oh-my-opencode 5.0.0-beta.12 → 5.0.0-beta.14

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (145) hide show
  1. package/.agents/skills/senpi-qa/SKILL.md +80 -0
  2. package/.agents/skills/senpi-qa/scripts/resolve-evidence-dir.mjs +65 -0
  3. package/.agents/skills/senpi-qa/scripts/resolve-evidence-dir.test.mjs +171 -0
  4. package/README.ja.md +25 -21
  5. package/README.ko.md +25 -21
  6. package/README.md +26 -22
  7. package/README.ru.md +24 -20
  8. package/README.zh-cn.md +25 -21
  9. package/dist/cli/index.js +16747 -15223
  10. package/dist/cli-node/index.js +16898 -15374
  11. package/dist/create-hooks.d.ts +1 -0
  12. package/dist/features/btw-side/btw-command-draft.d.ts +7 -0
  13. package/dist/features/btw-side/context-injector.d.ts +15 -0
  14. package/dist/features/btw-side/index.d.ts +8 -0
  15. package/dist/features/btw-side/metadata.d.ts +15 -0
  16. package/dist/features/btw-side/parent-context-budget.d.ts +9 -0
  17. package/dist/features/btw-side/server-session-registry.d.ts +8 -0
  18. package/dist/features/btw-side/tui-adoption-cache.d.ts +13 -0
  19. package/dist/features/btw-side/tui-adoption-guard.d.ts +5 -0
  20. package/dist/features/btw-side/tui-controller-types.d.ts +68 -0
  21. package/dist/features/btw-side/tui-controller.d.ts +19 -0
  22. package/dist/features/btw-side/tui-escape-return.d.ts +12 -0
  23. package/dist/features/btw-side/tui-keymap.d.ts +17 -0
  24. package/dist/features/btw-side/tui-parent-validator.d.ts +6 -0
  25. package/dist/features/btw-side/tui-picker-options.d.ts +20 -0
  26. package/dist/features/btw-side/tui-picker.d.ts +9 -0
  27. package/dist/features/btw-side/tui-prompt-queue.d.ts +8 -0
  28. package/dist/features/btw-side/tui-session-bridge.d.ts +11 -0
  29. package/dist/features/btw-side/tui-session-catalog.d.ts +35 -0
  30. package/dist/features/btw-side/tui-side-removal.d.ts +11 -0
  31. package/dist/features/btw-side/tui-side-start.d.ts +9 -0
  32. package/dist/features/btw-side/tui-wiring.d.ts +8 -0
  33. package/dist/features/opengateway-provider/index.d.ts +13 -0
  34. package/dist/hooks/runtime-fallback/chat-message-handler.d.ts +2 -0
  35. package/dist/hooks/runtime-fallback/retry-model-payload.d.ts +1 -0
  36. package/dist/hooks/runtime-fallback/runtime-model-settings.d.ts +6 -0
  37. package/dist/hooks/runtime-fallback/session-status-handler.d.ts +1 -1
  38. package/dist/hooks/runtime-fallback/types.d.ts +3 -1
  39. package/dist/index.js +10814 -6018
  40. package/dist/plugin/event-session-lifecycle.d.ts +1 -0
  41. package/dist/plugin/hooks/create-core-hooks.d.ts +1 -0
  42. package/dist/plugin/hooks/create-transform-hooks.d.ts +2 -0
  43. package/dist/plugin/messages-transform.d.ts +1 -0
  44. package/dist/shared/index.d.ts +1 -0
  45. package/dist/shared/runtime-fallback-retry-marker.d.ts +16 -0
  46. package/dist/skills/frontend/SKILL.md +1 -0
  47. package/dist/skills/frontend/references/design/print-paged-media.md +76 -0
  48. package/dist/skills/ulw-research/SKILL.md +1 -1
  49. package/dist/skills/visual-qa/SKILL.md +3 -2
  50. package/dist/tui.js +8273 -8493
  51. package/package.json +30 -29
  52. package/packages/git-bash-mcp/dist/cli.js +5 -1
  53. package/packages/git-bash-mcp/package.json +1 -1
  54. package/packages/lsp-daemon/dist/cli.js +86 -114
  55. package/packages/lsp-daemon/dist/client.js +87 -118
  56. package/packages/lsp-daemon/dist/ensure-daemon.js +1 -0
  57. package/packages/lsp-daemon/dist/index.js +93 -123
  58. package/packages/lsp-daemon/dist/version-reap.js +1 -1
  59. package/packages/lsp-tools-mcp/dist/cli.js +67 -94
  60. package/packages/lsp-tools-mcp/dist/lsp/manager.js +62 -92
  61. package/packages/lsp-tools-mcp/dist/mcp.js +69 -96
  62. package/packages/lsp-tools-mcp/dist/request-context.js +11 -12
  63. package/packages/lsp-tools-mcp/dist/tools.js +73 -104
  64. package/packages/omo-codex/plugin/.codex-plugin/plugin.json +1 -1
  65. package/packages/omo-codex/plugin/components/bootstrap/dist/cli.js +30 -29
  66. package/packages/omo-codex/plugin/components/bootstrap/hooks/hooks.json +1 -1
  67. package/packages/omo-codex/plugin/components/bootstrap/package.json +1 -1
  68. package/packages/omo-codex/plugin/components/bootstrap/src/hook.ts +1 -0
  69. package/packages/omo-codex/plugin/components/codegraph/dist/cli.js +86 -65
  70. package/packages/omo-codex/plugin/components/codegraph/dist/serve.js +86 -66
  71. package/packages/omo-codex/plugin/components/codegraph/package.json +4 -4
  72. package/packages/omo-codex/plugin/components/codegraph/src/mcp-bridge.ts +1 -0
  73. package/packages/omo-codex/plugin/components/codegraph/src/session-start-hook-runtime.ts +1 -0
  74. package/packages/omo-codex/plugin/components/comment-checker/dist/cli.js +2 -1
  75. package/packages/omo-codex/plugin/components/comment-checker/hooks/hooks.json +1 -1
  76. package/packages/omo-codex/plugin/components/comment-checker/package.json +5 -5
  77. package/packages/omo-codex/plugin/components/comment-checker/src/runner.ts +1 -0
  78. package/packages/omo-codex/plugin/components/git-bash/AGENTS.md +1 -1
  79. package/packages/omo-codex/plugin/components/git-bash/hooks/hooks.json +2 -2
  80. package/packages/omo-codex/plugin/components/git-bash/package.json +3 -4
  81. package/packages/omo-codex/plugin/components/lazycodex-executor-verify/hooks/hooks.json +1 -1
  82. package/packages/omo-codex/plugin/components/lazycodex-executor-verify/package.json +5 -5
  83. package/packages/omo-codex/plugin/components/lsp/dist/.omo-runtime-manifest.json +3 -3
  84. package/packages/omo-codex/plugin/components/lsp/dist/cli.js +70 -107
  85. package/packages/omo-codex/plugin/components/lsp/hooks/hooks.json +2 -2
  86. package/packages/omo-codex/plugin/components/lsp/package.json +5 -5
  87. package/packages/omo-codex/plugin/components/lsp/src/cli.ts +1 -1
