release: v3.9.0

The auto-commit section instructed Hephaestus to automatically commit after
implementation work. Users who didn't know about this behavior would get
surprise commits — a trust-breaking behavioral change flagged by 5 Oracle
reviews as the sole publish blocker for 3.9.0.

.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

@@ -24,19 +24,7 @@
     "disabled_agents": {
       "type": "array",
       "items": {
-        "type": "string",
-        "enum": [
-          "sisyphus",
-          "hephaestus",
-          "prometheus",
-          "oracle",
-          "librarian",
-          "explore",
-          "multimodal-looker",
-          "metis",
-          "momus",
-          "atlas"
-        ]
+        "type": "string"
       }
     },
     "disabled_skills": {
@@ -82,6 +70,9 @@
     "hashline_edit": {
       "type": "boolean"
     },
+    "model_fallback": {
+      "type": "boolean"
+    },
     "agents": {
       "type": "object",
       "properties": {
@@ -288,6 +279,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -495,6 +498,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -702,6 +717,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -909,6 +936,21 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
+            },
+            "allow_non_gpt_model": {
+              "type": "boolean"
             }
           },
           "additionalProperties": false
@@ -1116,6 +1158,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -1323,6 +1377,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -1530,6 +1596,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -1737,6 +1815,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -1944,6 +2034,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -2151,6 +2253,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -2358,6 +2472,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -2565,6 +2691,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -2772,6 +2910,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -2979,6 +3129,18 @@
                 }
               },
               "additionalProperties": false
+            },
+            "compaction": {
+              "type": "object",
+              "properties": {
+                "model": {
+                  "type": "string"
+                },
+                "variant": {
+                  "type": "string"
+                }
+              },
+              "additionalProperties": false
             }
           },
           "additionalProperties": false
@@ -3077,6 +3239,11 @@
           "prompt_append": {
             "type": "string"
           },
+          "max_prompt_tokens": {
+            "type": "integer",
+            "exclusiveMinimum": 0,
+            "maximum": 9007199254740991
+          },
           "is_unstable_agent": {
             "type": "boolean"
           },

benchmarks/bun.lock

@@ -0,0 +1,62 @@
+{
+  "lockfileVersion": 1,
+  "configVersion": 1,
+  "workspaces": {
+    "": {
+      "name": "hashline-edit-benchmark",
+      "dependencies": {
+        "@ai-sdk/openai": "^1.3.0",
+        "@friendliai/ai-provider": "^1.0.9",
+        "ai": "^6.0.94",
+        "zod": "^4.1.0",
+      },
+    },
+  },
+  "packages": {
+    "@ai-sdk/gateway": ["@ai-sdk/gateway@3.0.55", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.15", "@vercel/oidc": "3.1.0" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-7xMeTJnCjwRwXKVCiv4Ly4qzWvDuW3+W1WIV0X1EFu6W83d4mEhV9bFArto10MeTw40ewuDjrbrZd21mXKohkw=="],
+
+    "@ai-sdk/openai": ["@ai-sdk/openai@1.3.24", "", { "dependencies": { "@ai-sdk/provider": "1.1.3", "@ai-sdk/provider-utils": "2.2.8" }, "peerDependencies": { "zod": "^3.0.0" } }, "sha512-GYXnGJTHRTZc4gJMSmFRgEQudjqd4PUN0ZjQhPwOAYH1yOAvQoG/Ikqs+HyISRbLPCrhbZnPKCNHuRU4OfpW0Q=="],
+
+    "@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.30", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.15" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-iTjumHf1/u4NhjXYFn/aONM2GId3/o7J1Lp5ql8FCbgIMyRwrmanR5xy1S3aaVkfTscuDvLTzWiy1mAbGzK3nQ=="],
+
+    "@ai-sdk/provider": ["@ai-sdk/provider@1.1.3", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-qZMxYJ0qqX/RfnuIaab+zp8UAeJn/ygXXAffR5I4N0n1IrvA6qBsjc8hXLmBiMV2zoXlifkacF7sEFnYnjBcqg=="],
+
+    "@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@2.2.8", "", { "dependencies": { "@ai-sdk/provider": "1.1.3", "nanoid": "^3.3.8", "secure-json-parse": "^2.7.0" }, "peerDependencies": { "zod": "^3.23.8" } }, "sha512-fqhG+4sCVv8x7nFzYnFo19ryhAa3w096Kmc3hWxMQfW/TubPOmt3A6tYZhl4mUfQWWQMsuSkLrtjlWuXBVSGQA=="],
+
+    "@friendliai/ai-provider": ["@friendliai/ai-provider@1.1.4", "", { "dependencies": { "@ai-sdk/openai-compatible": "2.0.30", "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.15" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.12" } }, "sha512-9TU4B1QFqPhbkONjI5afCF7Ox4jOqtGg1xw8mA9QHZdtlEbZxU+mBNvMPlI5pU5kPoN6s7wkXmFmxpID+own1A=="],
+
+    "@opentelemetry/api": ["@opentelemetry/api@1.9.0", "", {}, "sha512-3giAOQvZiH5F9bMlMiv8+GSPMeqg0dbaeo58/0SlA9sxSqZhnUtxzX9/2FzyhS9sWQf5S0GJE0AKBrFqjpeYcg=="],
+
+    "@standard-schema/spec": ["@standard-schema/spec@1.1.0", "", {}, "sha512-l2aFy5jALhniG5HgqrD6jXLi/rUWrKvqN/qJx6yoJsgKhblVd+iqqU4RCXavm/jPityDo5TCvKMnpjKnOriy0w=="],
+
+    "@vercel/oidc": ["@vercel/oidc@3.1.0", "", {}, "sha512-Fw28YZpRnA3cAHHDlkt7xQHiJ0fcL+NRcIqsocZQUSmbzeIKRpwttJjik5ZGanXP+vlA4SbTg+AbA3bP363l+w=="],
+
+    "ai": ["ai@6.0.101", "", { "dependencies": { "@ai-sdk/gateway": "3.0.55", "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.15", "@opentelemetry/api": "1.9.0" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-Ur/NgbgOp1rdhyDiKDk6EOpSgd1g5ADlbcD1cjQJtQsnmhEngz3Rf8nK5JetDh0vnbLy2aEBpaQeL+zvLRWuaA=="],
+
+    "eventsource-parser": ["eventsource-parser@3.0.6", "", {}, "sha512-Vo1ab+QXPzZ4tCa8SwIHJFaSzy4R6SHf7BY79rFBDf0idraZWAkYrDjDj8uWaSm3S2TK+hJ7/t1CEmZ7jXw+pg=="],
+
+    "json-schema": ["json-schema@0.4.0", "", {}, "sha512-es94M3nTIfsEPisRafak+HDLfHXnKBhV3vU5eqPcS3flIWqcxJWgXHXiey3YrpaNsanY5ei1VoYEbOzijuq9BA=="],
+
+    "nanoid": ["nanoid@3.3.11", "", { "bin": { "nanoid": "bin/nanoid.cjs" } }, "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w=="],
+
+    "secure-json-parse": ["secure-json-parse@2.7.0", "", {}, "sha512-6aU+Rwsezw7VR8/nyvKTx8QpWH9FrcYiXXlqC4z5d5XQBDRqtbfsRjnwGyqbi3gddNtWHuEk9OANUotL26qKUw=="],
+
+    "zod": ["zod@4.3.6", "", {}, "sha512-rftlrkhHZOcjDwkGlnUtZZkvaPHCsDATp4pGpuOOMDaTdDDXF91wuVDJoWoPsKX/3YPQ5fHuF3STjcYyKr+Qhg=="],
+
+    "@ai-sdk/gateway/@ai-sdk/provider": ["@ai-sdk/provider@3.0.8", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-oGMAgGoQdBXbZqNG0Ze56CHjDZ1IDYOwGYxYjO5KLSlz5HiNQ9udIXsPZ61VWaHGZ5XW/jyjmr6t2xz2jGVwbQ=="],
+
+    "@ai-sdk/gateway/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.15", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-8XiKWbemmCbvNN0CLR9u3PQiet4gtEVIrX4zzLxnCj06AwsEDJwJVBbKrEI4t6qE8XRSIvU2irka0dcpziKW6w=="],
+
+    "@ai-sdk/openai-compatible/@ai-sdk/provider": ["@ai-sdk/provider@3.0.8", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-oGMAgGoQdBXbZqNG0Ze56CHjDZ1IDYOwGYxYjO5KLSlz5HiNQ9udIXsPZ61VWaHGZ5XW/jyjmr6t2xz2jGVwbQ=="],
+
+    "@ai-sdk/openai-compatible/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.15", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-8XiKWbemmCbvNN0CLR9u3PQiet4gtEVIrX4zzLxnCj06AwsEDJwJVBbKrEI4t6qE8XRSIvU2irka0dcpziKW6w=="],
+
+    "@friendliai/ai-provider/@ai-sdk/provider": ["@ai-sdk/provider@3.0.8", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-oGMAgGoQdBXbZqNG0Ze56CHjDZ1IDYOwGYxYjO5KLSlz5HiNQ9udIXsPZ61VWaHGZ5XW/jyjmr6t2xz2jGVwbQ=="],
+
+    "@friendliai/ai-provider/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.15", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-8XiKWbemmCbvNN0CLR9u3PQiet4gtEVIrX4zzLxnCj06AwsEDJwJVBbKrEI4t6qE8XRSIvU2irka0dcpziKW6w=="],
+
+    "ai/@ai-sdk/provider": ["@ai-sdk/provider@3.0.8", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-oGMAgGoQdBXbZqNG0Ze56CHjDZ1IDYOwGYxYjO5KLSlz5HiNQ9udIXsPZ61VWaHGZ5XW/jyjmr6t2xz2jGVwbQ=="],
+
+    "ai/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.15", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-8XiKWbemmCbvNN0CLR9u3PQiet4gtEVIrX4zzLxnCj06AwsEDJwJVBbKrEI4t6qE8XRSIvU2irka0dcpziKW6w=="],
+  }
+}

