Merge pull request #2134 from code-yeongyu/fix/issue-2064-config-overwrite

fix(config): preserve existing user config when writing new defaults

.issue-comment-2064.md

@@ -0,0 +1,61 @@
+[sisyphus-bot] 
+
+## Confirmed Bug
+
+We have identified the root cause of this issue. The bug is in the config writing logic during installation.
+
+### Root Cause
+
+**File:** `src/cli/config-manager/write-omo-config.ts` (line 46)
+
+```typescript
+const merged = deepMergeRecord(existing, newConfig)
+```
+
+When a user runs `oh-my-opencode install` (even just to update settings), the installer:
+1. Reads the existing config (with user's custom model settings)
+2. Generates a **new** config based on detected provider availability
+3. Calls `deepMergeRecord(existing, newConfig)` 
+4. Writes the result back
+
+**The problem:** `deepMergeRecord` overwrites values in `existing` with values from `newConfig`. This means your custom `"model": "openai/gpt-5.2-codex"` gets overwritten by the generated default model (e.g., `anthropic/claude-opus-4-6` if Claude is available).
+
+### Why This Happens
+
+Looking at `deepMergeRecord` (line 24-25):
+```typescript
+} else if (sourceValue !== undefined) {
+  result[key] = sourceValue as TTarget[keyof TTarget]
+}
+```
+
+Any defined value in the source (generated config) overwrites the target (user's config).
+
+### Fix Approach
+
+The merge direction should be reversed to respect user overrides:
+```typescript
+const merged = deepMergeRecord(newConfig, existing)
+```
+
+This ensures:
+- User's explicit settings take precedence
+- Only new/undefined keys get populated from generated defaults
+- Custom model choices are preserved
+
+### SEVERITY: HIGH
+
+- **Impact:** User configuration is overwritten without consent
+- **Affected Files:** 
+  - `src/cli/config-manager/write-omo-config.ts`
+  - `src/cli/config-manager/deep-merge-record.ts`
+- **Trigger:** Running `oh-my-opencode install` (even for unrelated updates)
+
+### Workaround (Until Fix)
+
+Backup your config before running install:
+```bash
+cp ~/.config/opencode/oh-my-opencode.jsonc ~/.config/opencode/oh-my-opencode.jsonc.backup
+```
+
+We're working on a fix that will preserve your explicit model configurations.

AGENTS.md

@@ -1,10 +1,10 @@
 # oh-my-opencode — OpenCode Plugin
 
-**Generated:** 2026-02-21 | **Commit:** 86e3c7d1 | **Branch:** dev
+**Generated:** 2026-02-24 | **Commit:** fcb90d92 | **Branch:** dev
 
 ## OVERVIEW
 
-OpenCode plugin (npm: `oh-my-opencode`) that extends Claude Code (OpenCode fork) with multi-agent orchestration, 44 lifecycle hooks, 26 tools, skill/command/MCP systems, and Claude Code compatibility. 1208 TypeScript files, 143k LOC.
+OpenCode plugin (npm: `oh-my-opencode`) that extends Claude Code (OpenCode fork) with multi-agent orchestration, 46 lifecycle hooks, 26 tools, skill/command/MCP systems, and Claude Code compatibility. 1208 TypeScript files, 143k LOC.
 
 ## STRUCTURE
 
@@ -14,14 +14,14 @@ oh-my-opencode/
 │   ├── index.ts              # Plugin entry: loadConfig → createManagers → createTools → createHooks → createPluginInterface
 │   ├── plugin-config.ts      # JSONC multi-level config: user → project → defaults (Zod v4)
 │   ├── agents/               # 11 agents (Sisyphus, Hephaestus, Oracle, Librarian, Explore, Atlas, Prometheus, Metis, Momus, Multimodal-Looker, Sisyphus-Junior)
-│   ├── hooks/                # 44 hooks across 39 directories + 6 standalone files
+| `hooks/`                # 46 hooks across 39 directories + 6 standalone files
 │   ├── tools/                # 26 tools across 15 directories
 │   ├── features/             # 19 feature modules (background-agent, skill-loader, tmux, MCP-OAuth, etc.)
 │   ├── shared/               # 100+ utility files in 13 categories
 │   ├── config/               # Zod v4 schema system (22+ files)
 │   ├── cli/                  # CLI: install, run, doctor, mcp-oauth (Commander.js)
 │   ├── mcp/                  # 3 built-in remote MCPs (websearch, context7, grep_app)
-│   ├── plugin/               # 8 OpenCode hook handlers + 44 hook composition
+│   ├── plugin/               # 8 OpenCode hook handlers + 46 hook composition
 │   └── plugin-handlers/      # 6-phase config loading pipeline
 ├── packages/                 # Monorepo: comment-checker, opencode-sdk, 10 platform binaries
 └── local-ignore/             # Dev-only test fixtures
@@ -34,7 +34,7 @@ OhMyOpenCodePlugin(ctx)
   ├─→ loadPluginConfig()         # JSONC parse → project/user merge → Zod validate → migrate
   ├─→ createManagers()           # TmuxSessionManager, BackgroundManager, SkillMcpManager, ConfigHandler
   ├─→ createTools()              # SkillContext + AvailableCategories + ToolRegistry (26 tools)
-  ├─→ createHooks()              # 3-tier: Core(35) + Continuation(7) + Skill(2) = 44 hooks
+  ├─→ createHooks()              # 3-tier: Core(37) + Continuation(7) + Skill(2) = 46 hooks
   └─→ createPluginInterface()    # 8 OpenCode hook handlers → PluginInterface
 ```
 
@@ -87,7 +87,7 @@ Fields: agents (14 overridable, 21 fields each), categories (8 built-in + custom
 
 - **Test pattern**: Bun test (`bun:test`), co-located `*.test.ts`, given/when/then style (nested describe with `#given`/`#when`/`#then` prefixes)
 - **Factory pattern**: `createXXX()` for all tools, hooks, agents
-- **Hook tiers**: Session (22) → Tool-Guard (10) → Transform (4) → Continuation (7) → Skill (2)
+- **Hook tiers**: Session (23) → Tool-Guard (10) → Transform (4) → Continuation (7) → Skill (2)
 - **Agent modes**: `primary` (respects UI model) vs `subagent` (own fallback chain) vs `all`
 - **Model resolution**: 3-step: override → category-default → provider-fallback → system-default
 - **Config format**: JSONC with comments, Zod v4 validation, snake_case keys

assets/oh-my-opencode.schema.json

@@ -960,6 +960,9 @@
                 }
               },
               "additionalProperties": false
+            },
+            "allow_non_gpt_model": {
+              "type": "boolean"
             }
           },
           "additionalProperties": false
@@ -3248,6 +3251,11 @@
           "prompt_append": {
             "type": "string"
           },
+          "max_prompt_tokens": {
+            "type": "integer",
+            "exclusiveMinimum": 0,
+            "maximum": 9007199254740991
+          },
           "is_unstable_agent": {
             "type": "boolean"
           },

bun.lock

@@ -14,6 +14,7 @@
         "@opencode-ai/sdk": "^1.1.19",
         "commander": "^14.0.2",
         "detect-libc": "^2.0.0",
+        "diff": "^8.0.3",
         "js-yaml": "^4.1.1",
         "jsonc-parser": "^3.3.1",
         "picocolors": "^1.1.1",
@@ -28,13 +29,13 @@
         "typescript": "^5.7.3",
       },
       "optionalDependencies": {
-        "oh-my-opencode-darwin-arm64": "3.8.1",
+        "oh-my-opencode-darwin-arm64": "3.8.5",
-        "oh-my-opencode-darwin-x64": "3.8.1",
+        "oh-my-opencode-darwin-x64": "3.8.5",
-        "oh-my-opencode-linux-arm64": "3.8.1",
+        "oh-my-opencode-linux-arm64": "3.8.5",
-        "oh-my-opencode-linux-arm64-musl": "3.8.1",
+        "oh-my-opencode-linux-arm64-musl": "3.8.5",
-        "oh-my-opencode-linux-x64": "3.8.1",
+        "oh-my-opencode-linux-x64": "3.8.5",
-        "oh-my-opencode-linux-x64-musl": "3.8.1",
+        "oh-my-opencode-linux-x64-musl": "3.8.5",
-        "oh-my-opencode-windows-x64": "3.8.1",
+        "oh-my-opencode-windows-x64": "3.8.5",
       },
     },
   },
@@ -138,6 +139,8 @@
 
     "detect-libc": ["detect-libc@2.1.2", "", {}, "sha512-Btj2BOOO83o3WyH59e8MgXsxEQVcarkUOpEYrubB0urwnN10yQ364rsiByU11nZlqWYZm05i/of7io4mzihBtQ=="],
 
+    "diff": ["diff@8.0.3", "", {}, "sha512-qejHi7bcSD4hQAZE0tNAawRK1ZtafHDmMTMkrrIGgSLl7hTnQHmKCeB45xAcbfTqK2zowkM3j3bHt/4b/ARbYQ=="],
+
     "dunder-proto": ["dunder-proto@1.0.1", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.1", "es-errors": "^1.3.0", "gopd": "^1.2.0" } }, "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A=="],
 
     "ee-first": ["ee-first@1.1.1", "", {}, "sha512-WMwm9LhRUo+WUaRN+vRuETqG89IgZphVSNkdFgeb6sS/E4OrDIN7t48CAewSHXc6C8lefD8KKfr5vY61brQlow=="],
@@ -228,19 +231,19 @@
 
     "object-inspect": ["object-inspect@1.13.4", "", {}, "sha512-W67iLl4J2EXEGTbfeHCffrjDfitvLANg0UlX3wFUUSTx92KXRFegMHUVgSqE+wvhAbi4WqjGg9czysTV2Epbew=="],
 
-    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.8.1", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-vbtS0WUFOZpufKzlX2G83fIDry3rpiXej8zNuXNCkx7hF34rK04rj0zeBH9dL+kdNV0Ys0Wl1rR1Mjto28UcAw=="],
+    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.8.5", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-bbLu1We9NNhYAVp9Q/FK8dYFlYLp2PKfvdBCr+O6QjNRixdjp8Ru4RK7i9mKg0ybYBUzzCcbbC2Cc1o8orkhBA=="],
 
-    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.8.1", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-gLz6dLNg9hr7roqBjaqlxta6+XYCs032/FiE0CiwypIBtYOq5EAgDVJ95JY5DQ2M+3Un028d50yMfwsfNfGlSw=="],
+    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.8.5", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-N9GcmzYgL87UybSaMGiHc5lwT5Mxg1tyB502el5syouN39wfeUYoj37SonENrMUTiEfn75Lwv/5cSLCesSubpA=="],
 
-    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.8.1", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-teAIuHlR5xOAoUmA+e0bGzy3ikgIr+nCdyOPwHYm8jIp0aBUWAqbcdoQLeNTgenWpoM8vhHk+2xh4WcCeQzjEA=="],
+    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.8.5", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-ki4a7s1DD5z5wEKmzcchqAKOIpw0LsBvyF8ieqNLS5Xl8PWE0gAZ7rqjlXC54NTubpexVH6lO2yenFJsk2Zk9A=="],
 
-    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.8.1", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-VzBEq1H5dllEloouIoLdbw1icNUW99qmvErFrNj66mX42DNXK+f1zTtvBG8U6eeFfUBRRJoUjdCsvO65f8BkFA=="],
+    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.8.5", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-9+6hU3z503fBzuV0VjxIkTKFElbKacHijFcdKAussG6gPFLWmCRWtdowzEDwUfAoIsoHHH7FBwvh5waGp/ZksA=="],
 
-    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.8.1", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-8hDcb8s+wdQpQObSmiyaaTV0P/js2Bs9Lu+HmzrkKjuMLXXj/Gk7K0kKWMoEnMbMGfj86GfBHHIWmu9juI/SjA=="],
+    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.8.5", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-DmnMK/PgvdcCYL+OQE5iZWgi/vmjm0sIPQVQgSUbWn3izcUF7C5DtlxqaU2cKxNZwrhDTlJdLWxmJqgLmLqd9A=="],
 
-    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.8.1", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-idyH5bdYn7wrLkIkYr83omN83E2BjA/9DUHCX2we8VXbhDVbBgmMpUg8B8nKnd5NK/SyLHgRs5QqQJw8XBC0cQ=="],
+    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.8.5", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-jhCNStljsyapVq9X7PaHSOcWxxEA4BUcIibvoPs/xc7fVP8D47p651LzIRsM6STn6Bx684mlYbxxX1P/0QPKNg=="],
 
-    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.8.1", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-O30L1PUF9aq1vSOyadcXQOLnDFSTvYn6cGd5huh0LAK/us0hGezoahtXegMdFtDXPIIREJlkRQhyJiafza7YgA=="],
+    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.8.5", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-lcPBp9NCNQ6TnqzsN9p/K+xKwOzBoIPw7HncxmrXSberZ3uHy0K9uNraQ7fqnXIKWqQiK4kSwWfSHpmhbaHiNg=="],
 
     "on-finished": ["on-finished@2.4.1", "", { "dependencies": { "ee-first": "1.1.1" } }, "sha512-oVlzkg3ENAhCk2zdv7IJwd/QUD4z2RxRwpkcGY8psCVcCYZNq4wYnVWALHM+brtuJjePWiYF/ClmuDr8Ch5+kg=="],
 

package.json

@@ -60,6 +60,7 @@
     "@opencode-ai/sdk": "^1.1.19",
     "commander": "^14.0.2",
     "detect-libc": "^2.0.0",
+    "diff": "^8.0.3",
     "js-yaml": "^4.1.1",
     "jsonc-parser": "^3.3.1",
     "picocolors": "^1.1.1",

signatures/cla.json

@@ -1703,6 +1703,70 @@
       "created_at": "2026-02-23T19:27:59Z",
       "repoId": 1108837393,
       "pullRequestNo": 2080
+    },
+    {
+      "name": "PHP-Expert",
+      "id": 12047666,
+      "comment_id": 3951828700,
+      "created_at": "2026-02-24T13:27:18Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2098
+    },
+    {
+      "name": "Pantoria",
+      "id": 37699442,
+      "comment_id": 3953543578,
+      "created_at": "2026-02-24T17:12:31Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1983
+    },
+    {
+      "name": "east-shine",
+      "id": 20237288,
+      "comment_id": 3957576758,
+      "created_at": "2026-02-25T08:19:34Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2113
+    },
+    {
+      "name": "SupenBysz",
+      "id": 3314033,
+      "comment_id": 3962352704,
+      "created_at": "2026-02-25T22:00:54Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2119
+    },
+    {
+      "name": "zhzy0077",
+      "id": 8717471,
+      "comment_id": 3964015975,
+      "created_at": "2026-02-26T04:45:23Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2125
+    },
+    {
+      "name": "spacecowboy0416",
+      "id": 239068998,
+      "comment_id": 3964320737,
+      "created_at": "2026-02-26T06:05:27Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2126
+    },
+    {
+      "name": "imwxc",
+      "id": 49653609,
+      "comment_id": 3965127447,
+      "created_at": "2026-02-26T09:00:16Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2129
+    },
+    {
+      "name": "maou-shonen",
+      "id": 22576780,
+      "comment_id": 3965445132,
+      "created_at": "2026-02-26T09:50:46Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2131
     }
   ]
 }

src/AGENTS.md

@@ -1,6 +1,6 @@
 # src/ — Plugin Source
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 
@@ -14,7 +14,7 @@ Root source directory. Entry point `index.ts` orchestrates 4-step initialization
 | `plugin-config.ts` | JSONC parse, multi-level merge (user → project → defaults), Zod validation |
 | `create-managers.ts` | TmuxSessionManager, BackgroundManager, SkillMcpManager, ConfigHandler |
 | `create-tools.ts` | SkillContext + AvailableCategories + ToolRegistry |
-| `create-hooks.ts` | 3-tier hook composition: Core(35) + Continuation(7) + Skill(2) |
+| `create-hooks.ts` | 3-tier hook composition: Core(37) + Continuation(7) + Skill(2) |
 | `plugin-interface.ts` | Assembles 8 OpenCode hook handlers into PluginInterface |
 
 ## CONFIG LOADING
@@ -32,9 +32,9 @@ loadPluginConfig(directory, ctx)
 
 ```
 createHooks()
-  ├─→ createCoreHooks()           # 35 hooks
+  ├─→ createCoreHooks()           # 37 hooks
-  │   ├─ createSessionHooks()     # 21: contextWindowMonitor, thinkMode, ralphLoop, sessionRecovery, jsonErrorRecovery, sisyphusGptHephaestusReminder, anthropicEffort...
+  │   ├─ createSessionHooks()     # 23: contextWindowMonitor, thinkMode, ralphLoop, modelFallback, runtimeFallback, noSisyphusGpt, noHephaestusNonGpt, anthropicEffort...
-  │   ├─ createToolGuardHooks()   # 10: commentChecker, rulesInjector, writeExistingFileGuard, hashlineEditDiffEnhancer...
+  │   ├─ createToolGuardHooks()   # 10: commentChecker, rulesInjector, writeExistingFileGuard, jsonErrorRecovery, hashlineReadEnhancer...
   │   └─ createTransformHooks()   # 4: claudeCodeHooks, keywordDetector, contextInjector, thinkingBlockValidator
   ├─→ createContinuationHooks()   # 7: todoContinuationEnforcer, atlas, stopContinuationGuard...
   └─→ createSkillHooks()          # 2: categorySkillReminder, autoSlashCommand

src/agents/AGENTS.md

@@ -1,6 +1,6 @@
 # src/agents/ — 11 Agent Definitions
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/agents/atlas/agent.ts

@@ -17,7 +17,6 @@ import type { AvailableAgent, AvailableSkill, AvailableCategory } from "../dynam
 import { buildCategorySkillsDelegationGuide } from "../dynamic-agent-prompt-builder"
 import type { CategoryConfig } from "../../config/schema"
 import { mergeCategories } from "../../shared/merge-categories"
-import { createAgentToolRestrictions } from "../../shared/permission-compat"
 
 import { getDefaultAtlasPrompt } from "./default"
 import { getGptAtlasPrompt } from "./gpt"
@@ -100,11 +99,6 @@ function buildDynamicOrchestratorPrompt(ctx?: OrchestratorContext): string {
 }
 
 export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
-  const restrictions = createAgentToolRestrictions([
-    "task",
-    "call_omo_agent",
-  ])
-
   const baseConfig = {
     description:
       "Orchestrates work via task() to complete ALL tasks in a todo list until fully done. (Atlas - OhMyOpenCode)",
@@ -113,7 +107,6 @@ export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
     temperature: 0.1,
     prompt: buildDynamicOrchestratorPrompt(ctx),
     color: "#10B981",
-    ...restrictions,
   }
 
   return baseConfig as AgentConfig

src/agents/env-context.test.ts

@@ -0,0 +1,41 @@
+/// <reference types="bun-types" />
+
+import { describe, test, expect } from "bun:test"
+import { createEnvContext } from "./env-context"
+
+describe("createEnvContext", () => {
+  test("returns omo-env block with timezone and locale", () => {
+    // #given - no setup needed
+
+    // #when
+    const result = createEnvContext()
+
+    // #then
+    expect(result).toContain("<omo-env>")
+    expect(result).toContain("</omo-env>")
+    expect(result).toContain("Timezone:")
+    expect(result).toContain("Locale:")
+    expect(result).not.toContain("Current date:")
+  })
+
+  test("does not include time with seconds precision to preserve token cache", () => {
+    // #given - seconds-precision time changes every second, breaking cache on every request
+
+    // #when
+    const result = createEnvContext()
+
+    // #then - no HH:MM:SS pattern anywhere in the output
+    expect(result).not.toMatch(/\d{1,2}:\d{2}:\d{2}/)
+  })
+
+  test("does not include date or time fields since OpenCode already provides them", () => {
+    // #given - OpenCode's system.ts already injects date, platform, working directory
+
+    // #when
+    const result = createEnvContext()
+
+    // #then - only timezone and locale remain; both are stable across requests
+    expect(result).not.toContain("Current date:")
+    expect(result).not.toContain("Current time:")
+  })
+})

src/agents/env-context.ts

@@ -1,32 +1,15 @@
 /**
- * Creates OmO-specific environment context (time, timezone, locale).
+ * Creates OmO-specific environment context (timezone, locale).
  * Note: Working directory, platform, and date are already provided by OpenCode's system.ts,
  * so we only include fields that OpenCode doesn't provide to avoid duplication.
  * See: https://github.com/code-yeongyu/oh-my-opencode/issues/379
  */
 export function createEnvContext(): string {
-  const now = new Date()
   const timezone = Intl.DateTimeFormat().resolvedOptions().timeZone
   const locale = Intl.DateTimeFormat().resolvedOptions().locale
 
-  const dateStr = now.toLocaleDateString(locale, {
-    weekday: "short",
-    year: "numeric",
-    month: "short",
-    day: "numeric",
-  })
-
-  const timeStr = now.toLocaleTimeString(locale, {
-    hour: "2-digit",
-    minute: "2-digit",
-    second: "2-digit",
-    hour12: true,
-  })
-
   return `
 <omo-env>
-  Current date: ${dateStr}
-  Current time: ${timeStr}
   Timezone: ${timezone}
   Locale: ${locale}
 </omo-env>`

src/agents/hephaestus.ts

@@ -448,6 +448,21 @@ ${oracleSection}
 4. **Run build** if applicable — exit code 0 required
 5. **Tell user** what you verified and the results — keep it clear and helpful
 
+### Auto-Commit Policy (MANDATORY for implementation/fix work)
+
+1. **Auto-commit after implementation is complete** when the task includes feature/fix code changes
+2. **Commit ONLY after verification gates pass**:
+   - \`lsp_diagnostics\` clean on all modified files
+   - Related tests pass
+   - Typecheck/build pass when applicable
+3. **If any gate fails, DO NOT commit** — fix issues first, re-run verification, then commit
+4. **Use Conventional Commits format** with meaningful intent-focused messages:
+   - \`feat(scope): add ...\` for new functionality
+   - \`fix(scope): resolve ...\` for bug fixes
+   - \`refactor(scope): simplify ...\` for internal restructuring
+5. **Do not make placeholder commits** (\`wip\`, \`temp\`, \`update\`) or commit unverified code
+6. **If user explicitly says not to commit**, skip commit and report that changes are left uncommitted
+
 - **File edit** — \`lsp_diagnostics\` clean
 - **Build** — Exit code 0
 - **Tests** — Pass (or pre-existing failures noted)

src/agents/tool-restrictions.test.ts

@@ -4,6 +4,7 @@ import { createLibrarianAgent } from "./librarian"
 import { createExploreAgent } from "./explore"
 import { createMomusAgent } from "./momus"
 import { createMetisAgent } from "./metis"
+import { createAtlasAgent } from "./atlas"
 
 const TEST_MODEL = "anthropic/claude-sonnet-4-5"
 
@@ -96,4 +97,18 @@ describe("read-only agent tool restrictions", () => {
       }
     })
   })
+
+  describe("Atlas", () => {
+    test("allows delegation tools for orchestration", () => {
+      // given
+      const agent = createAtlasAgent({ model: TEST_MODEL })
+
+      // when
+      const permission = (agent.permission ?? {}) as Record<string, string>
+
+      // then
+      expect(permission["task"]).toBeUndefined()
+      expect(permission["call_omo_agent"]).toBeUndefined()
+    })
+  })
 })

src/agents/types.test.ts

@@ -2,11 +2,17 @@ import { describe, test, expect } from "bun:test";
 import { isGptModel, isGeminiModel } from "./types";
 
 describe("isGptModel", () => {
-  test("standard openai provider models", () => {
+  test("standard openai provider gpt models", () => {
     expect(isGptModel("openai/gpt-5.2")).toBe(true);
     expect(isGptModel("openai/gpt-4o")).toBe(true);
-    expect(isGptModel("openai/o1")).toBe(true);
+  });
-    expect(isGptModel("openai/o3-mini")).toBe(true);
+
+  test("o-series models are not gpt by name", () => {
+    expect(isGptModel("openai/o1")).toBe(false);
+    expect(isGptModel("openai/o3-mini")).toBe(false);
+    expect(isGptModel("litellm/o1")).toBe(false);
+    expect(isGptModel("litellm/o3-mini")).toBe(false);
+    expect(isGptModel("litellm/o4-mini")).toBe(false);
   });
 
   test("github copilot gpt models", () => {
@@ -17,9 +23,6 @@ describe("isGptModel", () => {
   test("litellm proxied gpt models", () => {
     expect(isGptModel("litellm/gpt-5.2")).toBe(true);
     expect(isGptModel("litellm/gpt-4o")).toBe(true);
-    expect(isGptModel("litellm/o1")).toBe(true);
-    expect(isGptModel("litellm/o3-mini")).toBe(true);
-    expect(isGptModel("litellm/o4-mini")).toBe(true);
   });
 
   test("other proxied gpt models", () => {
@@ -27,6 +30,11 @@ describe("isGptModel", () => {
     expect(isGptModel("custom-provider/gpt-5.2")).toBe(true);
   });
 