  88. package/packages/omo-codex/plugin/components/rules/dist/cli.js +14 -12
  89. package/packages/omo-codex/plugin/components/rules/hooks/hooks.json +4 -4
  90. package/packages/omo-codex/plugin/components/rules/package.json +7 -7
  91. package/packages/omo-codex/plugin/components/start-work-continuation/hooks/hooks.json +2 -2
  92. package/packages/omo-codex/plugin/components/start-work-continuation/package.json +5 -5
  93. package/packages/omo-codex/plugin/components/teammode/hooks/hooks.json +1 -1
  94. package/packages/omo-codex/plugin/components/teammode/package.json +5 -5
  95. package/packages/omo-codex/plugin/components/telemetry/dist/cli.js +2266 -405
  96. package/packages/omo-codex/plugin/components/telemetry/dist/posthog.js +2270 -409
  97. package/packages/omo-codex/plugin/components/telemetry/hooks/hooks.json +1 -1
  98. package/packages/omo-codex/plugin/components/telemetry/package.json +5 -5
  99. package/packages/omo-codex/plugin/components/ultrawork/hooks/hooks.json +1 -1
  100. package/packages/omo-codex/plugin/components/ultrawork/package.json +5 -5
  101. package/packages/omo-codex/plugin/components/ulw-loop/dist/cli.js +1 -3
  102. package/packages/omo-codex/plugin/components/ulw-loop/dist/paths.js +1 -1
  103. package/packages/omo-codex/plugin/components/ulw-loop/hooks/hooks.json +4 -4
  104. package/packages/omo-codex/plugin/components/ulw-loop/package.json +5 -5
  105. package/packages/omo-codex/plugin/components/ulw-loop/src/paths.ts +1 -1
  106. package/packages/omo-codex/plugin/components/ulw-loop/test/cli-create-goals.test.ts +25 -0
  107. package/packages/omo-codex/plugin/components/ulw-loop/test/paths.test.ts +9 -0
  108. package/packages/omo-codex/plugin/components/ulw-loop/vitest.config.ts +1 -0
  109. package/packages/omo-codex/plugin/hooks/post-compact-resetting-git-bash-mcp-reminder.json +1 -1
  110. package/packages/omo-codex/plugin/hooks/post-compact-resetting-lsp-diagnostics-cache.json +1 -1
  111. package/packages/omo-codex/plugin/hooks/post-compact-resetting-project-rule-cache.json +1 -1
  112. package/packages/omo-codex/plugin/hooks/post-tool-use-checking-codegraph-init-guidance.json +1 -1
  113. package/packages/omo-codex/plugin/hooks/post-tool-use-checking-comments.json +1 -1
  114. package/packages/omo-codex/plugin/hooks/post-tool-use-checking-lsp-diagnostics.json +1 -1
  115. package/packages/omo-codex/plugin/hooks/post-tool-use-checking-thread-title-hygiene.json +1 -1
  116. package/packages/omo-codex/plugin/hooks/post-tool-use-matching-project-rules.json +1 -1
  117. package/packages/omo-codex/plugin/hooks/pre-tool-use-enforcing-unlimited-goal-budget.json +1 -1
  118. package/packages/omo-codex/plugin/hooks/pre-tool-use-guarding-ulw-loop-spawns.json +1 -1
  119. package/packages/omo-codex/plugin/hooks/pre-tool-use-recommending-git-bash-mcp.json +1 -1
  120. package/packages/omo-codex/plugin/hooks/session-start-checking-auto-update.json +1 -1
  121. package/packages/omo-codex/plugin/hooks/session-start-checking-bootstrap-provisioning.json +1 -1
  122. package/packages/omo-codex/plugin/hooks/session-start-checking-codegraph-bootstrap.json +1 -1
  123. package/packages/omo-codex/plugin/hooks/session-start-loading-project-rules.json +1 -1
  124. package/packages/omo-codex/plugin/hooks/session-start-recording-session-telemetry.json +1 -1
  125. package/packages/omo-codex/plugin/hooks/stop-checking-start-work-continuation.json +1 -1
  126. package/packages/omo-codex/plugin/hooks/stop-checking-ulw-loop-resume.json +1 -1
  127. package/packages/omo-codex/plugin/hooks/subagent-stop-checking-start-work-continuation.json +1 -1
  128. package/packages/omo-codex/plugin/hooks/subagent-stop-verifying-lazycodex-executor-evidence.json +1 -1
  129. package/packages/omo-codex/plugin/hooks/user-prompt-submit-checking-ultrawork-trigger.json +1 -1
  130. package/packages/omo-codex/plugin/hooks/user-prompt-submit-checking-ulw-loop-steering.json +1 -1
  131. package/packages/omo-codex/plugin/hooks/user-prompt-submit-loading-project-rules.json +1 -1
  132. package/packages/omo-codex/plugin/package-lock.json +661 -375
  133. package/packages/omo-codex/plugin/package.json +1 -1
  134. package/packages/omo-codex/plugin/shared/package.json +2 -3
  135. package/packages/omo-codex/plugin/skills/frontend/SKILL.md +1 -0
  136. package/packages/omo-codex/plugin/skills/frontend/references/design/print-paged-media.md +76 -0
  137. package/packages/omo-codex/plugin/skills/ulw-research/SKILL.md +1 -1
  138. package/packages/omo-codex/plugin/skills/visual-qa/SKILL.md +3 -2
  139. package/packages/omo-codex/scripts/install-dist/install-local.mjs +2410 -504
  140. package/packages/shared-skills/skills/frontend/SKILL.md +1 -0
  141. package/packages/shared-skills/skills/frontend/references/design/print-paged-media.md +76 -0
  142. package/packages/shared-skills/skills/ulw-research/SKILL.md +1 -1
  143. package/packages/shared-skills/skills/visual-qa/SKILL.md +3 -2
  144. package/script/qa/web-terminal-visual-qa.mjs +2 -0
  145. package/script/qa/xterm-live-terminal.mjs +18 -2
package/README.ko.md CHANGED
@@ -66,7 +66,7 @@
66
66
  [![GitHub Issues](https://img.shields.io/github/issues/code-yeongyu/oh-my-openagent?color=ff80eb&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-openagent/issues)
67
67
  [![License](https://img.shields.io/badge/license-SUL--1.0-white?labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-openagent/blob/dev/LICENSE.md)
68
68
  [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/code-yeongyu/oh-my-openagent)
69
- [![Docs](https://img.shields.io/badge/docs-omo.vibetip.help-369eff?labelColor=black&logo=readthedocs&logoColor=white&style=flat-square)](https://omo.vibetip.help/docs)
69
+ [![Docs](https://img.shields.io/badge/docs-omo.dev-369eff?labelColor=black&logo=readthedocs&logoColor=white&style=flat-square)](https://omo.dev/docs)
70
70
 
