(skill?.definition.description).toContain("brainstorming")
+        // then
+        expect(duplicates).toHaveLength(1)
+        expect(duplicates[0]?.scope).toBe("opencode-project")
+        expect(duplicates[0]?.definition.description).toContain("opencode-project")
       } finally {
         process.chdir(originalCwd)
-      }
-    })
-
-    it("discovers multiple skills in nested directories", async () => {
-      // #given - multiple nested skills
-      const skills = ["brainstorming", "debugging", "testing"]
-      for (const skillName of skills) {
-        const nestedDir = join(SKILLS_DIR, "superpowers", skillName)
-        mkdirSync(nestedDir, { recursive: true })
-        writeFileSync(join(nestedDir, "SKILL.md"), `---
-name: ${skillName}
-description: ${skillName} skill
----
-Content for ${skillName}.
-`)
-      }
-
-      // #when
-      const { discoverSkills } = await import("./loader")
-      const originalCwd = process.cwd()
-      process.chdir(TEST_DIR)
-
-      try {
-        const discoveredSkills = await discoverSkills({ includeClaudeCodePaths: false })
-
-        // #then
-        for (const skillName of skills) {
-          const skill = discoveredSkills.find(s => s.name === `superpowers/${skillName}`)
-          expect(skill).toBeDefined()
+        if (originalOpenCodeConfigDir === undefined) {
+          delete process.env.OPENCODE_CONFIG_DIR
+        } else {
+          process.env.OPENCODE_CONFIG_DIR = originalOpenCodeConfigDir
+        }
+        if (originalClaudeConfigDir === undefined) {
+          delete process.env.CLAUDE_CONFIG_DIR
+        } else {
+          process.env.CLAUDE_CONFIG_DIR = originalClaudeConfigDir
         }
-      } finally {
-        process.chdir(originalCwd)
       }
     })
 
-    it("respects max depth limit", async () => {
-      // #given - deeply nested skill (3 levels deep, beyond default maxDepth of 2)
-      const deepDir = join(SKILLS_DIR, "level1", "level2", "level3", "deep-skill")
-      mkdirSync(deepDir, { recursive: true })
-      writeFileSync(join(deepDir, "SKILL.md"), `---
-name: deep-skill
-description: A deeply nested skill
----
-Too deep.
-`)
-
-      // #when
-      const { discoverSkills } = await import("./loader")
+    it("prioritizes OpenCode global skills over legacy Claude project skills", async () => {
       const originalCwd = process.cwd()
+      const originalOpenCodeConfigDir = process.env.OPENCODE_CONFIG_DIR
+      const originalClaudeConfigDir = process.env.CLAUDE_CONFIG_DIR
+
+      const opencodeConfigDir = join(TEST_DIR, "opencode-global")
+      const opencodeGlobalSkillsDir = join(opencodeConfigDir, "skills")
+      const projectClaudeSkillsDir = join(TEST_DIR, ".claude", "skills")
+
+      process.env.OPENCODE_CONFIG_DIR = opencodeConfigDir
+      process.env.CLAUDE_CONFIG_DIR = join(TEST_DIR, "claude-user")
+
+      mkdirSync(join(opencodeGlobalSkillsDir, "global-over-project"), { recursive: true })
+      mkdirSync(join(projectClaudeSkillsDir, "global-over-project"), { recursive: true })
+
+      writeFileSync(
+        join(opencodeGlobalSkillsDir, "global-over-project", "SKILL.md"),
+        `---
+name: global-over-project
+description: From opencode-global (should win)
+---
+opencode-global body.
+`
+      )
+
+      writeFileSync(
+        join(projectClaudeSkillsDir, "global-over-project", "SKILL.md"),
+        `---
+name: global-over-project
+description: From claude project (should lose)
+---
+claude project body.
+`
+      )
+
+      const { discoverSkills } = await import("./loader")
       process.chdir(TEST_DIR)
 
       try {
-        const skills = await discoverSkills({ includeClaudeCodePaths: false })
-        const skill = skills.find(s => s.name.includes("deep-skill"))
+        const skills = await discoverSkills()
+        const matches = skills.filter(s => s.name === "global-over-project")
 
-        // #then - should not find skill beyond maxDepth
-        expect(skill).toBeUndefined()
+        expect(matches).toHaveLength(1)
+        expect(matches[0]?.scope).toBe("opencode")
+        expect(matches[0]?.definition.description).toContain("opencode-global")
       } finally {
         process.chdir(originalCwd)
+        if (originalOpenCodeConfigDir === undefined) {
+          delete process.env.OPENCODE_CONFIG_DIR
+        } else {
+          process.env.OPENCODE_CONFIG_DIR = originalOpenCodeConfigDir
+        }
+        if (originalClaudeConfigDir === undefined) {
+          delete process.env.CLAUDE_CONFIG_DIR
+        } else {
+          process.env.CLAUDE_CONFIG_DIR = originalClaudeConfigDir
+        }
       }
     })
 
-    it("flat skills still work alongside nested skills", async () => {
-      // #given - both flat and nested skills
-      const flatSkillDir = join(SKILLS_DIR, "flat-skill")
-      mkdirSync(flatSkillDir, { recursive: true })
-      writeFileSync(join(flatSkillDir, "SKILL.md"), `---
-name: flat-skill
-description: A flat skill
----
-Flat content.
-`)
-
-      const nestedDir = join(SKILLS_DIR, "nested", "nested-skill")
-      mkdirSync(nestedDir, { recursive: true })
-      writeFileSync(join(nestedDir, "SKILL.md"), `---
-name: nested-skill
-description: A nested skill
----
-Nested content.
-`)
-
-      // #when
-      const { discoverSkills } = await import("./loader")
+    it("returns no duplicates from discoverSkills", async () => {
       const originalCwd = process.cwd()
+      const originalOpenCodeConfigDir = process.env.OPENCODE_CONFIG_DIR
+
+      process.env.OPENCODE_CONFIG_DIR = join(TEST_DIR, "opencode-global")
+
+      // given
+      const skillContent = `---
+name: unique-test-skill
+description: A unique skill for dedup test
+---
+Skill body.
+`
+      createTestSkill("unique-test-skill", skillContent)
+
+      // when
+      const { discoverSkills } = await import("./loader")
       process.chdir(TEST_DIR)
 
       try {
         const skills = await discoverSkills({ includeClaudeCodePaths: false })
 
-        // #then - both should be found
-        const flatSkill = skills.find(s => s.name === "flat-skill")
-        const nestedSkill = skills.find(s => s.name === "nested/nested-skill")
-
-        expect(flatSkill).toBeDefined()
-        expect(nestedSkill).toBeDefined()
-      } finally {
-        process.chdir(originalCwd)
-      }
-    })
-
-    it("prefers directory skill (SKILL.md) over file skill (*.md) on name collision", async () => {
-      // #given - both foo.md file AND foo/SKILL.md directory exist
-      // Directory skill should win (deterministic precedence: SKILL.md > {dir}.md > *.md)
-      const dirSkillDir = join(SKILLS_DIR, "collision-test")
-      mkdirSync(dirSkillDir, { recursive: true })
-      writeFileSync(join(dirSkillDir, "SKILL.md"), `---
-name: collision-test
-description: Directory-based skill (should win)
----
-I am the directory skill.
-`)
-
-      // Also create a file with same base name at parent level
-      writeFileSync(join(SKILLS_DIR, "collision-test.md"), `---
-name: collision-test
-description: File-based skill (should lose)
----
-I am the file skill.
-`)
-
-      // #when
-      const { discoverSkills } = await import("./loader")
-      const originalCwd = process.cwd()
-      process.chdir(TEST_DIR)
-
-      try {
-        const skills = await discoverSkills({ includeClaudeCodePaths: false })
-
-        // #then - only one skill should exist, and it should be the directory-based one
-        const matchingSkills = skills.filter(s => s.name === "collision-test")
-        expect(matchingSkills).toHaveLength(1)
-        expect(matchingSkills[0]?.definition.description).toContain("Directory-based skill")
+        // then
+        const names = skills.map(s => s.name)
+        const uniqueNames = [...new Set(names)]
+        expect(names.length).toBe(uniqueNames.length)
       } finally {
         process.chdir(originalCwd)
+        if (originalOpenCodeConfigDir === undefined) {
+          delete process.env.OPENCODE_CONFIG_DIR
+        } else {
+          process.env.OPENCODE_CONFIG_DIR = originalOpenCodeConfigDir
+        }
       }
     })
   })

src/features/opencode-skill-loader/loader.ts

@@ -233,15 +233,33 @@ export interface DiscoverSkillsOptions {
   includeClaudeCodePaths?: boolean
 }
 
+/**
+ * Deduplicates skills by name, keeping the first occurrence (higher priority).
+ * Priority order: opencode-project > opencode > project > user
+ * (OpenCode Global skills take precedence over legacy Claude project skills)
+ */
+function deduplicateSkills(skills: LoadedSkill[]): LoadedSkill[] {
+  const seen = new Set<string>()
+  const result: LoadedSkill[] = []
+  for (const skill of skills) {
+    if (!seen.has(skill.name)) {
+      seen.add(skill.name)
+      result.push(skill)
+    }
+  }
+  return result
+}
+
 export async function discoverAllSkills(): Promise<LoadedSkill[]> {
-  const [opencodeProjectSkills, projectSkills, opencodeGlobalSkills, userSkills] = await Promise.all([
+  const [opencodeProjectSkills, opencodeGlobalSkills, projectSkills, userSkills] = await Promise.all([
     discoverOpencodeProjectSkills(),
-    discoverProjectClaudeSkills(),
     discoverOpencodeGlobalSkills(),
+    discoverProjectClaudeSkills(),
     discoverUserClaudeSkills(),
   ])
 
-  return [...opencodeProjectSkills, ...projectSkills, ...opencodeGlobalSkills, ...userSkills]
+  // Priority: opencode-project > opencode > project > user
+  return deduplicateSkills([...opencodeProjectSkills, ...opencodeGlobalSkills, ...projectSkills, ...userSkills])
 }
 
 export async function discoverSkills(options: DiscoverSkillsOptions = {}): Promise<LoadedSkill[]> {
@@ -253,7 +271,8 @@ export async function discoverSkills(options: DiscoverSkillsOptions = {}): Promi
   ])
 
   if (!includeClaudeCodePaths) {
-    return [...opencodeProjectSkills, ...opencodeGlobalSkills]
+    // Priority: opencode-project > opencode
+    return deduplicateSkills([...opencodeProjectSkills, ...opencodeGlobalSkills])
   }
 
   const [projectSkills, userSkills] = await Promise.all([
@@ -261,7 +280,8 @@ export async function discoverSkills(options: DiscoverSkillsOptions = {}): Promi
     discoverUserClaudeSkills(),
   ])
 
-  return [...opencodeProjectSkills, ...projectSkills, ...opencodeGlobalSkills, ...userSkills]
+  // Priority: opencode-project > opencode > project > user
+  return deduplicateSkills([...opencodeProjectSkills, ...opencodeGlobalSkills, ...projectSkills, ...userSkills])
 }
 
 export async function getSkillByName(name: string, options: DiscoverSkillsOptions = {}): Promise<LoadedSkill | undefined> {

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

@@ -192,7 +192,7 @@ describe("TaskToastManager", () => {
         description: "Task with inherited model",
         agent: "sisyphus-junior",
         isBackground: false,
-        modelInfo: { model: "cliproxy/claude-opus-4-5", type: "inherited" as const },
+        modelInfo: { model: "cliproxy/claude-opus-4-6", type: "inherited" as const },
       }
 
       // when - addTask is called
@@ -202,7 +202,7 @@ describe("TaskToastManager", () => {
       expect(mockClient.tui.showToast).toHaveBeenCalled()
       const call = mockClient.tui.showToast.mock.calls[0][0]
       expect(call.body.message).toContain("[FALLBACK]")
-      expect(call.body.message).toContain("cliproxy/claude-opus-4-5")
+      expect(call.body.message).toContain("cliproxy/claude-opus-4-6")
       expect(call.body.message).toContain("(inherited from parent)")
     })
 

src/hooks/AGENTS.md

@@ -2,7 +2,7 @@
 
 ## OVERVIEW
 
-34 lifecycle hooks intercepting/modifying agent behavior across 5 events.
+40+ lifecycle hooks intercepting/modifying agent behavior across 5 events.
 
 **Event Types**:
 - `UserPromptSubmit` (`chat.message`) - Can block
@@ -14,10 +14,10 @@
 ## STRUCTURE
 ```
 hooks/
-├── atlas/                      # Main orchestration (757 lines)
+├── atlas/                      # Main orchestration (770 lines)
 ├── anthropic-context-window-limit-recovery/ # Auto-summarize
-├── todo-continuation-enforcer.ts # Force TODO completion
-├── ralph-loop/                 # Self-referential dev loop
+├── todo-continuation-enforcer.ts # Force TODO completion (517 lines)
+├── ralph-loop/                 # Self-referential dev loop (428 lines)
 ├── claude-code-hooks/          # settings.json compat layer - see AGENTS.md
 ├── comment-checker/            # Prevents AI slop
 ├── auto-slash-command/         # Detects /command patterns
@@ -27,13 +27,14 @@ hooks/
 ├── edit-error-recovery/        # Recovers from failures
 ├── thinking-block-validator/   # Ensures valid <thinking>
 ├── context-window-monitor.ts   # Reminds of headroom
-├── session-recovery/           # Auto-recovers from crashes
+├── session-recovery/           # Auto-recovers from crashes (436 lines)
+├── session-notification.ts     # Session event notifications (337 lines)
 ├── think-mode/                 # Dynamic thinking budget
 ├── keyword-detector/           # ultrawork/search/analyze modes
 ├── background-notification/    # OS notification
 ├── prometheus-md-only/         # Planner read-only mode
 ├── agent-usage-reminder/       # Specialized agent hints
-├── auto-update-checker/        # Plugin update check
+├── auto-update-checker/        # Plugin update check (304 lines)
 ├── tool-output-truncator.ts    # Prevents context bloat
 ├── compaction-context-injector/ # Injects context on compaction
 ├── delegate-task-retry/        # Retries failed delegations
@@ -47,6 +48,11 @@ hooks/
 ├── sisyphus-junior-notepad/    # Sisyphus Junior notepad
 ├── stop-continuation-guard/    # Guards stop continuation
 ├── subagent-question-blocker/  # Blocks subagent questions
+├── task-reminder/              # Task progress reminders
+├── tasks-todowrite-disabler/   # Disables TodoWrite when task system active
+├── unstable-agent-babysitter/  # Monitors unstable agent behavior
+├── write-existing-file-guard/  # Guards against overwriting existing files
+├── preemptive-compaction.ts    # Preemptive context compaction
 └── index.ts                    # Hook aggregation + registration
 ```
 
@@ -61,8 +67,8 @@ hooks/
 
 ## EXECUTION ORDER
 - **UserPromptSubmit**: keywordDetector → claudeCodeHooks → autoSlashCommand → startWork
-- **PreToolUse**: subagentQuestionBlocker → questionLabelTruncator → claudeCodeHooks → nonInteractiveEnv → commentChecker → directoryAgentsInjector → directoryReadmeInjector → rulesInjector → prometheusMdOnly → sisyphusJuniorNotepad → atlasHook
-- **PostToolUse**: claudeCodeHooks → toolOutputTruncator → contextWindowMonitor → commentChecker → directoryAgentsInjector → directoryReadmeInjector → rulesInjector → emptyTaskResponseDetector → agentUsageReminder → interactiveBashSession → editErrorRecovery → delegateTaskRetry → atlasHook → taskResumeInfo
+- **PreToolUse**: subagentQuestionBlocker → questionLabelTruncator → claudeCodeHooks → nonInteractiveEnv → commentChecker → directoryAgentsInjector → directoryReadmeInjector → rulesInjector → prometheusMdOnly → sisyphusJuniorNotepad → writeExistingFileGuard → atlasHook
+- **PostToolUse**: claudeCodeHooks → toolOutputTruncator → contextWindowMonitor → commentChecker → directoryAgentsInjector → directoryReadmeInjector → rulesInjector → emptyTaskResponseDetector → agentUsageReminder → interactiveBashSession → editErrorRecovery → delegateTaskRetry → atlasHook → taskResumeInfo → taskReminder
 
 ## HOW TO ADD
 1. Create `src/hooks/name/` with `index.ts` exporting `createMyHook(ctx)`

src/hooks/anthropic-context-window-limit-recovery/executor.test.ts

@@ -80,7 +80,7 @@ describe("executeCompact lock management", () => {
   let fakeTimeouts: FakeTimeouts
   const sessionID = "test-session-123"
   const directory = "/test/dir"
-  const msg = { providerID: "anthropic", modelID: "claude-opus-4-5" }
+  const msg = { providerID: "anthropic", modelID: "claude-opus-4-6" }
 
   beforeEach(() => {
     // given: Fresh state for each test
@@ -332,7 +332,7 @@ describe("executeCompact lock management", () => {
     expect(mockClient.session.summarize).toHaveBeenCalledWith(
       expect.objectContaining({
         path: { id: sessionID },
-        body: { providerID: "anthropic", modelID: "claude-opus-4-5", auto: true },
+        body: { providerID: "anthropic", modelID: "claude-opus-4-6", auto: true },
       }),
     )
 

src/hooks/atlas/index.test.ts

@@ -47,7 +47,7 @@ describe("atlas hook", () => {
     }
     const messageData = {
       agent,
-      model: { providerID: "anthropic", modelID: "claude-opus-4-5" },
+      model: { providerID: "anthropic", modelID: "claude-opus-4-6" },
     }
     writeFileSync(join(messageDir, "msg_test001.json"), JSON.stringify(messageData))
   }
@@ -624,6 +624,11 @@ describe("atlas hook", () => {
   describe("session.idle handler (boulder continuation)", () => {
     const MAIN_SESSION_ID = "main-session-123"
 
+    async function flushMicrotasks(): Promise<void> {
+      await Promise.resolve()
+      await Promise.resolve()
+    }
+
      beforeEach(() => {
        mock.module("../../features/claude-code-session-state", () => ({
          getMainSessionID: () => MAIN_SESSION_ID,
@@ -858,8 +863,8 @@ describe("atlas hook", () => {
       expect(callArgs.body.parts[0].text).toContain("2 remaining")
     })
 
-     test("should not inject when last agent is not Atlas", async () => {
-       // given - boulder state with incomplete plan, but last agent is NOT Atlas
+     test("should not inject when last agent does not match boulder agent", async () => {
+       // given - boulder state with incomplete plan, but last agent does NOT match
        const planPath = join(TEST_DIR, "test-plan.md")
        writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [ ] Task 2")
 
@@ -868,10 +873,11 @@ describe("atlas hook", () => {
          started_at: "2026-01-02T10:00:00Z",
          session_ids: [MAIN_SESSION_ID],
          plan_name: "test-plan",
+         agent: "atlas",
        }
        writeBoulderState(TEST_DIR, state)
 
-       // given - last agent is NOT Atlas
+       // given - last agent is NOT the boulder agent
        cleanupMessageStorage(MAIN_SESSION_ID)
        setupMessageStorage(MAIN_SESSION_ID, "sisyphus")
 
@@ -886,10 +892,44 @@ describe("atlas hook", () => {
          },
        })
 
-       // then - should NOT call prompt because agent is not Atlas
+       // then - should NOT call prompt because agent does not match
        expect(mockInput._promptMock).not.toHaveBeenCalled()
      })
 
+     test("should inject when last agent matches boulder agent even if non-Atlas", async () => {
+       // given - boulder state expects sisyphus and last agent is sisyphus
+       const planPath = join(TEST_DIR, "test-plan.md")
+       writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [ ] Task 2")
+
+       const state: BoulderState = {
+         active_plan: planPath,
+         started_at: "2026-01-02T10:00:00Z",
+         session_ids: [MAIN_SESSION_ID],
+         plan_name: "test-plan",
+         agent: "sisyphus",
+       }
+       writeBoulderState(TEST_DIR, state)
+
+       cleanupMessageStorage(MAIN_SESSION_ID)
+       setupMessageStorage(MAIN_SESSION_ID, "sisyphus")
+
+       const mockInput = createMockPluginInput()
+       const hook = createAtlasHook(mockInput)
+
+       // when
+       await hook.handler({
+         event: {
+           type: "session.idle",
+           properties: { sessionID: MAIN_SESSION_ID },
+         },
+       })
+
+       // then - should call prompt for sisyphus
+       expect(mockInput._promptMock).toHaveBeenCalled()
+       const callArgs = mockInput._promptMock.mock.calls[0][0]
+       expect(callArgs.body.agent).toBe("sisyphus")
+     })
+
     test("should debounce rapid continuation injections (prevent infinite loop)", async () => {
       // given - boulder state with incomplete plan
       const planPath = join(TEST_DIR, "test-plan.md")
@@ -930,6 +970,135 @@ describe("atlas hook", () => {
       expect(mockInput._promptMock).toHaveBeenCalledTimes(1)
     })
 
+    test("should stop continuation after 2 consecutive prompt failures (issue #1355)", async () => {
+      //#given - boulder state with incomplete plan and prompt always fails
+      const planPath = join(TEST_DIR, "test-plan.md")
+      writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [ ] Task 2")
+
+      const state: BoulderState = {
+        active_plan: planPath,
+        started_at: "2026-01-02T10:00:00Z",
+        session_ids: [MAIN_SESSION_ID],
+        plan_name: "test-plan",
+      }
+      writeBoulderState(TEST_DIR, state)
+
+      const promptMock = mock(() => Promise.reject(new Error("Bad Request")))
+      const mockInput = createMockPluginInput({ promptMock })
+      const hook = createAtlasHook(mockInput)
+
+      const originalDateNow = Date.now
+      let now = 0
+      Date.now = () => now
+
+      try {
+        //#when - idle fires repeatedly, past cooldown each time
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: MAIN_SESSION_ID } } })
+        await flushMicrotasks()
+        now += 6000
+
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: MAIN_SESSION_ID } } })
+        await flushMicrotasks()
+        now += 6000
+
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: MAIN_SESSION_ID } } })
+        await flushMicrotasks()
+
+        //#then - should attempt only twice, then disable continuation
+        expect(promptMock).toHaveBeenCalledTimes(2)
+      } finally {
+        Date.now = originalDateNow
+      }
+    })
+
+    test("should reset prompt failure counter on success and only stop after 2 consecutive failures", async () => {
+      //#given - boulder state with incomplete plan
+      const planPath = join(TEST_DIR, "test-plan.md")
+      writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [ ] Task 2")
+
+      const state: BoulderState = {
+        active_plan: planPath,
+        started_at: "2026-01-02T10:00:00Z",
+        session_ids: [MAIN_SESSION_ID],
+        plan_name: "test-plan",
+      }
+      writeBoulderState(TEST_DIR, state)
+
+      const promptMock = mock(() => Promise.resolve())
+      promptMock.mockImplementationOnce(() => Promise.reject(new Error("Bad Request")))
+      promptMock.mockImplementationOnce(() => Promise.resolve())
+      promptMock.mockImplementationOnce(() => Promise.reject(new Error("Bad Request")))
+      promptMock.mockImplementationOnce(() => Promise.reject(new Error("Bad Request")))
+
+      const mockInput = createMockPluginInput({ promptMock })
+      const hook = createAtlasHook(mockInput)
+
+      const originalDateNow = Date.now
+      let now = 0
+      Date.now = () => now
+
+      try {
+        //#when - fail, succeed (reset), then fail twice (disable), then attempt again
+        for (let i = 0; i < 5; i++) {
+          await hook.handler({ event: { type: "session.idle", properties: { sessionID: MAIN_SESSION_ID } } })
+          await flushMicrotasks()
+          now += 6000
+        }
+
+        //#then - 4 prompt attempts; 5th idle is skipped after 2 consecutive failures
+        expect(promptMock).toHaveBeenCalledTimes(4)
+      } finally {
+        Date.now = originalDateNow
+      }
+    })
+
+    test("should reset continuation failure state on session.compacted event", async () => {
+      //#given - boulder state with incomplete plan and prompt always fails
+      const planPath = join(TEST_DIR, "test-plan.md")
+      writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [ ] Task 2")
+
+      const state: BoulderState = {
+        active_plan: planPath,
+        started_at: "2026-01-02T10:00:00Z",
+        session_ids: [MAIN_SESSION_ID],
+        plan_name: "test-plan",
+      }
+      writeBoulderState(TEST_DIR, state)
+
+      const promptMock = mock(() => Promise.reject(new Error("Bad Request")))
+      const mockInput = createMockPluginInput({ promptMock })
+      const hook = createAtlasHook(mockInput)
+
+      const originalDateNow = Date.now
+      let now = 0
+      Date.now = () => now
+
+      try {
+        //#when - two failures disables continuation, then compaction resets it
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: MAIN_SESSION_ID } } })
+        await flushMicrotasks()
+        now += 6000
+
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: MAIN_SESSION_ID } } })
+        await flushMicrotasks()
+        now += 6000
+
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: MAIN_SESSION_ID } } })
+        await flushMicrotasks()
+
+        await hook.handler({ event: { type: "session.compacted", properties: { sessionID: MAIN_SESSION_ID } } })
+        now += 6000
+
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: MAIN_SESSION_ID } } })
+        await flushMicrotasks()
+
+        //#then - 2 attempts + 1 after compaction (3 total)
+        expect(promptMock).toHaveBeenCalledTimes(3)
+      } finally {
+        Date.now = originalDateNow
+      }
+    })
+
     test("should cleanup on session.deleted", async () => {
       // given - boulder state
       const planPath = join(TEST_DIR, "test-plan.md")

src/hooks/atlas/index.ts

@@ -26,6 +26,13 @@ function isSisyphusPath(filePath: string): boolean {
 
 const WRITE_EDIT_TOOLS = ["Write", "Edit", "write", "edit"]
 
+function getLastAgentFromSession(sessionID: string): string | null {
+  const messageDir = getMessageDir(sessionID)
+  if (!messageDir) return null
+  const nearest = findNearestMessageWithFields(messageDir)
+  return nearest?.agent?.toLowerCase() ?? null
+}
+
 const DIRECT_WORK_REMINDER = `
 
 ---
@@ -384,6 +391,7 @@ interface ToolExecuteAfterOutput {
 interface SessionState {
   lastEventWasAbortError?: boolean
   lastContinuationInjectedAt?: number
+  promptFailureCount: number
 }
 
 const CONTINUATION_COOLDOWN_MS = 5000
@@ -425,13 +433,14 @@ export function createAtlasHook(
   function getState(sessionID: string): SessionState {
     let state = sessions.get(sessionID)
     if (!state) {
-      state = {}
+      state = { promptFailureCount: 0 }
       sessions.set(sessionID, state)
     }
     return state
   }
 
-  async function injectContinuation(sessionID: string, planName: string, remaining: number, total: number): Promise<void> {
+  async function injectContinuation(sessionID: string, planName: string, remaining: number, total: number, agent?: string): Promise<void> {
+    const state = getState(sessionID)
     const hasRunningBgTasks = backgroundManager
       ? backgroundManager.getTasksByParentSession(sessionID).some(t => t.status === "running")
       : false
@@ -474,21 +483,28 @@ export function createAtlasHook(
           : undefined
       }
 