+  test("venice provider gpt models", () => {
+    expect(isGptModel("venice/gpt-5.2")).toBe(true);
+    expect(isGptModel("venice/gpt-4o")).toBe(true);
+  });
+
   test("gpt4 prefix without hyphen (legacy naming)", () => {
     expect(isGptModel("litellm/gpt4o")).toBe(true);
     expect(isGptModel("ollama/gpt4")).toBe(true);

src/agents/types.ts

@@ -70,14 +70,9 @@ function extractModelName(model: string): string {
   return model.includes("/") ? model.split("/").pop() ?? model : model
 }
 
-const GPT_MODEL_PREFIXES = ["gpt-", "gpt4", "o1", "o3", "o4"]
-
 export function isGptModel(model: string): boolean {
-  if (model.startsWith("openai/") || model.startsWith("github-copilot/gpt-"))
-    return true
-
   const modelName = extractModelName(model).toLowerCase()
-  return GPT_MODEL_PREFIXES.some((prefix) => modelName.startsWith(prefix))
+  return modelName.includes("gpt")
 }
 
 const GEMINI_PROVIDERS = ["google/", "google-vertex/"]

src/agents/utils.test.ts

@@ -589,20 +589,22 @@ describe("createBuiltinAgents with requiresProvider gating (hephaestus)", () =>
     }
   })
 
-  test("hephaestus is created when github-copilot provider is connected", async () => {
+  test("hephaestus IS created when github-copilot is connected with a GPT model", async () => {
-    // #given - github-copilot provider has models available
+    // #given - github-copilot provider has gpt-5.3-codex available
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
       new Set(["github-copilot/gpt-5.3-codex"])
     )
+    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
 
     try {
       // #when
       const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], {})
 
-      // #then
+      // #then - github-copilot is now a valid provider for hephaestus
       expect(agents.hephaestus).toBeDefined()
     } finally {
       fetchSpy.mockRestore()
+      cacheSpy.mockRestore()
     }
   })
 

src/cli/AGENTS.md

@@ -1,6 +1,6 @@
 # src/cli/ — CLI: install, run, doctor, mcp-oauth
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

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

@@ -750,10 +750,6 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models when
     "explore": {
       "model": "github-copilot/gpt-5-mini",
     },
-    "hephaestus": {
-      "model": "github-copilot/gpt-5.3-codex",
-      "variant": "medium",
-    },
     "librarian": {
       "model": "github-copilot/claude-sonnet-4.5",
     },
@@ -786,16 +782,12 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models when
       "model": "github-copilot/gemini-3-pro-preview",
       "variant": "high",
     },
-    "deep": {
-      "model": "github-copilot/gpt-5.3-codex",
-      "variant": "medium",
-    },
     "quick": {
       "model": "github-copilot/claude-haiku-4.5",
     },
     "ultrabrain": {
-      "model": "github-copilot/gpt-5.3-codex",
+      "model": "github-copilot/gemini-3-pro-preview",
-      "variant": "xhigh",
+      "variant": "high",
     },
     "unspecified-high": {
       "model": "github-copilot/claude-sonnet-4.5",
@@ -824,10 +816,6 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models with
     "explore": {
       "model": "github-copilot/gpt-5-mini",
     },
-    "hephaestus": {
-      "model": "github-copilot/gpt-5.3-codex",
-      "variant": "medium",
-    },
     "librarian": {
       "model": "github-copilot/claude-sonnet-4.5",
     },
@@ -860,16 +848,12 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models with
       "model": "github-copilot/gemini-3-pro-preview",
       "variant": "high",
     },
-    "deep": {
-      "model": "github-copilot/gpt-5.3-codex",
-      "variant": "medium",
-    },
     "quick": {
       "model": "github-copilot/claude-haiku-4.5",
     },
     "ultrabrain": {
-      "model": "github-copilot/gpt-5.3-codex",
+      "model": "github-copilot/gemini-3-pro-preview",
-      "variant": "xhigh",
+      "variant": "high",
     },
     "unspecified-high": {
       "model": "github-copilot/claude-opus-4.6",
@@ -1285,7 +1269,7 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
       "model": "opencode/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "github-copilot/gpt-5.3-codex",
+      "model": "opencode/gpt-5.3-codex",
       "variant": "medium",
     },
     "librarian": {
@@ -1321,14 +1305,14 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
       "variant": "high",
     },
     "deep": {
-      "model": "github-copilot/gpt-5.3-codex",
+      "model": "opencode/gpt-5.3-codex",
       "variant": "medium",
     },
     "quick": {
       "model": "github-copilot/claude-haiku-4.5",
     },
     "ultrabrain": {
-      "model": "github-copilot/gpt-5.3-codex",
+      "model": "opencode/gpt-5.3-codex",
       "variant": "xhigh",
     },
     "unspecified-high": {

src/cli/config-manager/AGENTS.md

@@ -1,6 +1,6 @@
 # src/cli/config-manager/ — CLI Installation Utilities
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/cli/config-manager/write-omo-config.test.ts

@@ -0,0 +1,80 @@
+import { afterEach, beforeEach, describe, expect, it } from "bun:test"
+import { mkdirSync, readFileSync, rmSync, writeFileSync } from "node:fs"
+import { tmpdir } from "node:os"
+import { join } from "node:path"
+
+import { parseJsonc } from "../../shared/jsonc-parser"
+import type { InstallConfig } from "../types"
+import { resetConfigContext } from "./config-context"
+import { generateOmoConfig } from "./generate-omo-config"
+import { writeOmoConfig } from "./write-omo-config"
+
+const installConfig: InstallConfig = {
+  hasClaude: true,
+  isMax20: true,
+  hasOpenAI: true,
+  hasGemini: true,
+  hasCopilot: false,
+  hasOpencodeZen: false,
+  hasZaiCodingPlan: false,
+  hasKimiForCoding: false,
+}
+
+function getRecord(value: unknown): Record<string, unknown> {
+  if (value && typeof value === "object" && !Array.isArray(value)) {
+    return value as Record<string, unknown>
+  }
+
+  return {}
+}
+
+describe("writeOmoConfig", () => {
+  let testConfigDir = ""
+  let testConfigPath = ""
+
+  beforeEach(() => {
+    testConfigDir = join(tmpdir(), `omo-write-config-${Date.now()}-${Math.random().toString(36).slice(2)}`)
+    testConfigPath = join(testConfigDir, "oh-my-opencode.json")
+
+    mkdirSync(testConfigDir, { recursive: true })
+    process.env.OPENCODE_CONFIG_DIR = testConfigDir
+    resetConfigContext()
+  })
+
+  afterEach(() => {
+    rmSync(testConfigDir, { recursive: true, force: true })
+    resetConfigContext()
+    delete process.env.OPENCODE_CONFIG_DIR
+  })
+
+  it("preserves existing user values while adding new defaults", () => {
+    // given
+    const existingConfig = {
+      agents: {
+        sisyphus: {
+          model: "custom/provider-model",
+        },
+      },
+      disabled_hooks: ["comment-checker"],
+    }
+    writeFileSync(testConfigPath, JSON.stringify(existingConfig, null, 2) + "\n", "utf-8")
+
+    const generatedDefaults = generateOmoConfig(installConfig)
+
+    // when
+    const result = writeOmoConfig(installConfig)
+
+    // then
+    expect(result.success).toBe(true)
+
+    const savedConfig = parseJsonc<Record<string, unknown>>(readFileSync(testConfigPath, "utf-8"))
+    const savedAgents = getRecord(savedConfig.agents)
+    const savedSisyphus = getRecord(savedAgents.sisyphus)
+    expect(savedSisyphus.model).toBe("custom/provider-model")
+    expect(savedConfig.disabled_hooks).toEqual(["comment-checker"])
+
+    for (const defaultKey of Object.keys(generatedDefaults)) {
+      expect(savedConfig).toHaveProperty(defaultKey)
+    }
+  })
+})

src/cli/config-manager/write-omo-config.ts

@@ -43,7 +43,7 @@ export function writeOmoConfig(installConfig: InstallConfig): ConfigMergeResult
           return { success: true, configPath: omoConfigPath }
         }
 
-        const merged = deepMergeRecord(existing, newConfig)
+        const merged = deepMergeRecord(newConfig, existing)
         writeFileSync(omoConfigPath, JSON.stringify(merged, null, 2) + "\n")
       } catch (parseErr) {
         if (parseErr instanceof SyntaxError) {

src/cli/model-fallback-requirements.ts

@@ -17,9 +17,9 @@ export const CLI_AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   },
   hephaestus: {
     fallbackChain: [
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
+      { providers: ["openai", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
     ],
-    requiresProvider: ["openai", "github-copilot", "opencode"],
+    requiresProvider: ["openai", "opencode"],
   },
   oracle: {
     fallbackChain: [
@@ -100,14 +100,14 @@ export const CLI_CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> =
   },
   ultrabrain: {
     fallbackChain: [
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.3-codex", variant: "xhigh" },
+      { providers: ["openai", "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-4-6", variant: "max" },
     ],
   },
   deep: {
     fallbackChain: [
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
+      { providers: ["openai", "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" },
     ],
@@ -131,7 +131,7 @@ export const CLI_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-5.3-codex", variant: "medium" },
+      { providers: ["openai", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" },
     ],
   },

src/cli/model-fallback.test.ts

@@ -421,16 +421,15 @@ describe("generateModelConfig", () => {
       expect(result.agents?.hephaestus?.variant).toBe("medium")
     })
 
-    test("Hephaestus is created when Copilot is available (github-copilot provider connected)", () => {
+    test("Hephaestus is NOT created when only Copilot is available (gpt-5.3-codex unavailable on github-copilot)", () => {
       // #given
       const config = createConfig({ hasCopilot: true })
 
       // #when
       const result = generateModelConfig(config)
 
-      // #then
+      // #then - hephaestus is omitted because gpt-5.3-codex is not available on github-copilot
-      expect(result.agents?.hephaestus?.model).toBe("github-copilot/gpt-5.3-codex")
+      expect(result.agents?.hephaestus).toBeUndefined()
-      expect(result.agents?.hephaestus?.variant).toBe("medium")
     })
 
     test("Hephaestus is created when OpenCode Zen is available (opencode provider connected)", () => {

src/cli/run/AGENTS.md

@@ -1,6 +1,6 @@
 # src/cli/run/ — Non-Interactive Session Launcher
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/cli/run/event-handlers.test.ts

@@ -1,4 +1,4 @@
-import { describe, it, expect, spyOn } from "bun:test"
+const { describe, it, expect, spyOn } = require("bun:test")
 import type { RunContext } from "./types"
 import { createEventState } from "./events"
 import { handleSessionStatus, handleMessagePartUpdated, handleMessageUpdated, handleTuiToast } from "./event-handlers"
@@ -235,9 +235,7 @@ describe("handleMessagePartUpdated", () => {
 
   it("prints completion metadata once when assistant text part is completed", () => {
     // given
-    const nowSpy = spyOn(Date, "now")
+    const nowSpy = spyOn(Date, "now").mockReturnValue(3400)
-    nowSpy.mockReturnValueOnce(1000)
-    nowSpy.mockReturnValueOnce(3400)
 
     const ctx = createMockContext("ses_main")
     const state = createEventState()
@@ -259,6 +257,7 @@ describe("handleMessagePartUpdated", () => {
       } as any,
       state,
     )
+    state.messageStartedAtById["msg_1"] = 1000
 
     // when
     handleMessagePartUpdated(

src/cli/run/event-state.ts

@@ -7,6 +7,8 @@ export interface EventState {
   currentTool: string | null
   /** Set to true when the main session has produced meaningful work (text, tool call, or tool result) */
   hasReceivedMeaningfulWork: boolean
+  /** Timestamp of the last received event (for watchdog detection) */
+  lastEventTimestamp: number
   /** Count of assistant messages for the main session */
   messageCount: number
   /** Current agent name from the latest assistant message */
@@ -54,6 +56,7 @@ export function createEventState(): EventState {
     lastPartText: "",
     currentTool: null,
     hasReceivedMeaningfulWork: false,
+    lastEventTimestamp: Date.now(),
     messageCount: 0,
     currentAgent: null,
     currentModel: null,

src/cli/run/event-stream-processor.ts

@@ -35,6 +35,9 @@ export async function processEvents(
         logEventVerbose(ctx, payload)
       }
 
+      // Update last event timestamp for watchdog detection
+      state.lastEventTimestamp = Date.now()
+
       handleSessionError(ctx, payload, state)
       handleSessionIdle(ctx, payload, state)
       handleSessionStatus(ctx, payload, state)

src/cli/run/poll-for-completion.ts

@@ -8,11 +8,15 @@ const DEFAULT_POLL_INTERVAL_MS = 500
 const DEFAULT_REQUIRED_CONSECUTIVE = 1
 const ERROR_GRACE_CYCLES = 3
 const MIN_STABILIZATION_MS = 1_000
+const DEFAULT_EVENT_WATCHDOG_MS = 30_000 // 30 seconds
+const DEFAULT_SECONDARY_MEANINGFUL_WORK_TIMEOUT_MS = 60_000 // 60 seconds
 
 export interface PollOptions {
   pollIntervalMs?: number
   requiredConsecutive?: number
   minStabilizationMs?: number
+  eventWatchdogMs?: number
+  secondaryMeaningfulWorkTimeoutMs?: number
 }
 
 export async function pollForCompletion(
@@ -28,9 +32,15 @@ export async function pollForCompletion(
     options.minStabilizationMs ?? MIN_STABILIZATION_MS
   const minStabilizationMs =
     rawMinStabilizationMs > 0 ? rawMinStabilizationMs : MIN_STABILIZATION_MS
+  const eventWatchdogMs =
+    options.eventWatchdogMs ?? DEFAULT_EVENT_WATCHDOG_MS
+  const secondaryMeaningfulWorkTimeoutMs =
+    options.secondaryMeaningfulWorkTimeoutMs ??
+    DEFAULT_SECONDARY_MEANINGFUL_WORK_TIMEOUT_MS
   let consecutiveCompleteChecks = 0
   let errorCycleCount = 0
   let firstWorkTimestamp: number | null = null
+  let secondaryTimeoutChecked = false
   const pollStartTimestamp = Date.now()
 
   while (!abortController.signal.aborted) {
@@ -59,7 +69,37 @@ export async function pollForCompletion(
       errorCycleCount = 0
     }
 
-    const mainSessionStatus = await getMainSessionStatus(ctx)
+    // Watchdog: if no events received for N seconds, verify session status via API
+    let mainSessionStatus: "idle" | "busy" | "retry" | null = null
+    if (eventState.lastEventTimestamp !== null) {
+      const timeSinceLastEvent = Date.now() - eventState.lastEventTimestamp
+      if (timeSinceLastEvent > eventWatchdogMs) {
+        // Events stopped coming - verify actual session state
+        console.log(
+          pc.yellow(
+            `\n  No events for ${Math.round(
+              timeSinceLastEvent / 1000
+            )}s, verifying session status...`
+          )
+        )
+
+        // Force check session status directly
+        mainSessionStatus = await getMainSessionStatus(ctx)
+        if (mainSessionStatus === "idle") {
+          eventState.mainSessionIdle = true
+        } else if (mainSessionStatus === "busy" || mainSessionStatus === "retry") {
+          eventState.mainSessionIdle = false
+        }
+
+        // Reset timestamp to avoid repeated checks
+        eventState.lastEventTimestamp = Date.now()
+      }
+    }
+
+    // Only call getMainSessionStatus if watchdog didn't already check
+    if (mainSessionStatus === null) {
+      mainSessionStatus = await getMainSessionStatus(ctx)
+    }
     if (mainSessionStatus === "busy" || mainSessionStatus === "retry") {
       eventState.mainSessionIdle = false
     } else if (mainSessionStatus === "idle") {
@@ -81,6 +121,50 @@ export async function pollForCompletion(
         consecutiveCompleteChecks = 0
         continue
       }
+
+      // Secondary timeout: if we've been polling for reasonable time but haven't
+      // received meaningful work via events, check if there's active work via API
+      // Only check once to avoid unnecessary API calls every poll cycle
+      if (
+        Date.now() - pollStartTimestamp > secondaryMeaningfulWorkTimeoutMs &&
+        !secondaryTimeoutChecked
+      ) {
+        secondaryTimeoutChecked = true
+        // Check if session actually has pending work (children, todos, etc.)
+        const childrenRes = await ctx.client.session.children({
+          path: { id: ctx.sessionID },
+          query: { directory: ctx.directory },
+        })
+        const children = normalizeSDKResponse(childrenRes, [] as unknown[])
+        const todosRes = await ctx.client.session.todo({
+          path: { id: ctx.sessionID },
+          query: { directory: ctx.directory },
+        })
+        const todos = normalizeSDKResponse(todosRes, [] as unknown[])
+
+        const hasActiveChildren =
+          Array.isArray(children) && children.length > 0
+        const hasActiveTodos =
+          Array.isArray(todos) &&
+          todos.some(
+            (t: unknown) =>
+              (t as { status?: string })?.status !== "completed" &&
+              (t as { status?: string })?.status !== "cancelled"
+          )
+        const hasActiveWork = hasActiveChildren || hasActiveTodos
+
+        if (hasActiveWork) {
+          // Assume meaningful work is happening even without events
+          eventState.hasReceivedMeaningfulWork = true
+          console.log(
+            pc.yellow(
+              `\n  No meaningful work events for ${Math.round(
+                secondaryMeaningfulWorkTimeoutMs / 1000
+              )}s but session has active work - assuming in progress`
+            )
+          )
+        }
+      }
     } else {
       // Track when first meaningful work was received
       if (firstWorkTimestamp === null) {

src/config/AGENTS.md

@@ -1,6 +1,6 @@
 # src/config/ — Zod v4 Schema System
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/config/schema/agent-overrides.ts

@@ -59,7 +59,9 @@ export const AgentOverridesSchema = z.object({
   build: AgentOverrideConfigSchema.optional(),
   plan: AgentOverrideConfigSchema.optional(),
   sisyphus: AgentOverrideConfigSchema.optional(),
-  hephaestus: AgentOverrideConfigSchema.optional(),
+  hephaestus: AgentOverrideConfigSchema.extend({
+    allow_non_gpt_model: z.boolean().optional(),
+  }).optional(),
   "sisyphus-junior": AgentOverrideConfigSchema.optional(),
   "OpenCode-Builder": AgentOverrideConfigSchema.optional(),
   prometheus: AgentOverrideConfigSchema.optional(),

src/config/schema/categories.ts

@@ -20,6 +20,7 @@ export const CategoryConfigSchema = z.object({
   textVerbosity: z.enum(["low", "medium", "high"]).optional(),
   tools: z.record(z.string(), z.boolean()).optional(),
   prompt_append: z.string().optional(),
+  max_prompt_tokens: z.number().int().positive().optional(),
   /** Mark agent as unstable - forces background mode for monitoring. Auto-enabled for gemini/minimax models. */
   is_unstable_agent: z.boolean().optional(),
   /** Disable this category. Disabled categories are excluded from task delegation. */

src/features/AGENTS.md

@@ -1,6 +1,6 @@
 # src/features/ — 19 Feature Modules
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/features/background-agent/AGENTS.md

@@ -1,6 +1,6 @@
 # src/features/background-agent/ — Core Orchestration Engine
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

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

@@ -191,6 +191,10 @@ function getPendingByParent(manager: BackgroundManager): Map<string, Set<string>
   return (manager as unknown as { pendingByParent: Map<string, Set<string>> }).pendingByParent
 }
 
+function getPendingNotifications(manager: BackgroundManager): Map<string, string[]> {
+  return (manager as unknown as { pendingNotifications: Map<string, string[]> }).pendingNotifications
+}
+
 function getCompletionTimers(manager: BackgroundManager): Map<string, ReturnType<typeof setTimeout>> {
   return (manager as unknown as { completionTimers: Map<string, ReturnType<typeof setTimeout>> }).completionTimers
 }
@@ -1057,6 +1061,49 @@ describe("BackgroundManager.notifyParentSession - aborted parent", () => {
 
     manager.shutdown()
   })
+
+  test("should queue notification when promptAsync aborts while parent is idle", async () => {
+    //#given
+    const promptMock = async () => {
+      const error = new Error("Request aborted while waiting for input")
+      error.name = "MessageAbortedError"
+      throw error
+    }
+    const client = {
+      session: {
+        prompt: promptMock,
+        promptAsync: promptMock,
+        abort: async () => ({}),
+        messages: async () => ({ data: [] }),
+      },
+    }
+    const manager = new BackgroundManager({ client, directory: tmpdir() } as unknown as PluginInput)
+    const task: BackgroundTask = {
+      id: "task-aborted-idle-queue",
+      sessionID: "session-child",
+      parentSessionID: "session-parent",
+      parentMessageID: "msg-parent",
+      description: "task idle queue",
+      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
+    const queuedNotifications = getPendingNotifications(manager).get("session-parent") ?? []
+    expect(queuedNotifications).toHaveLength(1)
+    expect(queuedNotifications[0]).toContain("<system-reminder>")
+    expect(queuedNotifications[0]).toContain("[ALL BACKGROUND TASKS COMPLETE]")
+
+    manager.shutdown()
+  })
 })
 
 describe("BackgroundManager.notifyParentSession - notifications toggle", () => {
@@ -1105,6 +1152,29 @@ describe("BackgroundManager.notifyParentSession - notifications toggle", () => {
   })
 })
 
+describe("BackgroundManager.injectPendingNotificationsIntoChatMessage", () => {
+  test("should prepend queued notifications to first text part and clear queue", () => {
+    // given
+    const manager = createBackgroundManager()
+    manager.queuePendingNotification("session-parent", "<system-reminder>queued-one</system-reminder>")
+    manager.queuePendingNotification("session-parent", "<system-reminder>queued-two</system-reminder>")
+    const output = {
+      parts: [{ type: "text", text: "User prompt" }],
+    }
+
+    // when
+    manager.injectPendingNotificationsIntoChatMessage(output, "session-parent")
+
+    // then
+    expect(output.parts[0].text).toContain("<system-reminder>queued-one</system-reminder>")
+    expect(output.parts[0].text).toContain("<system-reminder>queued-two</system-reminder>")
+    expect(output.parts[0].text).toContain("User prompt")
+    expect(getPendingNotifications(manager).get("session-parent")).toBeUndefined()
+
+    manager.shutdown()
+  })
+})
+
 function buildNotificationPromptBody(
   task: BackgroundTask,
   currentMessage: CurrentMessage | null

src/features/background-agent/manager.ts

@@ -93,6 +93,7 @@ export class BackgroundManager {
 
   private tasks: Map<string, BackgroundTask>
   private notifications: Map<string, BackgroundTask[]>
+  private pendingNotifications: Map<string, string[]>
   private pendingByParent: Map<string, Set<string>>  // Track pending tasks per parent for batching
   private client: OpencodeClient
   private directory: string
@@ -125,6 +126,7 @@ export class BackgroundManager {
   ) {
     this.tasks = new Map()
     this.notifications = new Map()
+    this.pendingNotifications = new Map()
     this.pendingByParent = new Map()
     this.client = ctx.client
     this.directory = ctx.directory
@@ -917,6 +919,32 @@ export class BackgroundManager {
     this.notifications.delete(sessionID)
   }
 