71
71
  [English](README.md) | [한국어](README.ko.md) | [日本語](README.ja.md) | [简体中文](README.zh-cn.md)
72
72
 
@@ -130,11 +130,11 @@ https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/refs/heads/dev/do
130
130
  curl -s https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/refs/heads/dev/docs/guide/installation.md
131
131
  ```
132
132
 
133
- **참고**: 배포된 npm 패키지와 CLI 바이너리 이름은 여전히 `oh-my-opencode`입니다(전환 기간 동안 `oh-my-openagent`로도 함께 배포됩니다). `opencode.json` 안에서는 호환성 레이어가 이제 `oh-my-openagent` 플러그인 엔트리를 우선합니다. 기존 `oh-my-opencode` 엔트리도 경고와 함께 여전히 로드됩니다. 플러그인 설정 파일도 여전히 `oh-my-opencode.json`이나 `oh-my-opencode.jsonc`를 많이 씁니다. 전환 기간 동안에는 기존 이름과 이름 둘 다 인식됩니다.
133
+ **참고**: 배포된 npm 패키지와 CLI 바이너리 이름은 여전히 `oh-my-opencode`입니다(전환 기간 동안 `oh-my-openagent`로도 함께 배포됩니다). `opencode.json` 안에서는 호환성 레이어가 이제 `oh-my-openagent` 플러그인 엔트리를 우선합니다. 기존 `oh-my-opencode` 엔트리도 경고와 함께 여전히 로드됩니다. 런타임 설정은 `~/.omo/omo.jsonc`와 워킹 디렉터리에서 위로 탐색하는 프로젝트 `.omo/omo.jsonc`입니다. 기존 `oh-my-openagent.json[c]` / `oh-my-opencode.json[c]` 파일은 마이그레이션 엔진이 번만 가져오고, 후에는 읽지 않습니다.
134
134
 
135
135
  익명 텔레메트리는 활성 설치 수(DAU/WAU/MAU) 집계를 위해 기본적으로 활성화되어 있습니다. 머신당 UTC 하루에 최대 1회만 이벤트가 전송되며, 해시된 설치 식별자를 사용하고 원시 호스트명은 절대 사용하지 않으며 PostHog person profile은 생성되지 않습니다. `OMO_SEND_ANONYMOUS_TELEMETRY=0` 또는 `OMO_DISABLE_POSTHOG=1`로 비활성화할 수 있습니다. [개인정보처리방침](docs/legal/privacy-policy.md)과 [서비스 이용약관](docs/legal/terms-of-service.md)을 참조하세요.
136
136
 
137
- **Ultimate vs Light:** oh-my-openagent는 같은 제품의 두 에디션으로 출시됩니다. **Ultimate 에디션**(`bunx oh-my-openagent install` 또는 `--platform=opencode`, 기본값)은 OpenCode 위에서 풀 기능 — 11 agent, 54+ hook, Team Mode, 모든 MCP, 슬래시 명령, IntentGate 모드 — 을 제공합니다. **Light 에디션**(`npx lazycodex-ai install` 또는 `bunx oh-my-openagent install --platform=codex`)은 OpenAI Codex CLI의 플러그인 시스템에 깔끔히 포팅되는 8개 컴포넌트(`rules`, `comment-checker`, `git-bash`, `lsp`, `ultrawork`, `ulw-loop`, `start-work-continuation`, `telemetry`)를 제공합니다. 둘 다 설치하려면 `--platform=both`. Codex 전용 텔레메트리는 `OMO_CODEX_DISABLE_POSTHOG=1` 또는 `OMO_CODEX_SEND_ANONYMOUS_TELEMETRY=0`으로 비활성화할 수 있습니다.
137
+ **Ultimate vs Light:** oh-my-openagent는 같은 제품의 두 에디션으로 출시됩니다. **Ultimate 에디션**(`bunx oh-my-openagent install` 또는 `--platform=opencode`, 기본값)은 OpenCode 위에서 풀 기능 — 11 agent, 54+ hook, Team Mode, 모든 MCP, 슬래시 명령, IntentGate 모드 — 을 제공합니다. **Light 에디션**(`npx lazycodex-ai install` 또는 `bunx oh-my-openagent install --platform=codex`)은 OpenAI Codex CLI의 플러그인 시스템에 깔끔히 포팅되는 핵심 컴포넌트(`rules`, `comment-checker`, `git-bash`, `lsp`, `ultrawork`, `ulw-loop`, `start-work-continuation`, `telemetry`)에 더해 `teammode`와 지원 컴포넌트(`bootstrap`, `codegraph`, `lcx` 등)제공하고, Codex 에이전트 TOML을 `~/.codex/agents/`에 설치합니다. 둘 다 설치하려면 `--platform=both`. Codex 전용 텔레메트리는 `OMO_CODEX_DISABLE_POSTHOG=1` 또는 `OMO_CODEX_SEND_ANONYMOUS_TELEMETRY=0`으로 비활성화할 수 있습니다.
138
138
 
139
139
  ---
140
140
 
@@ -166,19 +166,19 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
166
166
  | | 기능 | Editions | 하는 일 |
167
167
  | :---: | :------------------------------------------------------- | :------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
168
168
  | 🤖 | **Discipline Agents** | Ultimate | Sisyphus가 Hephaestus, Oracle, Librarian, Explore를 지휘합니다. 병렬로 도는 풀스택 AI 개발팀. |
169
- | 🧩 | **Codex CLI Light Edition** | Light | OpenAI Codex CLI에서 동작하는 omo의 8개 포팅 컴포넌트(rules, comment-checker, git-bash, LSP, ultrawork, ulw-loop, start-work continuation, telemetry). 설치: `npx lazycodex-ai install`. |
169
+ | 🧩 | **Codex CLI Light Edition** | Light | OpenAI Codex CLI에서 동작하는 omo의 포팅 컴포넌트(rules, comment-checker, git-bash, LSP, ultrawork, ulw-loop, start-work continuation, telemetry, teammode 등). 설치: `npx lazycodex-ai install`. |
170
170
  | 👥 | **Team Mode** (v4.0, opt-in) | Ultimate | 리드 에이전트 + 최대 8명의 병렬 멤버, 실시간 tmux 시각화, 전용 `team_*` 도구. `hyperplan`(5명의 적대적 비평가)과 `security-research`(3명의 헌터 + 2명의 PoC 엔지니어)를 구동합니다. [문서 →](docs/guide/team-mode.md) |
171
171
  | ⚡ | **`ultrawork` / `ulw`** | Both | 한 단어. 모든 에이전트(Ultimate)나 Codex `ultrawork` 컴포넌트(Light)가 켜집니다. 끝날 때까지 멈추지 않습니다. |
172
- | 🚪 | **[IntentGate](https://factory.ai/news/terminal-bench)** | Ultimate | 분류하거나 행동하기 전에 사용자의 진짜 의도부터 분석합니다. `search` / `analyze` / `team` / `hyperplan` 트리거. (Light는 `ulw` / `ultrawork`만 hook.) |
173
- | 🔗 | **Hash-Anchored Edit Tool** | Ultimate | `LINE#ID` 콘텐츠 해시가 모든 변경을 검증합니다. 낡은 라인 에러 0건. [oh-my-pi](https://github.com/can1357/oh-my-pi)에서 영감. [The Harness Problem →](https://blog.can.ac/2026/02/12/the-harness-problem/) (Codex는 자체 `apply_patch` 사용.) |
172
+ | 🚪 | **[IntentGate](https://factory.ai/news/terminal-bench)** | Ultimate | 분류하거나 행동하기 전에 사용자의 진짜 의도부터 분석합니다. 이상 문자 그대로의 오해석은 없습니다. (Light는 `ulw` / `ultrawork` 키워드만 인식.) |
173
+ | 🔗 | **Hash-Anchored Edit Tool** | Ultimate | Hashline(`LINE#ID`) 편집/읽기 태깅. 옵트인: `~/.omo/omo.jsonc`에 `hashline_edit: true` 설정. 낡은 라인 에러 0건. [oh-my-pi](https://github.com/can1357/oh-my-pi)에서 영감. [The Harness Problem →](https://blog.can.ac/2026/02/12/the-harness-problem/) (Codex는 자체 `apply_patch` 사용.) |
174
174
  | 🛠️ | **LSP + AST-Grep** | Both | 워크스페이스 리네임, 빌드 전 진단, AST 기반 리라이트. LSP는 MCP로 제공하고 AST-Grep은 공유 `ast-grep` skill과 `sg`로 제공합니다. |
175
175
  | 🧠 | **Background Agents** | Ultimate | 전문가 5명 이상을 동시에 발사. 컨텍스트는 가볍게. 결과는 준비되면 도착. |
176
176
  | 📚 | **Built-in MCPs** | Both | Ultimate는 Exa(웹 검색), Context7(공식 문서), Grep.app(GitHub 검색)를 런타임에 주입합니다. Light는 plugin-scoped MCP로 `grep_app`, `context7`, `git_bash`, `lsp`를 제공합니다. |
177
- | 🔁 | **Ralph Loop / `/ulw-loop`** | Ultimate | 자기참조 루프. 100% 끝날 때까지 멈추지 않습니다. |
177
+ | 🔁 | **Goal / `/goal`** | Ultimate | `/goal`이 스레드의 영속 목표를 설정합니다. idle continuation은 `goal.enabled`가 true일 때만 동작합니다(기본값 false). |
178
178
  | ✅ | **Todo Enforcer** (Boulder) | Ultimate | 에이전트가 놀고 있나요? 시스템이 다시 끌어옵니다. 당신의 작업은 반드시 끝납니다. |
179
179
  | 💬 | **Comment Checker** | Both | 주석에 AI 슬롭 금지. 동일한 `@code-yeongyu/comment-checker` 바이너리가 두 에디션 모두에서 동작. |
180
180
  | 📜 | **Rules Injection** | Both | `AGENTS.md` / `CLAUDE.md` / `.omo/rules/**` 계층형 컨텍스트 주입. Ultimate은 hook, Light는 `rules` 컴포넌트. |
181
- | 🧬 | **Ulw Loop** | Light | `.omo/ulw-loop/` evidence audit 기반 영속 멀티 골 오케스트레이션. 현재 Codex 전용; OpenCode 사이드 포팅은 로드맵에 있음. |
181
+ | 🧬 | **Ulw Loop** | Light | evidence audit 기반 영속 멀티 골 오케스트레이션을 위한 Codex 컴포넌트 + CLI. OpenCode에서는 **Goal / `/goal`**을 사용하세요. |
182
182
  | 🖥️ | **Tmux Integration** | Ultimate | 풀 인터랙티브 터미널. REPL, 디버거, TUI 전부 라이브. |
183
183
  | 🔌 | **Claude Code Compatible** | Ultimate | 쓰시던 hook, command, skill, MCP, plugin 전부 그대로 동작합니다. (Codex는 자체 플러그인 시스템 보유.) |
184
184
  | 🎯 | **Skill-Embedded MCPs** | Ultimate | 스킬이 자기만의 MCP 서버를 들고 다닙니다. 컨텍스트 낭비 없음. |
@@ -194,7 +194,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
194
194
  <td align="center"><img src=".github/assets/hephaestus.png" height="300" /></td>
195
195
  </tr></table>
196
196
 
197
- **Sisyphus** (`claude-opus-5` / **`kimi-k3`** / **`glm-5`**)는 메인 오케스트레이터입니다. 계획을 세우고, 전문가에게 위임하고, 공격적인 병렬 실행으로 작업을 끝까지 밀어붙입니다. 중간에 멈추지 않습니다. Claude Opus 5와 Kimi K3가 권장 기본값입니다.
197
+ **Sisyphus** (`claude-opus-5` / **`kimi-k3`** / **`gpt-5.6-sol`** / **`glm-5.2`**)는 메인 오케스트레이터입니다. 계획을 세우고, 전문가에게 위임하고, 공격적인 병렬 실행으로 작업을 끝까지 밀어붙입니다. 중간에 멈추지 않습니다. Claude Opus 5와 Kimi K3가 권장 기본값입니다.
198
198
 
199
199
  **Hephaestus** (OpenAI, GitHub Copilot, Vercel 또는 OpenCode에서 medium effort의 `gpt-5.6-sol`만 사용하는)는 자율적으로 깊게 파는 작업자입니다. 레시피가 아니라 목표를 주세요. 코드베이스를 탐색하고, 패턴을 조사하고, 손을 잡아주지 않아도 엔드투엔드로 실행합니다. *The Legitimate Craftsman.*
200
200
 
@@ -213,7 +213,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
213
213
  **Team Mode**는 oh-my-openagent를 "서브에이전트를 가진 한 명의 에이전트"에서 진짜 멀티 에이전트 시스템으로 바꿉니다. 리드 에이전트가 카테고리별 전문화된 멤버 팀을 지휘하며, 모두 **병렬로** 동작하고 전용 도구(`team_create`, `team_send_message`, `team_task_create`, `team_status`, ...)로 통신합니다. tmux 레이아웃의 focus + grid 윈도우에서 모든 멤버의 작업을 동시에 지켜보세요.
214
214
 
215
215
  ```jsonc
216
- // .opencode/oh-my-openagent.jsonc
216
+ // ~/.omo/omo.jsonc (또는 프로젝트 .omo/omo.jsonc)
217
217
  {
218
218
  "team_mode": {
219
219
  "enabled": true,
@@ -241,7 +241,7 @@ Sisyphus가 서브에이전트에 위임할 때는 모델을 직접 고르지
241
241
  | `quick` | 단일 파일 변경, 오타 수정 |
242
242
  | `ultrabrain` | 어려운 로직, 아키텍처 결정 |
243
243
 