-       await ctx.client.session.prompt({
-         path: { id: sessionID },
-         body: {
-            agent: "atlas",
-           ...(model !== undefined ? { model } : {}),
-           parts: [{ type: "text", text: prompt }],
-         },
-         query: { directory: ctx.directory },
-       })
+        await ctx.client.session.prompt({
+          path: { id: sessionID },
+          body: {
+             agent: agent ?? "atlas",
+            ...(model !== undefined ? { model } : {}),
+            parts: [{ type: "text", text: prompt }],
+          },
+          query: { directory: ctx.directory },
+        })
 
-      log(`[${HOOK_NAME}] Boulder continuation injected`, { sessionID })
-    } catch (err) {
-      log(`[${HOOK_NAME}] Boulder continuation failed`, { sessionID, error: String(err) })
-    }
-  }
+       state.promptFailureCount = 0
+
+       log(`[${HOOK_NAME}] Boulder continuation injected`, { sessionID })
+     } catch (err) {
+      state.promptFailureCount += 1
+      log(`[${HOOK_NAME}] Boulder continuation failed`, {
+        sessionID,
+        error: String(err),
+        promptFailureCount: state.promptFailureCount,
+      })
+     }
+   }
 
   return {
     handler: async ({ event }: { event: { type: string; properties?: unknown } }): Promise<void> => {
@@ -534,6 +550,14 @@ export function createAtlasHook(
           return
         }
 
+        if (state.promptFailureCount >= 2) {
+          log(`[${HOOK_NAME}] Skipped: continuation disabled after repeated prompt failures`, {
+            sessionID,
+            promptFailureCount: state.promptFailureCount,
+          })
+          return
+        }
+
         const hasRunningBgTasks = backgroundManager
           ? backgroundManager.getTasksByParentSession(sessionID).some(t => t.status === "running")
           : false
@@ -549,8 +573,14 @@ export function createAtlasHook(
           return
         }
 
-        if (!isCallerOrchestrator(sessionID)) {
-          log(`[${HOOK_NAME}] Skipped: last agent is not Atlas`, { sessionID })
+        const requiredAgent = (boulderState.agent ?? "atlas").toLowerCase()
+        const lastAgent = getLastAgentFromSession(sessionID)
+        if (!lastAgent || lastAgent !== requiredAgent) {
+          log(`[${HOOK_NAME}] Skipped: last agent does not match boulder agent`, {
+            sessionID,
+            lastAgent: lastAgent ?? "unknown",
+            requiredAgent,
+          })
           return
         }
 
@@ -568,7 +598,7 @@ export function createAtlasHook(
 
         state.lastContinuationInjectedAt = now
         const remaining = progress.total - progress.completed
-        injectContinuation(sessionID, boulderState.plan_name, remaining, progress.total)
+        injectContinuation(sessionID, boulderState.plan_name, remaining, progress.total, boulderState.agent)
         return
       }
 
@@ -618,6 +648,17 @@ export function createAtlasHook(
         }
         return
       }
+
+      if (event.type === "session.compacted") {
+        const sessionID = (props?.sessionID ?? (props?.info as { id?: string } | undefined)?.id) as
+          | string
+          | undefined
+        if (sessionID) {
+          sessions.delete(sessionID)
+          log(`[${HOOK_NAME}] Session compacted: cleaned up`, { sessionID })
+        }
+        return
+      }
     },
 
     "tool.execute.before": async (

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

@@ -1,6 +1,6 @@
 import * as fs from "node:fs"
 import * as path from "node:path"
-import { CACHE_DIR, PACKAGE_NAME } from "./constants"
+import { PACKAGE_NAME, USER_CONFIG_DIR } from "./constants"
 import { log } from "../../shared/logger"
 
 interface BunLockfile {
@@ -17,7 +17,7 @@ function stripTrailingCommas(json: string): string {
 }
 
 function removeFromBunLock(packageName: string): boolean {
-  const lockPath = path.join(CACHE_DIR, "bun.lock")
+  const lockPath = path.join(USER_CONFIG_DIR, "bun.lock")
   if (!fs.existsSync(lockPath)) return false
 
   try {
@@ -48,8 +48,8 @@ function removeFromBunLock(packageName: string): boolean {
 
 export function invalidatePackage(packageName: string = PACKAGE_NAME): boolean {
   try {
-    const pkgDir = path.join(CACHE_DIR, "node_modules", packageName)
-    const pkgJsonPath = path.join(CACHE_DIR, "package.json")
+    const pkgDir = path.join(USER_CONFIG_DIR, "node_modules", packageName)
+    const pkgJsonPath = path.join(USER_CONFIG_DIR, "package.json")
 
     let packageRemoved = false
     let dependencyRemoved = false

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

@@ -16,12 +16,6 @@ function getCacheDir(): string {
 
 export const CACHE_DIR = getCacheDir()
 export const VERSION_FILE = path.join(CACHE_DIR, "version")
-export const INSTALLED_PACKAGE_JSON = path.join(
-  CACHE_DIR,
-  "node_modules",
-  PACKAGE_NAME,
-  "package.json"
-)
 
 export function getWindowsAppdataDir(): string | null {
   if (process.platform !== "win32") return null
@@ -31,3 +25,10 @@ export function getWindowsAppdataDir(): string | null {
 export const USER_CONFIG_DIR = getOpenCodeConfigDir({ binary: "opencode" })
 export const USER_OPENCODE_CONFIG = path.join(USER_CONFIG_DIR, "opencode.json")
 export const USER_OPENCODE_CONFIG_JSONC = path.join(USER_CONFIG_DIR, "opencode.jsonc")
+
+export const INSTALLED_PACKAGE_JSON = path.join(
+  USER_CONFIG_DIR,
+  "node_modules",
+  PACKAGE_NAME,
+  "package.json"
+)

src/hooks/category-skill-reminder/index.test.ts

@@ -1,6 +1,7 @@
 import { describe, expect, test, beforeEach, afterEach, spyOn } from "bun:test"
 import { createCategorySkillReminderHook } from "./index"
 import { updateSessionAgent, clearSessionAgent, _resetForTesting } from "../../features/claude-code-session-state"
+import type { AvailableSkill } from "../../agents/dynamic-agent-prompt-builder"
 import * as sharedModule from "../../shared"
 
 describe("category-skill-reminder hook", () => {
@@ -29,10 +30,14 @@ describe("category-skill-reminder hook", () => {
     } as any
   }
 
+  function createHook(availableSkills: AvailableSkill[] = []) {
+    return createCategorySkillReminderHook(createMockPluginInput(), availableSkills)
+  }
+
   describe("target agent detection", () => {
     test("should inject reminder for sisyphus agent after 3 tool calls", async () => {
       // given - sisyphus agent session with multiple tool calls
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "sisyphus-session"
       updateSessionAgent(sessionID, "Sisyphus")
 
@@ -52,7 +57,7 @@ describe("category-skill-reminder hook", () => {
 
     test("should inject reminder for atlas agent", async () => {
       // given - atlas agent session
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "atlas-session"
       updateSessionAgent(sessionID, "Atlas")
 
@@ -71,7 +76,7 @@ describe("category-skill-reminder hook", () => {
 
     test("should inject reminder for sisyphus-junior agent", async () => {
       // given - sisyphus-junior agent session
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "junior-session"
       updateSessionAgent(sessionID, "sisyphus-junior")
 
@@ -90,7 +95,7 @@ describe("category-skill-reminder hook", () => {
 
     test("should NOT inject reminder for non-target agents", async () => {
       // given - librarian agent session (not a target)
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "librarian-session"
       updateSessionAgent(sessionID, "librarian")
 
@@ -109,7 +114,7 @@ describe("category-skill-reminder hook", () => {
 
     test("should detect agent from input.agent when session state is empty", async () => {
       // given - no session state, agent provided in input
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "input-agent-session"
 
       const output = { title: "", output: "result", metadata: {} }
@@ -127,7 +132,7 @@ describe("category-skill-reminder hook", () => {
   describe("delegation tool tracking", () => {
     test("should NOT inject reminder if delegate_task is used", async () => {
       // given - sisyphus agent that uses delegate_task
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "delegation-session"
       updateSessionAgent(sessionID, "Sisyphus")
 
@@ -147,7 +152,7 @@ describe("category-skill-reminder hook", () => {
 
     test("should NOT inject reminder if call_omo_agent is used", async () => {
       // given - sisyphus agent that uses call_omo_agent
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "omo-agent-session"
       updateSessionAgent(sessionID, "Sisyphus")
 
@@ -167,7 +172,7 @@ describe("category-skill-reminder hook", () => {
 
     test("should NOT inject reminder if task tool is used", async () => {
       // given - sisyphus agent that uses task tool
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "task-session"
       updateSessionAgent(sessionID, "Sisyphus")
 
@@ -189,7 +194,7 @@ describe("category-skill-reminder hook", () => {
   describe("tool call counting", () => {
     test("should NOT inject reminder before 3 tool calls", async () => {
       // given - sisyphus agent with only 2 tool calls
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "few-calls-session"
       updateSessionAgent(sessionID, "Sisyphus")
 
@@ -207,7 +212,7 @@ describe("category-skill-reminder hook", () => {
 
     test("should only inject reminder once per session", async () => {
       // given - sisyphus agent session
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "once-session"
       updateSessionAgent(sessionID, "Sisyphus")
 
@@ -231,7 +236,7 @@ describe("category-skill-reminder hook", () => {
 
     test("should only count delegatable work tools", async () => {
       // given - sisyphus agent with mixed tool calls
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "mixed-tools-session"
       updateSessionAgent(sessionID, "Sisyphus")
 
@@ -252,7 +257,7 @@ describe("category-skill-reminder hook", () => {
   describe("event handling", () => {
     test("should reset state on session.deleted event", async () => {
       // given - sisyphus agent with reminder already shown
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "delete-session"
       updateSessionAgent(sessionID, "Sisyphus")
 
@@ -278,7 +283,7 @@ describe("category-skill-reminder hook", () => {
 
     test("should reset state on session.compacted event", async () => {
       // given - sisyphus agent with reminder already shown
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "compact-session"
       updateSessionAgent(sessionID, "Sisyphus")
 
@@ -306,7 +311,7 @@ describe("category-skill-reminder hook", () => {
   describe("case insensitivity", () => {
     test("should handle tool names case-insensitively", async () => {
       // given - sisyphus agent with mixed case tool names
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "case-session"
       updateSessionAgent(sessionID, "Sisyphus")
 
@@ -325,7 +330,7 @@ describe("category-skill-reminder hook", () => {
 
     test("should handle delegation tool names case-insensitively", async () => {
       // given - sisyphus agent using DELEGATE_TASK in uppercase
-      const hook = createCategorySkillReminderHook(createMockPluginInput())
+      const hook = createHook()
       const sessionID = "case-delegate-session"
       updateSessionAgent(sessionID, "Sisyphus")
 
@@ -343,4 +348,71 @@ describe("category-skill-reminder hook", () => {
       clearSessionAgent(sessionID)
     })
   })
+
+  describe("dynamic skills reminder message", () => {
+    test("shows built-in skills when only built-in skills are available", async () => {
+      // given
+      const availableSkills: AvailableSkill[] = [
+        { name: "frontend-ui-ux", description: "Frontend UI/UX work", location: "plugin" },
+        { name: "git-master", description: "Git operations", location: "plugin" },
+        { name: "playwright", description: "Browser automation", location: "plugin" },
+      ]
+      const hook = createHook(availableSkills)
+      const sessionID = "builtins-only"
+      updateSessionAgent(sessionID, "Sisyphus")
+      const output = { title: "", output: "result", metadata: {} }
+
+      // when
+      await hook["tool.execute.after"]({ tool: "edit", sessionID, callID: "1" }, output)
+      await hook["tool.execute.after"]({ tool: "edit", sessionID, callID: "2" }, output)
+      await hook["tool.execute.after"]({ tool: "edit", sessionID, callID: "3" }, output)
+
+      // then
+      expect(output.output).toContain("**Built-in**:")
+      expect(output.output).toContain("frontend-ui-ux")
+      expect(output.output).toContain("**⚡ YOUR SKILLS (PRIORITY)**")
+      expect(output.output).toContain("load_skills=[\"frontend-ui-ux\"")
+    })
+
+    test("emphasizes user skills with PRIORITY and uses first user skill in example", async () => {
+      // given
+      const availableSkills: AvailableSkill[] = [
+        { name: "frontend-ui-ux", description: "Frontend UI/UX work", location: "plugin" },
+        { name: "react-19", description: "React 19 expertise", location: "user" },
+        { name: "web-designer", description: "Visual design", location: "user" },
+      ]
+      const hook = createHook(availableSkills)
+      const sessionID = "user-skills"
+      updateSessionAgent(sessionID, "Atlas")
+      const output = { title: "", output: "result", metadata: {} }
+
+      // when
+      await hook["tool.execute.after"]({ tool: "bash", sessionID, callID: "1" }, output)
+      await hook["tool.execute.after"]({ tool: "bash", sessionID, callID: "2" }, output)
+      await hook["tool.execute.after"]({ tool: "bash", sessionID, callID: "3" }, output)
+
+      // then
+      expect(output.output).toContain("**⚡ YOUR SKILLS (PRIORITY)**")
+      expect(output.output).toContain("react-19")
+      expect(output.output).toContain("> User-installed skills OVERRIDE")
+      expect(output.output).toContain("load_skills=[\"react-19\"")
+    })
+
+    test("still injects a generic reminder when no skills are provided", async () => {
+      // given
+      const hook = createHook([])
+      const sessionID = "no-skills"
+      updateSessionAgent(sessionID, "Sisyphus")
+      const output = { title: "", output: "result", metadata: {} }
+
+      // when
+      await hook["tool.execute.after"]({ tool: "read", sessionID, callID: "1" }, output)
+      await hook["tool.execute.after"]({ tool: "read", sessionID, callID: "2" }, output)
+      await hook["tool.execute.after"]({ tool: "read", sessionID, callID: "3" }, output)
+
+      // then
+      expect(output.output).toContain("[Category+Skill Reminder]")
+      expect(output.output).toContain("load_skills=[]")
+    })
+  })
 })

src/hooks/category-skill-reminder/index.ts

@@ -1,4 +1,5 @@
 import type { PluginInput } from "@opencode-ai/plugin"
+import type { AvailableSkill } from "../../agents/dynamic-agent-prompt-builder"
 import { getSessionAgent } from "../../features/claude-code-session-state"
 import { log } from "../../shared"
 
@@ -34,33 +35,41 @@ const DELEGATION_TOOLS = new Set([
   "task",
 ])
 
-const REMINDER_MESSAGE = `
-[Category+Skill Reminder]
+function formatSkillNames(skills: AvailableSkill[], limit: number): string {
+  if (skills.length === 0) return "(none)"
+  const shown = skills.slice(0, limit).map((s) => s.name)
+  const remaining = skills.length - shown.length
+  const suffix = remaining > 0 ? ` (+${remaining} more)` : ""
+  return shown.join(", ") + suffix
+}
 
-You are an orchestrator agent. Consider whether this work should be delegated:
+function buildReminderMessage(availableSkills: AvailableSkill[]): string {
+  const builtinSkills = availableSkills.filter((s) => s.location === "plugin")
+  const customSkills = availableSkills.filter((s) => s.location !== "plugin")
 
-**DELEGATE when:**
-- UI/Frontend work → category: "visual-engineering", skills: ["frontend-ui-ux"]
-- Complex logic/architecture → category: "ultrabrain"
-- Quick/trivial tasks → category: "quick"
-- Git operations → skills: ["git-master"]
-- Browser automation → skills: ["playwright"] or ["agent-browser"]
+  const builtinText = formatSkillNames(builtinSkills, 8)
+  const customText = formatSkillNames(customSkills, 8)
 
-**DO IT YOURSELF when:**
-- Gathering context/exploring codebase
-- Simple edits that are part of a larger task you're coordinating
-- Tasks requiring your full context understanding
+  const exampleSkillName = customSkills[0]?.name ?? builtinSkills[0]?.name
+  const loadSkills = exampleSkillName ? `["${exampleSkillName}"]` : "[]"
 
-Example delegation:
-\`\`\`
-delegate_task(
-  category="visual-engineering",
-  load_skills=["frontend-ui-ux"],
-  description="Implement responsive navbar with animations",
-  run_in_background=true
-)
-\`\`\`
-`
+  const lines = [
+    "",
+    "[Category+Skill Reminder]",
+    "",
+    `**Built-in**: ${builtinText}`,
+    `**⚡ YOUR SKILLS (PRIORITY)**: ${customText}`,
+    "",
+    "> User-installed skills OVERRIDE built-in defaults. ALWAYS prefer YOUR SKILLS when domain matches.",
+    "",
+    "```typescript",
+    `delegate_task(category=\"visual-engineering\", load_skills=${loadSkills}, run_in_background=true)`,
+    "```",
+    "",
+  ]
+
+  return lines.join("\n")
+}
 
 interface ToolExecuteInput {
   tool: string
@@ -81,8 +90,12 @@ interface SessionState {
   toolCallCount: number
 }
 
-export function createCategorySkillReminderHook(_ctx: PluginInput) {
+export function createCategorySkillReminderHook(
+  _ctx: PluginInput,
+  availableSkills: AvailableSkill[] = []
+) {
   const sessionStates = new Map<string, SessionState>()
+  const reminderMessage = buildReminderMessage(availableSkills)
 
   function getOrCreateState(sessionID: string): SessionState {
     if (!sessionStates.has(sessionID)) {
@@ -130,7 +143,7 @@ export function createCategorySkillReminderHook(_ctx: PluginInput) {
     state.toolCallCount++
 
     if (state.toolCallCount >= 3 && !state.delegationUsed && !state.reminderShown) {
-      output.output += REMINDER_MESSAGE
+      output.output += reminderMessage
       state.reminderShown = true
       log("[category-skill-reminder] Reminder injected", { 
         sessionID, 

src/hooks/claude-code-hooks/AGENTS.md

@@ -4,12 +4,12 @@
 
 Full Claude Code `settings.json` hook compatibility layer. Intercepts OpenCode events to execute external scripts/commands.
 
-**Config Sources** (priority): `.claude/settings.json` (project) > `~/.claude/settings.json` (global)
+**Config Sources** (priority): `.claude/settings.local.json` > `.claude/settings.json` (project) > `~/.claude/settings.json` (global)
 
 ## STRUCTURE
 ```
 claude-code-hooks/
-├── index.ts              # Main factory (401 lines)
+├── index.ts              # Main factory (421 lines)
 ├── config.ts             # Loads ~/.claude/settings.json
 ├── config-loader.ts      # Extended config (disabledHooks)
 ├── pre-tool-use.ts       # PreToolUse executor
@@ -19,6 +19,7 @@ claude-code-hooks/
 ├── pre-compact.ts        # PreCompact executor
 ├── transcript.ts         # Tool use recording
 ├── tool-input-cache.ts   # Pre→post input caching
+├── todo.ts               # Todo integration
 └── types.ts              # Hook & IO type definitions
 ```
 
@@ -31,22 +32,16 @@ claude-code-hooks/
 | Stop | Session idle/end | Inject | sessionId, parentSessionId, cwd |
 | PreCompact | Before summarize | No | sessionId, cwd |
 
-## CONFIG SOURCES
-Priority (highest first):
-1. `.claude/settings.local.json` (Project-local, git-ignored)
-2. `.claude/settings.json` (Project)
-3. `~/.claude/settings.json` (Global user)
-
 ## HOOK EXECUTION
-- **Matchers**: Hooks filter by tool name or event type via regex/glob.
-- **Commands**: Executed via subprocess with env vars (`$SESSION_ID`, `$TOOL_NAME`).
+- **Matchers**: Hooks filter by tool name or event type via regex/glob
+- **Commands**: Executed via subprocess with env vars (`$SESSION_ID`, `$TOOL_NAME`)
 - **Exit Codes**:
   - `0`: Pass (Success)
   - `1`: Warn (Continue with system message)
   - `2`: Block (Abort operation/prompt)
 
 ## ANTI-PATTERNS
-- **Heavy PreToolUse**: Runs before EVERY tool; keep logic light to avoid latency.
-- **Blocking non-critical**: Prefer PostToolUse warnings for non-fatal issues.
-- **Direct state mutation**: Use `updatedInput` in PreToolUse instead of side effects.
-- **Ignoring Exit Codes**: Ensure scripts return `2` to properly block sensitive tools.
+- **Heavy PreToolUse**: Runs before EVERY tool; keep logic light to avoid latency
+- **Blocking non-critical**: Prefer PostToolUse warnings for non-fatal issues
+- **Direct state mutation**: Use `updatedInput` in PreToolUse instead of side effects
+- **Ignoring Exit Codes**: Ensure scripts return `2` to properly block sensitive tools

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

@@ -1,14 +1,4 @@
-import { describe, expect, it, mock, beforeEach } from "bun:test"
-
-// Mock dependencies before importing
-const mockInjectHookMessage = mock(() => true)
-mock.module("../../features/hook-message-injector", () => ({
-  injectHookMessage: mockInjectHookMessage,
-}))
-
-mock.module("../../shared/logger", () => ({
-  log: () => {},
-}))
+import { describe, expect, it, mock } from "bun:test"
 
 mock.module("../../shared/system-directive", () => ({
   createSystemDirective: (type: string) => `[DIRECTIVE:${type}]`,
@@ -25,78 +15,45 @@ mock.module("../../shared/system-directive", () => ({
 }))
 
 import { createCompactionContextInjector } from "./index"
-import type { SummarizeContext } from "./index"
 
 describe("createCompactionContextInjector", () => {
-  beforeEach(() => {
-    mockInjectHookMessage.mockClear()
-  })
-
   describe("Agent Verification State preservation", () => {
     it("includes Agent Verification State section in compaction prompt", async () => {
-      // given
+      //#given
       const injector = createCompactionContextInjector()
-      const context: SummarizeContext = {
-        sessionID: "test-session",
-        providerID: "anthropic",
-        modelID: "claude-sonnet-4-5",
-        usageRatio: 0.85,
-        directory: "/test/dir",
-      }
 
-      // when
-      await injector(context)
+      //#when
+      const prompt = injector()
 
-      // then
-      expect(mockInjectHookMessage).toHaveBeenCalledTimes(1)
-      const calls = mockInjectHookMessage.mock.calls as unknown as [string, string, unknown][]
-      const injectedPrompt = calls[0]?.[1] ?? ""
-      expect(injectedPrompt).toContain("Agent Verification State")
-      expect(injectedPrompt).toContain("Current Agent")
-      expect(injectedPrompt).toContain("Verification Progress")
+      //#then
+      expect(prompt).toContain("Agent Verification State")
+      expect(prompt).toContain("Current Agent")
+      expect(prompt).toContain("Verification Progress")
     })
 
-    it("includes Momus-specific context for reviewer agents", async () => {
-      // given
+    it("includes reviewer-agent continuity fields", async () => {
+      //#given
       const injector = createCompactionContextInjector()
-      const context: SummarizeContext = {
-        sessionID: "test-session",
-        providerID: "anthropic",
-        modelID: "claude-sonnet-4-5",
-        usageRatio: 0.9,
-        directory: "/test/dir",
-      }
 
-      // when
-      await injector(context)
+      //#when
+      const prompt = injector()
 
-      // then
-      const calls = mockInjectHookMessage.mock.calls as unknown as [string, string, unknown][]
-      const injectedPrompt = calls[0]?.[1] ?? ""
-      expect(injectedPrompt).toContain("Previous Rejections")
-      expect(injectedPrompt).toContain("Acceptance Status")
-      expect(injectedPrompt).toContain("reviewer agents")
+      //#then
+      expect(prompt).toContain("Previous Rejections")
+      expect(prompt).toContain("Acceptance Status")
+      expect(prompt).toContain("reviewer agents")
     })
 
-    it("preserves file verification progress in compaction prompt", async () => {
-      // given
+    it("preserves file verification progress fields", async () => {
+      //#given
       const injector = createCompactionContextInjector()
-      const context: SummarizeContext = {
-        sessionID: "test-session",
-        providerID: "anthropic",
-        modelID: "claude-sonnet-4-5",
-        usageRatio: 0.95,
-        directory: "/test/dir",
-      }
 
-      // when
-      await injector(context)
+      //#when
+      const prompt = injector()
 
-      // then
-      const calls = mockInjectHookMessage.mock.calls as unknown as [string, string, unknown][]
-      const injectedPrompt = calls[0]?.[1] ?? ""
-      expect(injectedPrompt).toContain("Pending Verifications")
-      expect(injectedPrompt).toContain("Files already verified")
+      //#then
+      expect(prompt).toContain("Pending Verifications")
+      expect(prompt).toContain("Files already verified")
     })
   })
 })

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

@@ -1,16 +1,6 @@
-import { injectHookMessage } from "../../features/hook-message-injector"
-import { log } from "../../shared/logger"
 import { createSystemDirective, SystemDirectiveTypes } from "../../shared/system-directive"
 
-export interface SummarizeContext {
-  sessionID: string
-  providerID: string
-  modelID: string
-  usageRatio: number
-  directory: string
-}
-
-const SUMMARIZE_CONTEXT_PROMPT = `${createSystemDirective(SystemDirectiveTypes.COMPACTION_CONTEXT)}
+const COMPACTION_CONTEXT_PROMPT = `${createSystemDirective(SystemDirectiveTypes.COMPACTION_CONTEXT)}
 
 When summarizing this session, you MUST include the following sections in your summary:
 
@@ -58,19 +48,5 @@ This context is critical for maintaining continuity after compaction.
 `
 
 export function createCompactionContextInjector() {
-  return async (ctx: SummarizeContext): Promise<void> => {
-    log("[compaction-context-injector] injecting context", { sessionID: ctx.sessionID })
-
-    const success = injectHookMessage(ctx.sessionID, SUMMARIZE_CONTEXT_PROMPT, {
-      agent: "general",
-      model: { providerID: ctx.providerID, modelID: ctx.modelID },
-      path: { cwd: ctx.directory },
-    })
-
-    if (success) {
-      log("[compaction-context-injector] context injected", { sessionID: ctx.sessionID })
-    } else {
-      log("[compaction-context-injector] injection failed", { sessionID: ctx.sessionID })
-    }
-  }
+  return (): string => COMPACTION_CONTEXT_PROMPT
 }

src/hooks/index.ts

@@ -34,7 +34,8 @@ export { createDelegateTaskRetryHook } from "./delegate-task-retry";
 export { createQuestionLabelTruncatorHook } from "./question-label-truncator";
 export { createSubagentQuestionBlockerHook } from "./subagent-question-blocker";
 export { createStopContinuationGuardHook, type StopContinuationGuard } from "./stop-continuation-guard";
-export { createCompactionContextInjector, type SummarizeContext } from "./compaction-context-injector";
+export { createCompactionContextInjector } from "./compaction-context-injector";
 export { createUnstableAgentBabysitterHook } from "./unstable-agent-babysitter";
 export { createPreemptiveCompactionHook } from "./preemptive-compaction";
 export { createTasksTodowriteDisablerHook } from "./tasks-todowrite-disabler";
+export { createWriteExistingFileGuardHook } from "./write-existing-file-guard";

src/hooks/preemptive-compaction.test.ts

@@ -34,7 +34,7 @@ describe("preemptive-compaction", () => {
             info: {
               role: "assistant",
               providerID: "anthropic",
-              modelID: "claude-opus-4-5",
+              modelID: "claude-opus-4-6",
               tokens: {
                 input: 180000,
                 output: 0,
@@ -60,6 +60,41 @@ describe("preemptive-compaction", () => {
     expect(summarize).toHaveBeenCalled()
   })
 
