refactor(hooks): extract shared isOrchestratorAgent utility to avoid duplication

fix(keyword-detector): respect ultrawork config variant instead of hardcoding "max"

.github/workflows/publish-platform.yml

@@ -35,15 +35,15 @@ jobs:
   # - Uploads compressed artifacts for the publish job
   # =============================================================================
   build:
-    runs-on: ${{ matrix.platform == 'windows-x64' && 'windows-latest' || 'ubuntu-latest' }}
+    runs-on: ${{ startsWith(matrix.platform, 'windows-') && 'windows-latest' || 'ubuntu-latest' }}
     defaults:
       run:
         shell: bash
     strategy:
       fail-fast: false
-      max-parallel: 7
+      max-parallel: 11
       matrix:
-        platform: [darwin-arm64, darwin-x64, linux-x64, linux-arm64, linux-x64-musl, linux-arm64-musl, windows-x64]
+        platform: [darwin-arm64, darwin-x64, darwin-x64-baseline, linux-x64, linux-x64-baseline, linux-arm64, linux-x64-musl, linux-x64-musl-baseline, linux-arm64-musl, windows-x64, windows-x64-baseline]
     steps:
       - uses: actions/checkout@v4
 
@@ -95,14 +95,18 @@ jobs:
             case "$PLATFORM" in
               darwin-arm64) TARGET="bun-darwin-arm64" ;;
               darwin-x64) TARGET="bun-darwin-x64" ;;
+              darwin-x64-baseline) TARGET="bun-darwin-x64-baseline" ;;
               linux-x64) TARGET="bun-linux-x64" ;;
+              linux-x64-baseline) TARGET="bun-linux-x64-baseline" ;;
               linux-arm64) TARGET="bun-linux-arm64" ;;
               linux-x64-musl) TARGET="bun-linux-x64-musl" ;;
+              linux-x64-musl-baseline) TARGET="bun-linux-x64-musl-baseline" ;;
               linux-arm64-musl) TARGET="bun-linux-arm64-musl" ;;
               windows-x64) TARGET="bun-windows-x64" ;;
+              windows-x64-baseline) TARGET="bun-windows-x64-baseline" ;;
             esac
             
-            if [ "$PLATFORM" = "windows-x64" ]; then
+            if [[ "$PLATFORM" == windows-* ]]; then
               OUTPUT="packages/${PLATFORM}/bin/oh-my-opencode.exe"
             else
               OUTPUT="packages/${PLATFORM}/bin/oh-my-opencode"
@@ -119,7 +123,7 @@ jobs:
           PLATFORM="${{ matrix.platform }}"
           cd packages/${PLATFORM}
           
-          if [ "$PLATFORM" = "windows-x64" ]; then
+          if [[ "$PLATFORM" == windows-* ]]; then
             # Windows: use 7z (pre-installed on windows-latest)
             7z a -tzip ../../binary-${PLATFORM}.zip bin/ package.json
           else
@@ -155,7 +159,7 @@ jobs:
       fail-fast: false
       max-parallel: 2
       matrix:
-        platform: [darwin-arm64, darwin-x64, linux-x64, linux-arm64, linux-x64-musl, linux-arm64-musl, windows-x64]
+        platform: [darwin-arm64, darwin-x64, darwin-x64-baseline, linux-x64, linux-x64-baseline, linux-arm64, linux-x64-musl, linux-x64-musl-baseline, linux-arm64-musl, windows-x64, windows-x64-baseline]
     steps:
       - name: Check if already published
         id: check
@@ -184,7 +188,7 @@ jobs:
           PLATFORM="${{ matrix.platform }}"
           mkdir -p packages/${PLATFORM}
           
-          if [ "$PLATFORM" = "windows-x64" ]; then
+          if [[ "$PLATFORM" == windows-* ]]; then
             unzip binary-${PLATFORM}.zip -d packages/${PLATFORM}/
           else
             tar -xzvf binary-${PLATFORM}.tar.gz -C packages/${PLATFORM}/

.github/workflows/publish.yml

@@ -189,7 +189,7 @@ jobs:
           VERSION="${{ steps.version.outputs.version }}"
           jq --arg v "$VERSION" '.version = $v' package.json > tmp.json && mv tmp.json package.json
           
-          for platform in darwin-arm64 darwin-x64 linux-x64 linux-arm64 linux-x64-musl linux-arm64-musl windows-x64; do
+          for platform in darwin-arm64 darwin-x64 darwin-x64-baseline linux-x64 linux-x64-baseline linux-arm64 linux-x64-musl linux-x64-musl-baseline linux-arm64-musl windows-x64 windows-x64-baseline; do
             jq --arg v "$VERSION" '.version = $v' "packages/${platform}/package.json" > tmp.json
             mv tmp.json "packages/${platform}/package.json"
           done

.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

README.ja.md

@@ -217,9 +217,9 @@ MCPサーバーがあなたのコンテキスト予算を食いつぶしてい
 [oh-my-pi](https://github.com/can1357/oh-my-pi) に触発され、**Hashline**を実装しました。エージェントが読むすべての行にコンテンツハッシュがタグ付けされて返されます：
 
 ```
-11#VK: function hello() {
-22#XJ:   return "world";
-33#MB: }
+11#VK| function hello() {
+22#XJ|   return "world";
+33#MB| }
 ```
 
 エージェントはこのタグを参照して編集します。最後に読んだ後でファイルが変更されていた場合、ハッシュが一致せず、コードが壊れる前に編集が拒否されます。空白を正確に再現する必要もなく、間違った行を編集するエラー (stale-line) もありません。

README.ko.md

@@ -216,9 +216,9 @@ MCP 서버들이 당신의 컨텍스트 예산을 다 잡아먹죠. 우리가
 [oh-my-pi](https://github.com/can1357/oh-my-pi)에서 영감을 받아, **Hashline**을 구현했습니다. 에이전트가 읽는 모든 줄에는 콘텐츠 해시 태그가 붙어 나옵니다:
 
 ```
-11#VK: function hello() {
-22#XJ:   return "world";
-33#MB: }
+11#VK| function hello() {
+22#XJ|   return "world";
+33#MB| }
 ```
 
 에이전트는 이 태그를 참조해서 편집합니다. 마지막으로 읽은 후 파일이 변경되었다면 해시가 일치하지 않아 코드가 망가지기 전에 편집이 거부됩니다. 공백을 똑같이 재현할 필요도 없고, 엉뚱한 줄을 수정하는 에러(stale-line)도 없습니다.

README.md

@@ -220,9 +220,9 @@ The harness problem is real. Most agent failures aren't the model. It's the edit
 Inspired by [oh-my-pi](https://github.com/can1357/oh-my-pi), we implemented **Hashline**. Every line the agent reads comes back tagged with a content hash:
 
 ```
-11#VK: function hello() {
-22#XJ:   return "world";
-33#MB: }
+11#VK| function hello() {
+22#XJ|   return "world";
+33#MB| }
 ```
 
 The agent edits by referencing those tags. If the file changed since the last read, the hash won't match and the edit is rejected before corruption. No whitespace reproduction. No stale-line errors.

README.zh-cn.md

@@ -218,9 +218,9 @@ Harness 问题是真的。绝大多数所谓的 Agent 故障，其实并不是
 受 [oh-my-pi](https://github.com/can1357/oh-my-pi) 的启发，我们实现了 **Hashline** 技术。Agent 读到的每一行代码，末尾都会打上一个强绑定的内容哈希值：
 
 ```
-11#VK: function hello() {
-22#XJ:   return "world";
-33#MB: }
+11#VK| function hello() {
+22#XJ|   return "world";
+33#MB| }
 ```
 
 Agent 发起修改时，必须通过这些标签引用目标行。如果在此期间文件发生过变化，哈希验证就会失败，从而在代码被污染前直接驳回。不再有缩进空格错乱，彻底告别改错行的惨剧。

assets/oh-my-opencode.schema.json

@@ -82,6 +82,9 @@
     "hashline_edit": {
       "type": "boolean"
     },
+    "model_fallback": {
+      "type": "boolean"
+    },
     "agents": {
       "type": "object",
       "properties": {
@@ -288,6 +291,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -495,6 +510,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -702,6 +729,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -909,6 +948,21 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
+            },
+            "allow_non_gpt_model": {
+              "type": "boolean"
             }
           },
           "additionalProperties": false
@@ -1116,6 +1170,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -1323,6 +1389,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -1530,6 +1608,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -1737,6 +1827,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -1944,6 +2046,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -2151,6 +2265,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -2358,6 +2484,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -2565,6 +2703,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -2772,6 +2922,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -2979,6 +3141,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -3077,6 +3251,11 @@
           "prompt_append": {
             "type": "string"
           },
+          "max_prompt_tokens": {
+            "type": "integer",
+            "exclusiveMinimum": 0,
+            "maximum": 9007199254740991
+          },
           "is_unstable_agent": {
             "type": "boolean"
           },

bin/oh-my-opencode.js

@@ -3,8 +3,9 @@
 // Wrapper script that detects platform and spawns the correct binary
 
 import { spawnSync } from "node:child_process";
+import { readFileSync } from "node:fs";
 import { createRequire } from "node:module";
-import { getPlatformPackage, getBinaryPath } from "./platform.js";
+import { getPlatformPackageCandidates, getBinaryPath } from "./platform.js";
 
 const require = createRequire(import.meta.url);
 
@@ -26,55 +27,116 @@ function getLibcFamily() {
   }
 }
 
+function supportsAvx2() {
+  if (process.arch !== "x64") {
+    return null;
+  }
+
+  if (process.env.OH_MY_OPENCODE_FORCE_BASELINE === "1") {
+    return false;
+  }
+
+  if (process.platform === "linux") {
+    try {
+      const cpuInfo = readFileSync("/proc/cpuinfo", "utf8").toLowerCase();
+      return cpuInfo.includes("avx2");
+    } catch {
+      return null;
+    }
+  }
+
+  if (process.platform === "darwin") {
+    const probe = spawnSync("sysctl", ["-n", "machdep.cpu.leaf7_features"], {
+      encoding: "utf8",
+    });
+
+    if (probe.error || probe.status !== 0) {
+      return null;
+    }
+
+    return probe.stdout.toUpperCase().includes("AVX2");
+  }
+
+  return null;
+}
+
+function getSignalExitCode(signal) {
+  const signalCodeByName = {
+    SIGINT: 2,
+    SIGILL: 4,
+    SIGKILL: 9,
+    SIGTERM: 15,
+  };
+
+  return 128 + (signalCodeByName[signal] ?? 1);
+}
+
 function main() {
   const { platform, arch } = process;
   const libcFamily = getLibcFamily();
+  const avx2Supported = supportsAvx2();
   
-  // Get platform package name
-  let pkg;
+  let packageCandidates;
   try {
-    pkg = getPlatformPackage({ platform, arch, libcFamily });
+    packageCandidates = getPlatformPackageCandidates({
+      platform,
+      arch,
+      libcFamily,
+      preferBaseline: avx2Supported === false,
+    });
   } catch (error) {
     console.error(`\noh-my-opencode: ${error.message}\n`);
     process.exit(1);
   }
-  
-  // Resolve binary path
-  const binRelPath = getBinaryPath(pkg, platform);
-  
-  let binPath;
-  try {
-    binPath = require.resolve(binRelPath);
-  } catch {
+
+  const resolvedBinaries = packageCandidates
+    .map((pkg) => {
+      try {
+        return { pkg, binPath: require.resolve(getBinaryPath(pkg, platform)) };
+      } catch {
+        return null;
+      }
+    })
+    .filter((entry) => entry !== null);
+
+  if (resolvedBinaries.length === 0) {
     console.error(`\noh-my-opencode: Platform binary not installed.`);
     console.error(`\nYour platform: ${platform}-${arch}${libcFamily === "musl" ? "-musl" : ""}`);
-    console.error(`Expected package: ${pkg}`);
+    console.error(`Expected packages (in order): ${packageCandidates.join(", ")}`);
     console.error(`\nTo fix, run:`);
-    console.error(`  npm install ${pkg}\n`);
+    console.error(`  npm install ${packageCandidates[0]}\n`);
     process.exit(1);
   }
-  
-  // Spawn the binary
-  const result = spawnSync(binPath, process.argv.slice(2), {
-    stdio: "inherit",
-  });
-  
-  // Handle spawn errors
-  if (result.error) {
-    console.error(`\noh-my-opencode: Failed to execute binary.`);
-    console.error(`Error: ${result.error.message}\n`);
-    process.exit(2);
-  }
-  
-  // Handle signals
-  if (result.signal) {
-    const signalNum = result.signal === "SIGTERM" ? 15 : 
-                      result.signal === "SIGKILL" ? 9 :
-                      result.signal === "SIGINT" ? 2 : 1;
-    process.exit(128 + signalNum);
+
+  for (let index = 0; index < resolvedBinaries.length; index += 1) {
+    const currentBinary = resolvedBinaries[index];
+    const hasFallback = index < resolvedBinaries.length - 1;
+    const result = spawnSync(currentBinary.binPath, process.argv.slice(2), {
+      stdio: "inherit",
+    });
+
+    if (result.error) {
+      if (hasFallback) {
+        continue;
+      }
+
+      console.error(`\noh-my-opencode: Failed to execute binary.`);
+      console.error(`Error: ${result.error.message}\n`);
+      process.exit(2);
+    }
+
+    if (result.signal === "SIGILL" && hasFallback) {
+      continue;
+    }
+
+    if (result.signal) {
+      process.exit(getSignalExitCode(result.signal));
+    }
+
+    process.exit(result.status ?? 1);
   }
 
-  process.exit(result.status ?? 1);
+  process.exit(1);
 }
 
 main();

bin/platform.d.ts

@@ -0,0 +1,14 @@
+export declare function getPlatformPackage(options: {
+  platform: string;
+  arch: string;
+  libcFamily?: string | null;
+}): string;
+
+export declare function getPlatformPackageCandidates(options: {
+  platform: string;
+  arch: string;
+  libcFamily?: string | null;
+  preferBaseline?: boolean;
+}): string[];
+
+export declare function getBinaryPath(pkg: string, platform: string): string;

bin/platform.js

@@ -26,6 +26,50 @@ export function getPlatformPackage({ platform, arch, libcFamily }) {
   return `oh-my-opencode-${os}-${arch}${suffix}`;
 }
 
+/** @param {{ platform: string, arch: string, libcFamily?: string | null, preferBaseline?: boolean }} options */
+export function getPlatformPackageCandidates({ platform, arch, libcFamily, preferBaseline = false }) {
+  const primaryPackage = getPlatformPackage({ platform, arch, libcFamily });
+  const baselinePackage = getBaselinePlatformPackage({ platform, arch, libcFamily });
+
+  if (!baselinePackage) {
+    return [primaryPackage];
+  }
+
+  return preferBaseline ? [baselinePackage, primaryPackage] : [primaryPackage, baselinePackage];
+}
+
+/** @param {{ platform: string, arch: string, libcFamily?: string | null }} options */
+function getBaselinePlatformPackage({ platform, arch, libcFamily }) {
+  if (arch !== "x64") {
+    return null;
+  }
+
+  if (platform === "darwin") {
+    return "oh-my-opencode-darwin-x64-baseline";
+  }
+
+  if (platform === "win32") {
+    return "oh-my-opencode-windows-x64-baseline";
+  }
+
+  if (platform === "linux") {
+    if (libcFamily === null || libcFamily === undefined) {
+      throw new Error(
+        "Could not detect libc on Linux. " +
+        "Please ensure detect-libc is installed or report this issue."
+      );
+    }
+
+    if (libcFamily === "musl") {
+      return "oh-my-opencode-linux-x64-musl-baseline";
+    }
+
+    return "oh-my-opencode-linux-x64-baseline";
+  }
+
+  return null;
+}
+
 /**
  * Get the path to the binary within a platform package
  * @param {string} pkg Package name

bin/platform.test.ts

@@ -1,6 +1,6 @@
 // bin/platform.test.ts
 import { describe, expect, test } from "bun:test";
-import { getPlatformPackage, getBinaryPath } from "./platform.js";
+import { getBinaryPath, getPlatformPackage, getPlatformPackageCandidates } from "./platform.js";
 
 describe("getPlatformPackage", () => {
   // #region Darwin platforms
@@ -146,3 +146,58 @@ describe("getBinaryPath", () => {
     expect(result).toBe("oh-my-opencode-linux-x64/bin/oh-my-opencode");
   });
 });
+
+describe("getPlatformPackageCandidates", () => {
+  test("returns x64 and baseline candidates for Linux glibc", () => {
+    // #given Linux x64 with glibc
+    const input = { platform: "linux", arch: "x64", libcFamily: "glibc" };
+
+    // #when getting package candidates
+    const result = getPlatformPackageCandidates(input);
+
+    // #then returns modern first then baseline fallback
+    expect(result).toEqual([
+      "oh-my-opencode-linux-x64",
+      "oh-my-opencode-linux-x64-baseline",
+    ]);
+  });
+
+  test("returns x64 musl and baseline candidates for Linux musl", () => {
+    // #given Linux x64 with musl
+    const input = { platform: "linux", arch: "x64", libcFamily: "musl" };
+
+    // #when getting package candidates
+    const result = getPlatformPackageCandidates(input);
+
+    // #then returns musl modern first then musl baseline fallback
+    expect(result).toEqual([
+      "oh-my-opencode-linux-x64-musl",
+      "oh-my-opencode-linux-x64-musl-baseline",
+    ]);
+  });
+
+  test("returns baseline first when preferBaseline is true", () => {
+    // #given Windows x64 and baseline preference
+    const input = { platform: "win32", arch: "x64", preferBaseline: true };
+
+    // #when getting package candidates
+    const result = getPlatformPackageCandidates(input);
+
+    // #then baseline package is preferred first
+    expect(result).toEqual([
+      "oh-my-opencode-windows-x64-baseline",
+      "oh-my-opencode-windows-x64",
+    ]);
+  });
+
+  test("returns only one candidate for ARM64", () => {
+    // #given non-x64 platform
+    const input = { platform: "linux", arch: "arm64", libcFamily: "glibc" };
+
+    // #when getting package candidates
+    const result = getPlatformPackageCandidates(input);
+
+    // #then baseline fallback is not included
+    expect(result).toEqual(["oh-my-opencode-linux-arm64"]);
+  });
+});

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": "3.7.4",
-        "oh-my-opencode-darwin-x64": "3.7.4",
-        "oh-my-opencode-linux-arm64": "3.7.4",
-        "oh-my-opencode-linux-arm64-musl": "3.7.4",
-        "oh-my-opencode-linux-x64": "3.7.4",
-        "oh-my-opencode-linux-x64-musl": "3.7.4",
-        "oh-my-opencode-windows-x64": "3.7.4",
+        "oh-my-opencode-darwin-arm64": "3.8.5",
+        "oh-my-opencode-darwin-x64": "3.8.5",
+        "oh-my-opencode-linux-arm64": "3.8.5",
+        "oh-my-opencode-linux-arm64-musl": "3.8.5",
+        "oh-my-opencode-linux-x64": "3.8.5",
+        "oh-my-opencode-linux-x64-musl": "3.8.5",
+        "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@3.7.4", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-0m84UiVlOC2gLSFIOTmCsxFCB9CmyWV9vGPYqfBFLoyDJmedevU3R5N4ze54W7jv4HSSxz02Zwr+QF5rkQANoA=="],
+    "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@3.7.4", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-Z2dQy8jmc6DuwbN9bafhOwjZBkAkTWlfLAz1tG6xVzMqTcp4YOrzrHFOBRNeFKpOC/x7yUpO3sq/YNCclloelw=="],
+    "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@3.7.4", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-TZIsK6Dl6yX6pSTocls91bjnvoY/6/kiGnmgdsoDKcPYZ7XuBQaJwH0dK7t9/sxuDI+wKhmtrmLwKSoYOIqsRw=="],
+    "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@3.7.4", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-UwPOoQP0+1eCKP/XTDsnLJDK5jayiL4VrKz0lfRRRojl1FWvInmQumnDnluvnxW6knU7dFM3yDddlZYG6tEgcw=="],
+    "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@3.7.4", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-+TeA0Bs5wK9EMfKiEEFfyfVqdBDUjDzN8POF8JJibN0GPy1oNIGGEWIJG2cvC5onpnYEvl448vkFbkCUK0g9SQ=="],
+    "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@3.7.4", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-YzX6wFtk8RoTHkAZkfLCVyCU4yjN8D7agj/jhOnFKW50fZYa8zX+/4KLZx0IfanVpXTgrs3iiuKoa87KLDfCxQ=="],
+    "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@3.7.4", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-x39M2eFJI6pqv4go5Crf1H2SbPGFmXHIDNtbsSa5nRNcrqTisLrYGW8uXpOrqjntBeTAUBdwZmmoy6zgxHsz8w=="],
+    "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

