From 5bfa38cbf2c113b069e69065ced2bb60ae87c8c6 Mon Sep 17 00:00:00 2001 From: RockChinQ Date: Sat, 13 Jun 2026 08:01:18 -0400 Subject: [PATCH 01/12] feat(plugins): show plugin logs on detail page via Docs/Logs tablist Add a Logs tab beside Documentation on the plugin detail page, showing the output a plugin prints through the standard Python logger (per the wiki style guide). Logs are captured from the plugin's stderr by the plugin runtime and fetched on demand. - Bump langbot-plugin pin to 0.4.4 (adds GET_PLUGIN_LOGS action) - plugin_connector/handler: get_plugin_logs RPC client - HTTP route GET /api/v1/plugins///logs (limit + level) - Frontend: wrap detail right panel in Docs/Logs Tabs; PluginLogs component with level filter, manual + 3s auto refresh, bottom-follow - i18n: 7 new keys across all 8 locales --- pyproject.toml | 2 +- .../pkg/api/http/controller/groups/plugins.py | 16 ++ src/langbot/pkg/plugin/connector.py | 10 ++ src/langbot/pkg/plugin/handler.py | 25 +++ uv.lock | 8 +- .../app/home/plugins/PluginDetailContent.tsx | 33 +++- .../plugin-logs/PluginLogs.tsx | 156 ++++++++++++++++++ web/src/app/infra/entities/plugin/index.ts | 7 + web/src/app/infra/http/BackendClient.ts | 17 ++ web/src/i18n/locales/en-US.ts | 8 + web/src/i18n/locales/es-ES.ts | 8 + web/src/i18n/locales/ja-JP.ts | 8 + web/src/i18n/locales/ru-RU.ts | 8 + web/src/i18n/locales/th-TH.ts | 7 + web/src/i18n/locales/vi-VN.ts | 8 + web/src/i18n/locales/zh-Hans.ts | 7 + web/src/i18n/locales/zh-Hant.ts | 7 + 17 files changed, 328 insertions(+), 7 deletions(-) create mode 100644 web/src/app/home/plugins/components/plugin-installed/plugin-logs/PluginLogs.tsx diff --git a/pyproject.toml b/pyproject.toml index 0ec0d418..024aa021 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -70,7 +70,7 @@ dependencies = [ "chromadb>=1.0.0,<2.0.0", "qdrant-client (>=1.15.1,<2.0.0)", "pyseekdb==1.1.0.post3", - "langbot-plugin==0.4.3", + "langbot-plugin==0.4.4", "asyncpg>=0.30.0", "line-bot-sdk>=3.19.0", "matrix-nio>=0.25.2", diff --git a/src/langbot/pkg/api/http/controller/groups/plugins.py b/src/langbot/pkg/api/http/controller/groups/plugins.py index 05a8a271..52b0fb20 100644 --- a/src/langbot/pkg/api/http/controller/groups/plugins.py +++ b/src/langbot/pkg/api/http/controller/groups/plugins.py @@ -271,6 +271,22 @@ class PluginsRouterGroup(group.RouterGroup): readme = await self.ap.plugin_connector.get_plugin_readme(author, plugin_name, language=language) return self.success(data={'readme': readme}) + @self.route( + '///logs', + methods=['GET'], + auth_type=group.AuthType.USER_TOKEN_OR_API_KEY, + ) + async def _(author: str, plugin_name: str) -> quart.Response: + try: + limit = int(quart.request.args.get('limit', 200)) + except (TypeError, ValueError): + limit = 200 + level = quart.request.args.get('level') or None + logs = await self.ap.plugin_connector.get_plugin_logs( + author, plugin_name, limit=limit, level=level + ) + return self.success(data={'logs': logs}) + @self.route( '///icon', methods=['GET'], diff --git a/src/langbot/pkg/plugin/connector.py b/src/langbot/pkg/plugin/connector.py index 2bb9088d..12413e49 100644 --- a/src/langbot/pkg/plugin/connector.py +++ b/src/langbot/pkg/plugin/connector.py @@ -689,6 +689,16 @@ class PluginRuntimeConnector(ManagedRuntimeConnector): async def get_plugin_readme(self, plugin_author: str, plugin_name: str, language: str = 'en') -> str: return await self.handler.get_plugin_readme(plugin_author, plugin_name, language) + async def get_plugin_logs( + self, + plugin_author: str, + plugin_name: str, + limit: int = 200, + level: str | None = None, + ) -> list[dict[str, Any]]: + # Not cached: logs are live and change constantly. + return await self.handler.get_plugin_logs(plugin_author, plugin_name, limit, level) + @alru_cache(ttl=5 * 60) async def get_plugin_assets(self, plugin_author: str, plugin_name: str, filepath: str) -> dict[str, Any]: return await self.handler.get_plugin_assets(plugin_author, plugin_name, filepath) diff --git a/src/langbot/pkg/plugin/handler.py b/src/langbot/pkg/plugin/handler.py index f5a8511e..3bd85ae6 100644 --- a/src/langbot/pkg/plugin/handler.py +++ b/src/langbot/pkg/plugin/handler.py @@ -953,6 +953,31 @@ class RuntimeConnectionHandler(handler.Handler): return readme_bytes.decode('utf-8') + async def get_plugin_logs( + self, + plugin_author: str, + plugin_name: str, + limit: int = 200, + level: str | None = None, + ) -> list[dict[str, Any]]: + """Get recent log lines captured from the plugin's stderr.""" + try: + result = await self.call_action( + LangBotToRuntimeAction.GET_PLUGIN_LOGS, + { + 'plugin_author': plugin_author, + 'plugin_name': plugin_name, + 'limit': limit, + 'level': level, + }, + timeout=20, + ) + except Exception: + traceback.print_exc() + return [] + + return result.get('logs', []) + async def get_plugin_assets(self, plugin_author: str, plugin_name: str, filepath: str) -> dict[str, Any]: """Get plugin assets""" result = await self.call_action( diff --git a/uv.lock b/uv.lock index 450328f5..24d8428e 100644 --- a/uv.lock +++ b/uv.lock @@ -2082,7 +2082,7 @@ requires-dist = [ { name = "ebooklib", specifier = ">=0.18" }, { name = "gewechat-client", specifier = ">=0.1.5" }, { name = "html2text", specifier = ">=2024.2.26" }, - { name = "langbot-plugin", specifier = "==0.4.3" }, + { name = "langbot-plugin", specifier = "==0.4.4" }, { name = "langchain", specifier = ">=0.2.0" }, { name = "langchain-core", specifier = ">=1.3.3" }, { name = "langchain-text-splitters", specifier = ">=1.1.2" }, @@ -2146,7 +2146,7 @@ dev = [ [[package]] name = "langbot-plugin" -version = "0.4.3" +version = "0.4.4" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "aiofiles" }, @@ -2167,9 +2167,9 @@ dependencies = [ { name = "watchdog" }, { name = "websockets" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/8e/f1/32ec67e8b8eb91159d2b9703f466cc2a763c8cea380dd56561efe793a55b/langbot_plugin-0.4.3.tar.gz", hash = "sha256:747fb78bc666cfac3842cb35130fa8323759dd8768fdaa1975099157a3749c6e", size = 309655, upload-time = "2026-06-13T04:58:10.279Z" } +sdist = { url = "https://files.pythonhosted.org/packages/68/1a/636c057f6e07a0c87dc7b9c1a373d73df82787b7706ba3ba1a95f633ce7c/langbot_plugin-0.4.4.tar.gz", hash = "sha256:8fdad2d22fe8360d2911557fac17f258f57e85f1a36bd50cd488cb44f61225a4", size = 312741, upload-time = "2026-06-13T11:59:36.772Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/28/05/84bd7537efd45fc02044ca9509973160a7d6d10520ff73e31424141a3a6c/langbot_plugin-0.4.3-py3-none-any.whl", hash = "sha256:46aca36e2193c18f9cf332460760dd7b9340ee2e96a57f2e4ae621c4d4c4b61c", size = 211384, upload-time = "2026-06-13T04:58:11.668Z" }, + { url = "https://files.pythonhosted.org/packages/f9/c6/3c313e4ec431fca68326f348bd2c7a61777d43c940bb46ae6c8ebfb66973/langbot_plugin-0.4.4-py3-none-any.whl", hash = "sha256:c91f082ca431539f34790e497e2f056f4e7030e46e0d2bf01a6114b055dd2feb", size = 214164, upload-time = "2026-06-13T11:59:38.053Z" }, ] [[package]] diff --git a/web/src/app/home/plugins/PluginDetailContent.tsx b/web/src/app/home/plugins/PluginDetailContent.tsx index 829e6868..0d1e56e5 100644 --- a/web/src/app/home/plugins/PluginDetailContent.tsx +++ b/web/src/app/home/plugins/PluginDetailContent.tsx @@ -2,10 +2,12 @@ import { useEffect, useState } from 'react'; import { useNavigate } from 'react-router-dom'; import PluginForm from '@/app/home/plugins/components/plugin-installed/plugin-form/PluginForm'; import PluginReadme from '@/app/home/plugins/components/plugin-installed/plugin-readme/PluginReadme'; +import PluginLogs from '@/app/home/plugins/components/plugin-installed/plugin-logs/PluginLogs'; import PluginComponentList from '@/app/home/plugins/components/plugin-installed/PluginComponentList'; import { useSidebarData } from '@/app/home/components/home-sidebar/SidebarDataContext'; import { useTranslation } from 'react-i18next'; import { Badge } from '@/components/ui/badge'; +import { Tabs, TabsContent, TabsList, TabsTrigger } from '@/components/ui/tabs'; import { Button } from '@/components/ui/button'; import { Checkbox } from '@/components/ui/checkbox'; import { @@ -217,8 +219,35 @@ export default function PluginDetailContent({ id }: { id: string }) { {dangerZone}