+  test("triggers summarize for non-anthropic providers when usage exceeds threshold", async () => {
+    //#given
+    const messages = mock(() =>
+      Promise.resolve({
+        data: [
+          {
+            info: {
+              role: "assistant",
+              providerID: "openai",
+              modelID: "gpt-5.2",
+              tokens: {
+                input: 180000,
+                output: 0,
+                reasoning: 0,
+                cache: { read: 0, write: 0 },
+              },
+            },
+          },
+        ],
+      })
+    )
+    const summarize = mock(() => Promise.resolve())
+    const hook = createPreemptiveCompactionHook(createMockCtx({ messages, summarize }))
+    const output = { title: "", output: "", metadata: {} }
+
+    //#when
+    await hook["tool.execute.after"](
+      { tool: "Read", sessionID, callID: "call-3" },
+      output
+    )
+
+    //#then
+    expect(summarize).toHaveBeenCalled()
+  })
+
   test("does not summarize when usage is below threshold", async () => {
     // #given
     const messages = mock(() =>
@@ -69,7 +104,7 @@ describe("preemptive-compaction", () => {
             info: {
               role: "assistant",
               providerID: "anthropic",
-              modelID: "claude-opus-4-5",
+              modelID: "claude-opus-4-6",
               tokens: {
                 input: 100000,
                 output: 0,

src/hooks/preemptive-compaction.ts

@@ -1,8 +1,10 @@
+const DEFAULT_ACTUAL_LIMIT = 200_000
+
 const ANTHROPIC_ACTUAL_LIMIT =
   process.env.ANTHROPIC_1M_CONTEXT === "true" ||
   process.env.VERTEX_ANTHROPIC_1M_CONTEXT === "true"
     ? 1_000_000
-    : 200_000
+    : DEFAULT_ACTUAL_LIMIT
 
 const PREEMPTIVE_COMPACTION_THRESHOLD = 0.78
 
@@ -59,11 +61,14 @@ export function createPreemptiveCompactionHook(ctx: PluginInput) {
       if (assistantMessages.length === 0) return
 
       const lastAssistant = assistantMessages[assistantMessages.length - 1]
-      if (lastAssistant.providerID !== "anthropic") return
+      const actualLimit =
+        lastAssistant.providerID === "anthropic"
+          ? ANTHROPIC_ACTUAL_LIMIT
+          : DEFAULT_ACTUAL_LIMIT
 
       const lastTokens = lastAssistant.tokens
       const totalInputTokens = (lastTokens?.input ?? 0) + (lastTokens?.cache?.read ?? 0)
-      const usageRatio = totalInputTokens / ANTHROPIC_ACTUAL_LIMIT
+      const usageRatio = totalInputTokens / actualLimit
 
       if (usageRatio < PREEMPTIVE_COMPACTION_THRESHOLD) return
 

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

@@ -352,6 +352,121 @@ describe("prometheus-md-only", () => {
     })
   })
 
+  describe("boulder state priority over message files (fixes #927)", () => {
+    const BOULDER_DIR = join(tmpdir(), `boulder-test-${randomUUID()}`)
+    const BOULDER_FILE = join(BOULDER_DIR, ".sisyphus", "boulder.json")
+
+    beforeEach(() => {
+      mkdirSync(join(BOULDER_DIR, ".sisyphus"), { recursive: true })
+    })
+
+    afterEach(() => {
+      rmSync(BOULDER_DIR, { recursive: true, force: true })
+    })
+
+    //#given session was started with prometheus (first message), but /start-work set boulder agent to atlas
+    //#when user types "continue" after interruption (memory cleared, falls back to message files)
+    //#then should use boulder state agent (atlas), not message file agent (prometheus)
+    test("should prioritize boulder agent over message file agent", async () => {
+      // given - prometheus in message files (from /plan)
+      setupMessageStorage(TEST_SESSION_ID, "prometheus")
+      
+      // given - atlas in boulder state (from /start-work)
+      writeFileSync(BOULDER_FILE, JSON.stringify({
+        active_plan: "/test/plan.md",
+        started_at: new Date().toISOString(),
+        session_ids: [TEST_SESSION_ID],
+        plan_name: "test-plan",
+        agent: "atlas"
+      }))
+
+      const hook = createPrometheusMdOnlyHook({
+        client: {},
+        directory: BOULDER_DIR,
+      } as never)
+
+      const input = {
+        tool: "Write",
+        sessionID: TEST_SESSION_ID,
+        callID: "call-1",
+      }
+      const output = {
+        args: { filePath: "/path/to/code.ts" },
+      }
+
+      // when / then - should NOT block because boulder says atlas, not prometheus
+      await expect(
+        hook["tool.execute.before"](input, output)
+      ).resolves.toBeUndefined()
+    })
+
+    test("should use prometheus from boulder state when set", async () => {
+      // given - atlas in message files (from some other agent)
+      setupMessageStorage(TEST_SESSION_ID, "atlas")
+      
+      // given - prometheus in boulder state (edge case, but should honor it)
+      writeFileSync(BOULDER_FILE, JSON.stringify({
+        active_plan: "/test/plan.md",
+        started_at: new Date().toISOString(),
+        session_ids: [TEST_SESSION_ID],
+        plan_name: "test-plan",
+        agent: "prometheus"
+      }))
+
+      const hook = createPrometheusMdOnlyHook({
+        client: {},
+        directory: BOULDER_DIR,
+      } as never)
+
+      const input = {
+        tool: "Write",
+        sessionID: TEST_SESSION_ID,
+        callID: "call-1",
+      }
+      const output = {
+        args: { filePath: "/path/to/code.ts" },
+      }
+
+      // when / then - should block because boulder says prometheus
+      await expect(
+        hook["tool.execute.before"](input, output)
+      ).rejects.toThrow("can only write/edit .md files")
+    })
+
+    test("should fall back to message files when session not in boulder", async () => {
+      // given - prometheus in message files
+      setupMessageStorage(TEST_SESSION_ID, "prometheus")
+      
+      // given - boulder state exists but for different session
+      writeFileSync(BOULDER_FILE, JSON.stringify({
+        active_plan: "/test/plan.md",
+        started_at: new Date().toISOString(),
+        session_ids: ["other-session-id"],
+        plan_name: "test-plan",
+        agent: "atlas"
+      }))
+
+      const hook = createPrometheusMdOnlyHook({
+        client: {},
+        directory: BOULDER_DIR,
+      } as never)
+
+      const input = {
+        tool: "Write",
+        sessionID: TEST_SESSION_ID,
+        callID: "call-1",
+      }
+      const output = {
+        args: { filePath: "/path/to/code.ts" },
+      }
+
+      // when / then - should block because falls back to message files (prometheus)
+      await expect(
+        hook["tool.execute.before"](input, output)
+      ).rejects.toThrow("can only write/edit .md files")
+    })
+  })
+
   describe("without message storage", () => {
     test("should handle missing session gracefully (no agent found)", async () => {
       // given

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

@@ -4,6 +4,7 @@ import { join, resolve, relative, isAbsolute } from "node:path"
 import { HOOK_NAME, PROMETHEUS_AGENT, ALLOWED_EXTENSIONS, ALLOWED_PATH_PREFIX, BLOCKED_TOOLS, PLANNING_CONSULT_WARNING, PROMETHEUS_WORKFLOW_REMINDER } from "./constants"
 import { findNearestMessageWithFields, findFirstMessageWithAgent, MESSAGE_STORAGE } from "../../features/hook-message-injector"
 import { getSessionAgent } from "../../features/claude-code-session-state"
+import { readBoulderState } from "../../features/boulder-state"
 import { log } from "../../shared/logger"
 import { SYSTEM_DIRECTIVE_PREFIX } from "../../shared/system-directive"
 import { getAgentDisplayName } from "../../shared/agent-display-names"
@@ -70,8 +71,31 @@ function getAgentFromMessageFiles(sessionID: string): string | undefined {
   return findFirstMessageWithAgent(messageDir) ?? findNearestMessageWithFields(messageDir)?.agent
 }
 
-function getAgentFromSession(sessionID: string): string | undefined {
-  return getSessionAgent(sessionID) ?? getAgentFromMessageFiles(sessionID)
+/**
+ * Get the effective agent for the session.
+ * Priority order:
+ * 1. In-memory session agent (most recent, set by /start-work)
+ * 2. Boulder state agent (persisted across restarts, fixes #927)
+ * 3. Message files (fallback for sessions without boulder state)
+ *
+ * This fixes issue #927 where after interruption:
+ * - In-memory map is cleared (process restart)
+ * - Message files return "prometheus" (oldest message from /plan)
+ * - But boulder.json has agent: "atlas" (set by /start-work)
+ */
+function getAgentFromSession(sessionID: string, directory: string): string | undefined {
+  // Check in-memory first (current session)
+  const memoryAgent = getSessionAgent(sessionID)
+  if (memoryAgent) return memoryAgent
+
+  // Check boulder state (persisted across restarts) - fixes #927
+  const boulderState = readBoulderState(directory)
+  if (boulderState?.session_ids.includes(sessionID) && boulderState.agent) {
+    return boulderState.agent
+  }
+
+  // Fallback to message files
+  return getAgentFromMessageFiles(sessionID)
 }
 
 export function createPrometheusMdOnlyHook(ctx: PluginInput) {
@@ -80,7 +104,7 @@ export function createPrometheusMdOnlyHook(ctx: PluginInput) {
       input: { tool: string; sessionID: string; callID: string },
       output: { args: Record<string, unknown>; message?: string }
     ): Promise<void> => {
-      const agentName = getAgentFromSession(input.sessionID)
+      const agentName = getAgentFromSession(input.sessionID, ctx.directory)
 
       if (agentName !== PROMETHEUS_AGENT) {
         return

src/hooks/start-work/index.ts

@@ -102,7 +102,7 @@ All ${progress.total} tasks are done. Create a new plan with: /plan "your task"`
             if (existingState) {
               clearBoulderState(ctx.directory)
             }
-            const newState = createBoulderState(matchedPlan, sessionId)
+            const newState = createBoulderState(matchedPlan, sessionId, "atlas")
             writeBoulderState(ctx.directory, newState)
             
             contextInfo = `
@@ -187,7 +187,7 @@ All ${plans.length} plan(s) are complete. Create a new plan with: /plan "your ta
         } else if (incompletePlans.length === 1) {
           const planPath = incompletePlans[0]
           const progress = getPlanProgress(planPath)
-          const newState = createBoulderState(planPath, sessionId)
+          const newState = createBoulderState(planPath, sessionId, "atlas")
           writeBoulderState(ctx.directory, newState)
 
           contextInfo += `

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

@@ -41,7 +41,7 @@ describe("createThinkModeHook integration", () => {
         const hook = createThinkModeHook()
         const input = createMockInput(
           "github-copilot",
-          "claude-opus-4-5",
+          "claude-opus-4-6",
           "Please think deeply about this problem"
         )
 
@@ -50,7 +50,7 @@ describe("createThinkModeHook integration", () => {
 
         // then should upgrade to high variant and inject thinking config
         const message = input.message as MessageWithInjectedProps
-        expect(input.message.model?.modelID).toBe("claude-opus-4-5-high")
+        expect(input.message.model?.modelID).toBe("claude-opus-4-6-high")
         expect(message.thinking).toBeDefined()
         expect((message.thinking as Record<string, unknown>)?.type).toBe(
           "enabled"
@@ -61,11 +61,11 @@ describe("createThinkModeHook integration", () => {
       })
 
       it("should handle github-copilot Claude with dots in version", async () => {
-        // given a github-copilot Claude model with dot format (claude-opus-4.5)
+        // given a github-copilot Claude model with dot format (claude-opus-4.6)
         const hook = createThinkModeHook()
         const input = createMockInput(
           "github-copilot",
-          "claude-opus-4.5",
+          "claude-opus-4.6",
           "ultrathink mode"
         )
 
@@ -74,7 +74,7 @@ describe("createThinkModeHook integration", () => {
 
         // then should upgrade to high variant (hyphen format)
         const message = input.message as MessageWithInjectedProps
-        expect(input.message.model?.modelID).toBe("claude-opus-4-5-high")
+        expect(input.message.model?.modelID).toBe("claude-opus-4-6-high")
         expect(message.thinking).toBeDefined()
       })
 
@@ -179,7 +179,7 @@ describe("createThinkModeHook integration", () => {
         const hook = createThinkModeHook()
         const input = createMockInput(
           "github-copilot",
-          "claude-opus-4-5",
+          "claude-opus-4-6",
           "Just do this task"
         )
         const originalModelID = input.message.model?.modelID
@@ -271,7 +271,7 @@ describe("createThinkModeHook integration", () => {
       const hook = createThinkModeHook()
       const input = createMockInput(
         "github-copilot",
-        "claude-opus-4-5-high",
+        "claude-opus-4-6-high",
         "think deeply"
       )
 
@@ -280,7 +280,7 @@ describe("createThinkModeHook integration", () => {
 
       // then should NOT modify the model (already high)
       const message = input.message as MessageWithInjectedProps
-      expect(input.message.model?.modelID).toBe("claude-opus-4-5-high")
+      expect(input.message.model?.modelID).toBe("claude-opus-4-6-high")
       // No additional thinking config should be injected
       expect(message.thinking).toBeUndefined()
     })
@@ -341,13 +341,13 @@ describe("createThinkModeHook integration", () => {
     it("should handle empty prompt gracefully", async () => {
       // given empty prompt
       const hook = createThinkModeHook()
-      const input = createMockInput("github-copilot", "claude-opus-4-5", "")
+      const input = createMockInput("github-copilot", "claude-opus-4-6", "")
 
       // when the chat.params hook is called
       await hook["chat.params"](input, sessionID)
 
       // then should not upgrade (no think keyword)
-      expect(input.message.model?.modelID).toBe("claude-opus-4-5")
+      expect(input.message.model?.modelID).toBe("claude-opus-4-6")
     })
   })
 

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

@@ -12,7 +12,7 @@ describe("think-mode switcher", () => {
       it("should resolve github-copilot Claude Opus to anthropic config", () => {
         // given a github-copilot provider with Claude Opus model
         const providerID = "github-copilot"
-        const modelID = "claude-opus-4-5"
+        const modelID = "claude-opus-4-6"
 
         // when getting thinking config
         const config = getThinkingConfig(providerID, modelID)
@@ -38,8 +38,8 @@ describe("think-mode switcher", () => {
       })
 
       it("should handle Claude with dots in version number", () => {
-        // given a model ID with dots (claude-opus-4.5)
-        const config = getThinkingConfig("github-copilot", "claude-opus-4.5")
+        // given a model ID with dots (claude-opus-4.6)
+        const config = getThinkingConfig("github-copilot", "claude-opus-4.6")
 
         // then should still return anthropic thinking config
         expect(config).not.toBeNull()
@@ -127,18 +127,26 @@ describe("think-mode switcher", () => {
     describe("getHighVariant with dots vs hyphens", () => {
       it("should handle dots in Claude version numbers", () => {
         // given a Claude model ID with dot format
-        const variant = getHighVariant("claude-opus-4.5")
+        const variant = getHighVariant("claude-opus-4.6")
 
         // then should return high variant with hyphen format
-        expect(variant).toBe("claude-opus-4-5-high")
+        expect(variant).toBe("claude-opus-4-6-high")
       })
 
       it("should handle hyphens in Claude version numbers", () => {
         // given a Claude model ID with hyphen format
-        const variant = getHighVariant("claude-opus-4-5")
+        const variant = getHighVariant("claude-opus-4-6")
 
         // then should return high variant
-        expect(variant).toBe("claude-opus-4-5-high")
+        expect(variant).toBe("claude-opus-4-6-high")
+      })
+
+      it("should handle claude-opus-4-6 high variant", () => {
+        // given a Claude Opus 4.6 model ID
+        const variant = getHighVariant("claude-opus-4-6")
+
+        // then should return high variant
+        expect(variant).toBe("claude-opus-4-6-high")
       })
 
       it("should handle dots in GPT version numbers", () => {
@@ -169,7 +177,7 @@ describe("think-mode switcher", () => {
 
       it("should return null for already-high variants", () => {
         // given model IDs that are already high variants
-        expect(getHighVariant("claude-opus-4-5-high")).toBeNull()
+        expect(getHighVariant("claude-opus-4-6-high")).toBeNull()
         expect(getHighVariant("gpt-5-2-high")).toBeNull()
         expect(getHighVariant("gemini-3-pro-high")).toBeNull()
       })
@@ -185,7 +193,7 @@ describe("think-mode switcher", () => {
   describe("isAlreadyHighVariant", () => {
     it("should detect -high suffix", () => {
       // given model IDs with -high suffix
-      expect(isAlreadyHighVariant("claude-opus-4-5-high")).toBe(true)
+      expect(isAlreadyHighVariant("claude-opus-4-6-high")).toBe(true)
       expect(isAlreadyHighVariant("gpt-5-2-high")).toBe(true)
       expect(isAlreadyHighVariant("gemini-3-pro-high")).toBe(true)
     })
@@ -197,8 +205,8 @@ describe("think-mode switcher", () => {
 
     it("should return false for base models", () => {
       // given base model IDs without -high suffix
-      expect(isAlreadyHighVariant("claude-opus-4-5")).toBe(false)
-      expect(isAlreadyHighVariant("claude-opus-4.5")).toBe(false)
+      expect(isAlreadyHighVariant("claude-opus-4-6")).toBe(false)
+      expect(isAlreadyHighVariant("claude-opus-4.6")).toBe(false)
       expect(isAlreadyHighVariant("gpt-5.2")).toBe(false)
       expect(isAlreadyHighVariant("gemini-3-pro")).toBe(false)
     })
@@ -214,7 +222,7 @@ describe("think-mode switcher", () => {
       it("should return null for already-high variants", () => {
         // given already-high model variants
         expect(
-          getThinkingConfig("anthropic", "claude-opus-4-5-high")
+          getThinkingConfig("anthropic", "claude-opus-4-6-high")
         ).toBeNull()
         expect(getThinkingConfig("openai", "gpt-5-2-high")).toBeNull()
         expect(getThinkingConfig("google", "gemini-3-pro-high")).toBeNull()
@@ -223,7 +231,7 @@ describe("think-mode switcher", () => {
       it("should return null for already-high variants via github-copilot", () => {
         // given already-high model variants via github-copilot
         expect(
-          getThinkingConfig("github-copilot", "claude-opus-4-5-high")
+          getThinkingConfig("github-copilot", "claude-opus-4-6-high")
         ).toBeNull()
         expect(getThinkingConfig("github-copilot", "gpt-5.2-high")).toBeNull()
       })
@@ -250,7 +258,7 @@ describe("think-mode switcher", () => {
   describe("Direct provider configs (backwards compatibility)", () => {
     it("should still work for direct anthropic provider", () => {
       // given direct anthropic provider
-      const config = getThinkingConfig("anthropic", "claude-opus-4-5")
+      const config = getThinkingConfig("anthropic", "claude-opus-4-6")
 
       // then should return anthropic thinking config
       expect(config).not.toBeNull()
@@ -343,10 +351,10 @@ describe("think-mode switcher", () => {
 
       it("should handle prefixes with dots in version numbers", () => {
         // given a model ID with prefix and dots
-        const variant = getHighVariant("vertex_ai/claude-opus-4.5")
+        const variant = getHighVariant("vertex_ai/claude-opus-4.6")
 
         // then should normalize dots and preserve prefix
-        expect(variant).toBe("vertex_ai/claude-opus-4-5-high")
+        expect(variant).toBe("vertex_ai/claude-opus-4-6-high")
       })
 
       it("should handle multiple different prefixes", () => {
@@ -364,7 +372,7 @@ describe("think-mode switcher", () => {
 
       it("should return null for already-high prefixed models", () => {
         // given prefixed model IDs that are already high
-        expect(getHighVariant("vertex_ai/claude-opus-4-5-high")).toBeNull()
+        expect(getHighVariant("vertex_ai/claude-opus-4-6-high")).toBeNull()
         expect(getHighVariant("openai/gpt-5-2-high")).toBeNull()
       })
     })
@@ -372,14 +380,14 @@ describe("think-mode switcher", () => {
     describe("isAlreadyHighVariant with prefixes", () => {
       it("should detect -high suffix in prefixed models", () => {
         // given prefixed model IDs with -high suffix
-        expect(isAlreadyHighVariant("vertex_ai/claude-opus-4-5-high")).toBe(true)
+        expect(isAlreadyHighVariant("vertex_ai/claude-opus-4-6-high")).toBe(true)
         expect(isAlreadyHighVariant("openai/gpt-5-2-high")).toBe(true)
         expect(isAlreadyHighVariant("custom/gemini-3-pro-high")).toBe(true)
       })
 
       it("should return false for prefixed base models", () => {
         // given prefixed base model IDs without -high suffix
-        expect(isAlreadyHighVariant("vertex_ai/claude-opus-4-5")).toBe(false)
+        expect(isAlreadyHighVariant("vertex_ai/claude-opus-4-6")).toBe(false)
         expect(isAlreadyHighVariant("openai/gpt-5-2")).toBe(false)
       })
 
@@ -402,7 +410,7 @@ describe("think-mode switcher", () => {
       it("should work with prefixed models on known providers", () => {
         // given known provider (anthropic) with prefixed model
         // This tests that the base model name is correctly extracted for capability check
-        const config = getThinkingConfig("anthropic", "custom-prefix/claude-opus-4-5")
+        const config = getThinkingConfig("anthropic", "custom-prefix/claude-opus-4-6")
 
         // then should return thinking config (base model is capable)
         expect(config).not.toBeNull()
@@ -411,7 +419,7 @@ describe("think-mode switcher", () => {
 
       it("should return null for prefixed models that are already high", () => {
         // given prefixed already-high model
-        const config = getThinkingConfig("anthropic", "vertex_ai/claude-opus-4-5-high")
+        const config = getThinkingConfig("anthropic", "vertex_ai/claude-opus-4-6-high")
 
         // then should return null
         expect(config).toBeNull()
@@ -444,11 +452,11 @@ describe("think-mode switcher", () => {
 
       it("should not break when switching to high variant in think mode", () => {
         // given think mode switching vertex_ai/claude model to high variant
-        const original = "vertex_ai/claude-opus-4-5"
+        const original = "vertex_ai/claude-opus-4-6"
         const high = getHighVariant(original)
 
         // then the high variant should be valid
-        expect(high).toBe("vertex_ai/claude-opus-4-5-high")
+        expect(high).toBe("vertex_ai/claude-opus-4-6-high")
 
         // #and should be recognized as already high
         expect(isAlreadyHighVariant(high!)).toBe(true)

src/hooks/think-mode/switcher.ts

@@ -38,14 +38,14 @@ function extractModelPrefix(modelID: string): { prefix: string; base: string } {
 