244
- 에이전트는 필요한 작업 종류만 말하고, 하네스가 적합한 모델을 고릅니다. `ultrabrain`은 OpenAI 또는 Vercel에서 사용 가능하면 GPT-5.6 Sol xhigh로, 그다음 GPT-5.6 Sol xhigh로 라우팅됩니다. 당신이 건드릴 건 없습니다.
244
+ 에이전트는 필요한 작업 종류만 말하고, 하네스가 적합한 모델을 고릅니다. `ultrabrain`은 GPT-5.6 Sol max로 라우팅됩니다(OpenAI / Vercel, 그다음 GitHub Copilot, 그다음 OpenCode). 당신이 건드릴 건 없습니다.
245
245
 
246
246
  ### Claude Code 호환성
247
247
 
@@ -272,7 +272,7 @@ MCP 서버는 컨텍스트 예산을 갉아먹습니다. 우리가 고쳤습니
272
272
  >
273
273
  > <br/>- [Can Bölük, The Harness Problem](https://blog.can.ac/2026/02/12/the-harness-problem/)
274
274
 
275
- [oh-my-pi](https://github.com/can1357/oh-my-pi)에서 영감을 받아 **Hashline**을 만들었습니다. 에이전트가 읽는 모든 라인은 콘텐츠 해시가 붙어 돌아옵니다:
275
+ [oh-my-pi](https://github.com/can1357/oh-my-pi)에서 영감을 받아 **Hashline**을 만들었습니다. `hashline_edit`를 활성화하면 에이전트가 읽는 모든 라인이 콘텐츠 해시가 붙어 돌아옵니다:
276
276
 
277
277
  ```
278
278
  11#VK| function hello() {
@@ -303,7 +303,7 @@ project/
303
303
 
304
304
  복잡한 작업인가요? 프롬프트 쓰고 기도하지 마세요.
305
305
 
306
- `/start-work`가 Prometheus 호출합니다. **진짜 엔지니어처럼 인터뷰**를 진행하고, 스코프와 모호한 부분을 짚어내고, 코드에 손대기 전에 검증된 계획을 세웁니다. 에이전트는 뭘 만들지 알고 나서야 시작합니다.
306
+ Prometheus **진짜 엔지니어처럼 인터뷰**를 진행하고, 스코프와 모호한 부분을 짚어내고, 코드에 손대기 전에 검증된 계획을 `.omo/plans/`에 작성합니다. `/start-work`는 그 계획으로 **Atlas** 작업 세션을 시작합니다. 에이전트는 뭘 만들지 알고 나서야 시작합니다.
307
307
 
308
308
  ### Skills
309
309
 
@@ -341,12 +341,16 @@ oh-my-openagent를 제거하려면:
341
341
  2. **설정 파일 제거 (선택 사항)**
342
342
 
343
343
  ```bash
344
- # 호환 기간 동안 인식되는 플러그인 설정 파일 제거
345
- rm -f ~/.config/opencode/oh-my-openagent.jsonc ~/.config/opencode/oh-my-openagent.json \
346
- ~/.config/opencode/oh-my-opencode.jsonc ~/.config/opencode/oh-my-opencode.json
344
+ # 런타임 설정 파일 제거
345
+ rm -f ~/.omo/omo.jsonc ~/.omo/omo.json
347
346
 
348
347
  # 프로젝트 설정 제거 (있다면)
349
- rm -f .opencode/oh-my-openagent.jsonc .opencode/oh-my-openagent.json \
348
+ rm -f .omo/omo.jsonc .omo/omo.json
349
+
350
+ # 남아 있는 레거시 마이그레이션 백업 제거 (있다면)
351
+ rm -f ~/.config/opencode/oh-my-openagent.jsonc ~/.config/opencode/oh-my-openagent.json \
352
+ ~/.config/opencode/oh-my-opencode.jsonc ~/.config/opencode/oh-my-opencode.json \
353
+ .opencode/oh-my-openagent.jsonc .opencode/oh-my-openagent.json \
350
354
  .opencode/oh-my-opencode.jsonc .opencode/oh-my-opencode.json
351
355
  ```
352
356
 
@@ -375,12 +379,12 @@ oh-my-openagent를 제거하려면:
375
379
  - **Agents**: Sisyphus(메인), Prometheus(플래너), Oracle(아키텍처·디버깅), Librarian(문서·코드 검색), Explore(빠른 코드베이스 grep), Multimodal Looker
376
380
  - **Background Agents**: 진짜 개발팀처럼 여러 에이전트를 병렬로 실행
377
381
  - **LSP & AST Tools**: 리팩터링, rename, 진단, AST 기반 코드 검색
378
- - **Hash-anchored Edit Tool**: `LINE#ID` 참조로 모든 변경 전에 내용을 검증. 수술적 편집, 낡은 라인 에러 0
382
+ - **Hash-anchored Edit Tool** (`hashline_edit: true`로 옵트인): `LINE#ID` 참조로 모든 변경 전에 내용을 검증. 수술적 편집, 낡은 라인 에러 0
379
383
  - **Context Injection**: AGENTS.md, README.md, 조건부 규칙 자동 주입
380
384
  - **Claude Code Compatibility**: 전체 hook 시스템, command, skill, agent, MCP
381
385
  - **Built-in MCPs**: websearch(Exa), context7(문서), grep_app(GitHub 검색)
382
386
  - **Session Tools**: 세션 히스토리 조회·읽기·검색·분석
383
- - **Productivity Features**: Ralph Loop, Todo Enforcer, Comment Checker, Think Mode 등
387
+ - **Productivity Features**: Goal, Todo Enforcer, Comment Checker, Think Mode 등
384
388
  - **Doctor Command**: 빌트인 진단(`bunx oh-my-opencode doctor`)으로 플러그인 등록, 설정, 모델, 환경 검증
385
389
  - **Model Fallbacks**: `fallback_models`에 단순 모델 문자열과 per-fallback 객체 설정을 같은 배열에 섞어 쓸 수 있음
386
390
  - **File Prompts**: 에이전트 설정에서 `file://`로 프롬프트를 파일에서 로드
@@ -394,13 +398,13 @@ oh-my-openagent를 제거하려면:
394
398
  자세한 내용은 [Configuration Documentation](docs/reference/configuration.md) 참고.
395
399
 
396
400
  **요약:**
397
- - **설정 파일 위치**: 호환성 레이어는 `oh-my-openagent.json[c]`와 기존 `oh-my-opencode.json[c]` 플러그인 설정 파일을 모두 인식합니다. 기존 설치는 아직 기존 이름을 쓰는 경우가 많습니다.
401
+ - **설정 파일 위치**: 사용자 `~/.omo/omo.jsonc`와 `$HOME`까지 위로 탐색하는 프로젝트 `.omo/omo.jsonc`; 가까운 설정이 우선합니다. 레거시 `oh-my-*` 파일은 번만 `omo.jsonc`로 마이그레이션됩니다.
398
402
  - **JSONC 지원**: 주석과 trailing comma 지원
399
403
  - **Agents**: 어떤 에이전트든 모델, temperature, 프롬프트, 권한을 오버라이드
400
404
  - **Built-in Skills**: `playwright`(브라우저 자동화), `git-master`(atomic 커밋)
401
405
  - **Sisyphus Agent**: Prometheus(플래너), Metis(플랜 컨설턴트)와 함께 도는 메인 오케스트레이터
402
406
  - **Background Tasks**: 프로바이더/모델별 동시성 제한 설정
403
- - **Categories**: 도메인별 태스크 위임(`visual`, `business-logic`, 커스텀)
407
+ - **Categories**: `visual-engineering`, `ultrabrain`, `deep`, `artistry`, `quick`, `unspecified-low`, `unspecified-high`, `writing`, 그리고 커스텀 이름
404
408
  - **Hooks**: 54개 이상의 라이프사이클 hook (Team Mode 활성화 시 61개), 전부 `disabled_hooks`로 제어 가능
405
409
  - **MCPs**: 빌트인 websearch(Exa), context7(문서), grep_app(GitHub 검색)
406
410
  - **LSP**: 리팩터링 도구까지 포함한 풀 LSP 지원
package/README.md CHANGED
@@ -66,7 +66,7 @@
66
66
  [![GitHub Issues](https://img.shields.io/github/issues/code-yeongyu/oh-my-openagent?color=ff80eb&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-openagent/issues)
67
67
  [![License](https://img.shields.io/badge/license-SUL--1.0-white?labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-openagent/blob/dev/LICENSE.md)
68
68
  [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/code-yeongyu/oh-my-openagent)
69
- [![Docs](https://img.shields.io/badge/docs-omo.vibetip.help-369eff?labelColor=black&logo=readthedocs&logoColor=white&style=flat-square)](https://omo.vibetip.help/docs)
69
+ [![Docs](https://img.shields.io/badge/docs-omo.dev-369eff?labelColor=black&logo=readthedocs&logoColor=white&style=flat-square)](https://omo.dev/docs)
70
70
 
71
71
  [English](README.md) | [한국어](README.ko.md) | [日本語](README.ja.md) | [简体中文](README.zh-cn.md)
72
72
 
@@ -113,8 +113,8 @@ Install oh-my-openagent. Type `ultrawork`. Done.
113
113
 
114
114
  oh-my-openagent ships in three editions of the same product: two plugins that load into a host you already run, plus one standalone edition.
115
115
 
116
- - **Ultimate Edition (omo for OpenCode)** — full omo. 11 agents, 54+ lifecycle hooks, 5 built-in MCPs, all slash commands, Team Mode, ulw-loop, ultrawork, hashline edits everything.
117
- - **Light Edition (omo for Codex CLI)** — the portable components that fit Codex's plugin system: `rules`, `comment-checker`, `git-bash`, `lsp`, `ultrawork`, `ulw-loop`, `start-work-continuation`, and `telemetry`, plus plugin-scoped MCPs for `grep_app`, `context7`, `codegraph`, `git_bash`, and `lsp`, and the shared `ast-grep` skill. No agent orchestration and no `team_*` tools — Codex CLI's own surface does that work.
116
+ - **Ultimate Edition (omo for OpenCode)** — full omo. 11 agents, 54+ lifecycle hooks, 5 built-in MCPs, all slash commands, Team Mode, `/goal`, ultrawork everything. Hashline edits are opt-in (`hashline_edit: true`).
117
+ - **Light Edition (omo for Codex CLI)** — the portable components that fit Codex's plugin system: `rules`, `comment-checker`, `git-bash`, `lsp`, `ultrawork`, `ulw-loop`, `start-work-continuation`, and `telemetry` at the core, plus `teammode` and supporting components (`bootstrap`, `codegraph`, `lcx`, and more), plugin-scoped MCPs for `grep_app`, `context7`, `codegraph`, `git_bash`, and `lsp`, and the shared `ast-grep` skill. It installs Codex agent TOMLs into `~/.codex/agents/`. No OpenCode `team_*` tools — Codex CLI's own spawn/collaboration surface does that work.
118
118
  - **Senpi Edition (standalone, beta)** — the native `omo` command with the OMO extension built in. It installs from `omo-ai@beta` rather than loading into OpenCode or Codex.
119
119
 
120
120
  Pick the edition(s) you want.
@@ -169,11 +169,11 @@ Fetch the full guide and follow it step by step:
169
169
  curl -fsSL https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/refs/heads/dev/docs/guide/installation.md
170
170
  ```
171
171
 