+  queuePendingNotification(sessionID: string | undefined, notification: string): void {
+    if (!sessionID) return
+    const existingNotifications = this.pendingNotifications.get(sessionID) ?? []
+    existingNotifications.push(notification)
+    this.pendingNotifications.set(sessionID, existingNotifications)
+  }
+
+  injectPendingNotificationsIntoChatMessage(output: { parts: Array<{ type: string; text?: string; [key: string]: unknown }> }, sessionID: string): void {
+    const pendingNotifications = this.pendingNotifications.get(sessionID)
+    if (!pendingNotifications || pendingNotifications.length === 0) {
+      return
+    }
+
+    this.pendingNotifications.delete(sessionID)
+    const notificationContent = pendingNotifications.join("\n\n")
+    const firstTextPartIndex = output.parts.findIndex((part) => part.type === "text")
+
+    if (firstTextPartIndex === -1) {
+      output.parts.unshift(createInternalAgentTextPart(notificationContent))
+      return
+    }
+
+    const originalText = output.parts[firstTextPartIndex].text ?? ""
+    output.parts[firstTextPartIndex].text = `${notificationContent}\n\n---\n\n${originalText}`
+  }
+
   /**
    * Validates that a session has actual assistant/tool output before marking complete.
    * Prevents premature completion when session.idle fires before agent responds.
@@ -1340,6 +1368,7 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
               taskId: task.id,
               parentSessionID: task.parentSessionID,
             })
+            this.queuePendingNotification(task.parentSessionID, notification)
           } else {
             log("[background-agent] Failed to send notification:", error)
           }
@@ -1568,6 +1597,7 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
     this.concurrencyManager.clear()
     this.tasks.clear()
     this.notifications.clear()
+    this.pendingNotifications.clear()
     this.pendingByParent.clear()
     this.notificationQueueByParent.clear()
     this.queuesByKey.clear()

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

@@ -269,6 +269,71 @@ describe("boulder-state", () => {
       expect(progress.isComplete).toBe(false)
     })
 
+    test("should count space-indented unchecked checkbox", () => {
+      // given - plan file with a two-space indented checkbox
+      const planPath = join(TEST_DIR, "space-indented-plan.md")
+      writeFileSync(planPath, `# Plan
+  - [ ] indented task
+`)
+
+      // when
+      const progress = getPlanProgress(planPath)
+
+      // then
+      expect(progress.total).toBe(1)
+      expect(progress.completed).toBe(0)
+      expect(progress.isComplete).toBe(false)
+    })
+
+    test("should count tab-indented unchecked checkbox", () => {
+      // given - plan file with a tab-indented checkbox
+      const planPath = join(TEST_DIR, "tab-indented-plan.md")
+      writeFileSync(planPath, `# Plan
+	- [ ] tab-indented task
+`)
+
+      // when
+      const progress = getPlanProgress(planPath)
+
+      // then
+      expect(progress.total).toBe(1)
+      expect(progress.completed).toBe(0)
+      expect(progress.isComplete).toBe(false)
+    })
+
+    test("should count mixed top-level checked and indented unchecked checkboxes", () => {
+      // given - plan file with checked top-level and unchecked indented task
+      const planPath = join(TEST_DIR, "mixed-indented-plan.md")
+      writeFileSync(planPath, `# Plan
+- [x] top-level completed task
+  - [ ] nested unchecked task
+`)
+
+      // when
+      const progress = getPlanProgress(planPath)
+
+      // then
+      expect(progress.total).toBe(2)
+      expect(progress.completed).toBe(1)
+      expect(progress.isComplete).toBe(false)
+    })
+
+    test("should count space-indented completed checkbox", () => {
+      // given - plan file with a two-space indented completed checkbox
+      const planPath = join(TEST_DIR, "indented-completed-plan.md")
+      writeFileSync(planPath, `# Plan
+  - [x] indented completed task
+`)
+
+      // when
+      const progress = getPlanProgress(planPath)
+
+      // then
+      expect(progress.total).toBe(1)
+      expect(progress.completed).toBe(1)
+      expect(progress.isComplete).toBe(true)
+    })
+
     test("should return isComplete true when all checked", () => {
       // given - all tasks completed
       const planPath = join(TEST_DIR, "complete-plan.md")

src/features/boulder-state/storage.ts

@@ -121,8 +121,8 @@ export function getPlanProgress(planPath: string): PlanProgress {
     const content = readFileSync(planPath, "utf-8")
     
     // Match markdown checkboxes: - [ ] or - [x] or - [X]
-    const uncheckedMatches = content.match(/^[-*]\s*\[\s*\]/gm) || []
+    const uncheckedMatches = content.match(/^\s*[-*]\s*\[\s*\]/gm) || []
-    const checkedMatches = content.match(/^[-*]\s*\[[xX]\]/gm) || []
+    const checkedMatches = content.match(/^\s*[-*]\s*\[[xX]\]/gm) || []
 
     const total = uncheckedMatches.length + checkedMatches.length
     const completed = checkedMatches.length
@@ -150,7 +150,8 @@ export function getPlanName(planPath: string): string {
 export function createBoulderState(
   planPath: string,
   sessionId: string,
-  agent?: string
+  agent?: string,
+  worktreePath?: string,
 ): BoulderState {
   return {
     active_plan: planPath,
@@ -158,5 +159,6 @@ export function createBoulderState(
     session_ids: [sessionId],
     plan_name: getPlanName(planPath),
     ...(agent !== undefined ? { agent } : {}),
+    ...(worktreePath !== undefined ? { worktree_path: worktreePath } : {}),
   }
 }

src/features/boulder-state/types.ts

@@ -16,6 +16,8 @@ export interface BoulderState {
   plan_name: string
   /** Agent type to use when resuming (e.g., 'atlas') */
   agent?: string
+  /** Absolute path to the git worktree root where work happens */
+  worktree_path?: string
 }
 
 export interface PlanProgress {

src/features/builtin-commands/templates/start-work.ts

@@ -1,5 +1,14 @@
 export const START_WORK_TEMPLATE = `You are starting a Sisyphus work session.
 
+## ARGUMENTS
+
+- \`/start-work [plan-name] [--worktree <path>]\`
+  - \`plan-name\` (optional): name or partial match of the plan to start
+  - \`--worktree <path>\` (optional): absolute path to an existing git worktree to work in
+    - If specified and valid: hook pre-sets worktree_path in boulder.json
+    - If specified but invalid: you must run \`git worktree add <path> <branch>\` first
+    - If omitted: you MUST choose or create a worktree (see Worktree Setup below)
+
 ## WHAT TO DO
 
 1. **Find available plans**: Search for Prometheus-generated plan files at \`.sisyphus/plans/\`
@@ -15,17 +24,24 @@ export const START_WORK_TEMPLATE = `You are starting a Sisyphus work session.
      - If ONE plan: auto-select it
      - If MULTIPLE plans: show list with timestamps, ask user to select
 
-4. **Create/Update boulder.json**:
+4. **Worktree Setup** (when \`worktree_path\` not already set in boulder.json):
+   1. \`git worktree list --porcelain\` — see available worktrees
+   2. Create: \`git worktree add <absolute-path> <branch-or-HEAD>\`
+   3. Update boulder.json to add \`"worktree_path": "<absolute-path>"\`
+   4. All work happens inside that worktree directory
+
+5. **Create/Update boulder.json**:
    \`\`\`json
    {
      "active_plan": "/absolute/path/to/plan.md",
      "started_at": "ISO_TIMESTAMP",
      "session_ids": ["session_id_1", "session_id_2"],
-     "plan_name": "plan-name"
+     "plan_name": "plan-name",
+     "worktree_path": "/absolute/path/to/git/worktree"
    }
    \`\`\`
 
-5. **Read the plan file** and start executing tasks according to atlas workflow
+6. **Read the plan file** and start executing tasks according to atlas workflow
 
 ## OUTPUT FORMAT
 
@@ -49,6 +65,7 @@ Resuming Work Session
 Active Plan: {plan-name}
 Progress: {completed}/{total} tasks
 Sessions: {count} (appending current session)
+Worktree: {worktree_path}
 
 Reading plan and continuing from last incomplete task...
 \`\`\`
@@ -60,6 +77,7 @@ Starting Work Session
 Plan: {plan-name}
 Session ID: {session_id}
 Started: {timestamp}
+Worktree: {worktree_path}
 
 Reading plan and beginning execution...
 \`\`\`
@@ -68,5 +86,6 @@ Reading plan and beginning execution...
 
 - The session_id is injected by the hook - use it directly
 - Always update boulder.json BEFORE starting work
+- Always set worktree_path in boulder.json before executing any tasks
 - Read the FULL plan file before delegating any tasks
 - Follow atlas delegation protocols (7-section format)`

src/features/claude-tasks/AGENTS.md

@@ -1,6 +1,6 @@
 # src/features/claude-tasks/ — Task Schema + Storage
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/features/mcp-oauth/AGENTS.md

@@ -1,6 +1,6 @@
 # src/features/mcp-oauth/ — OAuth 2.0 + PKCE + DCR for MCP Servers
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/features/opencode-skill-loader/AGENTS.md

@@ -1,6 +1,6 @@
 # src/features/opencode-skill-loader/ — 4-Scope Skill Discovery
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/features/tmux-subagent/AGENTS.md

@@ -1,6 +1,6 @@
 # src/features/tmux-subagent/ — Tmux Pane Management
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/hooks/AGENTS.md

@@ -1,14 +1,14 @@
-# src/hooks/ — 44 Lifecycle Hooks
+# src/hooks/ — 46 Lifecycle Hooks
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 
-44 hooks across 39 directories + 6 standalone files. Three-tier composition: Core(35) + Continuation(7) + Skill(2). All hooks follow `createXXXHook(deps) → HookFunction` factory pattern.
+46 hooks across 39 directories + 6 standalone files. Three-tier composition: Core(37) + Continuation(7) + Skill(2). All hooks follow `createXXXHook(deps) → HookFunction` factory pattern.
 