 /**
  * Normalizes model IDs to use consistent hyphen formatting.
- * GitHub Copilot may use dots (claude-opus-4.5) but our maps use hyphens (claude-opus-4-5).
+ * GitHub Copilot may use dots (claude-opus-4.6) but our maps use hyphens (claude-opus-4-6).
  * This ensures lookups work regardless of format.
  *
  * @example
- * normalizeModelID("claude-opus-4.5") // "claude-opus-4-5"
+ * normalizeModelID("claude-opus-4.6") // "claude-opus-4-6"
  * normalizeModelID("gemini-3.5-pro") // "gemini-3-5-pro"
  * normalizeModelID("gpt-5.2") // "gpt-5-2"
- * normalizeModelID("vertex_ai/claude-opus-4.5") // "vertex_ai/claude-opus-4-5"
+ * normalizeModelID("vertex_ai/claude-opus-4.6") // "vertex_ai/claude-opus-4-6"
  */
 function normalizeModelID(modelID: string): string {
   // Replace dots with hyphens when followed by a digit
@@ -59,10 +59,10 @@ function normalizeModelID(modelID: string): string {
  * model provider (Anthropic, Google, OpenAI).
  *
  * @example
- * resolveProvider("github-copilot", "claude-opus-4-5") // "anthropic"
+ * resolveProvider("github-copilot", "claude-opus-4-6") // "anthropic"
  * resolveProvider("github-copilot", "gemini-3-pro") // "google"
  * resolveProvider("github-copilot", "gpt-5.2") // "openai"
- * resolveProvider("anthropic", "claude-opus-4-5") // "anthropic" (unchanged)
+ * resolveProvider("anthropic", "claude-opus-4-6") // "anthropic" (unchanged)
  */
 function resolveProvider(providerID: string, modelID: string): string {
   // GitHub Copilot is a proxy - infer actual provider from model name
@@ -88,7 +88,7 @@ function resolveProvider(providerID: string, modelID: string): string {
 const HIGH_VARIANT_MAP: Record<string, string> = {
   // Claude
   "claude-sonnet-4-5": "claude-sonnet-4-5-high",
-  "claude-opus-4-5": "claude-opus-4-5-high",
+  "claude-opus-4-6": "claude-opus-4-6-high",
    // Gemini
    "gemini-3-pro": "gemini-3-pro-high",
    "gemini-3-pro-low": "gemini-3-pro-high",

src/hooks/write-existing-file-guard/index.test.ts

@@ -0,0 +1,206 @@
+import { describe, test, expect, beforeEach, afterEach } from "bun:test"
+import { createWriteExistingFileGuardHook } from "./index"
+import * as fs from "fs"
+import * as path from "path"
+import * as os from "os"
+
+describe("createWriteExistingFileGuardHook", () => {
+  let tempDir: string
+  let ctx: { directory: string }
+  let hook: ReturnType<typeof createWriteExistingFileGuardHook>
+
+  beforeEach(() => {
+    tempDir = fs.mkdtempSync(path.join(os.tmpdir(), "write-guard-test-"))
+    ctx = { directory: tempDir }
+    hook = createWriteExistingFileGuardHook(ctx as any)
+  })
+
+  afterEach(() => {
+    fs.rmSync(tempDir, { recursive: true, force: true })
+  })
+
+  describe("tool.execute.before", () => {
+    test("allows write to non-existing file", async () => {
+      //#given
+      const nonExistingFile = path.join(tempDir, "new-file.txt")
+      const input = { tool: "Write", sessionID: "ses_1", callID: "call_1" }
+      const output = { args: { filePath: nonExistingFile, content: "hello" } }
+
+      //#when
+      const result = hook["tool.execute.before"]?.(input as any, output as any)
+
+      //#then
+      await expect(result).resolves.toBeUndefined()
+    })
+
+    test("blocks write to existing file", async () => {
+      //#given
+      const existingFile = path.join(tempDir, "existing-file.txt")
+      fs.writeFileSync(existingFile, "existing content")
+      const input = { tool: "Write", sessionID: "ses_1", callID: "call_1" }
+      const output = { args: { filePath: existingFile, content: "new content" } }
+
+      //#when
+      const result = hook["tool.execute.before"]?.(input as any, output as any)
+
+      //#then
+      await expect(result).rejects.toThrow("File already exists. Use edit tool instead.")
+    })
+
+    test("blocks write tool (lowercase) to existing file", async () => {
+      //#given
+      const existingFile = path.join(tempDir, "existing-file.txt")
+      fs.writeFileSync(existingFile, "existing content")
+      const input = { tool: "write", sessionID: "ses_1", callID: "call_1" }
+      const output = { args: { filePath: existingFile, content: "new content" } }
+
+      //#when
+      const result = hook["tool.execute.before"]?.(input as any, output as any)
+
+      //#then
+      await expect(result).rejects.toThrow("File already exists. Use edit tool instead.")
+    })
+
+    test("ignores non-write tools", async () => {
+      //#given
+      const existingFile = path.join(tempDir, "existing-file.txt")
+      fs.writeFileSync(existingFile, "existing content")
+      const input = { tool: "Edit", sessionID: "ses_1", callID: "call_1" }
+      const output = { args: { filePath: existingFile, content: "new content" } }
+
+      //#when
+      const result = hook["tool.execute.before"]?.(input as any, output as any)
+
+      //#then
+      await expect(result).resolves.toBeUndefined()
+    })
+
+    test("ignores tools without any file path arg", async () => {
+      //#given
+      const input = { tool: "Write", sessionID: "ses_1", callID: "call_1" }
+      const output = { args: { command: "ls" } }
+
+      //#when
+      const result = hook["tool.execute.before"]?.(input as any, output as any)
+
+      //#then
+      await expect(result).resolves.toBeUndefined()
+    })
+
+    describe("alternative arg names", () => {
+      test("blocks write using 'path' arg to existing file", async () => {
+        //#given
+        const existingFile = path.join(tempDir, "existing-file.txt")
+        fs.writeFileSync(existingFile, "existing content")
+        const input = { tool: "Write", sessionID: "ses_1", callID: "call_1" }
+        const output = { args: { path: existingFile, content: "new content" } }
+
+        //#when
+        const result = hook["tool.execute.before"]?.(input as any, output as any)
+
+        //#then
+        await expect(result).rejects.toThrow("File already exists. Use edit tool instead.")
+      })
+
+      test("blocks write using 'file_path' arg to existing file", async () => {
+        //#given
+        const existingFile = path.join(tempDir, "existing-file.txt")
+        fs.writeFileSync(existingFile, "existing content")
+        const input = { tool: "Write", sessionID: "ses_1", callID: "call_1" }
+        const output = { args: { file_path: existingFile, content: "new content" } }
+
+        //#when
+        const result = hook["tool.execute.before"]?.(input as any, output as any)
+
+        //#then
+        await expect(result).rejects.toThrow("File already exists. Use edit tool instead.")
+      })
+
+      test("allows write using 'path' arg to non-existing file", async () => {
+        //#given
+        const nonExistingFile = path.join(tempDir, "new-file.txt")
+        const input = { tool: "Write", sessionID: "ses_1", callID: "call_1" }
+        const output = { args: { path: nonExistingFile, content: "hello" } }
+
+        //#when
+        const result = hook["tool.execute.before"]?.(input as any, output as any)
+
+        //#then
+        await expect(result).resolves.toBeUndefined()
+      })
+
+      test("allows write using 'file_path' arg to non-existing file", async () => {
+        //#given
+        const nonExistingFile = path.join(tempDir, "new-file.txt")
+        const input = { tool: "Write", sessionID: "ses_1", callID: "call_1" }
+        const output = { args: { file_path: nonExistingFile, content: "hello" } }
+
+        //#when
+        const result = hook["tool.execute.before"]?.(input as any, output as any)
+
+        //#then
+        await expect(result).resolves.toBeUndefined()
+      })
+    })
+
+    describe("relative path resolution using ctx.directory", () => {
+      test("blocks write to existing file using relative path", async () => {
+        //#given
+        const existingFile = path.join(tempDir, "existing-file.txt")
+        fs.writeFileSync(existingFile, "existing content")
+        const input = { tool: "Write", sessionID: "ses_1", callID: "call_1" }
+        const output = { args: { filePath: "existing-file.txt", content: "new content" } }
+
+        //#when
+        const result = hook["tool.execute.before"]?.(input as any, output as any)
+
+        //#then
+        await expect(result).rejects.toThrow("File already exists. Use edit tool instead.")
+      })
+
+      test("allows write to non-existing file using relative path", async () => {
+        //#given
+        const input = { tool: "Write", sessionID: "ses_1", callID: "call_1" }
+        const output = { args: { filePath: "new-file.txt", content: "hello" } }
+
+        //#when
+        const result = hook["tool.execute.before"]?.(input as any, output as any)
+
+        //#then
+        await expect(result).resolves.toBeUndefined()
+      })
+
+      test("blocks write to nested relative path when file exists", async () => {
+        //#given
+        const subDir = path.join(tempDir, "subdir")
+        fs.mkdirSync(subDir)
+        const existingFile = path.join(subDir, "existing.txt")
+        fs.writeFileSync(existingFile, "existing content")
+        const input = { tool: "Write", sessionID: "ses_1", callID: "call_1" }
+        const output = { args: { filePath: "subdir/existing.txt", content: "new content" } }
+
+        //#when
+        const result = hook["tool.execute.before"]?.(input as any, output as any)
+
+        //#then
+        await expect(result).rejects.toThrow("File already exists. Use edit tool instead.")
+      })
+
+      test("uses ctx.directory not process.cwd for relative path resolution", async () => {
+        //#given
+        const existingFile = path.join(tempDir, "test-file.txt")
+        fs.writeFileSync(existingFile, "content")
+        const differentCtx = { directory: tempDir }
+        const differentHook = createWriteExistingFileGuardHook(differentCtx as any)
+        const input = { tool: "Write", sessionID: "ses_1", callID: "call_1" }
+        const output = { args: { filePath: "test-file.txt", content: "new" } }
+
+        //#when
+        const result = differentHook["tool.execute.before"]?.(input as any, output as any)
+
+        //#then
+        await expect(result).rejects.toThrow("File already exists. Use edit tool instead.")
+      })
+    })
+  })
+})

src/hooks/write-existing-file-guard/index.ts

@@ -0,0 +1,33 @@
+import type { Hooks, PluginInput } from "@opencode-ai/plugin"
+import { existsSync } from "fs"
+import { resolve, isAbsolute } from "path"
+import { log } from "../../shared"
+
+export function createWriteExistingFileGuardHook(ctx: PluginInput): Hooks {
+  return {
+    "tool.execute.before": async (input, output) => {
+      const toolName = input.tool?.toLowerCase()
+      if (toolName !== "write") {
+        return
+      }
+
+      const args = output.args as { filePath?: string; path?: string; file_path?: string } | undefined
+      const filePath = args?.filePath ?? args?.path ?? args?.file_path
+      if (!filePath) {
+        return
+      }
+
+      const resolvedPath = isAbsolute(filePath) ? filePath : resolve(ctx.directory, filePath)
+
+      if (existsSync(resolvedPath)) {
+        log("[write-existing-file-guard] Blocking write to existing file", {
+          sessionID: input.sessionID,
+          filePath,
+          resolvedPath,
+        })
+
+        throw new Error("File already exists. Use edit tool instead.")
+      }
+    },
+  }
+}

src/index.compaction-model-agnostic.static.test.ts

@@ -0,0 +1,21 @@
+import { describe, expect, test } from "bun:test"
+import { readFileSync } from "node:fs"
+
+describe("experimental.session.compacting", () => {
+  test("does not hardcode a model and uses output.context", () => {
+    //#given
+    const indexUrl = new URL("./index.ts", import.meta.url)
+    const content = readFileSync(indexUrl, "utf-8")
+    const hookIndex = content.indexOf('"experimental.session.compacting"')
+
+    //#when
+    const hookSlice = hookIndex >= 0 ? content.slice(hookIndex, hookIndex + 1200) : ""
+
+    //#then
+    expect(hookIndex).toBeGreaterThanOrEqual(0)
+    expect(content.includes('modelID: "claude-opus-4-6"')).toBe(false)
+    expect(hookSlice.includes("output.context.push")).toBe(true)
+    expect(hookSlice.includes("providerID:")).toBe(false)
+    expect(hookSlice.includes("modelID:")).toBe(false)
+  })
+})

src/index.ts

@@ -1,4 +1,5 @@
 import type { Plugin, ToolDefinition } from "@opencode-ai/plugin";
+import type { AvailableSkill } from "./agents/dynamic-agent-prompt-builder";
 import {
   createTodoContinuationEnforcer,
   createContextWindowMonitorHook,
@@ -37,6 +38,7 @@ import {
   createUnstableAgentBabysitterHook,
   createPreemptiveCompactionHook,
   createTasksTodowriteDisablerHook,
+  createWriteExistingFileGuardHook,
 } from "./hooks";
 import {
   contextCollector,
@@ -55,6 +57,7 @@ import {
   discoverOpencodeProjectSkills,
   mergeSkills,
 } from "./features/opencode-skill-loader";
+import type { SkillScope } from "./features/opencode-skill-loader/types";
 import { createBuiltinSkills } from "./features/builtin-skills";
 import { getSystemMcpServerNames } from "./features/claude-code-mcp-loader";
 import {
@@ -83,6 +86,10 @@ import {
   createTaskList,
   createTaskUpdateTool,
 } from "./tools";
+import {
+  CATEGORY_DESCRIPTIONS,
+  DEFAULT_CATEGORIES,
+} from "./tools/delegate-task/constants";
 import { BackgroundManager } from "./features/background-agent";
 import { SkillMcpManager } from "./features/skill-mcp-manager";
 import { initTaskToastManager } from "./features/task-toast-manager";
@@ -100,6 +107,7 @@ import {
   OPENCODE_NATIVE_AGENTS_INJECTION_VERSION,
   injectServerAuthIntoClient,
 } from "./shared";
+import { filterDisabledTools } from "./shared/disabled-tools";
 import { loadPluginConfig } from "./plugin-config";
 import { createModelCacheState } from "./plugin-state";
 import { createConfigHandler } from "./plugin-handlers";
@@ -114,6 +122,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
 
   const pluginConfig = loadPluginConfig(ctx.directory, ctx);
   const disabledHooks = new Set(pluginConfig.disabled_hooks ?? []);
+
   const firstMessageVariantGate = createFirstMessageVariantGate();
 
   const tmuxConfig = {
@@ -241,9 +250,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
     ? createThinkingBlockValidatorHook()
     : null;
 
-  const categorySkillReminder = isHookEnabled("category-skill-reminder")
-    ? createCategorySkillReminderHook(ctx)
-    : null;
+  let categorySkillReminder: ReturnType<typeof createCategorySkillReminderHook> | null = null;
 
   const ralphLoop = isHookEnabled("ralph-loop")
     ? createRalphLoopHook(ctx, {
@@ -280,6 +287,9 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
 
   const questionLabelTruncator = createQuestionLabelTruncatorHook();
   const subagentQuestionBlocker = createSubagentQuestionBlockerHook();
+  const writeExistingFileGuard = isHookEnabled("write-existing-file-guard")
+    ? createWriteExistingFileGuardHook(ctx)
+    : null;
 
   const taskResumeInfo = createTaskResumeInfoHook();
 
@@ -389,33 +399,6 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
   const browserProvider =
     pluginConfig.browser_automation_engine?.provider ?? "playwright";
   const disabledSkills = new Set<string>(pluginConfig.disabled_skills ?? []);
-  const delegateTask = createDelegateTask({
-    manager: backgroundManager,
-    client: ctx.client,
-    directory: ctx.directory,
-    userCategories: pluginConfig.categories,
-    gitMasterConfig: pluginConfig.git_master,
-    sisyphusJuniorModel: pluginConfig.agents?.["sisyphus-junior"]?.model,
-    browserProvider,
-    disabledSkills,
-    onSyncSessionCreated: async (event) => {
-      log("[index] onSyncSessionCreated callback", {
-        sessionID: event.sessionID,
-        parentID: event.parentID,
-        title: event.title,
-      });
-      await tmuxSessionManager.onSessionCreated({
-        type: "session.created",
-        properties: {
-          info: {
-            id: event.sessionID,
-            parentID: event.parentID,
-            title: event.title,
-          },
-        },
-      });
-    },
-  });
   const systemMcpNames = getSystemMcpServerNames();
   const builtinSkills = createBuiltinSkills({ browserProvider, disabledSkills }).filter((skill) => {
       if (skill.mcpConfig) {
@@ -442,6 +425,68 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
     projectSkills,
     opencodeProjectSkills,
   );
+
+  function mapScopeToLocation(scope: SkillScope): AvailableSkill["location"] {
+    if (scope === "user" || scope === "opencode") return "user";
+    if (scope === "project" || scope === "opencode-project") return "project";
+    return "plugin";
+  }
+
+  const availableSkills: AvailableSkill[] = mergedSkills.map((skill) => ({
+    name: skill.name,
+    description: skill.definition.description ?? "",
+    location: mapScopeToLocation(skill.scope),
+  }));
+
+  const mergedCategories = pluginConfig.categories
+    ? { ...DEFAULT_CATEGORIES, ...pluginConfig.categories }
+    : DEFAULT_CATEGORIES;
+
+  const availableCategories = Object.entries(mergedCategories).map(
+    ([name, categoryConfig]) => ({
+      name,
+      description:
+        pluginConfig.categories?.[name]?.description
+          ?? CATEGORY_DESCRIPTIONS[name]
+          ?? "General tasks",
+      model: categoryConfig.model,
+    }),
+  );
+
+  const delegateTask = createDelegateTask({
+    manager: backgroundManager,
+    client: ctx.client,
+    directory: ctx.directory,
+    userCategories: pluginConfig.categories,
+    gitMasterConfig: pluginConfig.git_master,
+    sisyphusJuniorModel: pluginConfig.agents?.["sisyphus-junior"]?.model,
+    browserProvider,
+    disabledSkills,
+    availableCategories,
+    availableSkills,
+    onSyncSessionCreated: async (event) => {
+      log("[index] onSyncSessionCreated callback", {
+        sessionID: event.sessionID,
+        parentID: event.parentID,
+        title: event.title,
+      });
+      await tmuxSessionManager.onSessionCreated({
+        type: "session.created",
+        properties: {
+          info: {
+            id: event.sessionID,
+            parentID: event.parentID,
+            title: event.title,
+          },
+        },
+      });
+    },
+  });
+
+  categorySkillReminder = isHookEnabled("category-skill-reminder")
+    ? createCategorySkillReminderHook(ctx, availableSkills)
+    : null;
+
   const skillMcpManager = new SkillMcpManager();
   const getSessionIDForMcp = () => getMainSessionID() || "";
   const skillTool = createSkillTool({
@@ -483,19 +528,26 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
       }
     : {};
 
+  const allTools: Record<string, ToolDefinition> = {
+    ...builtinTools,
+    ...backgroundTools,
+    call_omo_agent: callOmoAgent,
+    ...(lookAt ? { look_at: lookAt } : {}),
+    delegate_task: delegateTask,
+    skill: skillTool,
+    skill_mcp: skillMcpTool,
+    slashcommand: slashcommandTool,
+    interactive_bash,
+    ...taskToolsRecord,
+  };
+
+  const filteredTools: Record<string, ToolDefinition> = filterDisabledTools(
+    allTools,
+    pluginConfig.disabled_tools,
+  );
+
   return {
-    tool: {
-      ...builtinTools,
-      ...backgroundTools,
-      call_omo_agent: callOmoAgent,
-      ...(lookAt ? { look_at: lookAt } : {}),
-      delegate_task: delegateTask,
-      skill: skillTool,
-      skill_mcp: skillMcpTool,
-      slashcommand: slashcommandTool,
-      interactive_bash,
-      ...taskToolsRecord,
-    },
+    tool: filteredTools,
 
     "chat.message": async (input, output) => {
       if (input.agent) {
@@ -720,6 +772,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
 
     "tool.execute.before": async (input, output) => {
       await subagentQuestionBlocker["tool.execute.before"]?.(input, output);
+      await writeExistingFileGuard?.["tool.execute.before"]?.(input, output);
       await questionLabelTruncator["tool.execute.before"]?.(input, output);
       await claudeCodeHooks["tool.execute.before"](input, output);
       await nonInteractiveEnv?.["tool.execute.before"](input, output);
@@ -837,17 +890,14 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
       await taskResumeInfo["tool.execute.after"](input, output);
     },
 
-    "experimental.session.compacting": async (input: { sessionID: string }) => {
+    "experimental.session.compacting": async (
+      _input: { sessionID: string },
+      output: { context: string[] },
+    ): Promise<void> => {
       if (!compactionContextInjector) {
         return;
       }
-      await compactionContextInjector({
-        sessionID: input.sessionID,
-        providerID: "anthropic",
-        modelID: "claude-opus-4-5",
-        usageRatio: 0.8,
-        directory: ctx.directory,
-      });
+      output.context.push(compactionContextInjector());
     },
   };
 };

src/mcp/AGENTS.md

@@ -14,7 +14,7 @@ Tier 1 of three-tier MCP system: 3 built-in remote HTTP MCPs.
 ```
 mcp/
 ├── index.ts        # createBuiltinMcps() factory
-├── websearch.ts    # Exa AI web search
+├── websearch.ts    # Exa AI / Tavily web search
 ├── context7.ts     # Library documentation
 ├── grep-app.ts     # GitHub code search
 ├── types.ts        # McpNameSchema
@@ -26,26 +26,16 @@ mcp/
 | Name | URL | Purpose | Auth |
 |------|-----|---------|------|
 | websearch | mcp.exa.ai / mcp.tavily.com | Real-time web search | EXA_API_KEY / TAVILY_API_KEY |
-| context7 | mcp.context7.com/mcp | Library docs | CONTEXT7_API_KEY |
+| context7 | mcp.context7.com/mcp | Library docs | CONTEXT7_API_KEY (optional) |
 | grep_app | mcp.grep.app | GitHub code search | None |
 
-## THREE-TIER MCP SYSTEM
-
-1. **Built-in** (this directory): websearch, context7, grep_app
-2. **Claude Code compat**: `.mcp.json` with `${VAR}` expansion
-3. **Skill-embedded**: YAML frontmatter in skills (handled by skill-mcp-manager)
-
 ## Websearch Provider Configuration
 
-The `websearch` MCP supports multiple providers. Exa is the default for backward compatibility and works without an API key.
-
 | Provider | URL | Auth | API Key Required |
 |----------|-----|------|------------------|
 | exa (default) | mcp.exa.ai | x-api-key header | No (optional) |
 | tavily | mcp.tavily.com | Authorization Bearer | Yes |
 
-### Configuration Example
-
 ```jsonc
 {
   "websearch": {
@@ -54,17 +44,6 @@ The `websearch` MCP supports multiple providers. Exa is the default for backward
 }
 ```
 
-### Environment Variables
-
-- `EXA_API_KEY`: Optional. Used when provider is `exa`.
-- `TAVILY_API_KEY`: Required when provider is `tavily`.
-
-### Priority and Behavior
-
-- **Default**: Exa is used if no provider is specified.
-- **Backward Compatibility**: Existing setups using `EXA_API_KEY` continue to work without changes.
-- **Validation**: Selecting `tavily` without providing `TAVILY_API_KEY` will result in a configuration error.
-
 ## CONFIG PATTERN
 