benchmarks/headless.ts

@@ -0,0 +1,193 @@
+#!/usr/bin/env bun
+import { readFile, writeFile, mkdir } from "node:fs/promises"
+import { join, dirname } from "node:path"
+import { stepCountIs, streamText, type CoreMessage } from "ai"
+import { tool } from "ai"
+import { createFriendli } from "@friendliai/ai-provider"
+import { z } from "zod"
+import { formatHashLines } from "../src/tools/hashline-edit/hash-computation"
+import { normalizeHashlineEdits } from "../src/tools/hashline-edit/normalize-edits"
+import { applyHashlineEditsWithReport } from "../src/tools/hashline-edit/edit-operations"
+import { canonicalizeFileText, restoreFileText } from "../src/tools/hashline-edit/file-text-canonicalization"
+
+const DEFAULT_MODEL = "MiniMaxAI/MiniMax-M2.5"
+const MAX_STEPS = 50
+const sessionId = `bench-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`
+
+const emit = (event: Record<string, unknown>) =>
+  console.log(JSON.stringify({ sessionId, timestamp: new Date().toISOString(), ...event }))
+
+// ── CLI ──────────────────────────────────────────────────────
+function parseArgs(): { prompt: string; modelId: string } {
+  const args = process.argv.slice(2)
+  let prompt = ""
+  let modelId = DEFAULT_MODEL
+  for (let i = 0; i < args.length; i++) {
+    if ((args[i] === "-p" || args[i] === "--prompt") && args[i + 1]) {
+      prompt = args[++i]
+    } else if ((args[i] === "-m" || args[i] === "--model") && args[i + 1]) {
+      modelId = args[++i]
+    } else if (args[i] === "--reasoning-mode" && args[i + 1]) {
+      i++ // consume
+    }
+    // --no-translate, --think consumed silently
+  }
+  if (!prompt) {
+    console.error("Usage: bun run benchmarks/headless.ts -p <prompt> [-m <model>]")
+    process.exit(1)
+  }
+  return { prompt, modelId }
+}
+
+// ── Tools ────────────────────────────────────────────────────
+const readFileTool = tool({
+  description: "Read a file with hashline-tagged content (LINE#ID format)",
+  inputSchema: z.object({ path: z.string().describe("File path") }),
+  execute: async ({ path }) => {
+    const fullPath = join(process.cwd(), path)
+    try {
+      const content = await readFile(fullPath, "utf-8")
+      const lines = content.split("\n")
+      const tagged = formatHashLines(content)
+      return `OK - read file\npath: ${path}\nlines: ${lines.length}\n\n${tagged}`
+    } catch {
+      return `Error: File not found: ${path}`
+    }
+  },
+})
+
+const editFileTool = tool({
+  description: "Edit a file using hashline anchors (LINE#ID format)",
+  inputSchema: z.object({
+    path: z.string(),
+    edits: z.array(
+      z.object({
+        op: z.enum(["replace", "append", "prepend"]),
+        pos: z.string().optional(),
+        end: z.string().optional(),
+        lines: z.union([z.array(z.string()), z.string(), z.null()]),
+      })
+    ).min(1),
+  }),
+  execute: async ({ path, edits }) => {
+    const fullPath = join(process.cwd(), path)
+    try {
+      let rawContent = ""
+      let exists = true
+      try {
+        rawContent = await readFile(fullPath, "utf-8")
+      } catch {
+        exists = false
+      }
+
+      const normalized = normalizeHashlineEdits(edits)
+
+      if (!exists) {
+        const canCreate = normalized.every(
+          (e) => (e.op === "append" || e.op === "prepend") && !e.pos
+        )
+        if (!canCreate) return `Error: File not found: ${path}`
+      }
+
+      const envelope = canonicalizeFileText(rawContent)
+      const result = applyHashlineEditsWithReport(envelope.content, normalized)
+
+      if (result.content === envelope.content) {
+        return `Error: No changes made to ${path}. The edits produced identical content.`
+      }
+
+      const writeContent = restoreFileText(result.content, envelope)
+      await mkdir(dirname(fullPath), { recursive: true })
+      await writeFile(fullPath, writeContent, "utf-8")
+
+      const oldLineCount = rawContent.split("\n").length
+      const newLineCount = writeContent.split("\n").length
+      const delta = newLineCount - oldLineCount
+      const sign = delta > 0 ? "+" : ""
+      const action = exists ? "Updated" : "Created"
+      return `${action} ${path}\n${edits.length} edit(s) applied, ${sign}${delta} line(s)`
+    } catch (error) {
+      return `Error: ${error instanceof Error ? error.message : String(error)}`
+    }
+  },
+})
+
+// ── Agent Loop ───────────────────────────────────────────────
+async function run() {
+  const { prompt, modelId } = parseArgs()
+
+  const friendli = createFriendli({ apiKey: process.env.FRIENDLI_TOKEN! })
+  const model = friendli(modelId)
+  const tools = { read_file: readFileTool, edit_file: editFileTool }
+
+  emit({ type: "user", content: prompt })
+
+  const messages: CoreMessage[] = [{ role: "user", content: prompt }]
+  const system =
+    "You are a code editing assistant. Use read_file to read files and edit_file to edit them. " +
+    "Always read a file before editing it to get fresh LINE#ID anchors."
+
+  for (let step = 0; step < MAX_STEPS; step++) {
+    const stream = streamText({
+      model,
+      tools,
+      messages,
+      system,
+      stopWhen: stepCountIs(1),
+    })
+
+    let currentText = ""
+    for await (const part of stream.fullStream) {
+      switch (part.type) {
+        case "text-delta":
+          currentText += part.text
+          break
+        case "tool-call":
+          emit({
+            type: "tool_call",
+            tool_call_id: part.toolCallId,
+            tool_name: part.toolName,
+            tool_input: part.args,
+            model: modelId,
+          })
+          break
+        case "tool-result": {
+          const output = typeof part.result === "string" ? part.result : JSON.stringify(part.result)
+          const isError = typeof output === "string" && output.startsWith("Error:")
+          emit({
+            type: "tool_result",
+            tool_call_id: part.toolCallId,
+            output,
+            ...(isError ? { error: output } : {}),
+          })
+          break
+      }
+    }
+
+    const response = await stream.response
+    messages.push(...response.messages)
+
+    const finishReason = await stream.finishReason
+    if (finishReason !== "tool-calls") {
+      if (currentText.trim()) {
+        emit({ type: "assistant", content: currentText, model: modelId })
+      }
+      break
+    }
+  }
+}
+
+// ── Signal + Startup ─────────────────────────────────────────
+process.once("SIGINT", () => process.exit(0))
+process.once("SIGTERM", () => process.exit(143))
+
+const startTime = Date.now()
+run()
+  .catch((error) => {
+    emit({ type: "error", error: error instanceof Error ? error.message : String(error) })
+    process.exit(1)
+  })
+  .then(() => {
+    const elapsed = ((Date.now() - startTime) / 1000).toFixed(2)
+    console.error(`[headless] Completed in ${elapsed}s`)
+  })

benchmarks/package.json

@@ -0,0 +1,19 @@
+{
+  "name": "hashline-edit-benchmark",
+  "version": "0.1.0",
+  "private": true,
+  "type": "module",
+  "description": "Hashline edit tool benchmark using Vercel AI SDK with FriendliAI provider",
+  "scripts": {
+    "bench:basic": "bun run test-edit-ops.ts",
+    "bench:edge": "bun run test-edge-cases.ts",
+    "bench:multi": "bun run test-multi-model.ts",
+    "bench:all": "bun run bench:basic && bun run bench:edge"
+  },
+  "dependencies": {
+    "ai": "^6.0.94",
+    "@ai-sdk/openai": "^1.3.0",
+    "@friendliai/ai-provider": "^1.0.9",
+    "zod": "^4.1.0"
+  }
+}