172
- The guide covers: platform selection, the subscription interview, provider authentication (Anthropic / Gemini / Copilot / Z.ai / OpenCode Zen), the agent-to-model matching matrix, modes (`ultrawork`, `search`, `analyze`, `team`, `hyperplan`), slash commands, the Light edition's 8 Codex components, Team Mode, and uninstall. Don't summarize it; read it end to end.
172
+ The guide covers: platform selection, the subscription interview, provider authentication (Anthropic / Gemini / Copilot / Z.ai / OpenCode Zen), the agent-to-model matching matrix, modes (`ultrawork`, `team`, `hyperplan`), slash commands, the Light edition's Codex components, Team Mode, and uninstall. Don't summarize it; read it end to end.
173
173
 
174
174
  ### Note on package and command names
175
175
 
176
- The published npm package and CLI binary are still named `oh-my-opencode` (dual-published as `oh-my-openagent` during the rename transition). Inside `opencode.json`, the compatibility layer prefers the plugin entry `oh-my-openagent`, while legacy `oh-my-opencode` entries still load with a warning. Plugin config files still commonly use `oh-my-opencode.json[c]`; both legacy and renamed basenames are recognized.
176
+ The published npm package and CLI binary are still named `oh-my-opencode` (dual-published as `oh-my-openagent` during the rename transition). Inside `opencode.json`, the compatibility layer prefers the plugin entry `oh-my-openagent`, while legacy `oh-my-opencode` entries still load with a warning. Runtime config is `~/.omo/omo.jsonc` plus walked project `.omo/omo.jsonc`. Legacy `oh-my-openagent.json[c]` / `oh-my-opencode.json[c]` files are imported once by the migration engine and are not read afterward.
177
177
 
178
178
  The recommended `bunx`/`npx` invocation is `oh-my-openagent install` (or the original `oh-my-opencode install`). Once installed, the short command is `omo-agent-toolkit`. The `omo` bin was removed from these packages in this major release; the name now belongs to the senpi-native edition, installed with `npm i -g omo-ai@beta` (beta channel only). Do **not** use `bunx omo` or `npx omo`: `omo` on npm is a different, unrelated package by a different author, and those commands resolve to it. The senpi edition's package name is `omo-ai`. `lazycodex-ai` is a single-purpose Node/npm installer package: `npx lazycodex-ai install` routes directly to the Codex Light installer. It is not the Codex marketplace name (the marketplace repository is `code-yeongyu/lazycodex`). Codex sees marketplace `sisyphuslabs` and plugin `omo`, enabled as `omo@sisyphuslabs`.
179
179
 
@@ -224,20 +224,20 @@ Even with only the following subscriptions, `ultrawork` works well (this project
224
224
  | | Feature | Edition | What it does |
225
225
  | :---: | :------------------------------------------------------- | :------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
226
226
  | 🤖 | **Discipline Agents** | Ultimate | Sisyphus orchestrates Hephaestus, Oracle, Librarian, Explore. A full AI dev team in parallel. |
227
- | 🧩 | **Codex CLI Light Edition** | Light | Portable OMO components (rules, comment-checker, git-bash, LSP, ultrawork, ulw-loop, start-work continuation, telemetry) running inside OpenAI Codex CLI. Install via `npx lazycodex-ai install`. |
227
+ | 🧩 | **Codex CLI Light Edition** | Light | Portable OMO components (rules, comment-checker, git-bash, LSP, ultrawork, ulw-loop, start-work continuation, telemetry, teammode, and more) running inside OpenAI Codex CLI. Install via `npx lazycodex-ai install`. |
228
228
  | 👥 | **Team Mode** (v4.0, opt-in) | Ultimate | Lead agent + up to 8 parallel members, real-time tmux visualization, dedicated `team_*` tools. Powers `hyperplan` (5 hostile critics) and `security-research` (3 hunters + 2 PoC engineers). [Docs →](docs/guide/team-mode.md) |
229
229
  | ⚡ | **`ultrawork` / `ulw`** | Both | One word. Every agent activates. Doesn't stop until done. |
230
230
  | 🚪 | **[IntentGate](https://factory.ai/news/terminal-bench)** | Ultimate | Analyzes true user intent before classifying or acting. No more literal misinterpretations. (Light edition only recognises the `ultrawork`/`ulw` keyword.) |
231
- | 🔗 | **Hash-Anchored Edit Tool** | Ultimate | `LINE#ID` content hash validates every change. Zero stale-line errors. Inspired by [oh-my-pi](https://github.com/can1357/oh-my-pi). [The Harness Problem →](https://blog.can.ac/2026/02/12/the-harness-problem/) |
231
+ | 🔗 | **Hash-Anchored Edit Tool** | Ultimate | Hashline (`LINE#ID`) edit/read tagging. Opt-in: set `hashline_edit: true` in `~/.omo/omo.jsonc`. Zero stale-line errors. Inspired by [oh-my-pi](https://github.com/can1357/oh-my-pi). [The Harness Problem →](https://blog.can.ac/2026/02/12/the-harness-problem/) |
232
232
  | 🛠️ | **LSP integration** | Both | Diagnostics, navigation, symbols, workspace rename. IDE precision for agents. Same LSP MCP server in both editions. |
233
- | 🔎 | **AST-Grep** | Ultimate | Pattern-aware code search and rewriting across 25 languages. |
233
+ | 🔎 | **AST-Grep** | Both | Pattern-aware code search and rewriting across 25 languages. Ultimate uses the MCP tools; Light uses the shared `ast-grep` skill with a provisioned `sg`. |
234
234
  | 🧠 | **Background Agents** | Ultimate | Fire 5+ specialists in parallel. Context stays lean. Results when ready. |
235
235
  | 📚 | **Built-in MCPs** (web/docs/code search) | Ultimate | Exa (web search), Context7 (official docs), Grep.app (GitHub search). Always on. |
236
- | 🔁 | **Goal / `/goal`** | Ultimate | Persistent per-session objective. Re-injects a continuation prompt on every idle until a completion audit says it's done. |
236
+ | 🔁 | **Goal / `/goal`** | Ultimate | `/goal` sets a persistent thread objective. Idle continuation runs only when `goal.enabled` is true (default false). |
237
237
  | ✅ | **Todo Enforcer** | Ultimate | Agent goes idle? System yanks it back. Your task gets done, period. |
238
238
  | 💬 | **Comment Checker** | Both | No AI slop in comments. Code reads like a senior wrote it. |
239
239
  | 📐 | **Rules Injection** (`AGENTS.md` / `.omo/rules/**`) | Both | Project rules and AGENTS.md auto-loaded into the agent's context at every prompt. |
240
- | 🎯 | **Ulw Loop** | Both | Durable multi-goal orchestration with evidence audit, backed by `.omo/ulw-loop/`. |
240
+ | 🎯 | **Ulw Loop** | Light | Codex component + CLI for durable multi-goal orchestration with evidence audit. On OpenCode, use **Goal / `/goal`** instead. |
241
241
  | 🖥️ | **Tmux Integration** | Ultimate | Full interactive terminal. REPLs, debuggers, TUIs. All live. |
242
242
  | 🔌 | **Claude Code Compatible** | Ultimate | Your hooks, commands, skills, MCPs, and plugins? All work here. |
243
243
  | 🧬 | **Skill-Embedded MCPs** | Ultimate | Skills carry their own MCP servers. No context bloat. |
@@ -253,7 +253,7 @@ Even with only the following subscriptions, `ultrawork` works well (this project
253
253
  <td align="center"><img src=".github/assets/hephaestus.png" height="300" /></td>
254
254
  </tr></table>
255
255
 