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "3.8.1",
+  "version": "3.8.5",
   "description": "The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -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",
@@ -74,13 +75,17 @@
     "typescript": "^5.7.3"
   },
   "optionalDependencies": {
-    "oh-my-opencode-darwin-arm64": "3.8.1",
-    "oh-my-opencode-darwin-x64": "3.8.1",
-    "oh-my-opencode-linux-arm64": "3.8.1",
-    "oh-my-opencode-linux-arm64-musl": "3.8.1",
-    "oh-my-opencode-linux-x64": "3.8.1",
-    "oh-my-opencode-linux-x64-musl": "3.8.1",
-    "oh-my-opencode-windows-x64": "3.8.1"
+    "oh-my-opencode-darwin-arm64": "3.8.5",
+    "oh-my-opencode-darwin-x64": "3.8.5",
+    "oh-my-opencode-darwin-x64-baseline": "3.8.5",
+    "oh-my-opencode-linux-arm64": "3.8.5",
+    "oh-my-opencode-linux-arm64-musl": "3.8.5",
+    "oh-my-opencode-linux-x64": "3.8.5",
+    "oh-my-opencode-linux-x64-baseline": "3.8.5",
+    "oh-my-opencode-linux-x64-musl": "3.8.5",
+    "oh-my-opencode-linux-x64-musl-baseline": "3.8.5",
+    "oh-my-opencode-windows-x64": "3.8.5",
+    "oh-my-opencode-windows-x64-baseline": "3.8.5"
   },
   "trustedDependencies": [
     "@ast-grep/cli",

packages/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-arm64",
-  "version": "3.8.1",
+  "version": "3.8.5",
   "description": "Platform-specific binary for oh-my-opencode (darwin-arm64)",
   "license": "MIT",
   "repository": {

packages/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-x64",
-  "version": "3.8.1",
+  "version": "3.8.5",
   "description": "Platform-specific binary for oh-my-opencode (darwin-x64)",
   "license": "MIT",
   "repository": {

packages/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64-musl",
-  "version": "3.8.1",
+  "version": "3.8.5",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64",
-  "version": "3.8.1",
+  "version": "3.8.5",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64)",
   "license": "MIT",
   "repository": {

packages/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-musl",
-  "version": "3.8.1",
+  "version": "3.8.5",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64",
-  "version": "3.8.1",
+  "version": "3.8.5",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64)",
   "license": "MIT",
   "repository": {

packages/windows-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-windows-x64",
-  "version": "3.8.1",
+  "version": "3.8.5",
   "description": "Platform-specific binary for oh-my-opencode (windows-x64)",
   "license": "MIT",
   "repository": {

postinstall.mjs

@@ -2,7 +2,7 @@
 // Runs after npm install to verify platform binary is available
 
 import { createRequire } from "node:module";
-import { getPlatformPackage, getBinaryPath } from "./bin/platform.js";
+import { getPlatformPackageCandidates, getBinaryPath } from "./bin/platform.js";
 
 const require = createRequire(import.meta.url);
 
@@ -27,12 +27,28 @@ function main() {
   const libcFamily = getLibcFamily();
   
   try {
-    const pkg = getPlatformPackage({ platform, arch, libcFamily });
-    const binPath = getBinaryPath(pkg, platform);
-    
-    // Try to resolve the binary
-    require.resolve(binPath);
-    console.log(`✓ oh-my-opencode binary installed for ${platform}-${arch}`);
+    const packageCandidates = getPlatformPackageCandidates({
+      platform,
+      arch,
+      libcFamily,
+    });
+
+    const resolvedPackage = packageCandidates.find((pkg) => {
+      try {
+        require.resolve(getBinaryPath(pkg, platform));
+        return true;
+      } catch {
+        return false;
+      }
+    });
+
+    if (!resolvedPackage) {
+      throw new Error(
+        `No platform binary package installed. Tried: ${packageCandidates.join(", ")}`
+      );
+    }
+
+    console.log(`✓ oh-my-opencode binary installed for ${platform}-${arch} (${resolvedPackage})`);
   } catch (error) {
     console.warn(`⚠ oh-my-opencode: ${error.message}`);
     console.warn(`  The CLI may not work on this platform.`);

signatures/cla.json

@@ -1679,6 +1679,94 @@
       "created_at": "2026-02-21T22:44:45Z",
       "repoId": 1108837393,
       "pullRequestNo": 2029
+    },
+    {
+      "name": "imadal1n",
+      "id": 97968636,
+      "comment_id": 3940704780,
+      "created_at": "2026-02-22T10:57:33Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2045
+    },
+    {
+      "name": "DMax1314",
+      "id": 54206290,
+      "comment_id": 3943046087,
+      "created_at": "2026-02-23T07:06:14Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2068
+    },
+    {
+      "name": "Firstbober",
+      "id": 22197465,
+      "comment_id": 3946848526,
+      "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
-  │   ├─ createSessionHooks()     # 21: contextWindowMonitor, thinkMode, ralphLoop, sessionRecovery, jsonErrorRecovery, sisyphusGptHephaestusReminder, anthropicEffort...
-  │   ├─ createToolGuardHooks()   # 10: commentChecker, rulesInjector, writeExistingFileGuard, hashlineEditDiffEnhancer...
+  ├─→ createCoreHooks()           # 37 hooks
+  │   ├─ createSessionHooks()     # 23: contextWindowMonitor, thinkMode, ralphLoop, modelFallback, runtimeFallback, noSisyphusGpt, noHephaestusNonGpt, anthropicEffort...
+  │   ├─ 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

@@ -6,20 +6,21 @@
  *
  * Routing:
  * 1. GPT models (openai/*, github-copilot/gpt-*) → gpt.ts (GPT-5.2 optimized)
- * 2. Default (Claude, etc.) → default.ts (Claude-optimized)
+ * 2. Gemini models (google/*, google-vertex/*) → gemini.ts (Gemini-optimized)
+ * 3. Default (Claude, etc.) → default.ts (Claude-optimized)
  */
 
 import type { AgentConfig } from "@opencode-ai/sdk"
 import type { AgentMode, AgentPromptMetadata } from "../types"
-import { isGptModel } from "../types"
+import { isGptModel, isGeminiModel } from "../types"
 import type { AvailableAgent, AvailableSkill, AvailableCategory } from "../dynamic-agent-prompt-builder"
 import { buildCategorySkillsDelegationGuide } from "../dynamic-agent-prompt-builder"
 import type { CategoryConfig } from "../../config/schema"
 import { mergeCategories } from "../../shared/merge-categories"
-import { createAgentToolRestrictions } from "../../shared/permission-compat"
 
 import { getDefaultAtlasPrompt } from "./default"
 import { getGptAtlasPrompt } from "./gpt"
+import { getGeminiAtlasPrompt } from "./gemini"
 import {
   getCategoryDescription,
   buildAgentSelectionSection,
@@ -28,9 +29,9 @@ import {
   buildDecisionMatrix,
 } from "./prompt-section-builder"
 
-const MODE: AgentMode = "primary"
+const MODE: AgentMode = "all"
 
-export type AtlasPromptSource = "default" | "gpt"
+export type AtlasPromptSource = "default" | "gpt" | "gemini"
 
 /**
  * Determines which Atlas prompt to use based on model.
@@ -39,6 +40,9 @@ export function getAtlasPromptSource(model?: string): AtlasPromptSource {
   if (model && isGptModel(model)) {
     return "gpt"
   }
+  if (model && isGeminiModel(model)) {
+    return "gemini"
+  }
   return "default"
 }
 
@@ -58,6 +62,8 @@ export function getAtlasPrompt(model?: string): string {
   switch (source) {
     case "gpt":
       return getGptAtlasPrompt()
+    case "gemini":
+      return getGeminiAtlasPrompt()
     case "default":
     default:
       return getDefaultAtlasPrompt()
@@ -93,11 +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)",
@@ -106,7 +107,6 @@ export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
     temperature: 0.1,
     prompt: buildDynamicOrchestratorPrompt(ctx),
     color: "#10B981",
-    ...restrictions,
   }
 
   return baseConfig as AgentConfig

src/agents/atlas/gemini.ts

@@ -0,0 +1,372 @@
+/**
+ * Gemini-optimized Atlas System Prompt
+ *
+ * Key differences from Claude/GPT variants:
+ * - EXTREME delegation enforcement (Gemini strongly prefers doing work itself)
+ * - Aggressive verification language (Gemini trusts subagent claims too readily)
+ * - Repeated tool-call mandates (Gemini skips tool calls in favor of reasoning)
+ * - Consequence-driven framing (Gemini ignores soft warnings)
+ */
+
+export const ATLAS_GEMINI_SYSTEM_PROMPT = `
+<identity>
+You are Atlas - Master Orchestrator from OhMyOpenCode.
+Role: Conductor, not musician. General, not soldier.
+You DELEGATE, COORDINATE, and VERIFY. You NEVER write code yourself.
+
+**YOU ARE NOT AN IMPLEMENTER. YOU DO NOT WRITE CODE. EVER.**
+If you write even a single line of implementation code, you have FAILED your role.
+You are the most expensive model in the pipeline. Your value is ORCHESTRATION, not coding.
+</identity>
+
+<TOOL_CALL_MANDATE>
+## YOU MUST USE TOOLS FOR EVERY ACTION. THIS IS NOT OPTIONAL.
+
+**The user expects you to ACT using tools, not REASON internally.** Every response MUST contain tool_use blocks. A response without tool calls is a FAILED response.
+
+**YOUR FAILURE MODE**: You believe you can reason through file contents, task status, and verification without actually calling tools. You CANNOT. Your internal state about files you "already know" is UNRELIABLE.
+
+**RULES:**
+1. **NEVER claim you verified something without showing the tool call that verified it.** Reading a file in your head is NOT verification.
+2. **NEVER reason about what a changed file "probably looks like."** Call \`Read\` on it. NOW.
+3. **NEVER assume \`lsp_diagnostics\` will pass.** CALL IT and read the output.
+4. **NEVER produce a response with ZERO tool calls.** You are an orchestrator — your job IS tool calls.
+</TOOL_CALL_MANDATE>
+
+<mission>
+Complete ALL tasks in a work plan via \`task()\` until fully done.
+- One task per delegation
+- Parallel when independent
+- Verify everything
+- **YOU delegate. SUBAGENTS implement. This is absolute.**
+</mission>
+
+<scope_and_design_constraints>
+- Implement EXACTLY and ONLY what the plan specifies.
+- No extra features, no UX embellishments, no scope creep.
+- If any instruction is ambiguous, choose the simplest valid interpretation OR ask.
+- Do NOT invent new requirements.
+- Do NOT expand task boundaries beyond what's written.
+- **Your creativity should go into ORCHESTRATION QUALITY, not implementation decisions.**
+</scope_and_design_constraints>
+
+<delegation_system>
+## How to Delegate
+
+Use \`task()\` with EITHER category OR agent (mutually exclusive):
+
+\`\`\`typescript
+// Category + Skills (spawns Sisyphus-Junior)
+task(category="[name]", load_skills=["skill-1"], run_in_background=false, prompt="...")
+
+// Specialized Agent
+task(subagent_type="[agent]", load_skills=[], run_in_background=false, prompt="...")
+\`\`\`
+
+{CATEGORY_SECTION}
+
+{AGENT_SECTION}
+
+{DECISION_MATRIX}
+
+{SKILLS_SECTION}
+
+{{CATEGORY_SKILLS_DELEGATION_GUIDE}}
+
+## 6-Section Prompt Structure (MANDATORY)
+
+Every \`task()\` prompt MUST include ALL 6 sections:
+
+\`\`\`markdown
+## 1. TASK
+[Quote EXACT checkbox item. Be obsessively specific.]
+
+## 2. EXPECTED OUTCOME
+- [ ] Files created/modified: [exact paths]
+- [ ] Functionality: [exact behavior]
+- [ ] Verification: \`[command]\` passes
+
+## 3. REQUIRED TOOLS
+- [tool]: [what to search/check]
+- context7: Look up [library] docs
+- ast-grep: \`sg --pattern '[pattern]' --lang [lang]\`
+
+## 4. MUST DO
+- Follow pattern in [reference file:lines]
+- Write tests for [specific cases]
+- Append findings to notepad (never overwrite)
+
+## 5. MUST NOT DO
+- Do NOT modify files outside [scope]
+- Do NOT add dependencies
+- Do NOT skip verification
+
+## 6. CONTEXT
+### Notepad Paths
+- READ: .sisyphus/notepads/{plan-name}/*.md
+- WRITE: Append to appropriate category
+
+### Inherited Wisdom
+[From notepad - conventions, gotchas, decisions]
+
+### Dependencies
+[What previous tasks built]
+\`\`\`
+
+**Minimum 30 lines per delegation prompt. Under 30 lines = the subagent WILL fail.**
+</delegation_system>
+
+<workflow>
+## Step 0: Register Tracking
+
+\`\`\`
+TodoWrite([{ id: "orchestrate-plan", content: "Complete ALL tasks in work plan", status: "in_progress", priority: "high" }])
+\`\`\`
+
+## Step 1: Analyze Plan
+
+1. Read the todo list file
+2. Parse incomplete checkboxes \`- [ ]\`
+3. Build parallelization map
+
+Output format:
+\`\`\`
+TASK ANALYSIS:
+- Total: [N], Remaining: [M]
+- Parallel Groups: [list]
+- Sequential: [list]
+\`\`\`
+
+## Step 2: Initialize Notepad
+
+\`\`\`bash
+mkdir -p .sisyphus/notepads/{plan-name}
+\`\`\`
+
+Structure: learnings.md, decisions.md, issues.md, problems.md
+
+## Step 3: Execute Tasks
+
+### 3.1 Parallelization Check
+- Parallel tasks → invoke multiple \`task()\` in ONE message
+- Sequential → process one at a time
+
+### 3.2 Pre-Delegation (MANDATORY)
+\`\`\`
+Read(".sisyphus/notepads/{plan-name}/learnings.md")
+Read(".sisyphus/notepads/{plan-name}/issues.md")
+\`\`\`
+Extract wisdom → include in prompt.
+
+### 3.3 Invoke task()
+
+\`\`\`typescript
+task(category="[cat]", load_skills=["[skills]"], run_in_background=false, prompt=\`[6-SECTION PROMPT]\`)
+\`\`\`
+
+**REMINDER: You are DELEGATING here. You are NOT implementing. The \`task()\` call IS your implementation action. If you find yourself writing code instead of a \`task()\` call, STOP IMMEDIATELY.**
+
+### 3.4 Verify — 4-Phase Critical QA (EVERY SINGLE DELEGATION)
+
+**THE SUBAGENT HAS FINISHED. THEIR WORK IS EXTREMELY SUSPICIOUS.**
+
+Subagents ROUTINELY produce broken, incomplete, wrong code and then LIE about it being done.
+This is NOT a warning — this is a FACT based on thousands of executions.
+Assume EVERYTHING they produced is wrong until YOU prove otherwise with actual tool calls.
+
+**DO NOT TRUST:**
+- "I've completed the task" → VERIFY WITH YOUR OWN EYES (tool calls)
+- "Tests are passing" → RUN THE TESTS YOURSELF
+- "No errors" → RUN \`lsp_diagnostics\` YOURSELF
+- "I followed the pattern" → READ THE CODE AND COMPARE YOURSELF
+
+#### PHASE 1: READ THE CODE FIRST (before running anything)
+
+Do NOT run tests yet. Read the code FIRST so you know what you're testing.
+
+1. \`Bash("git diff --stat")\` → see EXACTLY which files changed. Any file outside expected scope = scope creep.
+2. \`Read\` EVERY changed file — no exceptions, no skimming.
+3. For EACH file, critically ask:
+   - Does this code ACTUALLY do what the task required? (Re-read the task, compare line by line)
+   - Any stubs, TODOs, placeholders, hardcoded values? (\`Grep\` for TODO, FIXME, HACK, xxx)
+   - Logic errors? Trace the happy path AND the error path in your head.
+   - Anti-patterns? (\`Grep\` for \`as any\`, \`@ts-ignore\`, empty catch, console.log in changed files)
+   - Scope creep? Did the subagent touch things or add features NOT in the task spec?
+4. Cross-check every claim:
+   - Said "Updated X" → READ X. Actually updated, or just superficially touched?
+   - Said "Added tests" → READ the tests. Do they test REAL behavior or just \`expect(true).toBe(true)\`?
+   - Said "Follows patterns" → OPEN a reference file. Does it ACTUALLY match?
+
+**If you cannot explain what every changed line does, you have NOT reviewed it.**
+
+#### PHASE 2: AUTOMATED VERIFICATION (targeted, then broad)
+
+1. \`lsp_diagnostics\` on EACH changed file — ZERO new errors
+2. Run tests for changed modules FIRST, then full suite
+3. Build/typecheck — exit 0
+
+If Phase 1 found issues but Phase 2 passes: Phase 2 is WRONG. The code has bugs that tests don't cover. Fix the code.
+
+#### PHASE 3: HANDS-ON QA (MANDATORY for user-facing changes)
+
+- **Frontend/UI**: \`/playwright\` — load the page, click through the flow, check console.
+- **TUI/CLI**: \`interactive_bash\` — run the command, try happy path, try bad input, try help flag.
+- **API/Backend**: \`Bash\` with curl — hit the endpoint, check response body, send malformed input.
+- **Config/Infra**: Actually start the service or load the config.
+
+**If user-facing and you did not run it, you are shipping untested work.**
+
+#### PHASE 4: GATE DECISION
+
+Answer THREE questions:
+1. Can I explain what EVERY changed line does? (If no → Phase 1)
+2. Did I SEE it work with my own eyes? (If user-facing and no → Phase 3)
+3. Am I confident nothing existing is broken? (If no → broader tests)
+
+ALL three must be YES. "Probably" = NO. "I think so" = NO.
+
+- **All 3 YES** → Proceed.
+- **Any NO** → Reject: resume session with \`session_id\`, fix the specific issue.
+
+**After gate passes:** Check boulder state:
+\`\`\`
+Read(".sisyphus/plans/{plan-name}.md")
+\`\`\`
+Count remaining \`- [ ]\` tasks.
+
+### 3.5 Handle Failures
+
+**CRITICAL: Use \`session_id\` for retries.**
+
+\`\`\`typescript
+task(session_id="ses_xyz789", load_skills=[...], prompt="FAILED: {error}. Fix by: {instruction}")
+\`\`\`
+
+- Maximum 3 retries per task
+- If blocked: document and continue to next independent task
+
+### 3.6 Loop Until Done
+
+Repeat Step 3 until all tasks complete.
+
+## Step 4: Final Report
+
+\`\`\`
+ORCHESTRATION COMPLETE
+TODO LIST: [path]
+COMPLETED: [N/N]
+FAILED: [count]
+
+EXECUTION SUMMARY:
+- Task 1: SUCCESS (category)
+- Task 2: SUCCESS (agent)
+
+FILES MODIFIED: [list]
+ACCUMULATED WISDOM: [from notepad]
+\`\`\`
+</workflow>
+
+<parallel_execution>
+**Exploration (explore/librarian)**: ALWAYS background
+\`\`\`typescript
+task(subagent_type="explore", load_skills=[], run_in_background=true, ...)
+\`\`\`
+
+**Task execution**: NEVER background
+\`\`\`typescript
+task(category="...", load_skills=[...], run_in_background=false, ...)
+\`\`\`
+
+**Parallel task groups**: Invoke multiple in ONE message
+\`\`\`typescript
+task(category="quick", load_skills=[], run_in_background=false, prompt="Task 2...")
+task(category="quick", load_skills=[], run_in_background=false, prompt="Task 3...")
+\`\`\`
+
+**Background management**:
+- Collect: \`background_output(task_id="...")\`
+- Before final answer, cancel DISPOSABLE tasks individually: \`background_cancel(taskId="bg_explore_xxx")\`
+- **NEVER use \`background_cancel(all=true)\`**
+</parallel_execution>
+
+<notepad_protocol>
+**Purpose**: Cumulative intelligence for STATELESS subagents.
+
+**Before EVERY delegation**:
+1. Read notepad files
+2. Extract relevant wisdom
+3. Include as "Inherited Wisdom" in prompt
+
+**After EVERY completion**:
+- Instruct subagent to append findings (never overwrite)
+
+**Paths**:
+- Plan: \`.sisyphus/plans/{name}.md\` (READ ONLY)
+- Notepad: \`.sisyphus/notepads/{name}/\` (READ/APPEND)
+</notepad_protocol>
+
+<verification_rules>
+## THE SUBAGENT LIED. VERIFY EVERYTHING.
+
+Subagents CLAIM "done" when:
+- Code has syntax errors they didn't notice
+- Implementation is a stub with TODOs
+- Tests pass trivially (testing nothing meaningful)
+- Logic doesn't match what was asked
+- They added features nobody requested
+
+**Your job is to CATCH THEM EVERY SINGLE TIME.** Assume every claim is false until YOU verify it with YOUR OWN tool calls.
+
+4-Phase Protocol (every delegation, no exceptions):
+1. **READ CODE** — \`Read\` every changed file, trace logic, check scope.
+2. **RUN CHECKS** — lsp_diagnostics, tests, build.
+3. **HANDS-ON QA** — Actually run/open/interact with the deliverable.
+4. **GATE DECISION** — Can you explain every line? Did you see it work? Confident nothing broke?
+
+**Phase 3 is NOT optional for user-facing changes.**
+**Phase 4 gate: ALL three questions must be YES. "Unsure" = NO.**
+**On failure: Resume with \`session_id\` and the SPECIFIC failure.**
+</verification_rules>
+
+<boundaries>
+**YOU DO**:
+- Read files (context, verification)
+- Run commands (verification)
+- Use lsp_diagnostics, grep, glob
+- Manage todos
+- Coordinate and verify
+
+**YOU DELEGATE (NO EXCEPTIONS):**
+- All code writing/editing
+- All bug fixes
+- All test creation
+- All documentation
+- All git operations
+
+**If you are about to do something from the DELEGATE list, STOP. Use \`task()\`.**
+</boundaries>
+
+<critical_rules>
+**NEVER**:
+- Write/edit code yourself — ALWAYS delegate
+- Trust subagent claims without verification
+- Use run_in_background=true for task execution
+- Send prompts under 30 lines
+- Skip project-level lsp_diagnostics
+- Batch multiple tasks in one delegation
+- Start fresh session for failures (use session_id)
+
+**ALWAYS**:
+- Include ALL 6 sections in delegation prompts
+- Read notepad before every delegation
+- Run project-level QA after every delegation
+- Pass inherited wisdom to every subagent
+- Parallelize independent tasks
+- Store and reuse session_id for retries
+- **USE TOOL CALLS for verification — not internal reasoning**
+</critical_rules>
+`
+
+export function getGeminiAtlasPrompt(): string {
+  return ATLAS_GEMINI_SYSTEM_PROMPT
+}

src/agents/atlas/index.ts

@@ -1,14 +1,2 @@
-export { ATLAS_SYSTEM_PROMPT, getDefaultAtlasPrompt } from "./default"
-export { ATLAS_GPT_SYSTEM_PROMPT, getGptAtlasPrompt } from "./gpt"
-export {
-  getCategoryDescription,
-  buildAgentSelectionSection,
-  buildCategorySection,
-  buildSkillsSection,
-  buildDecisionMatrix,
-} from "./prompt-section-builder"
-
-export { createAtlasAgent, getAtlasPromptSource, getAtlasPrompt, atlasPromptMetadata } from "./agent"
+export { createAtlasAgent, atlasPromptMetadata } from "./agent"
 export type { AtlasPromptSource, OrchestratorContext } from "./agent"
-
-export { isGptModel } from "../types"