 ```typescript
@@ -77,15 +56,6 @@ export const mcp_name = {
 }
 ```
 
-## USAGE
-
-```typescript
-import { createBuiltinMcps } from "./mcp"
-
-const mcps = createBuiltinMcps()  // Enable all
-const mcps = createBuiltinMcps(["websearch"])  // Disable specific
-```
-
 ## HOW TO ADD
 
 1. Create `src/mcp/my-mcp.ts`
@@ -96,6 +66,5 @@ const mcps = createBuiltinMcps(["websearch"])  // Disable specific
 
 - **Remote only**: HTTP/SSE, no stdio
 - **Disable**: User can set `disabled_mcps: ["name"]` in config
-- **Context7**: Optional auth using `CONTEXT7_API_KEY` env var
-- **Exa**: Optional auth using `EXA_API_KEY` env var
+- **Exa**: Default provider, works without API key
 - **Tavily**: Requires `TAVILY_API_KEY` env var

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

@@ -23,12 +23,6 @@ beforeEach(() => {
     oracle: { name: "oracle", prompt: "test", mode: "subagent" },
   })
 
-  spyOn(sisyphusJunior, "createSisyphusJuniorAgentWithOverrides" as any).mockReturnValue({
-    name: "sisyphus-junior",
-    prompt: "test",
-    mode: "subagent",
-  })
-
   spyOn(commandLoader, "loadUserCommands" as any).mockResolvedValue({})
   spyOn(commandLoader, "loadProjectCommands" as any).mockResolvedValue({})
   spyOn(commandLoader, "loadOpencodeGlobalCommands" as any).mockResolvedValue({})
@@ -63,7 +57,7 @@ beforeEach(() => {
   spyOn(mcpModule, "createBuiltinMcps" as any).mockReturnValue({})
 
   spyOn(shared, "log" as any).mockImplementation(() => {})
-  spyOn(shared, "fetchAvailableModels" as any).mockResolvedValue(new Set(["anthropic/claude-opus-4-5"]))
+  spyOn(shared, "fetchAvailableModels" as any).mockResolvedValue(new Set(["anthropic/claude-opus-4-6"]))
   spyOn(shared, "readConnectedProvidersCache" as any).mockReturnValue(null)
 
   spyOn(configDir, "getOpenCodeConfigPaths" as any).mockReturnValue({
@@ -73,7 +67,7 @@ beforeEach(() => {
 
   spyOn(permissionCompat, "migrateAgentConfig" as any).mockImplementation((config: Record<string, unknown>) => config)
 
-  spyOn(modelResolver, "resolveModelWithFallback" as any).mockReturnValue({ model: "anthropic/claude-opus-4-5" })
+  spyOn(modelResolver, "resolveModelWithFallback" as any).mockReturnValue({ model: "anthropic/claude-opus-4-6" })
 })
 
 afterEach(() => {
@@ -105,6 +99,66 @@ afterEach(() => {
   ;(modelResolver.resolveModelWithFallback as any)?.mockRestore?.()
 })
 
+describe("Sisyphus-Junior model inheritance", () => {
+  test("does not inherit UI-selected model as system default", async () => {
+    // #given
+    const pluginConfig: OhMyOpenCodeConfig = {}
+    const config: Record<string, unknown> = {
+      model: "opencode/kimi-k2.5-free",
+      agent: {},
+    }
+    const handler = createConfigHandler({
+      ctx: { directory: "/tmp" },
+      pluginConfig,
+      modelCacheState: {
+        anthropicContext1MEnabled: false,
+        modelContextLimitsCache: new Map(),
+      },
+    })
+
+    // #when
+    await handler(config)
+
+    // #then
+    const agentConfig = config.agent as Record<string, { model?: string }>
+    expect(agentConfig["sisyphus-junior"]?.model).toBe(
+      sisyphusJunior.SISYPHUS_JUNIOR_DEFAULTS.model
+    )
+  })
+
+  test("uses explicitly configured sisyphus-junior model", async () => {
+    // #given
+    const pluginConfig: OhMyOpenCodeConfig = {
+      agents: {
+        "sisyphus-junior": {
+          model: "openai/gpt-5.3-codex",
+        },
+      },
+    }
+    const config: Record<string, unknown> = {
+      model: "opencode/kimi-k2.5-free",
+      agent: {},
+    }
+    const handler = createConfigHandler({
+      ctx: { directory: "/tmp" },
+      pluginConfig,
+      modelCacheState: {
+        anthropicContext1MEnabled: false,
+        modelContextLimitsCache: new Map(),
+      },
+    })
+
+    // #when
+    await handler(config)
+
+    // #then
+    const agentConfig = config.agent as Record<string, { model?: string }>
+    expect(agentConfig["sisyphus-junior"]?.model).toBe(
+      "openai/gpt-5.3-codex"
+    )
+  })
+})
+
 describe("Plan agent demote behavior", () => {
   test("orders core agents as sisyphus -> hephaestus -> prometheus -> atlas", async () => {
     // #given
@@ -123,7 +177,7 @@ describe("Plan agent demote behavior", () => {
       },
     }
     const config: Record<string, unknown> = {
-      model: "anthropic/claude-opus-4-5",
+      model: "anthropic/claude-opus-4-6",
       agent: {},
     }
     const handler = createConfigHandler({
@@ -154,7 +208,7 @@ describe("Plan agent demote behavior", () => {
       },
     }
     const config: Record<string, unknown> = {
-      model: "anthropic/claude-opus-4-5",
+      model: "anthropic/claude-opus-4-6",
       agent: {
         plan: {
           name: "plan",
@@ -191,7 +245,7 @@ describe("Plan agent demote behavior", () => {
       },
     }
     const config: Record<string, unknown> = {
-      model: "anthropic/claude-opus-4-5",
+      model: "anthropic/claude-opus-4-6",
       agent: {
         plan: {
           name: "plan",
@@ -228,7 +282,7 @@ describe("Plan agent demote behavior", () => {
       },
     }
     const config: Record<string, unknown> = {
-      model: "anthropic/claude-opus-4-5",
+      model: "anthropic/claude-opus-4-6",
       agent: {},
     }
     const handler = createConfigHandler({
@@ -263,7 +317,7 @@ describe("Agent permission defaults", () => {
     })
     const pluginConfig: OhMyOpenCodeConfig = {}
     const config: Record<string, unknown> = {
-      model: "anthropic/claude-opus-4-5",
+      model: "anthropic/claude-opus-4-6",
       agent: {},
     }
     const handler = createConfigHandler({
@@ -295,7 +349,7 @@ describe("Prometheus category config resolution", () => {
 
     // then
     expect(config).toBeDefined()
-    expect(config?.model).toBe("openai/gpt-5.2-codex")
+    expect(config?.model).toBe("openai/gpt-5.3-codex")
     expect(config?.variant).toBe("xhigh")
   })
 
@@ -355,7 +409,7 @@ describe("Prometheus category config resolution", () => {
 
     // then - falls back to DEFAULT_CATEGORIES
     expect(config).toBeDefined()
-    expect(config?.model).toBe("openai/gpt-5.2-codex")
+    expect(config?.model).toBe("openai/gpt-5.3-codex")
     expect(config?.variant).toBe("xhigh")
   })
 
@@ -406,7 +460,7 @@ describe("Prometheus direct override priority over category", () => {
       },
     }
     const config: Record<string, unknown> = {
-      model: "anthropic/claude-opus-4-5",
+      model: "anthropic/claude-opus-4-6",
       agent: {},
     }
     const handler = createConfigHandler({
@@ -446,7 +500,7 @@ describe("Prometheus direct override priority over category", () => {
       },
     }
     const config: Record<string, unknown> = {
-      model: "anthropic/claude-opus-4-5",
+      model: "anthropic/claude-opus-4-6",
       agent: {},
     }
     const handler = createConfigHandler({
@@ -487,7 +541,7 @@ describe("Prometheus direct override priority over category", () => {
       },
     }
     const config: Record<string, unknown> = {
-      model: "anthropic/claude-opus-4-5",
+      model: "anthropic/claude-opus-4-6",
       agent: {},
     }
     const handler = createConfigHandler({
@@ -522,7 +576,7 @@ describe("Prometheus direct override priority over category", () => {
       },
     }
     const config: Record<string, unknown> = {
-      model: "anthropic/claude-opus-4-5",
+      model: "anthropic/claude-opus-4-6",
       agent: {},
     }
     const handler = createConfigHandler({
@@ -560,7 +614,7 @@ describe("Deadlock prevention - fetchAvailableModels must not receive client", (
       },
     }
     const config: Record<string, unknown> = {
-      model: "anthropic/claude-opus-4-5",
+      model: "anthropic/claude-opus-4-6",
       agent: {},
     }
     const mockClient = {

src/plugin-handlers/config-handler.ts

@@ -222,7 +222,7 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
 
       agentConfig["sisyphus-junior"] = createSisyphusJuniorAgentWithOverrides(
         pluginConfig.agents?.["sisyphus-junior"],
-        config.model as string | undefined
+        undefined
       );
 
       if (builderEnabled) {

src/plugin-state.ts

@@ -9,22 +9,3 @@ export function createModelCacheState(): ModelCacheState {
     anthropicContext1MEnabled: false,
   };
 }
-
-export function getModelLimit(
-  state: ModelCacheState,
-  providerID: string,
-  modelID: string
-): number | undefined {
-  const key = `${providerID}/${modelID}`;
-  const cached = state.modelContextLimitsCache.get(key);
-  if (cached) return cached;
-
-  if (
-    providerID === "anthropic" &&
-    state.anthropicContext1MEnabled &&
-    modelID.includes("sonnet")
-  ) {
-    return 1_000_000;
-  }
-  return undefined;
-}

src/shared/AGENTS.md

@@ -9,12 +9,14 @@
 ## STRUCTURE
 ```
 shared/
-├── tmux/                  # Tmux TUI integration (types, utils, constants)
+├── tmux/                  # Tmux TUI integration (types, utils 312 lines, constants)
 ├── logger.ts              # File-based logging (/tmp/oh-my-opencode.log) - 53 imports
 ├── dynamic-truncator.ts   # Token-aware context window management (194 lines)
 ├── model-resolver.ts      # 3-step resolution (Override → Fallback → Default)
 ├── model-requirements.ts  # Agent/category model fallback chains (162 lines)
-├── model-availability.ts  # Provider model fetching & fuzzy matching (154 lines)
+├── model-availability.ts  # Provider model fetching & fuzzy matching (357 lines)
+├── model-sanitizer.ts     # Model name sanitization
+├── model-suggestion-retry.ts # Model suggestion on failure
 ├── jsonc-parser.ts        # JSONC parsing with comment support
 ├── frontmatter.ts         # YAML frontmatter extraction (JSON_SCHEMA only) - 9 imports
 ├── data-path.ts           # XDG-compliant storage resolution
@@ -22,16 +24,26 @@ shared/
 ├── claude-config-dir.ts   # ~/.claude resolution - 9 imports
 ├── migration.ts           # Legacy config migration logic (231 lines)
 ├── opencode-version.ts    # Semantic version comparison
-├── permission-compat.ts   # Agent tool restriction enforcement
-├── system-directive.ts    # Unified system message prefix & types
+├── permission-compat.ts   # Agent tool restriction enforcement - 6 imports
+├── system-directive.ts    # Unified system message prefix & types - 8 imports
 ├── session-utils.ts       # Session cursor, orchestrator detection
+├── session-cursor.ts      # Session message cursor tracking
 ├── shell-env.ts           # Cross-platform shell environment
 ├── agent-variant.ts       # Agent variant from config
 ├── zip-extractor.ts       # Binary/Resource ZIP extraction
 ├── deep-merge.ts          # Recursive object merging (proto-pollution safe, MAX_DEPTH=50)
 ├── case-insensitive.ts    # Case-insensitive object lookups
-├── session-cursor.ts      # Session message cursor tracking
 ├── command-executor.ts    # Shell command execution (225 lines)
+├── snake-case.ts          # Case conversion utilities
+├── tool-name.ts           # Tool naming conventions
+├── pattern-matcher.ts     # Pattern matching utilities
+├── port-utils.ts          # Port management
+├── file-utils.ts          # File operation utilities
+├── file-reference-resolver.ts # File reference resolution
+├── connected-providers-cache.ts # Provider caching
+├── external-plugin-detector.ts  # Plugin detection
+├── first-message-variant.ts     # Message variant types
+├── opencode-server-auth.ts      # Authentication utilities
 └── index.ts               # Barrel export for all utilities
 ```
 

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

@@ -8,9 +8,9 @@ describe("Agent Config Integration", () => {
     test("migrates old format agent keys to lowercase", () => {
       // given - config with old format keys
       const oldConfig = {
-        Sisyphus: { model: "anthropic/claude-opus-4-5" },
-        Atlas: { model: "anthropic/claude-opus-4-5" },
-        "Prometheus (Planner)": { model: "anthropic/claude-opus-4-5" },
+        Sisyphus: { model: "anthropic/claude-opus-4-6" },
+        Atlas: { model: "anthropic/claude-opus-4-6" },
+        "Prometheus (Planner)": { model: "anthropic/claude-opus-4-6" },
         "Metis (Plan Consultant)": { model: "anthropic/claude-sonnet-4-5" },
         "Momus (Plan Reviewer)": { model: "anthropic/claude-sonnet-4-5" },
       }
@@ -33,9 +33,9 @@ describe("Agent Config Integration", () => {
       expect(result.migrated).not.toHaveProperty("Momus (Plan Reviewer)")
 
       // then - values are preserved
-      expect(result.migrated.sisyphus).toEqual({ model: "anthropic/claude-opus-4-5" })
-      expect(result.migrated.atlas).toEqual({ model: "anthropic/claude-opus-4-5" })
-      expect(result.migrated.prometheus).toEqual({ model: "anthropic/claude-opus-4-5" })
+      expect(result.migrated.sisyphus).toEqual({ model: "anthropic/claude-opus-4-6" })
+      expect(result.migrated.atlas).toEqual({ model: "anthropic/claude-opus-4-6" })
+      expect(result.migrated.prometheus).toEqual({ model: "anthropic/claude-opus-4-6" })
       
       // then - changed flag is true
       expect(result.changed).toBe(true)
@@ -44,7 +44,7 @@ describe("Agent Config Integration", () => {
     test("preserves already lowercase keys", () => {
       // given - config with lowercase keys
       const config = {
-        sisyphus: { model: "anthropic/claude-opus-4-5" },
+        sisyphus: { model: "anthropic/claude-opus-4-6" },
         oracle: { model: "openai/gpt-5.2" },
         librarian: { model: "opencode/glm-4.7-free" },
       }
@@ -62,9 +62,9 @@ describe("Agent Config Integration", () => {
     test("handles mixed case config", () => {
       // given - config with mixed old and new format
       const mixedConfig = {
-        Sisyphus: { model: "anthropic/claude-opus-4-5" },
+        Sisyphus: { model: "anthropic/claude-opus-4-6" },
         oracle: { model: "openai/gpt-5.2" },
-        "Prometheus (Planner)": { model: "anthropic/claude-opus-4-5" },
+        "Prometheus (Planner)": { model: "anthropic/claude-opus-4-6" },
         librarian: { model: "opencode/glm-4.7-free" },
       }
 
@@ -172,8 +172,8 @@ describe("Agent Config Integration", () => {
     test("old config migrates and displays correctly", () => {
       // given - old format config
       const oldConfig = {
-        Sisyphus: { model: "anthropic/claude-opus-4-5", temperature: 0.1 },
-        "Prometheus (Planner)": { model: "anthropic/claude-opus-4-5" },
+        Sisyphus: { model: "anthropic/claude-opus-4-6", temperature: 0.1 },
+        "Prometheus (Planner)": { model: "anthropic/claude-opus-4-6" },
       }
 
       // when - config is migrated
@@ -192,15 +192,15 @@ describe("Agent Config Integration", () => {
       expect(prometheusDisplay).toBe("Prometheus (Plan Builder)")
 
       // then - config values are preserved
-      expect(result.migrated.sisyphus).toEqual({ model: "anthropic/claude-opus-4-5", temperature: 0.1 })
-      expect(result.migrated.prometheus).toEqual({ model: "anthropic/claude-opus-4-5" })
+      expect(result.migrated.sisyphus).toEqual({ model: "anthropic/claude-opus-4-6", temperature: 0.1 })
+      expect(result.migrated.prometheus).toEqual({ model: "anthropic/claude-opus-4-6" })
     })
 
     test("new config works without migration", () => {
       // given - new format config (already lowercase)
       const newConfig = {
-        sisyphus: { model: "anthropic/claude-opus-4-5" },
-        atlas: { model: "anthropic/claude-opus-4-5" },
+        sisyphus: { model: "anthropic/claude-opus-4-6" },
+        atlas: { model: "anthropic/claude-opus-4-6" },
       }
 
       // when - migration is applied (should be no-op)

src/shared/agent-tool-restrictions.ts

@@ -22,6 +22,7 @@ const AGENT_RESTRICTIONS: Record<string, Record<string, boolean>> = {
     edit: false,
     task: false,
     delegate_task: false,
+    call_omo_agent: false,
   },
 
   metis: {

src/shared/agent-variant.test.ts

@@ -84,14 +84,14 @@ describe("applyAgentVariant", () => {
 
 describe("resolveVariantForModel", () => {
   test("returns agent override variant when configured", () => {
-    // given - use a model in sisyphus chain (claude-opus-4-5 has default variant "max")
+    // given - use a model in sisyphus chain (claude-opus-4-6 has default variant "max")
     // to verify override takes precedence over fallback chain
     const config = {
       agents: {
         sisyphus: { variant: "high" },
       },
     } as OhMyOpenCodeConfig
-    const model = { providerID: "anthropic", modelID: "claude-opus-4-5" }
+    const model = { providerID: "anthropic", modelID: "claude-opus-4-6" }
 
     // when
     const variant = resolveVariantForModel(config, "sisyphus", model)
@@ -103,7 +103,7 @@ describe("resolveVariantForModel", () => {
   test("returns correct variant for anthropic provider", () => {
     // given
     const config = {} as OhMyOpenCodeConfig
-    const model = { providerID: "anthropic", modelID: "claude-opus-4-5" }
+    const model = { providerID: "anthropic", modelID: "claude-opus-4-6" }
 
     // when
     const variant = resolveVariantForModel(config, "sisyphus", model)
@@ -113,9 +113,9 @@ describe("resolveVariantForModel", () => {
   })
 
   test("returns correct variant for openai provider (hephaestus agent)", () => {
-    // #given hephaestus has openai/gpt-5.2-codex with variant "medium" in its chain
+    // #given hephaestus has openai/gpt-5.3-codex with variant "medium" in its chain
     const config = {} as OhMyOpenCodeConfig
-    const model = { providerID: "openai", modelID: "gpt-5.2-codex" }
+    const model = { providerID: "openai", modelID: "gpt-5.3-codex" }
 
     // #when
     const variant = resolveVariantForModel(config, "hephaestus", model)
@@ -151,7 +151,7 @@ describe("resolveVariantForModel", () => {
   test("returns undefined for unknown agent", () => {
     // given
     const config = {} as OhMyOpenCodeConfig
-    const model = { providerID: "anthropic", modelID: "claude-opus-4-5" }
+    const model = { providerID: "anthropic", modelID: "claude-opus-4-6" }
 
     // when
     const variant = resolveVariantForModel(config, "nonexistent-agent", model)
@@ -179,7 +179,7 @@ describe("resolveVariantForModel", () => {
         "custom-agent": { category: "ultrabrain" },
       },
     } as OhMyOpenCodeConfig
-    const model = { providerID: "openai", modelID: "gpt-5.2-codex" }
+    const model = { providerID: "openai", modelID: "gpt-5.3-codex" }
 
     // when
     const variant = resolveVariantForModel(config, "custom-agent", model)
@@ -203,7 +203,7 @@ describe("resolveVariantForModel", () => {
   test("returns correct variant for oracle agent with anthropic", () => {
     // given
     const config = {} as OhMyOpenCodeConfig
-    const model = { providerID: "anthropic", modelID: "claude-opus-4-5" }
+    const model = { providerID: "anthropic", modelID: "claude-opus-4-6" }
 
     // when
     const variant = resolveVariantForModel(config, "oracle", model)

src/shared/connected-providers-cache.ts

@@ -11,8 +11,16 @@ interface ConnectedProvidersCache {
 	updatedAt: string
 }
 
+interface ModelMetadata {
+	id: string
+	provider?: string
+	context?: number
+	output?: number
+	name?: string
+}
+
 interface ProviderModelsCache {
-	models: Record<string, string[]>
+	models: Record<string, string[] | ModelMetadata[]>
 	connected: string[]
 	updatedAt: string
 }

src/shared/disabled-tools.ts

@@ -0,0 +1,19 @@
+import type { ToolDefinition } from "@opencode-ai/plugin"
+
+export function filterDisabledTools(
+  tools: Record<string, ToolDefinition>,
+  disabledTools: readonly string[] | undefined
+): Record<string, ToolDefinition> {
+  if (!disabledTools || disabledTools.length === 0) {
+    return tools
+  }
+
+  const disabledToolSet = new Set(disabledTools)
+  const filtered: Record<string, ToolDefinition> = {}
+  for (const [toolName, toolDefinition] of Object.entries(tools)) {
+    if (!disabledToolSet.has(toolName)) {
+      filtered[toolName] = toolDefinition
+    }
+  }
+  return filtered
+}

src/shared/index.ts

@@ -40,3 +40,4 @@ export * from "./session-utils"
 export * from "./tmux"
 export * from "./model-suggestion-retry"
 export * from "./opencode-server-auth"
+export * from "./port-utils"

src/shared/migration.test.ts

@@ -4,8 +4,10 @@ import * as path from "path"
 import {
   AGENT_NAME_MAP,
   HOOK_NAME_MAP,
+  MODEL_VERSION_MAP,
   migrateAgentNames,
   migrateHookNames,
+  migrateModelVersions,
   migrateConfigFile,
   migrateAgentConfigToCategory,
   shouldDeleteAgentConfig,
@@ -15,7 +17,7 @@ describe("migrateAgentNames", () => {
   test("migrates legacy OmO names to lowercase", () => {
     // given: Config with legacy OmO agent names
     const agents = {
-      omo: { model: "anthropic/claude-opus-4-5" },
+      omo: { model: "anthropic/claude-opus-4-6" },
       OmO: { temperature: 0.5 },
       "OmO-Plan": { prompt: "custom prompt" },
     }
@@ -84,7 +86,7 @@ describe("migrateAgentNames", () => {
   test("migrates orchestrator-sisyphus to atlas", () => {
     // given: Config with legacy orchestrator-sisyphus agent name
     const agents = {
-      "orchestrator-sisyphus": { model: "anthropic/claude-opus-4-5" },
+      "orchestrator-sisyphus": { model: "anthropic/claude-opus-4-6" },
     }
 
     // when: Migrate agent names
@@ -92,14 +94,14 @@ describe("migrateAgentNames", () => {
 
     // then: orchestrator-sisyphus should be migrated to atlas
     expect(changed).toBe(true)
-    expect(migrated["atlas"]).toEqual({ model: "anthropic/claude-opus-4-5" })
+    expect(migrated["atlas"]).toEqual({ model: "anthropic/claude-opus-4-6" })
     expect(migrated["orchestrator-sisyphus"]).toBeUndefined()
   })
 
   test("migrates lowercase atlas to atlas", () => {
     // given: Config with lowercase atlas agent name
     const agents = {
-      atlas: { model: "anthropic/claude-opus-4-5" },
+      atlas: { model: "anthropic/claude-opus-4-6" },
     }
 
     // when: Migrate agent names
@@ -107,7 +109,7 @@ describe("migrateAgentNames", () => {
 
     // then: lowercase atlas should remain atlas (no change needed)
     expect(changed).toBe(false)
-    expect(migrated["atlas"]).toEqual({ model: "anthropic/claude-opus-4-5" })
+    expect(migrated["atlas"]).toEqual({ model: "anthropic/claude-opus-4-6" })
   })
 
   test("migrates Sisyphus variants to lowercase", () => {
@@ -369,29 +371,81 @@ describe("migrateConfigFile", () => {
     expect(needsWrite).toBe(false)
   })
 
-  test("handles migration of all legacy items together", () => {
-    // given: Config with all legacy items
-    const rawConfig: Record<string, unknown> = {
-      omo_agent: { disabled: false },
-      agents: {
-        omo: { model: "test" },
-        "OmO-Plan": { prompt: "custom" },
-      },
-      disabled_hooks: ["anthropic-auto-compact"],
-    }
+   test("handles migration of all legacy items together", () => {
+     // given: Config with all legacy items
+     const rawConfig: Record<string, unknown> = {
+       omo_agent: { disabled: false },
+       agents: {
+         omo: { model: "test" },
+         "OmO-Plan": { prompt: "custom" },
+       },
+       disabled_hooks: ["anthropic-auto-compact"],
+     }
 
-    // when: Migrate config file
-    const needsWrite = migrateConfigFile(testConfigPath, rawConfig)
+     // when: Migrate config file
+     const needsWrite = migrateConfigFile(testConfigPath, rawConfig)
 
-    // then: All legacy items should be migrated
-    expect(needsWrite).toBe(true)
-    expect(rawConfig.sisyphus_agent).toEqual({ disabled: false })
-    expect(rawConfig.omo_agent).toBeUndefined()
-    const agents = rawConfig.agents as Record<string, unknown>
-    expect(agents["sisyphus"]).toBeDefined()
-    expect(agents["prometheus"]).toBeDefined()
-    expect(rawConfig.disabled_hooks).toContain("anthropic-context-window-limit-recovery")
-  })
+     // then: All legacy items should be migrated
+     expect(needsWrite).toBe(true)
+     expect(rawConfig.sisyphus_agent).toEqual({ disabled: false })
+     expect(rawConfig.omo_agent).toBeUndefined()
+     const agents = rawConfig.agents as Record<string, unknown>
+     expect(agents["sisyphus"]).toBeDefined()
+     expect(agents["prometheus"]).toBeDefined()
+     expect(rawConfig.disabled_hooks).toContain("anthropic-context-window-limit-recovery")
+   })
+
+   test("migrates model versions in agents", () => {
+     // given: Config with old model version in agents
+     const rawConfig: Record<string, unknown> = {
+       agents: {
+         sisyphus: { model: "openai/gpt-5.2-codex", temperature: 0.1 },
+       },
+     }
+
+     // when: Migrate config file
+     const needsWrite = migrateConfigFile(testConfigPath, rawConfig)
+
+     // then: Model version should be migrated
+     expect(needsWrite).toBe(true)
+     const agents = rawConfig.agents as Record<string, Record<string, unknown>>
+     expect(agents["sisyphus"].model).toBe("openai/gpt-5.3-codex")
+   })
+
+   test("migrates model versions in categories", () => {
+     // given: Config with old model version in categories
+     const rawConfig: Record<string, unknown> = {
+       categories: {
+         "my-category": { model: "anthropic/claude-opus-4-5", temperature: 0.2 },
+       },
+     }
+
+     // when: Migrate config file
+     const needsWrite = migrateConfigFile(testConfigPath, rawConfig)
+
+     // then: Model version should be migrated
+     expect(needsWrite).toBe(true)
+     const categories = rawConfig.categories as Record<string, Record<string, unknown>>
+     expect(categories["my-category"].model).toBe("anthropic/claude-opus-4-6")
+   })
+
+   test("does not set needsWrite when no model versions need migration", () => {
+     // given: Config with current model versions
+     const rawConfig: Record<string, unknown> = {
+       agents: {
+         sisyphus: { model: "openai/gpt-5.3-codex" },
+       },
+       categories: {
+         "my-category": { model: "anthropic/claude-opus-4-6" },
+       },
+     }
+
+     // when: Migrate config file
+     const needsWrite = migrateConfigFile(testConfigPath, rawConfig)
+
+     // then: No write should be needed
+     expect(needsWrite).toBe(false)
+   })
 })
 
 describe("migration maps", () => {
@@ -413,6 +467,126 @@ describe("migration maps", () => {
   })
 })
 
+describe("MODEL_VERSION_MAP", () => {
+  test("maps openai/gpt-5.2-codex to openai/gpt-5.3-codex", () => {
+    // given/when: Check MODEL_VERSION_MAP
+    // then: Should contain correct mapping
+    expect(MODEL_VERSION_MAP["openai/gpt-5.2-codex"]).toBe("openai/gpt-5.3-codex")
+  })
+
+  test("maps anthropic/claude-opus-4-5 to anthropic/claude-opus-4-6", () => {
+    // given/when: Check MODEL_VERSION_MAP
+    // then: Should contain correct mapping
+    expect(MODEL_VERSION_MAP["anthropic/claude-opus-4-5"]).toBe("anthropic/claude-opus-4-6")
+  })
+})
+
+describe("migrateModelVersions", () => {
+  test("replaces old model string in agent config", () => {
+    // given: Agent config with old model version
+    const agents = {
+      sisyphus: { model: "openai/gpt-5.2-codex", temperature: 0.1 },
+    }
+
+    // when: Migrate model versions
+    const { migrated, changed } = migrateModelVersions(agents)
+
+    // then: Model should be updated, other fields preserved
+    expect(changed).toBe(true)
+    const sisyphus = migrated["sisyphus"] as Record<string, unknown>
+    expect(sisyphus.model).toBe("openai/gpt-5.3-codex")
+    expect(sisyphus.temperature).toBe(0.1)
+  })
+
+  test("replaces anthropic model version", () => {
+    // given: Agent config with old anthropic model
+    const agents = {
+      prometheus: { model: "anthropic/claude-opus-4-5" },
+    }
+
+    // when: Migrate model versions
+    const { migrated, changed } = migrateModelVersions(agents)
+
+    // then: Model should be updated
+    expect(changed).toBe(true)
+    const prometheus = migrated["prometheus"] as Record<string, unknown>
+    expect(prometheus.model).toBe("anthropic/claude-opus-4-6")