benchmarks/test-edit-ops.ts

@@ -0,0 +1,808 @@
+#!/usr/bin/env bun
+/**
+ * Comprehensive headless edit_file stress test: 21 operation types
+ *
+ * Tests: 5 basic ops + 10 creative cases + 6 whitespace cases
+ * Each runs via headless mode with its own demo file + prompt.
+ *
+ * Usage:
+ *   bun run scripts/test-headless-edit-ops.ts [-m <model>] [--provider <provider>]
+ */
+
+import { spawn } from "node:child_process";
+import { mkdirSync, readFileSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join, resolve } from "node:path";
+
+// ── CLI arg passthrough ───────────────────────────────────────
+const extraArgs: string[] = [];
+const rawArgs = process.argv.slice(2);
+for (let i = 0; i < rawArgs.length; i++) {
+  const arg = rawArgs[i];
+  if (
+    (arg === "-m" || arg === "--model" || arg === "--provider") &&
+    i + 1 < rawArgs.length
+  ) {
+    extraArgs.push(arg, rawArgs[i + 1]);
+    i++;
+  } else if (arg === "--think" || arg === "--no-translate") {
+    extraArgs.push(arg);
+  } else if (arg === "--reasoning-mode" && i + 1 < rawArgs.length) {
+    extraArgs.push(arg, rawArgs[i + 1]);
+    i++;
+  }
+}
+
+// ── Colors ────────────────────────────────────────────────────
+const BOLD = "\x1b[1m";
+const GREEN = "\x1b[32m";
+const RED = "\x1b[31m";
+const YELLOW = "\x1b[33m";
+const DIM = "\x1b[2m";
+const CYAN = "\x1b[36m";
+const RESET = "\x1b[0m";
+
+const pass = (msg: string) => console.log(`  ${GREEN}✓${RESET} ${msg}`);
+const fail = (msg: string) => console.log(`  ${RED}✗${RESET} ${msg}`);
+const info = (msg: string) => console.log(`  ${DIM}${msg}${RESET}`);
+const warn = (msg: string) => console.log(`  ${YELLOW}⚠${RESET} ${msg}`);
+
+// ── Test case definition ─────────────────────────────────────
+interface TestCase {
+  fileContent: string;
+  fileName: string;
+  name: string;
+  prompt: string;
+  validate: (content: string) => { passed: boolean; reason: string };
+}
+
+const TEST_CASES: TestCase[] = [
+  {
+    name: "1. Replace single line",
+    fileName: "config.txt",
+    fileContent: [
+      "host: localhost",
+      "port: 3000",
+      "debug: false",
+      "timeout: 30",
+      "retries: 3",
+    ].join("\n"),
+    prompt: [
+      "Follow these steps exactly:",
+      "Step 1: Call read_file on config.txt.",
+      "Step 2: Note the anchor for the port line (line 2).",
+      "Step 3: Call edit_file with path='config.txt' and edits containing ONE object:",
+      "  { op: 'replace', pos: '<line2 anchor>', lines: ['port: 8080'] }",
+      "IMPORTANT: pos must be ONLY the anchor (like '2#KB'). lines must be a SEPARATE array field with the new content.",
+    ].join(" "),
+    validate: (content) => {
+      const has8080 = content.includes("port: 8080");
+      const has3000 = content.includes("port: 3000");
+      if (has8080 && !has3000) {
+        return { passed: true, reason: "port changed to 8080" };
+      }
+      if (has3000) {
+        return { passed: false, reason: "port still 3000 — edit not applied" };
+      }
+      return {
+        passed: false,
+        reason: `unexpected content: ${content.slice(0, 100)}`,
+      };
+    },
+  },
+  {
+    name: "2. Append after line",
+    fileName: "fruits.txt",
+    fileContent: ["apple", "banana", "cherry"].join("\n"),
+    prompt:
+      "Read fruits.txt with read_file. Then use edit_file with op='append' to insert a new line 'grape' after the 'banana' line. Use pos='LINE#HASH' of the banana line and lines=['grape'].",
+    validate: (content) => {
+      const lines = content.trim().split("\n");
+      const bananaIdx = lines.findIndex((l) => l.trim() === "banana");
+      const grapeIdx = lines.findIndex((l) => l.trim() === "grape");
+      if (grapeIdx === -1) {
+        return { passed: false, reason: '"grape" not found in file' };
+      }
+      if (bananaIdx === -1) {
+        return { passed: false, reason: '"banana" was removed' };
+      }
+      if (grapeIdx !== bananaIdx + 1) {
+        return {
+          passed: false,
+          reason: `"grape" at line ${grapeIdx + 1} but expected after "banana" at line ${bananaIdx + 1}`,
+        };
+      }
+      if (lines.length !== 4) {
+        return {
+          passed: false,
+          reason: `expected 4 lines, got ${lines.length}`,
+        };
+      }
+      return {
+        passed: true,
+        reason: '"grape" correctly appended after "banana"',
+      };
+    },
+  },
+  {
+    name: "3. Prepend before line",
+    fileName: "code.txt",
+    fileContent: ["function greet() {", '  return "hello";', "}"].join("\n"),
+    prompt:
+      "Read code.txt with read_file. Then use edit_file with op='prepend' to add '// Greeting function' before the function line. Use pos='LINE#HASH' of the function line and lines=['// Greeting function'].",
+    validate: (content) => {
+      const lines = content.trim().split("\n");
+      const commentIdx = lines.findIndex(
+        (l) => l.trim().startsWith("//") && l.toLowerCase().includes("greet")
+      );
+      const funcIdx = lines.findIndex((l) =>
+        l.trim().startsWith("function greet")
+      );
+      if (commentIdx === -1) {
+        return { passed: false, reason: "comment line not found" };
+      }
+      if (funcIdx === -1) {
+        return { passed: false, reason: '"function greet" line was removed' };
+      }
+      if (commentIdx !== funcIdx - 1) {
+        return {
+          passed: false,
+          reason: `comment at line ${commentIdx + 1} but function at ${funcIdx + 1} — not directly before`,
+        };
+      }
+      return {
+        passed: true,
+        reason: "comment correctly prepended before function",
+      };
+    },
+  },
+  {
+    name: "4. Range replace (multi-line → single line)",
+    fileName: "log.txt",
+    fileContent: [
+      "=== Log Start ===",
+      "INFO: started",
+      "WARN: slow query",
+      "ERROR: timeout",
+      "INFO: recovered",
+      "=== Log End ===",
+    ].join("\n"),
+    prompt: [
+      "Follow these steps exactly:",
+      "Step 1: Call read_file on log.txt to see line anchors.",
+      "Step 2: Note the anchor for 'WARN: slow query' (line 3) and 'ERROR: timeout' (line 4).",
+      "Step 3: Call edit_file with path='log.txt' and edits containing ONE object with THREE separate JSON fields:",
+      "  { op: 'replace', pos: '<line3 anchor>', end: '<line4 anchor>', lines: ['RESOLVED: issues cleared'] }",
+      "CRITICAL: pos, end, and lines are THREE SEPARATE JSON fields. pos is ONLY '3#XX'. end is ONLY '4#YY'. lines is ['RESOLVED: issues cleared'].",
+      "If edit_file fails or errors, use write_file to write the complete correct file content instead.",
+      "The correct final content should be: === Log Start ===, INFO: started, RESOLVED: issues cleared, INFO: recovered, === Log End ===",
+      "Do not make any other changes.",
+    ].join(" "),
+    validate: (content) => {
+      const lines = content.trim().split("\n");
+      const hasResolved = lines.some(
+        (l) => l.trim() === "RESOLVED: issues cleared"
+      );
+      const hasWarn = content.includes("WARN: slow query");
+      const hasError = content.includes("ERROR: timeout");
+      if (!hasResolved) {
+        return {
+          passed: false,
+          reason: '"RESOLVED: issues cleared" not found',
+        };
+      }
+      if (hasWarn || hasError) {
+        return { passed: false, reason: "old WARN/ERROR lines still present" };
+      }
+      // Core assertion: 2 old lines removed, 1 new line added = net -1 line
+      // Allow slight overshoot from model adding extra content
+      if (lines.length < 4 || lines.length > 6) {
+        return {
+          passed: false,
+          reason: `expected ~5 lines, got ${lines.length}`,
+        };
+      }
+      return {
+        passed: true,
+        reason: "range replace succeeded — 2 lines → 1 line",
+      };
+    },
+  },
+  {
+    name: "5. Delete line",
+    fileName: "settings.txt",
+    fileContent: [
+      "mode: production",
+      "debug: true",
+      "cache: enabled",
+      "log_level: info",
+    ].join("\n"),
+    prompt: [
+      "Follow these steps exactly:",
+      "Step 1: Call read_file on settings.txt to see line anchors.",
+      "Step 2: Note the anchor for 'debug: true' (line 2).",
+      "Step 3: Call edit_file with path='settings.txt' and edits containing ONE object:",
+      "  { op: 'replace', pos: '<line2 anchor>', lines: [] }",
+      "IMPORTANT: lines must be an empty array [] to delete the line. pos must be ONLY the anchor like '2#SR'.",
+    ].join(" "),
+    validate: (content) => {
+      const lines = content.trim().split("\n");
+      const hasDebug = content.includes("debug: true");
+      if (hasDebug) {
+        return { passed: false, reason: '"debug: true" still present' };
+      }
+      if (lines.length !== 3) {
+        return {
+          passed: false,
+          reason: `expected 3 lines, got ${lines.length}`,
+        };
+      }
+      if (
+        !(
+          content.includes("mode: production") &&
+          content.includes("cache: enabled")
+        )
+      ) {
+        return { passed: false, reason: "other lines were removed" };
+      }
+      return { passed: true, reason: '"debug: true" successfully deleted' };
+    },
+  },
+
+  // ── Creative cases (6-15) ────────────────────────────────────
+  {
+    name: "6. Batch edit — two replacements in one call",
+    fileName: "batch.txt",
+    fileContent: ["red", "green", "blue", "yellow"].join("\n"),
+    prompt: [
+      "Read batch.txt with read_file.",
+      "Then call edit_file ONCE with path='batch.txt' and edits containing TWO objects:",
+      "  1) { op: 'replace', pos: '<line1 anchor>', lines: ['crimson'] }",
+      "  2) { op: 'replace', pos: '<line3 anchor>', lines: ['navy'] }",
+      "Both edits must be in the SAME edits array in a single edit_file call.",
+    ].join(" "),
+    validate: (c) => {
+      const lines = c.trim().split("\n");
+      if (!c.includes("crimson")) return { passed: false, reason: "'crimson' not found" };
+      if (!c.includes("navy")) return { passed: false, reason: "'navy' not found" };
+      if (c.includes("red")) return { passed: false, reason: "'red' still present" };
+      if (c.includes("blue")) return { passed: false, reason: "'blue' still present" };
+      if (lines.length !== 4) return { passed: false, reason: `expected 4 lines, got ${lines.length}` };
+      return { passed: true, reason: "both lines replaced in single call" };
+    },
+  },
+  {
+    name: "7. Line expansion — 1 line → 3 lines",
+    fileName: "expand.txt",
+    fileContent: ["header", "TODO: implement", "footer"].join("\n"),