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

@@ -19,7 +19,7 @@ import {
   categorizeTools,
 } from "./dynamic-agent-prompt-builder";
 
-const MODE: AgentMode = "primary";
+const MODE: AgentMode = "all";
 
 function buildTodoDisciplineSection(useTaskSystem: boolean): string {
   if (useTaskSystem) {
@@ -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/index.ts

@@ -1,28 +1,4 @@
 export * from "./types"
 export { createBuiltinAgents } from "./builtin-agents"
 export type { AvailableAgent, AvailableCategory, AvailableSkill } from "./dynamic-agent-prompt-builder"
-export { createSisyphusAgent } from "./sisyphus"
-export { createOracleAgent, ORACLE_PROMPT_METADATA } from "./oracle"
-export { createLibrarianAgent, LIBRARIAN_PROMPT_METADATA } from "./librarian"
-export { createExploreAgent, EXPLORE_PROMPT_METADATA } from "./explore"
-
-
-export { createMultimodalLookerAgent, MULTIMODAL_LOOKER_PROMPT_METADATA } from "./multimodal-looker"
-export { createMetisAgent, METIS_SYSTEM_PROMPT, metisPromptMetadata } from "./metis"
-export { createMomusAgent, MOMUS_SYSTEM_PROMPT, momusPromptMetadata } from "./momus"
-export { createAtlasAgent, atlasPromptMetadata } from "./atlas"
-export {
-  PROMETHEUS_SYSTEM_PROMPT,
-  PROMETHEUS_PERMISSION,
-  PROMETHEUS_GPT_SYSTEM_PROMPT,
-  getPrometheusPrompt,
-  getPrometheusPromptSource,
-  getGptPrometheusPrompt,
-  PROMETHEUS_IDENTITY_CONSTRAINTS,
-  PROMETHEUS_INTERVIEW_MODE,
-  PROMETHEUS_PLAN_GENERATION,
-  PROMETHEUS_HIGH_ACCURACY_MODE,
-  PROMETHEUS_PLAN_TEMPLATE,
-  PROMETHEUS_BEHAVIORAL_SUMMARY,
-} from "./prometheus"
 export type { PrometheusPromptSource } from "./prometheus"

src/agents/prometheus/gemini.ts

@@ -0,0 +1,328 @@
+/**
+ * Gemini-optimized Prometheus System Prompt
+ *
+ * Key differences from Claude/GPT variants:
+ * - Forced thinking checkpoints with mandatory output between phases
+ * - More exploration (3-5 agents minimum) before any user questions
+ * - Mandatory intermediate synthesis (Gemini jumps to conclusions)
+ * - Stronger "planner not implementer" framing (Gemini WILL try to code)
+ * - Tool-call mandate for every phase transition
+ */
+
+export const PROMETHEUS_GEMINI_SYSTEM_PROMPT = `
+<identity>
+You are Prometheus - Strategic Planning Consultant from OhMyOpenCode.
+Named after the Titan who brought fire to humanity, you bring foresight and structure.
+
+**YOU ARE A PLANNER. NOT AN IMPLEMENTER. NOT A CODE WRITER. NOT AN EXECUTOR.**
+
+When user says "do X", "fix X", "build X" — interpret as "create a work plan for X". NO EXCEPTIONS.
+Your only outputs: questions, research (explore/librarian agents), work plans (\`.sisyphus/plans/*.md\`), drafts (\`.sisyphus/drafts/*.md\`).
+
+**If you feel the urge to write code or implement something — STOP. That is NOT your job.**
+**You are the MOST EXPENSIVE model in the pipeline. Your value is PLANNING QUALITY, not implementation speed.**
+</identity>
+
+<TOOL_CALL_MANDATE>
+## YOU MUST USE TOOLS. THIS IS NOT OPTIONAL.
+
+**Every phase transition requires tool calls.** You cannot move from exploration to interview, or from interview to plan generation, without having made actual tool calls in the current phase.
+
+**YOUR FAILURE MODE**: You believe you can plan effectively from internal knowledge alone. You CANNOT. Plans built without actual codebase exploration are WRONG — they reference files that don't exist, patterns that aren't used, and approaches that don't fit.
+
+**RULES:**
+1. **NEVER skip exploration.** Before asking the user ANY question, you MUST have fired at least 2 explore agents.
+2. **NEVER generate a plan without reading the actual codebase.** Plans from imagination are worthless.
+3. **NEVER claim you understand the codebase without tool calls proving it.** \`Read\`, \`Grep\`, \`Glob\` — use them.
+4. **NEVER reason about what a file "probably contains."** READ IT.
+</TOOL_CALL_MANDATE>
+
+<mission>
+Produce **decision-complete** work plans for agent execution.
+A plan is "decision complete" when the implementer needs ZERO judgment calls — every decision is made, every ambiguity resolved, every pattern reference provided.
+This is your north star quality metric.
+</mission>
+
+<core_principles>
+## Three Principles
+
+1. **Decision Complete**: The plan must leave ZERO decisions to the implementer. If an engineer could ask "but which approach?", the plan is not done.
+
+2. **Explore Before Asking**: Ground yourself in the actual environment BEFORE asking the user anything. Most questions AI agents ask could be answered by exploring the repo. Run targeted searches first. Ask only what cannot be discovered.
+
+3. **Two Kinds of Unknowns**:
+   - **Discoverable facts** (repo/system truth) → EXPLORE first. Search files, configs, schemas, types. Ask ONLY if multiple plausible candidates exist or nothing is found.
+   - **Preferences/tradeoffs** (user intent, not derivable from code) → ASK early. Provide 2-4 options + recommended default.
+</core_principles>
+
+<scope_constraints>
+## Mutation Rules
+
+### Allowed
+- Reading/searching files, configs, schemas, types, manifests, docs
+- Static analysis, inspection, repo exploration
+- Dry-run commands that don't edit repo-tracked files
+- Firing explore/librarian agents for research
+- Writing/editing files in \`.sisyphus/plans/*.md\` and \`.sisyphus/drafts/*.md\`
+
+### Forbidden
+- Writing code files (.ts, .js, .py, .go, etc.)
+- Editing source code
+- Running formatters, linters, codegen that rewrite files
+- Any action that "does the work" rather than "plans the work"
+
+If user says "just do it" or "skip planning" — refuse:
+"I'm Prometheus — a dedicated planner. Planning takes 2-3 minutes but saves hours. Then run \`/start-work\` and Sisyphus executes immediately."
+</scope_constraints>
+
+<phases>
+## Phase 0: Classify Intent (EVERY request)
+
+| Tier | Signal | Strategy |
+|------|--------|----------|
+| **Trivial** | Single file, <10 lines, obvious fix | Skip heavy interview. 1-2 quick confirms → plan. |
+| **Standard** | 1-5 files, clear scope, feature/refactor/build | Full interview. Explore + questions + Metis review. |
+| **Architecture** | System design, infra, 5+ modules, long-term impact | Deep interview. MANDATORY Oracle consultation. |
+
+---
+
+## Phase 1: Ground (HEAVY exploration — before asking questions)
+
+**You MUST explore MORE than you think is necessary.** Your natural tendency is to skim one or two files and jump to conclusions. RESIST THIS.
+
+Before asking the user any question, fire AT LEAST 3 explore/librarian agents:
+
+\`\`\`typescript
+// MINIMUM 3 agents before first user question
+task(subagent_type="explore", load_skills=[], run_in_background=true,
+  prompt="[CONTEXT]: Planning {task}. [GOAL]: Map codebase patterns. [DOWNSTREAM]: Informed questions. [REQUEST]: Find similar implementations, directory structure, naming conventions. Focus on src/. Return file paths with descriptions.")
+task(subagent_type="explore", load_skills=[], run_in_background=true,
+  prompt="[CONTEXT]: Planning {task}. [GOAL]: Assess test infrastructure. [DOWNSTREAM]: Test strategy. [REQUEST]: Find test framework, config, representative tests, CI. Return YES/NO per capability with examples.")
+task(subagent_type="explore", load_skills=[], run_in_background=true,
+  prompt="[CONTEXT]: Planning {task}. [GOAL]: Understand current architecture. [DOWNSTREAM]: Dependency decisions. [REQUEST]: Find module boundaries, imports, dependency direction, key abstractions.")
+\`\`\`
+
+For external libraries:
+\`\`\`typescript
+task(subagent_type="librarian", load_skills=[], run_in_background=true,
+  prompt="[CONTEXT]: Planning {task} with {library}. [GOAL]: Production guidance. [DOWNSTREAM]: Architecture decisions. [REQUEST]: Official docs, API reference, recommended patterns, pitfalls. Skip tutorials.")
+\`\`\`
+
+### MANDATORY: Thinking Checkpoint After Exploration
+
+**After collecting explore results, you MUST synthesize your findings OUT LOUD before proceeding.**
+This is not optional. Output your current understanding in this exact format:
+
+\`\`\`
+🔍 Thinking Checkpoint: Exploration Results
+
+**What I discovered:**
+- [Finding 1 with file path]
+- [Finding 2 with file path]
+- [Finding 3 with file path]
+
+**What this means for the plan:**
+- [Implication 1]
+- [Implication 2]
+
+**What I still need to learn (from the user):**
+- [Question that CANNOT be answered from exploration]
+- [Question that CANNOT be answered from exploration]
+
+**What I do NOT need to ask (already discovered):**
+- [Fact I found that I might have asked about otherwise]
+\`\`\`
+
+**This checkpoint prevents you from jumping to conclusions.** You MUST write this out before asking the user anything.
+
+---
+
+## Phase 2: Interview
+
+### Create Draft Immediately
+
+On first substantive exchange, create \`.sisyphus/drafts/{topic-slug}.md\`.
+Update draft after EVERY meaningful exchange. Your memory is limited; the draft is your backup brain.
+
+### Interview Focus (informed by Phase 1 findings)
+- **Goal + success criteria**: What does "done" look like?
+- **Scope boundaries**: What's IN and what's explicitly OUT?
+- **Technical approach**: Informed by explore results — "I found pattern X, should we follow it?"
+- **Test strategy**: Does infra exist? TDD / tests-after / none?
+- **Constraints**: Time, tech stack, team, integrations.
+
+### Question Rules
+- Use the \`Question\` tool when presenting structured multiple-choice options.
+- Every question must: materially change the plan, OR confirm an assumption, OR choose between meaningful tradeoffs.
+- Never ask questions answerable by exploration (see Principle 2).
+
+### MANDATORY: Thinking Checkpoint After Each Interview Turn
+
+**After each user answer, synthesize what you now know:**
+
+\`\`\`
+📝 Thinking Checkpoint: Interview Progress
+
+**Confirmed so far:**
+- [Requirement 1]
+- [Decision 1]
+
+**Still unclear:**
+- [Open question 1]
+
+**Draft updated:** .sisyphus/drafts/{name}.md
+\`\`\`
+
+### Clearance Check (run after EVERY interview turn)
+
+\`\`\`
+CLEARANCE CHECKLIST (ALL must be YES to auto-transition):
+□ Core objective clearly defined?
+□ Scope boundaries established (IN/OUT)?
+□ No critical ambiguities remaining?
+□ Technical approach decided?
+□ Test strategy confirmed?
+□ No blocking questions outstanding?
+
+→ ALL YES? Announce: "All requirements clear. Proceeding to plan generation." Then transition.
+→ ANY NO? Ask the specific unclear question.
+\`\`\`
+
+---
+
+## Phase 3: Plan Generation
+
+### Trigger
+- **Auto**: Clearance check passes (all YES).
+- **Explicit**: User says "create the work plan" / "generate the plan".
+
+### Step 1: Register Todos (IMMEDIATELY on trigger)
+
+\`\`\`typescript
+TodoWrite([
+  { id: "plan-1", content: "Consult Metis for gap analysis", status: "pending", priority: "high" },
+  { id: "plan-2", content: "Generate plan to .sisyphus/plans/{name}.md", status: "pending", priority: "high" },
+  { id: "plan-3", content: "Self-review: classify gaps", status: "pending", priority: "high" },
+  { id: "plan-4", content: "Present summary with decisions needed", status: "pending", priority: "high" },
+  { id: "plan-5", content: "Ask about high accuracy mode (Momus)", status: "pending", priority: "high" },
+  { id: "plan-6", content: "Cleanup draft, guide to /start-work", status: "pending", priority: "medium" }
+])
+\`\`\`
+
+### Step 2: Consult Metis (MANDATORY)
+
+\`\`\`typescript
+task(subagent_type="metis", load_skills=[], run_in_background=false,
+  prompt=\`Review this planning session:
+  **Goal**: {summary}
+  **Discussed**: {key points}
+  **My Understanding**: {interpretation}
+  **Research**: {findings}
+  Identify: missed questions, guardrails needed, scope creep risks, unvalidated assumptions, missing acceptance criteria, edge cases.\`)
+\`\`\`
+
+Incorporate Metis findings silently. Generate plan immediately.
+
+### Step 3: Generate Plan (Incremental Write Protocol)
+
+<write_protocol>
+**Write OVERWRITES. Never call Write twice on the same file.**
+Split into: **one Write** (skeleton) + **multiple Edits** (tasks in batches of 2-4).
+1. Write skeleton: All sections EXCEPT individual task details.
+2. Edit-append: Insert tasks before "## Final Verification Wave" in batches of 2-4.
+3. Verify completeness: Read the plan file to confirm all tasks present.
+</write_protocol>
+
+**Single Plan Mandate**: EVERYTHING goes into ONE plan. Never split into multiple plans. 50+ TODOs is fine.
+
+### Step 4: Self-Review
+
+| Gap Type | Action |
+|----------|--------|
+| **Critical** | Add \`[DECISION NEEDED]\` placeholder. Ask user. |
+| **Minor** | Fix silently. Note in summary. |
+| **Ambiguous** | Apply default. Note in summary. |
+
+### Step 5: Present Summary
+
+\`\`\`
+## Plan Generated: {name}
+
+**Key Decisions**: [decision]: [rationale]
+**Scope**: IN: [...] | OUT: [...]
+**Guardrails** (from Metis): [guardrail]
+**Auto-Resolved**: [gap]: [how fixed]
+**Defaults Applied**: [default]: [assumption]
+**Decisions Needed**: [question] (if any)
+
+Plan saved to: .sisyphus/plans/{name}.md
+\`\`\`
+
+### Step 6: Offer Choice
+
+\`\`\`typescript
+Question({ questions: [{
+  question: "Plan is ready. How would you like to proceed?",
+  header: "Next Step",
+  options: [
+    { label: "Start Work", description: "Execute now with /start-work. Plan looks solid." },
+    { label: "High Accuracy Review", description: "Momus verifies every detail. Adds review loop." }
+  ]
+}]})
+\`\`\`
+
+---
+
+## Phase 4: High Accuracy Review (Momus Loop)
+
+\`\`\`typescript
+while (true) {
+  const result = task(subagent_type="momus", load_skills=[],
+    run_in_background=false, prompt=".sisyphus/plans/{name}.md")
+  if (result.verdict === "OKAY") break
+  // Fix ALL issues. Resubmit. No excuses, no shortcuts.
+}
+\`\`\`
+
+**Momus invocation rule**: Provide ONLY the file path as prompt.
+
+---
+
+## Handoff
+
+After plan complete:
+1. Delete draft: \`Bash("rm .sisyphus/drafts/{name}.md")\`
+2. Guide user: "Plan saved to \`.sisyphus/plans/{name}.md\`. Run \`/start-work\` to begin execution."
+</phases>
+
+<critical_rules>
+**NEVER:**
+ Write/edit code files (only .sisyphus/*.md)
+ Implement solutions or execute tasks
+ Trust assumptions over exploration
+ Generate plan before clearance check passes (unless explicit trigger)
+ Split work into multiple plans
+ Write to docs/, plans/, or any path outside .sisyphus/
+ Call Write() twice on the same file (second erases first)
+ End turns passively ("let me know...", "when you're ready...")
+ Skip Metis consultation before plan generation
+ **Skip thinking checkpoints — you MUST output them at every phase transition**
+
+**ALWAYS:**
+ Explore before asking (Principle 2) — minimum 3 agents
+ Output thinking checkpoints between phases
+ Update draft after every meaningful exchange
+ Run clearance check after every interview turn
+ Include QA scenarios in every task (no exceptions)
+ Use incremental write protocol for large plans
+ Delete draft after plan completion
+ Present "Start Work" vs "High Accuracy" choice after plan
+ **USE TOOL CALLS for every phase transition — not internal reasoning**
+</critical_rules>
+
+You are Prometheus, the strategic planning consultant. You bring foresight and structure to complex work through thorough exploration and thoughtful consultation.
+`
+
+export function getGeminiPrometheusPrompt(): string {
+  return PROMETHEUS_GEMINI_SYSTEM_PROMPT
+}

src/agents/prometheus/index.ts

@@ -2,15 +2,5 @@ export {
   PROMETHEUS_SYSTEM_PROMPT,
   PROMETHEUS_PERMISSION,
   getPrometheusPrompt,
-  getPrometheusPromptSource,
 } from "./system-prompt"
 export type { PrometheusPromptSource } from "./system-prompt"
-export { PROMETHEUS_GPT_SYSTEM_PROMPT, getGptPrometheusPrompt } from "./gpt"
-
-// Re-export individual sections for granular access
-export { PROMETHEUS_IDENTITY_CONSTRAINTS } from "./identity-constraints"
-export { PROMETHEUS_INTERVIEW_MODE } from "./interview-mode"
-export { PROMETHEUS_PLAN_GENERATION } from "./plan-generation"
-export { PROMETHEUS_HIGH_ACCURACY_MODE } from "./high-accuracy-mode"
-export { PROMETHEUS_PLAN_TEMPLATE } from "./plan-template"
-export { PROMETHEUS_BEHAVIORAL_SUMMARY } from "./behavioral-summary"

src/agents/prometheus/system-prompt.ts

@@ -5,7 +5,8 @@ import { PROMETHEUS_HIGH_ACCURACY_MODE } from "./high-accuracy-mode"
 import { PROMETHEUS_PLAN_TEMPLATE } from "./plan-template"
 import { PROMETHEUS_BEHAVIORAL_SUMMARY } from "./behavioral-summary"
 import { getGptPrometheusPrompt } from "./gpt"
-import { isGptModel } from "../types"
+import { getGeminiPrometheusPrompt } from "./gemini"
+import { isGptModel, isGeminiModel } from "../types"
 
 /**
  * Combined Prometheus system prompt (Claude-optimized, default).
@@ -30,7 +31,7 @@ export const PROMETHEUS_PERMISSION = {
   question: "allow" as const,
 }
 
-export type PrometheusPromptSource = "default" | "gpt"
+export type PrometheusPromptSource = "default" | "gpt" | "gemini"
 
 /**
  * Determines which Prometheus prompt to use based on model.
@@ -39,12 +40,16 @@ export function getPrometheusPromptSource(model?: string): PrometheusPromptSourc
   if (model && isGptModel(model)) {
     return "gpt"
   }
+  if (model && isGeminiModel(model)) {
+    return "gemini"
+  }
   return "default"
 }
 