-
- +
+ + + + {t('plugins.tabDocs')} + + + {t('plugins.tabLogs')} + + + + + + + + +
diff --git a/web/src/app/home/plugins/components/plugin-installed/plugin-logs/PluginLogs.tsx b/web/src/app/home/plugins/components/plugin-installed/plugin-logs/PluginLogs.tsx new file mode 100644 index 00000000..08643aad --- /dev/null +++ b/web/src/app/home/plugins/components/plugin-installed/plugin-logs/PluginLogs.tsx @@ -0,0 +1,156 @@ +import { useCallback, useEffect, useRef, useState } from 'react'; +import { httpClient } from '@/app/infra/http/HttpClient'; +import { useTranslation } from 'react-i18next'; +import { PluginLogEntry } from '@/app/infra/entities/plugin'; +import { Button } from '@/components/ui/button'; +import { + Select, + SelectContent, + SelectItem, + SelectTrigger, + SelectValue, +} from '@/components/ui/select'; +import { RefreshCw } from 'lucide-react'; + +const LEVEL_OPTIONS = ['ALL', 'DEBUG', 'INFO', 'WARNING', 'ERROR'] as const; + +function levelClassName(level: string): string { + switch (level) { + case 'ERROR': + case 'CRITICAL': + return 'text-red-500'; + case 'WARNING': + return 'text-amber-500'; + case 'DEBUG': + return 'text-gray-400 dark:text-gray-500'; + default: + return 'text-gray-700 dark:text-gray-300'; + } +} + +export default function PluginLogs({ + pluginAuthor, + pluginName, +}: { + pluginAuthor: string; + pluginName: string; +}) { + const { t } = useTranslation(); + const [logs, setLogs] = useState([]); + const [isLoading, setIsLoading] = useState(false); + const [level, setLevel] = useState('ALL'); + const [autoRefresh, setAutoRefresh] = useState(true); + const scrollRef = useRef(null); + const atBottomRef = useRef(true); + + const fetchLogs = useCallback(() => { + setIsLoading(true); + httpClient + .getPluginLogs( + pluginAuthor, + pluginName, + 500, + level === 'ALL' ? undefined : level, + ) + .then((res) => { + setLogs(res.logs ?? []); + }) + .catch(() => { + setLogs([]); + }) + .finally(() => { + setIsLoading(false); + }); + }, [pluginAuthor, pluginName, level]); + + useEffect(() => { + fetchLogs(); + }, [fetchLogs]); + + // Auto-refresh poll loop. + useEffect(() => { + if (!autoRefresh) return; + const timer = setInterval(fetchLogs, 3000); + return () => clearInterval(timer); + }, [autoRefresh, fetchLogs]); + + // Keep view pinned to bottom when the user is already at the bottom. + useEffect(() => { + const el = scrollRef.current; + if (el && atBottomRef.current) { + el.scrollTop = el.scrollHeight; + } + }, [logs]); + + function handleScroll() { + const el = scrollRef.current; + if (!el) return; + atBottomRef.current = el.scrollHeight - el.scrollTop - el.clientHeight < 40; + } + + return ( +
+
+ + + +
+ +
+ {logs.length === 0 ? ( +
+ {t('plugins.logsEmpty')} +
+ ) : ( + logs.map((entry, idx) => ( +
+ {entry.text} +
+ )) + )} +
+
+ ); +} diff --git a/web/src/app/infra/entities/plugin/index.ts b/web/src/app/infra/entities/plugin/index.ts index ac9b9563..ad661211 100644 --- a/web/src/app/infra/entities/plugin/index.ts +++ b/web/src/app/infra/entities/plugin/index.ts @@ -21,6 +21,13 @@ export interface PluginComponent { }; } +// A single log line captured from a running plugin's stderr. +export interface PluginLogEntry { + ts: number; + level: string; + text: string; +} + // marketplace plugin v4 export enum PluginV4Status { Any = 'any', diff --git a/web/src/app/infra/http/BackendClient.ts b/web/src/app/infra/http/BackendClient.ts index e9cdb51c..b2f3f7b5 100644 --- a/web/src/app/infra/http/BackendClient.ts +++ b/web/src/app/infra/http/BackendClient.ts @@ -55,6 +55,7 @@ import { ApiRespSkill, } from '@/app/infra/entities/api'; import { Plugin } from '@/app/infra/entities/plugin'; +import type { PluginLogEntry } from '@/app/infra/entities/plugin'; import type { I18nObject } from '@/app/infra/entities/common'; import { GetBotLogsRequest } from '@/app/infra/http/requestParam/bots/GetBotLogsRequest'; import { GetBotLogsResponse } from '@/app/infra/http/requestParam/bots/GetBotLogsResponse'; @@ -604,6 +605,22 @@ export class BackendClient extends BaseHttpClient { ); } + public getPluginLogs( + author: string, + name: string, + limit: number = 200, + level?: string, + ): Promise<{ logs: PluginLogEntry[] }> { + const params = new URLSearchParams(); + params.set('limit', String(limit)); + if (level) { + params.set('level', level); + } + return this.get( + `/api/v1/plugins/${author}/${name}/logs?${params.toString()}`, + ); + } + public getPluginAssetURL( author: string, name: string, diff --git a/web/src/i18n/locales/en-US.ts b/web/src/i18n/locales/en-US.ts index ddf1ab43..91f0b6f3 100644 --- a/web/src/i18n/locales/en-US.ts +++ b/web/src/i18n/locales/en-US.ts @@ -577,6 +577,14 @@ const enUS = { viewSource: 'View Source', loadingReadme: 'Loading documentation...', noReadme: 'This plugin does not provide README documentation', + tabDocs: 'Documentation', + tabLogs: 'Logs', + logsLevelAll: 'All levels', + logsRefresh: 'Refresh', + logsAutoRefreshOn: 'Auto-refresh: On', + logsAutoRefreshOff: 'Auto-refresh: Off', + logsEmpty: + 'No logs yet. Logs printed by the plugin via logger will appear here.', fileUpload: { tooLarge: 'File size exceeds 10MB limit', success: 'File uploaded successfully', diff --git a/web/src/i18n/locales/es-ES.ts b/web/src/i18n/locales/es-ES.ts index 1e85f504..5f802815 100644 --- a/web/src/i18n/locales/es-ES.ts +++ b/web/src/i18n/locales/es-ES.ts @@ -589,6 +589,14 @@ const esES = { viewSource: 'Ver código fuente', loadingReadme: 'Cargando documentación...', noReadme: 'Este plugin no proporciona documentación README', + tabDocs: 'Documentación', + tabLogs: 'Registros', + logsLevelAll: 'Todos los niveles', + logsRefresh: 'Actualizar', + logsAutoRefreshOn: 'Auto-actualizar: Activado', + logsAutoRefreshOff: 'Auto-actualizar: Desactivado', + logsEmpty: + 'Aún no hay registros. Los registros que el plugin imprima mediante logger aparecerán aquí.', fileUpload: { tooLarge: 'El tamaño del archivo supera el límite de 10MB', success: 'Archivo subido correctamente', diff --git a/web/src/i18n/locales/ja-JP.ts b/web/src/i18n/locales/ja-JP.ts index d87113c0..c8c65152 100644 --- a/web/src/i18n/locales/ja-JP.ts +++ b/web/src/i18n/locales/ja-JP.ts @@ -582,6 +582,14 @@ const jaJP = { viewSource: 'ソースを表示', loadingReadme: 'ドキュメントを読み込み中...', noReadme: 'このプラグインはREADMEドキュメントを提供していません', + tabDocs: 'ドキュメント', + tabLogs: 'ログ', + logsLevelAll: 'すべてのレベル', + logsRefresh: '更新', + logsAutoRefreshOn: '自動更新：オン', + logsAutoRefreshOff: '自動更新：オフ', + logsEmpty: + 'ログはまだありません。プラグインが logger で出力したログがここに表示されます。', fileUpload: { tooLarge: 'ファイルサイズが 10MB の制限を超えています', success: 'ファイルのアップロードに成功しました', diff --git a/web/src/i18n/locales/ru-RU.ts b/web/src/i18n/locales/ru-RU.ts index 846e16f7..8ebb4fa2 100644 --- a/web/src/i18n/locales/ru-RU.ts +++ b/web/src/i18n/locales/ru-RU.ts @@ -588,6 +588,14 @@ const ruRU = { viewSource: 'Исходный код', loadingReadme: 'Загрузка документации...', noReadme: 'Этот плагин не предоставляет документацию README', + tabDocs: 'Документация', + tabLogs: 'Журналы', + logsLevelAll: 'Все уровни', + logsRefresh: 'Обновить', + logsAutoRefreshOn: 'Автообновление: вкл.', + logsAutoRefreshOff: 'Автообновление: выкл.', + logsEmpty: + 'Журналов пока нет. Здесь появятся логи, выводимые плагином через logger.', fileUpload: { tooLarge: 'Размер файла превышает лимит 10 МБ', success: 'Файл успешно загружен', diff --git