 ## HOOK TIERS
 
-### Tier 1: Session Hooks (22) — `create-session-hooks.ts`
+### Tier 1: Session Hooks (23) — `create-session-hooks.ts`
 ## STRUCTURE
 ```
 hooks/
@@ -70,11 +70,12 @@ hooks/
 | questionLabelTruncator | tool.execute.before | Truncate long question labels |
 | taskResumeInfo | chat.message | Inject task context on resume |
 | anthropicEffort | chat.params | Adjust reasoning effort level |
-| jsonErrorRecovery | tool.execute.after | Detect JSON parse errors, inject correction reminder |
+| modelFallback | chat.params | Provider-level model fallback on errors |
-| sisyphusGptHephaestusReminder | chat.message | Toast warning when Sisyphus uses GPT model |
+| noSisyphusGpt | chat.message | Block Sisyphus from using GPT models (toast warning) |
-| taskReminder | tool.execute.after | Remind about task tools after 10 turns without usage |
+| noHephaestusNonGpt | chat.message | Block Hephaestus from using non-GPT models |
+| runtimeFallback | event | Auto-switch models on API provider errors |
 
-### Tier 2: Tool Guard Hooks (9) — `create-tool-guard-hooks.ts`
+### Tier 2: Tool Guard Hooks (10) — `create-tool-guard-hooks.ts`
 
 | Hook | Event | Purpose |
 |------|-------|---------|
@@ -87,6 +88,7 @@ hooks/
 | tasksTodowriteDisabler | tool.execute.before | Disable TodoWrite when task system active |
 | writeExistingFileGuard | tool.execute.before | Require Read before Write on existing files |
 | hashlineReadEnhancer | tool.execute.after | Enhance Read output with line hashes |
+| jsonErrorRecovery | tool.execute.after | Detect JSON parse errors, inject correction reminder |
 
 ### Tier 3: Transform Hooks (4) — `create-transform-hooks.ts`
 

src/hooks/anthropic-context-window-limit-recovery/AGENTS.md

@@ -1,6 +1,6 @@
 # src/hooks/anthropic-context-window-limit-recovery/ — Multi-Strategy Context Recovery
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/hooks/anthropic-context-window-limit-recovery/state.ts

@@ -6,7 +6,7 @@ export function getOrCreateRetryState(
 ): RetryState {
   let state = autoCompactState.retryStateBySession.get(sessionID)
   if (!state) {
-    state = { attempt: 0, lastAttemptTime: 0 }
+    state = { attempt: 0, lastAttemptTime: 0, firstAttemptTime: 0 }
     autoCompactState.retryStateBySession.set(sessionID, state)
   }
   return state

src/hooks/anthropic-context-window-limit-recovery/summarize-retry-strategy.test.ts

@@ -0,0 +1,122 @@
+import { afterEach, beforeEach, describe, expect, mock, test } from "bun:test"
+import { runSummarizeRetryStrategy } from "./summarize-retry-strategy"
+import type { AutoCompactState, ParsedTokenLimitError, RetryState } from "./types"
+import type { OhMyOpenCodeConfig } from "../../config"
+
+type TimeoutCall = {
+  delay: number
+}
+
+function createAutoCompactState(): AutoCompactState {
+  return {
+    pendingCompact: new Set<string>(),
+    errorDataBySession: new Map<string, ParsedTokenLimitError>(),
+    retryStateBySession: new Map<string, RetryState>(),
+    truncateStateBySession: new Map(),
+    emptyContentAttemptBySession: new Map(),
+    compactionInProgress: new Set<string>(),
+  }
+}
+
+describe("runSummarizeRetryStrategy", () => {
+  const sessionID = "ses_retry_timeout"
+  const directory = "/tmp"
+  let autoCompactState: AutoCompactState
+
+  const summarizeMock = mock(() => Promise.resolve())
+  const showToastMock = mock(() => Promise.resolve())
+  const client = {
+    session: {
+      summarize: summarizeMock,
+      messages: mock(() => Promise.resolve({ data: [] })),
+      promptAsync: mock(() => Promise.resolve()),
+      revert: mock(() => Promise.resolve()),
+    },
+    tui: {
+      showToast: showToastMock,
+    },
+  }
+
+  beforeEach(() => {
+    autoCompactState = createAutoCompactState()
+    summarizeMock.mockReset()
+    showToastMock.mockReset()
+    summarizeMock.mockResolvedValue(undefined)
+    showToastMock.mockResolvedValue(undefined)
+  })
+
+  afterEach(() => {
+    globalThis.setTimeout = originalSetTimeout
+  })
+
+  const originalSetTimeout = globalThis.setTimeout
+
+  test("stops retries when total summarize timeout is exceeded", async () => {
+    //#given
+    autoCompactState.pendingCompact.add(sessionID)
+    autoCompactState.errorDataBySession.set(sessionID, {
+      currentTokens: 250000,
+      maxTokens: 200000,
+      errorType: "token_limit_exceeded",
+    })
+    autoCompactState.retryStateBySession.set(sessionID, {
+      attempt: 1,
+      lastAttemptTime: Date.now(),
+      firstAttemptTime: Date.now() - 130000,
+    })
+
+    //#when
+    await runSummarizeRetryStrategy({
+      sessionID,
+      msg: { providerID: "anthropic", modelID: "claude-sonnet-4-6" },
+      autoCompactState,
+      client: client as never,
+      directory,
+      pluginConfig: {} as OhMyOpenCodeConfig,
+    })
+
+    //#then
+    expect(summarizeMock).not.toHaveBeenCalled()
+    expect(autoCompactState.pendingCompact.has(sessionID)).toBe(false)
+    expect(autoCompactState.errorDataBySession.has(sessionID)).toBe(false)
+    expect(autoCompactState.retryStateBySession.has(sessionID)).toBe(false)
+    expect(showToastMock).toHaveBeenCalledWith(
+      expect.objectContaining({
+        body: expect.objectContaining({
+          title: "Auto Compact Timed Out",
+        }),
+      }),
+    )
+  })
+
+  test("caps retry delay by remaining total timeout window", async () => {
+    //#given
+    const timeoutCalls: TimeoutCall[] = []
+    globalThis.setTimeout = ((_: (...args: unknown[]) => void, delay?: number) => {
+      timeoutCalls.push({ delay: delay ?? 0 })
+      return 1 as unknown as ReturnType<typeof setTimeout>
+    }) as typeof setTimeout
+
+    autoCompactState.retryStateBySession.set(sessionID, {
+      attempt: 1,
+      lastAttemptTime: Date.now(),
+      firstAttemptTime: Date.now() - 119700,
+    })
+    summarizeMock.mockRejectedValueOnce(new Error("rate limited"))
+
+    //#when
+    await runSummarizeRetryStrategy({
+      sessionID,
+      msg: { providerID: "anthropic", modelID: "claude-sonnet-4-6" },
+      autoCompactState,
+      client: client as never,
+      directory,
+      pluginConfig: {} as OhMyOpenCodeConfig,
+    })
+
+    //#then
+    expect(timeoutCalls.length).toBe(1)
+    expect(timeoutCalls[0]!.delay).toBeGreaterThan(0)
+    expect(timeoutCalls[0]!.delay).toBeLessThanOrEqual(500)
+  })
+})

src/hooks/anthropic-context-window-limit-recovery/summarize-retry-strategy.ts

@@ -7,6 +7,8 @@ import { sanitizeEmptyMessagesBeforeSummarize } from "./message-builder"
 import { fixEmptyMessages } from "./empty-content-recovery"
 
 import { resolveCompactionModel } from "../shared/compaction-model-resolver"
+
+const SUMMARIZE_RETRY_TOTAL_TIMEOUT_MS = 120_000
 export async function runSummarizeRetryStrategy(params: {
   sessionID: string
   msg: Record<string, unknown>
@@ -18,6 +20,27 @@ export async function runSummarizeRetryStrategy(params: {
   messageIndex?: number
 }): Promise<void> {
   const retryState = getOrCreateRetryState(params.autoCompactState, params.sessionID)
+  const now = Date.now()
+
+  if (retryState.firstAttemptTime === 0) {
+    retryState.firstAttemptTime = now
+  }
+
+  const elapsedTimeMs = now - retryState.firstAttemptTime
+  if (elapsedTimeMs >= SUMMARIZE_RETRY_TOTAL_TIMEOUT_MS) {
+    clearSessionState(params.autoCompactState, params.sessionID)
+    await params.client.tui
+      .showToast({
+        body: {
+          title: "Auto Compact Timed Out",
+          message: "Compaction retries exceeded the timeout window. Please start a new session.",
+          variant: "error",
+          duration: 5000,
+        },
+      })
+      .catch(() => {})
+    return
+  }
 
   if (params.errorType?.includes("non-empty content")) {
     const attempt = getEmptyContentAttempt(params.autoCompactState, params.sessionID)
@@ -52,6 +75,7 @@ export async function runSummarizeRetryStrategy(params: {
 
   if (Date.now() - retryState.lastAttemptTime > 300000) {
     retryState.attempt = 0
+    retryState.firstAttemptTime = Date.now()
     params.autoCompactState.truncateStateBySession.delete(params.sessionID)
   }
 
@@ -92,10 +116,26 @@ export async function runSummarizeRetryStrategy(params: {
         })
         return
       } catch {
+        const remainingTimeMs = SUMMARIZE_RETRY_TOTAL_TIMEOUT_MS - (Date.now() - retryState.firstAttemptTime)
+        if (remainingTimeMs <= 0) {
+          clearSessionState(params.autoCompactState, params.sessionID)
+          await params.client.tui
+            .showToast({
+              body: {
+                title: "Auto Compact Timed Out",
+                message: "Compaction retries exceeded the timeout window. Please start a new session.",
+                variant: "error",
+                duration: 5000,
+              },
+            })
+            .catch(() => {})
+          return
+        }
+
         const delay =
           RETRY_CONFIG.initialDelayMs *
           Math.pow(RETRY_CONFIG.backoffFactor, retryState.attempt - 1)
-        const cappedDelay = Math.min(delay, RETRY_CONFIG.maxDelayMs)
+        const cappedDelay = Math.min(delay, RETRY_CONFIG.maxDelayMs, remainingTimeMs)
 
         setTimeout(() => {
           void runSummarizeRetryStrategy(params)

src/hooks/anthropic-context-window-limit-recovery/types.ts

@@ -11,6 +11,7 @@ export interface ParsedTokenLimitError {
 export interface RetryState {
   attempt: number
   lastAttemptTime: number
+  firstAttemptTime: number
 }
 
 export interface TruncateState {

src/hooks/atlas/AGENTS.md

@@ -1,6 +1,6 @@
 # src/hooks/atlas/ — Master Boulder Orchestrator
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/hooks/atlas/boulder-continuation-injector.ts

@@ -14,6 +14,7 @@ export async function injectBoulderContinuation(input: {
   remaining: number
   total: number
   agent?: string
+  worktreePath?: string
   backgroundManager?: BackgroundManager
   sessionState: SessionState
 }): Promise<void> {
@@ -24,6 +25,7 @@ export async function injectBoulderContinuation(input: {
     remaining,
     total,
     agent,
+    worktreePath,
     backgroundManager,
     sessionState,
   } = input
@@ -37,9 +39,11 @@ export async function injectBoulderContinuation(input: {
     return
   }
 
+  const worktreeContext = worktreePath ? `\n\n[Worktree: ${worktreePath}]` : ""
   const prompt =
     BOULDER_CONTINUATION_PROMPT.replace(/{PLAN_NAME}/g, planName) +
-    `\n\n[Status: ${total - remaining}/${total} completed, ${remaining} remaining]`
+    `\n\n[Status: ${total - remaining}/${total} completed, ${remaining} remaining]` +
+    worktreeContext
 
   try {
     log(`[${HOOK_NAME}] Injecting boulder continuation`, { sessionID, planName, remaining })
@@ -62,6 +66,7 @@ export async function injectBoulderContinuation(input: {
     log(`[${HOOK_NAME}] Boulder continuation injected`, { sessionID })
   } catch (err) {
     sessionState.promptFailureCount += 1
+    sessionState.lastFailureAt = Date.now()
     log(`[${HOOK_NAME}] Boulder continuation failed`, {
       sessionID,
       error: String(err),

src/hooks/atlas/event-handler.ts

@@ -10,6 +10,7 @@ import { getLastAgentFromSession } from "./session-last-agent"
 import type { AtlasHookOptions, SessionState } from "./types"
 
 const CONTINUATION_COOLDOWN_MS = 5000
+const FAILURE_BACKOFF_MS = 5 * 60 * 1000
 
 export function createAtlasEventHandler(input: {
   ctx: PluginInput
@@ -53,6 +54,7 @@ export function createAtlasEventHandler(input: {
       }
 
       const state = getState(sessionID)
+      const now = Date.now()
 
       if (state.lastEventWasAbortError) {
         state.lastEventWasAbortError = false
@@ -61,11 +63,18 @@ export function createAtlasEventHandler(input: {
       }
 
       if (state.promptFailureCount >= 2) {
-        log(`[${HOOK_NAME}] Skipped: continuation disabled after repeated prompt failures`, {
+        const timeSinceLastFailure = state.lastFailureAt !== undefined ? now - state.lastFailureAt : Number.POSITIVE_INFINITY
-          sessionID,
+        if (timeSinceLastFailure < FAILURE_BACKOFF_MS) {
-          promptFailureCount: state.promptFailureCount,
+          log(`[${HOOK_NAME}] Skipped: continuation in backoff after repeated failures`, {
-        })
+            sessionID,
-        return
+            promptFailureCount: state.promptFailureCount,
+            backoffRemaining: FAILURE_BACKOFF_MS - timeSinceLastFailure,
+          })
+          return
+        }
+
+        state.promptFailureCount = 0
+        state.lastFailureAt = undefined
       }
 
       const backgroundManager = options?.backgroundManager
@@ -92,17 +101,15 @@ export function createAtlasEventHandler(input: {
       const lastAgentKey = getAgentConfigKey(lastAgent ?? "")
       const requiredAgent = getAgentConfigKey(boulderState.agent ?? "atlas")
       const lastAgentMatchesRequired = lastAgentKey === requiredAgent
-      const boulderAgentWasNotExplicitlySet = boulderState.agent === undefined
       const boulderAgentDefaultsToAtlas = requiredAgent === "atlas"
       const lastAgentIsSisyphus = lastAgentKey === "sisyphus"
-      const allowSisyphusWhenDefaultAtlas = boulderAgentWasNotExplicitlySet && boulderAgentDefaultsToAtlas && lastAgentIsSisyphus
+      const allowSisyphusForAtlasBoulder = boulderAgentDefaultsToAtlas && lastAgentIsSisyphus
-      const agentMatches = lastAgentMatchesRequired || allowSisyphusWhenDefaultAtlas
+      const agentMatches = lastAgentMatchesRequired || allowSisyphusForAtlasBoulder
       if (!agentMatches) {
         log(`[${HOOK_NAME}] Skipped: last agent does not match boulder agent`, {
           sessionID,
           lastAgent: lastAgent ?? "unknown",
           requiredAgent,
-          boulderAgentExplicitlySet: boulderState.agent !== undefined,
         })
         return
       }
@@ -113,7 +120,6 @@ export function createAtlasEventHandler(input: {
         return
       }
 
-      const now = Date.now()
       if (state.lastContinuationInjectedAt && now - state.lastContinuationInjectedAt < CONTINUATION_COOLDOWN_MS) {
         log(`[${HOOK_NAME}] Skipped: continuation cooldown active`, {
           sessionID,
@@ -132,6 +138,7 @@ export function createAtlasEventHandler(input: {
           remaining,
           total: progress.total,
           agent: boulderState.agent,
+          worktreePath: boulderState.worktree_path,
           backgroundManager,
           sessionState: state,
         })

src/hooks/atlas/index.test.ts

@@ -933,8 +933,8 @@ describe("atlas hook", () => {
       expect(callArgs.body.parts[0].text).toContain("2 remaining")
     })
 
-     test("should not inject when last agent does not match boulder agent", async () => {
+     test("should inject when last agent is sisyphus and boulder targets atlas explicitly", async () => {
-       // given - boulder state with incomplete plan, but last agent does NOT match
+       // given - boulder explicitly set to atlas, but last agent is sisyphus (initial state after /start-work)
        const planPath = join(TEST_DIR, "test-plan.md")
        writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [ ] Task 2")
 
@@ -947,7 +947,7 @@ describe("atlas hook", () => {
        }
        writeBoulderState(TEST_DIR, state)
 
-       // given - last agent is NOT the boulder agent
+       // given - last agent is sisyphus (typical state right after /start-work)
        cleanupMessageStorage(MAIN_SESSION_ID)
        setupMessageStorage(MAIN_SESSION_ID, "sisyphus")
 
@@ -962,7 +962,39 @@ describe("atlas hook", () => {
          },
        })
 
-       // then - should NOT call prompt because agent does not match
+       // then - should call prompt because sisyphus is always allowed for atlas boulders
+       expect(mockInput._promptMock).toHaveBeenCalled()
+     })
+
+     test("should not inject when last agent is non-sisyphus and does not match boulder agent", async () => {
+       // given - boulder explicitly set to atlas, last agent is hephaestus (unrelated agent)
+       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: "atlas",
+       }
+       writeBoulderState(TEST_DIR, state)
+
+       cleanupMessageStorage(MAIN_SESSION_ID)
+       setupMessageStorage(MAIN_SESSION_ID, "hephaestus")
+
+       const mockInput = createMockPluginInput()
+       const hook = createAtlasHook(mockInput)
+
+       // when
+       await hook.handler({
+         event: {
+           type: "session.idle",
+           properties: { sessionID: MAIN_SESSION_ID },
+         },
+       })
+
+       // then - should NOT call prompt because hephaestus does not match atlas or sisyphus
        expect(mockInput._promptMock).not.toHaveBeenCalled()
      })
 
@@ -1122,6 +1154,144 @@ describe("atlas hook", () => {
       }
     })
 
+    test("should keep skipping continuation during 5-minute backoff after 2 consecutive failures", 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 - third idle occurs inside 5-minute backoff window
+        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 += 60000
+
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: MAIN_SESSION_ID } } })
+        await flushMicrotasks()
+
+        //#then - third attempt should still be skipped
+        expect(promptMock).toHaveBeenCalledTimes(2)
+      } finally {
+        Date.now = originalDateNow
+      }
+    })
+
+    test("should retry continuation after 5-minute backoff expires following 2 consecutive failures", 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 - third idle occurs after 5+ minutes
+        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 += 300000
+
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: MAIN_SESSION_ID } } })
+        await flushMicrotasks()
+
+        //#then - third attempt should run after backoff expiration
+        expect(promptMock).toHaveBeenCalledTimes(3)
+      } finally {
+        Date.now = originalDateNow
+      }
+    })
+
+    test("should reset prompt failure counter after successful retry beyond backoff window", async () => {
+      //#given - boulder state with incomplete plan and success on first retry after backoff
+      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<void> => Promise.reject(new Error("Bad Request")))
+      promptMock.mockImplementationOnce(() => Promise.reject(new Error("Bad Request")))
+      promptMock.mockImplementationOnce(() => Promise.reject(new Error("Bad Request")))
+      promptMock.mockImplementationOnce(() => Promise.resolve(undefined))
+      const mockInput = createMockPluginInput({ promptMock })
+      const hook = createAtlasHook(mockInput)
+
+      const originalDateNow = Date.now
+      let now = 0
+      Date.now = () => now
+
+      try {
+        //#when - fail twice, recover after backoff with success, then fail twice again
+        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 += 300000
+
+        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()
+        now += 6000
+
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: MAIN_SESSION_ID } } })
+        await flushMicrotasks()
+
+        //#then - success retry resets counter, so two additional failures are allowed before skip
+        expect(promptMock).toHaveBeenCalledTimes(5)
+      } 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")

src/hooks/atlas/types.ts

@@ -26,4 +26,5 @@ export interface SessionState {
   lastEventWasAbortError?: boolean
   lastContinuationInjectedAt?: number
   promptFailureCount: number
+  lastFailureAt?: number
 }

src/hooks/background-notification/hook.ts

@@ -9,6 +9,14 @@ interface EventInput {
   event: Event
 }
 
+interface ChatMessageInput {
+  sessionID: string
+}
+
+interface ChatMessageOutput {
+  parts: Array<{ type: string; text?: string; [key: string]: unknown }>
+}
+
 /**
  * Background notification hook - handles event routing to BackgroundManager.
  *
@@ -20,7 +28,15 @@ export function createBackgroundNotificationHook(manager: BackgroundManager) {
     manager.handleEvent(event)
   }
 
+  const chatMessageHandler = async (
+    input: ChatMessageInput,
+    output: ChatMessageOutput,
+  ): Promise<void> => {
+    manager.injectPendingNotificationsIntoChatMessage(output, input.sessionID)
+  }
+
   return {
+    "chat.message": chatMessageHandler,
     event: eventHandler,
   }
 }

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

@@ -1,6 +1,6 @@
 # src/hooks/claude-code-hooks/ — Claude Code Compatibility
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/hooks/keyword-detector/AGENTS.md

@@ -1,6 +1,6 @@
 # src/hooks/keyword-detector/ — Mode Keyword Injection
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/hooks/no-hephaestus-non-gpt/hook.ts

@@ -12,12 +12,16 @@ const TOAST_MESSAGE = [
 ].join("\n")
 const SISYPHUS_DISPLAY = getAgentDisplayName("sisyphus")
 
-function showToast(ctx: PluginInput, sessionID: string): void {
+type NoHephaestusNonGptHookOptions = {
+  allowNonGptModel?: boolean
+}
+
+function showToast(ctx: PluginInput, sessionID: string, variant: "error" | "warning"): void {
   ctx.client.tui.showToast({
     body: {
       title: TOAST_TITLE,
       message: TOAST_MESSAGE,
-      variant: "error",
+      variant,
       duration: 10000,
     },
   }).catch((error) => {
@@ -28,7 +32,10 @@ function showToast(ctx: PluginInput, sessionID: string): void {
   })
 }
 
-export function createNoHephaestusNonGptHook(ctx: PluginInput) {
+export function createNoHephaestusNonGptHook(
+  ctx: PluginInput,
+  options?: NoHephaestusNonGptHookOptions,
+) {
   return {
     "chat.message": async (input: {
       sessionID: string
@@ -40,9 +47,13 @@ export function createNoHephaestusNonGptHook(ctx: PluginInput) {
       const rawAgent = input.agent ?? getSessionAgent(input.sessionID) ?? ""
       const agentKey = getAgentConfigKey(rawAgent)
       const modelID = input.model?.modelID
+      const allowNonGptModel = options?.allowNonGptModel === true
 
       if (agentKey === "hephaestus" && modelID && !isGptModel(modelID)) {
-        showToast(ctx, input.sessionID)
+        showToast(ctx, input.sessionID, allowNonGptModel ? "warning" : "error")
+        if (allowNonGptModel) {
+          return
+        }
         input.agent = SISYPHUS_DISPLAY
         if (output?.message) {
           output.message.agent = SISYPHUS_DISPLAY

src/hooks/no-hephaestus-non-gpt/index.test.ts

@@ -1,3 +1,5 @@
+/// <reference types="bun-types" />
+
 import { describe, expect, spyOn, test } from "bun:test"
 import { _resetForTesting, updateSessionAgent } from "../../features/claude-code-session-state"
 import { getAgentDisplayName } from "../../shared/agent-display-names"
@@ -8,7 +10,7 @@ const SISYPHUS_DISPLAY = getAgentDisplayName("sisyphus")
 
 function createOutput() {
   return {
-    message: {},
+    message: {} as { agent?: string; [key: string]: unknown },
     parts: [],
   }
 }
@@ -16,7 +18,7 @@ function createOutput() {
 describe("no-hephaestus-non-gpt hook", () => {
   test("shows toast on every chat.message when hephaestus uses non-gpt model", async () => {
     // given - hephaestus with claude model
-    const showToast = spyOn({ fn: async () => ({}) }, "fn")
+    const showToast = spyOn({ fn: async (_input: unknown) => ({}) }, "fn")
     const hook = createNoHephaestusNonGptHook({
       client: { tui: { showToast } },
     } as any)
@@ -49,9 +51,38 @@ describe("no-hephaestus-non-gpt hook", () => {
     })
   })
 
+  test("shows warning and does not switch agent when allow_non_gpt_model is enabled", async () => {
+    // given - hephaestus with claude model and opt-out enabled
+    const showToast = spyOn({ fn: async (_input: unknown) => ({}) }, "fn")
+    const hook = createNoHephaestusNonGptHook({
+      client: { tui: { showToast } },
+    } as any, {
+      allowNonGptModel: true,
+    })
+
+    const output = createOutput()
+
+    // when - chat.message runs
+    await hook["chat.message"]?.({
+      sessionID: "ses_opt_out",
+      agent: HEPHAESTUS_DISPLAY,
+      model: { providerID: "anthropic", modelID: "claude-opus-4-6" },
+    }, output)
+
+    // then - warning toast is shown but agent is not switched
+    expect(showToast).toHaveBeenCalledTimes(1)
+    expect(output.message.agent).toBeUndefined()
+    expect(showToast.mock.calls[0]?.[0]).toMatchObject({
+      body: {
+        title: "NEVER Use Hephaestus with Non-GPT",
+        variant: "warning",
+      },
+    })
+  })
+
   test("does not show toast when hephaestus uses gpt model", async () => {
     // given - hephaestus with gpt model
-    const showToast = spyOn({ fn: async () => ({}) }, "fn")
+    const showToast = spyOn({ fn: async (_input: unknown) => ({}) }, "fn")
     const hook = createNoHephaestusNonGptHook({
       client: { tui: { showToast } },
     } as any)
@@ -72,7 +103,7 @@ describe("no-hephaestus-non-gpt hook", () => {
 
   test("does not show toast for non-hephaestus agent", async () => {
     // given - sisyphus with claude model (non-gpt)
-    const showToast = spyOn({ fn: async () => ({}) }, "fn")
+    const showToast = spyOn({ fn: async (_input: unknown) => ({}) }, "fn")
     const hook = createNoHephaestusNonGptHook({
       client: { tui: { showToast } },
     } as any)
@@ -95,7 +126,7 @@ describe("no-hephaestus-non-gpt hook", () => {
     // given - session agent saved as hephaestus
     _resetForTesting()
     updateSessionAgent("ses_4", HEPHAESTUS_DISPLAY)
-    const showToast = spyOn({ fn: async () => ({}) }, "fn")
+    const showToast = spyOn({ fn: async (_input: unknown) => ({}) }, "fn")
     const hook = createNoHephaestusNonGptHook({
       client: { tui: { showToast } },
     } as any)

src/hooks/preemptive-compaction.test.ts

@@ -45,6 +45,23 @@ function createMockCtx() {
   }
 }
 
+function setupImmediateTimeouts(): () => void {
+  const originalSetTimeout = globalThis.setTimeout
+  const originalClearTimeout = globalThis.clearTimeout
+
+  globalThis.setTimeout = ((callback: (...args: unknown[]) => void, _delay?: number, ...args: unknown[]) => {
+    callback(...args)
+    return 1 as unknown as ReturnType<typeof setTimeout>
+  }) as typeof setTimeout
+
+  globalThis.clearTimeout = (() => {}) as typeof clearTimeout
+
+  return () => {
+    globalThis.setTimeout = originalSetTimeout
+    globalThis.clearTimeout = originalClearTimeout
+  }
+}
+
 describe("preemptive-compaction", () => {
   let ctx: ReturnType<typeof createMockCtx>
 
@@ -63,7 +80,7 @@ describe("preemptive-compaction", () => {
   // #when tool.execute.after is called
   // #then session.messages() should NOT be called
   it("should use cached token info instead of fetching session.messages()", async () => {
-    const hook = createPreemptiveCompactionHook(ctx as never)
+    const hook = createPreemptiveCompactionHook(ctx as never, {} as never)
     const sessionID = "ses_test1"
 
     // Simulate message.updated with token info below threshold
@@ -101,7 +118,7 @@ describe("preemptive-compaction", () => {
   // #when tool.execute.after is called
   // #then should skip without fetching
   it("should skip gracefully when no cached token info exists", async () => {
-    const hook = createPreemptiveCompactionHook(ctx as never)
+    const hook = createPreemptiveCompactionHook(ctx as never, {} as never)
 
     const output = { title: "", output: "test", metadata: null }
     await hook["tool.execute.after"](
@@ -116,7 +133,7 @@ describe("preemptive-compaction", () => {
   // #when tool.execute.after runs
   // #then should trigger summarize
   it("should trigger compaction when usage exceeds threshold", async () => {