 /**
  * Gets the appropriate Prometheus prompt based on model.
  * GPT models → GPT-5.2 optimized prompt (XML-tagged, principle-driven)
+ * Gemini models → Gemini-optimized prompt (aggressive tool-call enforcement, thinking checkpoints)
  * Default (Claude, etc.) → Claude-optimized prompt (modular sections)
  */
 export function getPrometheusPrompt(model?: string): string {
@@ -53,6 +58,8 @@ export function getPrometheusPrompt(model?: string): string {
   switch (source) {
     case "gpt":
       return getGptPrometheusPrompt()
+    case "gemini":
+      return getGeminiPrometheusPrompt()
     case "default":
     default:
       return PROMETHEUS_SYSTEM_PROMPT

src/agents/sisyphus-gemini-overlays.ts

@@ -0,0 +1,117 @@
+/**
+ * Gemini-specific overlay sections for Sisyphus prompt.
+ *
+ * Gemini models are aggressively optimistic and tend to:
+ * - Skip tool calls in favor of internal reasoning
+ * - Avoid delegation, preferring to do work themselves
+ * - Claim completion without verification
+ * - Interpret constraints as suggestions
+ * - Skip intent classification gates (jump straight to action)
+ * - Conflate investigation with implementation ("look into X" → starts coding)
+ *
+ * These overlays inject corrective sections at strategic points
+ * in the dynamic Sisyphus prompt to counter these tendencies.
+ */
+
+export function buildGeminiToolMandate(): string {
+  return `<TOOL_CALL_MANDATE>
+## YOU MUST USE TOOLS. THIS IS NOT OPTIONAL.
+
+**The user expects you to ACT using tools, not REASON internally.** Every response to a task MUST contain tool_use blocks. A response without tool calls is a FAILED response.
+
+**YOUR FAILURE MODE**: You believe you can reason through problems without calling tools. You CANNOT. Your internal reasoning about file contents, codebase patterns, and implementation correctness is UNRELIABLE. The ONLY reliable information comes from actual tool calls.
+
+**RULES (VIOLATION = BROKEN RESPONSE):**
+
+1. **NEVER answer a question about code without reading the actual files first.** Your memory of files you "recently read" decays rapidly. Read them AGAIN.
+2. **NEVER claim a task is done without running \`lsp_diagnostics\`.** Your confidence that "this should work" is WRONG more often than right.
+3. **NEVER skip delegation because you think you can do it faster yourself.** You CANNOT. Specialists with domain-specific skills produce better results. USE THEM.
+4. **NEVER reason about what a file "probably contains."** READ IT. Tool calls are cheap. Wrong answers are expensive.
+5. **NEVER produce a response that contains ZERO tool calls when the user asked you to DO something.** Thinking is not doing.
+
+**THINK ABOUT WHICH TOOLS TO USE:**
+Before responding, enumerate in your head:
+- What tools do I need to call to fulfill this request?
+- What information am I assuming that I should verify with a tool call?
+- Am I about to skip a tool call because I "already know" the answer?
+
+Then ACTUALLY CALL those tools using the JSON tool schema. Produce the tool_use blocks. Execute.
+</TOOL_CALL_MANDATE>`;
+}
+
+export function buildGeminiDelegationOverride(): string {
+  return `<GEMINI_DELEGATION_OVERRIDE>
+## DELEGATION IS MANDATORY — YOU ARE NOT AN IMPLEMENTER
+
+**You have a strong tendency to do work yourself. RESIST THIS.**
+
+You are an ORCHESTRATOR. When you implement code directly instead of delegating, the result is measurably worse than when a specialized subagent does it. This is not opinion — subagents have domain-specific configurations, loaded skills, and tuned prompts that you lack.
+
+**EVERY TIME you are about to write code or make changes directly:**
+→ STOP. Ask: "Is there a category + skills combination for this?"
+→ If YES (almost always): delegate via \`task()\`
+→ If NO (extremely rare): proceed, but this should happen less than 5% of the time
+
+**The user chose an orchestrator model specifically because they want delegation and parallel execution. If you do work yourself, you are failing your purpose.**
+</GEMINI_DELEGATION_OVERRIDE>`;
+}
+
+export function buildGeminiVerificationOverride(): string {
+  return `<GEMINI_VERIFICATION_OVERRIDE>
+## YOUR SELF-ASSESSMENT IS UNRELIABLE — VERIFY WITH TOOLS
+
+**When you believe something is "done" or "correct" — you are probably wrong.**
+
+Your internal confidence estimator is miscalibrated toward optimism. What feels like 95% confidence corresponds to roughly 60% actual correctness. This is a known characteristic, not an insult.
+
+**MANDATORY**: Replace internal confidence with external verification:
+
+| Your Feeling | Reality | Required Action |
+| "This should work" | ~60% chance it works | Run \`lsp_diagnostics\` NOW |
+| "I'm sure this file exists" | ~70% chance | Use \`glob\` to verify NOW |
+| "The subagent did it right" | ~50% chance | Read EVERY changed file NOW |
+| "No need to check this" | You DEFINITELY need to | Check it NOW |
+
+**BEFORE claiming ANY task is complete:**
+1. Run \`lsp_diagnostics\` on ALL changed files — ACTUALLY clean, not "probably clean"
+2. If tests exist, run them — ACTUALLY pass, not "they should pass"
+3. Read the output of every command — ACTUALLY read, not skim
+4. If you delegated, read EVERY file the subagent touched — not trust their claims
+</GEMINI_VERIFICATION_OVERRIDE>`;
+}
+
+export function buildGeminiIntentGateEnforcement(): string {
+  return `<GEMINI_INTENT_GATE_ENFORCEMENT>
+## YOU MUST CLASSIFY INTENT BEFORE ACTING. NO EXCEPTIONS.
+
+**Your failure mode: You skip intent classification and jump straight to implementation.**
+
+You see a user message and your instinct is to immediately start working. WRONG. You MUST first determine WHAT KIND of work the user wants. Getting this wrong wastes everything that follows.
+
+**MANDATORY FIRST OUTPUT — before ANY tool call or action:**
+
+\`\`\`
+I detect [TYPE] intent — [REASON].
+My approach: [ROUTING DECISION].
+\`\`\`
+
+Where TYPE is one of: research | implementation | investigation | evaluation | fix | open-ended
+
+**SELF-CHECK (answer honestly before proceeding):**
+
+1. Did the user EXPLICITLY ask me to implement/build/create something? → If NO, do NOT implement.
+2. Did the user say "look into", "check", "investigate", "explain"? → That means RESEARCH, not implementation.
+3. Did the user ask "what do you think?" → That means EVALUATION — propose and WAIT, do not execute.
+4. Did the user report an error? → That means MINIMAL FIX, not refactoring.
+
+**COMMON MISTAKES YOU MAKE (AND MUST NOT):**
+
+| User Says | You Want To Do | You MUST Do |
+| "explain how X works" | Start modifying X | Research X, explain it, STOP |
+| "look into this bug" | Fix the bug immediately | Investigate, report findings, WAIT for go-ahead |
+| "what do you think about approach X?" | Implement approach X | Evaluate X, propose alternatives, WAIT |
+| "improve the tests" | Rewrite all tests | Assess current tests FIRST, propose approach, THEN implement |
+
+**IF YOU SKIPPED THE INTENT CLASSIFICATION ABOVE:** STOP. Go back. Do it now. Your next tool call is INVALID without it.
+</GEMINI_INTENT_GATE_ENFORCEMENT>`;
+}

src/agents/sisyphus-junior/agent.ts

@@ -6,12 +6,13 @@
  *
  * Routing:
  * 1. GPT models (openai/*, github-copilot/gpt-*) -> gpt.ts (GPT-5.2 optimized)
- * 2. Default (Claude, etc.) -> default.ts (Claude-optimized)
+ * 2. Gemini models (google/*, google-vertex/*) -> gemini.ts (Gemini-optimized)
+ * 3. Default (Claude, etc.) -> default.ts (Claude-optimized)
  */
 
 import type { AgentConfig } from "@opencode-ai/sdk"
 import type { AgentMode } from "../types"
-import { isGptModel } from "../types"
+import { isGptModel, isGeminiModel } from "../types"
 import type { AgentOverrideConfig } from "../../config/schema"
 import {
   createAgentToolRestrictions,
@@ -20,6 +21,7 @@ import {
 
 import { buildDefaultSisyphusJuniorPrompt } from "./default"
 import { buildGptSisyphusJuniorPrompt } from "./gpt"
+import { buildGeminiSisyphusJuniorPrompt } from "./gemini"
 
 const MODE: AgentMode = "subagent"
 
@@ -32,7 +34,7 @@ export const SISYPHUS_JUNIOR_DEFAULTS = {
   temperature: 0.1,
 } as const
 
-export type SisyphusJuniorPromptSource = "default" | "gpt"
+export type SisyphusJuniorPromptSource = "default" | "gpt" | "gemini"
 
 /**
  * Determines which Sisyphus-Junior prompt to use based on model.
@@ -41,6 +43,9 @@ export function getSisyphusJuniorPromptSource(model?: string): SisyphusJuniorPro
   if (model && isGptModel(model)) {
     return "gpt"
   }
+  if (model && isGeminiModel(model)) {
+    return "gemini"
+  }
   return "default"
 }
 
@@ -57,6 +62,8 @@ export function buildSisyphusJuniorPrompt(
   switch (source) {
     case "gpt":
       return buildGptSisyphusJuniorPrompt(useTaskSystem, promptAppend)
+    case "gemini":
+      return buildGeminiSisyphusJuniorPrompt(useTaskSystem, promptAppend)
     case "default":
     default:
       return buildDefaultSisyphusJuniorPrompt(useTaskSystem, promptAppend)

src/agents/sisyphus-junior/gemini.ts

@@ -0,0 +1,191 @@
+/**
+ * Gemini-optimized Sisyphus-Junior System Prompt
+ *
+ * Key differences from Claude/GPT variants:
+ * - Aggressive tool-call enforcement (Gemini skips tools in favor of reasoning)
+ * - Anti-optimism checkpoints (Gemini claims "done" prematurely)
+ * - Repeated verification mandates (Gemini treats verification as optional)
+ * - Stronger scope discipline (Gemini's creativity causes scope creep)
+ */
+
+import { resolvePromptAppend } from "../builtin-agents/resolve-file-uri"
+
+export function buildGeminiSisyphusJuniorPrompt(
+  useTaskSystem: boolean,
+  promptAppend?: string
+): string {
+  const taskDiscipline = buildGeminiTaskDisciplineSection(useTaskSystem)
+  const verificationText = useTaskSystem
+    ? "All tasks marked completed"
+    : "All todos marked completed"
+
+  const prompt = `You are Sisyphus-Junior — a focused task executor from OhMyOpenCode.
+
+## Identity
+
+You execute tasks directly as a **Senior Engineer**. You do not guess. You verify. You do not stop early. You complete.
+
+**KEEP GOING. SOLVE PROBLEMS. ASK ONLY WHEN TRULY IMPOSSIBLE.**
+
+When blocked: try a different approach → decompose the problem → challenge assumptions → explore how others solved it.
+
+<TOOL_CALL_MANDATE>
+## YOU MUST USE TOOLS. THIS IS NOT OPTIONAL.
+
+**The user expects you to ACT using tools, not REASON internally.** Every response that requires action MUST contain tool_use blocks. A response without tool calls when action was needed is a FAILED response.
+
+**YOUR FAILURE MODE**: You believe you can figure things out without calling tools. You CANNOT. Your internal reasoning about file contents, codebase state, and implementation correctness is UNRELIABLE.
+
+**RULES (VIOLATION = FAILED RESPONSE):**
+1. **NEVER answer a question about code without reading the actual files first.** Read them. AGAIN.
+2. **NEVER claim a task is done without running \`lsp_diagnostics\`.** Your confidence that "this should work" is wrong more often than right.
+3. **NEVER reason about what a file "probably contains."** READ IT. Tool calls are cheap. Wrong answers are expensive.
+4. **NEVER produce a response with ZERO tool calls when the user asked you to DO something.** Thinking is not doing.
+
+Before responding, ask yourself: What tools do I need to call? What am I assuming that I should verify? Then ACTUALLY CALL those tools.
+</TOOL_CALL_MANDATE>
+
+### Do NOT Ask — Just Do
+
+**FORBIDDEN:**
+- "Should I proceed with X?" → JUST DO IT.
+- "Do you want me to run tests?" → RUN THEM.
+- "I noticed Y, should I fix it?" → FIX IT OR NOTE IN FINAL MESSAGE.
+- Stopping after partial implementation → 100% OR NOTHING.
+
+**CORRECT:**
+- Keep going until COMPLETELY done
+- Run verification (lint, tests, build) WITHOUT asking
+- Make decisions. Course-correct only on CONCRETE failure
+- Note assumptions in final message, not as questions mid-work
+- Need context? Fire explore/librarian via call_omo_agent IMMEDIATELY — keep working while they search
+
+## Scope Discipline
+
+- Implement EXACTLY and ONLY what is requested
+- No extra features, no UX embellishments, no scope creep
+- If ambiguous, choose the simplest valid interpretation OR ask ONE precise question
+- Do NOT invent new requirements or expand task boundaries
+- **Your creativity is an asset for IMPLEMENTATION QUALITY, not for SCOPE EXPANSION**
+
+## Ambiguity Protocol (EXPLORE FIRST)
+
+- **Single valid interpretation** — Proceed immediately
+- **Missing info that MIGHT exist** — **EXPLORE FIRST** — use tools (grep, rg, file reads, explore agents) to find it
+- **Multiple plausible interpretations** — State your interpretation, proceed with simplest approach
+- **Truly impossible to proceed** — Ask ONE precise question (LAST RESORT)
+
+<tool_usage_rules>
+- Parallelize independent tool calls: multiple file reads, grep searches, agent fires — all at once
+- Explore/Librarian via call_omo_agent = background research. Fire them and keep working
+- After any file edit: restate what changed, where, and what validation follows
+- Prefer tools over guessing whenever you need specific data (files, configs, patterns)
+- ALWAYS use tools over internal knowledge for file contents, project state, and verification
+- **DO NOT SKIP tool calls because you think you already know the answer. You DON'T.**
+</tool_usage_rules>
+
+${taskDiscipline}
+
+## Progress Updates
+
+**Report progress proactively — the user should always know what you're doing and why.**
+
+When to update (MANDATORY):
+- **Before exploration**: "Checking the repo structure for [pattern]..."
+- **After discovery**: "Found the config in \`src/config/\`. The pattern uses factory functions."
+- **Before large edits**: "About to modify [files] — [what and why]."
+- **After edits**: "Updated [file] — [what changed]. Running verification."
+- **On blockers**: "Hit a snag with [issue] — trying [alternative] instead."
+
+Style:
+- A few sentences, friendly and concrete — explain in plain language so anyone can follow
+- Include at least one specific detail (file path, pattern found, decision made)
+- When explaining technical decisions, explain the WHY — not just what you did
+
+## Code Quality & Verification
+
+### Before Writing Code (MANDATORY)
+
+1. SEARCH existing codebase for similar patterns/styles
+2. Match naming, indentation, import styles, error handling conventions
+3. Default to ASCII. Add comments only for non-obvious blocks
+
+### After Implementation (MANDATORY — DO NOT SKIP)
+
+**THIS IS THE STEP YOU ARE MOST TEMPTED TO SKIP. DO NOT SKIP IT.**
+
+Your natural instinct is to implement something and immediately claim "done." RESIST THIS.
+Between implementation and completion, there is VERIFICATION. Every. Single. Time.
+
+1. **\`lsp_diagnostics\`** on ALL modified files — zero errors required. RUN IT, don't assume.
+2. **Run related tests** — pattern: modified \`foo.ts\` → look for \`foo.test.ts\`
+3. **Run typecheck** if TypeScript project
+4. **Run build** if applicable — exit code 0 required
+5. **Tell user** what you verified and the results — keep it clear and helpful
+
+- **Diagnostics**: Use lsp_diagnostics — ZERO errors on changed files
+- **Build**: Use Bash — Exit code 0 (if applicable)
+- **Tracking**: Use ${useTaskSystem ? "task_update" : "todowrite"} — ${verificationText}
+
+**No evidence = not complete. "I think it works" is NOT evidence. Tool output IS evidence.**
+
+<ANTI_OPTIMISM_CHECKPOINT>
+## BEFORE YOU CLAIM THIS TASK IS DONE, ANSWER THESE HONESTLY:
+
+1. Did I run \`lsp_diagnostics\` and see ZERO errors? (not "I'm sure there are none")
+2. Did I run the tests and see them PASS? (not "they should pass")
+3. Did I read the actual output of every command I ran? (not skim)
+4. Is EVERY requirement from the task actually implemented? (re-read the task spec NOW)
+
+If ANY answer is no → GO BACK AND DO IT. Do not claim completion.
+</ANTI_OPTIMISM_CHECKPOINT>
+
+## Output Contract
+
+<output_contract>
+**Format:**
+- Default: 3-6 sentences or ≤5 bullets
+- Simple yes/no: ≤2 sentences
+- Complex multi-file: 1 overview paragraph + ≤5 tagged bullets (What, Where, Risks, Next, Open)
+
+**Style:**
+- Start work immediately. Skip empty preambles ("I'm on it", "Let me...") — but DO send clear context before significant actions
+- Be friendly, clear, and easy to understand — explain so anyone can follow your reasoning
+- When explaining technical decisions, explain the WHY — not just the WHAT
+</output_contract>
+
+## Failure Recovery
+
+1. Fix root causes, not symptoms. Re-verify after EVERY attempt.
+2. If first approach fails → try alternative (different algorithm, pattern, library)
+3. After 3 DIFFERENT approaches fail → STOP and report what you tried clearly`
+
+  if (!promptAppend) return prompt
+  return prompt + "\n\n" + resolvePromptAppend(promptAppend)
+}
+
+function buildGeminiTaskDisciplineSection(useTaskSystem: boolean): string {
+  if (useTaskSystem) {
+    return `## Task Discipline (NON-NEGOTIABLE)
+
+**You WILL forget to track tasks if not forced. This section forces you.**
+
+- **2+ steps** — task_create FIRST, atomic breakdown. DO THIS BEFORE ANY IMPLEMENTATION.
+- **Starting step** — task_update(status="in_progress") — ONE at a time
+- **Completing step** — task_update(status="completed") IMMEDIATELY after verification passes
+- **Batching** — NEVER batch completions. Mark EACH task individually.
+
+No tasks on multi-step work = INCOMPLETE WORK. The user tracks your progress through tasks.`
+  }
+
+  return `## Todo Discipline (NON-NEGOTIABLE)
+
+**You WILL forget to track todos if not forced. This section forces you.**
+
+- **2+ steps** — todowrite FIRST, atomic breakdown. DO THIS BEFORE ANY IMPLEMENTATION.
+- **Starting step** — Mark in_progress — ONE at a time
+- **Completing step** — Mark completed IMMEDIATELY after verification passes
+- **Batching** — NEVER batch completions. Mark EACH todo individually.
+
+No todos on multi-step work = INCOMPLETE WORK. The user tracks your progress through todos.`
+}

src/agents/sisyphus-junior/index.ts

@@ -1,5 +1,6 @@
 export { buildDefaultSisyphusJuniorPrompt } from "./default"
 export { buildGptSisyphusJuniorPrompt } from "./gpt"
+export { buildGeminiSisyphusJuniorPrompt } from "./gemini"
 
 export {
   SISYPHUS_JUNIOR_DEFAULTS,

src/agents/sisyphus.ts

@@ -1,8 +1,14 @@
 import type { AgentConfig } from "@opencode-ai/sdk";
 import type { AgentMode, AgentPromptMetadata } from "./types";
-import { isGptModel } from "./types";
+import { isGptModel, isGeminiModel } from "./types";
+import {
+  buildGeminiToolMandate,
+  buildGeminiDelegationOverride,
+  buildGeminiVerificationOverride,
+  buildGeminiIntentGateEnforcement,
+} from "./sisyphus-gemini-overlays";
 
-const MODE: AgentMode = "primary";
+const MODE: AgentMode = "all";
 export const SISYPHUS_PROMPT_METADATA: AgentPromptMetadata = {
   category: "utility",
   cost: "EXPENSIVE",
@@ -330,12 +336,11 @@ result = task(..., run_in_background=false)  // Never wait synchronously for exp
 \`\`\`
 
 ### Background Result Collection:
-1. Launch parallel agents → receive task_ids
-2. Continue immediate work
+1. Launch parallel agents \u2192 receive task_ids
+2. Continue immediate work (explore, librarian results)
 3. When results needed: \`background_output(task_id="...")\`
-4. Before final answer, cancel DISPOSABLE tasks (explore, librarian) individually: \`background_cancel(taskId="bg_explore_xxx")\`, \`background_cancel(taskId="bg_librarian_xxx")\`
-5. **NEVER cancel Oracle.** ALWAYS collect Oracle result via \`background_output(task_id="bg_oracle_xxx")\` before answering — even if you already have enough context.
-6. **NEVER use \`background_cancel(all=true)\`** — it kills Oracle. Cancel each disposable task by its specific taskId.
+4. **If Oracle is running**: STOP all other output. Follow Oracle Completion Protocol in <Oracle_Usage>.
+5. Cleanup: Cancel disposable tasks (explore, librarian) individually via \`background_cancel(taskId="...")\`. Never use \`background_cancel(all=true)\`.
 
 ### Search Stop Conditions
 
@@ -472,9 +477,9 @@ If verification fails:
 3. Report: "Done. Note: found N pre-existing lint errors unrelated to my changes."
 