256
- **Sisyphus** (`claude-opus-5` / **`kimi-k3`** / **`glm-5`** ) is your main orchestrator. He plans, delegates to specialists, and drives tasks to completion with aggressive parallel execution. He does not stop halfway. Claude Opus 5 and Kimi K3 are the recommended defaults.
256
+ **Sisyphus** (`claude-opus-5` / **`kimi-k3`** / **`gpt-5.6-sol`** / **`glm-5.2`** ) is your main orchestrator. He plans, delegates to specialists, and drives tasks to completion with aggressive parallel execution. He does not stop halfway. Claude Opus 5 and Kimi K3 are the recommended defaults.
257
257
 
258
258
  **Hephaestus** (`gpt-5.6-sol` through OpenAI, GitHub Copilot, Vercel, or OpenCode at medium effort) is your autonomous deep worker. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. *The Legitimate Craftsman.*
259
259
 
@@ -272,7 +272,7 @@ One agent is fast. A coordinated team is *devastating*.
272
272
  **Team Mode** turns oh-my-openagent from "one agent with subagents" into a real multi-agent system. A lead agent orchestrates a team of category-specialized members, all running **in parallel** and communicating through dedicated tools (`team_create`, `team_send_message`, `team_task_create`, `team_status`, ...). Watch every member work simultaneously in a tmux layout with focus + grid windows.
273
273
 
274
274
  ```jsonc
275
- // .opencode/oh-my-openagent.jsonc
275
+ // ~/.omo/omo.jsonc (or project .omo/omo.jsonc)
276
276
  {
277
277
  "team_mode": {
278
278
  "enabled": true,
@@ -300,7 +300,7 @@ When Sisyphus delegates to a subagent, it doesn't pick a model. It picks a **cat
300
300
  | `quick` | Single-file changes, typos |
301
301
  | `ultrabrain` | Hard logic, architecture decisions |
302
302
 
303
- The agent says what kind of work it needs; the harness picks the right model. `ultrabrain` now routes to GPT-5.6 Sol xhigh through OpenAI or Vercel when available, then GPT-5.6 Sol xhigh. You touch nothing.
303
+ The agent says what kind of work it needs; the harness picks the right model. `ultrabrain` routes to GPT-5.6 Sol max (OpenAI / Vercel, then GitHub Copilot, then OpenCode). You touch nothing.
304
304
 
305
305
  ### Claude Code Compatibility
306
306
 
@@ -331,7 +331,7 @@ The harness problem is real. Most agent failures aren't the model's fault; it's
331
331
  >
332
332
  > <br/>- [Can Bölük, The Harness Problem](https://blog.can.ac/2026/02/12/the-harness-problem/)
333
333
 
334
- Inspired by [oh-my-pi](https://github.com/can1357/oh-my-pi), we built **Hashline**. Every line the agent reads comes back tagged with a content hash:
334
+ Inspired by [oh-my-pi](https://github.com/can1357/oh-my-pi), we built **Hashline**. When `hashline_edit` is enabled, every line the agent reads comes back tagged with a content hash:
335
335
 
336
336
  ```
337
337
  11#VK| function hello() {
@@ -362,7 +362,7 @@ Agents auto-read relevant context. Zero manual management.
362
362
 
363
363
  Complex task? Don't prompt and pray.
364
364
 
365
- `/start-work` calls Prometheus. He **interviews you like a real engineer**, identifies scope and ambiguities, and builds a verified plan before touching code. The agent knows what it's building before it starts.
365
+ Prometheus **interviews you like a real engineer**, identifies scope and ambiguities, and writes a verified plan to `.omo/plans/` before touching code. `/start-work` then starts an **Atlas** work session from that plan. The agent knows what it's building before it starts.
366
366
 
367
367
  ### Skills
368
368
 
@@ -400,12 +400,16 @@ To remove oh-my-openagent:
400
400
  2. **Remove configuration files (optional)**
401
401
 
402
402
  ```bash
403
- # Remove plugin config files recognized during the compatibility window
404
- rm -f ~/.config/opencode/oh-my-openagent.jsonc ~/.config/opencode/oh-my-openagent.json \
405
- ~/.config/opencode/oh-my-opencode.jsonc ~/.config/opencode/oh-my-opencode.json
403
+ # Remove the runtime config files
404
+ rm -f ~/.omo/omo.jsonc ~/.omo/omo.json
406
405
 
407
406
  # Remove project config (if exists)
408
- rm -f .opencode/oh-my-openagent.jsonc .opencode/oh-my-openagent.json \
407
+ rm -f .omo/omo.jsonc .omo/omo.json
408
+
409
+ # Remove leftover legacy migration backups (if any)
410
+ rm -f ~/.config/opencode/oh-my-openagent.jsonc ~/.config/opencode/oh-my-openagent.json \
411
+ ~/.config/opencode/oh-my-opencode.jsonc ~/.config/opencode/oh-my-opencode.json \
412
+ .opencode/oh-my-openagent.jsonc .opencode/oh-my-openagent.json \
409
413
  .opencode/oh-my-opencode.jsonc .opencode/oh-my-opencode.json
410
414
  ```
411
415
 
@@ -440,7 +444,7 @@ See full [Features Documentation](docs/reference/features.md).
440
444
  - **Agents**: Sisyphus (the main agent), Prometheus (planner), Oracle (architecture/debugging), Librarian (docs/code search), Explore (fast codebase grep), Multimodal Looker
441
445
  - **Background Agents**: Run multiple agents in parallel like a real dev team
442
446
  - **LSP & AST Tools**: Refactoring, rename, diagnostics, AST-aware code search
443
- - **Hash-anchored Edit Tool**: `LINE#ID` references validate content before applying every change. Surgical edits, zero stale-line errors
447
+ - **Hash-anchored Edit Tool** (opt-in via `hashline_edit: true`): `LINE#ID` references validate content before applying every change. Surgical edits, zero stale-line errors
444
448
  - **Context Injection**: Auto-inject AGENTS.md, README.md, conditional rules
445
449
  - **Claude Code Compatibility**: Full hook system, commands, skills, agents, MCPs
446
450
  - **Built-in MCPs**: websearch (Exa), context7 (docs), grep_app (GitHub search) — injected at runtime by the plugin; not visible in `opencode mcp list` (see [MCP docs](docs/reference/features.md#native-vs-plugin-injected-mcps))
@@ -459,13 +463,13 @@ Opinionated defaults, adjustable if you insist.
459
463
  See [Configuration Documentation](docs/reference/configuration.md).
460
464
 