+    prompt: [
+      "Read expand.txt with read_file.",
+      "Replace the 'TODO: implement' line (line 2) with THREE lines:",
+      "  'step 1: init', 'step 2: process', 'step 3: cleanup'",
+      "Use edit_file with op='replace', pos=<line2 anchor>, lines=['step 1: init', 'step 2: process', 'step 3: cleanup'].",
+    ].join(" "),
+    validate: (c) => {
+      const lines = c.trim().split("\n");
+      if (c.includes("TODO")) return { passed: false, reason: "TODO line still present" };
+      if (!c.includes("step 1: init")) return { passed: false, reason: "'step 1: init' not found" };
+      if (!c.includes("step 3: cleanup")) return { passed: false, reason: "'step 3: cleanup' not found" };
+      if (lines.length !== 5) return { passed: false, reason: `expected 5 lines, got ${lines.length}` };
+      return { passed: true, reason: "1 line expanded to 3 lines" };
+    },
+  },
+  {
+    name: "8. Append at EOF",
+    fileName: "eof.txt",
+    fileContent: ["line one", "line two"].join("\n"),
+    prompt: [
+      "Read eof.txt with read_file.",
+      "Use edit_file to append 'line three' after the LAST line of the file.",
+      "Use op='append', pos=<last line anchor>, lines=['line three'].",
+    ].join(" "),
+    validate: (c) => {
+      const lines = c.trim().split("\n");
+      if (!c.includes("line three")) return { passed: false, reason: "'line three' not found" };
+      if (lines[lines.length - 1].trim() !== "line three")
+        return { passed: false, reason: "'line three' not at end" };
+      if (lines.length !== 3) return { passed: false, reason: `expected 3 lines, got ${lines.length}` };
+      return { passed: true, reason: "appended at EOF" };
+    },
+  },
+  {
+    name: "9. Special characters in content",
+    fileName: "special.json",
+    fileContent: [
+      '{',
+      '  "name": "old-value",',
+      '  "count": 42',
+      '}',
+    ].join("\n"),
+    prompt: [
+      "Read special.json with read_file.",
+      'Replace the line containing \"name\": \"old-value\" with \"name\": \"new-value\".',
+      "Use edit_file with op='replace', pos=<that line's anchor>, lines=['  \"name\": \"new-value\",'].",
+    ].join(" "),
+    validate: (c) => {
+      if (c.includes("old-value")) return { passed: false, reason: "'old-value' still present" };
+      if (!c.includes('"new-value"')) return { passed: false, reason: "'new-value' not found" };
+      if (!c.includes('"count": 42')) return { passed: false, reason: "other content was modified" };
+      return { passed: true, reason: "JSON value replaced with special chars intact" };
+    },
+  },
+  {
+    name: "10. Replace first line",
+    fileName: "first.txt",
+    fileContent: ["OLD HEADER", "body content", "footer"].join("\n"),
+    prompt: [
+      "Read first.txt with read_file.",
+      "Replace the very first line 'OLD HEADER' with 'NEW HEADER'.",
+      "Use edit_file with op='replace', pos=<line1 anchor>, lines=['NEW HEADER'].",
+    ].join(" "),
+    validate: (c) => {
+      const lines = c.trim().split("\n");
+      if (c.includes("OLD HEADER")) return { passed: false, reason: "'OLD HEADER' still present" };
+      if (lines[0].trim() !== "NEW HEADER") return { passed: false, reason: "first line is not 'NEW HEADER'" };
+      if (!c.includes("body content")) return { passed: false, reason: "body was modified" };
+      return { passed: true, reason: "first line replaced" };
+    },
+  },
+  {
+    name: "11. Replace last line",
+    fileName: "last.txt",
+    fileContent: ["alpha", "bravo", "OLD_FOOTER"].join("\n"),
+    prompt: [
+      "Read last.txt with read_file.",
+      "Replace the last line 'OLD_FOOTER' with 'NEW_FOOTER'.",
+      "Use edit_file with op='replace', pos=<last line anchor>, lines=['NEW_FOOTER'].",
+    ].join(" "),
+    validate: (c) => {
+      const lines = c.trim().split("\n");
+      if (c.includes("OLD_FOOTER")) return { passed: false, reason: "'OLD_FOOTER' still present" };
+      if (lines[lines.length - 1].trim() !== "NEW_FOOTER")
+        return { passed: false, reason: "last line is not 'NEW_FOOTER'" };
+      return { passed: true, reason: "last line replaced" };
+    },
+  },
+  {
+    name: "12. Adjacent line edits",
+    fileName: "adjacent.txt",
+    fileContent: ["aaa", "bbb", "ccc", "ddd"].join("\n"),
+    prompt: [
+      "Read adjacent.txt with read_file.",
+      "Replace line 2 ('bbb') with 'BBB' and line 3 ('ccc') with 'CCC'.",
+      "Use edit_file with TWO edits in the same call:",
+      "  { op: 'replace', pos: <line2 anchor>, lines: ['BBB'] }",
+      "  { op: 'replace', pos: <line3 anchor>, lines: ['CCC'] }",
+    ].join(" "),
+    validate: (c) => {
+      const lines = c.trim().split("\n");
+      if (c.includes("bbb")) return { passed: false, reason: "'bbb' still present" };
+      if (c.includes("ccc")) return { passed: false, reason: "'ccc' still present" };
+      if (!c.includes("BBB")) return { passed: false, reason: "'BBB' not found" };
+      if (!c.includes("CCC")) return { passed: false, reason: "'CCC' not found" };
+      if (lines.length !== 4) return { passed: false, reason: `expected 4 lines, got ${lines.length}` };
+      return { passed: true, reason: "two adjacent lines replaced" };
+    },
+  },
+  {
+    name: "13. Prepend multi-line block",
+    fileName: "block.py",
+    fileContent: ["def main():", "    print('hello')", "", "main()"].join("\n"),
+    prompt: [
+      "Read block.py with read_file.",
+      "Prepend a 2-line comment block before 'def main():' (line 1).",
+      "The two lines are: '# Author: test' and '# Date: 2025-01-01'.",
+      "Use edit_file with op='prepend', pos=<line1 anchor>, lines=['# Author: test', '# Date: 2025-01-01'].",
+    ].join(" "),
+    validate: (c) => {
+      const lines = c.trim().split("\n");
+      if (!c.includes("# Author: test")) return { passed: false, reason: "author comment not found" };
+      if (!c.includes("# Date: 2025-01-01")) return { passed: false, reason: "date comment not found" };
+      const defIdx = lines.findIndex((l) => l.startsWith("def main"));
+      const authorIdx = lines.findIndex((l) => l.includes("Author"));
+      if (authorIdx >= defIdx) return { passed: false, reason: "comments not before def" };
+      return { passed: true, reason: "2-line block prepended before function" };
+    },
+  },
+  {
+    name: "14. Delete range — 3 consecutive lines",
+    fileName: "cleanup.txt",
+    fileContent: ["keep1", "remove-a", "remove-b", "remove-c", "keep2"].join("\n"),
+    prompt: [
+      "Read cleanup.txt with read_file.",
+      "Delete lines 2-4 ('remove-a', 'remove-b', 'remove-c') using a single range replace.",
+      "Use edit_file with op='replace', pos=<line2 anchor>, end=<line4 anchor>, lines=[].",
+      "An empty lines array deletes the range.",
+    ].join(" "),
+    validate: (c) => {
+      const lines = c.trim().split("\n");
+      if (c.includes("remove")) return { passed: false, reason: "'remove' lines still present" };
+      if (!c.includes("keep1")) return { passed: false, reason: "'keep1' was deleted" };
+      if (!c.includes("keep2")) return { passed: false, reason: "'keep2' was deleted" };
+      if (lines.length !== 2) return { passed: false, reason: `expected 2 lines, got ${lines.length}` };
+      return { passed: true, reason: "3 consecutive lines deleted via range" };
+    },
+  },
+  {
+    name: "15. Replace with duplicate-content line",
+    fileName: "dupes.txt",
+    fileContent: ["item", "item", "item", "item"].join("\n"),
+    prompt: [
+      "Read dupes.txt with read_file. All 4 lines have the same text 'item'.",
+      "Replace ONLY line 3 with 'CHANGED'. Do NOT modify any other line.",
+      "Use edit_file with op='replace', pos=<line3 anchor>, lines=['CHANGED'].",
+      "The anchor hash uniquely identifies line 3 even though the content is identical.",
+    ].join(" "),
+    validate: (c) => {
+      const lines = c.trim().split("\n");
+      if (!c.includes("CHANGED")) return { passed: false, reason: "'CHANGED' not found" };
+      const changedCount = lines.filter((l) => l.trim() === "CHANGED").length;
+      const itemCount = lines.filter((l) => l.trim() === "item").length;
+      if (changedCount !== 1) return { passed: false, reason: `expected 1 CHANGED, got ${changedCount}` };
+      if (itemCount !== 3) return { passed: false, reason: `expected 3 item lines, got ${itemCount}` };
+      if (lines.length !== 4) return { passed: false, reason: `expected 4 lines, got ${lines.length}` };
+      return { passed: true, reason: "only line 3 changed among duplicates" };
+    },
+  },
+
+  // ── Whitespace cases (16-21) ──────────────────────────────────
+  {
+    name: "16. Fix indentation — 2 spaces → 4 spaces",
+    fileName: "indent.js",
+    fileContent: ["function foo() {", "  const x = 1;", "  return x;", "}"].join("\n"),
+    prompt: [
+      "Read indent.js with read_file.",
+      "Replace line 2 '  const x = 1;' (2-space indent) with '    const x = 1;' (4-space indent).",
+      "Use edit_file with op='replace', pos=<line2 anchor>, lines=['    const x = 1;'].",
+      "The ONLY change is the indentation: 2 spaces → 4 spaces. Content stays the same.",
+    ].join(" "),
+    validate: (c) => {
+      const lines = c.split("\n");
+      const line2 = lines[1];
+      if (!line2) return { passed: false, reason: "line 2 missing" };
+      if (line2 === "    const x = 1;") return { passed: true, reason: "indentation fixed to 4 spaces" };
+      if (line2 === "  const x = 1;") return { passed: false, reason: "still 2-space indent" };
+      return { passed: false, reason: `unexpected line 2: '${line2}'` };
+    },
+  },
+  {
+    name: "17. Replace preserving leading whitespace",
+    fileName: "preserve.py",
+    fileContent: [
+      "class Foo:",
+      "    def old_method(self):",
+      "        pass",
+    ].join("\n"),
+    prompt: [
+      "Read preserve.py with read_file.",
+      "Replace line 2 '    def old_method(self):' with '    def new_method(self):'.",
+      "Keep the 4-space indentation. Only change the method name.",
+      "Use edit_file with op='replace', pos=<line2 anchor>, lines=['    def new_method(self):'].",
+    ].join(" "),
+    validate: (c) => {
+      if (c.includes("old_method")) return { passed: false, reason: "'old_method' still present" };
+      const lines = c.split("\n");
+      const methodLine = lines.find((l) => l.includes("new_method"));
+      if (!methodLine) return { passed: false, reason: "'new_method' not found" };
+      if (!methodLine.startsWith("    ")) return { passed: false, reason: "indentation lost" };