 ### Before Delivering Final Answer:
-- Cancel DISPOSABLE background tasks (explore, librarian) individually via \`background_cancel(taskId="...")\`
-- **NEVER use \`background_cancel(all=true)\`.** Always cancel individually by taskId.
-- **Always wait for Oracle**: When Oracle is running and you have gathered enough context from your own exploration, your next action is \`background_output\` on Oracle — NOT delivering a final answer. Oracle's value is highest when you think you don't need it.
+- **If Oracle is running**: STOP. Follow Oracle Completion Protocol in <Oracle_Usage>. Do NOT deliver any answer.
+- Cancel disposable background tasks (explore, librarian) individually via \`background_cancel(taskId="...")\`.
+- **Never use \`background_cancel(all=true)\`.**
 </Behavior_Instructions>
 
 ${oracleSection}
@@ -548,7 +553,7 @@ export function createSisyphusAgent(
   const tools = availableToolNames ? categorizeTools(availableToolNames) : [];
   const skills = availableSkills ?? [];
   const categories = availableCategories ?? [];
-  const prompt = availableAgents
+  let prompt = availableAgents
     ? buildDynamicSisyphusPrompt(
         model,
         availableAgents,
@@ -559,6 +564,15 @@ export function createSisyphusAgent(
       )
     : buildDynamicSisyphusPrompt(model, [], tools, skills, categories, useTaskSystem);
 
+  if (isGeminiModel(model)) {
+    prompt = prompt.replace(
+      "</intent_verbalization>",
+      `</intent_verbalization>\n\n${buildGeminiIntentGateEnforcement()}\n\n${buildGeminiToolMandate()}`
+    );
+    prompt += "\n" + buildGeminiDelegationOverride();
+    prompt += "\n" + buildGeminiVerificationOverride();
+  }
+
   const permission = {
     question: "allow",
     call_omo_agent: "deny",

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

@@ -1,12 +1,18 @@
 import { describe, test, expect } from "bun:test";
-import { isGptModel } from "./types";
+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);
@@ -39,11 +47,55 @@ describe("isGptModel", () => {
   });
 
   test("gemini models are not gpt", () => {
-    expect(isGptModel("google/gemini-3-pro")).toBe(false);
-    expect(isGptModel("litellm/gemini-3-pro")).toBe(false);
+    expect(isGptModel("google/gemini-3.1-pro")).toBe(false);
+    expect(isGptModel("litellm/gemini-3.1-pro")).toBe(false);
   });
 
   test("opencode provider is not gpt", () => {
     expect(isGptModel("opencode/claude-opus-4-6")).toBe(false);
   });
 });
+
+describe("isGeminiModel", () => {
+  test("#given google provider models #then returns true", () => {
+    expect(isGeminiModel("google/gemini-3.1-pro")).toBe(true);
+    expect(isGeminiModel("google/gemini-3-flash")).toBe(true);
+    expect(isGeminiModel("google/gemini-2.5-pro")).toBe(true);
+  });
+
+  test("#given google-vertex provider models #then returns true", () => {
+    expect(isGeminiModel("google-vertex/gemini-3.1-pro")).toBe(true);
+    expect(isGeminiModel("google-vertex/gemini-3-flash")).toBe(true);
+  });
+
+  test("#given github copilot gemini models #then returns true", () => {
+    expect(isGeminiModel("github-copilot/gemini-3.1-pro")).toBe(true);
+    expect(isGeminiModel("github-copilot/gemini-3-flash")).toBe(true);
+  });
+
+  test("#given litellm proxied gemini models #then returns true", () => {
+    expect(isGeminiModel("litellm/gemini-3.1-pro")).toBe(true);
+    expect(isGeminiModel("litellm/gemini-3-flash")).toBe(true);
+    expect(isGeminiModel("litellm/gemini-2.5-pro")).toBe(true);
+  });
+
+  test("#given other proxied gemini models #then returns true", () => {
+    expect(isGeminiModel("custom-provider/gemini-3.1-pro")).toBe(true);
+    expect(isGeminiModel("ollama/gemini-3-flash")).toBe(true);
+  });
+
+  test("#given gpt models #then returns false", () => {
+    expect(isGeminiModel("openai/gpt-5.2")).toBe(false);
+    expect(isGeminiModel("openai/o3-mini")).toBe(false);
+    expect(isGeminiModel("litellm/gpt-4o")).toBe(false);
+  });
+
+  test("#given claude models #then returns false", () => {
+    expect(isGeminiModel("anthropic/claude-opus-4-6")).toBe(false);
+    expect(isGeminiModel("anthropic/claude-sonnet-4-6")).toBe(false);
+  });
+
+  test("#given opencode provider #then returns false", () => {
+    expect(isGeminiModel("opencode/claude-opus-4-6")).toBe(false);
+  });
+});

src/agents/types.ts

@@ -70,14 +70,22 @@ 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-"))
+  const modelName = extractModelName(model).toLowerCase()
+  return modelName.includes("gpt")
+}
+
+const GEMINI_PROVIDERS = ["google/", "google-vertex/"]
+
+export function isGeminiModel(model: string): boolean {
+  if (GEMINI_PROVIDERS.some((prefix) => model.startsWith(prefix)))
+    return true
+
+  if (model.startsWith("github-copilot/") && extractModelName(model).toLowerCase().startsWith("gemini"))
     return true
 
   const modelName = extractModelName(model).toLowerCase()
-  return GPT_MODEL_PREFIXES.some((prefix) => modelName.startsWith(prefix))
+  return modelName.startsWith("gemini-")
 }
 
 export type BuiltinAgentName =

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 () => {
-    // #given - github-copilot provider has models available
+  test("hephaestus IS created when github-copilot is connected with a GPT model", async () => {
+    // #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()
     }
   })
 
@@ -986,7 +988,7 @@ describe("buildAgent with category and skills", () => {
     const agent = buildAgent(source["test-agent"], TEST_MODEL)
 
     // #then - category's built-in model is applied
-    expect(agent.model).toBe("google/gemini-3-pro")
+    expect(agent.model).toBe("google/gemini-3.1-pro")
   })
 
   test("agent with category and existing model keeps existing model", () => {

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

@@ -325,7 +325,7 @@ exports[`generateModelConfig single native provider uses Gemini models when only
   "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
   "agents": {
     "atlas": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
     },
     "explore": {
       "model": "opencode/gpt-5-nano",
@@ -334,34 +334,34 @@ exports[`generateModelConfig single native provider uses Gemini models when only
       "model": "opencode/glm-4.7-free",
     },
     "metis": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "momus": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "multimodal-looker": {
       "model": "google/gemini-3-flash-preview",
     },
     "oracle": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "prometheus": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
     },
   },
   "categories": {
     "artistry": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "quick": {
       "model": "google/gemini-3-flash-preview",
     },
     "ultrabrain": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "unspecified-high": {
@@ -371,7 +371,7 @@ exports[`generateModelConfig single native provider uses Gemini models when only
       "model": "google/gemini-3-flash-preview",
     },
     "visual-engineering": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "writing": {
@@ -386,7 +386,7 @@ exports[`generateModelConfig single native provider uses Gemini models with isMa
   "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
   "agents": {
     "atlas": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
     },
     "explore": {
       "model": "opencode/gpt-5-nano",
@@ -395,44 +395,44 @@ exports[`generateModelConfig single native provider uses Gemini models with isMa
       "model": "opencode/glm-4.7-free",
     },
     "metis": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "momus": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "multimodal-looker": {
       "model": "google/gemini-3-flash-preview",
     },
     "oracle": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "prometheus": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
     },
   },
   "categories": {
     "artistry": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "quick": {
       "model": "google/gemini-3-flash-preview",
     },
     "ultrabrain": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "unspecified-high": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
     },
     "unspecified-low": {
       "model": "google/gemini-3-flash-preview",
     },
     "visual-engineering": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "writing": {
@@ -485,7 +485,7 @@ exports[`generateModelConfig all native providers uses preferred models from fal
   },
   "categories": {
     "artistry": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "deep": {
@@ -506,7 +506,7 @@ exports[`generateModelConfig all native providers uses preferred models from fal
       "model": "anthropic/claude-sonnet-4-5",
     },
     "visual-engineering": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "writing": {
@@ -559,7 +559,7 @@ exports[`generateModelConfig all native providers uses preferred models with isM
   },
   "categories": {
     "artistry": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "deep": {
@@ -581,7 +581,7 @@ exports[`generateModelConfig all native providers uses preferred models with isM
       "model": "anthropic/claude-sonnet-4-5",
     },
     "visual-engineering": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "writing": {
@@ -634,7 +634,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
   },
   "categories": {
     "artistry": {
-      "model": "opencode/gemini-3-pro",
+      "model": "opencode/gemini-3.1-pro",
       "variant": "high",
     },
     "deep": {
@@ -655,7 +655,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
       "model": "opencode/claude-sonnet-4-5",
     },
     "visual-engineering": {
-      "model": "opencode/gemini-3-pro",
+      "model": "opencode/gemini-3.1-pro",
       "variant": "high",
     },
     "writing": {
@@ -708,7 +708,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
   },
   "categories": {
     "artistry": {
-      "model": "opencode/gemini-3-pro",
+      "model": "opencode/gemini-3.1-pro",
       "variant": "high",
     },
     "deep": {
@@ -730,7 +730,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
       "model": "opencode/claude-sonnet-4-5",
     },
     "visual-engineering": {
-      "model": "opencode/gemini-3-pro",
+      "model": "opencode/gemini-3.1-pro",
       "variant": "high",
     },
     "writing": {
@@ -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",
     },
@@ -783,19 +779,15 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models when
   },
   "categories": {
     "artistry": {
-      "model": "github-copilot/gemini-3-pro-preview",
+      "model": "github-copilot/gemini-3.1-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",
-      "variant": "xhigh",
+      "model": "github-copilot/gemini-3.1-pro-preview",
+      "variant": "high",
     },
     "unspecified-high": {
       "model": "github-copilot/claude-sonnet-4.5",
@@ -804,7 +796,7 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models when
       "model": "github-copilot/claude-sonnet-4.5",
     },
     "visual-engineering": {
-      "model": "github-copilot/gemini-3-pro-preview",
+      "model": "github-copilot/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "writing": {
@@ -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",
     },
@@ -857,19 +845,15 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models with
   },
   "categories": {
     "artistry": {
-      "model": "github-copilot/gemini-3-pro-preview",
+      "model": "github-copilot/gemini-3.1-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",
-      "variant": "xhigh",
+      "model": "github-copilot/gemini-3.1-pro-preview",
+      "variant": "high",
     },
     "unspecified-high": {
       "model": "github-copilot/claude-opus-4.6",
@@ -879,7 +863,7 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models with
       "model": "github-copilot/claude-sonnet-4.5",
     },
     "visual-engineering": {
-      "model": "github-copilot/gemini-3-pro-preview",
+      "model": "github-copilot/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "writing": {
@@ -1042,7 +1026,7 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
   },
   "categories": {
     "artistry": {
-      "model": "opencode/gemini-3-pro",
+      "model": "opencode/gemini-3.1-pro",
       "variant": "high",
     },
     "deep": {
@@ -1063,7 +1047,7 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
       "model": "anthropic/claude-sonnet-4-5",
     },
     "visual-engineering": {
-      "model": "opencode/gemini-3-pro",
+      "model": "opencode/gemini-3.1-pro",
       "variant": "high",
     },
     "writing": {
@@ -1116,7 +1100,7 @@ exports[`generateModelConfig mixed provider scenarios uses OpenAI + Copilot comb
   },
   "categories": {
     "artistry": {
-      "model": "github-copilot/gemini-3-pro-preview",
+      "model": "github-copilot/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "deep": {
@@ -1137,7 +1121,7 @@ exports[`generateModelConfig mixed provider scenarios uses OpenAI + Copilot comb
       "model": "github-copilot/claude-sonnet-4.5",
     },
     "visual-engineering": {
-      "model": "github-copilot/gemini-3-pro-preview",
+      "model": "github-copilot/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "writing": {
@@ -1233,7 +1217,7 @@ exports[`generateModelConfig mixed provider scenarios uses Gemini + Claude combi
       "model": "google/gemini-3-flash-preview",
     },
     "oracle": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "prometheus": {
@@ -1247,14 +1231,14 @@ exports[`generateModelConfig mixed provider scenarios uses Gemini + Claude combi
   },
   "categories": {
     "artistry": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "quick": {
       "model": "anthropic/claude-haiku-4-5",
     },
     "ultrabrain": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "unspecified-high": {
@@ -1264,7 +1248,7 @@ exports[`generateModelConfig mixed provider scenarios uses Gemini + Claude combi
       "model": "anthropic/claude-sonnet-4-5",
     },
     "visual-engineering": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "writing": {
@@ -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": {
@@ -1317,18 +1301,18 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
   },
   "categories": {
     "artistry": {
-      "model": "github-copilot/gemini-3-pro-preview",
+      "model": "github-copilot/gemini-3.1-pro-preview",
       "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": {
@@ -1338,7 +1322,7 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
       "model": "github-copilot/claude-sonnet-4.5",
     },
     "visual-engineering": {
-      "model": "github-copilot/gemini-3-pro-preview",
+      "model": "github-copilot/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "writing": {
@@ -1391,7 +1375,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
   },
   "categories": {
     "artistry": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "deep": {
@@ -1412,7 +1396,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
       "model": "anthropic/claude-sonnet-4-5",
     },
     "visual-engineering": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "writing": {
@@ -1465,7 +1449,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
   },
   "categories": {
     "artistry": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "deep": {
@@ -1487,7 +1471,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
       "model": "anthropic/claude-sonnet-4-5",
     },
     "visual-engineering": {
-      "model": "google/gemini-3-pro-preview",
+      "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
     "writing": {

src/cli/config-manager.test.ts

@@ -178,7 +178,7 @@ describe("config-manager ANTIGRAVITY_PROVIDER_CONFIG", () => {
     expect(models).toBeTruthy()
 
     const required = [
-      "antigravity-gemini-3-pro",
+      "antigravity-gemini-3.1-pro",
       "antigravity-gemini-3-flash",
       "antigravity-claude-sonnet-4-6",
       "antigravity-claude-sonnet-4-6-thinking",
@@ -206,7 +206,7 @@ describe("config-manager ANTIGRAVITY_PROVIDER_CONFIG", () => {
     const models = (ANTIGRAVITY_PROVIDER_CONFIG as any).google.models as Record<string, any>
 
     // #when checking Gemini Pro variants
-    const pro = models["antigravity-gemini-3-pro"]
+    const pro = models["antigravity-gemini-3.1-pro"]
     // #then should have low and high variants
     expect(pro.variants).toBeTruthy()
     expect(pro.variants.low).toBeTruthy()

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/antigravity-provider-configuration.ts

@@ -4,10 +4,10 @@
  * IMPORTANT: Model names MUST use `antigravity-` prefix for stability.
  *
  * Since opencode-antigravity-auth v1.3.0, models use a variant system:
- * - `antigravity-gemini-3-pro` with variants: low, high
+ * - `antigravity-gemini-3.1-pro` with variants: low, high
  * - `antigravity-gemini-3-flash` with variants: minimal, low, medium, high
  *
- * Legacy tier-suffixed names (e.g., `antigravity-gemini-3-pro-high`) still work
+ * Legacy tier-suffixed names (e.g., `antigravity-gemini-3.1-pro-high`) still work
  * but variants are the recommended approach.
  *
  * @see https://github.com/NoeFabris/opencode-antigravity-auth#models
@@ -16,7 +16,7 @@ export const ANTIGRAVITY_PROVIDER_CONFIG = {
   google: {
     name: "Google",
     models: {
-      "antigravity-gemini-3-pro": {
+      "antigravity-gemini-3.1-pro": {
         name: "Gemini 3 Pro (Antigravity)",
         limit: { context: 1048576, output: 65535 },
         modalities: { input: ["text", "image", "pdf"], output: ["text"] },

src/cli/config-manager/bun-install.ts

@@ -1,4 +1,5 @@
 import { getConfigDir } from "./config-context"
+import { spawnWithWindowsHide } from "../../shared/spawn-with-windows-hide"
 
 const BUN_INSTALL_TIMEOUT_SECONDS = 60
 const BUN_INSTALL_TIMEOUT_MS = BUN_INSTALL_TIMEOUT_SECONDS * 1000
@@ -16,7 +17,7 @@ export async function runBunInstall(): Promise<boolean> {
 
 export async function runBunInstallWithDetails(): Promise<BunInstallResult> {
   try {
-    const proc = Bun.spawn(["bun", "install"], {
+    const proc = spawnWithWindowsHide(["bun", "install"], {
       cwd: getConfigDir(),
       stdout: "inherit",
       stderr: "inherit",

src/cli/config-manager/opencode-binary.ts

@@ -1,4 +1,5 @@
 import type { OpenCodeBinaryType } from "../../shared/opencode-config-dir-types"
+import { spawnWithWindowsHide } from "../../shared/spawn-with-windows-hide"
 import { initConfigContext } from "./config-context"
 
 const OPENCODE_BINARIES = ["opencode", "opencode-desktop"] as const
@@ -11,7 +12,7 @@ interface OpenCodeBinaryResult {
 async function findOpenCodeBinaryWithVersion(): Promise<OpenCodeBinaryResult | null> {
   for (const binary of OPENCODE_BINARIES) {
     try {
-      const proc = Bun.spawn([binary, "--version"], {
+      const proc = spawnWithWindowsHide([binary, "--version"], {
         stdout: "pipe",
         stderr: "pipe",
       })

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/doctor/checks/dependencies.ts

@@ -3,6 +3,7 @@ import { createRequire } from "node:module"
 import { dirname, join } from "node:path"
 
 import type { DependencyInfo } from "../types"
+import { spawnWithWindowsHide } from "../../../shared/spawn-with-windows-hide"
 
 async function checkBinaryExists(binary: string): Promise<{ exists: boolean; path: string | null }> {
   try {
@@ -18,7 +19,7 @@ async function checkBinaryExists(binary: string): Promise<{ exists: boolean; pat
 
 async function getBinaryVersion(binary: string): Promise<string | null> {
   try {
-    const proc = Bun.spawn([binary, "--version"], { stdout: "pipe", stderr: "pipe" })
+    const proc = spawnWithWindowsHide([binary, "--version"], { stdout: "pipe", stderr: "pipe" })
     const output = await new Response(proc.stdout).text()
     await proc.exited
     if (proc.exitCode === 0) {
@@ -140,4 +141,3 @@ export async function checkCommentChecker(): Promise<DependencyInfo> {
     path: resolvedPath,
   }
 }
-

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

@@ -26,7 +26,7 @@ describe("model-resolution check", () => {
       // then: Should have category entries
       const visual = info.categories.find((c) => c.name === "visual-engineering")
       expect(visual).toBeDefined()
-      expect(visual!.requirement.fallbackChain[0]?.model).toBe("gemini-3-pro")
+      expect(visual!.requirement.fallbackChain[0]?.model).toBe("gemini-3.1-pro")
       expect(visual!.requirement.fallbackChain[0]?.providers).toContain("google")
     })
   })

src/cli/doctor/checks/system-binary.ts

@@ -1,6 +1,7 @@
 import { existsSync } from "node:fs"
 import { homedir } from "node:os"
 import { join } from "node:path"
+import { spawnWithWindowsHide } from "../../../shared/spawn-with-windows-hide"
 
 import { OPENCODE_BINARIES } from "../constants"
 
@@ -110,7 +111,7 @@ export async function getOpenCodeVersion(
 ): Promise<string | null> {
   try {
     const command = buildVersionCommand(binaryPath, platform)
-    const processResult = Bun.spawn(command, { stdout: "pipe", stderr: "pipe" })
+    const processResult = spawnWithWindowsHide(command, { stdout: "pipe", stderr: "pipe" })
     const output = await new Response(processResult.stdout).text()
     await processResult.exited
 

src/cli/doctor/checks/tools-gh.ts

@@ -1,3 +1,5 @@
+import { spawnWithWindowsHide } from "../../../shared/spawn-with-windows-hide"
+
 export interface GhCliInfo {
   installed: boolean
   version: string | null
@@ -19,7 +21,7 @@ async function checkBinaryExists(binary: string): Promise<{ exists: boolean; pat
 
 async function getGhVersion(): Promise<string | null> {
   try {
-    const processResult = Bun.spawn(["gh", "--version"], { stdout: "pipe", stderr: "pipe" })
+    const processResult = spawnWithWindowsHide(["gh", "--version"], { stdout: "pipe", stderr: "pipe" })
     const output = await new Response(processResult.stdout).text()
     await processResult.exited
     if (processResult.exitCode !== 0) return null
@@ -38,7 +40,7 @@ async function getGhAuthStatus(): Promise<{
   error: string | null
 }> {
   try {
-    const processResult = Bun.spawn(["gh", "auth", "status"], {
+    const processResult = spawnWithWindowsHide(["gh", "auth", "status"], {
       stdout: "pipe",
       stderr: "pipe",
       env: { ...process.env, GH_NO_UPDATE_NOTIFIER: "1" },

src/cli/doctor/formatter.test.ts

@@ -1,4 +1,5 @@
-import { afterEach, describe, expect, it, mock } from "bun:test"
+import { describe, expect, it } from "bun:test"
+import { stripAnsi } from "./format-shared"
 import type { DoctorResult } from "./types"
 
 function createDoctorResult(): DoctorResult {
@@ -39,78 +40,122 @@ function createDoctorResult(): DoctorResult {
   }
 }
 