-    const hook = createPreemptiveCompactionHook(ctx as never)
+    const hook = createPreemptiveCompactionHook(ctx as never, {} as never)
     const sessionID = "ses_high"
 
     // 170K input + 10K cache = 180K → 90% of 200K
@@ -153,7 +170,7 @@ describe("preemptive-compaction", () => {
 
   it("should trigger compaction for google-vertex-anthropic provider", async () => {
     //#given google-vertex-anthropic usage above threshold
-    const hook = createPreemptiveCompactionHook(ctx as never)
+    const hook = createPreemptiveCompactionHook(ctx as never, {} as never)
     const sessionID = "ses_vertex_anthropic_high"
 
     await hook.event({
@@ -191,7 +208,7 @@ describe("preemptive-compaction", () => {
   // #given session deleted
   // #then cache should be cleaned up
   it("should clean up cache on session.deleted", async () => {
-    const hook = createPreemptiveCompactionHook(ctx as never)
+    const hook = createPreemptiveCompactionHook(ctx as never, {} as never)
     const sessionID = "ses_del"
 
     await hook.event({
@@ -228,7 +245,7 @@ describe("preemptive-compaction", () => {
 
   it("should log summarize errors instead of swallowing them", async () => {
     //#given
-    const hook = createPreemptiveCompactionHook(ctx as never)
+    const hook = createPreemptiveCompactionHook(ctx as never, {} as never)
     const sessionID = "ses_log_error"
     const summarizeError = new Error("summarize failed")
     ctx.client.session.summarize.mockRejectedValueOnce(summarizeError)
@@ -343,4 +360,58 @@ describe("preemptive-compaction", () => {
     //#then
     expect(ctx.client.session.summarize).not.toHaveBeenCalled()
   })
+
+  it("should clear in-progress lock when summarize times out", async () => {
+    //#given
+    const restoreTimeouts = setupImmediateTimeouts()
+    const hook = createPreemptiveCompactionHook(ctx as never, {} as never)
+    const sessionID = "ses_timeout"
+
+    ctx.client.session.summarize
+      .mockImplementationOnce(() => new Promise(() => {}))
+      .mockResolvedValueOnce({})
+
+    try {
+      await hook.event({
+        event: {
+          type: "message.updated",
+          properties: {
+            info: {
+              role: "assistant",
+              sessionID,
+              providerID: "anthropic",
+              modelID: "claude-sonnet-4-6",
+              finish: true,
+              tokens: {
+                input: 170000,
+                output: 0,
+                reasoning: 0,
+                cache: { read: 10000, write: 0 },
+              },
+            },
+          },
+        },
+      })
+
+      //#when
+      await hook["tool.execute.after"](
+        { tool: "bash", sessionID, callID: "call_timeout_1" },
+        { title: "", output: "test", metadata: null },
+      )
+
+      await hook["tool.execute.after"](
+        { tool: "bash", sessionID, callID: "call_timeout_2" },
+        { title: "", output: "test", metadata: null },
+      )
+
+      //#then
+      expect(ctx.client.session.summarize).toHaveBeenCalledTimes(2)
+      expect(logMock).toHaveBeenCalledWith("[preemptive-compaction] Compaction failed", {
+        sessionID,
+        error: expect.stringContaining("Compaction summarize timed out"),
+      })
+    } finally {
+      restoreTimeouts()
+    }
+  })
 })

src/hooks/preemptive-compaction.ts

@@ -3,6 +3,7 @@ import type { OhMyOpenCodeConfig } from "../config"
 
 import { resolveCompactionModel } from "./shared/compaction-model-resolver"
 const DEFAULT_ACTUAL_LIMIT = 200_000
+const PREEMPTIVE_COMPACTION_TIMEOUT_MS = 120_000
 
 type ModelCacheStateLike = {
   anthropicContext1MEnabled: boolean
@@ -31,6 +32,26 @@ interface CachedCompactionState {
   tokens: TokenInfo
 }
 
+function withTimeout<TValue>(
+  promise: Promise<TValue>,
+  timeoutMs: number,
+  errorMessage: string,
+): Promise<TValue> {
+  let timeoutID: ReturnType<typeof setTimeout> | undefined
+
+  const timeoutPromise = new Promise<never>((_, reject) => {
+    timeoutID = setTimeout(() => {
+      reject(new Error(errorMessage))
+    }, timeoutMs)
+  })
+
+  return Promise.race([promise, timeoutPromise]).finally(() => {
+    if (timeoutID !== undefined) {
+      clearTimeout(timeoutID)
+    }
+  })
+}
+
 function isAnthropicProvider(providerID: string): boolean {
   return providerID === "anthropic" || providerID === "google-vertex-anthropic"
 }
@@ -94,11 +115,15 @@ export function createPreemptiveCompactionHook(
         modelID
       )
 
-      await ctx.client.session.summarize({
+      await withTimeout(
-        path: { id: sessionID },
+        ctx.client.session.summarize({
-        body: { providerID: targetProviderID, modelID: targetModelID, auto: true } as never,
+          path: { id: sessionID },
-        query: { directory: ctx.directory },
+          body: { providerID: targetProviderID, modelID: targetModelID, auto: true } as never,
-      })
+          query: { directory: ctx.directory },
+        }),
+        PREEMPTIVE_COMPACTION_TIMEOUT_MS,
+        `Compaction summarize timed out after ${PREEMPTIVE_COMPACTION_TIMEOUT_MS}ms`,
+      )
 
       compactedSessions.add(sessionID)
     } catch (error) {

src/hooks/ralph-loop/AGENTS.md

@@ -1,6 +1,6 @@
 # src/hooks/ralph-loop/ — Self-Referential Dev Loop
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/hooks/ralph-loop/iteration-continuation.ts

@@ -33,15 +33,6 @@ export async function continueIteration(
       return
     }
 
-    const boundState = options.loopState.setSessionID(newSessionID)
-    if (!boundState) {
-      log(`[${HOOK_NAME}] Failed to bind loop state to new session`, {
-        previousSessionID: options.previousSessionID,
-        newSessionID,
-      })
-      return
-    }
-
     await injectContinuationPrompt(ctx, {
       sessionID: newSessionID,
       inheritFromSessionID: options.previousSessionID,
@@ -51,6 +42,16 @@ export async function continueIteration(
     })
 
     await selectSessionInTui(ctx.client, newSessionID)
+
+    const boundState = options.loopState.setSessionID(newSessionID)
+    if (!boundState) {
+      log(`[${HOOK_NAME}] Failed to bind loop state to new session`, {
+        previousSessionID: options.previousSessionID,
+        newSessionID,
+      })
+      return
+    }
+
     return
   }
 

src/hooks/ralph-loop/reset-strategy-race-condition.test.ts

@@ -0,0 +1,113 @@
+/// <reference types="bun-types" />
+import { describe, expect, test } from "bun:test"
+import { createRalphLoopHook } from "./index"
+
+function createDeferred(): {
+  promise: Promise<void>
+  resolve: () => void
+} {
+  let resolvePromise: (() => void) | null = null
+  const promise = new Promise<void>((resolve) => {
+    resolvePromise = resolve
+  })
+
+  return {
+    promise,
+    resolve: () => {
+      if (resolvePromise) {
+        resolvePromise()
+      }
+    },
+  }
+}
+
+async function waitUntil(condition: () => boolean): Promise<void> {
+  for (let index = 0; index < 100; index++) {
+    if (condition()) {
+      return
+    }
+
+    await new Promise<void>((resolve) => {
+      setTimeout(resolve, 0)
+    })
+  }
+
+  throw new Error("Condition was not met in time")
+}
+
+describe("ralph-loop reset strategy race condition", () => {
+  test("should continue iteration when old session idle arrives before TUI switch completes", async () => {
+    // given - reset strategy loop with blocked TUI session switch
+    const promptCalls: Array<{ sessionID: string; text: string }> = []
+    const createSessionCalls: Array<{ parentID?: string }> = []
+    let selectSessionCalls = 0
+    const selectSessionDeferred = createDeferred()
+
+    const hook = createRalphLoopHook({
+      directory: process.cwd(),
+      client: {
+        session: {
+          prompt: async (options: {
+            path: { id: string }
+            body: { parts: Array<{ type: string; text: string }> }
+          }) => {
+            promptCalls.push({
+              sessionID: options.path.id,
+              text: options.body.parts[0].text,
+            })
+            return {}
+          },
+          promptAsync: async (options: {
+            path: { id: string }
+            body: { parts: Array<{ type: string; text: string }> }
+          }) => {
+            promptCalls.push({
+              sessionID: options.path.id,
+              text: options.body.parts[0].text,
+            })
+            return {}
+          },
+          create: async (options: {
+            body: { parentID?: string; title?: string }
+            query?: { directory?: string }
+          }) => {
+            createSessionCalls.push({ parentID: options.body.parentID })
+            return { data: { id: `new-session-${createSessionCalls.length}` } }
+          },
+          messages: async () => ({ data: [] }),
+        },
+        tui: {
+          showToast: async () => ({}),
+          selectSession: async () => {
+            selectSessionCalls += 1
+            await selectSessionDeferred.promise
+            return {}
+          },
+        },
+      },
+    } as Parameters<typeof createRalphLoopHook>[0])
+
+    hook.startLoop("session-old", "Build feature", { strategy: "reset" })
+
+    // when - first idle is in-flight and old session fires idle again before TUI switch resolves
+    const firstIdleEvent = hook.event({
+      event: { type: "session.idle", properties: { sessionID: "session-old" } },
+    })
+
+    await waitUntil(() => selectSessionCalls > 0)
+
+    const secondIdleEvent = hook.event({
+      event: { type: "session.idle", properties: { sessionID: "session-old" } },
+    })
+
+    await waitUntil(() => selectSessionCalls > 1)
+
+    selectSessionDeferred.resolve()
+    await Promise.all([firstIdleEvent, secondIdleEvent])
+
+    // then - second idle should not be skipped during reset transition
+    expect(createSessionCalls.length).toBe(2)
+    expect(promptCalls.length).toBe(2)
+    expect(hook.getState()?.iteration).toBe(3)
+  })
+})

src/hooks/rules-injector/AGENTS.md

@@ -1,6 +1,6 @@
 # src/hooks/rules-injector/ — Conditional Rules Injection
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/hooks/session-notification-input-needed.test.ts

@@ -3,6 +3,7 @@ const { describe, expect, test, beforeEach, afterEach, spyOn } = require("bun:te
 const { createSessionNotification } = require("./session-notification")
 const { setMainSession, subagentSessions, _resetForTesting } = require("../features/claude-code-session-state")
 const utils = require("./session-notification-utils")
+const sender = require("./session-notification-sender")
 
 describe("session-notification input-needed events", () => {
   let notificationCalls: string[]
@@ -37,6 +38,10 @@ describe("session-notification input-needed events", () => {
     spyOn(utils, "getNotifySendPath").mockResolvedValue("/usr/bin/notify-send")
     spyOn(utils, "getPowershellPath").mockResolvedValue("powershell")
     spyOn(utils, "startBackgroundCheck").mockImplementation(() => {})
+    spyOn(sender, "detectPlatform").mockReturnValue("darwin")
+    spyOn(sender, "sendSessionNotification").mockImplementation(async (_ctx: unknown, _platform: unknown, _title: unknown, message: string) => {
+      notificationCalls.push(message)
+    })
   })
 
   afterEach(() => {
@@ -47,7 +52,7 @@ describe("session-notification input-needed events", () => {
   test("sends question notification when question tool asks for input", async () => {
     const sessionID = "main-question"
     setMainSession(sessionID)
-    const hook = createSessionNotification(createMockPluginInput())
+    const hook = createSessionNotification(createMockPluginInput(), { enforceMainSessionFilter: false })
 
     await hook({
       event: {
@@ -74,7 +79,7 @@ describe("session-notification input-needed events", () => {
   test("sends permission notification for permission events", async () => {
     const sessionID = "main-permission"
     setMainSession(sessionID)
-    const hook = createSessionNotification(createMockPluginInput())
+    const hook = createSessionNotification(createMockPluginInput(), { enforceMainSessionFilter: false })
 
     await hook({
       event: {

src/hooks/session-notification.test.ts

@@ -1,8 +1,9 @@
-import { describe, expect, test, beforeEach, afterEach, spyOn } from "bun:test"
+const { describe, expect, test, beforeEach, afterEach, spyOn } = require("bun:test")
 
 import { createSessionNotification } from "./session-notification"
 import { setMainSession, subagentSessions, _resetForTesting } from "../features/claude-code-session-state"
 import * as utils from "./session-notification-utils"
+import * as sender from "./session-notification-sender"
 
 describe("session-notification", () => {
   let notificationCalls: string[]
@@ -40,6 +41,10 @@ describe("session-notification", () => {
     spyOn(utils, "getPaplayPath").mockResolvedValue("/usr/bin/paplay")
     spyOn(utils, "getAplayPath").mockResolvedValue("/usr/bin/aplay")
     spyOn(utils, "startBackgroundCheck").mockImplementation(() => {})
+    spyOn(sender, "detectPlatform").mockReturnValue("darwin")
+    spyOn(sender, "sendSessionNotification").mockImplementation(async (_ctx, _platform, _title, message) => {
+      notificationCalls.push(message)
+    })
   })
 
   afterEach(() => {
@@ -105,6 +110,7 @@ describe("session-notification", () => {
     const hook = createSessionNotification(createMockPluginInput(), {
       idleConfirmationDelay: 10,
       skipIfIncompleteTodos: false,
+      enforceMainSessionFilter: false,
     })
 
     // when - main session goes idle
@@ -332,6 +338,7 @@ describe("session-notification", () => {
     const hook = createSessionNotification(createMockPluginInput(), {
       idleConfirmationDelay: 10,
       skipIfIncompleteTodos: false,
+      enforceMainSessionFilter: false,
     })
 
     // when - session goes idle twice

src/hooks/session-notification.ts

@@ -4,11 +4,9 @@ import {
   startBackgroundCheck,
 } from "./session-notification-utils"
 import {
-  detectPlatform,
+  type Platform,
-  getDefaultSoundPath,
-  playSessionNotificationSound,
-  sendSessionNotification,
 } from "./session-notification-sender"
+import * as sessionNotificationSender from "./session-notification-sender"
 import { hasIncompleteTodos } from "./session-todo-status"
 import { createIdleNotificationScheduler } from "./session-notification-scheduler"
 
@@ -25,13 +23,14 @@ interface SessionNotificationConfig {
   skipIfIncompleteTodos?: boolean
   /** Maximum number of sessions to track before cleanup (default: 100) */
   maxTrackedSessions?: number
+  enforceMainSessionFilter?: boolean
 }
 export function createSessionNotification(
   ctx: PluginInput,
   config: SessionNotificationConfig = {}
 ) {
-  const currentPlatform = detectPlatform()
+  const currentPlatform: Platform = sessionNotificationSender.detectPlatform()
-  const defaultSoundPath = getDefaultSoundPath(currentPlatform)
+  const defaultSoundPath = sessionNotificationSender.getDefaultSoundPath(currentPlatform)
 
   startBackgroundCheck(currentPlatform)
 
@@ -45,6 +44,7 @@ export function createSessionNotification(
     idleConfirmationDelay: 1500,
     skipIfIncompleteTodos: true,
     maxTrackedSessions: 100,
+    enforceMainSessionFilter: true,
     ...config,
   }
 
@@ -53,8 +53,8 @@ export function createSessionNotification(
     platform: currentPlatform,
     config: mergedConfig,
     hasIncompleteTodos,
-    send: sendSessionNotification,
+    send: sessionNotificationSender.sendSessionNotification,
-    playSound: playSessionNotificationSound,
+    playSound: sessionNotificationSender.playSessionNotificationSound,
   })
 
   const QUESTION_TOOLS = new Set(["question", "ask_user_question", "askuserquestion"])
@@ -81,8 +81,10 @@ export function createSessionNotification(
   const shouldNotifyForSession = (sessionID: string): boolean => {
     if (subagentSessions.has(sessionID)) return false
 
-    const mainSessionID = getMainSessionID()
+    if (mergedConfig.enforceMainSessionFilter) {
-    if (mainSessionID && sessionID !== mainSessionID) return false
+      const mainSessionID = getMainSessionID()
+      if (mainSessionID && sessionID !== mainSessionID) return false
+    }
 
     return true
   }
@@ -146,9 +148,14 @@ export function createSessionNotification(
       if (!shouldNotifyForSession(sessionID)) return
 
       scheduler.markSessionActivity(sessionID)
-      await sendSessionNotification(ctx, currentPlatform, mergedConfig.title, mergedConfig.permissionMessage)
+      await sessionNotificationSender.sendSessionNotification(
+        ctx,
+        currentPlatform,
+        mergedConfig.title,
+        mergedConfig.permissionMessage,
+      )
       if (mergedConfig.playSound && mergedConfig.soundPath) {
-        await playSessionNotificationSound(ctx, currentPlatform, mergedConfig.soundPath)
+        await sessionNotificationSender.playSessionNotificationSound(ctx, currentPlatform, mergedConfig.soundPath)
       }
       return
     }
@@ -168,9 +175,9 @@ export function createSessionNotification(
               ? mergedConfig.permissionMessage
               : mergedConfig.questionMessage
 
-            await sendSessionNotification(ctx, currentPlatform, mergedConfig.title, message)
+            await sessionNotificationSender.sendSessionNotification(ctx, currentPlatform, mergedConfig.title, message)
             if (mergedConfig.playSound && mergedConfig.soundPath) {
-              await playSessionNotificationSound(ctx, currentPlatform, mergedConfig.soundPath)
+              await sessionNotificationSender.playSessionNotificationSound(ctx, currentPlatform, mergedConfig.soundPath)
             }
           }
         }

src/hooks/session-recovery/AGENTS.md

@@ -1,6 +1,6 @@
 # src/hooks/session-recovery/ — Auto Session Error Recovery
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

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

@@ -7,9 +7,12 @@ import { createStartWorkHook } from "./index"
 import {
   writeBoulderState,
   clearBoulderState,
+  readBoulderState,
 } from "../../features/boulder-state"
 import type { BoulderState } from "../../features/boulder-state"
 import * as sessionState from "../../features/claude-code-session-state"
+import * as worktreeDetector from "./worktree-detector"
+import * as worktreeDetector from "./worktree-detector"
 
 describe("start-work hook", () => {
   let testDir: string
@@ -402,4 +405,152 @@ describe("start-work hook", () => {
       updateSpy.mockRestore()
     })
   })
+
+  describe("worktree support", () => {
+    let detectSpy: ReturnType<typeof spyOn>
+
+    beforeEach(() => {
+      detectSpy = spyOn(worktreeDetector, "detectWorktreePath").mockReturnValue(null)
+    })
+
+    afterEach(() => {
+      detectSpy.mockRestore()
+    })
+
+    test("should inject model-decides instructions when no --worktree flag", async () => {
+      // given - single plan, no worktree flag
+      const plansDir = join(testDir, ".sisyphus", "plans")
+      mkdirSync(plansDir, { recursive: true })
+      writeFileSync(join(plansDir, "my-plan.md"), "# Plan\n- [ ] Task 1")
+
+      const hook = createStartWorkHook(createMockPluginInput())
+      const output = {
+        parts: [{ type: "text", text: "<session-context></session-context>" }],
+      }
+
+      // when
+      await hook["chat.message"]({ sessionID: "session-123" }, output)
+
+      // then - model-decides instructions should appear
+      expect(output.parts[0].text).toContain("Worktree Setup Required")
+      expect(output.parts[0].text).toContain("git worktree list --porcelain")
+      expect(output.parts[0].text).toContain("git worktree add")
+    })
+
+    test("should inject worktree path when --worktree flag is valid", async () => {
+      // given - single plan + valid worktree path
+      const plansDir = join(testDir, ".sisyphus", "plans")
+      mkdirSync(plansDir, { recursive: true })
+      writeFileSync(join(plansDir, "my-plan.md"), "# Plan\n- [ ] Task 1")
+      detectSpy.mockReturnValue("/validated/worktree")
+
+      const hook = createStartWorkHook(createMockPluginInput())
+      const output = {
+        parts: [{ type: "text", text: "<session-context>\n<user-request>--worktree /validated/worktree</user-request>\n</session-context>" }],
+      }
+
+      // when
+      await hook["chat.message"]({ sessionID: "session-123" }, output)
+
+      // then - validated path shown, no model-decides instructions
+      expect(output.parts[0].text).toContain("**Worktree**: /validated/worktree")
+      expect(output.parts[0].text).not.toContain("Worktree Setup Required")
+    })
+
+    test("should store worktree_path in boulder when --worktree is valid", async () => {
+      // given - plan + valid worktree
+      const plansDir = join(testDir, ".sisyphus", "plans")
+      mkdirSync(plansDir, { recursive: true })
+      writeFileSync(join(plansDir, "my-plan.md"), "# Plan\n- [ ] Task 1")
+      detectSpy.mockReturnValue("/valid/wt")
+
+      const hook = createStartWorkHook(createMockPluginInput())
+      const output = {
+        parts: [{ type: "text", text: "<session-context>\n<user-request>--worktree /valid/wt</user-request>\n</session-context>" }],
+      }
+
+      // when
+      await hook["chat.message"]({ sessionID: "session-123" }, output)
+
+      // then - boulder.json has worktree_path
+      const state = readBoulderState(testDir)
+      expect(state?.worktree_path).toBe("/valid/wt")
+    })
+
+    test("should NOT store worktree_path when --worktree path is invalid", async () => {
+      // given - plan + invalid worktree path (detectWorktreePath returns null)
+      const plansDir = join(testDir, ".sisyphus", "plans")
+      mkdirSync(plansDir, { recursive: true })
+      writeFileSync(join(plansDir, "my-plan.md"), "# Plan\n- [ ] Task 1")
+      // detectSpy already returns null by default
+
+      const hook = createStartWorkHook(createMockPluginInput())
+      const output = {
+        parts: [{ type: "text", text: "<session-context>\n<user-request>--worktree /nonexistent/wt</user-request>\n</session-context>" }],
+      }
+
+      // when
+      await hook["chat.message"]({ sessionID: "session-123" }, output)
+
+      // then - worktree_path absent, setup instructions present
+      const state = readBoulderState(testDir)
+      expect(state?.worktree_path).toBeUndefined()
+      expect(output.parts[0].text).toContain("needs setup")
+      expect(output.parts[0].text).toContain("git worktree add /nonexistent/wt")
+    })
+
+    test("should update boulder worktree_path on resume when new --worktree given", async () => {
+      // given - existing boulder with old worktree, user provides new worktree
+      const planPath = join(testDir, "plan.md")
+      writeFileSync(planPath, "# Plan\n- [ ] Task 1")
+      const existingState: BoulderState = {
+        active_plan: planPath,
+        started_at: "2026-01-01T00:00:00Z",
+        session_ids: ["old-session"],
+        plan_name: "plan",
+        worktree_path: "/old/wt",
+      }
+      writeBoulderState(testDir, existingState)
+      detectSpy.mockReturnValue("/new/wt")
+
+      const hook = createStartWorkHook(createMockPluginInput())
+      const output = {
+        parts: [{ type: "text", text: "<session-context>\n<user-request>--worktree /new/wt</user-request>\n</session-context>" }],
+      }
+
+      // when
+      await hook["chat.message"]({ sessionID: "session-456" }, output)
+
+      // then - boulder reflects updated worktree and new session appended
+      const state = readBoulderState(testDir)
+      expect(state?.worktree_path).toBe("/new/wt")
+      expect(state?.session_ids).toContain("session-456")
+    })
+
+    test("should show existing worktree on resume when no --worktree flag", async () => {
+      // given - existing boulder already has worktree_path, no flag given
+      const planPath = join(testDir, "plan.md")
+      writeFileSync(planPath, "# Plan\n- [ ] Task 1")
+      const existingState: BoulderState = {
+        active_plan: planPath,
+        started_at: "2026-01-01T00:00:00Z",
+        session_ids: ["old-session"],
+        plan_name: "plan",
+        worktree_path: "/existing/wt",
+      }
+      writeBoulderState(testDir, existingState)
+
+      const hook = createStartWorkHook(createMockPluginInput())
+      const output = {
+        parts: [{ type: "text", text: "<session-context></session-context>" }],
+      }
+
+      // when
+      await hook["chat.message"]({ sessionID: "session-789" }, output)
+
+      // then - shows existing worktree, no model-decides instructions
+      expect(output.parts[0].text).toContain("/existing/wt")
+      expect(output.parts[0].text).not.toContain("Worktree Setup Required")
+    })
+  })
 })

src/hooks/start-work/index.ts

@@ -1 +1,4 @@
 export { HOOK_NAME, createStartWorkHook } from "./start-work-hook"
+export { detectWorktreePath } from "./worktree-detector"
+export type { ParsedUserRequest } from "./parse-user-request"
+export { parseUserRequest } from "./parse-user-request"

src/hooks/start-work/parse-user-request.test.ts

@@ -0,0 +1,78 @@
+/// <reference types="bun-types" />
+
+import { describe, expect, test } from "bun:test"
+import { parseUserRequest } from "./parse-user-request"
+
+describe("parseUserRequest", () => {
+  describe("when no user-request tag", () => {
+    test("#given prompt without tag #when parsing #then returns nulls", () => {
+      const result = parseUserRequest("Just a regular message without any tags")
+      expect(result.planName).toBeNull()
+      expect(result.explicitWorktreePath).toBeNull()
+    })
+  })
+
+  describe("when user-request tag is empty", () => {
+    test("#given empty user-request tag #when parsing #then returns nulls", () => {
+      const result = parseUserRequest("<user-request>  </user-request>")
+      expect(result.planName).toBeNull()
+      expect(result.explicitWorktreePath).toBeNull()
+    })
+  })
+
+  describe("when only plan name given", () => {
+    test("#given plan name without worktree flag #when parsing #then returns plan name with null worktree", () => {
+      const result = parseUserRequest("<session-context>\n<user-request>my-plan</user-request>\n</session-context>")
+      expect(result.planName).toBe("my-plan")
+      expect(result.explicitWorktreePath).toBeNull()
+    })
+  })
+
+  describe("when only --worktree flag given", () => {
+    test("#given --worktree with path only #when parsing #then returns worktree path with null plan", () => {
+      const result = parseUserRequest("<user-request>--worktree /home/user/repo-feat</user-request>")
+      expect(result.planName).toBeNull()
+      expect(result.explicitWorktreePath).toBe("/home/user/repo-feat")
+    })
+  })
+
+  describe("when plan name and --worktree are both given", () => {
+    test("#given plan name before --worktree #when parsing #then returns both", () => {
+      const result = parseUserRequest("<user-request>my-plan --worktree /path/to/worktree</user-request>")
+      expect(result.planName).toBe("my-plan")
+      expect(result.explicitWorktreePath).toBe("/path/to/worktree")
+    })
+
+    test("#given --worktree before plan name #when parsing #then returns both", () => {
+      const result = parseUserRequest("<user-request>--worktree /path/to/worktree my-plan</user-request>")
+      expect(result.planName).toBe("my-plan")
+      expect(result.explicitWorktreePath).toBe("/path/to/worktree")
+    })
+  })
+
+  describe("when --worktree flag has no path", () => {