+      return { passed: true, reason: "method renamed with indentation preserved" };
+    },
+  },
+  {
+    name: "18. Insert blank line between sections",
+    fileName: "sections.txt",
+    fileContent: ["[section-a]", "value-a=1", "[section-b]", "value-b=2"].join("\n"),
+    prompt: [
+      "Read sections.txt with read_file.",
+      "Insert a blank empty line between 'value-a=1' (line 2) and '[section-b]' (line 3).",
+      "Use edit_file with op='append', pos=<line2 anchor>, lines=[''].",
+      "lines=[''] inserts one empty line.",
+    ].join(" "),
+    validate: (c) => {
+      const lines = c.split("\n");
+      const valAIdx = lines.findIndex((l) => l.includes("value-a=1"));
+      const secBIdx = lines.findIndex((l) => l.includes("[section-b]"));
+      if (valAIdx === -1) return { passed: false, reason: "'value-a=1' missing" };
+      if (secBIdx === -1) return { passed: false, reason: "'[section-b]' missing" };
+      if (secBIdx - valAIdx < 2) return { passed: false, reason: "no blank line between sections" };
+      const between = lines[valAIdx + 1];
+      if (between.trim() !== "") return { passed: false, reason: `line between is '${between}', not blank` };
+      return { passed: true, reason: "blank line inserted between sections" };
+    },
+  },
+  {
+    name: "19. Delete blank line",
+    fileName: "noblank.txt",
+    fileContent: ["first", "", "second", "third"].join("\n"),
+    prompt: [
+      "Read noblank.txt with read_file.",
+      "Delete the empty blank line (line 2). Use edit_file with op='replace', pos=<line2 anchor>, lines=[].",
+    ].join(" "),
+    validate: (c) => {
+      const lines = c.trim().split("\n");
+      if (lines.length !== 3) return { passed: false, reason: `expected 3 lines, got ${lines.length}` };
+      if (lines[0].trim() !== "first") return { passed: false, reason: "'first' not on line 1" };
+      if (lines[1].trim() !== "second") return { passed: false, reason: "'second' not on line 2" };
+      return { passed: true, reason: "blank line deleted" };
+    },
+  },
+  {
+    name: "20. Tab → spaces conversion",
+    fileName: "tabs.txt",
+    fileContent: ["start", "\tindented-with-tab", "end"].join("\n"),
+    prompt: [
+      "Read tabs.txt with read_file.",
+      "Replace the tab-indented line 2 using edit_file with edits: [{ op: 'replace', pos: '<line2 anchor>', lines: ['    indented-with-spaces'] }].",
+      "Expected final line 2 to be 4 spaces followed by indented-with-spaces.",
+    ].join(" "),
+    validate: (c) => {
+      if (c.includes("\t")) return { passed: false, reason: "tab still present" };
+      if (!c.includes("    indented-with-spaces"))
+        return { passed: false, reason: "'    indented-with-spaces' not found" };
+      if (!c.includes("start")) return { passed: false, reason: "'start' was modified" };
+      return { passed: true, reason: "tab converted to 4 spaces" };
+    },
+  },
+  {
+    name: "21. Deeply nested indent replacement",
+    fileName: "nested.ts",
+    fileContent: [
+      "if (a) {",
+      "  if (b) {",
+      "    if (c) {",
+      "      old_call();",
+      "    }",
+      "  }",
+      "}",
+    ].join("\n"),
+    prompt: [
+      "Read nested.ts with read_file.",
+      "Replace line 4 '      old_call();' with '      new_call();'.",
+      "Preserve the exact 6-space indentation. Only change the function name.",
+      "Use edit_file with op='replace', pos=<line4 anchor>, lines=['      new_call();'].",
+    ].join(" "),
+    validate: (c) => {
+      if (c.includes("old_call")) return { passed: false, reason: "'old_call' still present" };
+      const lines = c.split("\n");
+      const callLine = lines.find((l) => l.includes("new_call"));
+      if (!callLine) return { passed: false, reason: "'new_call' not found" };
+      const leadingSpaces = callLine.match(/^ */)?.[0].length ?? 0;
+      if (leadingSpaces !== 6) return { passed: false, reason: `expected 6-space indent, got ${leadingSpaces}` };
+      return { passed: true, reason: "deeply nested line replaced with indent preserved" };
+    },
+  },
+];
+
+// ── JSONL event types ─────────────────────────────────────────
+interface ToolCallEvent {
+  tool_call_id: string;
+  tool_input: Record<string, unknown>;
+  tool_name: string;
+  type: "tool_call";
+}
+
+interface ToolResultEvent {
+  error?: string;
+  output: string;
+  tool_call_id: string;
+  type: "tool_result";
+}
+
+interface AnyEvent {
+  type: string;
+  [key: string]: unknown;
+}
+
+// ── Run single test case ─────────────────────────────────────
+async function runTestCase(
+  tc: TestCase,
+  testDir: string
+): Promise<{
+  passed: boolean;
+  editCalls: number;
+  editSuccesses: number;
+  duration: number;
+}> {
+  const testFile = join(testDir, tc.fileName);
+  writeFileSync(testFile, tc.fileContent, "utf-8");
+
+  const headlessScript = resolve(import.meta.dir, "headless.ts");
+  const headlessArgs = [
+    "run",
+    headlessScript,
+    "-p",
+    tc.prompt,
+    "--no-translate",
+    ...extraArgs,
+  ];
+
+  const startTime = Date.now();
+
+  const output = await new Promise<string>((res, reject) => {
+    const proc = spawn("bun", headlessArgs, {
+      cwd: testDir,
+      env: { ...process.env, BUN_INSTALL: process.env.BUN_INSTALL },
+      stdio: ["ignore", "pipe", "pipe"],
+    });
+
+    let stdout = "";
+    let stderr = "";
+
+    proc.stdout.on("data", (chunk: Buffer) => {
+      stdout += chunk.toString();
+    });
+    proc.stderr.on("data", (chunk: Buffer) => {
+      stderr += chunk.toString();
+    });
+
+    const timeout = setTimeout(
+      () => {
+        proc.kill("SIGTERM");
+        reject(new Error("Timed out after 4 minutes"));
+      },
+      4 * 60 * 1000
+    );
+
+    proc.on("close", (code) => {
+      clearTimeout(timeout);
+      if (code !== 0) {
+        reject(new Error(`Exit code ${code}\n${stderr.slice(-500)}`));
+      } else {
+        res(stdout);
+      }
+    });
+    proc.on("error", (err) => {
+      clearTimeout(timeout);
+      reject(err);
+    });
+  });
+
+  const duration = Date.now() - startTime;
+
+  // Parse events
+  const events: AnyEvent[] = [];
+  for (const line of output.split("\n").filter((l) => l.trim())) {
+    try {
+      events.push(JSON.parse(line) as AnyEvent);
+    } catch {
+      // skip non-JSON
+    }
+  }
+
+  const toolCalls = events.filter(
+    (e) => e.type === "tool_call"
+  ) as unknown as ToolCallEvent[];
+  const toolResults = events.filter(
+    (e) => e.type === "tool_result"
+  ) as unknown as ToolResultEvent[];
+
+  const editCalls = toolCalls.filter((e) => e.tool_name === "edit_file");
+  const editCallIds = new Set(editCalls.map((e) => e.tool_call_id));
+  const editResults = toolResults.filter((e) =>
+    editCallIds.has(e.tool_call_id)
+  );
+  const editSuccesses = editResults.filter((e) => !e.error);
+
+  // Show blocked calls
+  const editErrors = editResults.filter((e) => e.error);
+  for (const err of editErrors) {
+    const matchingCall = editCalls.find(
+      (c) => c.tool_call_id === err.tool_call_id
+    );
+    info(`  blocked: ${err.error?.slice(0, 120)}`);
+    if (matchingCall) {
+      info(`  input: ${JSON.stringify(matchingCall.tool_input).slice(0, 200)}`);
+    }
+  }
+
+  // Validate file content
+  let finalContent: string;
+  try {
+    finalContent = readFileSync(testFile, "utf-8");
+  } catch {
+    return {
+      passed: false,
+      editCalls: editCalls.length,
+      editSuccesses: editSuccesses.length,
+      duration,
+    };
+  }
+
+  const validation = tc.validate(finalContent);
+
+  return {
+    passed: validation.passed,
+    editCalls: editCalls.length,
+    editSuccesses: editSuccesses.length,
+    duration,
+  };
+}
+
+// ── Main ──────────────────────────────────────────────────────
+const main = async () => {
+  console.log(`\n${BOLD}Headless Edit Operations Test — ${TEST_CASES.length} Types${RESET}\n`);
+
+  const testDir = join(tmpdir(), `edit-ops-${Date.now()}`);
+  mkdirSync(testDir, { recursive: true });
+  info(`Test dir: ${testDir}`);
+  console.log();
+
+  let totalPassed = 0;
+  const results: { name: string; passed: boolean; detail: string }[] = [];
+
+  for (const tc of TEST_CASES) {
+    console.log(`${CYAN}${BOLD}${tc.name}${RESET}`);
+    info(`File: ${tc.fileName}`);
+    info(`Prompt: "${tc.prompt.slice(0, 80)}..."`);
+
+    try {
+      const result = await runTestCase(tc, testDir);
+      const status = result.passed
+        ? `${GREEN}PASS${RESET}`
+        : `${RED}FAIL${RESET}`;
+      const detail = `edit_file: ${result.editSuccesses}/${result.editCalls} succeeded, ${(result.duration / 1000).toFixed(1)}s`;
+
+      console.log(`  ${status} — ${detail}`);
+
+      if (result.passed) {
+        totalPassed++;
+        // Validate the file to show reason
+        const content = readFileSync(join(testDir, tc.fileName), "utf-8");
+        const v = tc.validate(content);
+        pass(v.reason);
+      } else {
+        const content = readFileSync(join(testDir, tc.fileName), "utf-8");
+        const v = tc.validate(content);
+        fail(v.reason);
+        info(
+          `Final content:\n${content
+            .split("\n")
+            .map((l, i) => `    ${i + 1}: ${l}`)
+            .join("\n")}`
+        );
+      }
+
+      results.push({ name: tc.name, passed: result.passed, detail });
+    } catch (error) {
+      const msg = error instanceof Error ? error.message : String(error);
+      console.log(`  ${RED}ERROR${RESET} — ${msg.slice(0, 200)}`);
+      fail(msg.slice(0, 200));
+      results.push({ name: tc.name, passed: false, detail: msg.slice(0, 100) });
+    }
+
+    // Reset file for next test (in case of side effects)
+    try {
+      rmSync(join(testDir, tc.fileName), { force: true });
+    } catch {}
+
+    console.log();
+  }
+
+  // Summary
+  console.log(`${BOLD}━━━ Summary ━━━${RESET}`);
+  for (const r of results) {
+    const icon = r.passed ? `${GREEN}✓${RESET}` : `${RED}✗${RESET}`;
+    console.log(`  ${icon} ${r.name} — ${r.detail}`);
+  }
+  console.log();
+  console.log(
+    `${BOLD}Result: ${totalPassed}/${TEST_CASES.length} passed (${Math.round((totalPassed / TEST_CASES.length) * 100)}%)${RESET}`
+  );
+
+  // Cleanup
+  try {
+    rmSync(testDir, { recursive: true, force: true });
+  } catch {}
+
+  if (totalPassed === TEST_CASES.length) {
+    console.log(
+      `\n${BOLD}${GREEN}🎉 ALL TESTS PASSED — 100% success rate!${RESET}\n`
+    );
+    process.exit(0);
+  } else {
+    console.log(`\n${BOLD}${RED}Some tests failed.${RESET}\n`);
+    process.exit(1);
+  }
+};
+
+main();