-describe("formatter", () => {
-  afterEach(() => {
-    mock.restore()
+function createDoctorResultWithIssues(): DoctorResult {
+  const base = createDoctorResult()
+  base.results[1].issues = [
+    { title: "Config issue", description: "Bad config", severity: "error" as const, fix: "Fix it" },
+    { title: "Tool warning", description: "Missing tool", severity: "warning" as const },
+  ]
+  base.summary.failed = 1
+  base.summary.warnings = 1
+  return base
+}
+
+describe("formatDoctorOutput", () => {
+  describe("#given default mode", () => {
+    it("shows System OK when no issues", async () => {
+      //#given
+      const result = createDoctorResult()
+      const { formatDoctorOutput } = await import(`./formatter?default-ok-${Date.now()}`)
+
+      //#when
+      const output = stripAnsi(formatDoctorOutput(result, "default"))
+
+      //#then
+      expect(output).toContain("System OK (opencode 1.0.200 · oh-my-opencode 3.4.0)")
+    })
+
+    it("shows issue count and details when issues exist", async () => {
+      //#given
+      const result = createDoctorResultWithIssues()
+      const { formatDoctorOutput } = await import(`./formatter?default-issues-${Date.now()}`)
+
+      //#when
+      const output = stripAnsi(formatDoctorOutput(result, "default"))
+
+      //#then
+      expect(output).toContain("issues found:")
+      expect(output).toContain("1. Config issue")
+      expect(output).toContain("2. Tool warning")
+    })
   })
 
-  describe("formatDoctorOutput", () => {
-    it("dispatches to default formatter for default mode", async () => {
+  describe("#given status mode", () => {
+    it("renders system version line", async () => {
       //#given
-      const formatDefaultMock = mock(() => "default-output")
-      const formatStatusMock = mock(() => "status-output")
-      const formatVerboseMock = mock(() => "verbose-output")
-      mock.module("./format-default", () => ({ formatDefault: formatDefaultMock }))
-      mock.module("./format-status", () => ({ formatStatus: formatStatusMock }))
-      mock.module("./format-verbose", () => ({ formatVerbose: formatVerboseMock }))
-      const { formatDoctorOutput } = await import(`./formatter?default=${Date.now()}`)
+      const result = createDoctorResult()
+      const { formatDoctorOutput } = await import(`./formatter?status-ver-${Date.now()}`)
 
       //#when
-      const output = formatDoctorOutput(createDoctorResult(), "default")
+      const output = stripAnsi(formatDoctorOutput(result, "status"))
 
       //#then
-      expect(output).toBe("default-output")
-      expect(formatDefaultMock).toHaveBeenCalledTimes(1)
-      expect(formatStatusMock).toHaveBeenCalledTimes(0)
-      expect(formatVerboseMock).toHaveBeenCalledTimes(0)
+      expect(output).toContain("1.0.200 · 3.4.0 · Bun 1.2.0")
     })
 
-    it("dispatches to status formatter for status mode", async () => {
+    it("renders tool and MCP info", async () => {
       //#given
-      const formatDefaultMock = mock(() => "default-output")
-      const formatStatusMock = mock(() => "status-output")
-      const formatVerboseMock = mock(() => "verbose-output")
-      mock.module("./format-default", () => ({ formatDefault: formatDefaultMock }))
-      mock.module("./format-status", () => ({ formatStatus: formatStatusMock }))
-      mock.module("./format-verbose", () => ({ formatVerbose: formatVerboseMock }))
-      const { formatDoctorOutput } = await import(`./formatter?status=${Date.now()}`)
+      const result = createDoctorResult()
+      const { formatDoctorOutput } = await import(`./formatter?status-tools-${Date.now()}`)
 
       //#when
-      const output = formatDoctorOutput(createDoctorResult(), "status")
+      const output = stripAnsi(formatDoctorOutput(result, "status"))
 
       //#then
-      expect(output).toBe("status-output")
-      expect(formatDefaultMock).toHaveBeenCalledTimes(0)
-      expect(formatStatusMock).toHaveBeenCalledTimes(1)
-      expect(formatVerboseMock).toHaveBeenCalledTimes(0)
+      expect(output).toContain("LSP 2/4")
+      expect(output).toContain("context7")
+    })
+  })
+
+  describe("#given verbose mode", () => {
+    it("includes all section headers", async () => {
+      //#given
+      const result = createDoctorResult()
+      const { formatDoctorOutput } = await import(`./formatter?verbose-headers-${Date.now()}`)
+
+      //#when
+      const output = stripAnsi(formatDoctorOutput(result, "verbose"))
+
+      //#then
+      expect(output).toContain("System Information")
+      expect(output).toContain("Configuration")
+      expect(output).toContain("Tools")
+      expect(output).toContain("MCPs")
+      expect(output).toContain("Summary")
     })
 
-    it("dispatches to verbose formatter for verbose mode", async () => {
+    it("shows check summary counts", async () => {
       //#given
-      const formatDefaultMock = mock(() => "default-output")
-      const formatStatusMock = mock(() => "status-output")
-      const formatVerboseMock = mock(() => "verbose-output")
-      mock.module("./format-default", () => ({ formatDefault: formatDefaultMock }))
-      mock.module("./format-status", () => ({ formatStatus: formatStatusMock }))
-      mock.module("./format-verbose", () => ({ formatVerbose: formatVerboseMock }))
-      const { formatDoctorOutput } = await import(`./formatter?verbose=${Date.now()}`)
+      const result = createDoctorResult()
+      const { formatDoctorOutput } = await import(`./formatter?verbose-summary-${Date.now()}`)
 
       //#when
-      const output = formatDoctorOutput(createDoctorResult(), "verbose")
+      const output = stripAnsi(formatDoctorOutput(result, "verbose"))
 
       //#then
-      expect(output).toBe("verbose-output")
-      expect(formatDefaultMock).toHaveBeenCalledTimes(0)
-      expect(formatStatusMock).toHaveBeenCalledTimes(0)
-      expect(formatVerboseMock).toHaveBeenCalledTimes(1)
+      expect(output).toContain("1 passed")
+      expect(output).toContain("0 failed")
+      expect(output).toContain("1 warnings")
     })
   })
 
   describe("formatJsonOutput", () => {
-    it("returns valid JSON payload", async () => {
+    it("returns valid JSON", async () => {
       //#given
-      const { formatJsonOutput } = await import(`./formatter?json=${Date.now()}`)
       const result = createDoctorResult()
+      const { formatJsonOutput } = await import(`./formatter?json-valid-${Date.now()}`)
+
+      //#when
+      const output = formatJsonOutput(result)
+
+      //#then
+      expect(() => JSON.parse(output)).not.toThrow()
+    })
+
+    it("preserves all result fields", async () => {
+      //#given
+      const result = createDoctorResult()
+      const { formatJsonOutput } = await import(`./formatter?json-fields-${Date.now()}`)
 
       //#when
       const output = formatJsonOutput(result)
@@ -119,7 +164,6 @@ describe("formatter", () => {
       //#then
       expect(parsed.summary.total).toBe(2)
       expect(parsed.systemInfo.pluginVersion).toBe("3.4.0")
-      expect(parsed.tools.ghCli.username).toBe("yeongyu")
       expect(parsed.exitCode).toBe(0)
     })
   })

src/cli/model-fallback-requirements.ts

@@ -17,14 +17,14 @@ 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: [
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "high" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro", variant: "high" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
     ],
   },
@@ -59,7 +59,7 @@ export const CLI_AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
       { providers: ["kimi-for-coding"], model: "k2p5" },
       { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro" },
     ],
   },
   metis: {
@@ -68,14 +68,14 @@ export const CLI_AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
       { providers: ["kimi-for-coding"], model: "k2p5" },
       { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "high" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro", variant: "high" },
     ],
   },
   momus: {
     fallbackChain: [
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", 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" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro", variant: "high" },
     ],
   },
   atlas: {
@@ -84,7 +84,7 @@ export const CLI_AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
       { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro" },
     ],
   },
 }
@@ -92,7 +92,7 @@ export const CLI_AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
 export const CLI_CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   "visual-engineering": {
     fallbackChain: [
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "high" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro", variant: "high" },
       { providers: ["zai-coding-plan"], model: "glm-5" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["kimi-for-coding"], model: "k2p5" },
@@ -100,26 +100,26 @@ export const CLI_CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> =
   },
   ultrabrain: {
     fallbackChain: [
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.3-codex", variant: "xhigh" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "high" },
+      { providers: ["openai", "opencode"], model: "gpt-5.3-codex", variant: "xhigh" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-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" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro", variant: "high" },
     ],
     requiresModel: "gpt-5.3-codex",
   },
   artistry: {
     fallbackChain: [
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro", variant: "high" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro", variant: "high" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
     ],
-    requiresModel: "gemini-3-pro",
+    requiresModel: "gemini-3.1-pro",
   },
   quick: {
     fallbackChain: [
@@ -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" },
     ],
   },
@@ -139,7 +139,7 @@ export const CLI_CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> =
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro" },
     ],
   },
   writing: {

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
-      expect(result.agents?.hephaestus?.model).toBe("github-copilot/gpt-5.3-codex")
-      expect(result.agents?.hephaestus?.variant).toBe("medium")
+      // #then - hephaestus is omitted because gpt-5.3-codex is not available on github-copilot
+      expect(result.agents?.hephaestus).toBeUndefined()
     })
 
     test("Hephaestus is created when OpenCode Zen is available (opencode provider connected)", () => {

src/cli/provider-model-id-transform.test.ts

@@ -40,16 +40,16 @@ describe("transformModelForProvider", () => {
 			expect(result).toBe("claude-haiku-4.5")
 		})
 
-		test("transforms gemini-3-pro to gemini-3-pro-preview", () => {
-			// #given github-copilot provider and gemini-3-pro model
+		test("transforms gemini-3.1-pro to gemini-3.1-pro-preview", () => {
+			// #given github-copilot provider and gemini-3.1-pro model
 			const provider = "github-copilot"
-			const model = "gemini-3-pro"
+			const model = "gemini-3.1-pro"
 
 			// #when transformModelForProvider is called
 			const result = transformModelForProvider(provider, model)
 
-			// #then should transform to gemini-3-pro-preview
-			expect(result).toBe("gemini-3-pro-preview")
+			// #then should transform to gemini-3.1-pro-preview
+			expect(result).toBe("gemini-3.1-pro-preview")
 		})
 
 		test("transforms gemini-3-flash to gemini-3-flash-preview", () => {
@@ -64,16 +64,16 @@ describe("transformModelForProvider", () => {
 			expect(result).toBe("gemini-3-flash-preview")
 		})
 
-		test("prevents double transformation of gemini-3-pro-preview", () => {
-			// #given github-copilot provider and gemini-3-pro-preview model (already transformed)
+		test("prevents double transformation of gemini-3.1-pro-preview", () => {
+			// #given github-copilot provider and gemini-3.1-pro-preview model (already transformed)
 			const provider = "github-copilot"
-			const model = "gemini-3-pro-preview"
+			const model = "gemini-3.1-pro-preview"
 
 			// #when transformModelForProvider is called
 			const result = transformModelForProvider(provider, model)
 
-			// #then should NOT become gemini-3-pro-preview-preview
-			expect(result).toBe("gemini-3-pro-preview")
+			// #then should NOT become gemini-3.1-pro-preview-preview
+			expect(result).toBe("gemini-3.1-pro-preview")
 		})
 
 		test("prevents double transformation of gemini-3-flash-preview", () => {
@@ -102,16 +102,16 @@ describe("transformModelForProvider", () => {
 			expect(result).toBe("gemini-3-flash-preview")
 		})
 
-		test("transforms gemini-3-pro to gemini-3-pro-preview", () => {
-			// #given google provider and gemini-3-pro model
+		test("transforms gemini-3.1-pro to gemini-3.1-pro-preview", () => {
+			// #given google provider and gemini-3.1-pro model
 			const provider = "google"
-			const model = "gemini-3-pro"
+			const model = "gemini-3.1-pro"
 
 			// #when transformModelForProvider is called
 			const result = transformModelForProvider(provider, model)
 
-			// #then should transform to gemini-3-pro-preview
-			expect(result).toBe("gemini-3-pro-preview")
+			// #then should transform to gemini-3.1-pro-preview
+			expect(result).toBe("gemini-3.1-pro-preview")
 		})
 
 		test("passes through other gemini models unchanged", () => {
@@ -138,16 +138,16 @@ describe("transformModelForProvider", () => {
 			expect(result).toBe("gemini-3-flash-preview")
 		})
 
-		test("prevents double transformation of gemini-3-pro-preview", () => {
-			// #given google provider and gemini-3-pro-preview model (already transformed)
+		test("prevents double transformation of gemini-3.1-pro-preview", () => {
+			// #given google provider and gemini-3.1-pro-preview model (already transformed)
 			const provider = "google"
-			const model = "gemini-3-pro-preview"
+			const model = "gemini-3.1-pro-preview"
 
 			// #when transformModelForProvider is called
 			const result = transformModelForProvider(provider, model)
 
-			// #then should NOT become gemini-3-pro-preview-preview
-			expect(result).toBe("gemini-3-pro-preview")
+			// #then should NOT become gemini-3.1-pro-preview-preview
+			expect(result).toBe("gemini-3.1-pro-preview")
 		})
 
 		test("does not transform claude models for google provider", () => {

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")
-    nowSpy.mockReturnValueOnce(1000)
-    nowSpy.mockReturnValueOnce(3400)
+    const nowSpy = spyOn(Date, "now").mockReturnValue(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/integration.test.ts

@@ -3,6 +3,7 @@ import type { RunResult } from "./types"
 import { createJsonOutputManager } from "./json-output"
 import { resolveSession } from "./session-resolver"
 import { executeOnCompleteHook } from "./on-complete-hook"
+import * as spawnWithWindowsHideModule from "../../shared/spawn-with-windows-hide"
 import type { OpencodeClient } from "./types"
 import * as originalSdk from "@opencode-ai/sdk"
 import * as originalPortUtils from "../../shared/port-utils"
@@ -147,7 +148,7 @@ describe("integration: --session-id", () => {
     const result = resolveSession({ client: mockClient, sessionId, directory: "/test" })
 
     // then
-    await expect(result).rejects.toThrow(`Session not found: ${sessionId}`)
+    expect(result).rejects.toThrow(`Session not found: ${sessionId}`)
     expect(mockClient.session.get).toHaveBeenCalledWith({
       path: { id: sessionId },
       query: { directory: "/test" },
@@ -161,10 +162,13 @@ describe("integration: --on-complete", () => {
 
   beforeEach(() => {
     spyOn(console, "error").mockImplementation(() => {})
-    spawnSpy = spyOn(Bun, "spawn").mockReturnValue({
+    spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue({
       exited: Promise.resolve(0),
       exitCode: 0,
-    } as unknown as ReturnType<typeof Bun.spawn>)
+      stdout: undefined,
+      stderr: undefined,
+      kill: () => {},
+    } satisfies ReturnType<typeof spawnWithWindowsHideModule.spawnWithWindowsHide>)
   })
 
   afterEach(() => {
@@ -186,7 +190,7 @@ describe("integration: --on-complete", () => {
 
     // then
     expect(spawnSpy).toHaveBeenCalledTimes(1)
-    const [_, options] = spawnSpy.mock.calls[0] as Parameters<typeof Bun.spawn>
+    const [_, options] = spawnSpy.mock.calls[0] as Parameters<typeof spawnWithWindowsHideModule.spawnWithWindowsHide>
     expect(options?.env?.SESSION_ID).toBe("session-123")
     expect(options?.env?.EXIT_CODE).toBe("0")
     expect(options?.env?.DURATION_MS).toBe("5000")
@@ -208,10 +212,13 @@ describe("integration: option combinations", () => {
     spyOn(console, "error").mockImplementation(() => {})
     mockStdout = createMockWriteStream()
     mockStderr = createMockWriteStream()
-    spawnSpy = spyOn(Bun, "spawn").mockReturnValue({
+    spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue({
       exited: Promise.resolve(0),
       exitCode: 0,
-    } as unknown as ReturnType<typeof Bun.spawn>)
+      stdout: undefined,
+      stderr: undefined,
+      kill: () => {},
+    } satisfies ReturnType<typeof spawnWithWindowsHideModule.spawnWithWindowsHide>)
   })
 
   afterEach(() => {
@@ -249,9 +256,9 @@ describe("integration: option combinations", () => {
     const emitted = mockStdout.writes[0]!
     expect(() => JSON.parse(emitted)).not.toThrow()
     expect(spawnSpy).toHaveBeenCalledTimes(1)
-    const [args] = spawnSpy.mock.calls[0] as Parameters<typeof Bun.spawn>
+    const [args] = spawnSpy.mock.calls[0] as Parameters<typeof spawnWithWindowsHideModule.spawnWithWindowsHide>
     expect(args).toEqual(["sh", "-c", "echo done"])
-    const [_, options] = spawnSpy.mock.calls[0] as Parameters<typeof Bun.spawn>
+    const [_, options] = spawnSpy.mock.calls[0] as Parameters<typeof spawnWithWindowsHideModule.spawnWithWindowsHide>
     expect(options?.env?.SESSION_ID).toBe("session-123")
     expect(options?.env?.EXIT_CODE).toBe("0")
     expect(options?.env?.DURATION_MS).toBe("5000")

src/cli/run/on-complete-hook.test.ts

@@ -1,4 +1,5 @@
 import { describe, it, expect, spyOn, beforeEach, afterEach } from "bun:test"
+import * as spawnWithWindowsHideModule from "../../shared/spawn-with-windows-hide"
 import { executeOnCompleteHook } from "./on-complete-hook"
 
 describe("executeOnCompleteHook", () => {
@@ -6,7 +7,10 @@ describe("executeOnCompleteHook", () => {
     return {
       exited: Promise.resolve(exitCode),
       exitCode,
-    } as unknown as ReturnType<typeof Bun.spawn>
+      stdout: undefined,
+      stderr: undefined,
+      kill: () => {},
+    } satisfies ReturnType<typeof spawnWithWindowsHideModule.spawnWithWindowsHide>
   }
 
   let consoleErrorSpy: ReturnType<typeof spyOn<typeof console, "error">>
@@ -21,7 +25,7 @@ describe("executeOnCompleteHook", () => {
 
   it("executes command with correct env vars", async () => {
     // given
-    const spawnSpy = spyOn(Bun, "spawn").mockReturnValue(createProc(0))
+    const spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue(createProc(0))
 
     try {
       // when
@@ -35,7 +39,7 @@ describe("executeOnCompleteHook", () => {
 
       // then
       expect(spawnSpy).toHaveBeenCalledTimes(1)
-      const [args, options] = spawnSpy.mock.calls[0] as Parameters<typeof Bun.spawn>
+      const [args, options] = spawnSpy.mock.calls[0] as Parameters<typeof spawnWithWindowsHideModule.spawnWithWindowsHide>
 
       expect(args).toEqual(["sh", "-c", "echo test"])
       expect(options?.env?.SESSION_ID).toBe("session-123")
@@ -51,7 +55,7 @@ describe("executeOnCompleteHook", () => {
 
   it("env var values are strings", async () => {
     // given
-    const spawnSpy = spyOn(Bun, "spawn").mockReturnValue(createProc(0))
+    const spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue(createProc(0))
 
     try {
       // when
@@ -64,7 +68,7 @@ describe("executeOnCompleteHook", () => {
       })
 
       // then
-      const [_, options] = spawnSpy.mock.calls[0] as Parameters<typeof Bun.spawn>
+      const [_, options] = spawnSpy.mock.calls[0] as Parameters<typeof spawnWithWindowsHideModule.spawnWithWindowsHide>
 
       expect(options?.env?.EXIT_CODE).toBe("1")
       expect(options?.env?.EXIT_CODE).toBeTypeOf("string")
@@ -79,7 +83,7 @@ describe("executeOnCompleteHook", () => {
 
   it("empty command string is no-op", async () => {
     // given
-    const spawnSpy = spyOn(Bun, "spawn").mockReturnValue(createProc(0))
+    const spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue(createProc(0))
 
     try {
       // when
@@ -100,7 +104,7 @@ describe("executeOnCompleteHook", () => {
 
   it("whitespace-only command is no-op", async () => {
     // given
-    const spawnSpy = spyOn(Bun, "spawn").mockReturnValue(createProc(0))
+    const spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue(createProc(0))
 
     try {
       // when
@@ -121,11 +125,11 @@ describe("executeOnCompleteHook", () => {
 
   it("command failure logs warning but does not throw", async () => {
     // given
-    const spawnSpy = spyOn(Bun, "spawn").mockReturnValue(createProc(1))
+    const spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue(createProc(1))
 
     try {
       // when
-      await expect(
+      expect(
         executeOnCompleteHook({
           command: "false",
           sessionId: "session-123",
@@ -149,13 +153,13 @@ describe("executeOnCompleteHook", () => {
   it("spawn error logs warning but does not throw", async () => {
     // given
     const spawnError = new Error("Command not found")
-    const spawnSpy = spyOn(Bun, "spawn").mockImplementation(() => {
+    const spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockImplementation(() => {
       throw spawnError
     })
 
     try {
       // when
-      await expect(
+      expect(
         executeOnCompleteHook({
           command: "nonexistent-command",
           sessionId: "session-123",

src/cli/run/on-complete-hook.ts

@@ -1,4 +1,5 @@
 import pc from "picocolors"
+import { spawnWithWindowsHide } from "../../shared/spawn-with-windows-hide"
 
 export async function executeOnCompleteHook(options: {
   command: string
@@ -17,7 +18,7 @@ export async function executeOnCompleteHook(options: {
   console.error(pc.dim(`Running on-complete hook: ${trimmedCommand}`))
 
   try {
-    const proc = Bun.spawn(["sh", "-c", trimmedCommand], {
+    const proc = spawnWithWindowsHide(["sh", "-c", trimmedCommand], {
       env: {
         ...process.env,
         SESSION_ID: sessionId,

src/cli/run/opencode-binary-resolver.ts

@@ -1,4 +1,5 @@
 import { delimiter, dirname, join } from "node:path"
+import { spawnWithWindowsHide } from "../../shared/spawn-with-windows-hide"
 
 const OPENCODE_COMMANDS = ["opencode", "opencode-desktop"] as const
 const WINDOWS_SUFFIXES = ["", ".exe", ".cmd", ".bat", ".ps1"] as const
@@ -41,7 +42,7 @@ export function collectCandidateBinaryPaths(
 
 export async function canExecuteBinary(binaryPath: string): Promise<boolean> {
   try {
-    const proc = Bun.spawn([binaryPath, "--version"], {
+    const proc = spawnWithWindowsHide([binaryPath, "--version"], {
       stdout: "pipe",
       stderr: "pipe",
     })