+    test("#given --worktree without path #when parsing #then worktree path is null", () => {
+      const result = parseUserRequest("<user-request>--worktree</user-request>")
+      expect(result.explicitWorktreePath).toBeNull()
+    })
+  })
+
+  describe("when ultrawork keywords are present", () => {
+    test("#given plan name with ultrawork keyword #when parsing #then strips keyword from plan name", () => {
+      const result = parseUserRequest("<user-request>my-plan ultrawork</user-request>")
+      expect(result.planName).toBe("my-plan")
+    })
+
+    test("#given plan name with ulw keyword and worktree #when parsing #then strips ulw, preserves worktree", () => {
+      const result = parseUserRequest("<user-request>my-plan ulw --worktree /path/to/wt</user-request>")
+      expect(result.planName).toBe("my-plan")
+      expect(result.explicitWorktreePath).toBe("/path/to/wt")
+    })
+
+    test("#given only ultrawork keyword with worktree #when parsing #then plan name is null, worktree preserved", () => {
+      const result = parseUserRequest("<user-request>ultrawork --worktree /wt</user-request>")
+      expect(result.planName).toBeNull()
+      expect(result.explicitWorktreePath).toBe("/wt")
+    })
+  })
+})

src/hooks/start-work/parse-user-request.ts

@@ -0,0 +1,29 @@
+const KEYWORD_PATTERN = /\b(ultrawork|ulw)\b/gi
+const WORKTREE_FLAG_PATTERN = /--worktree(?:\s+(\S+))?/
+
+export interface ParsedUserRequest {
+  planName: string | null
+  explicitWorktreePath: string | null
+}
+
+export function parseUserRequest(promptText: string): ParsedUserRequest {
+  const match = promptText.match(/<user-request>\s*([\s\S]*?)\s*<\/user-request>/i)
+  if (!match) return { planName: null, explicitWorktreePath: null }
+
+  let rawArg = match[1].trim()
+  if (!rawArg) return { planName: null, explicitWorktreePath: null }
+
+  const worktreeMatch = rawArg.match(WORKTREE_FLAG_PATTERN)
+  const explicitWorktreePath = worktreeMatch ? (worktreeMatch[1] ?? null) : null
+
+  if (worktreeMatch) {
+    rawArg = rawArg.replace(worktreeMatch[0], "").trim()
+  }
+
+  const cleanedArg = rawArg.replace(KEYWORD_PATTERN, "").trim()
+
+  return {
+    planName: cleanedArg || null,
+    explicitWorktreePath,
+  }
+}

src/hooks/start-work/start-work-hook.ts

@@ -1,3 +1,4 @@
+import { statSync } from "node:fs"
 import type { PluginInput } from "@opencode-ai/plugin"
 import {
   readBoulderState,
@@ -11,11 +12,11 @@ import {
 } from "../../features/boulder-state"
 import { log } from "../../shared/logger"
 import { updateSessionAgent } from "../../features/claude-code-session-state"
+import { detectWorktreePath } from "./worktree-detector"
+import { parseUserRequest } from "./parse-user-request"
 
 export const HOOK_NAME = "start-work" as const
 
-const KEYWORD_PATTERN = /\b(ultrawork|ulw)\b/gi
-
 interface StartWorkHookInput {
   sessionID: string
   messageID?: string
@@ -25,73 +26,76 @@ interface StartWorkHookOutput {
   parts: Array<{ type: string; text?: string }>
 }
 
-function extractUserRequestPlanName(promptText: string): string | null {
-  const userRequestMatch = promptText.match(/<user-request>\s*([\s\S]*?)\s*<\/user-request>/i)
-  if (!userRequestMatch) return null
-  
-  const rawArg = userRequestMatch[1].trim()
-  if (!rawArg) return null
-  
-  const cleanedArg = rawArg.replace(KEYWORD_PATTERN, "").trim()
-  return cleanedArg || null
-}
-
 function findPlanByName(plans: string[], requestedName: string): string | null {
   const lowerName = requestedName.toLowerCase()
-  
+  const exactMatch = plans.find((p) => getPlanName(p).toLowerCase() === lowerName)
-  const exactMatch = plans.find(p => getPlanName(p).toLowerCase() === lowerName)
   if (exactMatch) return exactMatch
-  
+  const partialMatch = plans.find((p) => getPlanName(p).toLowerCase().includes(lowerName))
-  const partialMatch = plans.find(p => getPlanName(p).toLowerCase().includes(lowerName))
   return partialMatch || null
 }
 
+const MODEL_DECIDES_WORKTREE_BLOCK = `
+## Worktree Setup Required
+
+No worktree specified. Before starting work, you MUST choose or create one:
+
+1. \`git worktree list --porcelain\` — list existing worktrees
+2. Create if needed: \`git worktree add <absolute-path> <branch-or-HEAD>\`
+3. Update \`.sisyphus/boulder.json\` — add \`"worktree_path": "<absolute-path>"\`
+4. Work exclusively inside that worktree directory`
+
+function resolveWorktreeContext(
+  explicitWorktreePath: string | null,
+): { worktreePath: string | undefined; block: string } {
+  if (explicitWorktreePath === null) {
+    return { worktreePath: undefined, block: MODEL_DECIDES_WORKTREE_BLOCK }
+  }
+
+  const validatedPath = detectWorktreePath(explicitWorktreePath)
+  if (validatedPath) {
+    return { worktreePath: validatedPath, block: `\n**Worktree**: ${validatedPath}` }
+  }
+
+  return {
+    worktreePath: undefined,
+    block: `\n**Worktree** (needs setup): \`git worktree add ${explicitWorktreePath} <branch>\`, then add \`"worktree_path"\` to boulder.json`,
+  }
+}
+
 export function createStartWorkHook(ctx: PluginInput) {
   return {
-    "chat.message": async (
+    "chat.message": async (input: StartWorkHookInput, output: StartWorkHookOutput): Promise<void> => {
-      input: StartWorkHookInput,
-      output: StartWorkHookOutput
-    ): Promise<void> => {
       const parts = output.parts
-      const promptText = parts
+      const promptText =
-        ?.filter((p) => p.type === "text" && p.text)
+        parts
-        .map((p) => p.text)
+          ?.filter((p) => p.type === "text" && p.text)
-        .join("\n")
+          .map((p) => p.text)
-        .trim() || ""
+          .join("\n")
+          .trim() || ""
 
-      // Only trigger on actual command execution (contains <session-context> tag)
+      if (!promptText.includes("<session-context>")) return
-      // NOT on description text like "Start Sisyphus work session from Prometheus plan"
-      const isStartWorkCommand = promptText.includes("<session-context>")
 
-      if (!isStartWorkCommand) {
+      log(`[${HOOK_NAME}] Processing start-work command`, { sessionID: input.sessionID })
-        return
+      updateSessionAgent(input.sessionID, "atlas")
-      }
-
-      log(`[${HOOK_NAME}] Processing start-work command`, {
-        sessionID: input.sessionID,
-      })
-
-      updateSessionAgent(input.sessionID, "atlas") // Always switch: fixes #1298
 
       const existingState = readBoulderState(ctx.directory)
       const sessionId = input.sessionID
       const timestamp = new Date().toISOString()
 
+      const { planName: explicitPlanName, explicitWorktreePath } = parseUserRequest(promptText)
+      const { worktreePath, block: worktreeBlock } = resolveWorktreeContext(explicitWorktreePath)
+
       let contextInfo = ""
-      
+
-      const explicitPlanName = extractUserRequestPlanName(promptText)
-      
       if (explicitPlanName) {
-        log(`[${HOOK_NAME}] Explicit plan name requested: ${explicitPlanName}`, {
+        log(`[${HOOK_NAME}] Explicit plan name requested: ${explicitPlanName}`, { sessionID: input.sessionID })
-          sessionID: input.sessionID,
+
-        })
-        
         const allPlans = findPrometheusPlans(ctx.directory)
         const matchedPlan = findPlanByName(allPlans, explicitPlanName)
-        
+
         if (matchedPlan) {
           const progress = getPlanProgress(matchedPlan)
-          
+
           if (progress.isComplete) {
             contextInfo = `
 ## Plan Already Complete
@@ -99,12 +103,10 @@ export function createStartWorkHook(ctx: PluginInput) {
 The requested plan "${getPlanName(matchedPlan)}" has been completed.
 All ${progress.total} tasks are done. Create a new plan with: /plan "your task"`
           } else {
-            if (existingState) {
+            if (existingState) clearBoulderState(ctx.directory)
-              clearBoulderState(ctx.directory)
+            const newState = createBoulderState(matchedPlan, sessionId, "atlas", worktreePath)
-            }
-            const newState = createBoulderState(matchedPlan, sessionId, "atlas")
             writeBoulderState(ctx.directory, newState)
-            
+
             contextInfo = `
 ## Auto-Selected Plan
 
@@ -113,17 +115,20 @@ All ${progress.total} tasks are done. Create a new plan with: /plan "your task"`
 **Progress**: ${progress.completed}/${progress.total} tasks
 **Session ID**: ${sessionId}
 **Started**: ${timestamp}
+${worktreeBlock}
 
 boulder.json has been created. Read the plan and begin execution.`
           }
         } else {
-          const incompletePlans = allPlans.filter(p => !getPlanProgress(p).isComplete)
+          const incompletePlans = allPlans.filter((p) => !getPlanProgress(p).isComplete)
           if (incompletePlans.length > 0) {
-            const planList = incompletePlans.map((p, i) => {
+            const planList = incompletePlans
-              const prog = getPlanProgress(p)
+              .map((p, i) => {
-              return `${i + 1}. [${getPlanName(p)}] - Progress: ${prog.completed}/${prog.total}`
+                const prog = getPlanProgress(p)
-            }).join("\n")
+                return `${i + 1}. [${getPlanName(p)}] - Progress: ${prog.completed}/${prog.total}`
-            
+              })
+              .join("\n")
+
             contextInfo = `
 ## Plan Not Found
 
@@ -143,9 +148,25 @@ No incomplete plans available. Create a new plan with: /plan "your task"`
         }
       } else if (existingState) {
         const progress = getPlanProgress(existingState.active_plan)
-        
+
         if (!progress.isComplete) {
-          appendSessionId(ctx.directory, sessionId)
+          const effectiveWorktree = worktreePath ?? existingState.worktree_path
+
+          if (worktreePath !== undefined) {
+            const updatedSessions = existingState.session_ids.includes(sessionId)
+              ? existingState.session_ids
+              : [...existingState.session_ids, sessionId]
+            writeBoulderState(ctx.directory, {
+              ...existingState,
+              worktree_path: worktreePath,
+              session_ids: updatedSessions,
+            })
+          } else {
+            appendSessionId(ctx.directory, sessionId)
+          }
+
+          const worktreeDisplay = effectiveWorktree ? `\n**Worktree**: ${effectiveWorktree}` : worktreeBlock
+
           contextInfo = `
 ## Active Work Session Found
 
@@ -155,6 +176,7 @@ No incomplete plans available. Create a new plan with: /plan "your task"`
 **Progress**: ${progress.completed}/${progress.total} tasks completed
 **Sessions**: ${existingState.session_ids.length + 1} (current session appended)
 **Started**: ${existingState.started_at}
+${worktreeDisplay}
 
 The current session (${sessionId}) has been added to session_ids.
 Read the plan file and continue from the first unchecked task.`
@@ -167,13 +189,15 @@ Looking for new plans...`
         }
       }
 
-      if ((!existingState && !explicitPlanName) || (existingState && !explicitPlanName && getPlanProgress(existingState.active_plan).isComplete)) {
+      if (
+        (!existingState && !explicitPlanName) ||
+        (existingState && !explicitPlanName && getPlanProgress(existingState.active_plan).isComplete)
+      ) {
         const plans = findPrometheusPlans(ctx.directory)
-        const incompletePlans = plans.filter(p => !getPlanProgress(p).isComplete)
+        const incompletePlans = plans.filter((p) => !getPlanProgress(p).isComplete)
-        
+
         if (plans.length === 0) {
           contextInfo += `
-
 ## No Plans Found
 
 No Prometheus plan files found at .sisyphus/plans/
@@ -187,7 +211,7 @@ 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, "atlas")
+          const newState = createBoulderState(planPath, sessionId, "atlas", worktreePath)
           writeBoulderState(ctx.directory, newState)
 
           contextInfo += `
@@ -199,15 +223,17 @@ All ${plans.length} plan(s) are complete. Create a new plan with: /plan "your ta
 **Progress**: ${progress.completed}/${progress.total} tasks
 **Session ID**: ${sessionId}
 **Started**: ${timestamp}
+${worktreeBlock}
 
 boulder.json has been created. Read the plan and begin execution.`
         } else {
-          const planList = incompletePlans.map((p, i) => {
+          const planList = incompletePlans
-            const progress = getPlanProgress(p)
+            .map((p, i) => {
-            const stat = require("node:fs").statSync(p)
+              const progress = getPlanProgress(p)
-            const modified = new Date(stat.mtimeMs).toISOString()
+              const modified = new Date(statSync(p).mtimeMs).toISOString()
-            return `${i + 1}. [${getPlanName(p)}] - Modified: ${modified} - Progress: ${progress.completed}/${progress.total}`
+              return `${i + 1}. [${getPlanName(p)}] - Modified: ${modified} - Progress: ${progress.completed}/${progress.total}`
-          }).join("\n")
+            })
+            .join("\n")
 
           contextInfo += `
 
@@ -220,6 +246,7 @@ Session ID: ${sessionId}
 ${planList}
 
 Ask the user which plan to work on. Present the options above and wait for their response.
+${worktreeBlock}
 </system-reminder>`
         }
       }
@@ -229,13 +256,14 @@ Ask the user which plan to work on. Present the options above and wait for their
         output.parts[idx].text = output.parts[idx].text
           .replace(/\$SESSION_ID/g, sessionId)
           .replace(/\$TIMESTAMP/g, timestamp)
-        
+
         output.parts[idx].text += `\n\n---\n${contextInfo}`
       }
 
       log(`[${HOOK_NAME}] Context injected`, {
         sessionID: input.sessionID,
         hasExistingState: !!existingState,
+        worktreePath,
       })
     },
   }

src/hooks/start-work/worktree-detector.test.ts

@@ -0,0 +1,79 @@
+/// <reference types="bun-types" />
+
+import { describe, expect, test, spyOn, beforeEach, afterEach } from "bun:test"
+import * as childProcess from "node:child_process"
+import { detectWorktreePath } from "./worktree-detector"
+
+describe("detectWorktreePath", () => {
+  let execFileSyncSpy: ReturnType<typeof spyOn>
+
+  beforeEach(() => {
+    execFileSyncSpy = spyOn(childProcess, "execFileSync").mockImplementation(
+      ((_file: string, _args: string[]) => "") as typeof childProcess.execFileSync,
+    )
+  })
+
+  afterEach(() => {
+    execFileSyncSpy.mockRestore()
+  })
+
+  describe("when directory is a valid git worktree", () => {
+    test("#given valid git dir #when detecting #then returns worktree root path", () => {
+      execFileSyncSpy.mockImplementation(
+        ((_file: string, _args: string[]) => "/home/user/my-repo\n") as typeof childProcess.execFileSync,
+      )
+
+      // when
+      const result = detectWorktreePath("/home/user/my-repo/src")
+
+      // then
+      expect(result).toBe("/home/user/my-repo")
+    })
+
+    test("#given git output with trailing newline #when detecting #then trims output", () => {
+      execFileSyncSpy.mockImplementation(
+        ((_file: string, _args: string[]) => "/projects/worktree-a\n\n") as typeof childProcess.execFileSync,
+      )
+
+      const result = detectWorktreePath("/projects/worktree-a")
+
+      expect(result).toBe("/projects/worktree-a")
+    })
+
+    test("#given valid dir #when detecting #then calls git rev-parse with cwd", () => {
+      execFileSyncSpy.mockImplementation(
+        ((_file: string, _args: string[]) => "/repo\n") as typeof childProcess.execFileSync,
+      )
+
+      detectWorktreePath("/repo/some/subdir")
+
+      expect(execFileSyncSpy).toHaveBeenCalledWith(
+        "git",
+        ["rev-parse", "--show-toplevel"],
+        expect.objectContaining({ cwd: "/repo/some/subdir" }),
+      )
+    })
+  })
+
+  describe("when directory is not a git worktree", () => {
+    test("#given non-git directory #when detecting #then returns null", () => {
+      execFileSyncSpy.mockImplementation((_file: string, _args: string[]) => {
+        throw new Error("not a git repository")
+      })
+
+      const result = detectWorktreePath("/tmp/not-a-repo")
+
+      expect(result).toBeNull()
+    })
+
+    test("#given non-existent directory #when detecting #then returns null", () => {
+      execFileSyncSpy.mockImplementation((_file: string, _args: string[]) => {
+        throw new Error("ENOENT: no such file or directory")
+      })
+
+      const result = detectWorktreePath("/nonexistent/path")
+
+      expect(result).toBeNull()
+    })
+  })
+})

src/hooks/start-work/worktree-detector.ts

@@ -0,0 +1,14 @@
+import { execFileSync } from "node:child_process"
+
+export function detectWorktreePath(directory: string): string | null {
+  try {
+    return execFileSync("git", ["rev-parse", "--show-toplevel"], {
+      cwd: directory,
+      encoding: "utf-8",
+      timeout: 5000,
+      stdio: ["pipe", "pipe", "pipe"],
+    }).trim()
+  } catch {
+    return null
+  }
+}

src/hooks/think-mode/hook.ts

@@ -1,6 +1,6 @@
 import { detectThinkKeyword, extractPromptText } from "./detector"
-import { getHighVariant, getThinkingConfig, isAlreadyHighVariant } from "./switcher"
+import { getHighVariant, isAlreadyHighVariant } from "./switcher"
-import type { ThinkModeInput, ThinkModeState } from "./types"
+import type { ThinkModeState } from "./types"
 import { log } from "../../shared"
 
 const thinkModeState = new Map<string, ThinkModeState>()
@@ -10,53 +10,24 @@ export function clearThinkModeState(sessionID: string): void {
 }
 
 export function createThinkModeHook() {
-  function isDisabledThinkingConfig(config: Record<string, unknown>): boolean {
-    const thinkingConfig = config.thinking
-    if (
-      typeof thinkingConfig === "object" &&
-      thinkingConfig !== null &&
-      "type" in thinkingConfig &&
-      (thinkingConfig as { type?: string }).type === "disabled"
-    ) {
-      return true
-    }
-
-    const providerOptions = config.providerOptions
-    if (typeof providerOptions !== "object" || providerOptions === null) {
-      return false
-    }
-
-    return Object.values(providerOptions as Record<string, unknown>).some(
-      (providerConfig) => {
-        if (typeof providerConfig !== "object" || providerConfig === null) {
-          return false
-        }
-
-        const providerConfigMap = providerConfig as Record<string, unknown>
-        const extraBody = providerConfigMap.extra_body
-        if (typeof extraBody !== "object" || extraBody === null) {
-          return false
-        }
-
-        const extraBodyMap = extraBody as Record<string, unknown>
-        const extraThinking = extraBodyMap.thinking
-        return (
-          typeof extraThinking === "object" &&
-          extraThinking !== null &&
-          (extraThinking as { type?: string }).type === "disabled"
-        )
-      }
-    )
-  }
-
   return {
-    "chat.params": async (output: ThinkModeInput, sessionID: string): Promise<void> => {
+    "chat.message": async (
+      input: {
+        sessionID: string
+        model?: { providerID: string; modelID: string }
+      },
+      output: {
+        message: Record<string, unknown>
+        parts: Array<{ type: string; text?: string; [key: string]: unknown }>
+      }
+    ): Promise<void> => {
       const promptText = extractPromptText(output.parts)
+      const sessionID = input.sessionID
 
       const state: ThinkModeState = {
         requested: false,
         modelSwitched: false,
-        thinkingConfigInjected: false,
+        variantSet: false,
       }
 
       if (!detectThinkKeyword(promptText)) {
@@ -66,7 +37,12 @@ export function createThinkModeHook() {
 
       state.requested = true
 
-      const currentModel = output.message.model
+      if (typeof output.message.variant === "string") {
+        thinkModeState.set(sessionID, state)
+        return
+      }
+
+      const currentModel = input.model
       if (!currentModel) {
         thinkModeState.set(sessionID, state)
         return
@@ -81,14 +57,15 @@ export function createThinkModeHook() {
       }
 
       const highVariant = getHighVariant(currentModel.modelID)
-      const thinkingConfig = getThinkingConfig(currentModel.providerID, currentModel.modelID)
 
       if (highVariant) {
         output.message.model = {
           providerID: currentModel.providerID,
           modelID: highVariant,
         }
+        output.message.variant = "high"
         state.modelSwitched = true
+        state.variantSet = true
         log("Think mode: model switched to high variant", {
           sessionID,
           from: currentModel.modelID,
@@ -96,42 +73,6 @@ export function createThinkModeHook() {
         })
       }
 
-      if (thinkingConfig) {
-        const messageData = output.message as Record<string, unknown>
-        const agentThinking = messageData.thinking as { type?: string } | undefined
-        const agentProviderOptions = messageData.providerOptions
-
-        const agentDisabledThinking = agentThinking?.type === "disabled"
-        const agentHasCustomProviderOptions = Boolean(agentProviderOptions)
-
-        if (agentDisabledThinking) {
-          log("Think mode: skipping - agent has thinking disabled", {
-            sessionID,
-            provider: currentModel.providerID,
-          })
-        } else if (agentHasCustomProviderOptions) {
-          log("Think mode: skipping - agent has custom providerOptions", {
-            sessionID,
-            provider: currentModel.providerID,
-          })
-        } else if (
-          !isDisabledThinkingConfig(thinkingConfig as Record<string, unknown>)
-        ) {
-          Object.assign(output.message, thinkingConfig)
-          state.thinkingConfigInjected = true
-          log("Think mode: thinking config injected", {
-            sessionID,
-            provider: currentModel.providerID,
-            config: thinkingConfig,
-          })
-        } else {
-          log("Think mode: skipping disabled thinking config", {
-            sessionID,
-            provider: currentModel.providerID,
-          })
-        }
-      }
-
       thinkModeState.set(sessionID, state)
     },
 

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

@@ -1,452 +1,155 @@
-import { describe, expect, it, beforeEach } from "bun:test"
+import { beforeEach, describe, expect, it } from "bun:test"
-import type { ThinkModeInput } from "./types"
 
-const { createThinkModeHook, clearThinkModeState } = await import("./index")
+const { clearThinkModeState, createThinkModeHook } = await import("./index")
+
+type ThinkModeHookInput = {
+  sessionID: string
+  model?: { providerID: string; modelID: string }
+}
+
+type ThinkModeHookOutput = {
+  message: Record<string, unknown>
+  parts: Array<{ type: string; text?: string; [key: string]: unknown }>
+}
+
+function createHookInput(args: {
+  sessionID?: string
+  providerID?: string
+  modelID?: string
+}): ThinkModeHookInput {
+  const { sessionID = "test-session-id", providerID, modelID } = args
+
+  if (!providerID || !modelID) {
+    return { sessionID }
+  }
 
-/**
- * Helper to create a mock ThinkModeInput for testing
- */
-function createMockInput(
-  providerID: string,
-  modelID: string,
-  promptText: string
-): ThinkModeInput {
   return {
-    parts: [{ type: "text", text: promptText }],
+    sessionID,
-    message: {
+    model: { providerID, modelID },
-      model: {
-        providerID,
-        modelID,
-      },
-    },
   }
 }
 
-/**
+function createHookOutput(promptText: string, variant?: string): ThinkModeHookOutput {
- * Type helper for accessing dynamically injected properties on message
+  return {
- */
+    message: variant ? { variant } : {},
-type MessageWithInjectedProps = Record<string, unknown>
+    parts: [{ type: "text", text: promptText }],
+  }
+}
 
-describe("createThinkModeHook integration", () => {
+describe("createThinkModeHook", () => {
   const sessionID = "test-session-id"
 
   beforeEach(() => {
     clearThinkModeState(sessionID)
   })
 
-  describe("GitHub Copilot provider integration", () => {
+  it("sets high variant and switches model when think keyword is present", async () => {
-    describe("Claude models", () => {
+    // given
-      it("should activate thinking mode for github-copilot Claude with think keyword", async () => {
+    const hook = createThinkModeHook()
-        // given a github-copilot Claude model and prompt with "think" keyword
+    const input = createHookInput({
-        const hook = createThinkModeHook()
+      sessionID,
-        const input = createMockInput(
+      providerID: "github-copilot",
-          "github-copilot",
+      modelID: "claude-opus-4-6",
-          "claude-opus-4-6",
-          "Please think deeply about this problem"
-        )
-
-        // when the chat.params hook is called
-        await hook["chat.params"](input, sessionID)
-
-        // then should upgrade to high variant and inject thinking config
-        const message = input.message as MessageWithInjectedProps
-        expect(input.message.model?.modelID).toBe("claude-opus-4-6-high")
-        expect(message.thinking).toBeDefined()
-        expect((message.thinking as Record<string, unknown>)?.type).toBe(
-          "enabled"
-        )
-        expect(
-          (message.thinking as Record<string, unknown>)?.budgetTokens
-        ).toBe(64000)
-      })
-
-      it("should handle github-copilot Claude with dots in version", async () => {
-        // given a github-copilot Claude model with dot format (claude-opus-4.6)
-        const hook = createThinkModeHook()
-        const input = createMockInput(
-          "github-copilot",
-          "claude-opus-4.6",
-          "ultrathink mode"
-        )
-
-        // when the chat.params hook is called
-        await hook["chat.params"](input, sessionID)
-
-        // then should upgrade to high variant (hyphen format)
-        const message = input.message as MessageWithInjectedProps
-        expect(input.message.model?.modelID).toBe("claude-opus-4-6-high")
-        expect(message.thinking).toBeDefined()
-      })
-
-      it("should handle github-copilot Claude Sonnet", async () => {
-        // given a github-copilot Claude Sonnet model
-        const hook = createThinkModeHook()
-        const input = createMockInput(
-          "github-copilot",
-          "claude-sonnet-4-6",
-          "think about this"
-        )
-
-        // when the chat.params hook is called
-        await hook["chat.params"](input, sessionID)
-
-        // then should upgrade to high variant
-        const message = input.message as MessageWithInjectedProps
-        expect(input.message.model?.modelID).toBe("claude-sonnet-4-6-high")
-        expect(message.thinking).toBeDefined()
-      })
     })
+    const output = createHookOutput("Please think deeply about this")
 
-    describe("Gemini models", () => {
+    // when
-      it("should activate thinking mode for github-copilot Gemini Pro", async () => {
+    await hook["chat.message"](input, output)
-        // given a github-copilot Gemini Pro model
-        const hook = createThinkModeHook()
-        const input = createMockInput(
-          "github-copilot",
-          "gemini-3-pro",
-          "think about this"
-        )
 
-        // when the chat.params hook is called
+    // then
-        await hook["chat.params"](input, sessionID)
+    expect(output.message.variant).toBe("high")
-
+    expect(output.message.model).toEqual({
-        // then should upgrade to high variant and inject google thinking config