+  })
+
+  test("leaves unknown model strings untouched", () => {
+    // given: Agent config with unknown model
+    const agents = {
+      oracle: { model: "openai/gpt-5.2", temperature: 0.5 },
+    }
+
+    // when: Migrate model versions
+    const { migrated, changed } = migrateModelVersions(agents)
+
+    // then: Config should remain unchanged
+    expect(changed).toBe(false)
+    const oracle = migrated["oracle"] as Record<string, unknown>
+    expect(oracle.model).toBe("openai/gpt-5.2")
+  })
+
+  test("handles agent config with no model field", () => {
+    // given: Agent config without model field
+    const agents = {
+      sisyphus: { temperature: 0.1, prompt: "custom" },
+    }
+
+    // when: Migrate model versions
+    const { migrated, changed } = migrateModelVersions(agents)
+
+    // then: Config should remain unchanged
+    expect(changed).toBe(false)
+    const sisyphus = migrated["sisyphus"] as Record<string, unknown>
+    expect(sisyphus.temperature).toBe(0.1)
+  })
+
+  test("handles agent config with non-string model", () => {
+    // given: Agent config with non-string model
+    const agents = {
+      sisyphus: { model: 123, temperature: 0.1 },
+    }
+
+    // when: Migrate model versions
+    const { migrated, changed } = migrateModelVersions(agents)
+
+    // then: Config should remain unchanged
+    expect(changed).toBe(false)
+  })
+
+  test("migrates multiple agents in one pass", () => {
+    // given: Multiple agents with old models
+    const agents = {
+      sisyphus: { model: "openai/gpt-5.2-codex" },
+      prometheus: { model: "anthropic/claude-opus-4-5" },
+      oracle: { model: "openai/gpt-5.2" },
+    }
+
+    // when: Migrate model versions
+    const { migrated, changed } = migrateModelVersions(agents)
+
+    // then: Only mapped models should be updated
+    expect(changed).toBe(true)
+    expect((migrated["sisyphus"] as Record<string, unknown>).model).toBe("openai/gpt-5.3-codex")
+    expect((migrated["prometheus"] as Record<string, unknown>).model).toBe("anthropic/claude-opus-4-6")
+    expect((migrated["oracle"] as Record<string, unknown>).model).toBe("openai/gpt-5.2")
+  })
+
+  test("handles empty object", () => {
+    // given: Empty agents object
+    const agents = {}
+
+    // when: Migrate model versions
+    const { migrated, changed } = migrateModelVersions(agents)
+
+    // then: Should return empty with no change
+    expect(changed).toBe(false)
+    expect(Object.keys(migrated)).toHaveLength(0)
+  })
+})
+
 describe("migrateAgentConfigToCategory", () => {
   test("migrates model to category when mapping exists", () => {
     // given: Config with a model that has a category mapping
@@ -470,7 +644,7 @@ describe("migrateAgentConfigToCategory", () => {
       { model: "google/gemini-3-flash" },
       { model: "openai/gpt-5.2" },
       { model: "anthropic/claude-haiku-4-5" },
-      { model: "anthropic/claude-opus-4-5" },
+      { model: "anthropic/claude-opus-4-6" },
       { model: "anthropic/claude-sonnet-4-5" },
     ]
 
@@ -550,7 +724,7 @@ describe("shouldDeleteAgentConfig", () => {
     // given: Config with custom model override
     const config = {
       category: "visual-engineering",
-      model: "anthropic/claude-opus-4-5",
+      model: "anthropic/claude-opus-4-6",
     }
 
     // when: Check if config should be deleted

src/shared/migration.ts

@@ -85,10 +85,22 @@ export const MODEL_TO_CATEGORY_MAP: Record<string, string> = {
   "google/gemini-3-flash": "writing",
   "openai/gpt-5.2": "ultrabrain",
   "anthropic/claude-haiku-4-5": "quick",
-  "anthropic/claude-opus-4-5": "unspecified-high",
+  "anthropic/claude-opus-4-6": "unspecified-high",
   "anthropic/claude-sonnet-4-5": "unspecified-low",
 }
 
+/**
+ * Model version migration map: old full model strings → new full model strings.
+ * Used to auto-upgrade hardcoded model versions in user configs when the plugin
+ * bumps to newer model versions.
+ *
+ * Keys are full "provider/model" strings. Only openai and anthropic entries needed.
+ */
+export const MODEL_VERSION_MAP: Record<string, string> = {
+  "openai/gpt-5.2-codex": "openai/gpt-5.3-codex",
+  "anthropic/claude-opus-4-5": "anthropic/claude-opus-4-6",
+}
+
 export function migrateAgentNames(agents: Record<string, unknown>): { migrated: Record<string, unknown>; changed: boolean } {
   const migrated: Record<string, unknown> = {}
   let changed = false
@@ -104,6 +116,25 @@ export function migrateAgentNames(agents: Record<string, unknown>): { migrated:
   return { migrated, changed }
 }
 
+export function migrateModelVersions(configs: Record<string, unknown>): { migrated: Record<string, unknown>; changed: boolean } {
+  const migrated: Record<string, unknown> = {}
+  let changed = false
+
+  for (const [key, value] of Object.entries(configs)) {
+    if (value && typeof value === "object" && !Array.isArray(value)) {
+      const config = value as Record<string, unknown>
+      if (typeof config.model === "string" && MODEL_VERSION_MAP[config.model]) {
+        migrated[key] = { ...config, model: MODEL_VERSION_MAP[config.model] }
+        changed = true
+        continue
+      }
+    }
+    migrated[key] = value
+  }
+
+  return { migrated, changed }
+}
+
 export function migrateHookNames(hooks: string[]): { migrated: string[]; changed: boolean; removed: string[] } {
   const migrated: string[] = []
   const removed: string[] = []
@@ -178,7 +209,25 @@ export function migrateConfigFile(configPath: string, rawConfig: Record<string,
     }
   }
 
+  // Migrate model versions in agents
+  if (rawConfig.agents && typeof rawConfig.agents === "object") {
+    const { migrated, changed } = migrateModelVersions(rawConfig.agents as Record<string, unknown>)
+    if (changed) {
+      rawConfig.agents = migrated
+      needsWrite = true
+      log(`Migrated model versions in agents config`)
+    }
+  }
 
+  // Migrate model versions in categories
+  if (rawConfig.categories && typeof rawConfig.categories === "object") {
+    const { migrated, changed } = migrateModelVersions(rawConfig.categories as Record<string, unknown>)
+    if (changed) {
+      rawConfig.categories = migrated
+      needsWrite = true
+      log(`Migrated model versions in categories config`)
+    }
+  }
 
   if (rawConfig.omo_agent) {
     rawConfig.sisyphus_agent = rawConfig.omo_agent

src/shared/model-availability.test.ts

@@ -33,7 +33,7 @@ describe("fetchAvailableModels", () => {
   it("#given cache file with models #when fetchAvailableModels called with connectedProviders #then returns Set of model IDs", async () => {
     writeModelsCache({
       openai: { id: "openai", models: { "gpt-5.2": { id: "gpt-5.2" } } },
-      anthropic: { id: "anthropic", models: { "claude-opus-4-5": { id: "claude-opus-4-5" } } },
+      anthropic: { id: "anthropic", models: { "claude-opus-4-6": { id: "claude-opus-4-6" } } },
       google: { id: "google", models: { "gemini-3-pro": { id: "gemini-3-pro" } } },
     })
 
@@ -44,7 +44,7 @@ describe("fetchAvailableModels", () => {
     expect(result).toBeInstanceOf(Set)
     expect(result.size).toBe(3)
     expect(result.has("openai/gpt-5.2")).toBe(true)
-    expect(result.has("anthropic/claude-opus-4-5")).toBe(true)
+    expect(result.has("anthropic/claude-opus-4-6")).toBe(true)
     expect(result.has("google/gemini-3-pro")).toBe(true)
   })
 
@@ -67,7 +67,7 @@ describe("fetchAvailableModels", () => {
       model: {
         list: async () => ({
           data: [
-            { id: "gpt-5.2-codex", provider: "openai" },
+            { id: "gpt-5.3-codex", provider: "openai" },
             { id: "gemini-3-pro", provider: "google" },
           ],
         }),
@@ -77,7 +77,7 @@ describe("fetchAvailableModels", () => {
     const result = await fetchAvailableModels(client)
 
     expect(result).toBeInstanceOf(Set)
-    expect(result.has("openai/gpt-5.2-codex")).toBe(true)
+    expect(result.has("openai/gpt-5.3-codex")).toBe(true)
     expect(result.has("google/gemini-3-pro")).toBe(false)
   })
 
@@ -96,7 +96,7 @@ describe("fetchAvailableModels", () => {
       model: {
         list: async () => ({
           data: [
-            { id: "gpt-5.2-codex", provider: "openai" },
+            { id: "gpt-5.3-codex", provider: "openai" },
             { id: "gemini-3-pro", provider: "google" },
           ],
         }),
@@ -106,14 +106,14 @@ describe("fetchAvailableModels", () => {
     const result = await fetchAvailableModels(client, { connectedProviders: ["openai", "google"] })
 
     expect(result).toBeInstanceOf(Set)
-    expect(result.has("openai/gpt-5.2-codex")).toBe(true)
+    expect(result.has("openai/gpt-5.3-codex")).toBe(true)
     expect(result.has("google/gemini-3-pro")).toBe(true)
   })
 
   it("#given cache read twice #when second call made with same providers #then reads fresh each time", async () => {
     writeModelsCache({
       openai: { id: "openai", models: { "gpt-5.2": { id: "gpt-5.2" } } },
-      anthropic: { id: "anthropic", models: { "claude-opus-4-5": { id: "claude-opus-4-5" } } },
+      anthropic: { id: "anthropic", models: { "claude-opus-4-6": { id: "claude-opus-4-6" } } },
     })
 
     const result1 = await fetchAvailableModels(undefined, { connectedProviders: ["openai"] })
@@ -134,7 +134,7 @@ describe("fetchAvailableModels", () => {
 
   it("#given cache file with various providers #when fetchAvailableModels called with all providers #then extracts all IDs correctly", async () => {
     writeModelsCache({
-      openai: { id: "openai", models: { "gpt-5.2-codex": { id: "gpt-5.2-codex" } } },
+      openai: { id: "openai", models: { "gpt-5.3-codex": { id: "gpt-5.3-codex" } } },
       anthropic: { id: "anthropic", models: { "claude-sonnet-4-5": { id: "claude-sonnet-4-5" } } },
       google: { id: "google", models: { "gemini-3-flash": { id: "gemini-3-flash" } } },
       opencode: { id: "opencode", models: { "gpt-5-nano": { id: "gpt-5-nano" } } },
@@ -145,7 +145,7 @@ describe("fetchAvailableModels", () => {
     })
 
     expect(result.size).toBe(4)
-    expect(result.has("openai/gpt-5.2-codex")).toBe(true)
+    expect(result.has("openai/gpt-5.3-codex")).toBe(true)
     expect(result.has("anthropic/claude-sonnet-4-5")).toBe(true)
     expect(result.has("google/gemini-3-flash")).toBe(true)
     expect(result.has("opencode/gpt-5-nano")).toBe(true)
@@ -159,8 +159,8 @@ describe("fuzzyMatchModel", () => {
 	it("should match substring in model name", () => {
 		const available = new Set([
 			"openai/gpt-5.2",
-			"openai/gpt-5.2-codex",
-			"anthropic/claude-opus-4-5",
+			"openai/gpt-5.3-codex",
+			"anthropic/claude-opus-4-6",
 		])
 		const result = fuzzyMatchModel("gpt-5.2", available)
 		expect(result).toBe("openai/gpt-5.2")
@@ -185,7 +185,7 @@ describe("fuzzyMatchModel", () => {
 	it("should prefer exact match over substring match", () => {
 		const available = new Set([
 			"openai/gpt-5.2",
-			"openai/gpt-5.2-codex",
+			"openai/gpt-5.3-codex",
 			"openai/gpt-5.2-ultra",
 		])
 		const result = fuzzyMatchModel("gpt-5.2", available)
@@ -207,13 +207,13 @@ describe("fuzzyMatchModel", () => {
 	// given available models with claude variants
 	// when searching for claude-opus
 	// then return matching claude-opus model
-	it("should match claude-opus to claude-opus-4-5", () => {
+	it("should match claude-opus to claude-opus-4-6", () => {
 		const available = new Set([
-			"anthropic/claude-opus-4-5",
+			"anthropic/claude-opus-4-6",
 			"anthropic/claude-sonnet-4-5",
 		])
 		const result = fuzzyMatchModel("claude-opus", available)
-		expect(result).toBe("anthropic/claude-opus-4-5")
+		expect(result).toBe("anthropic/claude-opus-4-6")
 	})
 
 	// given available models from multiple providers
@@ -222,7 +222,7 @@ describe("fuzzyMatchModel", () => {
 	it("should filter by provider when providers array is given", () => {
 		const available = new Set([
 			"openai/gpt-5.2",
-			"anthropic/claude-opus-4-5",
+			"anthropic/claude-opus-4-6",
 			"google/gemini-3",
 		])
 		const result = fuzzyMatchModel("gpt", available, ["openai"])
@@ -235,7 +235,7 @@ describe("fuzzyMatchModel", () => {
 	it("should return null when provider filter excludes all matches", () => {
 		const available = new Set([
 			"openai/gpt-5.2",
-			"anthropic/claude-opus-4-5",
+			"anthropic/claude-opus-4-6",
 		])
 		const result = fuzzyMatchModel("claude", available, ["openai"])
 		expect(result).toBeNull()
@@ -247,7 +247,7 @@ describe("fuzzyMatchModel", () => {
 	it("should return null when no match found", () => {
 		const available = new Set([
 			"openai/gpt-5.2",
-			"anthropic/claude-opus-4-5",
+			"anthropic/claude-opus-4-6",
 		])
 		const result = fuzzyMatchModel("gemini", available)
 		expect(result).toBeNull()
@@ -259,7 +259,7 @@ describe("fuzzyMatchModel", () => {
 	it("should match case-insensitively", () => {
 		const available = new Set([
 			"openai/gpt-5.2",
-			"anthropic/claude-opus-4-5",
+			"anthropic/claude-opus-4-6",
 		])
 		const result = fuzzyMatchModel("GPT-5.2", available)
 		expect(result).toBe("openai/gpt-5.2")
@@ -270,11 +270,11 @@ describe("fuzzyMatchModel", () => {
 	// then return exact match first
 	it("should prioritize exact match over longer variants", () => {
 		const available = new Set([
-			"anthropic/claude-opus-4-5",
-			"anthropic/claude-opus-4-5-extended",
+			"anthropic/claude-opus-4-6",
+			"anthropic/claude-opus-4-6-extended",
 		])
-		const result = fuzzyMatchModel("claude-opus-4-5", available)
-		expect(result).toBe("anthropic/claude-opus-4-5")
+		const result = fuzzyMatchModel("claude-opus-4-6", available)
+		expect(result).toBe("anthropic/claude-opus-4-6")
 	})
 
 	// given available models with similar model IDs (e.g., glm-4.7 and glm-4.7-free)
@@ -319,7 +319,7 @@ describe("fuzzyMatchModel", () => {
 	it("should search all specified providers", () => {
 		const available = new Set([
 			"openai/gpt-5.2",
-			"anthropic/claude-opus-4-5",
+			"anthropic/claude-opus-4-6",
 			"google/gemini-3",
 		])
 		const result = fuzzyMatchModel("gpt", available, ["openai", "google"])
@@ -464,7 +464,7 @@ describe("fetchAvailableModels with connected providers filtering", () => {
 	it("should filter models by connected providers", async () => {
 		writeModelsCache({
 			openai: { models: { "gpt-5.2": { id: "gpt-5.2" } } },
-			anthropic: { models: { "claude-opus-4-5": { id: "claude-opus-4-5" } } },
+			anthropic: { models: { "claude-opus-4-6": { id: "claude-opus-4-6" } } },
 			google: { models: { "gemini-3-pro": { id: "gemini-3-pro" } } },
 		})
 
@@ -473,7 +473,7 @@ describe("fetchAvailableModels with connected providers filtering", () => {
 		})
 
 		expect(result.size).toBe(1)
-		expect(result.has("anthropic/claude-opus-4-5")).toBe(true)
+		expect(result.has("anthropic/claude-opus-4-6")).toBe(true)
 		expect(result.has("openai/gpt-5.2")).toBe(false)
 		expect(result.has("google/gemini-3-pro")).toBe(false)
 	})
@@ -484,7 +484,7 @@ describe("fetchAvailableModels with connected providers filtering", () => {
 	it("should filter models by multiple connected providers", async () => {
 		writeModelsCache({
 			openai: { models: { "gpt-5.2": { id: "gpt-5.2" } } },
-			anthropic: { models: { "claude-opus-4-5": { id: "claude-opus-4-5" } } },
+			anthropic: { models: { "claude-opus-4-6": { id: "claude-opus-4-6" } } },
 			google: { models: { "gemini-3-pro": { id: "gemini-3-pro" } } },
 		})
 
@@ -493,7 +493,7 @@ describe("fetchAvailableModels with connected providers filtering", () => {
 		})
 
 		expect(result.size).toBe(2)
-		expect(result.has("anthropic/claude-opus-4-5")).toBe(true)
+		expect(result.has("anthropic/claude-opus-4-6")).toBe(true)
 		expect(result.has("google/gemini-3-pro")).toBe(true)
 		expect(result.has("openai/gpt-5.2")).toBe(false)
 	})
@@ -504,7 +504,7 @@ describe("fetchAvailableModels with connected providers filtering", () => {
 	it("should return empty set when connectedProviders is empty", async () => {
 		writeModelsCache({
 			openai: { models: { "gpt-5.2": { id: "gpt-5.2" } } },
-			anthropic: { models: { "claude-opus-4-5": { id: "claude-opus-4-5" } } },
+			anthropic: { models: { "claude-opus-4-6": { id: "claude-opus-4-6" } } },
 		})
 
 		const result = await fetchAvailableModels(undefined, {
@@ -520,7 +520,7 @@ describe("fetchAvailableModels with connected providers filtering", () => {
 	it("should return empty set when connectedProviders not specified", async () => {
 		writeModelsCache({
 			openai: { models: { "gpt-5.2": { id: "gpt-5.2" } } },
-			anthropic: { models: { "claude-opus-4-5": { id: "claude-opus-4-5" } } },
+			anthropic: { models: { "claude-opus-4-6": { id: "claude-opus-4-6" } } },
 		})
 
 		const result = await fetchAvailableModels()
@@ -549,7 +549,7 @@ describe("fetchAvailableModels with connected providers filtering", () => {
 	it("should return models from providers that exist in both cache and connected list", async () => {
 		writeModelsCache({
 			openai: { models: { "gpt-5.2": { id: "gpt-5.2" } } },
-			anthropic: { models: { "claude-opus-4-5": { id: "claude-opus-4-5" } } },
+			anthropic: { models: { "claude-opus-4-6": { id: "claude-opus-4-6" } } },
 		})
 
 		const result = await fetchAvailableModels(undefined, {
@@ -557,7 +557,7 @@ describe("fetchAvailableModels with connected providers filtering", () => {
 		})
 
 		expect(result.size).toBe(1)
-		expect(result.has("anthropic/claude-opus-4-5")).toBe(true)
+		expect(result.has("anthropic/claude-opus-4-6")).toBe(true)
 	})
 
 	// given filtered fetch
@@ -566,7 +566,7 @@ describe("fetchAvailableModels with connected providers filtering", () => {
 	it("should not cache filtered results", async () => {
 		writeModelsCache({
 			openai: { models: { "gpt-5.2": { id: "gpt-5.2" } } },
-			anthropic: { models: { "claude-opus-4-5": { id: "claude-opus-4-5" } } },
+			anthropic: { models: { "claude-opus-4-6": { id: "claude-opus-4-6" } } },
 		})
 
 		// First call with anthropic
@@ -619,7 +619,7 @@ describe("fetchAvailableModels with provider-models cache (whitelist-filtered)",
 		rmSync(tempDir, { recursive: true, force: true })
 	})
 
-	function writeProviderModelsCache(data: { models: Record<string, string[]>; connected: string[] }) {
+	function writeProviderModelsCache(data: { models: Record<string, string[] | any[]>; connected: string[] }) {
 		const cacheDir = join(tempDir, "oh-my-opencode")
 		require("fs").mkdirSync(cacheDir, { recursive: true })
 		writeFileSync(join(cacheDir, "provider-models.json"), JSON.stringify({
@@ -641,13 +641,13 @@ describe("fetchAvailableModels with provider-models cache (whitelist-filtered)",
 		writeProviderModelsCache({
 			models: {
 				opencode: ["glm-4.7-free", "gpt-5-nano"],
-				anthropic: ["claude-opus-4-5"]
+				anthropic: ["claude-opus-4-6"]
 			},
 			connected: ["opencode", "anthropic"]
 		})
 		writeModelsCache({
 			opencode: { models: { "glm-4.7-free": {}, "gpt-5-nano": {}, "gpt-5.2": {} } },
-			anthropic: { models: { "claude-opus-4-5": {}, "claude-sonnet-4-5": {} } }
+			anthropic: { models: { "claude-opus-4-6": {}, "claude-sonnet-4-5": {} } }
 		})
 
 		const result = await fetchAvailableModels(undefined, {
@@ -657,7 +657,7 @@ describe("fetchAvailableModels with provider-models cache (whitelist-filtered)",
 		expect(result.size).toBe(3)
 		expect(result.has("opencode/glm-4.7-free")).toBe(true)
 		expect(result.has("opencode/gpt-5-nano")).toBe(true)
-		expect(result.has("anthropic/claude-opus-4-5")).toBe(true)
+		expect(result.has("anthropic/claude-opus-4-6")).toBe(true)
 		expect(result.has("opencode/gpt-5.2")).toBe(false)
 		expect(result.has("anthropic/claude-sonnet-4-5")).toBe(false)
 	})
@@ -708,7 +708,7 @@ describe("fetchAvailableModels with provider-models cache (whitelist-filtered)",
 		writeProviderModelsCache({
 			models: {
 				opencode: ["glm-4.7-free"],
-				anthropic: ["claude-opus-4-5"],
+				anthropic: ["claude-opus-4-6"],
 				google: ["gemini-3-pro"]
 			},
 			connected: ["opencode", "anthropic", "google"]
@@ -720,18 +720,84 @@ describe("fetchAvailableModels with provider-models cache (whitelist-filtered)",
 
 		expect(result.size).toBe(1)
 		expect(result.has("opencode/glm-4.7-free")).toBe(true)
-		expect(result.has("anthropic/claude-opus-4-5")).toBe(false)
+		expect(result.has("anthropic/claude-opus-4-6")).toBe(false)
 		expect(result.has("google/gemini-3-pro")).toBe(false)
 	})
+
+	it("should handle object[] format with metadata (Ollama-style)", async () => {
+		writeProviderModelsCache({
+			models: {
+				ollama: [
+					{ id: "ministral-3:14b-32k-agent", provider: "ollama", context: 32768, output: 8192 },
+					{ id: "qwen3-coder:32k-agent", provider: "ollama", context: 32768, output: 8192 }
+				]
+			},
+			connected: ["ollama"]
+		})
+
+		const result = await fetchAvailableModels(undefined, {
+			connectedProviders: ["ollama"]
+		})
+
+		expect(result.size).toBe(2)
+		expect(result.has("ollama/ministral-3:14b-32k-agent")).toBe(true)
+		expect(result.has("ollama/qwen3-coder:32k-agent")).toBe(true)
+	})
+
+	it("should handle mixed string[] and object[] formats across providers", async () => {
+		writeProviderModelsCache({
+			models: {
+				anthropic: ["claude-opus-4-6", "claude-sonnet-4-5"],
+				ollama: [
+					{ id: "ministral-3:14b-32k-agent", provider: "ollama" },
+					{ id: "qwen3-coder:32k-agent", provider: "ollama" }
+				]
+			},
+			connected: ["anthropic", "ollama"]
+		})
+
+		const result = await fetchAvailableModels(undefined, {
+			connectedProviders: ["anthropic", "ollama"]
+		})
+
+		expect(result.size).toBe(4)
+		expect(result.has("anthropic/claude-opus-4-6")).toBe(true)
+		expect(result.has("anthropic/claude-sonnet-4-5")).toBe(true)
+		expect(result.has("ollama/ministral-3:14b-32k-agent")).toBe(true)
+		expect(result.has("ollama/qwen3-coder:32k-agent")).toBe(true)
+	})
+
+	it("should skip invalid entries in object[] format", async () => {
+		writeProviderModelsCache({
+			models: {
+				ollama: [
+					{ id: "valid-model", provider: "ollama" },
+					{ provider: "ollama" },
+					{ id: "", provider: "ollama" },
+					null,
+					"string-model"
+				]
+			},
+			connected: ["ollama"]
+		})
+
+		const result = await fetchAvailableModels(undefined, {
+			connectedProviders: ["ollama"]
+		})
+
+		expect(result.size).toBe(2)
+		expect(result.has("ollama/valid-model")).toBe(true)
+		expect(result.has("ollama/string-model")).toBe(true)
+	})
 })
 
 describe("isModelAvailable", () => {
 	it("returns true when model exists via fuzzy match", () => {
 		// given
-		const available = new Set(["openai/gpt-5.2-codex", "anthropic/claude-opus-4-5"])
+		const available = new Set(["openai/gpt-5.3-codex", "anthropic/claude-opus-4-6"])
 
 		// when
-		const result = isModelAvailable("gpt-5.2-codex", available)
+		const result = isModelAvailable("gpt-5.3-codex", available)
 
 		// then
 		expect(result).toBe(true)
@@ -739,10 +805,10 @@ describe("isModelAvailable", () => {
 
 	it("returns false when model not found", () => {
 		// given
-		const available = new Set(["anthropic/claude-opus-4-5"])
+		const available = new Set(["anthropic/claude-opus-4-6"])
 
 		// when
-		const result = isModelAvailable("gpt-5.2-codex", available)
+		const result = isModelAvailable("gpt-5.3-codex", available)
 
 		// then
 		expect(result).toBe(false)
@@ -753,7 +819,7 @@ describe("isModelAvailable", () => {
 		const available = new Set<string>()
 
 		// when
-		const result = isModelAvailable("gpt-5.2-codex", available)
+		const result = isModelAvailable("gpt-5.3-codex", available)
 
 		// then
 		expect(result).toBe(false)

src/shared/model-availability.ts

@@ -2,7 +2,7 @@ import { existsSync, readFileSync } from "fs"
 import { join } from "path"
 import { log } from "./logger"
 import { getOpenCodeCacheDir } from "./data-path"
-import { readProviderModelsCache, hasProviderModelsCache } from "./connected-providers-cache"
+import { readProviderModelsCache, hasProviderModelsCache, readConnectedProvidersCache } from "./connected-providers-cache"
 
 /**
  * Fuzzy match a target model name against available models
@@ -20,7 +20,7 @@ import { readProviderModelsCache, hasProviderModelsCache } from "./connected-pro
  * If providers array is given, only models starting with "provider/" are considered.
  * 
  * @example
- * const available = new Set(["openai/gpt-5.2", "openai/gpt-5.2-codex", "anthropic/claude-opus-4-5"])
+ * const available = new Set(["openai/gpt-5.2", "openai/gpt-5.3-codex", "anthropic/claude-opus-4-6"])
  * fuzzyMatchModel("gpt-5.2", available) // → "openai/gpt-5.2"
  * fuzzyMatchModel("claude", available, ["openai"]) // → null (provider filter excludes anthropic)
  */
@@ -105,7 +105,7 @@ export function fuzzyMatchModel(
 /**
  * Check if a target model is available (fuzzy match by model name, no provider filtering)
  * 
- * @param targetModel - Model name to check (e.g., "gpt-5.2-codex")
+ * @param targetModel - Model name to check (e.g., "gpt-5.3-codex")
  * @param availableModels - Set of available models in "provider/model" format
  * @returns true if model is available, false otherwise
  */
@@ -187,16 +187,23 @@ export async function fetchAvailableModels(
 		if (providerCount === 0) {
 			log("[fetchAvailableModels] provider-models cache empty, falling back to models.json")
 		} else {
-			log("[fetchAvailableModels] using provider-models cache (whitelist-filtered)")
-			
-			for (const [providerId, modelIds] of Object.entries(providerModelsCache.models)) {
-				if (!connectedSet.has(providerId)) {
-					continue
-				}
-				for (const modelId of modelIds) {
+		log("[fetchAvailableModels] using provider-models cache (whitelist-filtered)")
+		
+		for (const [providerId, modelIds] of Object.entries(providerModelsCache.models)) {
+			if (!connectedSet.has(providerId)) {
+				continue
+			}
+			for (const modelItem of modelIds) {
+				// Handle both string[] (legacy) and object[] (with metadata) formats
+				const modelId = typeof modelItem === 'string' 
+					? modelItem 
+					: (modelItem as any)?.id
+				
+				if (modelId) {
 					modelSet.add(`${providerId}/${modelId}`)
 				}
 			}
+		}
 
 			log("[fetchAvailableModels] parsed from provider-models cache", {
 				count: modelSet.size,
@@ -278,19 +285,64 @@ export function isAnyFallbackModelAvailable(
 	fallbackChain: Array<{ providers: string[]; model: string }>,
 	availableModels: Set<string>,
 ): boolean {
-	if (availableModels.size === 0) {
-		return false
-	}
-
-	for (const entry of fallbackChain) {
-		const hasAvailableProvider = entry.providers.some((provider) => {
-			return fuzzyMatchModel(entry.model, availableModels, [provider]) !== null
-		})
-		if (hasAvailableProvider) {
-			return true
+	// If we have models, check them first
+	if (availableModels.size > 0) {
+		for (const entry of fallbackChain) {
+			const hasAvailableProvider = entry.providers.some((provider) => {
+				return fuzzyMatchModel(entry.model, availableModels, [provider]) !== null
+			})
+			if (hasAvailableProvider) {
+				return true
+			}
 		}
 	}
-	log("[isAnyFallbackModelAvailable] no model available in chain", { chainLength: fallbackChain.length })
+
+	// Fallback: check if any provider in the chain is connected
+	// This handles race conditions where availableModels is empty or incomplete
+	// but we know the provider is connected.
+	const connectedProviders = readConnectedProvidersCache()
+	if (connectedProviders) {
+		const connectedSet = new Set(connectedProviders)
+		for (const entry of fallbackChain) {
+			if (entry.providers.some((p) => connectedSet.has(p))) {
+				log("[isAnyFallbackModelAvailable] model not in available set, but provider is connected", {
+					model: entry.model,
+					availableCount: availableModels.size,
+				})
+				return true
+			}
+		}
+	}
+
+	return false
+}
+
+export function isAnyProviderConnected(
+	providers: string[],
+	availableModels: Set<string>,
+): boolean {
+	if (availableModels.size > 0) {