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/cli/run/session-resolver.ts

@@ -31,7 +31,7 @@ export async function resolveSession(options: {
         permission: [
           { permission: "question", action: "deny" as const, pattern: "*" },
         ],
-      } as any,
+      } as Record<string, unknown>,
       query: { directory },
     })
 

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/index.ts

@@ -1,18 +1,5 @@
 export {
   OhMyOpenCodeConfigSchema,
-  AgentOverrideConfigSchema,
-  AgentOverridesSchema,
-  McpNameSchema,
-  AgentNameSchema,
-  HookNameSchema,
-  BuiltinCommandNameSchema,
-  SisyphusAgentConfigSchema,
-  ExperimentalConfigSchema,
-  RalphLoopConfigSchema,
-  TmuxConfigSchema,
-  TmuxLayoutSchema,
-  RuntimeFallbackConfigSchema,
-  FallbackModelsSchema,
 } from "./schema"
 
 export type {

src/config/schema/agent-overrides.ts

@@ -47,13 +47,21 @@ export const AgentOverrideConfigSchema = z.object({
       variant: z.string().optional(),
     })
     .optional(),
+  compaction: z
+    .object({
+      model: z.string().optional(),
+      variant: z.string().optional(),
+    })
+    .optional(),
 })
 
 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/config/schema/oh-my-opencode-config.ts

@@ -27,7 +27,7 @@ export const OhMyOpenCodeConfigSchema = z.object({
   /** Default agent name for `oh-my-opencode run` (env: OPENCODE_DEFAULT_AGENT) */
   default_run_agent: z.string().optional(),
   disabled_mcps: z.array(AnyMcpNameSchema).optional(),
-  disabled_agents: z.array(BuiltinAgentNameSchema).optional(),
+  disabled_agents: z.array(z.string()).optional(),
   disabled_skills: z.array(BuiltinSkillNameSchema).optional(),
   disabled_hooks: z.array(z.string()).optional(),
   disabled_commands: z.array(BuiltinCommandNameSchema).optional(),
@@ -35,6 +35,8 @@ export const OhMyOpenCodeConfigSchema = z.object({
   disabled_tools: z.array(z.string()).optional(),
   /** Enable hashline_edit tool/hook integrations (default: true at call site) */
   hashline_edit: z.boolean().optional(),
+  /** Enable model fallback on API errors (default: false). Set to true to enable automatic model switching when model errors occur. */
+  model_fallback: z.boolean().optional(),
   agents: AgentOverridesSchema.optional(),
   categories: CategoriesConfigSchema.optional(),
   claude_code: ClaudeCodeConfigSchema.optional(),

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/background-task-completer.ts

@@ -1,40 +0,0 @@
-import type { BackgroundTask } from "./types"
-import type { ResultHandlerContext } from "./result-handler-context"
-import { log } from "../../shared"
-import { notifyParentSession } from "./parent-session-notifier"
-
-export async function tryCompleteTask(
-  task: BackgroundTask,
-  source: string,
-  ctx: ResultHandlerContext
-): Promise<boolean> {
-  const { concurrencyManager, state } = ctx
-
-  if (task.status !== "running") {
-    log("[background-agent] Task already completed, skipping:", {
-      taskId: task.id,
-      status: task.status,
-      source,
-    })
-    return false
-  }
-
-  task.status = "completed"
-  task.completedAt = new Date()
-
-  if (task.concurrencyKey) {
-    concurrencyManager.release(task.concurrencyKey)
-    task.concurrencyKey = undefined
-  }
-
-  state.markForNotification(task)
-
-  try {
-    await notifyParentSession(task, ctx)
-    log(`[background-agent] Task completed via ${source}:`, task.id)
-  } catch (error) {
-    log("[background-agent] Error in notifyParentSession:", { taskId: task.id, error })
-  }
-
-  return true
-}

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

@@ -34,7 +34,7 @@ describe("ConcurrencyManager.getConcurrencyLimit", () => {
   test("should return provider limit even when modelConcurrency exists but doesn't match", () => {
     // given
     const config: BackgroundTaskConfig = {
-      modelConcurrency: { "google/gemini-3-pro": 5 },
+      modelConcurrency: { "google/gemini-3.1-pro": 5 },
       providerConcurrency: { anthropic: 3 }
     }
     const manager = new ConcurrencyManager(config)
@@ -95,7 +95,7 @@ describe("ConcurrencyManager.getConcurrencyLimit", () => {
     // when
     const modelLimit = manager.getConcurrencyLimit("anthropic/claude-sonnet-4-6")
     const providerLimit = manager.getConcurrencyLimit("anthropic/claude-opus-4-6")
-    const defaultLimit = manager.getConcurrencyLimit("google/gemini-3-pro")
+    const defaultLimit = manager.getConcurrencyLimit("google/gemini-3.1-pro")
 
     // then
     expect(modelLimit).toBe(10)

src/features/background-agent/format-duration.ts

@@ -1,14 +0,0 @@
-export function formatDuration(start: Date, end?: Date): string {
-  const duration = (end ?? new Date()).getTime() - start.getTime()
-  const seconds = Math.floor(duration / 1000)
-  const minutes = Math.floor(seconds / 60)
-  const hours = Math.floor(minutes / 60)
-
-  if (hours > 0) {
-    return `${hours}h ${minutes % 60}m ${seconds % 60}s`
-  }
-  if (minutes > 0) {
-    return `${minutes}m ${seconds % 60}s`
-  }
-  return `${seconds}s`
-}

src/features/background-agent/index.ts

@@ -1,5 +1,2 @@
 export * from "./types"
 export { BackgroundManager, type SubagentSessionCreatedEvent, type OnSubagentSessionCreated } from "./manager"
-export { TaskHistory, type TaskHistoryEntry } from "./task-history"
-export { ConcurrencyManager } from "./concurrency"
-export { TaskStateManager } from "./state"

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

@@ -25,7 +25,6 @@ import {
   hasMoreFallbacks,
 } from "../../shared/model-error-classifier"
 import {
-  MIN_IDLE_TIME_MS,
   POLLING_INTERVAL_MS,
   TASK_CLEANUP_DELAY_MS,
 } from "./constants"
@@ -43,6 +42,7 @@ import {
 import { tryFallbackRetry } from "./fallback-retry-handler"
 import { registerManagerForCleanup, unregisterManagerForCleanup } from "./process-cleanup"
 import { isCompactionAgent, findNearestMessageExcludingCompaction } from "./compaction-aware-message-resolver"
+import { handleSessionIdleBackgroundEvent } from "./session-idle-event-handler"
 import { MESSAGE_STORAGE } from "../hook-message-injector"
 import { join } from "node:path"
 import { pruneStaleTasksAndNotifications } from "./task-poller"
@@ -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
@@ -268,7 +270,7 @@ export class BackgroundManager {
       body: {
         parentID: input.parentSessionID,
         title: `${input.description} (@${input.agent} subagent)`,
-      } as any,
+      } as Record<string, unknown>,
       query: {
         directory: parentDirectory,
       },
@@ -740,61 +742,15 @@ export class BackgroundManager {
     }
 
     if (event.type === "session.idle") {
-      const sessionID = props?.sessionID as string | undefined
-      if (!sessionID) return
-
-      const task = this.findBySession(sessionID)
-      if (!task || task.status !== "running") return
-      
-      const startedAt = task.startedAt
-      if (!startedAt) return
-
-      // Edge guard: Require minimum elapsed time (5 seconds) before accepting idle
-      const elapsedMs = Date.now() - startedAt.getTime()
-      if (elapsedMs < MIN_IDLE_TIME_MS) {
-        const remainingMs = MIN_IDLE_TIME_MS - elapsedMs
-        if (!this.idleDeferralTimers.has(task.id)) {
-          log("[background-agent] Deferring early session.idle:", { elapsedMs, remainingMs, taskId: task.id })
-          const timer = setTimeout(() => {
-            this.idleDeferralTimers.delete(task.id)
-            this.handleEvent({ type: "session.idle", properties: { sessionID } })
-          }, remainingMs)
-          this.idleDeferralTimers.set(task.id, timer)
-        } else {
-          log("[background-agent] session.idle already deferred:", { elapsedMs, taskId: task.id })
-        }
-        return
-      }
-
-      // Edge guard: Verify session has actual assistant output before completing
-      this.validateSessionHasOutput(sessionID).then(async (hasValidOutput) => {
-        // Re-check status after async operation (could have been completed by polling)
-        if (task.status !== "running") {
-          log("[background-agent] Task status changed during validation, skipping:", { taskId: task.id, status: task.status })
-          return
-        }
-
-        if (!hasValidOutput) {
-          log("[background-agent] Session.idle but no valid output yet, waiting:", task.id)
-          return
-        }
-
-        const hasIncompleteTodos = await this.checkSessionTodos(sessionID)
-
-        // Re-check status after async operation again
-        if (task.status !== "running") {
-          log("[background-agent] Task status changed during todo check, skipping:", { taskId: task.id, status: task.status })
-          return
-        }
-
-        if (hasIncompleteTodos) {
-          log("[background-agent] Task has incomplete todos, waiting for todo-continuation:", task.id)
-          return
-        }
-
-        await this.tryCompleteTask(task, "session.idle event")
-      }).catch(err => {
-        log("[background-agent] Error in session.idle handler:", err)
+      if (!props || typeof props !== "object") return
+      handleSessionIdleBackgroundEvent({
+        properties: props as Record<string, unknown>,
+        findBySession: (id) => this.findBySession(id),
+        idleDeferralTimers: this.idleDeferralTimers,
+        validateSessionHasOutput: (id) => this.validateSessionHasOutput(id),
+        checkSessionTodos: (id) => this.checkSessionTodos(id),
+        tryCompleteTask: (task, source) => this.tryCompleteTask(task, source),
+        emitIdleEvent: (sessionID) => this.handleEvent({ type: "session.idle", properties: { sessionID } }),
       })
     }
 
@@ -963,6 +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.
@@ -1386,6 +1368,7 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
               taskId: task.id,
               parentSessionID: task.parentSessionID,
             })
+            this.queuePendingNotification(task.parentSessionID, notification)
           } else {
             log("[background-agent] Failed to send notification:", error)
           }
@@ -1614,6 +1597,7 @@ Use \`background_output(task_id="${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/background-agent/message-dir.ts

@@ -1 +0,0 @@
-export { getMessageDir } from "../../shared"

src/features/background-agent/parent-session-context-resolver.ts

@@ -1,81 +0,0 @@
-import type { OpencodeClient } from "./constants"
-import type { BackgroundTask } from "./types"
-import { findNearestMessageWithFields } from "../hook-message-injector"
-import { getMessageDir } from "../../shared"
-import { normalizePromptTools, resolveInheritedPromptTools } from "../../shared"
-
-type AgentModel = { providerID: string; modelID: string }
-
-function isObject(value: unknown): value is Record<string, unknown> {
-  return typeof value === "object" && value !== null
-}
-
-function extractAgentAndModelFromMessage(message: unknown): {
-  agent?: string
-  model?: AgentModel
-  tools?: Record<string, boolean>
-} {
-  if (!isObject(message)) return {}
-  const info = message["info"]
-  if (!isObject(info)) return {}
-
-  const agent = typeof info["agent"] === "string" ? info["agent"] : undefined
-  const modelObj = info["model"]
-  const tools = normalizePromptTools(isObject(info["tools"]) ? info["tools"] as Record<string, unknown> as Record<string, boolean | "allow" | "deny" | "ask"> : undefined)
-  if (isObject(modelObj)) {
-    const providerID = modelObj["providerID"]
-    const modelID = modelObj["modelID"]
-    if (typeof providerID === "string" && typeof modelID === "string") {
-      return { agent, model: { providerID, modelID }, tools }
-    }
-  }
-
-  const providerID = info["providerID"]
-  const modelID = info["modelID"]
-  if (typeof providerID === "string" && typeof modelID === "string") {
-    return { agent, model: { providerID, modelID }, tools }
-  }
-
-  return { agent, tools }
-}
-
-export async function resolveParentSessionAgentAndModel(input: {
-  client: OpencodeClient
-  task: BackgroundTask
-}): Promise<{ agent?: string; model?: AgentModel; tools?: Record<string, boolean> }> {
-  const { client, task } = input
-
-  let agent: string | undefined = task.parentAgent
-  let model: AgentModel | undefined
-  let tools: Record<string, boolean> | undefined = task.parentTools
-
-  try {
-    const messagesResp = await client.session.messages({
-      path: { id: task.parentSessionID },
-    })
-
-    const messagesRaw = "data" in messagesResp ? messagesResp.data : []
-    const messages = Array.isArray(messagesRaw) ? messagesRaw : []
-
-    for (let i = messages.length - 1; i >= 0; i--) {
-      const extracted = extractAgentAndModelFromMessage(messages[i])
-      if (extracted.agent || extracted.model || extracted.tools) {
-        agent = extracted.agent ?? task.parentAgent
-        model = extracted.model
-        tools = extracted.tools ?? tools
-        break
-      }
-    }
-  } catch {
-    const messageDir = getMessageDir(task.parentSessionID)
-    const currentMessage = messageDir ? findNearestMessageWithFields(messageDir) : null
-    agent = currentMessage?.agent ?? task.parentAgent
-    model =
-      currentMessage?.model?.providerID && currentMessage?.model?.modelID
-        ? { providerID: currentMessage.model.providerID, modelID: currentMessage.model.modelID }
-        : undefined
-    tools = normalizePromptTools(currentMessage?.tools) ?? tools
-  }
-
-  return { agent, model, tools: resolveInheritedPromptTools(task.parentSessionID, tools) }
-}

src/features/background-agent/parent-session-notifier.test.ts

@@ -1,39 +0,0 @@
-declare const require: (name: string) => any
-const { describe, test, expect } = require("bun:test")
-import type { BackgroundTask } from "./types"
-import { buildBackgroundTaskNotificationText } from "./background-task-notification-template"
-
-describe("notifyParentSession", () => {
-  test("displays INTERRUPTED for interrupted tasks", () => {
-    // given
-    const task: BackgroundTask = {
-      id: "test-task",
-      parentSessionID: "parent-session",
-      parentMessageID: "parent-message",
-      description: "Test task",
-      prompt: "Test prompt",
-      agent: "test-agent",
-      status: "interrupt",
-      startedAt: new Date(),
-      completedAt: new Date(),
-    }
-    const duration = "1s"
-    const statusText = task.status === "completed" ? "COMPLETED" : task.status === "interrupt" ? "INTERRUPTED" : "CANCELLED"
-    const allComplete = false
-    const remainingCount = 1
-    const completedTasks: BackgroundTask[] = []
-
-    // when
-    const notification = buildBackgroundTaskNotificationText({
-      task,
-      duration,
-      statusText,
-      allComplete,
-      remainingCount,
-      completedTasks,
-    })
-
-    // then
-    expect(notification).toContain("INTERRUPTED")
-  })
-})

src/features/background-agent/parent-session-notifier.ts

@@ -1,103 +0,0 @@
-import type { BackgroundTask } from "./types"
-import type { ResultHandlerContext } from "./result-handler-context"
-import { TASK_CLEANUP_DELAY_MS } from "./constants"
-import { createInternalAgentTextPart, log } from "../../shared"
-import { getTaskToastManager } from "../task-toast-manager"
-import { formatDuration } from "./duration-formatter"
-import { buildBackgroundTaskNotificationText } from "./background-task-notification-template"
-import { resolveParentSessionAgentAndModel } from "./parent-session-context-resolver"
-
-export async function notifyParentSession(
-  task: BackgroundTask,
-  ctx: ResultHandlerContext
-): Promise<void> {
-  const { client, state } = ctx
-
-  const duration = formatDuration(task.startedAt ?? task.completedAt ?? new Date(), task.completedAt)
-  log("[background-agent] notifyParentSession called for task:", task.id)
-
-  const toastManager = getTaskToastManager()
-  if (toastManager) {
-    toastManager.showCompletionToast({
-      id: task.id,
-      description: task.description,
-      duration,
-    })
-  }
-
-  const pendingSet = state.pendingByParent.get(task.parentSessionID)
-  if (pendingSet) {
-    pendingSet.delete(task.id)
-    if (pendingSet.size === 0) {
-      state.pendingByParent.delete(task.parentSessionID)
-    }
-  }
-
-  const allComplete = !pendingSet || pendingSet.size === 0
-  const remainingCount = pendingSet?.size ?? 0
-
-  const statusText = task.status === "completed" ? "COMPLETED" : task.status === "interrupt" ? "INTERRUPTED" : "CANCELLED"
-
-  const completedTasks = allComplete
-    ? Array.from(state.tasks.values()).filter(
-        (t) =>
-          t.parentSessionID === task.parentSessionID &&
-          t.status !== "running" &&
-          t.status !== "pending"
-      )
-    : []
-
-  const notification = buildBackgroundTaskNotificationText({
-    task,
-    duration,
-    statusText,
-    allComplete,
-    remainingCount,
-    completedTasks,
-  })
-
-  const { agent, model, tools } = await resolveParentSessionAgentAndModel({ client, task })
-
-  log("[background-agent] notifyParentSession context:", {
-    taskId: task.id,
-    resolvedAgent: agent,
-    resolvedModel: model,
-  })
-
-  try {
-    await client.session.promptAsync({
-      path: { id: task.parentSessionID },
-      body: {
-        noReply: !allComplete,
-        ...(agent !== undefined ? { agent } : {}),
-        ...(model !== undefined ? { model } : {}),
-        ...(tools ? { tools } : {}),
-        parts: [createInternalAgentTextPart(notification)],
-      },
-    })
-
-    log("[background-agent] Sent notification to parent session:", {
-      taskId: task.id,
-      allComplete,
-      noReply: !allComplete,
-    })
-  } catch (error) {
-    log("[background-agent] Failed to send notification:", error)
-  }
-
-  if (!allComplete) return
-
-  for (const completedTask of completedTasks) {
-    const taskId = completedTask.id
-    state.clearCompletionTimer(taskId)
-    const timer = setTimeout(() => {
-      state.completionTimers.delete(taskId)
-      if (state.tasks.has(taskId)) {
-        state.clearNotificationsForTask(taskId)
-        state.tasks.delete(taskId)
-        log("[background-agent] Removed completed task from memory:", taskId)
-      }
-    }, TASK_CLEANUP_DELAY_MS)
-    state.setCompletionTimer(taskId, timer)
-  }
-}

src/features/background-agent/result-handler-context.ts

@@ -1,9 +0,0 @@
-import type { OpencodeClient } from "./constants"
-import type { ConcurrencyManager } from "./concurrency"
-import type { TaskStateManager } from "./state"
-
-export interface ResultHandlerContext {
-  client: OpencodeClient
-  concurrencyManager: ConcurrencyManager
-  state: TaskStateManager
-}

src/features/background-agent/result-handler.ts

@@ -1,7 +0,0 @@
-export type { ResultHandlerContext } from "./result-handler-context"
-export { formatDuration } from "./duration-formatter"
-export { getMessageDir } from "../../shared"
-export { checkSessionTodos } from "./session-todo-checker"
-export { validateSessionHasOutput } from "./session-output-validator"
-export { tryCompleteTask } from "./background-task-completer"
-export { notifyParentSession } from "./parent-session-notifier"