461
465
  **Quick Overview:**
462
- - **Config Locations**: User config plus walked `.opencode/oh-my-openagent.json[c]` configs up to `$HOME`; closest wins. Legacy `oh-my-opencode.json[c]` still works.
466
+ - **Config Locations**: User `~/.omo/omo.jsonc` plus walked project `.omo/omo.jsonc` configs up to `$HOME`; closest wins. Legacy `oh-my-*` files are migrated once into `omo.jsonc`.
463
467
  - **JSONC Support**: Comments and trailing commas supported
464
468
  - **Agents**: Override models, temperatures, prompts, and permissions for any agent
465
469
  - **Built-in Skills**: `playwright` (browser automation), `git-master` (atomic commits)
466
470
  - **Sisyphus Agent**: Main orchestrator with Prometheus (Planner) and Metis (Plan Consultant)
467
471
  - **Background Tasks**: Configure concurrency limits per provider/model
468
- - **Categories**: Domain-specific task delegation (`visual`, `business-logic`, custom)
472
+ - **Categories**: Domain-specific task delegation (`visual-engineering`, `ultrabrain`, `deep`, `artistry`, `quick`, `unspecified-low`, `unspecified-high`, `writing`, plus custom names)
469
473
  - **Hooks**: 54+ lifecycle hooks (61 with Team Mode), all configurable via `disabled_hooks`
470
474
  - **MCPs**: Built-in websearch (Exa), context7 (docs), grep_app (GitHub search) — runtime-injected, not shown in `opencode mcp list`
471
475
  - **LSP**: Full LSP support with refactoring tools
package/README.ru.md CHANGED
@@ -127,11 +127,11 @@ https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/refs/heads/dev/do
127
127
  curl -s https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/refs/heads/dev/docs/guide/installation.md
128
128
  ```
129
129
 
130
- **Примечание**: Опубликованное имя npm-пакета и CLI-бинарника по-прежнему `oh-my-opencode` (в переходный период пакет также дублируется под именем `oh-my-openagent`). Внутри `opencode.json` слой совместимости теперь предпочитает точку входа плагина `oh-my-openagent`, в то время как устаревшие записи `oh-my-opencode` всё ещё загружаются с предупреждением. Файлы конфигурации плагина по-прежнему часто называются `oh-my-opencode.json` или `oh-my-opencode.jsonc`; в переходный период распознаются как устаревшие, так и новые имена.
130
+ **Примечание**: Опубликованное имя npm-пакета и CLI-бинарника по-прежнему `oh-my-opencode` (в переходный период пакет также дублируется под именем `oh-my-openagent`). Внутри `opencode.json` слой совместимости теперь предпочитает точку входа плагина `oh-my-openagent`, в то время как устаревшие записи `oh-my-opencode` всё ещё загружаются с предупреждением. Рабочая конфигурация это `~/.omo/omo.jsonc` плюс проектные `.omo/omo.jsonc`, найденные при подъёме по дереву каталогов. Устаревшие файлы `oh-my-openagent.json[c]` / `oh-my-opencode.json[c]` импортируются движком миграции один раз и после этого не читаются.
131
131
 
132
132
  Анонимная телеметрия включена по умолчанию для подсчёта активных установок (DAU/WAU/MAU). Не более одного события на машину за UTC-сутки, использует хешированный идентификатор установки, никогда не использует исходное имя хоста, и не создаёт PostHog person profile. Можно отключить через `OMO_SEND_ANONYMOUS_TELEMETRY=0` или `OMO_DISABLE_POSTHOG=1`. См. [Политику конфиденциальности](docs/legal/privacy-policy.md) и [Условия обслуживания](docs/legal/terms-of-service.md).
133
133
 
134
- **Ultimate и Light:** oh-my-openagent поставляется в двух редакциях одного продукта. **Ultimate** (`bunx oh-my-openagent install` или `--platform=opencode`, по умолчанию) — полнофункциональная редакция поверх OpenCode: 11 агентов, 54+ хука, Team Mode, все MCP, все слэш-команды, режимы IntentGate. **Light** (`npx lazycodex-ai install` или `bunx oh-my-openagent install --platform=codex`) — 8 компонентов omo, которые портируются в систему плагинов OpenAI Codex CLI: `rules`, `comment-checker`, `git-bash`, `lsp`, `ultrawork`, `ulw-loop`, `start-work-continuation`, `telemetry`. Чтобы установить обе редакции одной командой, используйте `--platform=both`. Телеметрию только для Codex можно отключить через `OMO_CODEX_DISABLE_POSTHOG=1` или `OMO_CODEX_SEND_ANONYMOUS_TELEMETRY=0`.
134
+ **Ultimate и Light:** oh-my-openagent поставляется в двух редакциях одного продукта. **Ultimate** (`bunx oh-my-openagent install` или `--platform=opencode`, по умолчанию) — полнофункциональная редакция поверх OpenCode: 11 агентов, 54+ хука, Team Mode, все MCP, все слэш-команды, режимы IntentGate. **Light** (`npx lazycodex-ai install` или `bunx oh-my-openagent install --platform=codex`) — портируемые компоненты omo для системы плагинов OpenAI Codex CLI: ядро (`rules`, `comment-checker`, `git-bash`, `lsp`, `ultrawork`, `ulw-loop`, `start-work-continuation`, `telemetry`), а также `teammode` и вспомогательные компоненты (`bootstrap`, `codegraph`, `lcx` и другие); TOML-файлы Codex-агентов устанавливаются в `~/.codex/agents/`. Чтобы установить обе редакции одной командой, используйте `--platform=both`. Телеметрию только для Codex можно отключить через `OMO_CODEX_DISABLE_POSTHOG=1` или `OMO_CODEX_SEND_ANONYMOUS_TELEMETRY=0`.
135
135
 
136
136
  ------
137
137
 
@@ -164,19 +164,19 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
164
164
  | | Функция | Editions | Что делает |
165
165
  | --- | -------------------------------------------------------- | :------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
166
166
  | 🤖 | **Дисциплинированные агенты** | Ultimate | Sisyphus оркестрирует Hephaestus, Oracle, Librarian, Explore. Полноценная AI-команда разработки в параллельном режиме. |
167
- | 🧩 | **Codex CLI Light Edition** | Light | 8 компонентов omo, портированных в OpenAI Codex CLI (rules, comment-checker, git-bash, LSP, ultrawork, ulw-loop, start-work continuation, telemetry). Установка: `npx lazycodex-ai install`. |
167
+ | 🧩 | **Codex CLI Light Edition** | Light | Портируемые компоненты omo в OpenAI Codex CLI (rules, comment-checker, git-bash, LSP, ultrawork, ulw-loop, start-work continuation, telemetry, teammode и другие). Установка: `npx lazycodex-ai install`. |
168
168
  | 👥 | **Team Mode** (v4.0, opt-in) | Ultimate | Лид-агент + до 8 параллельных участников, визуализация в tmux в реальном времени, выделенные инструменты `team_*`. Питает `hyperplan` (5 враждебных критиков) и `security-research` (3 охотника + 2 PoC-инженера). [Документация →](docs/guide/team-mode.md) |
169
169
  | ⚡ | **`ultrawork` / `ulw`** | Both | Одно слово. Все агенты (Ultimate) или Codex-компонент `ultrawork` (Light) активируются. Не останавливается, пока задача не выполнена. |
170
- | 🚪 | **[IntentGate](https://factory.ai/news/terminal-bench)** | Ultimate | Анализирует истинное намерение пользователя перед классификацией и действием. Триггеры `search` / `analyze` / `team` / `hyperplan`. (Light хукает только `ulw` / `ultrawork`.) |
171
- | 🔗 | **Инструмент правок на основе хэш-якорей** | Ultimate | Хэш содержимого `LINE#ID` проверяет каждое изменение. Ноль ошибок с устаревшими строками. Вдохновлено [oh-my-pi](https://github.com/can1357/oh-my-pi). [The Harness Problem →](https://blog.can.ac/2026/02/12/the-harness-problem/) (Codex использует собственный `apply_patch`.) |
170
+ | 🚪 | **[IntentGate](https://factory.ai/news/terminal-bench)** | Ultimate | Анализирует истинное намерение пользователя перед классификацией и действием. Никаких буквальных искажений смысла. (Light распознаёт только ключевые слова `ulw` / `ultrawork`.) |
171
+ | 🔗 | **Инструмент правок на основе хэш-якорей** | Ultimate | Тегирование чтения/правок Hashline (`LINE#ID`). Включается вручную: `hashline_edit: true` в `~/.omo/omo.jsonc`. Ноль ошибок с устаревшими строками. Вдохновлено [oh-my-pi](https://github.com/can1357/oh-my-pi). [The Harness Problem →](https://blog.can.ac/2026/02/12/the-harness-problem/) (Codex использует собственный `apply_patch`.) |
172
172
  | 🛠️ | **LSP + AST-Grep** | Both | Переименование в рабочем пространстве, диагностика перед сборкой, переписывание с учётом AST. LSP предоставляется через MCP, AST-Grep — через общий skill `ast-grep` и `sg`. |
173
173
  | 🧠 | **Фоновые агенты** | Ultimate | Запускайте 5+ специалистов параллельно. Контекст остаётся компактным. Результаты — когда готовы. |
174
174
  | 📚 | **Встроенные MCP** | Both | Ultimate внедряет Exa (веб-поиск), Context7 (официальная документация) и Grep.app (поиск по GitHub) во время выполнения. Light предоставляет plugin-scoped MCP: `grep_app`, `context7`, `git_bash`, `lsp`. |
175
- | 🔁 | **Ralph Loop / `/ulw-loop`** | Ultimate | Самореферентный цикл. Не останавливается, пока задача не выполнена на 100%. |
175
+ | 🔁 | **Goal / `/goal`** | Ultimate | `/goal` задаёт постоянную цель треда. Idle continuation работает только при `goal.enabled: true` (по умолчанию false). |
176
176
  | ✅ | **Todo Enforcer** (Boulder) | Ultimate | Агент завис? Система немедленно возвращает его в работу. Ваша задача будет выполнена, точка. |
177
177
  | 💬 | **Comment Checker** | Both | Никакого AI-мусора в комментариях. Тот же бинарник `@code-yeongyu/comment-checker` работает в обеих редакциях. |
178
178
  | 📜 | **Rules Injection** | Both | Иерархическое внедрение контекста из `AGENTS.md` / `CLAUDE.md` / `.omo/rules/**`. В Ultimate это хук, в Light — компонент `rules`. |
179
- | 🧬 | **Ulw Loop** | Light | Долговечная оркестрация нескольких целей с аудитом доказательств в `.omo/ulw-loop/`. Сейчас только в Codex; порт в сторону OpenCode в дорожной карте. |
179
+ | 🧬 | **Ulw Loop** | Light | Codex-компонент + CLI для долговечной оркестрации нескольких целей с аудитом доказательств. В OpenCode используйте **Goal / `/goal`**. |
180
180
  | 🖥️ | **Интеграция с Tmux** | Ultimate | Полноценный интерактивный терминал. REPL, дебаггеры, TUI. Всё живое. |
181
181
  | 🔌 | **Совместимость с Claude Code** | Ultimate | Ваши хуки, команды, навыки, MCP и плагины? Всё работает без изменений. (У Codex своя нативная плагин-система.) |
182
182
  | 🎯 | **MCP, встроенные в навыки** | Ultimate | Навыки несут собственные MCP-серверы. Никакого раздувания контекста. |
@@ -192,7 +192,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
192
192
  <td align="center"><img src=".github/assets/hephaestus.png" height="300" /></td>
193
193
  </tr></table>
194
194
 
195
- **Sisyphus** (`claude-opus-5` / **`kimi-k3`** / **`glm-5`**) — главный оркестратор. Он планирует, делегирует задачи специалистам и доводит их до завершения с агрессивным параллельным выполнением. Он не останавливается на полпути. Claude Opus 5 и Kimi K3 — рекомендуемые значения по умолчанию.
195
+ **Sisyphus** (`claude-opus-5` / **`kimi-k3`** / **`gpt-5.6-sol`** / **`glm-5.2`**) — главный оркестратор. Он планирует, делегирует задачи специалистам и доводит их до завершения с агрессивным параллельным выполнением. Он не останавливается на полпути. Claude Opus 5 и Kimi K3 — рекомендуемые значения по умолчанию.
196
196
 
197
197
  **Hephaestus** (использует только `gpt-5.6-sol` с medium effort через OpenAI, GitHub Copilot, Vercel или OpenCode) — автономный глубокий исполнитель. Дайте ему цель, а не рецепт. Он исследует кодовую базу, изучает паттерны и выполняет задачи сквозным образом без лишних подсказок. *Законный Мастер.*
198
198
 
@@ -211,7 +211,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
211
211
  **Team Mode** превращает oh-my-openagent из «одного агента с подагентами» в полноценную мультиагентную систему. Лид-агент оркестрирует команду специализированных по категориям участников, все они работают **параллельно** и общаются через выделенные инструменты (`team_create`, `team_send_message`, `team_task_create`, `team_status`, …). Наблюдайте за работой каждого участника одновременно в tmux-раскладке с focus- и grid-окнами.
212
212
 
213
213
  ```jsonc
214
- // .opencode/oh-my-openagent.jsonc
214
+ // ~/.omo/omo.jsonc (или проектный .omo/omo.jsonc)
215
215
  {
216
216
  "team_mode": {
217
217
  "enabled": true,
@@ -239,7 +239,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
239
239
  | `quick` | Изменения в одном файле, опечатки |
240
240
  | `ultrabrain` | Сложная логика, архитектурные решения |
241
241
 