+		const providerSet = new Set(providers)
+		for (const model of availableModels) {
+			const [provider] = model.split("/")
+			if (providerSet.has(provider)) {
+				log("[isAnyProviderConnected] found model from required provider", { provider, model })
+				return true
+			}
+		}
+	}
+
+	const connectedProviders = readConnectedProvidersCache()
+	if (connectedProviders) {
+		const connectedSet = new Set(connectedProviders)
+		for (const provider of providers) {
+			if (connectedSet.has(provider)) {
+				log("[isAnyProviderConnected] provider connected via cache", { provider })
+				return true
+			}
+		}
+	}
+
 	return false
 }
 

src/shared/model-requirements.test.ts

@@ -23,20 +23,20 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     expect(primary.variant).toBe("high")
   })
 
-  test("sisyphus has valid fallbackChain with claude-opus-4-5 as primary and requiresAnyModel", () => {
+  test("sisyphus has claude-opus-4-6 as primary and requiresAnyModel", () => {
     // #given - sisyphus agent requirement
     const sisyphus = AGENT_MODEL_REQUIREMENTS["sisyphus"]
 
     // #when - accessing Sisyphus requirement
-    // #then - fallbackChain exists with claude-opus-4-5 as first entry, glm-4.7-free as last
+    // #then - fallbackChain has claude-opus-4-6 first, glm-4.7-free last
     expect(sisyphus).toBeDefined()
     expect(sisyphus.fallbackChain).toBeArray()
     expect(sisyphus.fallbackChain).toHaveLength(5)
     expect(sisyphus.requiresAnyModel).toBe(true)
 
     const primary = sisyphus.fallbackChain[0]
-    expect(primary.providers[0]).toBe("anthropic")
-    expect(primary.model).toBe("claude-opus-4-5")
+    expect(primary.providers).toEqual(["anthropic", "github-copilot", "opencode"])
+    expect(primary.model).toBe("claude-opus-4-6")
     expect(primary.variant).toBe("max")
 
     const last = sisyphus.fallbackChain[4]
@@ -98,35 +98,35 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     expect(primary.model).toBe("gemini-3-flash")
   })
 
-  test("prometheus has valid fallbackChain with claude-opus-4-5 as primary", () => {
-    // given - prometheus agent requirement
+  test("prometheus has claude-opus-4-6 as primary", () => {
+    // #given - prometheus agent requirement
     const prometheus = AGENT_MODEL_REQUIREMENTS["prometheus"]
 
-    // when - accessing Prometheus requirement
-    // then - fallbackChain exists with claude-opus-4-5 as first entry
+    // #when - accessing Prometheus requirement
+    // #then - claude-opus-4-6 is first
     expect(prometheus).toBeDefined()
     expect(prometheus.fallbackChain).toBeArray()
-    expect(prometheus.fallbackChain.length).toBeGreaterThan(0)
+    expect(prometheus.fallbackChain.length).toBeGreaterThan(1)
 
     const primary = prometheus.fallbackChain[0]
-    expect(primary.model).toBe("claude-opus-4-5")
-    expect(primary.providers[0]).toBe("anthropic")
+    expect(primary.model).toBe("claude-opus-4-6")
+    expect(primary.providers).toEqual(["anthropic", "github-copilot", "opencode"])
     expect(primary.variant).toBe("max")
   })
 
-  test("metis has valid fallbackChain with claude-opus-4-5 as primary", () => {
-    // given - metis agent requirement
+  test("metis has claude-opus-4-6 as primary", () => {
+    // #given - metis agent requirement
     const metis = AGENT_MODEL_REQUIREMENTS["metis"]
 
-    // when - accessing Metis requirement
-    // then - fallbackChain exists with claude-opus-4-5 as first entry
+    // #when - accessing Metis requirement
+    // #then - claude-opus-4-6 is first
     expect(metis).toBeDefined()
     expect(metis.fallbackChain).toBeArray()
-    expect(metis.fallbackChain.length).toBeGreaterThan(0)
+    expect(metis.fallbackChain.length).toBeGreaterThan(1)
 
     const primary = metis.fallbackChain[0]
-    expect(primary.model).toBe("claude-opus-4-5")
-    expect(primary.providers[0]).toBe("anthropic")
+    expect(primary.model).toBe("claude-opus-4-6")
+    expect(primary.providers).toEqual(["anthropic", "github-copilot", "opencode"])
     expect(primary.variant).toBe("max")
   })
 
@@ -161,14 +161,15 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     expect(primary.providers[0]).toBe("kimi-for-coding")
   })
 
-  test("hephaestus requires gpt-5.2-codex", () => {
+  test("hephaestus requires openai/github-copilot/opencode provider", () => {
     // #given - hephaestus agent requirement
     const hephaestus = AGENT_MODEL_REQUIREMENTS["hephaestus"]
 
     // #when - accessing hephaestus requirement
-    // #then - requiresModel is set to gpt-5.2-codex
+    // #then - requiresProvider is set to openai, github-copilot, opencode (not requiresModel)
     expect(hephaestus).toBeDefined()
-    expect(hephaestus.requiresModel).toBe("gpt-5.2-codex")
+    expect(hephaestus.requiresProvider).toEqual(["openai", "github-copilot", "opencode"])
+    expect(hephaestus.requiresModel).toBeUndefined()
   })
 
   test("all 10 builtin agents have valid fallbackChain arrays", () => {
@@ -208,35 +209,35 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
 })
 
 describe("CATEGORY_MODEL_REQUIREMENTS", () => {
-  test("ultrabrain has valid fallbackChain with gpt-5.2-codex as primary", () => {
+  test("ultrabrain has valid fallbackChain with gpt-5.3-codex as primary", () => {
     // given - ultrabrain category requirement
     const ultrabrain = CATEGORY_MODEL_REQUIREMENTS["ultrabrain"]
 
     // when - accessing ultrabrain requirement
-    // then - fallbackChain exists with gpt-5.2-codex as first entry
+    // then - fallbackChain exists with gpt-5.3-codex as first entry
     expect(ultrabrain).toBeDefined()
     expect(ultrabrain.fallbackChain).toBeArray()
     expect(ultrabrain.fallbackChain.length).toBeGreaterThan(0)
 
     const primary = ultrabrain.fallbackChain[0]
     expect(primary.variant).toBe("xhigh")
-    expect(primary.model).toBe("gpt-5.2-codex")
+    expect(primary.model).toBe("gpt-5.3-codex")
     expect(primary.providers[0]).toBe("openai")
   })
 
-  test("deep has valid fallbackChain with gpt-5.2-codex as primary", () => {
+  test("deep has valid fallbackChain with gpt-5.3-codex as primary", () => {
     // given - deep category requirement
     const deep = CATEGORY_MODEL_REQUIREMENTS["deep"]
 
     // when - accessing deep requirement
-    // then - fallbackChain exists with gpt-5.2-codex as first entry, medium variant
+    // then - fallbackChain exists with gpt-5.3-codex as first entry, medium variant
     expect(deep).toBeDefined()
     expect(deep.fallbackChain).toBeArray()
     expect(deep.fallbackChain.length).toBeGreaterThan(0)
 
     const primary = deep.fallbackChain[0]
     expect(primary.variant).toBe("medium")
-    expect(primary.model).toBe("gpt-5.2-codex")
+    expect(primary.model).toBe("gpt-5.3-codex")
     expect(primary.providers[0]).toBe("openai")
   })
 
@@ -285,20 +286,20 @@ describe("CATEGORY_MODEL_REQUIREMENTS", () => {
     expect(primary.providers[0]).toBe("anthropic")
   })
 
-  test("unspecified-high has valid fallbackChain with claude-opus-4-5 as primary", () => {
-    // given - unspecified-high category requirement
+  test("unspecified-high has claude-opus-4-6 as primary", () => {
+    // #given - unspecified-high category requirement
     const unspecifiedHigh = CATEGORY_MODEL_REQUIREMENTS["unspecified-high"]
 
-    // when - accessing unspecified-high requirement
-    // then - fallbackChain exists with claude-opus-4-5 as first entry
+    // #when - accessing unspecified-high requirement
+    // #then - claude-opus-4-6 is first
     expect(unspecifiedHigh).toBeDefined()
     expect(unspecifiedHigh.fallbackChain).toBeArray()
-    expect(unspecifiedHigh.fallbackChain.length).toBeGreaterThan(0)
+    expect(unspecifiedHigh.fallbackChain.length).toBeGreaterThan(1)
 
     const primary = unspecifiedHigh.fallbackChain[0]
-    expect(primary.model).toBe("claude-opus-4-5")
+    expect(primary.model).toBe("claude-opus-4-6")
     expect(primary.variant).toBe("max")
-    expect(primary.providers[0]).toBe("anthropic")
+    expect(primary.providers).toEqual(["anthropic", "github-copilot", "opencode"])
   })
 
   test("artistry has valid fallbackChain with gemini-3-pro as primary", () => {
@@ -371,14 +372,14 @@ describe("FallbackEntry type", () => {
     // given - a valid FallbackEntry object
     const entry: FallbackEntry = {
       providers: ["anthropic", "github-copilot", "opencode"],
-      model: "claude-opus-4-5",
+      model: "claude-opus-4-6",
       variant: "high",
     }
 
     // when - accessing properties
     // then - all properties are accessible
     expect(entry.providers).toEqual(["anthropic", "github-copilot", "opencode"])
-    expect(entry.model).toBe("claude-opus-4-5")
+    expect(entry.model).toBe("claude-opus-4-6")
     expect(entry.variant).toBe("high")
   })
 
@@ -400,7 +401,7 @@ describe("ModelRequirement type", () => {
     // given - a valid ModelRequirement object
     const requirement: ModelRequirement = {
       fallbackChain: [
-        { providers: ["anthropic", "github-copilot"], model: "claude-opus-4-5", variant: "max" },
+        { providers: ["anthropic", "github-copilot"], model: "claude-opus-4-6", variant: "max" },
         { providers: ["openai", "github-copilot"], model: "gpt-5.2", variant: "high" },
       ],
     }
@@ -409,7 +410,7 @@ describe("ModelRequirement type", () => {
     // then - fallbackChain is accessible with correct structure
     expect(requirement.fallbackChain).toBeArray()
     expect(requirement.fallbackChain).toHaveLength(2)
-    expect(requirement.fallbackChain[0].model).toBe("claude-opus-4-5")
+    expect(requirement.fallbackChain[0].model).toBe("claude-opus-4-6")
     expect(requirement.fallbackChain[1].model).toBe("gpt-5.2")
   })
 
@@ -459,12 +460,12 @@ describe("ModelRequirement type", () => {
 })
 
 describe("requiresModel field in categories", () => {
-  test("deep category has requiresModel set to gpt-5.2-codex", () => {
+  test("deep category has requiresModel set to gpt-5.3-codex", () => {
     // given
     const deep = CATEGORY_MODEL_REQUIREMENTS["deep"]
 
     // when / #then
-    expect(deep.requiresModel).toBe("gpt-5.2-codex")
+    expect(deep.requiresModel).toBe("gpt-5.3-codex")
   })
 
   test("artistry category has requiresModel set to gemini-3-pro", () => {

src/shared/model-requirements.ts

@@ -9,12 +9,13 @@ export type ModelRequirement = {
   variant?: string // Default variant (used when entry doesn't specify one)
   requiresModel?: string // If set, only activates when this model is available (fuzzy match)
   requiresAnyModel?: boolean // If true, requires at least ONE model in fallbackChain to be available (or empty availability treated as unavailable)
+  requiresProvider?: string[] // If set, only activates when any of these providers is connected
 }
 
 export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   sisyphus: {
     fallbackChain: [
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["kimi-for-coding"], model: "k2p5" },
       { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["zai-coding-plan"], model: "glm-4.7" },
@@ -24,15 +25,15 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   },
   hephaestus: {
     fallbackChain: [
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2-codex", variant: "medium" },
+      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
     ],
-    requiresModel: "gpt-5.2-codex",
+    requiresProvider: ["openai", "github-copilot", "opencode"],
   },
   oracle: {
     fallbackChain: [
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "high" },
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
     ],
   },
    librarian: {
@@ -62,7 +63,7 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   },
   prometheus: {
     fallbackChain: [
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["kimi-for-coding"], model: "k2p5" },
       { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
@@ -71,7 +72,7 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   },
   metis: {
     fallbackChain: [
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["kimi-for-coding"], model: "k2p5" },
       { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
@@ -81,7 +82,7 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   momus: {
     fallbackChain: [
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "medium" },
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "high" },
     ],
   },
@@ -100,33 +101,33 @@ export const CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   "visual-engineering": {
     fallbackChain: [
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["zai-coding-plan"], model: "glm-4.7" },
     ],
   },
   ultrabrain: {
     fallbackChain: [
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2-codex", variant: "xhigh" },
+      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.3-codex", variant: "xhigh" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "high" },
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
     ],
   },
-   deep: {
-     fallbackChain: [
-       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2-codex", variant: "medium" },
-       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
-       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "high" },
-     ],
-     requiresModel: "gpt-5.2-codex",
-   },
-    artistry: {
-      fallbackChain: [
-        { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "high" },
-        { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
-        { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
-      ],
-      requiresModel: "gemini-3-pro",
-    },
+  deep: {
+    fallbackChain: [
+      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "high" },
+    ],
+    requiresModel: "gpt-5.3-codex",
+  },
+  artistry: {
+    fallbackChain: [
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "high" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
+      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
+    ],
+    requiresModel: "gemini-3-pro",
+  },
   quick: {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-haiku-4-5" },
@@ -137,13 +138,13 @@ export const CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   "unspecified-low": {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" },
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2-codex", variant: "medium" },
+      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" },
     ],
   },
   "unspecified-high": {
     fallbackChain: [
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
     ],

src/shared/model-resolver.test.ts

@@ -8,7 +8,7 @@ describe("resolveModel", () => {
     test("returns userModel when all three are set", () => {
       // given
       const input: ModelResolutionInput = {
-        userModel: "anthropic/claude-opus-4-5",
+        userModel: "anthropic/claude-opus-4-6",
         inheritedModel: "openai/gpt-5.2",
         systemDefault: "google/gemini-3-pro",
       }
@@ -17,7 +17,7 @@ describe("resolveModel", () => {
       const result = resolveModel(input)
 
       // then
-      expect(result).toBe("anthropic/claude-opus-4-5")
+      expect(result).toBe("anthropic/claude-opus-4-6")
     })
 
     test("returns inheritedModel when userModel is undefined", () => {
@@ -87,7 +87,7 @@ describe("resolveModel", () => {
     test("same input returns same output (referential transparency)", () => {
       // given
       const input: ModelResolutionInput = {
-        userModel: "anthropic/claude-opus-4-5",
+        userModel: "anthropic/claude-opus-4-6",
         inheritedModel: "openai/gpt-5.2",
         systemDefault: "google/gemini-3-pro",
       }
@@ -118,11 +118,11 @@ describe("resolveModelWithFallback", () => {
       // given
       const input: ExtendedModelResolutionInput = {
         uiSelectedModel: "opencode/glm-4.7-free",
-        userModel: "anthropic/claude-opus-4-5",
+        userModel: "anthropic/claude-opus-4-6",
         fallbackChain: [
-          { providers: ["anthropic", "github-copilot"], model: "claude-opus-4-5" },
+          { providers: ["anthropic", "github-copilot"], model: "claude-opus-4-6" },
         ],
-        availableModels: new Set(["anthropic/claude-opus-4-5", "github-copilot/claude-opus-4-5-preview"]),
+        availableModels: new Set(["anthropic/claude-opus-4-6", "github-copilot/claude-opus-4-6-preview"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -139,8 +139,8 @@ describe("resolveModelWithFallback", () => {
       // given
       const input: ExtendedModelResolutionInput = {
         uiSelectedModel: "opencode/glm-4.7-free",
-        userModel: "anthropic/claude-opus-4-5",
-        availableModels: new Set(["anthropic/claude-opus-4-5"]),
+        userModel: "anthropic/claude-opus-4-6",
+        availableModels: new Set(["anthropic/claude-opus-4-6"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -156,8 +156,8 @@ describe("resolveModelWithFallback", () => {
       // given
       const input: ExtendedModelResolutionInput = {
         uiSelectedModel: "   ",
-        userModel: "anthropic/claude-opus-4-5",
-        availableModels: new Set(["anthropic/claude-opus-4-5"]),
+        userModel: "anthropic/claude-opus-4-6",
+        availableModels: new Set(["anthropic/claude-opus-4-6"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -165,16 +165,16 @@ describe("resolveModelWithFallback", () => {
       const result = resolveModelWithFallback(input)
 
       // then
-      expect(result!.model).toBe("anthropic/claude-opus-4-5")
-      expect(logSpy).toHaveBeenCalledWith("Model resolved via config override", { model: "anthropic/claude-opus-4-5" })
+      expect(result!.model).toBe("anthropic/claude-opus-4-6")
+      expect(logSpy).toHaveBeenCalledWith("Model resolved via config override", { model: "anthropic/claude-opus-4-6" })
     })
 
     test("empty string uiSelectedModel falls through to config override", () => {
       // given
       const input: ExtendedModelResolutionInput = {
         uiSelectedModel: "",
-        userModel: "anthropic/claude-opus-4-5",
-        availableModels: new Set(["anthropic/claude-opus-4-5"]),
+        userModel: "anthropic/claude-opus-4-6",
+        availableModels: new Set(["anthropic/claude-opus-4-6"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -182,7 +182,7 @@ describe("resolveModelWithFallback", () => {
       const result = resolveModelWithFallback(input)
 
       // then
-      expect(result!.model).toBe("anthropic/claude-opus-4-5")
+      expect(result!.model).toBe("anthropic/claude-opus-4-6")
     })
   })
 
@@ -190,11 +190,11 @@ describe("resolveModelWithFallback", () => {
     test("returns userModel with override source when userModel is provided", () => {
       // given
       const input: ExtendedModelResolutionInput = {
-        userModel: "anthropic/claude-opus-4-5",
+        userModel: "anthropic/claude-opus-4-6",
         fallbackChain: [
-          { providers: ["anthropic", "github-copilot"], model: "claude-opus-4-5" },
+          { providers: ["anthropic", "github-copilot"], model: "claude-opus-4-6" },
         ],
-        availableModels: new Set(["anthropic/claude-opus-4-5", "github-copilot/claude-opus-4-5-preview"]),
+        availableModels: new Set(["anthropic/claude-opus-4-6", "github-copilot/claude-opus-4-6-preview"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -202,9 +202,9 @@ describe("resolveModelWithFallback", () => {
       const result = resolveModelWithFallback(input)
 
       // then
-      expect(result!.model).toBe("anthropic/claude-opus-4-5")
+      expect(result!.model).toBe("anthropic/claude-opus-4-6")
       expect(result!.source).toBe("override")
-      expect(logSpy).toHaveBeenCalledWith("Model resolved via config override", { model: "anthropic/claude-opus-4-5" })
+      expect(logSpy).toHaveBeenCalledWith("Model resolved via config override", { model: "anthropic/claude-opus-4-6" })
     })
 
     test("override takes priority even if model not in availableModels", () => {
@@ -212,9 +212,9 @@ describe("resolveModelWithFallback", () => {
       const input: ExtendedModelResolutionInput = {
         userModel: "custom/my-model",
         fallbackChain: [
-          { providers: ["anthropic"], model: "claude-opus-4-5" },
+          { providers: ["anthropic"], model: "claude-opus-4-6" },
         ],
-        availableModels: new Set(["anthropic/claude-opus-4-5"]),
+        availableModels: new Set(["anthropic/claude-opus-4-6"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -231,9 +231,9 @@ describe("resolveModelWithFallback", () => {
       const input: ExtendedModelResolutionInput = {
         userModel: "   ",
         fallbackChain: [
-          { providers: ["anthropic"], model: "claude-opus-4-5" },
+          { providers: ["anthropic"], model: "claude-opus-4-6" },
         ],
-        availableModels: new Set(["anthropic/claude-opus-4-5"]),
+        availableModels: new Set(["anthropic/claude-opus-4-6"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -249,9 +249,9 @@ describe("resolveModelWithFallback", () => {
       const input: ExtendedModelResolutionInput = {
         userModel: "",
         fallbackChain: [
-          { providers: ["anthropic"], model: "claude-opus-4-5" },
+          { providers: ["anthropic"], model: "claude-opus-4-6" },
         ],
-        availableModels: new Set(["anthropic/claude-opus-4-5"]),
+        availableModels: new Set(["anthropic/claude-opus-4-6"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -268,9 +268,9 @@ describe("resolveModelWithFallback", () => {
       // given
       const input: ExtendedModelResolutionInput = {
         fallbackChain: [
-          { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5" },
+          { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6" },
         ],
-        availableModels: new Set(["github-copilot/claude-opus-4-5-preview", "opencode/claude-opus-4-7"]),
+        availableModels: new Set(["github-copilot/claude-opus-4-6-preview", "opencode/claude-opus-4-7"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -278,12 +278,12 @@ describe("resolveModelWithFallback", () => {
       const result = resolveModelWithFallback(input)
 
       // then
-      expect(result!.model).toBe("github-copilot/claude-opus-4-5-preview")
+      expect(result!.model).toBe("github-copilot/claude-opus-4-6-preview")
       expect(result!.source).toBe("provider-fallback")
       expect(logSpy).toHaveBeenCalledWith("Model resolved via fallback chain (availability confirmed)", {
         provider: "github-copilot",
-        model: "claude-opus-4-5",
-        match: "github-copilot/claude-opus-4-5-preview",
+        model: "claude-opus-4-6",
+        match: "github-copilot/claude-opus-4-6-preview",
         variant: undefined,
       })
     })
@@ -294,7 +294,7 @@ describe("resolveModelWithFallback", () => {
         fallbackChain: [
           { providers: ["openai", "anthropic", "google"], model: "gpt-5.2" },
         ],
-        availableModels: new Set(["openai/gpt-5.2", "anthropic/claude-opus-4-5", "google/gemini-3-pro"]),
+        availableModels: new Set(["openai/gpt-5.2", "anthropic/claude-opus-4-6", "google/gemini-3-pro"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -330,7 +330,7 @@ describe("resolveModelWithFallback", () => {
         fallbackChain: [
           { providers: ["anthropic", "github-copilot"], model: "claude-opus" },
         ],
-        availableModels: new Set(["anthropic/claude-opus-4-5", "github-copilot/claude-opus-4-5-preview"]),
+        availableModels: new Set(["anthropic/claude-opus-4-6", "github-copilot/claude-opus-4-6-preview"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -338,14 +338,14 @@ describe("resolveModelWithFallback", () => {
       const result = resolveModelWithFallback(input)
 
       // then
-      expect(result!.model).toBe("anthropic/claude-opus-4-5")
+      expect(result!.model).toBe("anthropic/claude-opus-4-6")
       expect(result!.source).toBe("provider-fallback")
     })
 
     test("skips fallback chain when not provided", () => {
       // given
       const input: ExtendedModelResolutionInput = {
-        availableModels: new Set(["anthropic/claude-opus-4-5"]),
+        availableModels: new Set(["anthropic/claude-opus-4-6"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -360,7 +360,7 @@ describe("resolveModelWithFallback", () => {
       // given
       const input: ExtendedModelResolutionInput = {
         fallbackChain: [],
-        availableModels: new Set(["anthropic/claude-opus-4-5"]),
+        availableModels: new Set(["anthropic/claude-opus-4-6"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -377,7 +377,7 @@ describe("resolveModelWithFallback", () => {
         fallbackChain: [
           { providers: ["anthropic"], model: "CLAUDE-OPUS" },
         ],
-        availableModels: new Set(["anthropic/claude-opus-4-5"]),
+        availableModels: new Set(["anthropic/claude-opus-4-6"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -385,7 +385,7 @@ describe("resolveModelWithFallback", () => {
       const result = resolveModelWithFallback(input)
 
       // then
-      expect(result!.model).toBe("anthropic/claude-opus-4-5")
+      expect(result!.model).toBe("anthropic/claude-opus-4-6")
       expect(result!.source).toBe("provider-fallback")
     })
 
@@ -476,7 +476,7 @@ describe("resolveModelWithFallback", () => {
         fallbackChain: [
           { providers: ["anthropic"], model: "nonexistent-model" },
         ],
-        availableModels: new Set(["openai/gpt-5.2", "anthropic/claude-opus-4-5"]),
+        availableModels: new Set(["openai/gpt-5.2", "anthropic/claude-opus-4-6"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 
@@ -494,7 +494,7 @@ describe("resolveModelWithFallback", () => {
       const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
       const input: ExtendedModelResolutionInput = {
         fallbackChain: [
-          { providers: ["anthropic"], model: "claude-opus-4-5" },
+          { providers: ["anthropic"], model: "claude-opus-4-6" },
         ],
         availableModels: new Set(),
         systemDefaultModel: undefined, // no system default configured
@@ -513,7 +513,7 @@ describe("resolveModelWithFallback", () => {
       const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai", "google"])
       const input: ExtendedModelResolutionInput = {
         fallbackChain: [
-          { providers: ["anthropic", "openai"], model: "claude-opus-4-5" },
+          { providers: ["anthropic", "openai"], model: "claude-opus-4-6" },
         ],
         availableModels: new Set(),
         systemDefaultModel: "google/gemini-3-pro",
@@ -523,7 +523,7 @@ describe("resolveModelWithFallback", () => {
       const result = resolveModelWithFallback(input)
 
       // then - should use connected provider (openai) from fallback chain
-      expect(result!.model).toBe("openai/claude-opus-4-5")
+      expect(result!.model).toBe("openai/claude-opus-4-6")
       expect(result!.source).toBe("provider-fallback")
       cacheSpy.mockRestore()
     })
@@ -556,14 +556,14 @@ describe("resolveModelWithFallback", () => {
           { providers: ["anthropic", "opencode"], model: "claude-haiku-4-5" },
         ],
         availableModels: new Set(),
-        systemDefaultModel: "quotio/claude-opus-4-5-20251101",
+        systemDefaultModel: "quotio/claude-opus-4-6-20251101",
       }
 
       // when
       const result = resolveModelWithFallback(input)
 
       // then - no provider in fallback is connected, fall through to system default
-      expect(result!.model).toBe("quotio/claude-opus-4-5-20251101")
+      expect(result!.model).toBe("quotio/claude-opus-4-6-20251101")
       expect(result!.source).toBe("system-default")
       cacheSpy.mockRestore()
     })
@@ -573,7 +573,7 @@ describe("resolveModelWithFallback", () => {
       const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