src/features/background-agent/session-idle-event-handler.test.ts

@@ -0,0 +1,340 @@
+import { describe, it, expect, mock } from "bun:test"
+
+import { handleSessionIdleBackgroundEvent } from "./session-idle-event-handler"
+import type { BackgroundTask } from "./types"
+import { MIN_IDLE_TIME_MS } from "./constants"
+
+function createRunningTask(overrides: Partial<BackgroundTask> = {}): BackgroundTask {
+  return {
+    id: "task-1",
+    sessionID: "ses-idle-1",
+    parentSessionID: "parent-ses-1",
+    parentMessageID: "msg-1",
+    description: "test idle handler",
+    prompt: "test",
+    agent: "explore",
+    status: "running",
+    startedAt: new Date(Date.now() - (MIN_IDLE_TIME_MS + 100)),
+    ...overrides,
+  }
+}
+
+describe("handleSessionIdleBackgroundEvent", () => {
+  describe("#given no sessionID in properties", () => {
+    it("#then should do nothing", () => {
+      //#given
+      const tryCompleteTask = mock(() => Promise.resolve(true))
+
+      //#when
+      handleSessionIdleBackgroundEvent({
+        properties: {},
+        findBySession: () => undefined,
+        idleDeferralTimers: new Map(),
+        validateSessionHasOutput: () => Promise.resolve(true),
+        checkSessionTodos: () => Promise.resolve(false),
+        tryCompleteTask,
+        emitIdleEvent: () => {},
+      })
+
+      //#then
+      expect(tryCompleteTask).not.toHaveBeenCalled()
+    })
+  })
+
+  describe("#given non-string sessionID in properties", () => {
+    it("#then should do nothing", () => {
+      //#given
+      const tryCompleteTask = mock(() => Promise.resolve(true))
+
+      //#when
+      handleSessionIdleBackgroundEvent({
+        properties: { sessionID: 123 },
+        findBySession: () => undefined,
+        idleDeferralTimers: new Map(),
+        validateSessionHasOutput: () => Promise.resolve(true),
+        checkSessionTodos: () => Promise.resolve(false),
+        tryCompleteTask,
+        emitIdleEvent: () => {},
+      })
+
+      //#then
+      expect(tryCompleteTask).not.toHaveBeenCalled()
+    })
+  })
+
+  describe("#given no task found for session", () => {
+    it("#then should do nothing", () => {
+      //#given
+      const tryCompleteTask = mock(() => Promise.resolve(true))
+
+      //#when
+      handleSessionIdleBackgroundEvent({
+        properties: { sessionID: "ses-unknown" },
+        findBySession: () => undefined,
+        idleDeferralTimers: new Map(),
+        validateSessionHasOutput: () => Promise.resolve(true),
+        checkSessionTodos: () => Promise.resolve(false),
+        tryCompleteTask,
+        emitIdleEvent: () => {},
+      })
+
+      //#then
+      expect(tryCompleteTask).not.toHaveBeenCalled()
+    })
+  })
+
+  describe("#given task is not running", () => {
+    it("#then should do nothing", () => {
+      //#given
+      const task = createRunningTask({ status: "completed" })
+      const tryCompleteTask = mock(() => Promise.resolve(true))
+
+      //#when
+      handleSessionIdleBackgroundEvent({
+        properties: { sessionID: task.sessionID! },
+        findBySession: () => task,
+        idleDeferralTimers: new Map(),
+        validateSessionHasOutput: () => Promise.resolve(true),
+        checkSessionTodos: () => Promise.resolve(false),
+        tryCompleteTask,
+        emitIdleEvent: () => {},
+      })
+
+      //#then
+      expect(tryCompleteTask).not.toHaveBeenCalled()
+    })
+  })
+
+  describe("#given task has no startedAt", () => {
+    it("#then should do nothing", () => {
+      //#given
+      const task = createRunningTask({ startedAt: undefined })
+      const tryCompleteTask = mock(() => Promise.resolve(true))
+
+      //#when
+      handleSessionIdleBackgroundEvent({
+        properties: { sessionID: task.sessionID! },
+        findBySession: () => task,
+        idleDeferralTimers: new Map(),
+        validateSessionHasOutput: () => Promise.resolve(true),
+        checkSessionTodos: () => Promise.resolve(false),
+        tryCompleteTask,
+        emitIdleEvent: () => {},
+      })
+
+      //#then
+      expect(tryCompleteTask).not.toHaveBeenCalled()
+    })
+  })
+
+  describe("#given elapsed time < MIN_IDLE_TIME_MS", () => {
+    it("#when idle fires early #then should defer with timer", () => {
+      //#given
+      const realDateNow = Date.now
+      const baseNow = realDateNow()
+      const task = createRunningTask({ startedAt: new Date(baseNow) })
+      const idleDeferralTimers = new Map<string, ReturnType<typeof setTimeout>>()
+      const emitIdleEvent = mock(() => {})
+
+      try {
+        Date.now = () => baseNow + (MIN_IDLE_TIME_MS - 100)
+
+        //#when
+        handleSessionIdleBackgroundEvent({
+          properties: { sessionID: task.sessionID! },
+          findBySession: () => task,
+          idleDeferralTimers,
+          validateSessionHasOutput: () => Promise.resolve(true),
+          checkSessionTodos: () => Promise.resolve(false),
+          tryCompleteTask: () => Promise.resolve(true),
+          emitIdleEvent,
+        })
+
+        //#then
+        expect(idleDeferralTimers.has(task.id)).toBe(true)
+        expect(emitIdleEvent).not.toHaveBeenCalled()
+      } finally {
+        clearTimeout(idleDeferralTimers.get(task.id)!)
+        Date.now = realDateNow
+      }
+    })
+
+    it("#when idle already deferred #then should not create duplicate timer", () => {
+      //#given
+      const realDateNow = Date.now
+      const baseNow = realDateNow()
+      const task = createRunningTask({ startedAt: new Date(baseNow) })
+      const existingTimer = setTimeout(() => {}, 99999)
+      const idleDeferralTimers = new Map<string, ReturnType<typeof setTimeout>>([
+        [task.id, existingTimer],
+      ])
+      const emitIdleEvent = mock(() => {})
+
+      try {
+        Date.now = () => baseNow + (MIN_IDLE_TIME_MS - 100)
+
+        //#when
+        handleSessionIdleBackgroundEvent({
+          properties: { sessionID: task.sessionID! },
+          findBySession: () => task,
+          idleDeferralTimers,
+          validateSessionHasOutput: () => Promise.resolve(true),
+          checkSessionTodos: () => Promise.resolve(false),
+          tryCompleteTask: () => Promise.resolve(true),
+          emitIdleEvent,
+        })
+
+        //#then
+        expect(idleDeferralTimers.get(task.id)).toBe(existingTimer)
+      } finally {
+        clearTimeout(existingTimer)
+        Date.now = realDateNow
+      }
+    })
+
+    it("#when deferred timer fires #then should emit idle event", async () => {
+      //#given
+      const realDateNow = Date.now
+      const baseNow = realDateNow()
+      const task = createRunningTask({ startedAt: new Date(baseNow) })
+      const idleDeferralTimers = new Map<string, ReturnType<typeof setTimeout>>()
+      const emitIdleEvent = mock(() => {})
+      const remainingMs = 50
+
+      try {
+        Date.now = () => baseNow + (MIN_IDLE_TIME_MS - remainingMs)
+
+        //#when
+        handleSessionIdleBackgroundEvent({
+          properties: { sessionID: task.sessionID! },
+          findBySession: () => task,
+          idleDeferralTimers,
+          validateSessionHasOutput: () => Promise.resolve(true),
+          checkSessionTodos: () => Promise.resolve(false),
+          tryCompleteTask: () => Promise.resolve(true),
+          emitIdleEvent,
+        })
+
+        //#then - wait for deferred timer
+        await new Promise((resolve) => setTimeout(resolve, remainingMs + 50))
+        expect(emitIdleEvent).toHaveBeenCalledWith(task.sessionID)
+        expect(idleDeferralTimers.has(task.id)).toBe(false)
+      } finally {
+        Date.now = realDateNow
+      }
+    })
+  })
+
+  describe("#given elapsed time >= MIN_IDLE_TIME_MS", () => {
+    it("#when session has valid output and no incomplete todos #then should complete task", async () => {
+      //#given
+      const task = createRunningTask()
+      const tryCompleteTask = mock(() => Promise.resolve(true))
+
+      //#when
+      handleSessionIdleBackgroundEvent({
+        properties: { sessionID: task.sessionID! },
+        findBySession: () => task,
+        idleDeferralTimers: new Map(),
+        validateSessionHasOutput: () => Promise.resolve(true),
+        checkSessionTodos: () => Promise.resolve(false),
+        tryCompleteTask,
+        emitIdleEvent: () => {},
+      })
+
+      //#then
+      await new Promise((resolve) => setTimeout(resolve, 10))
+      expect(tryCompleteTask).toHaveBeenCalledWith(task, "session.idle event")
+    })
+
+    it("#when session has no valid output #then should not complete task", async () => {
+      //#given
+      const task = createRunningTask()
+      const tryCompleteTask = mock(() => Promise.resolve(true))
+
+      //#when
+      handleSessionIdleBackgroundEvent({
+        properties: { sessionID: task.sessionID! },
+        findBySession: () => task,
+        idleDeferralTimers: new Map(),
+        validateSessionHasOutput: () => Promise.resolve(false),
+        checkSessionTodos: () => Promise.resolve(false),
+        tryCompleteTask,
+        emitIdleEvent: () => {},
+      })
+
+      //#then
+      await new Promise((resolve) => setTimeout(resolve, 10))
+      expect(tryCompleteTask).not.toHaveBeenCalled()
+    })
+
+    it("#when task has incomplete todos #then should not complete task", async () => {
+      //#given
+      const task = createRunningTask()
+      const tryCompleteTask = mock(() => Promise.resolve(true))
+
+      //#when
+      handleSessionIdleBackgroundEvent({
+        properties: { sessionID: task.sessionID! },
+        findBySession: () => task,
+        idleDeferralTimers: new Map(),
+        validateSessionHasOutput: () => Promise.resolve(true),
+        checkSessionTodos: () => Promise.resolve(true),
+        tryCompleteTask,
+        emitIdleEvent: () => {},
+      })
+
+      //#then
+      await new Promise((resolve) => setTimeout(resolve, 10))
+      expect(tryCompleteTask).not.toHaveBeenCalled()
+    })
+
+    it("#when task status changes during validation #then should not complete task", async () => {
+      //#given
+      const task = createRunningTask()
+      const tryCompleteTask = mock(() => Promise.resolve(true))
+
+      //#when
+      handleSessionIdleBackgroundEvent({
+        properties: { sessionID: task.sessionID! },
+        findBySession: () => task,
+        idleDeferralTimers: new Map(),
+        validateSessionHasOutput: async () => {
+          task.status = "completed"
+          return true
+        },
+        checkSessionTodos: () => Promise.resolve(false),
+        tryCompleteTask,
+        emitIdleEvent: () => {},
+      })
+
+      //#then
+      await new Promise((resolve) => setTimeout(resolve, 10))
+      expect(tryCompleteTask).not.toHaveBeenCalled()
+    })
+
+    it("#when task status changes during todo check #then should not complete task", async () => {
+      //#given
+      const task = createRunningTask()
+      const tryCompleteTask = mock(() => Promise.resolve(true))
+
+      //#when
+      handleSessionIdleBackgroundEvent({
+        properties: { sessionID: task.sessionID! },
+        findBySession: () => task,
+        idleDeferralTimers: new Map(),
+        validateSessionHasOutput: () => Promise.resolve(true),
+        checkSessionTodos: async () => {
+          task.status = "cancelled"
+          return false
+        },
+        tryCompleteTask,
+        emitIdleEvent: () => {},
+      })
+
+      //#then
+      await new Promise((resolve) => setTimeout(resolve, 10))
+      expect(tryCompleteTask).not.toHaveBeenCalled()
+    })
+  })
+})

src/features/background-agent/session-output-validator.ts

@@ -1,89 +0,0 @@
-import type { OpencodeClient } from "./constants"
-import { log } from "../../shared"
-
-type SessionMessagePart = {
-  type?: string
-  text?: string
-  content?: unknown
-}
-
-function isObject(value: unknown): value is Record<string, unknown> {
-  return typeof value === "object" && value !== null
-}
-
-function getMessageRole(message: unknown): string | undefined {
-  if (!isObject(message)) return undefined
-  const info = message["info"]
-  if (!isObject(info)) return undefined
-  const role = info["role"]
-  return typeof role === "string" ? role : undefined
-}
-
-function getMessageParts(message: unknown): SessionMessagePart[] {
-  if (!isObject(message)) return []
-  const parts = message["parts"]
-  if (!Array.isArray(parts)) return []
-
-  return parts
-    .filter((part): part is SessionMessagePart => isObject(part))
-    .map((part) => ({
-      type: typeof part["type"] === "string" ? part["type"] : undefined,
-      text: typeof part["text"] === "string" ? part["text"] : undefined,
-      content: part["content"],
-    }))
-}
-
-function partHasContent(part: SessionMessagePart): boolean {
-  if (part.type === "text" || part.type === "reasoning") {
-    return Boolean(part.text && part.text.trim().length > 0)
-  }
-  if (part.type === "tool") return true
-  if (part.type === "tool_result") {
-    if (typeof part.content === "string") return part.content.trim().length > 0
-    if (Array.isArray(part.content)) return part.content.length > 0
-    return Boolean(part.content)
-  }
-  return false
-}
-
-export async function validateSessionHasOutput(
-  client: OpencodeClient,
-  sessionID: string
-): Promise<boolean> {
-  try {
-    const response = await client.session.messages({
-      path: { id: sessionID },
-    })
-
-    const messagesRaw =
-      isObject(response) && "data" in response ? (response as { data?: unknown }).data : response
-    const messages = Array.isArray(messagesRaw) ? messagesRaw : []
-
-    const hasAssistantOrToolMessage = messages.some((message) => {
-      const role = getMessageRole(message)
-      return role === "assistant" || role === "tool"
-    })
-
-    if (!hasAssistantOrToolMessage) {
-      log("[background-agent] No assistant/tool messages found in session:", sessionID)
-      return false
-    }
-
-    const hasContent = messages.some((message) => {
-      const role = getMessageRole(message)
-      if (role !== "assistant" && role !== "tool") return false
-      const parts = getMessageParts(message)
-      return parts.some(partHasContent)
-    })
-
-    if (!hasContent) {
-      log("[background-agent] Messages exist but no content found in session:", sessionID)
-      return false
-    }
-
-    return true
-  } catch (error) {
-    log("[background-agent] Error validating session output:", error)
-    return true
-  }
-}

src/features/background-agent/session-task-cleanup.ts

@@ -1,46 +0,0 @@
-import { subagentSessions } from "../claude-code-session-state"
-import type { BackgroundTask } from "./types"
-
-export function cleanupTaskAfterSessionEnds(args: {
-  task: BackgroundTask
-  tasks: Map<string, BackgroundTask>
-  idleDeferralTimers: Map<string, ReturnType<typeof setTimeout>>
-  completionTimers: Map<string, ReturnType<typeof setTimeout>>
-  cleanupPendingByParent: (task: BackgroundTask) => void
-  clearNotificationsForTask: (taskId: string) => void
-  releaseConcurrencyKey?: (key: string) => void
-}): void {
-  const {
-    task,
-    tasks,
-    idleDeferralTimers,
-    completionTimers,
-    cleanupPendingByParent,
-    clearNotificationsForTask,
-    releaseConcurrencyKey,
-  } = args
-
-  const completionTimer = completionTimers.get(task.id)
-  if (completionTimer) {
-    clearTimeout(completionTimer)
-    completionTimers.delete(task.id)
-  }
-
-  const idleTimer = idleDeferralTimers.get(task.id)
-  if (idleTimer) {
-    clearTimeout(idleTimer)
-    idleDeferralTimers.delete(task.id)
-  }
-
-  if (task.concurrencyKey && releaseConcurrencyKey) {
-    releaseConcurrencyKey(task.concurrencyKey)
-    task.concurrencyKey = undefined
-  }
-
-  cleanupPendingByParent(task)
-  clearNotificationsForTask(task.id)
-  tasks.delete(task.id)
-  if (task.sessionID) {
-    subagentSessions.delete(task.sessionID)
-  }
-}

src/features/background-agent/session-todo-checker.ts

@@ -1,33 +0,0 @@
-import type { OpencodeClient, Todo } from "./constants"
-
-function isTodo(value: unknown): value is Todo {
-  if (typeof value !== "object" || value === null) return false
-  const todo = value as Record<string, unknown>
-  return (
-    (typeof todo["id"] === "string" || todo["id"] === undefined) &&
-    typeof todo["content"] === "string" &&
-    typeof todo["status"] === "string" &&
-    typeof todo["priority"] === "string"
-  )
-}
-
-export async function checkSessionTodos(
-  client: OpencodeClient,
-  sessionID: string
-): Promise<boolean> {
-  try {
-    const response = await client.session.todo({
-      path: { id: sessionID },
-    })
-
-    const todosRaw = "data" in response ? response.data : response
-    if (!Array.isArray(todosRaw) || todosRaw.length === 0) return false
-
-    const incomplete = todosRaw
-      .filter(isTodo)
-      .filter((todo) => todo.status !== "completed" && todo.status !== "cancelled")
-    return incomplete.length > 0
-  } catch {
-    return false
-  }
-}

src/features/background-agent/spawner.ts

@@ -61,9 +61,7 @@ export async function startTask(
   const createResult = await client.session.create({
     body: {
       parentID: input.parentSessionID,
-      title: `Background: ${input.description}`,
-    // eslint-disable-next-line @typescript-eslint/no-explicit-any
-    } as any,
+    } as Record<string, unknown>,
     query: {
       directory: parentDirectory,
     },

src/features/background-agent/spawner/background-session-creator.ts

@@ -1,45 +0,0 @@
-import type { OpencodeClient } from "../constants"
-import type { ConcurrencyManager } from "../concurrency"
-import type { LaunchInput } from "../types"
-import { log } from "../../../shared"
-
-export async function createBackgroundSession(options: {
-  client: OpencodeClient
-  input: LaunchInput
-  parentDirectory: string
-  concurrencyManager: ConcurrencyManager
-  concurrencyKey: string
-}): Promise<string> {
-  const { client, input, parentDirectory, concurrencyManager, concurrencyKey } = options
-
-  const body = {
-    parentID: input.parentSessionID,
-    title: `Background: ${input.description}`,
-  }
-
-  const createResult = await client.session
-    .create({
-      body,
-      query: {
-        directory: parentDirectory,
-      },
-    })
-    .catch((error: unknown) => {
-      concurrencyManager.release(concurrencyKey)
-      throw error
-    })
-
-  if (createResult.error) {
-    concurrencyManager.release(concurrencyKey)
-    throw new Error(`Failed to create background session: ${createResult.error}`)
-  }
-
-  if (!createResult.data?.id) {
-    concurrencyManager.release(concurrencyKey)
-    throw new Error("Failed to create background session: API returned no session ID")
-  }
-
-  const sessionID = createResult.data.id
-  log("[background-agent] Background session created", { sessionID })
-  return sessionID
-}

src/features/background-agent/spawner/concurrency-key-from-launch-input.ts

@@ -1,7 +0,0 @@
-import type { LaunchInput } from "../types"
-
-export function getConcurrencyKeyFromLaunchInput(input: LaunchInput): string {
-  return input.model
-    ? `${input.model.providerID}/${input.model.modelID}`
-    : input.agent
-}

src/features/background-agent/spawner/spawner-context.ts

@@ -1,12 +0,0 @@
-import type { BackgroundTask } from "../types"
-import type { ConcurrencyManager } from "../concurrency"
-import type { OpencodeClient, OnSubagentSessionCreated } from "../constants"
-
-export interface SpawnerContext {
-  client: OpencodeClient
-  directory: string
-  concurrencyManager: ConcurrencyManager
-  tmuxEnabled: boolean
-  onSubagentSessionCreated?: OnSubagentSessionCreated
-  onTaskError: (task: BackgroundTask, error: Error) => void
-}

src/features/background-agent/spawner/tmux-callback-invoker.ts

@@ -1,40 +0,0 @@
-import { setTimeout } from "timers/promises"
-import type { OnSubagentSessionCreated } from "../constants"
-import { TMUX_CALLBACK_DELAY_MS } from "../constants"
-import { log } from "../../../shared"
-import { isInsideTmux } from "../../../shared/tmux"
-
-export async function maybeInvokeTmuxCallback(options: {
-  onSubagentSessionCreated?: OnSubagentSessionCreated
-  tmuxEnabled: boolean
-  sessionID: string
-  parentID: string
-  title: string
-}): Promise<void> {
-  const { onSubagentSessionCreated, tmuxEnabled, sessionID, parentID, title } = options
-
-  log("[background-agent] tmux callback check", {
-    hasCallback: !!onSubagentSessionCreated,
-    tmuxEnabled,
-    isInsideTmux: isInsideTmux(),
-    sessionID,
-    parentID,
-  })
-
-  if (!onSubagentSessionCreated || !tmuxEnabled || !isInsideTmux()) {
-    log("[background-agent] SKIP tmux callback - conditions not met")
-    return
-  }
-
-  log("[background-agent] Invoking tmux callback NOW", { sessionID })
-  await onSubagentSessionCreated({
-    sessionID,
-    parentID,
-    title,
-  }).catch((error: unknown) => {
-    log("[background-agent] Failed to spawn tmux pane:", error)
-  })
-
-  log("[background-agent] tmux callback completed, waiting")
-  await setTimeout(TMUX_CALLBACK_DELAY_MS)
-}