+      providerID: "github-copilot",
-        const message = input.message as MessageWithInjectedProps
+      modelID: "claude-opus-4-6-high",
-        expect(input.message.model?.modelID).toBe("gemini-3-pro-high")
-        expect(message.providerOptions).toBeDefined()
-        const googleOptions = (
-          message.providerOptions as Record<string, unknown>
-        )?.google as Record<string, unknown>
-        expect(googleOptions?.thinkingConfig).toBeDefined()
-      })
-
-      it("should activate thinking mode for github-copilot Gemini Flash", async () => {
-        // given a github-copilot Gemini Flash model
-        const hook = createThinkModeHook()
-        const input = createMockInput(
-          "github-copilot",
-          "gemini-3-flash",
-          "ultrathink"
-        )
-
-        // when the chat.params hook is called
-        await hook["chat.params"](input, sessionID)
-
-        // then should upgrade to high variant
-        const message = input.message as MessageWithInjectedProps
-        expect(input.message.model?.modelID).toBe("gemini-3-flash-high")
-        expect(message.providerOptions).toBeDefined()
-      })
-    })
-
-    describe("GPT models", () => {
-      it("should activate thinking mode for github-copilot GPT-5.2", async () => {
-        // given a github-copilot GPT-5.2 model
-        const hook = createThinkModeHook()
-        const input = createMockInput(
-          "github-copilot",
-          "gpt-5.2",
-          "please think"
-        )
-
-        // when the chat.params hook is called
-        await hook["chat.params"](input, sessionID)
-
-        // then should upgrade to high variant and inject openai thinking config
-        const message = input.message as MessageWithInjectedProps
-        expect(input.message.model?.modelID).toBe("gpt-5-2-high")
-        expect(message.reasoning_effort).toBe("high")
-      })
-
-      it("should activate thinking mode for github-copilot GPT-5", async () => {
-        // given a github-copilot GPT-5 model
-        const hook = createThinkModeHook()
-        const input = createMockInput("github-copilot", "gpt-5", "think deeply")
-
-        // when the chat.params hook is called
-        await hook["chat.params"](input, sessionID)
-
-        // then should upgrade to high variant
-        const message = input.message as MessageWithInjectedProps
-        expect(input.message.model?.modelID).toBe("gpt-5-high")
-        expect(message.reasoning_effort).toBe("high")
-      })
-    })
-
-    describe("No think keyword", () => {
-      it("should NOT activate for github-copilot without think keyword", async () => {
-        // given a prompt without any think keyword
-        const hook = createThinkModeHook()
-        const input = createMockInput(
-          "github-copilot",
-          "claude-opus-4-6",
-          "Just do this task"
-        )
-        const originalModelID = input.message.model?.modelID
-
-        // when the chat.params hook is called
-        await hook["chat.params"](input, sessionID)
-
-        // then should NOT change model or inject config
-        const message = input.message as MessageWithInjectedProps
-        expect(input.message.model?.modelID).toBe(originalModelID)
-        expect(message.thinking).toBeUndefined()
-      })
     })
   })
 
-  describe("Backwards compatibility with direct providers", () => {
+  it("supports dotted model IDs by switching to normalized high variant", async () => {
-    it("should still work for direct anthropic provider", async () => {
+    // given
-      // given direct anthropic provider
+    const hook = createThinkModeHook()
-      const hook = createThinkModeHook()
+    const input = createHookInput({
-      const input = createMockInput(
+      sessionID,
-        "anthropic",
+      providerID: "github-copilot",
-        "claude-sonnet-4-6",
+      modelID: "gpt-5.2",
-        "think about this"
-      )
-
-      // when the chat.params hook is called
-      await hook["chat.params"](input, sessionID)
-
-      // then should work as before
-      const message = input.message as MessageWithInjectedProps
-      expect(input.message.model?.modelID).toBe("claude-sonnet-4-6-high")
-      expect(message.thinking).toBeDefined()
     })
+    const output = createHookOutput("ultrathink about this")
 
-    it("should work for direct google-vertex-anthropic provider", async () => {
+    // when
-      //#given direct google-vertex-anthropic provider
+    await hook["chat.message"](input, output)
-      const hook = createThinkModeHook()
-      const input = createMockInput(
-        "google-vertex-anthropic",
-        "claude-opus-4-6",
-        "think deeply"
-      )
 
-      //#when the chat.params hook is called
+    // then
-      await hook["chat.params"](input, sessionID)
+    expect(output.message.variant).toBe("high")
-
+    expect(output.message.model).toEqual({
-      //#then should upgrade model and inject Claude thinking config
+      providerID: "github-copilot",
-      const message = input.message as MessageWithInjectedProps
+      modelID: "gpt-5-2-high",
-      expect(input.message.model?.modelID).toBe("claude-opus-4-6-high")
-      expect(message.thinking).toBeDefined()
-      expect((message.thinking as Record<string, unknown>)?.budgetTokens).toBe(
-        64000
-      )
-    })
-
-    it("should still work for direct google provider", async () => {
-      // given direct google provider
-      const hook = createThinkModeHook()
-      const input = createMockInput(
-        "google",
-        "gemini-3-pro",
-        "think about this"
-      )
-
-      // when the chat.params hook is called
-      await hook["chat.params"](input, sessionID)
-
-      // then should work as before
-      const message = input.message as MessageWithInjectedProps
-      expect(input.message.model?.modelID).toBe("gemini-3-pro-high")
-      expect(message.providerOptions).toBeDefined()
-    })
-
-    it("should still work for direct openai provider", async () => {
-      // given direct openai provider
-      const hook = createThinkModeHook()
-      const input = createMockInput("openai", "gpt-5", "think about this")
-
-      // when the chat.params hook is called
-      await hook["chat.params"](input, sessionID)
-
-      // then should work
-      const message = input.message as MessageWithInjectedProps
-      expect(input.message.model?.modelID).toBe("gpt-5-high")
-      expect(message.reasoning_effort).toBe("high")
-    })
-
-    it("should still work for amazon-bedrock provider", async () => {
-      // given amazon-bedrock provider
-      const hook = createThinkModeHook()
-      const input = createMockInput(
-        "amazon-bedrock",
-        "claude-sonnet-4-6",
-        "think"
-      )
-
-      // when the chat.params hook is called
-      await hook["chat.params"](input, sessionID)
-
-      // then should inject bedrock thinking config
-      const message = input.message as MessageWithInjectedProps
-      expect(input.message.model?.modelID).toBe("claude-sonnet-4-6-high")
-      expect(message.reasoningConfig).toBeDefined()
     })
   })
 
-  describe("Already-high variants", () => {
+  it("skips when message variant is already set", async () => {
-    it("should NOT re-upgrade already-high variants", async () => {
+    // given
-      // given an already-high variant model
+    const hook = createThinkModeHook()
-      const hook = createThinkModeHook()
+    const input = createHookInput({
-      const input = createMockInput(
+      sessionID,
-        "github-copilot",
+      providerID: "github-copilot",
-        "claude-opus-4-6-high",
+      modelID: "claude-sonnet-4-6",
-        "think deeply"
-      )
-
-      // when the chat.params hook is called
-      await hook["chat.params"](input, sessionID)
-
-      // then should NOT modify the model (already high)
-      const message = input.message as MessageWithInjectedProps
-      expect(input.message.model?.modelID).toBe("claude-opus-4-6-high")
-      // No additional thinking config should be injected
-      expect(message.thinking).toBeUndefined()
     })
+    const output = createHookOutput("think through this", "max")
 
-    it("should NOT re-upgrade already-high GPT variants", async () => {
+    // when
-      // given an already-high GPT variant
+    await hook["chat.message"](input, output)
-      const hook = createThinkModeHook()
-      const input = createMockInput(
-        "github-copilot",
-        "gpt-5.2-high",
-        "ultrathink"
-      )
 
-      // when the chat.params hook is called
+    // then
-      await hook["chat.params"](input, sessionID)
+    expect(output.message.variant).toBe("max")
-
+    expect(output.message.model).toBeUndefined()
-      // then should NOT modify the model
-      const message = input.message as MessageWithInjectedProps
-      expect(input.message.model?.modelID).toBe("gpt-5.2-high")
-      expect(message.reasoning_effort).toBeUndefined()
-    })
   })
 
-  describe("Unknown models", () => {
+  it("does nothing when think keyword is absent", async () => {
-    it("should not crash for unknown models via github-copilot", async () => {
+    // given
-      // given an unknown model type
+    const hook = createThinkModeHook()
-      const hook = createThinkModeHook()
+    const input = createHookInput({
-      const input = createMockInput(
+      sessionID,
-        "github-copilot",
+      providerID: "google",
-        "llama-3-70b",
+      modelID: "gemini-3-pro",
-        "think about this"
-      )
-
-      // when the chat.params hook is called
-      await hook["chat.params"](input, sessionID)
-
-      // then should not crash and model should remain unchanged
-      expect(input.message.model?.modelID).toBe("llama-3-70b")
     })
+    const output = createHookOutput("Please solve this directly")
+
+    // when
+    await hook["chat.message"](input, output)
+
+    // then
+    expect(output.message.variant).toBeUndefined()
+    expect(output.message.model).toBeUndefined()
   })
 
-  describe("Edge cases", () => {
+  it("does not modify already-high models", async () => {
-    it("should handle missing model gracefully", async () => {
+    // given
-      // given input without a model
+    const hook = createThinkModeHook()
-      const hook = createThinkModeHook()
+    const input = createHookInput({
-      const input: ThinkModeInput = {
+      sessionID,
-        parts: [{ type: "text", text: "think about this" }],
+      providerID: "openai",
-        message: {},
+      modelID: "gpt-5-high",
-      }
-
-      // when the chat.params hook is called
-      // then should not crash
-      await expect(
-        hook["chat.params"](input, sessionID)
-      ).resolves.toBeUndefined()
     })
+    const output = createHookOutput("think deeply")
 
-    it("should handle empty prompt gracefully", async () => {
+    // when
-      // given empty prompt
+    await hook["chat.message"](input, output)
-      const hook = createThinkModeHook()
-      const input = createMockInput("github-copilot", "claude-opus-4-6", "")
 
-      // when the chat.params hook is called
+    // then
-      await hook["chat.params"](input, sessionID)
+    expect(output.message.variant).toBeUndefined()
-
+    expect(output.message.model).toBeUndefined()
-      // then should not upgrade (no think keyword)
-      expect(input.message.model?.modelID).toBe("claude-opus-4-6")
-    })
   })
 
-  describe("Agent-level thinking configuration respect", () => {
+  it("handles missing input model without crashing", async () => {
-    it("should omit Z.ai GLM disabled thinking config", async () => {
+    // given
-      //#given a Z.ai GLM model with think prompt
+    const hook = createThinkModeHook()
-      const hook = createThinkModeHook()
+    const input = createHookInput({ sessionID })
-      const input = createMockInput(
+    const output = createHookOutput("think about this")
-        "zai-coding-plan",
-        "glm-5",
-        "ultrathink mode"
-      )
 
-      //#when think mode resolves Z.ai thinking configuration
+    // when
-      await hook["chat.params"](input, sessionID)
+    await expect(hook["chat.message"](input, output)).resolves.toBeUndefined()
 
-      //#then thinking config should be omitted from request
+    // then
-      const message = input.message as MessageWithInjectedProps
+    expect(output.message.variant).toBeUndefined()
-      expect(input.message.model?.modelID).toBe("glm-5")
+    expect(output.message.model).toBeUndefined()
-      expect(message.thinking).toBeUndefined()
-      expect(message.providerOptions).toBeUndefined()
-    })
-
-    it("should NOT inject thinking config when agent has thinking disabled", async () => {
-      // given agent with thinking explicitly disabled
-      const hook = createThinkModeHook()
-      const input: ThinkModeInput = {
-        parts: [{ type: "text", text: "ultrathink deeply" }],
-        message: {
-          model: { providerID: "google", modelID: "gemini-3-pro" },
-          thinking: { type: "disabled" },
-        } as ThinkModeInput["message"],
-      }
-
-      // when the chat.params hook is called
-      await hook["chat.params"](input, sessionID)
-
-      // then should NOT override agent's thinking disabled setting
-      const message = input.message as MessageWithInjectedProps
-      expect((message.thinking as { type: string }).type).toBe("disabled")
-      expect(message.providerOptions).toBeUndefined()
-    })
-
-    it("should NOT inject thinking config when agent has custom providerOptions", async () => {
-      // given agent with custom providerOptions
-      const hook = createThinkModeHook()
-      const input: ThinkModeInput = {
-        parts: [{ type: "text", text: "ultrathink" }],
-        message: {
-          model: { providerID: "google", modelID: "gemini-3-flash" },
-          providerOptions: {
-            google: { thinkingConfig: { thinkingBudget: 0 } },
-          },
-        } as ThinkModeInput["message"],
-      }
-
-      // when the chat.params hook is called
-      await hook["chat.params"](input, sessionID)
-
-      // then should NOT override agent's providerOptions
-      const message = input.message as MessageWithInjectedProps
-      const providerOpts = message.providerOptions as Record<string, unknown>
-      expect((providerOpts.google as Record<string, unknown>).thinkingConfig).toEqual({
-        thinkingBudget: 0,
-      })
-    })
-
-    it("should still inject thinking config when agent has no thinking override", async () => {
-      // given agent without thinking override
-      const hook = createThinkModeHook()
-      const input = createMockInput("google", "gemini-3-pro", "ultrathink")
-
-      // when the chat.params hook is called
-      await hook["chat.params"](input, sessionID)
-
-      // then should inject thinking config as normal
-      const message = input.message as MessageWithInjectedProps
-      expect(message.providerOptions).toBeDefined()
-    })
   })
 })

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

@@ -1,128 +1,10 @@
 import { describe, expect, it } from "bun:test"
 import {
   getHighVariant,
-  getThinkingConfig,
   isAlreadyHighVariant,
-  THINKING_CONFIGS,
 } from "./switcher"
 
 describe("think-mode switcher", () => {
-  describe("GitHub Copilot provider support", () => {
-    describe("Claude models via github-copilot", () => {
-      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-4-6"
-
-        // when getting thinking config
-        const config = getThinkingConfig(providerID, modelID)
-
-        // then should return anthropic thinking config
-        expect(config).not.toBeNull()
-        expect(config?.thinking).toBeDefined()
-        expect((config?.thinking as Record<string, unknown>)?.type).toBe(
-          "enabled"
-        )
-        expect((config?.thinking as Record<string, unknown>)?.budgetTokens).toBe(
-          64000
-        )
-      })
-
-      it("should resolve github-copilot Claude Sonnet to anthropic config", () => {
-        // given a github-copilot provider with Claude Sonnet model
-        const config = getThinkingConfig("github-copilot", "claude-sonnet-4-6")
-
-        // then should return anthropic thinking config
-        expect(config).not.toBeNull()
-        expect(config?.thinking).toBeDefined()
-      })
-
-      it("should handle Claude with dots in version number", () => {
-        // 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()
-        expect(config?.thinking).toBeDefined()
-      })
-    })
-
-    describe("Gemini models via github-copilot", () => {
-      it("should resolve github-copilot Gemini Pro to google config", () => {
-        // given a github-copilot provider with Gemini Pro model
-        const config = getThinkingConfig("github-copilot", "gemini-3-pro")
-
-        // then should return google thinking config
-        expect(config).not.toBeNull()
-        expect(config?.providerOptions).toBeDefined()
-        const googleOptions = (
-          config?.providerOptions as Record<string, unknown>
-        )?.google as Record<string, unknown>
-        expect(googleOptions?.thinkingConfig).toBeDefined()
-      })
-
-      it("should resolve github-copilot Gemini Flash to google config", () => {
-        // given a github-copilot provider with Gemini Flash model
-        const config = getThinkingConfig(
-          "github-copilot",
-          "gemini-3-flash"
-        )
-
-        // then should return google thinking config
-        expect(config).not.toBeNull()
-        expect(config?.providerOptions).toBeDefined()
-      })
-    })
-
-    describe("GPT models via github-copilot", () => {
-      it("should resolve github-copilot GPT-5.2 to openai config", () => {
-        // given a github-copilot provider with GPT-5.2 model
-        const config = getThinkingConfig("github-copilot", "gpt-5.2")
-
-        // then should return openai thinking config
-        expect(config).not.toBeNull()
-        expect(config?.reasoning_effort).toBe("high")
-      })
-
-      it("should resolve github-copilot GPT-5 to openai config", () => {
-        // given a github-copilot provider with GPT-5 model
-        const config = getThinkingConfig("github-copilot", "gpt-5")
-
-        // then should return openai thinking config
-        expect(config).not.toBeNull()
-        expect(config?.reasoning_effort).toBe("high")
-      })
-
-      it("should resolve github-copilot o1 to openai config", () => {
-        // given a github-copilot provider with o1 model
-        const config = getThinkingConfig("github-copilot", "o1-preview")
-
-        // then should return openai thinking config
-        expect(config).not.toBeNull()
-        expect(config?.reasoning_effort).toBe("high")
-      })
-
-      it("should resolve github-copilot o3 to openai config", () => {
-        // given a github-copilot provider with o3 model
-        const config = getThinkingConfig("github-copilot", "o3-mini")
-
-        // then should return openai thinking config
-        expect(config).not.toBeNull()
-        expect(config?.reasoning_effort).toBe("high")
-      })
-    })
-
-    describe("Unknown models via github-copilot", () => {
-      it("should return null for unknown model types", () => {
-        // given a github-copilot provider with unknown model
-        const config = getThinkingConfig("github-copilot", "llama-3-70b")
-
-        // then should return null (no matching provider)
-        expect(config).toBeNull()
-      })
-    })
-  })
-
   describe("Model ID normalization", () => {
     describe("getHighVariant with dots vs hyphens", () => {
       it("should handle dots in Claude version numbers", () => {
@@ -217,149 +99,6 @@ describe("think-mode switcher", () => {
     })
   })
 
-  describe("getThinkingConfig", () => {
-    describe("Already high variants", () => {
-      it("should return null for already-high variants", () => {
-        // given already-high model variants
-        expect(
-          getThinkingConfig("anthropic", "claude-opus-4-6-high")
-        ).toBeNull()
-        expect(getThinkingConfig("openai", "gpt-5-2-high")).toBeNull()
-        expect(getThinkingConfig("google", "gemini-3-pro-high")).toBeNull()
-      })
-
-      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-4-6-high")
-        ).toBeNull()
-        expect(getThinkingConfig("github-copilot", "gpt-5.2-high")).toBeNull()
-      })
-    })
-
-    describe("Non-thinking-capable models", () => {
-      it("should return null for non-thinking-capable models", () => {
-        // given models that don't support thinking mode
-        expect(getThinkingConfig("anthropic", "claude-2")).toBeNull()
-        expect(getThinkingConfig("openai", "gpt-4")).toBeNull()
-        expect(getThinkingConfig("google", "gemini-1")).toBeNull()
-      })
-    })
-
-    describe("Unknown providers", () => {
-      it("should return null for unknown providers", () => {
-        // given unknown provider IDs
-        expect(getThinkingConfig("unknown-provider", "some-model")).toBeNull()
-        expect(getThinkingConfig("azure", "gpt-5")).toBeNull()
-      })
-    })
-  })
-
-  describe("Direct provider configs (backwards compatibility)", () => {
-    it("should still work for direct anthropic provider", () => {
-      // given direct anthropic provider
-      const config = getThinkingConfig("anthropic", "claude-opus-4-6")
-
-      // then should return anthropic thinking config
-      expect(config).not.toBeNull()
-      expect(config?.thinking).toBeDefined()
-      expect((config?.thinking as Record<string, unknown>)?.type).toBe("enabled")
-    })
-
-    it("should work for direct google-vertex-anthropic provider", () => {
-      //#given direct google-vertex-anthropic provider
-      const config = getThinkingConfig(
-        "google-vertex-anthropic",
-        "claude-opus-4-6"
-      )
-
-      //#when thinking config is resolved
-
-      //#then it should return anthropic-style thinking config
-      expect(config).not.toBeNull()
-      expect(config?.thinking).toBeDefined()
-      expect((config?.thinking as Record<string, unknown>)?.type).toBe("enabled")
-      expect((config?.thinking as Record<string, unknown>)?.budgetTokens).toBe(
-        64000
-      )
-    })
-
-    it("should still work for direct google provider", () => {
-      // given direct google provider
-      const config = getThinkingConfig("google", "gemini-3-pro")
-
-      // then should return google thinking config
-      expect(config).not.toBeNull()
-      expect(config?.providerOptions).toBeDefined()
-    })
-
-    it("should still work for amazon-bedrock provider", () => {
-      // given amazon-bedrock provider with claude model
-      const config = getThinkingConfig("amazon-bedrock", "claude-sonnet-4-6")
-
-      // then should return bedrock thinking config
-      expect(config).not.toBeNull()
-      expect(config?.reasoningConfig).toBeDefined()
-    })
-
-    it("should still work for google-vertex provider", () => {
-      // given google-vertex provider
-      const config = getThinkingConfig("google-vertex", "gemini-3-pro")
-
-      // then should return google-vertex thinking config
-      expect(config).not.toBeNull()
-      expect(config?.providerOptions).toBeDefined()
-      const vertexOptions = (config?.providerOptions as Record<string, unknown>)?.[
-        "google-vertex"
-      ] as Record<string, unknown>
-      expect(vertexOptions?.thinkingConfig).toBeDefined()
-    })
-
-    it("should work for direct openai provider", () => {
-      // given direct openai provider
-      const config = getThinkingConfig("openai", "gpt-5")
-
-      // then should return openai thinking config
-      expect(config).not.toBeNull()
-      expect(config?.reasoning_effort).toBe("high")
-    })
-  })
-
-  describe("THINKING_CONFIGS structure", () => {
-    it("should have correct structure for anthropic", () => {
-      const config = THINKING_CONFIGS.anthropic
-      expect(config.thinking).toBeDefined()
-      expect(config.maxTokens).toBe(128000)
-    })
-
-    it("should have correct structure for google-vertex-anthropic", () => {
-      //#given google-vertex-anthropic config entry
-      const config = THINKING_CONFIGS["google-vertex-anthropic"]
-
-      //#when structure is validated
-
-      //#then it should match anthropic style structure
-      expect(config.thinking).toBeDefined()
-      expect(config.maxTokens).toBe(128000)
-    })
-
-    it("should have correct structure for google", () => {
-      const config = THINKING_CONFIGS.google
-      expect(config.providerOptions).toBeDefined()
-    })
-
-    it("should have correct structure for openai", () => {
-      const config = THINKING_CONFIGS.openai
-      expect(config.reasoning_effort).toBe("high")
-    })
-
-    it("should have correct structure for amazon-bedrock", () => {
-      const config = THINKING_CONFIGS["amazon-bedrock"]
-      expect(config.reasoningConfig).toBeDefined()
-      expect(config.maxTokens).toBe(64000)
-    })
-  })
-
   describe("Custom provider prefixes support", () => {
     describe("getHighVariant with prefixes", () => {
       it("should preserve vertex_ai/ prefix when getting high variant", () => {
@@ -426,141 +165,6 @@ describe("think-mode switcher", () => {
         expect(isAlreadyHighVariant("vertex_ai/gpt-5.2-high")).toBe(true)
       })
     })
-
-    describe("getThinkingConfig with prefixes", () => {
-      it("should return null for custom providers (not in THINKING_CONFIGS)", () => {
-        // given custom provider with prefixed Claude model
-        const config = getThinkingConfig("dia-llm", "vertex_ai/claude-sonnet-4-6")
-
-        // then should return null (custom provider not in THINKING_CONFIGS)
-        expect(config).toBeNull()
-      })
-
-      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-4-6")
-
-        // then should return thinking config (base model is capable)
-        expect(config).not.toBeNull()
-        expect(config?.thinking).toBeDefined()
-      })
-
-      it("should return null for prefixed models that are already high", () => {
-        // given prefixed already-high model
-        const config = getThinkingConfig("anthropic", "vertex_ai/claude-opus-4-6-high")
-
-        // then should return null
-        expect(config).toBeNull()
-      })
-    })
-
-    describe("Real-world custom provider scenario", () => {
-      it("should handle LLM proxy with vertex_ai prefix correctly", () => {
-        // given a custom LLM proxy provider using vertex_ai/ prefix
-        const providerID = "dia-llm"
-        const modelID = "vertex_ai/claude-sonnet-4-6"
-
-        // when getting high variant
-        const highVariant = getHighVariant(modelID)
-
-        // then should preserve the prefix
-        expect(highVariant).toBe("vertex_ai/claude-sonnet-4-6-high")
-
-        // #and when checking if already high
-        expect(isAlreadyHighVariant(modelID)).toBe(false)
-        expect(isAlreadyHighVariant(highVariant!)).toBe(true)
-
-        // #and when getting thinking config for custom provider
-        const config = getThinkingConfig(providerID, modelID)
-
-        // then should return null (custom provider, not anthropic)
-        // This prevents applying incompatible thinking configs to custom providers
-        expect(config).toBeNull()
-      })
-