242
- Агент сообщает тип задачи, а обвязка подбирает нужную модель. `ultrabrain` направляется в GPT-5.6 Sol xhigh через OpenAI или Vercel, когда они доступны, затем в GPT-5.6 Sol xhigh. Вы ни к чему не прикасаетесь.
242
+ Агент сообщает тип задачи, а обвязка подбирает нужную модель. `ultrabrain` направляется в GPT-5.6 Sol max (OpenAI / Vercel, затем GitHub Copilot, затем OpenCode). Вы ни к чему не прикасаетесь.
243
243
 
244
244
  ### Совместимость с Claude Code
245
245
 
@@ -270,7 +270,7 @@ MCP-серверы съедают бюджет контекста. Мы это
270
270
  >
271
271
  > <br/>— [Can Bölük, The Harness Problem](https://blog.can.ac/2026/02/12/the-harness-problem/)
272
272
 
273
- Вдохновлённые [oh-my-pi](https://github.com/can1357/oh-my-pi), мы сделали **Hashline**. Каждая строка, которую читает агент, возвращается с тегом хэша содержимого:
273
+ Вдохновлённые [oh-my-pi](https://github.com/can1357/oh-my-pi), мы сделали **Hashline**. Когда включён `hashline_edit`, каждая строка, которую читает агент, возвращается с тегом хэша содержимого:
274
274
 
275
275
  ```
276
276
  11#VK| function hello() {
@@ -301,7 +301,7 @@ project/
301
301
 
302
302
  Сложная задача? Не нужно молиться и надеяться на промпт.
303
303
 
304
- `/start-work` вызывает Prometheus. Он **интервьюирует вас как настоящий инженер**, определяет объём работ и неоднозначности и формирует проверенный план до прикосновения к коду. Агент знает, что строит, прежде чем начать.
304
+ Prometheus **интервьюирует вас как настоящий инженер**, определяет объём работ и неоднозначности и записывает проверенный план в `.omo/plans/` до прикосновения к коду. Затем `/start-work` запускает рабочую сессию **Atlas** по этому плану. Агент знает, что строит, прежде чем начать.
305
305
 
306
306
  ### Навыки
307
307
 
@@ -339,12 +339,16 @@ project/
339
339
  2. **Удалите файлы конфигурации (опционально)**
340
340
 
341
341
  ```bash
342
- # Удалить файлы конфигурации плагина, распознаваемые в переходный период
343
- rm -f ~/.config/opencode/oh-my-openagent.jsonc ~/.config/opencode/oh-my-openagent.json \
344
- ~/.config/opencode/oh-my-opencode.jsonc ~/.config/opencode/oh-my-opencode.json
342
+ # Удалить рабочие файлы конфигурации
343
+ rm -f ~/.omo/omo.jsonc ~/.omo/omo.json
345
344
 
346
345
  # Удалить конфиг проекта (если существует)
347
- rm -f .opencode/oh-my-openagent.jsonc .opencode/oh-my-openagent.json \
346
+ rm -f .omo/omo.jsonc .omo/omo.json
347
+
348
+ # Удалить оставшиеся резервные копии миграции (если есть)
349
+ rm -f ~/.config/opencode/oh-my-openagent.jsonc ~/.config/opencode/oh-my-openagent.json \
350
+ ~/.config/opencode/oh-my-opencode.jsonc ~/.config/opencode/oh-my-opencode.json \
351
+ .opencode/oh-my-openagent.jsonc .opencode/oh-my-openagent.json \
348
352
  .opencode/oh-my-opencode.jsonc .opencode/oh-my-opencode.json
349
353
  ```
350
354
 
@@ -374,12 +378,12 @@ project/
374
378
  - **Агенты**: Sisyphus (главный агент), Prometheus (планировщик), Oracle (архитектура/отладка), Librarian (документация/поиск по коду), Explore (быстрый grep по кодовой базе), Multimodal Looker
375
379
  - **Фоновые агенты**: Запускайте несколько агентов параллельно, как настоящая команда разработки
376
380
  - **Инструменты LSP и AST**: Рефакторинг, переименование, диагностика, поиск кода с учётом AST
377
- - **Инструмент правок на основе хэш-якорей**: Ссылки `LINE#ID` проверяют содержимое перед применением каждого изменения. Хирургические правки, ноль ошибок с устаревшими строками
381
+ - **Инструмент правок на основе хэш-якорей** (включается через `hashline_edit: true`): Ссылки `LINE#ID` проверяют содержимое перед применением каждого изменения. Хирургические правки, ноль ошибок с устаревшими строками
378
382
  - **Инъекция контекста**: Автоматическое добавление AGENTS.md, README.md, условных правил
379
383
  - **Совместимость с Claude Code**: Полная система хуков, команды, навыки, агенты, MCP
380
384
  - **Встроенные MCP**: websearch (Exa), context7 (документация), grep_app (поиск по GitHub)
381
385
  - **Инструменты сессий**: Список, чтение, поиск и анализ истории сессий
382
- - **Инструменты продуктивности**: Ralph Loop, Todo Enforcer, Comment Checker, Think Mode и другое
386
+ - **Инструменты продуктивности**: Goal, Todo Enforcer, Comment Checker, Think Mode и другое
383
387
  - **Команда Doctor**: Встроенная диагностика (`bunx oh-my-opencode doctor`) проверяет регистрацию плагина, конфиг, модели и окружение
384
388
  - **Фолбэки моделей**: `fallback_models` позволяет смешивать простые строки моделей и объектные настройки per-fallback в одном массиве
385
389
  - **Файловые промпты**: Загрузка промптов из файлов через `file://` в конфигурации агентов
@@ -394,13 +398,13 @@ project/
394
398
 
395
399
  **Краткий обзор:**
396
400
 
397
- - **Расположение конфигов**: Слой совместимости распознаёт как `oh-my-openagent.json[c]`, так и устаревшие `oh-my-opencode.json[c]` файлы конфигурации плагина. Существующие установки по-прежнему часто используют устаревшее имя.
401
+ - **Расположение конфигов**: Пользовательский `~/.omo/omo.jsonc` плюс проектные `.omo/omo.jsonc`, найденные при подъёме до `$HOME`; ближайший конфиг выигрывает. Устаревшие файлы `oh-my-*` мигрируются в `omo.jsonc` один раз.
398
402
  - **Поддержка JSONC**: Комментарии и конечные запятые поддерживаются
399
403
  - **Агенты**: Переопределение моделей, температур, промптов и разрешений для любого агента
400
404
  - **Встроенные навыки**: `playwright` (автоматизация браузера), `git-master` (атомарные коммиты)
401
405
  - **Агент Sisyphus**: Главный оркестратор с Prometheus (Планировщик) и Metis (Консультант по плану)
402
406
  - **Фоновые задачи**: Настройка ограничений параллельности по провайдеру/модели
403
- - **Категории**: Делегирование задач по предметной области (`visual`, `business-logic`, пользовательские)
407
+ - **Категории**: `visual-engineering`, `ultrabrain`, `deep`, `artistry`, `quick`, `unspecified-low`, `unspecified-high`, `writing`, плюс пользовательские имена
404
408
  - **Хуки**: 54+ встроенных хуков жизненного цикла (61 с включённым Team Mode), все настраиваются через `disabled_hooks`
405
409
  - **MCP**: Встроенные websearch (Exa), context7 (документация), grep_app (поиск по GitHub)
406
410
  - **LSP**: Полная поддержка LSP с инструментами рефакторинга