benchmarks/test-multi-model.ts

@@ -0,0 +1,280 @@
+#!/usr/bin/env bun
+/**
+ * Multi-model edit_file test runner
+ *
+ * Runs test-headless-edit-ops.ts against every available model
+ * and produces a summary table.
+ *
+ * Usage:
+ *   bun run scripts/test-multi-model-edit.ts [--timeout <seconds>]
+ */
+
+import { spawn } from "node:child_process";
+import { resolve } from "node:path";
+
+// ── Models ────────────────────────────────────────────────────
+const MODELS = [
+  { id: "MiniMaxAI/MiniMax-M2.5", short: "M2.5" },
+  // { id: "MiniMaxAI/MiniMax-M2.1", short: "M2.1" },  // masked: slow + timeout-prone
+  // { id: "zai-org/GLM-5", short: "GLM-5" },            // masked: API 503
+  { id: "zai-org/GLM-4.7", short: "GLM-4.7" },
+];
+
+// ── CLI args ──────────────────────────────────────────────────
+let perModelTimeoutSec = 900; // 15 min default per model (5 tests)
+const rawArgs = process.argv.slice(2);
+for (let i = 0; i < rawArgs.length; i++) {
+  if (rawArgs[i] === "--timeout" && i + 1 < rawArgs.length) {
+    const parsed = Number.parseInt(rawArgs[i + 1], 10);
+    if (Number.isNaN(parsed) || parsed <= 0) {
+      console.error(`Invalid --timeout value: ${rawArgs[i + 1]}`);
+      process.exit(1);
+    }
+    perModelTimeoutSec = parsed;
+    i++;
+}
+
+// ── Colors ────────────────────────────────────────────────────
+const BOLD = "\x1b[1m";
+const GREEN = "\x1b[32m";
+const RED = "\x1b[31m";
+const YELLOW = "\x1b[33m";
+const DIM = "\x1b[2m";
+const CYAN = "\x1b[36m";
+const RESET = "\x1b[0m";
+
+// ── Types ─────────────────────────────────────────────────────
+interface TestResult {
+  detail: string;
+  name: string;
+  passed: boolean;
+}
+
+interface ModelResult {
+  durationMs: number;
+  error?: string;
+  modelId: string;
+  modelShort: string;
+  tests: TestResult[];
+  totalPassed: number;
+  totalTests: number;
+}
+
+// ── Parse test-headless-edit-ops stdout ───────────────────────
+function parseOpsOutput(stdout: string): TestResult[] {
+  const results: TestResult[] = [];
+
+  // Match lines like: "  PASS — edit_file: 1/1 succeeded, 32.5s"
+  // or "  FAIL — edit_file: 0/3 succeeded, 15.2s"
+  // or "  ERROR — Timed out after 10 minutes"
+  // Following a line like: "1. Replace single line"
+  const lines = stdout.split("\n");
+
+  let currentTestName = "";
+  for (const line of lines) {
+    // Detect test name: starts with ANSI-colored bold cyan + "N. Name"
+    // Strip ANSI codes for matching
+    const stripped = line.replace(/\x1b\[[0-9;]*m/g, "");
+
+    // Test name pattern: "N. <name>"
+    const testNameMatch = stripped.match(/^\s*(\d+\.\s+.+)$/);
+    if (
+      testNameMatch &&
+      !stripped.includes("—") &&
+      !stripped.includes("✓") &&
+      !stripped.includes("✗")
+    ) {
+      currentTestName = testNameMatch[1].trim();
+      continue;
+    }
+
+    // Result line: PASS/FAIL/ERROR
+    if (currentTestName && stripped.includes("PASS")) {
+      const detail = stripped.replace(/^\s*PASS\s*—?\s*/, "").trim();
+      results.push({
+        name: currentTestName,
+        passed: true,
+        detail: detail || "passed",
+      });
+      currentTestName = "";
+    } else if (currentTestName && stripped.includes("FAIL")) {
+      const detail = stripped.replace(/^\s*FAIL\s*—?\s*/, "").trim();
+      results.push({
+        name: currentTestName,
+        passed: false,
+        detail: detail || "failed",
+      });
+      currentTestName = "";
+    } else if (currentTestName && stripped.includes("ERROR")) {
+      const detail = stripped.replace(/^\s*ERROR\s*—?\s*/, "").trim();
+      results.push({
+        name: currentTestName,
+        passed: false,
+        detail: detail || "error",
+      });
+      currentTestName = "";
+    }
+  }
+
+  return results;
+}
+
+// ── Run one model ────────────────────────────────────────────
+async function runModel(model: {
+  id: string;
+  short: string;
+}): Promise<ModelResult> {
+  const opsScript = resolve(import.meta.dir, "test-edit-ops.ts");
+  const startTime = Date.now();
+
+  return new Promise<ModelResult>((resolvePromise) => {
+    const proc = spawn(
+      "bun",
+      ["run", opsScript, "-m", model.id, "--no-translate"],
+      {
+        cwd: resolve(import.meta.dir),
+        env: { ...process.env, BUN_INSTALL: process.env.BUN_INSTALL },
+        stdio: ["ignore", "pipe", "pipe"],
+      }
+    );
+
+    let stdout = "";
+    let stderr = "";
+
+    proc.stdout.on("data", (chunk: Buffer) => {
+      stdout += chunk.toString();
+    });
+    proc.stderr.on("data", (chunk: Buffer) => {
+      stderr += chunk.toString();
+    });
+
+    const timeout = setTimeout(() => {
+      proc.kill("SIGTERM");
+      resolvePromise({
+        modelId: model.id,
+        modelShort: model.short,
+        tests: [],
+        totalPassed: 0,
+        totalTests: 0,
+        durationMs: Date.now() - startTime,
+        error: `Timed out after ${perModelTimeoutSec}s`,
+      });
+    }, perModelTimeoutSec * 1000);
+
+    proc.on("close", () => {
+      clearTimeout(timeout);
+      const tests = parseOpsOutput(stdout);
+      const totalPassed = tests.filter((t) => t.passed).length;
+
+      resolvePromise({
+        modelId: model.id,
+        modelShort: model.short,
+        tests,
+        totalPassed,
+        totalTests: Math.max(tests.length, 5),
+        durationMs: Date.now() - startTime,
+      });
+    });
+
+    proc.on("error", (err) => {
+      clearTimeout(timeout);
+      resolvePromise({
+        modelId: model.id,
+        modelShort: model.short,
+        tests: [],
+        totalPassed: 0,
+        totalTests: 0,
+        durationMs: Date.now() - startTime,
+        error: err.message,
+      });
+    });
+  });
+}
+
+// ── Main ──────────────────────────────────────────────────────
+const main = async () => {
+  console.log(`\n${BOLD}═══ Multi-Model edit_file Test Runner ═══${RESET}\n`);
+  console.log(`${DIM}Models: ${MODELS.map((m) => m.short).join(", ")}${RESET}`);
+  console.log(`${DIM}Timeout: ${perModelTimeoutSec}s per model${RESET}`);
+  console.log();
+
+  const allResults: ModelResult[] = [];
+
+  for (const model of MODELS) {
+    console.log(`${CYAN}${BOLD}▶ Testing ${model.short} (${model.id})${RESET}`);
+    const result = await runModel(model);
+    allResults.push(result);
+
+    const timeStr = `${(result.durationMs / 1000).toFixed(1)}s`;
+    if (result.error) {
+      console.log(`  ${RED}ERROR${RESET}: ${result.error} (${timeStr})`);
+    } else {
+      const color =
+        result.totalPassed === result.totalTests
+          ? GREEN
+          : result.totalPassed > 0
+            ? YELLOW
+            : RED;
+      console.log(
+        `  ${color}${result.totalPassed}/${result.totalTests} passed${RESET} (${timeStr})`
+      );
+      for (const t of result.tests) {
+        const icon = t.passed ? `${GREEN}✓${RESET}` : `${RED}✗${RESET}`;
+        console.log(`    ${icon} ${t.name}`);
+      }
+    }
+    console.log();
+  }
+
+  // ── Summary Table ──────────────────────────────────────────
+  console.log(`${BOLD}═══ Summary ═══${RESET}\n`);
+
+  // Per-model results
+  for (const r of allResults) {
+    const timeStr = `${(r.durationMs / 1000).toFixed(0)}s`;
+    const color = r.error ? RED : r.totalPassed === r.totalTests ? GREEN : r.totalPassed > 0 ? YELLOW : RED;
+    const label = r.error ? `ERROR: ${r.error}` : `${r.totalPassed}/${r.totalTests}`;
+    console.log(`  ${r.modelShort.padEnd(8)} ${color}${label}${RESET} (${timeStr})`);
+    for (const t of r.tests) {
+      const icon = t.passed ? `${GREEN}✓${RESET}` : `${RED}✗${RESET}`;
+      console.log(`    ${icon} ${t.name}`);
+    }
+  }
+
+  console.log();
+
+  // Overall
+  const totalModels = allResults.length;
+  const erroredModels = allResults.filter((r) => r.error).length;
+  const perfectModels = allResults.filter(
+    (r) => !r.error && r.totalPassed === r.totalTests && r.totalTests > 0
+  ).length;
+  console.log(
+    `${BOLD}Models with 100%: ${perfectModels}/${totalModels}${RESET}`
+  );
+
+  const overallPassed = allResults.reduce((sum, r) => sum + r.totalPassed, 0);
+  const overallTotal = allResults.reduce((sum, r) => sum + r.totalTests, 0);
+  console.log(
+    `${BOLD}Overall: ${overallPassed}/${overallTotal} (${Math.round((overallPassed / overallTotal) * 100)}%)${RESET}`
+  );
+
+  console.log();
+
+  if (erroredModels > 0) {
+    console.log(
+      `${BOLD}${RED}${erroredModels} model(s) errored. See details above.${RESET}\n`
+    );
+    process.exit(1);
+  } else if (perfectModels === totalModels) {
+    console.log(`${BOLD}${GREEN}🎉 ALL MODELS PASSED ALL TESTS!${RESET}\n`);
+    process.exit(0);
+  } else {
+    console.log(
+      `${BOLD}${YELLOW}Some models have failures. See details above.${RESET}\n`
+    );
+    process.exit(1);
+  }
+};
+
+main();