a/web/src/i18n/locales/th-TH.ts b/web/src/i18n/locales/th-TH.ts index 0922b31a..ac976402 100644 --- a/web/src/i18n/locales/th-TH.ts +++ b/web/src/i18n/locales/th-TH.ts @@ -569,6 +569,13 @@ const thTH = { viewSource: 'ดูซอร์สโค้ด', loadingReadme: 'กำลังโหลดเอกสาร...', noReadme: 'ปลั๊กอินนี้ไม่มีเอกสาร README', + tabDocs: 'เอกสาร', + tabLogs: 'บันทึก', + logsLevelAll: 'ทุกระดับ', + logsRefresh: 'รีเฟรช', + logsAutoRefreshOn: 'รีเฟรชอัตโนมัติ: เปิด', + logsAutoRefreshOff: 'รีเฟรชอัตโนมัติ: ปิด', + logsEmpty: 'ยังไม่มีบันทึก บันทึกที่ปลั๊กอินพิมพ์ผ่าน logger จะแสดงที่นี่', fileUpload: { tooLarge: 'ขนาดไฟล์เกินขีดจำกัด 10MB', success: 'อัปโหลดไฟล์สำเร็จ', diff --git a/web/src/i18n/locales/vi-VN.ts b/web/src/i18n/locales/vi-VN.ts index 47d51f2a..be1e7754 100644 --- a/web/src/i18n/locales/vi-VN.ts +++ b/web/src/i18n/locales/vi-VN.ts @@ -583,6 +583,14 @@ const viVN = { viewSource: 'Xem mã nguồn', loadingReadme: 'Đang tải tài liệu...', noReadme: 'Plugin này không cung cấp tài liệu README', + tabDocs: 'Tài liệu', + tabLogs: 'Nhật ký', + logsLevelAll: 'Tất cả cấp độ', + logsRefresh: 'Làm mới', + logsAutoRefreshOn: 'Tự động làm mới: Bật', + logsAutoRefreshOff: 'Tự động làm mới: Tắt', + logsEmpty: + 'Chưa có nhật ký. Nhật ký do plugin in qua logger sẽ hiển thị ở đây.', fileUpload: { tooLarge: 'Kích thước tệp vượt quá giới hạn 10MB', success: 'Tải tệp lên thành công', diff --git a/web/src/i18n/locales/zh-Hans.ts b/web/src/i18n/locales/zh-Hans.ts index a7ef0a53..f32f039a 100644 --- a/web/src/i18n/locales/zh-Hans.ts +++ b/web/src/i18n/locales/zh-Hans.ts @@ -552,6 +552,13 @@ const zhHans = { viewSource: '查看来源', loadingReadme: '正在加载文档...', noReadme: '该插件没有提供 README 文档', + tabDocs: '文档', + tabLogs: '日志', + logsLevelAll: '全部级别', + logsRefresh: '刷新', + logsAutoRefreshOn: '自动刷新：开', + logsAutoRefreshOff: '自动刷新：关', + logsEmpty: '暂无日志。插件通过 logger 打印的日志会显示在这里。', fileUpload: { tooLarge: '文件大小超过 10MB 限制', success: '文件上传成功', diff --git a/web/src/i18n/locales/zh-Hant.ts b/web/src/i18n/locales/zh-Hant.ts index 1d0d9da2..539b34c4 100644 --- a/web/src/i18n/locales/zh-Hant.ts +++ b/web/src/i18n/locales/zh-Hant.ts @@ -552,6 +552,13 @@ const zhHant = { viewSource: '查看來源', loadingReadme: '正在載入文件...', noReadme: '該插件沒有提供 README 文件', + tabDocs: '文件', + tabLogs: '日誌', + logsLevelAll: '全部級別', + logsRefresh: '重新整理', + logsAutoRefreshOn: '自動重新整理：開', + logsAutoRefreshOff: '自動重新整理：關', + logsEmpty: '暫無日誌。外掛透過 logger 列印的日誌會顯示在這裡。', fileUpload: { tooLarge: '檔案大小超過 10MB 限制', success: '檔案上傳成功', From b6fde30aa7de42a31bee0e4c97db230c3d5f7340 Mon Sep 17 00:00:00 2001 From: RockChinQ Date: Sat, 13 Jun 2026 08:03:29 -0400 Subject: [PATCH 02/12] style(plugins): ruff format logs route --- src/langbot/pkg/api/http/controller/groups/plugins.py | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/src/langbot/pkg/api/http/controller/groups/plugins.py b/src/langbot/pkg/api/http/controller/groups/plugins.py index 52b0fb20..c291c123 100644 --- a/src/langbot/pkg/api/http/controller/groups/plugins.py +++ b/src/langbot/pkg/api/http/controller/groups/plugins.py @@ -282,9 +282,7 @@ class PluginsRouterGroup(group.RouterGroup): except (TypeError, ValueError): limit = 200 level = quart.request.args.get('level') or None - logs = await self.ap.plugin_connector.get_plugin_logs( - author, plugin_name, limit=limit, level=level - ) + logs = await self.ap.plugin_connector.get_plugin_logs(author, plugin_name, limit=limit, level=level) return self.success(data={'logs': logs}) @self.route( From 7fe3eedeea189e266b1d430ecd3aaaa666260c0a Mon Sep 17 00:00:00 2001 From: huanghuoguoguo <1051233107@qq.com> Date: Sat, 13 Jun 2026 21:27:47 +0800 Subject: [PATCH 03/12] fix(provider): use LiteLLM input window for context length (#2243) --- .../modelmgr/requesters/litellmchat.py | 38 ++++++++++++------- tests/unit_tests/provider/test_litellmchat.py | 23 +++++++++-- 2 files changed, 45 insertions(+), 16 deletions(-) diff --git a/src/langbot/pkg/provider/modelmgr/requesters/litellmchat.py b/src/langbot/pkg/provider/modelmgr/requesters/litellmchat.py index 6b087916..63536a2c 100644 --- a/src/langbot/pkg/provider/modelmgr/requesters/litellmchat.py +++ b/src/langbot/pkg/provider/modelmgr/requesters/litellmchat.py @@ -75,22 +75,33 @@ class LiteLLMRequester(requester.ProviderAPIRequester): continue return False + @staticmethod + def _positive_int(value: typing.Any) -> int | None: + if isinstance(value, bool): + return None + if isinstance(value, int) and value > 0: + return value + if isinstance(value, str) and value.isdigit(): + parsed_value = int(value) + if parsed_value > 0: + return parsed_value + return None + def _context_length_from_scan_payload(self, model_payload: dict[str, typing.Any] | None) -> int | None: if not model_payload: return None for field_name in ('context_length', 'context_window', 'max_context_length'): - value = model_payload.get(field_name) - if isinstance(value, bool): - continue - if isinstance(value, int) and value > 0: - return value - if isinstance(value, str) and value.isdigit(): - parsed_value = int(value) - if parsed_value > 0: - return parsed_value + context_length = self._positive_int(model_payload.get(field_name)) + if context_length is not None: + return context_length return None + def _context_length_from_litellm_model_info(self, model_info: typing.Any) -> int | None: + if isinstance(model_info, dict): + return self._positive_int(model_info.get('max_input_tokens')) + return self._positive_int(getattr(model_info, 'max_input_tokens', None)) + def _metadata_provider_candidates(self, model_name: str) -> list[str]: normalized_model_name = (model_name or '').lower() candidates = [] @@ -126,7 +137,7 @@ class LiteLLMRequester(requester.ProviderAPIRequester): return None def _safe_context_length(self, model_name: str) -> int | None: - helper = getattr(litellm, 'get_max_tokens', None) + helper = getattr(litellm, 'get_model_info', None) if not callable(helper): return self._known_context_length_fallback(model_name) @@ -143,11 +154,12 @@ class LiteLLMRequester(requester.ProviderAPIRequester): continue tried_candidates.append(candidate) try: - max_tokens = helper(candidate) + model_info = helper(candidate) except Exception: continue - if isinstance(max_tokens, int) and max_tokens > 0: - return max_tokens + context_length = self._context_length_from_litellm_model_info(model_info) + if context_length is not None: + return context_length return self._known_context_length_fallback(model_name) def _supports_function_calling(self, model_name: str) -> bool: diff --git a/tests/unit_tests/provider/test_litellmchat.py b/tests/unit_tests/provider/test_litellmchat.py index 1ec12d82..2878d827 100644 --- a/tests/unit_tests/provider/test_litellmchat.py +++ b/tests/unit_tests/provider/test_litellmchat.py @@ -1034,11 +1034,28 @@ class TestScanModels: }, ) - with patch.object(litellmchat.litellm, 'get_max_tokens') as mock_get_max_tokens: - mock_get_max_tokens.side_effect = lambda model: 131072 if model == 'moonshot/moonshot-v1-128k' else None + with patch.object(litellmchat.litellm, 'get_model_info') as mock_get_model_info: + mock_get_model_info.side_effect = ( + lambda model: {'max_input_tokens': 131072} + if model == 'moonshot/moonshot-v1-128k' + else {} + ) assert requester._safe_context_length('moonshot-v1-128k') == 131072 + def test_safe_context_length_uses_litellm_max_input_tokens(self): + """LiteLLM max_output_tokens must not be treated as the context window.""" + requester = litellmchat.LiteLLMRequester(ap=Mock(), config={}) + + with patch.object(litellmchat.litellm, 'get_model_info') as mock_get_model_info: + mock_get_model_info.return_value = { + 'max_input_tokens': 128000, + 'max_output_tokens': 16384, + 'max_tokens': 16384, + } + + assert requester._safe_context_length('gpt-4o') == 128000 + def