-      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-4-6"
-        const high = getHighVariant(original)
-
-        // then the high variant should be valid
-        expect(high).toBe("vertex_ai/claude-opus-4-6-high")
-
-        // #and should be recognized as already high
-        expect(isAlreadyHighVariant(high!)).toBe(true)
-
-        // #and switching again should return null (already high)
-        expect(getHighVariant(high!)).toBeNull()
-      })
-    })
-  })
-
-  describe("Z.AI GLM-4.7 provider support", () => {
-    describe("getThinkingConfig for zai-coding-plan", () => {
-      it("should return thinking config for glm-5", () => {
-        //#given a Z.ai GLM model
-        const config = getThinkingConfig("zai-coding-plan", "glm-5")
-
-        //#when thinking config is resolved
-
-        //#then thinking type is "disabled"
-        expect(config).not.toBeNull()
-        expect(config?.providerOptions).toBeDefined()
-        const zaiOptions = (config?.providerOptions as Record<string, unknown>)?.[
-          "zai-coding-plan"
-        ] as Record<string, unknown>
-        expect(zaiOptions?.extra_body).toBeDefined()
-        const extraBody = zaiOptions?.extra_body as Record<string, unknown>
-        expect(extraBody?.thinking).toBeDefined()
-        expect((extraBody?.thinking as Record<string, unknown>)?.type).toBe("disabled")
-      })
-
-      it("should return thinking config for glm-4.6v (multimodal)", () => {
-        // given zai-coding-plan provider with glm-4.6v model
-        const config = getThinkingConfig("zai-coding-plan", "glm-4.6v")
-
-        // then should return zai-coding-plan thinking config
-        expect(config).not.toBeNull()
-        expect(config?.providerOptions).toBeDefined()
-      })
-
-      it("should return null for non-GLM models on zai-coding-plan", () => {
-        // given zai-coding-plan provider with unknown model
-        const config = getThinkingConfig("zai-coding-plan", "some-other-model")
-
-        // then should return null
-        expect(config).toBeNull()
-      })
-    })
-
-    describe("HIGH_VARIANT_MAP for GLM", () => {
-      it("should NOT have high variant for glm-5", () => {
-        // given glm-5 model
-        const variant = getHighVariant("glm-5")
-
-        // then should return null (no high variant needed)
-        expect(variant).toBeNull()
-      })
-
-      it("should NOT have high variant for glm-4.6v", () => {
-        // given glm-4.6v model
-        const variant = getHighVariant("glm-4.6v")
-
-        // then should return null
-        expect(variant).toBeNull()
-      })
-    })
-  })
-
-  describe("THINKING_CONFIGS structure for zai-coding-plan", () => {
-    it("should have correct structure for zai-coding-plan", () => {
-      const config = THINKING_CONFIGS["zai-coding-plan"]
-      expect(config.providerOptions).toBeDefined()
-      const zaiOptions = (config.providerOptions as Record<string, unknown>)?.[
-        "zai-coding-plan"
-      ] as Record<string, unknown>
-      expect(zaiOptions?.extra_body).toBeDefined()
-    })
-  })
 })
+})
+

src/hooks/think-mode/switcher.ts

@@ -53,35 +53,7 @@ function normalizeModelID(modelID: string): string {
   return modelID.replace(/\.(\d+)/g, "-$1")
 }
 
-/**
- * Resolves proxy providers (like github-copilot) to their underlying provider.
- * This allows GitHub Copilot to inherit thinking configurations from the actual
- * model provider (Anthropic, Google, OpenAI).
- *
- * @example
- * 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-4-6") // "anthropic" (unchanged)
- */
-function resolveProvider(providerID: string, modelID: string): string {
-  // GitHub Copilot is a proxy - infer actual provider from model name
-  if (providerID === "github-copilot") {
-    const modelLower = modelID.toLowerCase()
-    if (modelLower.includes("claude")) return "anthropic"
-    if (modelLower.includes("gemini")) return "google"
-    if (
-      modelLower.includes("gpt") ||
-      modelLower.includes("o1") ||
-      modelLower.includes("o3")
-    ) {
-      return "openai"
-    }
-  }
 
-  // Direct providers or unknown - return as-is
-  return providerID
-}
 
 // Maps model IDs to their "high reasoning" variant (internal convention)
 // For OpenAI models, this signals that reasoning_effort should be set to "high"
@@ -116,71 +88,6 @@ const HIGH_VARIANT_MAP: Record<string, string> = {
 
 const ALREADY_HIGH: Set<string> = new Set(Object.values(HIGH_VARIANT_MAP))
 
-export const THINKING_CONFIGS = {
-  anthropic: {
-    thinking: {
-      type: "enabled",
-      budgetTokens: 64000,
-    },
-    maxTokens: 128000,
-  },
-  "google-vertex-anthropic": {
-    thinking: {
-      type: "enabled",
-      budgetTokens: 64000,
-    },
-    maxTokens: 128000,
-  },
-  "amazon-bedrock": {
-    reasoningConfig: {
-      type: "enabled",
-      budgetTokens: 32000,
-    },
-    maxTokens: 64000,
-  },
-  google: {
-    providerOptions: {
-      google: {
-        thinkingConfig: {
-          thinkingLevel: "HIGH",
-        },
-      },
-    },
-  },
-  "google-vertex": {
-    providerOptions: {
-      "google-vertex": {
-        thinkingConfig: {
-          thinkingLevel: "HIGH",
-        },
-      },
-    },
-  },
-  openai: {
-    reasoning_effort: "high",
-  },
-  "zai-coding-plan": {
-    providerOptions: {
-      "zai-coding-plan": {
-        extra_body: {
-          thinking: {
-            type: "disabled",
-          },
-        },
-      },
-    },
-  },
-} as const satisfies Record<string, Record<string, unknown>>
-
-const THINKING_CAPABLE_MODELS = {
-  anthropic: ["claude-sonnet-4", "claude-opus-4", "claude-3"],
-  "google-vertex-anthropic": ["claude-sonnet-4", "claude-opus-4", "claude-3"],
-  "amazon-bedrock": ["claude", "anthropic"],
-  google: ["gemini-2", "gemini-3"],
-  "google-vertex": ["gemini-2", "gemini-3"],
-  openai: ["gpt-5", "o1", "o3"],
-  "zai-coding-plan": ["glm"],
-} as const satisfies Record<string, readonly string[]>
 
 export function getHighVariant(modelID: string): string | null {
   const normalized = normalizeModelID(modelID)
@@ -207,37 +114,4 @@ export function isAlreadyHighVariant(modelID: string): boolean {
   return ALREADY_HIGH.has(base) || base.endsWith("-high")
 }
 
-type ThinkingProvider = keyof typeof THINKING_CONFIGS
 
-function isThinkingProvider(provider: string): provider is ThinkingProvider {
-  return provider in THINKING_CONFIGS
-}
-
-export function getThinkingConfig(
-  providerID: string,
-  modelID: string
-): Record<string, unknown> | null {
-  const normalized = normalizeModelID(modelID)
-  const { base } = extractModelPrefix(normalized)
-
-  if (isAlreadyHighVariant(normalized)) {
-    return null
-  }
-
-  const resolvedProvider = resolveProvider(providerID, modelID)
-
-  if (!isThinkingProvider(resolvedProvider)) {
-    return null
-  }
-
-  const config = THINKING_CONFIGS[resolvedProvider]
-  const capablePatterns = THINKING_CAPABLE_MODELS[resolvedProvider]
-
-  // Check capability using base model name (without prefix)
-  const baseLower = base.toLowerCase()
-  const isCapable = capablePatterns.some((pattern) =>
-    baseLower.includes(pattern.toLowerCase())
-  )
-
-  return isCapable ? config : null
-}

src/hooks/think-mode/types.ts

@@ -1,21 +1,16 @@
 export interface ThinkModeState {
   requested: boolean
   modelSwitched: boolean
-  thinkingConfigInjected: boolean
+  variantSet: boolean
   providerID?: string
   modelID?: string
 }
 
-export interface ModelRef {
+interface ModelRef {
   providerID: string
   modelID: string
 }
 
-export interface MessageWithModel {
+interface MessageWithModel {
   model?: ModelRef
 }
-
-export interface ThinkModeInput {
-  parts: Array<{ type: string; text?: string }>
-  message: MessageWithModel
-}

src/hooks/todo-continuation-enforcer/AGENTS.md

@@ -1,6 +1,6 @@
 # src/hooks/todo-continuation-enforcer/ — Boulder Continuation Mechanism
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

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

@@ -17,6 +17,6 @@ export const TOAST_DURATION_MS = 900
 export const COUNTDOWN_GRACE_PERIOD_MS = 500
 
 export const ABORT_WINDOW_MS = 3000
-export const CONTINUATION_COOLDOWN_MS = 30_000
+export const CONTINUATION_COOLDOWN_MS = 5_000
 export const MAX_CONSECUTIVE_FAILURES = 5
 export const FAILURE_RESET_WINDOW_MS = 5 * 60 * 1000

src/mcp/AGENTS.md

@@ -1,6 +1,6 @@
 # src/mcp/ — 3 Built-in Remote MCPs
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/plugin-handlers/AGENTS.md

@@ -1,6 +1,6 @@
 # src/plugin-handlers/ — 6-Phase Config Loading Pipeline
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/plugin-handlers/agent-key-remapper.test.ts

@@ -2,7 +2,7 @@ import { describe, it, expect } from "bun:test"
 import { remapAgentKeysToDisplayNames } from "./agent-key-remapper"
 
 describe("remapAgentKeysToDisplayNames", () => {
-  it("remaps known agent keys to display names", () => {
+  it("remaps known agent keys to display names while preserving original keys", () => {
     // given agents with lowercase keys
     const agents = {
       sisyphus: { prompt: "test", mode: "primary" },
@@ -12,10 +12,11 @@ describe("remapAgentKeysToDisplayNames", () => {
     // when remapping
     const result = remapAgentKeysToDisplayNames(agents)
 
-    // then known agents get display name keys
+    // then known agents get display name keys and original keys remain accessible
     expect(result["Sisyphus (Ultraworker)"]).toBeDefined()
     expect(result["oracle"]).toBeDefined()
-    expect(result["sisyphus"]).toBeUndefined()
+    expect(result["sisyphus"]).toBeDefined()
+    expect(result["Sisyphus (Ultraworker)"]).toBe(result["sisyphus"])
   })
 
   it("preserves unknown agent keys unchanged", () => {
@@ -31,7 +32,7 @@ describe("remapAgentKeysToDisplayNames", () => {
     expect(result["custom-agent"]).toBeDefined()
   })
 
-  it("remaps all core agents", () => {
+  it("remaps all core agents while preserving original keys", () => {
     // given all core agents
     const agents = {
       sisyphus: {},
@@ -46,15 +47,20 @@ describe("remapAgentKeysToDisplayNames", () => {
     // when remapping
     const result = remapAgentKeysToDisplayNames(agents)
 
-    // then all get display name keys
+    // then all get display name keys while original keys still work
-    expect(Object.keys(result)).toEqual([
+    expect(result["Sisyphus (Ultraworker)"]).toBeDefined()
-      "Sisyphus (Ultraworker)",
+    expect(result["sisyphus"]).toBeDefined()
-      "Hephaestus (Deep Agent)",
+    expect(result["Hephaestus (Deep Agent)"]).toBeDefined()
-      "Prometheus (Plan Builder)",
+    expect(result["hephaestus"]).toBeDefined()
-      "Atlas (Plan Executor)",
+    expect(result["Prometheus (Plan Builder)"]).toBeDefined()
-      "Metis (Plan Consultant)",
+    expect(result["prometheus"]).toBeDefined()
-      "Momus (Plan Critic)",
+    expect(result["Atlas (Plan Executor)"]).toBeDefined()
-      "Sisyphus-Junior",
+    expect(result["atlas"]).toBeDefined()
-    ])
+    expect(result["Metis (Plan Consultant)"]).toBeDefined()
+    expect(result["metis"]).toBeDefined()
+    expect(result["Momus (Plan Critic)"]).toBeDefined()
+    expect(result["momus"]).toBeDefined()
+    expect(result["Sisyphus-Junior"]).toBeDefined()
+    expect(result["sisyphus-junior"]).toBeDefined()
   })
 })

src/plugin-handlers/agent-key-remapper.ts

@@ -9,6 +9,7 @@ export function remapAgentKeysToDisplayNames(
     const displayName = AGENT_DISPLAY_NAMES[key]
     if (displayName && displayName !== key) {
       result[displayName] = value
+      result[key] = value
     } else {
       result[key] = value
     }

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

@@ -0,0 +1,120 @@
+import { afterEach, beforeEach, describe, expect, spyOn, test } from "bun:test"
+
+import type { OhMyOpenCodeConfig } from "../config"
+import { createConfigHandler } from "./config-handler"
+import * as agentConfigHandler from "./agent-config-handler"
+import * as commandConfigHandler from "./command-config-handler"
+import * as mcpConfigHandler from "./mcp-config-handler"
+import * as pluginComponentsLoader from "./plugin-components-loader"
+import * as providerConfigHandler from "./provider-config-handler"
+import * as shared from "../shared"
+import * as toolConfigHandler from "./tool-config-handler"
+
+let logSpy: ReturnType<typeof spyOn>
+let loadPluginComponentsSpy: ReturnType<typeof spyOn>
+let applyAgentConfigSpy: ReturnType<typeof spyOn>
+let applyToolConfigSpy: ReturnType<typeof spyOn>
+let applyMcpConfigSpy: ReturnType<typeof spyOn>
+let applyCommandConfigSpy: ReturnType<typeof spyOn>
+let applyProviderConfigSpy: ReturnType<typeof spyOn>
+
+beforeEach(() => {
+  logSpy = spyOn(shared, "log").mockImplementation(() => {})
+  loadPluginComponentsSpy = spyOn(
+    pluginComponentsLoader,
+    "loadPluginComponents",
+  ).mockResolvedValue({
+    commands: {},
+    skills: {},
+    agents: {},
+    mcpServers: {},
+    hooksConfigs: [],
+    plugins: [],
+    errors: [],
+  })
+  applyAgentConfigSpy = spyOn(agentConfigHandler, "applyAgentConfig").mockResolvedValue(
+    {},
+  )
+  applyToolConfigSpy = spyOn(toolConfigHandler, "applyToolConfig").mockImplementation(
+    () => {},
+  )
+  applyMcpConfigSpy = spyOn(mcpConfigHandler, "applyMcpConfig").mockResolvedValue()
+  applyCommandConfigSpy = spyOn(
+    commandConfigHandler,
+    "applyCommandConfig",
+  ).mockResolvedValue()
+  applyProviderConfigSpy = spyOn(
+    providerConfigHandler,
+    "applyProviderConfig",
+  ).mockImplementation(() => {})
+})
+
+afterEach(() => {
+  logSpy.mockRestore()
+  loadPluginComponentsSpy.mockRestore()
+  applyAgentConfigSpy.mockRestore()
+  applyToolConfigSpy.mockRestore()
+  applyMcpConfigSpy.mockRestore()
+  applyCommandConfigSpy.mockRestore()
+  applyProviderConfigSpy.mockRestore()
+})
+
+describe("createConfigHandler formatter pass-through", () => {
+  test("preserves formatter object configured in opencode config", async () => {
+    // given
+    const pluginConfig: OhMyOpenCodeConfig = {}
+    const formatterConfig = {
+      prettier: {
+        command: ["prettier", "--write"],
+        extensions: [".ts", ".tsx"],
+        environment: {
+          PRETTIERD_DEFAULT_CONFIG: ".prettierrc",
+        },
+      },
+      eslint: {
+        disabled: false,
+        command: ["eslint", "--fix"],
+        extensions: [".js", ".ts"],
+      },
+    }
+    const config: Record<string, unknown> = {
+      formatter: formatterConfig,
+    }
+    const handler = createConfigHandler({
+      ctx: { directory: "/tmp" },
+      pluginConfig,
+      modelCacheState: {
+        anthropicContext1MEnabled: false,
+        modelContextLimitsCache: new Map(),
+      },
+    })
+
+    // when
+    await handler(config)
+
+    // then
+    expect(config.formatter).toEqual(formatterConfig)
+  })
+
+  test("preserves formatter=false configured in opencode config", async () => {
+    // given
+    const pluginConfig: OhMyOpenCodeConfig = {}
+    const config: Record<string, unknown> = {
+      formatter: false,
+    }
+    const handler = createConfigHandler({
+      ctx: { directory: "/tmp" },
+      pluginConfig,
+      modelCacheState: {
+        anthropicContext1MEnabled: false,
+        modelContextLimitsCache: new Map(),
+      },
+    })
+
+    // when
+    await handler(config)
+
+    // then
+    expect(config.formatter).toBe(false)
+  })
+})

src/plugin-handlers/config-handler.ts

@@ -20,6 +20,8 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
   const { ctx, pluginConfig, modelCacheState } = deps;
 
   return async (config: Record<string, unknown>) => {
+    const formatterConfig = config.formatter;
+
     applyProviderConfig({ config, modelCacheState });
 
     const pluginComponents = await loadPluginComponents({ pluginConfig });
@@ -35,6 +37,8 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
     await applyMcpConfig({ config, pluginConfig, pluginComponents });
     await applyCommandConfig({ config, pluginConfig, ctx, pluginComponents });
 
+    config.formatter = formatterConfig;
+
     log("[config-handler] config handler applied", {
       agentCount: Object.keys(agentResult).length,
       commandCount: Object.keys((config.command as Record<string, unknown>) ?? {})

src/plugin/AGENTS.md

@@ -1,10 +1,10 @@
 # src/plugin/ — 8 OpenCode Hook Handlers + Hook Composition
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 
-Core glue layer. 20 source files assembling the 8 OpenCode hook handlers and composing 44 hooks into the PluginInterface. Every handler file corresponds to one OpenCode hook type.
+Core glue layer. 20 source files assembling the 8 OpenCode hook handlers and composing 46 hooks into the PluginInterface. Every handler file corresponds to one OpenCode hook type.
 
 ## HANDLER FILES
 
@@ -25,10 +25,10 @@ Core glue layer. 20 source files assembling the 8 OpenCode hook handlers and com
 |------|------|-------|
 | `create-session-hooks.ts` | Session | 21 |
 | `create-tool-guard-hooks.ts` | Tool Guard | 10 |
-| `create-transform-hooks.ts` | Transform | 4 |
+| `create-session-hooks.ts` | Session | 23 |
-| `create-continuation-hooks.ts` | Continuation | 7 |
+| `create-tool-guard-hooks.ts` | Tool Guard | 10 |
 | `create-skill-hooks.ts` | Skill | 2 |
-| `create-core-hooks.ts` | Aggregator | Session + Guard + Transform = 35 |
+| `create-core-hooks.ts` | Aggregator | Session + Guard + Transform = 37 |
 
 ## SUPPORT FILES
 

src/plugin/chat-message.test.ts

@@ -19,6 +19,7 @@ function createMockHandlerArgs(overrides?: {
     },
     hooks: {
       stopContinuationGuard: null,
+      backgroundNotificationHook: null,
       keywordDetector: null,
       claudeCodeHooks: null,
       autoSlashCommand: null,
@@ -115,4 +116,30 @@ describe("createChatMessageHandler - TUI variant passthrough", () => {
     //#then - gate should still be marked as applied
     expect(args._appliedSessions).toContain("test-session")
   })
+
+  test("injects queued background notifications through chat.message hook", async () => {
+    //#given
+    const args = createMockHandlerArgs()
+    args.hooks.backgroundNotificationHook = {
+      "chat.message": async (
+        _input: { sessionID: string },
+        output: ChatMessageHandlerOutput,
+      ): Promise<void> => {
+        output.parts.push({
+          type: "text",
+          text: "<system-reminder>[BACKGROUND TASK COMPLETED]</system-reminder>",
+        })
+      },
+    }
+    const handler = createChatMessageHandler(args)
+    const input = createMockInput("hephaestus", { providerID: "openai", modelID: "gpt-5.3-codex" })
+    const output = createMockOutput()
+
+    //#when
+    await handler(input, output)
+
+    //#then
+    expect(output.parts).toHaveLength(1)
+    expect(output.parts[0].text).toContain("[BACKGROUND TASK COMPLETED]")
+  })
 })

src/plugin/chat-message.ts

@@ -97,8 +97,10 @@ export function createChatMessageHandler(args: {
       setSessionModel(input.sessionID, input.model)
     }
     await hooks.stopContinuationGuard?.["chat.message"]?.(input)
+    await hooks.backgroundNotificationHook?.["chat.message"]?.(input, output)
     await hooks.runtimeFallback?.["chat.message"]?.(input, output)
     await hooks.keywordDetector?.["chat.message"]?.(input, output)
+    await hooks.thinkMode?.["chat.message"]?.(input, output)
     await hooks.claudeCodeHooks?.["chat.message"]?.(input, output)
     await hooks.autoSlashCommand?.["chat.message"]?.(input, output)
     await hooks.noSisyphusGpt?.["chat.message"]?.(input, output)

src/plugin/hooks/create-session-hooks.ts

@@ -232,7 +232,10 @@ export function createSessionHooks(args: {
     : null
 
   const noHephaestusNonGpt = isHookEnabled("no-hephaestus-non-gpt")
-    ? safeHook("no-hephaestus-non-gpt", () => createNoHephaestusNonGptHook(ctx))
+    ? safeHook("no-hephaestus-non-gpt", () =>
+      createNoHephaestusNonGptHook(ctx, {
+        allowNonGptModel: pluginConfig.agents?.hephaestus?.allow_non_gpt_model,
+      }))
     : null
 
   const questionLabelTruncator = isHookEnabled("question-label-truncator")

src/plugin/ultrawork-db-model-override.ts

@@ -21,11 +21,10 @@ function tryUpdateMessageModel(
   )
   const result = stmt.run(targetModel.providerID, targetModel.modelID, messageId)
   if (result.changes === 0) return false
-
   if (variant) {
     db.prepare(
-      `UPDATE message SET data = json_set(data, '$.variant', ?, '$.thinking', ?) WHERE id = ?`,
+      `UPDATE message SET data = json_set(data, '$.variant', ?) WHERE id = ?`,
-    ).run(variant, variant, messageId)
+    ).run(variant, messageId)
   }
   return true
 }

src/plugin/ultrawork-model-override.test.ts

@@ -308,7 +308,6 @@ describe("applyUltraworkModelOverrideOnMessage", () => {
     //#then
     expect(output.message.model).toEqual({ providerID: "anthropic", modelID: "claude-opus-4-6" })
     expect(output.message["variant"]).toBe("max")
-    expect(output.message["thinking"]).toBe("max")
     expect(dbOverrideSpy).not.toHaveBeenCalled()
   })
 
@@ -324,7 +323,6 @@ describe("applyUltraworkModelOverrideOnMessage", () => {
     //#then
     expect(output.message.model).toBeUndefined()
     expect(output.message["variant"]).toBe("high")
-    expect(output.message["thinking"]).toBe("high")
     expect(dbOverrideSpy).not.toHaveBeenCalled()
   })
 

src/plugin/ultrawork-model-override.ts

@@ -117,7 +117,6 @@ export function applyUltraworkModelOverrideOnMessage(
   if (!override.providerID || !override.modelID) {
     if (override.variant) {
       output.message["variant"] = override.variant
-      output.message["thinking"] = override.variant
     }
     return
   }
@@ -134,7 +133,6 @@ export function applyUltraworkModelOverrideOnMessage(
     output.message.model = targetModel
     if (override.variant) {
       output.message["variant"] = override.variant
-      output.message["thinking"] = override.variant
     }
     return
   }

src/shared/AGENTS.md

@@ -1,6 +1,6 @@
 # src/shared/ — 101 Utility Files in 13 Categories
 
-**Generated:** 2026-02-21
+**Generated:** 2026-02-24
 
 ## OVERVIEW
 

src/shared/model-requirements.test.ts

@@ -168,14 +168,14 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     expect(primary.providers[0]).toBe("opencode")
   })
 
-  test("hephaestus requires openai/github-copilot/opencode provider", () => {
+  test("hephaestus supports openai, github-copilot, venice, and opencode providers", () => {
     // #given - hephaestus agent requirement
     const hephaestus = AGENT_MODEL_REQUIREMENTS["hephaestus"]
 
     // #when - accessing hephaestus requirement
-    // #then - requiresProvider is set to openai, github-copilot, opencode (not requiresModel)
+    // #then - requiresProvider includes openai, github-copilot, venice, and opencode
     expect(hephaestus).toBeDefined()
-    expect(hephaestus.requiresProvider).toEqual(["openai", "github-copilot", "opencode"])
+    expect(hephaestus.requiresProvider).toEqual(["openai", "github-copilot", "venice", "opencode"])
     expect(hephaestus.requiresModel).toBeUndefined()
   })
 
@@ -497,3 +497,35 @@ describe("requiresModel field in categories", () => {
     expect(artistry.requiresModel).toBe("gemini-3-pro")
   })
 })
+
+describe("gpt-5.3-codex provider restrictions", () => {
+  test("no gpt-5.3-codex entry in AGENT_MODEL_REQUIREMENTS includes github-copilot as provider", () => {
+    // given - all agent requirements
+    const allAgentEntries = Object.values(AGENT_MODEL_REQUIREMENTS).flatMap(
+      (req) => req.fallbackChain
+    )
+
+    // when - filtering entries with gpt-5.3-codex model
+    const codexEntries = allAgentEntries.filter((entry) => entry.model === "gpt-5.3-codex")
+
+    // then - none of them include github-copilot as a provider
+    for (const entry of codexEntries) {
+      expect(entry.providers).not.toContain("github-copilot")
+    }
+  })
+
+  test("no gpt-5.3-codex entry in CATEGORY_MODEL_REQUIREMENTS includes github-copilot as provider", () => {
+    // given - all category requirements
+    const allCategoryEntries = Object.values(CATEGORY_MODEL_REQUIREMENTS).flatMap(
+      (req) => req.fallbackChain
+    )
+
+    // when - filtering entries with gpt-5.3-codex model
+    const codexEntries = allCategoryEntries.filter((entry) => entry.model === "gpt-5.3-codex")
+
+    // then - none of them include github-copilot as a provider
+    for (const entry of codexEntries) {
+      expect(entry.providers).not.toContain("github-copilot")
+    }
+  })
+})

src/shared/model-requirements.ts

@@ -24,9 +24,10 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   },
   hephaestus: {
     fallbackChain: [
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
+      { providers: ["openai", "venice", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
+      { providers: ["github-copilot"], model: "gpt-5.2", variant: "medium" },
     ],
-    requiresProvider: ["openai", "github-copilot", "opencode"],
+    requiresProvider: ["openai", "github-copilot", "venice", "opencode"],
   },
   oracle: {
     fallbackChain: [
@@ -101,14 +102,14 @@ export const CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   },
   ultrabrain: {
     fallbackChain: [
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.3-codex", variant: "xhigh" },
+      { providers: ["openai", "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-4-6", variant: "max" },
     ],
   },
   deep: {
     fallbackChain: [
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
+      { providers: ["openai", "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" },
     ],
@@ -132,7 +133,7 @@ export const CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   "unspecified-low": {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-6" },
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
+      { providers: ["openai", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" },
     ],
   },

src/shared/model-suggestion-retry.test.ts

@@ -399,6 +399,43 @@ describe("promptSyncWithModelSuggestionRetry", () => {
     expect(promptAsyncMock).toHaveBeenCalledTimes(0)
   })
 
+  it("should abort and throw timeout error when sync prompt hangs", async () => {
+    // given a client where sync prompt never resolves unless aborted
+    let receivedSignal: AbortSignal | undefined
+    const promptMock = mock((input: { signal?: AbortSignal }) => {
+      receivedSignal = input.signal
+      return new Promise((_, reject) => {
+        const signal = input.signal
+        if (!signal) {
+          return
+        }
+        signal.addEventListener("abort", () => {
+          reject(signal.reason)
+        })
+      })
+    })
+    const client = {
+      session: {
+        prompt: promptMock,
+        promptAsync: mock(() => Promise.resolve()),
+      },
+    }
+
+    // when calling with short timeout
+    // then should abort the request and throw timeout error
+    await expect(
+      promptSyncWithModelSuggestionRetry(client as any, {
+        path: { id: "session-1" },
+        body: {
+          parts: [{ type: "text", text: "hello" }],
+          model: { providerID: "anthropic", modelID: "claude-sonnet-4" },
+        },
+      }, { timeoutMs: 1 })
+    ).rejects.toThrow("prompt timed out after 1ms")
+
+    expect(receivedSignal?.aborted).toBe(true)
+  })
+
   it("should retry with suggested model on ProviderModelNotFoundError", async () => {
     // given a client that fails first with model-not-found, then succeeds
     const promptMock = mock()