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": "3.8.1",
-        "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-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@3.8.1", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-vbtS0WUFOZpufKzlX2G83fIDry3rpiXej8zNuXNCkx7hF34rK04rj0zeBH9dL+kdNV0Ys0Wl1rR1Mjto28UcAw=="],
+    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.8.5", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-bbLu1We9NNhYAVp9Q/FK8dYFlYLp2PKfvdBCr+O6QjNRixdjp8Ru4RK7i9mKg0ybYBUzzCcbbC2Cc1o8orkhBA=="],
 
-    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.8.1", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-gLz6dLNg9hr7roqBjaqlxta6+XYCs032/FiE0CiwypIBtYOq5EAgDVJ95JY5DQ2M+3Un028d50yMfwsfNfGlSw=="],
+    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.8.5", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-N9GcmzYgL87UybSaMGiHc5lwT5Mxg1tyB502el5syouN39wfeUYoj37SonENrMUTiEfn75Lwv/5cSLCesSubpA=="],
 
-    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.8.1", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-teAIuHlR5xOAoUmA+e0bGzy3ikgIr+nCdyOPwHYm8jIp0aBUWAqbcdoQLeNTgenWpoM8vhHk+2xh4WcCeQzjEA=="],
+    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.8.5", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-ki4a7s1DD5z5wEKmzcchqAKOIpw0LsBvyF8ieqNLS5Xl8PWE0gAZ7rqjlXC54NTubpexVH6lO2yenFJsk2Zk9A=="],
 
-    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.8.1", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-VzBEq1H5dllEloouIoLdbw1icNUW99qmvErFrNj66mX42DNXK+f1zTtvBG8U6eeFfUBRRJoUjdCsvO65f8BkFA=="],
+    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.8.5", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-9+6hU3z503fBzuV0VjxIkTKFElbKacHijFcdKAussG6gPFLWmCRWtdowzEDwUfAoIsoHHH7FBwvh5waGp/ZksA=="],
 
-    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.8.1", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-8hDcb8s+wdQpQObSmiyaaTV0P/js2Bs9Lu+HmzrkKjuMLXXj/Gk7K0kKWMoEnMbMGfj86GfBHHIWmu9juI/SjA=="],
+    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.8.5", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-DmnMK/PgvdcCYL+OQE5iZWgi/vmjm0sIPQVQgSUbWn3izcUF7C5DtlxqaU2cKxNZwrhDTlJdLWxmJqgLmLqd9A=="],
 
-    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.8.1", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-idyH5bdYn7wrLkIkYr83omN83E2BjA/9DUHCX2we8VXbhDVbBgmMpUg8B8nKnd5NK/SyLHgRs5QqQJw8XBC0cQ=="],
+    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.8.5", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-jhCNStljsyapVq9X7PaHSOcWxxEA4BUcIibvoPs/xc7fVP8D47p651LzIRsM6STn6Bx684mlYbxxX1P/0QPKNg=="],
 
-    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.8.1", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-O30L1PUF9aq1vSOyadcXQOLnDFSTvYn6cGd5huh0LAK/us0hGezoahtXegMdFtDXPIIREJlkRQhyJiafza7YgA=="],
+    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.8.5", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-lcPBp9NCNQ6TnqzsN9p/K+xKwOzBoIPw7HncxmrXSberZ3uHy0K9uNraQ7fqnXIKWqQiK4kSwWfSHpmhbaHiNg=="],
 
     "on-finished": ["on-finished@2.4.1", "", { "dependencies": { "ee-first": "1.1.1" } }, "sha512-oVlzkg3ENAhCk2zdv7IJwd/QUD4z2RxRwpkcGY8psCVcCYZNq4wYnVWALHM+brtuJjePWiYF/ClmuDr8Ch5+kg=="],
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "3.8.2",
+  "version": "3.9.0",
   "description": "The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -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": "3.8.2",
-    "oh-my-opencode-darwin-x64": "3.8.2",
-    "oh-my-opencode-linux-arm64": "3.8.2",
-    "oh-my-opencode-linux-arm64-musl": "3.8.2",
-    "oh-my-opencode-linux-x64": "3.8.2",
-    "oh-my-opencode-linux-x64-musl": "3.8.2",
-    "oh-my-opencode-windows-x64": "3.8.2"
+    "oh-my-opencode-darwin-arm64": "3.9.0",
+    "oh-my-opencode-darwin-x64": "3.9.0",
+    "oh-my-opencode-darwin-x64-baseline": "3.9.0",
+    "oh-my-opencode-linux-arm64": "3.9.0",
+    "oh-my-opencode-linux-arm64-musl": "3.9.0",
+    "oh-my-opencode-linux-x64": "3.9.0",
+    "oh-my-opencode-linux-x64-baseline": "3.9.0",
+    "oh-my-opencode-linux-x64-musl": "3.9.0",
+    "oh-my-opencode-linux-x64-musl-baseline": "3.9.0",
+    "oh-my-opencode-windows-x64": "3.9.0",
+    "oh-my-opencode-windows-x64-baseline": "3.9.0"
   },
   "trustedDependencies": [
     "@ast-grep/cli",

packages/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-arm64",
-  "version": "3.8.2",
+  "version": "3.9.0",
   "description": "Platform-specific binary for oh-my-opencode (darwin-arm64)",
   "license": "MIT",
   "repository": {

packages/darwin-x64-baseline/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-x64-baseline",
-  "version": "3.1.1",
+  "version": "3.9.0",
   "description": "Platform-specific binary for oh-my-opencode (darwin-x64-baseline, no AVX2)",
   "license": "MIT",
   "repository": {

packages/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-x64",
-  "version": "3.8.2",
+  "version": "3.9.0",
   "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": "3.8.2",
+  "version": "3.9.0",
   "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": "3.8.2",
+  "version": "3.9.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64)",
   "license": "MIT",
   "repository": {

packages/linux-x64-baseline/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-baseline",
-  "version": "3.1.1",
+  "version": "3.9.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64-baseline, no AVX2)",
   "license": "MIT",
   "repository": {

packages/linux-x64-musl-baseline/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-musl-baseline",
-  "version": "3.1.1",
+  "version": "3.9.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64-musl-baseline, no AVX2)",
   "license": "MIT",
   "repository": {

packages/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-musl",
-  "version": "3.8.2",
+  "version": "3.9.0",
   "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": "3.8.2",
+  "version": "3.9.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64)",
   "license": "MIT",
   "repository": {

packages/windows-x64-baseline/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-windows-x64-baseline",
-  "version": "3.1.1",
+  "version": "3.9.0",
   "description": "Platform-specific binary for oh-my-opencode (windows-x64-baseline, no AVX2)",
   "license": "MIT",
   "repository": {

packages/windows-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-windows-x64",
-  "version": "3.8.2",
+  "version": "3.9.0",
   "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