       const input: ExtendedModelResolutionInput = {
         fallbackChain: [
-          { providers: ["anthropic"], model: "claude-opus-4-5" },
+          { providers: ["anthropic"], model: "claude-opus-4-6" },
         ],
         availableModels: new Set(),
         systemDefaultModel: "google/gemini-3-pro",
@@ -607,20 +607,20 @@ describe("resolveModelWithFallback", () => {
   describe("Multi-entry fallbackChain", () => {
     test("resolves to claude-opus when OpenAI unavailable but Anthropic available (oracle scenario)", () => {
       // given
-      const availableModels = new Set(["anthropic/claude-opus-4-5"])
+      const availableModels = new Set(["anthropic/claude-opus-4-6"])
 
       // when
       const result = resolveModelWithFallback({
         fallbackChain: [
           { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
-          { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5", variant: "max" },
+          { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
         ],
         availableModels,
         systemDefaultModel: "system/default",
       })
 
       // then
-      expect(result!.model).toBe("anthropic/claude-opus-4-5")
+      expect(result!.model).toBe("anthropic/claude-opus-4-6")
       expect(result!.source).toBe("provider-fallback")
     })
 
@@ -647,14 +647,14 @@ describe("resolveModelWithFallback", () => {
       // given
       const availableModels = new Set([
         "openai/gpt-5.2",
-        "anthropic/claude-opus-4-5",
+        "anthropic/claude-opus-4-6",
       ])
 
       // when
       const result = resolveModelWithFallback({
         fallbackChain: [
           { providers: ["openai"], model: "gpt-5.2" },
-          { providers: ["anthropic"], model: "claude-opus-4-5" },
+          { providers: ["anthropic"], model: "claude-opus-4-6" },
         ],
         availableModels,
         systemDefaultModel: "system/default",
@@ -673,7 +673,7 @@ describe("resolveModelWithFallback", () => {
       const result = resolveModelWithFallback({
         fallbackChain: [
           { providers: ["openai"], model: "gpt-5.2" },
-          { providers: ["anthropic"], model: "claude-opus-4-5" },
+          { providers: ["anthropic"], model: "claude-opus-4-6" },
           { providers: ["google"], model: "gemini-3-pro" },
         ],
         availableModels,
@@ -690,7 +690,7 @@ describe("resolveModelWithFallback", () => {
     test("result has correct ModelResolutionResult shape", () => {
       // given
       const input: ExtendedModelResolutionInput = {
-        userModel: "anthropic/claude-opus-4-5",
+        userModel: "anthropic/claude-opus-4-6",
         availableModels: new Set(),
         systemDefaultModel: "google/gemini-3-pro",
       }
@@ -713,7 +713,7 @@ describe("resolveModelWithFallback", () => {
         fallbackChain: [
           { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
         ],
-        availableModels: new Set(["google/gemini-3-pro-preview", "anthropic/claude-opus-4-5"]),
+        availableModels: new Set(["google/gemini-3-pro-preview", "anthropic/claude-opus-4-6"]),
         systemDefaultModel: "anthropic/claude-sonnet-4-5",
       }
 
@@ -749,9 +749,9 @@ describe("resolveModelWithFallback", () => {
       const input: ExtendedModelResolutionInput = {
         categoryDefaultModel: "google/gemini-3-pro",
         fallbackChain: [
-          { providers: ["anthropic"], model: "claude-opus-4-5" },
+          { providers: ["anthropic"], model: "claude-opus-4-6" },
         ],
-        availableModels: new Set(["anthropic/claude-opus-4-5"]),
+        availableModels: new Set(["anthropic/claude-opus-4-6"]),
         systemDefaultModel: "system/default",
       }
 
@@ -759,19 +759,19 @@ describe("resolveModelWithFallback", () => {
       const result = resolveModelWithFallback(input)
 
       // then - should fall through to fallbackChain
-      expect(result!.model).toBe("anthropic/claude-opus-4-5")
+      expect(result!.model).toBe("anthropic/claude-opus-4-6")
       expect(result!.source).toBe("provider-fallback")
     })
 
     test("userModel takes priority over categoryDefaultModel", () => {
       // given - both userModel and categoryDefaultModel provided
       const input: ExtendedModelResolutionInput = {
-        userModel: "anthropic/claude-opus-4-5",
+        userModel: "anthropic/claude-opus-4-6",
         categoryDefaultModel: "google/gemini-3-pro",
         fallbackChain: [
           { providers: ["google"], model: "gemini-3-pro" },
         ],
-        availableModels: new Set(["google/gemini-3-pro-preview", "anthropic/claude-opus-4-5"]),
+        availableModels: new Set(["google/gemini-3-pro-preview", "anthropic/claude-opus-4-6"]),
         systemDefaultModel: "system/default",
       }
 
@@ -779,7 +779,7 @@ describe("resolveModelWithFallback", () => {
       const result = resolveModelWithFallback(input)
 
       // then - userModel wins
-      expect(result!.model).toBe("anthropic/claude-opus-4-5")
+      expect(result!.model).toBe("anthropic/claude-opus-4-6")
       expect(result!.source).toBe("override")
     })
 
@@ -837,7 +837,7 @@ describe("resolveModelWithFallback", () => {
     test("still returns override when userModel provided even if systemDefaultModel undefined", () => {
       // given
       const input: ExtendedModelResolutionInput = {
-        userModel: "anthropic/claude-opus-4-5",
+        userModel: "anthropic/claude-opus-4-6",
         availableModels: new Set(),
         systemDefaultModel: undefined,
       }
@@ -847,7 +847,7 @@ describe("resolveModelWithFallback", () => {
 
       // then
       expect(result).toBeDefined()
-      expect(result!.model).toBe("anthropic/claude-opus-4-5")
+      expect(result!.model).toBe("anthropic/claude-opus-4-6")
       expect(result!.source).toBe("override")
     })
 
@@ -855,9 +855,9 @@ describe("resolveModelWithFallback", () => {
       // given
       const input: ExtendedModelResolutionInput = {
         fallbackChain: [
-          { providers: ["anthropic"], model: "claude-opus-4-5" },
+          { providers: ["anthropic"], model: "claude-opus-4-6" },
         ],
-        availableModels: new Set(["anthropic/claude-opus-4-5"]),
+        availableModels: new Set(["anthropic/claude-opus-4-6"]),
         systemDefaultModel: undefined,
       }
 
@@ -866,7 +866,7 @@ describe("resolveModelWithFallback", () => {
 
       // then
       expect(result).toBeDefined()
-      expect(result!.model).toBe("anthropic/claude-opus-4-5")
+      expect(result!.model).toBe("anthropic/claude-opus-4-6")
       expect(result!.source).toBe("provider-fallback")
     })
   })

src/shared/ollama-ndjson-parser.ts

@@ -1,198 +0,0 @@
-/**
- * Ollama NDJSON Parser
- *
- * Parses newline-delimited JSON (NDJSON) responses from Ollama API.
- *
- * @module ollama-ndjson-parser
- * @see https://github.com/code-yeongyu/oh-my-opencode/issues/1124
- * @see https://github.com/ollama/ollama/blob/main/docs/api.md
- */
-
-import { log } from "./logger"
-
-/**
- * Ollama message structure
- */
-export interface OllamaMessage {
-  tool_calls?: Array<{
-    function: {
-      name: string
-      arguments: Record<string, unknown>
-    }
-  }>
-  content?: string
-}
-
-/**
- * Ollama NDJSON line structure
- */
-export interface OllamaNDJSONLine {
-  message?: OllamaMessage
-  done: boolean
-  total_duration?: number
-  load_duration?: number
-  prompt_eval_count?: number
-  prompt_eval_duration?: number
-  eval_count?: number
-  eval_duration?: number
-}
-
-/**
- * Merged Ollama response
- */
-export interface OllamaMergedResponse {
-  message: OllamaMessage
-  done: boolean
-  stats?: {
-    total_duration?: number
-    load_duration?: number
-    prompt_eval_count?: number
-    prompt_eval_duration?: number
-    eval_count?: number
-    eval_duration?: number
-  }
-}
-
-/**
- * Parse Ollama streaming NDJSON response into a single merged object.
- *
- * Ollama returns streaming responses as newline-delimited JSON (NDJSON):
- * ```
- * {"message":{"tool_calls":[...]}, "done":false}
- * {"message":{"content":""}, "done":true}
- * ```
- *
- * This function:
- * 1. Splits the response by newlines
- * 2. Parses each line as JSON
- * 3. Merges tool_calls and content from all lines
- * 4. Returns a single merged response
- *
- * @param response - Raw NDJSON response string from Ollama API
- * @returns Merged response with all tool_calls and content combined
- * @throws {Error} If no valid JSON lines are found
- *
- * @example
- * ```typescript
- * const ndjsonResponse = `
- * {"message":{"tool_calls":[{"function":{"name":"read","arguments":{"filePath":"README.md"}}}]}, "done":false}
- * {"message":{"content":""}, "done":true}
- * `;
- *
- * const merged = parseOllamaStreamResponse(ndjsonResponse);
- * // Result:
- * // {
- * //   message: {
- * //     tool_calls: [{ function: { name: "read", arguments: { filePath: "README.md" } } }],
- * //     content: ""
- * //   },
- * //   done: true
- * // }
- * ```
- */
-export function parseOllamaStreamResponse(response: string): OllamaMergedResponse {
-  const lines = response.split("\n").filter((line) => line.trim())
-
-  if (lines.length === 0) {
-    throw new Error("No valid NDJSON lines found in response")
-  }
-
-  const mergedMessage: OllamaMessage = {
-    tool_calls: [],
-    content: "",
-  }
-
-  let done = false
-  let stats: OllamaMergedResponse["stats"] = {}
-
-  for (const line of lines) {
-    try {
-      const json = JSON.parse(line) as OllamaNDJSONLine
-
-      // Merge tool_calls
-      if (json.message?.tool_calls) {
-        mergedMessage.tool_calls = [
-          ...(mergedMessage.tool_calls || []),
-          ...json.message.tool_calls,
-        ]
-      }
-
-      // Merge content (concatenate)
-      if (json.message?.content) {
-        mergedMessage.content = (mergedMessage.content || "") + json.message.content
-      }
-
-      // Update done flag (final line has done: true)
-      if (json.done) {
-        done = true
-
-        // Capture stats from final line
-        stats = {
-          total_duration: json.total_duration,
-          load_duration: json.load_duration,
-          prompt_eval_count: json.prompt_eval_count,
-          prompt_eval_duration: json.prompt_eval_duration,
-          eval_count: json.eval_count,
-          eval_duration: json.eval_duration,
-        }
-      }
-    } catch (error) {
-      log(`[ollama-ndjson-parser] Skipping malformed NDJSON line: ${line}`, { error })
-      continue
-    }
-  }
-
-  return {
-    message: mergedMessage,
-    done,
-    ...(Object.keys(stats).length > 0 ? { stats } : {}),
-  }
-}
-
-/**
- * Check if a response string is NDJSON format.
- *
- * NDJSON is identified by:
- * - Multiple lines
- * - Each line is valid JSON
- * - At least one line has "done" field
- *
- * @param response - Response string to check
- * @returns true if response appears to be NDJSON
- *
- * @example
- * ```typescript
- * const ndjson = '{"done":false}\n{"done":true}';
- * const singleJson = '{"done":true}';
- *
- * isNDJSONResponse(ndjson);     // true
- * isNDJSONResponse(singleJson); // false
- * ```
- */
-export function isNDJSONResponse(response: string): boolean {
-  const lines = response.split("\n").filter((line) => line.trim())
-
-  // Single line is not NDJSON
-  if (lines.length <= 1) {
-    return false
-  }
-
-  let hasValidJSON = false
-  let hasDoneField = false
-
-  for (const line of lines) {
-    try {
-      const json = JSON.parse(line) as Record<string, unknown>
-      hasValidJSON = true
-
-      if ("done" in json) {
-        hasDoneField = true
-      }
-    } catch {
-      // If any line fails to parse, it's not NDJSON
-      return false
-    }
-  }
-
-  return hasValidJSON && hasDoneField
-}

src/shared/pattern-matcher.test.ts

@@ -0,0 +1,194 @@
+import { describe, test, expect } from "bun:test"
+import { matchesToolMatcher, findMatchingHooks } from "./pattern-matcher"
+import type { ClaudeHooksConfig } from "../hooks/claude-code-hooks/types"
+
+describe("matchesToolMatcher", () => {
+  describe("exact matching", () => {
+    //#given a pattern without wildcards
+    //#when matching against a tool name
+    //#then it should match case-insensitively
+
+    test("matches exact tool name", () => {
+      expect(matchesToolMatcher("bash", "bash")).toBe(true)
+    })
+
+    test("matches case-insensitively", () => {
+      expect(matchesToolMatcher("Bash", "bash")).toBe(true)
+      expect(matchesToolMatcher("bash", "BASH")).toBe(true)
+    })
+
+    test("does not match different tool names", () => {
+      expect(matchesToolMatcher("bash", "edit")).toBe(false)
+    })
+  })
+
+  describe("wildcard matching", () => {
+    //#given a pattern with asterisk wildcard
+    //#when matching against tool names
+    //#then it should treat * as glob-style wildcard
+
+    test("matches prefix wildcard", () => {
+      expect(matchesToolMatcher("lsp_goto_definition", "lsp_*")).toBe(true)
+      expect(matchesToolMatcher("lsp_find_references", "lsp_*")).toBe(true)
+    })
+
+    test("matches suffix wildcard", () => {
+      expect(matchesToolMatcher("file_read", "*_read")).toBe(true)
+    })
+
+    test("matches middle wildcard", () => {
+      expect(matchesToolMatcher("get_user_info", "get_*_info")).toBe(true)
+    })
+
+    test("matches multiple wildcards", () => {
+      expect(matchesToolMatcher("get_user_data", "*_user_*")).toBe(true)
+    })
+
+    test("single asterisk matches any tool", () => {
+      expect(matchesToolMatcher("anything", "*")).toBe(true)
+    })
+  })
+
+  describe("pipe-separated patterns", () => {
+    //#given multiple patterns separated by pipes
+    //#when matching against tool names
+    //#then it should match if any pattern matches
+
+    test("matches first pattern", () => {
+      expect(matchesToolMatcher("bash", "bash | edit | write")).toBe(true)
+    })
+
+    test("matches middle pattern", () => {
+      expect(matchesToolMatcher("edit", "bash | edit | write")).toBe(true)
+    })
+
+    test("matches last pattern", () => {
+      expect(matchesToolMatcher("write", "bash | edit | write")).toBe(true)
+    })
+
+    test("does not match if none match", () => {
+      expect(matchesToolMatcher("read", "bash | edit | write")).toBe(false)
+    })
+  })
+
+  describe("regex special character escaping (issue #1521)", () => {
+    //#given a pattern containing regex special characters
+    //#when matching against tool names
+    //#then it should NOT throw SyntaxError and should handle them as literals
+
+    test("handles parentheses in pattern without throwing", () => {
+      expect(() => matchesToolMatcher("bash", "bash(*)")).not.toThrow()
+      expect(matchesToolMatcher("bash(test)", "bash(*)")).toBe(true)
+    })
+
+    test("handles unmatched opening parenthesis", () => {
+      expect(() => matchesToolMatcher("test", "test(*")).not.toThrow()
+      expect(matchesToolMatcher("test(foo", "test(*")).toBe(true)
+      expect(matchesToolMatcher("testfoo", "test(*")).toBe(false)
+    })
+
+    test("handles unmatched closing parenthesis", () => {
+      expect(() => matchesToolMatcher("test", "test*)")).not.toThrow()
+      expect(matchesToolMatcher("test)", "test*)")).toBe(true)
+      expect(matchesToolMatcher("testanything)", "test*)")).toBe(true)
+      expect(matchesToolMatcher("foo)", "test*)")).toBe(false)
+    })
+
+    test("handles square brackets", () => {
+      expect(() => matchesToolMatcher("test", "test[*]")).not.toThrow()
+      expect(matchesToolMatcher("test[1]", "test[*]")).toBe(true)
+    })
+
+    test("handles plus sign as literal", () => {
+      expect(() => matchesToolMatcher("test", "test+*")).not.toThrow()
+      expect(matchesToolMatcher("test+value", "test+*")).toBe(true)
+      expect(matchesToolMatcher("testvalue", "test+*")).toBe(false)
+    })
+
+    test("handles question mark as literal", () => {
+      expect(() => matchesToolMatcher("test", "test?*")).not.toThrow()
+      expect(matchesToolMatcher("test?foo", "test?*")).toBe(true)
+      expect(matchesToolMatcher("testfoo", "test?*")).toBe(false)
+    })
+
+    test("handles caret as literal", () => {
+      expect(() => matchesToolMatcher("test", "^test*")).not.toThrow()
+      expect(matchesToolMatcher("^test_tool", "^test*")).toBe(true)
+      expect(matchesToolMatcher("test_tool", "^test*")).toBe(false)
+    })
+
+    test("handles dollar sign as literal", () => {
+      expect(() => matchesToolMatcher("test", "test$*")).not.toThrow()
+      expect(matchesToolMatcher("test$var", "test$*")).toBe(true)
+      expect(matchesToolMatcher("testvar", "test$*")).toBe(false)
+    })
+
+    test("handles curly braces as literal", () => {
+      expect(() => matchesToolMatcher("test", "test{*}")).not.toThrow()
+      expect(matchesToolMatcher("test{foo}", "test{*}")).toBe(true)
+      expect(matchesToolMatcher("testfoo", "test{*}")).toBe(false)
+    })
+
+    test("handles pipe as pattern separator", () => {
+      expect(() => matchesToolMatcher("test", "test|value")).not.toThrow()
+      expect(matchesToolMatcher("test", "test|value")).toBe(true)
+      expect(matchesToolMatcher("value", "test|value")).toBe(true)
+    })
+
+    test("handles backslash as literal", () => {
+      expect(() => matchesToolMatcher("test\\path", "test\\*")).not.toThrow()
+      expect(matchesToolMatcher("test\\path", "test\\*")).toBe(true)
+      expect(matchesToolMatcher("testpath", "test\\*")).toBe(false)
+    })
+
+    test("handles dot", () => {
+      expect(() => matchesToolMatcher("test.ts", "test.*")).not.toThrow()
+      expect(matchesToolMatcher("test.ts", "test.*")).toBe(true)
+    })
+
+    test("complex pattern with multiple special chars", () => {
+      expect(() => matchesToolMatcher("func(arg)", "func(*)")).not.toThrow()
+      expect(matchesToolMatcher("func(arg)", "func(*)")).toBe(true)
+    })
+  })
+
+  describe("empty matcher", () => {
+    //#given an empty or undefined matcher
+    //#when matching
+    //#then it should match everything
+
+    test("empty string matches everything", () => {
+      expect(matchesToolMatcher("anything", "")).toBe(true)
+    })
+  })
+})
+
+describe("findMatchingHooks", () => {
+  const mockHooks: ClaudeHooksConfig = {
+    PreToolUse: [
+      { matcher: "bash", hooks: [{ type: "command", command: "/test/hook1" }] },
+      { matcher: "edit*", hooks: [{ type: "command", command: "/test/hook2" }] },
+      { matcher: "*", hooks: [{ type: "command", command: "/test/hook3" }] },
+    ],
+  }
+
+  test("finds hooks matching exact tool name", () => {
+    const result = findMatchingHooks(mockHooks, "PreToolUse", "bash")
+    expect(result.length).toBe(2) // "bash" and "*"
+  })
+
+  test("finds hooks matching wildcard pattern", () => {
+    const result = findMatchingHooks(mockHooks, "PreToolUse", "edit_file")
+    expect(result.length).toBe(2) // "edit*" and "*"
+  })
+
+  test("returns all hooks when no toolName provided", () => {
+    const result = findMatchingHooks(mockHooks, "PreToolUse")
+    expect(result.length).toBe(3)
+  })
+
+  test("returns empty array for non-existent event", () => {
+    const result = findMatchingHooks(mockHooks, "PostToolUse", "bash")
+    expect(result.length).toBe(0)
+  })
+})

src/shared/pattern-matcher.ts

@@ -1,5 +1,14 @@
 import type { ClaudeHooksConfig, HookMatcher } from "../hooks/claude-code-hooks/types"
 
+/**
+ * Escape all regex special characters EXCEPT asterisk (*).
+ * Asterisk is preserved for glob-to-regex conversion.
+ */
+function escapeRegexExceptAsterisk(str: string): string {
+  // Escape all regex special chars except * (which we convert to .* for glob matching)
+  return str.replace(/[.+?^${}()|[\]\\]/g, "\\$&")
+}
+
 export function matchesToolMatcher(toolName: string, matcher: string): boolean {
   if (!matcher) {
     return true
@@ -7,7 +16,9 @@ export function matchesToolMatcher(toolName: string, matcher: string): boolean {
   const patterns = matcher.split("|").map((p) => p.trim())
   return patterns.some((p) => {
     if (p.includes("*")) {
-      const regex = new RegExp(`^${p.replace(/\*/g, ".*")}$`, "i")
+      // First escape regex special chars (except *), then convert * to .*
+      const escaped = escapeRegexExceptAsterisk(p)
+      const regex = new RegExp(`^${escaped.replace(/\*/g, ".*")}$`, "i")
       return regex.test(toolName)
     }
     return p.toLowerCase() === toolName.toLowerCase()

src/shared/port-utils.test.ts

@@ -0,0 +1,105 @@
+import { describe, it, expect, beforeAll, afterAll } from "bun:test"
+import {
+  isPortAvailable,
+  findAvailablePort,
+  getAvailableServerPort,
+  DEFAULT_SERVER_PORT,
+} from "./port-utils"
+
+describe("port-utils", () => {
+  describe("isPortAvailable", () => {
+    it("#given unused port #when checking availability #then returns true", async () => {
+      const port = 59999
+      const result = await isPortAvailable(port)
+      expect(result).toBe(true)
+    })
+
+    it("#given port in use #when checking availability #then returns false", async () => {
+      const port = 59998
+      const blocker = Bun.serve({
+        port,
+        hostname: "127.0.0.1",
+        fetch: () => new Response("blocked"),
+      })
+
+      try {
+        const result = await isPortAvailable(port)
+        expect(result).toBe(false)
+      } finally {
+        blocker.stop(true)
+      }
+    })
+  })
+
+  describe("findAvailablePort", () => {
+    it("#given start port available #when finding port #then returns start port", async () => {
+      const startPort = 59997
+      const result = await findAvailablePort(startPort)
+      expect(result).toBe(startPort)
+    })
+
+    it("#given start port blocked #when finding port #then returns next available", async () => {
+      const startPort = 59996
+      const blocker = Bun.serve({
+        port: startPort,
+        hostname: "127.0.0.1",
+        fetch: () => new Response("blocked"),
+      })
+
+      try {
+        const result = await findAvailablePort(startPort)
+        expect(result).toBe(startPort + 1)
+      } finally {
+        blocker.stop(true)
+      }
+    })
+
+    it("#given multiple ports blocked #when finding port #then skips all blocked", async () => {
+      const startPort = 59993
+      const blockers = [
+        Bun.serve({ port: startPort, hostname: "127.0.0.1", fetch: () => new Response() }),
+        Bun.serve({ port: startPort + 1, hostname: "127.0.0.1", fetch: () => new Response() }),
+        Bun.serve({ port: startPort + 2, hostname: "127.0.0.1", fetch: () => new Response() }),
+      ]
+
+      try {
+        const result = await findAvailablePort(startPort)
+        expect(result).toBe(startPort + 3)
+      } finally {
+        blockers.forEach((b) => b.stop(true))
+      }
+    })
+  })
+
+  describe("getAvailableServerPort", () => {
+    it("#given preferred port available #when getting port #then returns preferred with wasAutoSelected=false", async () => {
+      const preferredPort = 59990
+      const result = await getAvailableServerPort(preferredPort)
+      expect(result.port).toBe(preferredPort)
+      expect(result.wasAutoSelected).toBe(false)
+    })
+
+    it("#given preferred port blocked #when getting port #then returns alternative with wasAutoSelected=true", async () => {
+      const preferredPort = 59989
+      const blocker = Bun.serve({
+        port: preferredPort,
+        hostname: "127.0.0.1",
+        fetch: () => new Response("blocked"),
+      })
+
+      try {
+        const result = await getAvailableServerPort(preferredPort)
+        expect(result.port).toBeGreaterThan(preferredPort)
+        expect(result.wasAutoSelected).toBe(true)
+      } finally {
+        blocker.stop(true)
+      }
+    })
+  })
+
+  describe("DEFAULT_SERVER_PORT", () => {
+    it("#given constant #when accessed #then returns 4096", () => {
+      expect(DEFAULT_SERVER_PORT).toBe(4096)
+    })
+  })
+})

src/shared/port-utils.ts

@@ -0,0 +1,48 @@
+const DEFAULT_SERVER_PORT = 4096
+const MAX_PORT_ATTEMPTS = 20
+
+export async function isPortAvailable(port: number, hostname: string = "127.0.0.1"): Promise<boolean> {
+  try {
+    const server = Bun.serve({
+      port,
+      hostname,
+      fetch: () => new Response(),
+    })
+    server.stop(true)
+    return true
+  } catch {
+    return false
+  }
+}
+
+export async function findAvailablePort(
+  startPort: number = DEFAULT_SERVER_PORT,
+  hostname: string = "127.0.0.1"
+): Promise<number> {
+  for (let attempt = 0; attempt < MAX_PORT_ATTEMPTS; attempt++) {
+    const port = startPort + attempt
+    if (await isPortAvailable(port, hostname)) {
+      return port
+    }
+  }
+  throw new Error(`No available port found in range ${startPort}-${startPort + MAX_PORT_ATTEMPTS - 1}`)
+}
+
+export interface AutoPortResult {
+  port: number
+  wasAutoSelected: boolean
+}
+
+export async function getAvailableServerPort(
+  preferredPort: number = DEFAULT_SERVER_PORT,
+  hostname: string = "127.0.0.1"
+): Promise<AutoPortResult> {
+  if (await isPortAvailable(preferredPort, hostname)) {
+    return { port: preferredPort, wasAutoSelected: false }
+  }
+
+  const port = await findAvailablePort(preferredPort + 1, hostname)
+  return { port, wasAutoSelected: true }
+}
+
+export { DEFAULT_SERVER_PORT }

src/tools/AGENTS.md

@@ -2,9 +2,9 @@
 
 ## OVERVIEW
 
-20+ tools across 7 categories. Two patterns: Direct ToolDefinition (static) and Factory Function (context-dependent).
+25+ tools across 8 categories. Two patterns: Direct ToolDefinition (static) and Factory Function (context-dependent).
 
-**Categories**: LSP (6), AST-Grep (2), Search (2), Session (4), Agent delegation (2), Background (2), Skill (3)
+**Categories**: LSP (6), AST-Grep (2), Search (2), Session (4), Task (4), Agent delegation (2), Background (2), Skill (3), System (2)
 
 ## STRUCTURE
 
@@ -15,20 +15,20 @@ tools/
 │   ├── tools.ts      # ToolDefinition or factory
 │   ├── types.ts      # Zod schemas
 │   └── constants.ts  # Fixed values
-├── lsp/              # 6 tools: definition, references, symbols, diagnostics, rename (client.ts 540 lines)
+├── lsp/              # 6 tools: definition, references, symbols, diagnostics, rename (client.ts 803 lines)
 ├── ast-grep/         # 2 tools: search, replace (25 languages)
-├── delegate-task/    # Category-based routing (1135 lines)
+├── delegate-task/    # Category-based routing (executor.ts 983 lines, constants.ts 552 lines)
 ├── task/             # 4 tools: create, get, list, update (Claude Code compatible)
 ├── session-manager/  # 4 tools: list, read, search, info
 ├── grep/             # Custom grep with timeout (60s, 10MB)
 ├── glob/             # 60s timeout, 100 file limit
 ├── interactive-bash/ # Tmux session management
-├── look-at/          # Multimodal PDF/image
+├── look-at/          # Multimodal PDF/image (307 lines)
 ├── skill/            # Skill execution
 ├── skill-mcp/        # Skill MCP operations
 ├── slashcommand/     # Slash command dispatch
-├── call-omo-agent/   # Direct agent invocation
-└── background-task/  # background_output, background_cancel
+├── call-omo-agent/   # Direct agent invocation (358 lines)
+└── background-task/  # background_output, background_cancel (734 lines)
 ```
 
 ## TOOL CATEGORIES
@@ -49,13 +49,9 @@ tools/
 Claude Code compatible task management.
 
 - **task_create**: Creates a new task. Auto-generates ID and syncs to Todo.
-  - Args: `subject`, `description`, `activeForm`, `blocks`, `blockedBy`, `owner`, `metadata`
 - **task_get**: Retrieves a task by ID.
-  - Args: `id`
 - **task_list**: Lists active tasks. Filters out completed/deleted by default.
-  - Args: `status`, `parentID`
 - **task_update**: Updates task fields. Supports additive `addBlocks`/`addBlockedBy`.
-  - Args: `id`, `subject`, `description`, `status`, `activeForm`, `addBlocks`, `addBlockedBy`, `owner`, `metadata`
 
 ## HOW TO ADD