@@ -17,7 +17,6 @@ import type { AvailableAgent, AvailableSkill, AvailableCategory } from "../dynam
 import { buildCategorySkillsDelegationGuide } from "../dynamic-agent-prompt-builder"
 import type { CategoryConfig } from "../../config/schema"
 import { mergeCategories } from "../../shared/merge-categories"
-import { createAgentToolRestrictions } from "../../shared/permission-compat"
 
 import { getDefaultAtlasPrompt } from "./default"
 import { getGptAtlasPrompt } from "./gpt"
@@ -30,7 +29,7 @@ import {
   buildDecisionMatrix,
 } from "./prompt-section-builder"
 
-const MODE: AgentMode = "primary"
+const MODE: AgentMode = "all"
 
 export type AtlasPromptSource = "default" | "gpt" | "gemini"
 
@@ -100,11 +99,6 @@ function buildDynamicOrchestratorPrompt(ctx?: OrchestratorContext): string {
 }
 
 export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
-  const restrictions = createAgentToolRestrictions([
-    "task",
-    "call_omo_agent",
-  ])
-
   const baseConfig = {
     description:
       "Orchestrates work via task() to complete ALL tasks in a todo list until fully done. (Atlas - OhMyOpenCode)",
@@ -113,7 +107,6 @@ export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
     temperature: 0.1,
     prompt: buildDynamicOrchestratorPrompt(ctx),
     color: "#10B981",
-    ...restrictions,
   }
 
   return baseConfig as AgentConfig

src/agents/atlas/index.ts

@@ -1,15 +1,2 @@
-export { ATLAS_SYSTEM_PROMPT, getDefaultAtlasPrompt } from "./default"
-export { ATLAS_GPT_SYSTEM_PROMPT, getGptAtlasPrompt } from "./gpt"
-export { ATLAS_GEMINI_SYSTEM_PROMPT, getGeminiAtlasPrompt } from "./gemini"
-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) {

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/index.ts

@@ -2,16 +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"
-export { PROMETHEUS_GEMINI_SYSTEM_PROMPT, getGeminiPrometheusPrompt } from "./gemini"
-
-// 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/sisyphus-gemini-overlays.ts

@@ -6,6 +6,8 @@
  * - 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.
@@ -77,3 +79,39 @@ Your internal confidence estimator is miscalibrated toward optimism. What feels
 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.ts

@@ -5,9 +5,10 @@ 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",
@@ -335,12 +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
 
@@ -477,9 +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>
 
 ${oracleSection}
@@ -567,7 +567,7 @@ export function createSisyphusAgent(
   if (isGeminiModel(model)) {
     prompt = prompt.replace(
       "</intent_verbalization>",
-      `</intent_verbalization>\n\n${buildGeminiToolMandate()}`
+      `</intent_verbalization>\n\n${buildGeminiIntentGateEnforcement()}\n\n${buildGeminiToolMandate()}`
     );
     prompt += "\n" + buildGeminiDelegationOverride();
     prompt += "\n" + buildGeminiVerificationOverride();

src/agents/tool-restrictions.test.ts

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

src/agents/types.test.ts

@@ -2,11 +2,17 @@ import { describe, test, expect } from "bun:test";
 import { isGptModel, isGeminiModel } from "./types";
 
 describe("isGptModel", () => {
-  test("standard openai provider models", () => {
+  test("standard openai provider gpt models", () => {
     expect(isGptModel("openai/gpt-5.2")).toBe(true);
     expect(isGptModel("openai/gpt-4o")).toBe(true);
-    expect(isGptModel("openai/o1")).toBe(true);
-    expect(isGptModel("openai/o3-mini")).toBe(true);
+  });
+
+  test("o-series models are not gpt by name", () => {
+    expect(isGptModel("openai/o1")).toBe(false);
+    expect(isGptModel("openai/o3-mini")).toBe(false);
+    expect(isGptModel("litellm/o1")).toBe(false);
+    expect(isGptModel("litellm/o3-mini")).toBe(false);
+    expect(isGptModel("litellm/o4-mini")).toBe(false);
   });
 
   test("github copilot gpt models", () => {
@@ -17,9 +23,6 @@ describe("isGptModel", () => {
   test("litellm proxied gpt models", () => {
     expect(isGptModel("litellm/gpt-5.2")).toBe(true);
     expect(isGptModel("litellm/gpt-4o")).toBe(true);
-    expect(isGptModel("litellm/o1")).toBe(true);
-    expect(isGptModel("litellm/o3-mini")).toBe(true);
-    expect(isGptModel("litellm/o4-mini")).toBe(true);
   });
 
   test("other proxied gpt models", () => {
@@ -27,6 +30,11 @@ describe("isGptModel", () => {
     expect(isGptModel("custom-provider/gpt-5.2")).toBe(true);
   });
 
+  test("venice provider gpt models", () => {
+    expect(isGptModel("venice/gpt-5.2")).toBe(true);
+    expect(isGptModel("venice/gpt-4o")).toBe(true);
+  });
+
   test("gpt4 prefix without hyphen (legacy naming)", () => {
     expect(isGptModel("litellm/gpt4o")).toBe(true);
     expect(isGptModel("ollama/gpt4")).toBe(true);
@@ -39,8 +47,8 @@ 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", () => {
@@ -50,29 +58,29 @@ describe("isGptModel", () => {
 
 describe("isGeminiModel", () => {
   test("#given google provider models #then returns true", () => {
-    expect(isGeminiModel("google/gemini-3-pro")).toBe(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-pro")).toBe(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-pro")).toBe(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-pro")).toBe(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-pro")).toBe(true);
+    expect(isGeminiModel("custom-provider/gemini-3.1-pro")).toBe(true);
     expect(isGeminiModel("ollama/gemini-3-flash")).toBe(true);
   });
 

src/agents/types.ts

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

src/agents/utils.test.ts

@@ -589,20 +589,22 @@ describe("createBuiltinAgents with requiresProvider gating (hephaestus)", () =>
     }
   })
 
-  test("hephaestus is created when github-copilot provider is connected", async () => {
-    // #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
@@ -2917,6 +2987,28 @@ describe("BackgroundManager.handleEvent - session.deleted cascade", () => {
     manager.shutdown()
     resetToastManager()
   })
+
+  test("should clean pending notifications for deleted sessions", () => {
+    //#given
+    const manager = createBackgroundManager()
+    const sessionID = "session-pending-notifications"
+
+    manager.queuePendingNotification(sessionID, "<system-reminder>queued</system-reminder>")
+    expect(getPendingNotifications(manager).get(sessionID)).toEqual([
+      "<system-reminder>queued</system-reminder>",
+    ])
+
+    //#when
+    manager.handleEvent({
+      type: "session.deleted",
+      properties: { info: { id: sessionID } },
+    })
+
+    //#then
+    expect(getPendingNotifications(manager).has(sessionID)).toBe(false)
+
+    manager.shutdown()
+  })
 })
 
 describe("BackgroundManager.handleEvent - session.error", () => {

src/features/background-agent/manager.ts

@@ -93,6 +93,7 @@ export class BackgroundManager {
 
   private tasks: Map<string, BackgroundTask>
   private notifications: Map<string, BackgroundTask[]>
+  private pendingNotifications: Map<string, string[]>
   private pendingByParent: Map<string, Set<string>>  // Track pending tasks per parent for batching
   private client: OpencodeClient
   private directory: string
@@ -125,6 +126,7 @@ export class BackgroundManager {
   ) {
     this.tasks = new Map()
     this.notifications = new Map()
+    this.pendingNotifications = new Map()
     this.pendingByParent = new Map()
     this.client = ctx.client
     this.directory = ctx.directory
@@ -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,
       },
@@ -828,6 +830,8 @@ export class BackgroundManager {
         tasksToCancel.set(descendant.id, descendant)
       }
 
+      this.pendingNotifications.delete(sessionID)
+
       if (tasksToCancel.size === 0) return
 
       for (const task of tasksToCancel.values()) {
@@ -864,6 +868,13 @@ export class BackgroundManager {
           subagentSessions.delete(task.sessionID)
         }
       }
+
+      for (const task of tasksToCancel.values()) {
+        if (task.parentSessionID) {
+          this.pendingNotifications.delete(task.parentSessionID)
+        }
+      }
+
       SessionCategoryRegistry.remove(sessionID)
     }
 
@@ -917,6 +928,32 @@ export class BackgroundManager {
     this.notifications.delete(sessionID)
   }
 
+  queuePendingNotification(sessionID: string | undefined, notification: string): void {
+    if (!sessionID) return
+    const existingNotifications = this.pendingNotifications.get(sessionID) ?? []
+    existingNotifications.push(notification)
+    this.pendingNotifications.set(sessionID, existingNotifications)
+  }
+
+  injectPendingNotificationsIntoChatMessage(output: { parts: Array<{ type: string; text?: string; [key: string]: unknown }> }, sessionID: string): void {
+    const pendingNotifications = this.pendingNotifications.get(sessionID)
+    if (!pendingNotifications || pendingNotifications.length === 0) {
+      return
+    }
+
+    this.pendingNotifications.delete(sessionID)
+    const notificationContent = pendingNotifications.join("\n\n")
+    const firstTextPartIndex = output.parts.findIndex((part) => part.type === "text")
+
+    if (firstTextPartIndex === -1) {
+      output.parts.unshift(createInternalAgentTextPart(notificationContent))
+      return
+    }
+
+    const originalText = output.parts[firstTextPartIndex].text ?? ""
+    output.parts[firstTextPartIndex].text = `${notificationContent}\n\n---\n\n${originalText}`
+  }
+
   /**
    * Validates that a session has actual assistant/tool output before marking complete.
    * Prevents premature completion when session.idle fires before agent responds.
@@ -1340,6 +1377,7 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
               taskId: task.id,
               parentSessionID: task.parentSessionID,
             })
+            this.queuePendingNotification(task.parentSessionID, notification)
           } else {
             log("[background-agent] Failed to send notification:", error)
           }
@@ -1568,6 +1606,7 @@ Use \`background_output(task_id="${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-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
-}