test_litellm_bool_helper_tries_moonshot_metadata_alias(self): """OpenAI-compatible Moonshot endpoints still use Moonshot metadata for abilities.""" requester = litellmchat.LiteLLMRequester( @@ -1102,7 +1119,7 @@ class TestScanModels: }, ) - with patch.object(litellmchat.litellm, 'get_max_tokens', side_effect=Exception('not mapped')): + with patch.object(litellmchat.litellm, 'get_model_info', side_effect=Exception('not mapped')): assert requester._safe_context_length('deepseek-v4-pro') == 1_000_000 assert requester._safe_context_length('deepseek-v4-flash') == 1_000_000 From b7d8332cb0a4b745561aa8b63426677afc4fde45 Mon Sep 17 00:00:00 2001 From: RockChinQ Date: Sat, 13 Jun 2026 11:13:18 -0400 Subject: [PATCH 04/12] feat(telemetry): include instance_create_ts in heartbeat payload Load the instance creation timestamp from data/labels/instance_id.json (backfilling+persisting it for instances created before the field existed), expose it as constants.instance_create_ts, and include it in the heartbeat payload so Space can anchor Time-To-Value / onboarding analytics on real install time rather than first-heartbeat. Verified: py_compile, ruff, pytest tests/unit_tests/telemetry/ (37 passed). --- src/langbot/pkg/core/stages/load_config.py | 10 ++++++++++ src/langbot/pkg/telemetry/heartbeat.py | 1 + src/langbot/pkg/utils/constants.py | 8 ++++++++ tests/unit_tests/telemetry/test_heartbeat.py | 1 + 4 files changed, 20 insertions(+) diff --git a/src/langbot/pkg/core/stages/load_config.py b/src/langbot/pkg/core/stages/load_config.py index 26f4a9e1..6fc890f1 100644 --- a/src/langbot/pkg/core/stages/load_config.py +++ b/src/langbot/pkg/core/stages/load_config.py @@ -202,6 +202,16 @@ class LoadConfigStage(stage.BootingStage): constants.instance_id = new_id constants.edition = ap.instance_config.data.get('system', {}).get('edition', 'community') + # Instance creation timestamp: sourced from data/labels/instance_id.json. + # Instances created before this field existed (or supplied via + # system.instance_id) won't have it, so backfill with the current time + # and persist it via the dump below — from then on it stays stable. + instance_create_ts = ap.instance_id.data.get('instance_create_ts', 0) + if not isinstance(instance_create_ts, int) or instance_create_ts <= 0: + instance_create_ts = int(time.time()) + ap.instance_id.data['instance_create_ts'] = instance_create_ts + constants.instance_create_ts = instance_create_ts + print(f'LangBot instance id: {constants.instance_id}') print(f'LangBot edition: {constants.edition}') diff --git a/src/langbot/pkg/telemetry/heartbeat.py b/src/langbot/pkg/telemetry/heartbeat.py index dd2a58d3..34b61673 100644 --- a/src/langbot/pkg/telemetry/heartbeat.py +++ b/src/langbot/pkg/telemetry/heartbeat.py @@ -109,6 +109,7 @@ async def build_heartbeat_payload(ap: core_app.Application) -> dict: 'query_id': '', 'version': constants.semantic_version, 'instance_id': constants.instance_id, + 'instance_create_ts': constants.instance_create_ts, 'edition': constants.edition, 'features': features, 'timestamp': datetime.now(timezone.utc).isoformat(), diff --git a/src/langbot/pkg/utils/constants.py b/src/langbot/pkg/utils/constants.py index fb520da9..2af16486 100644 --- a/src/langbot/pkg/utils/constants.py +++ b/src/langbot/pkg/utils/constants.py @@ -16,3 +16,11 @@ debug_mode = False edition = 'community' instance_id = '' + +instance_create_ts = 0 +"""Unix timestamp (seconds) of when this instance was first created. + +Sourced from ``data/labels/instance_id.json``. Backfilled to the current +time for instances created before this field existed, so it is always a +positive value once load_config has run. +""" diff --git a/tests/unit_tests/telemetry/test_heartbeat.py b/tests/unit_tests/telemetry/test_heartbeat.py index a5bd2e32..18d61f2d 100644 --- a/tests/unit_tests/telemetry/test_heartbeat.py +++ b/tests/unit_tests/telemetry/test_heartbeat.py @@ -62,6 +62,7 @@ class TestBuildHeartbeatPayload: assert payload['event_type'] == 'instance_heartbeat' assert payload['query_id'] == '' + assert 'instance_create_ts' in payload assert 'timestamp' in payload f = payload['features'] assert f['database'] == 'postgresql' From 2e7978317c650fc2b3c23e8a6d35cd007a3c45e5 Mon Sep 17 00:00:00 2001 From: RockChinQ Date: Sat, 13 Jun 2026 11:21:44 -0400 Subject: [PATCH 05/12] chore(release): bump version to 4.10.2 --- pyproject.toml | 2 +- src/langbot/__init__.py | 2 +- uv.lock | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index 024aa021..96e95f7f 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "langbot" -version = "4.10.1" +version = "4.10.2" description = "Production-grade platform for building agentic IM bots" readme = "README.md" license-files = ["LICENSE"] diff --git a/src/langbot/__init__.py b/src/langbot/__init__.py index e2cdf58d..f6a11354 100644 --- a/src/langbot/__init__.py +++ b/src/langbot/__init__.py @@ -1,3 +1,3 @@ """LangBot - Production-grade platform for building agentic IM bots""" -__version__ = '4.10.1' +__version__ = '4.10.2' diff --git a/uv.lock b/uv.lock index 24d8428e..bca1495a 100644 --- a/uv.lock +++ b/uv.lock @@ -1967,7 +1967,7 @@ wheels = [ [[package]] name = "langbot" -version = "4.10.1" +version = "4.10.2" source = { editable = "." } dependencies = [ { name = "aiocqhttp" }, From 1ef4507d9a6ce1718cbbc83596ec0ea7c3ece485 Mon Sep 17 00:00:00 2001 From: huanghuoguoguo <1051233107@qq.com> Date: Sun, 14 Jun 2026 10:57:53 +0800 Subject: [PATCH 06/12] [codex] Delegate web page bot stream helpers (#2245) * fix(platform): delegate web page bot stream helpers * style(platform): format web page bot adapter --- .../pkg/platform/sources/web_page_bot_adapter.py | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/src/langbot/pkg/platform/sources/web_page_bot_adapter.py b/src/langbot/pkg/platform/sources/web_page_bot_adapter.py index d424debd..fa7f8174 100644 --- a/src/langbot/pkg/platform/sources/web_page_bot_adapter.py +++ b/src/langbot/pkg/platform/sources/web_page_bot_adapter.py @@ -84,6 +84,18 @@ class WebPageBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter ): self.listeners.pop(event_type, None) + async def is_stream_output_supported(self) -> bool: + """Delegate stream output check to ws_adapter.""" + if self._ws_adapter is not None: + return await self._ws_adapter.is_stream_output_supported() + return False + + async def create_message_card(self, message_id: str | int, event: platform_events.MessageEvent) -> bool: + """Delegate create_message_card to ws_adapter.""" + if self._ws_adapter is not None: + return await self._ws_adapter.create_message_card(message_id, event) + return False + async def is_muted(self, group_id: int) -> bool: return False From 27be09ab15287e31f1aab3ecf81bf6b80ac7e359 Mon Sep 17 00:00:00 2001 From: huanghuoguoguo <1051233107@qq.com> Date: Sun, 14 Jun 2026 11:12:29 +0800 Subject: [PATCH 07/12] fix(provider): preserve litellm usage details (#2246) --- .../pkg/provider/modelmgr/requester.py | 21 ++++- .../modelmgr/requesters/litellmchat.py | 84 +++++++++++++++---- tests/unit_tests/provider/test_litellmchat.py | 39 +++++++-- 3 files changed, 117 insertions(+), 27 deletions(-) diff --git a/src/langbot/pkg/provider/modelmgr/requester.py b/src/langbot/pkg/provider/modelmgr/requester.py index b673c758..377f7d4a 100644 --- a/src/langbot/pkg/provider/modelmgr/requester.py +++ b/src/langbot/pkg/provider/modelmgr/requester.py @@ -12,6 +12,19 @@ import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query import langbot_plugin.api.entities.builtin.provider.message as provider_message +LLM_USAGE_QUERY_VARIABLE = '_llm_usage' +STREAM_USAGE_QUERY_VARIABLE = '_stream_usage' + + +def _store_llm_usage(query: pipeline_query.Query | None, usage_info: dict | None) -> None: + """Store the latest provider usage on the query for upstream action handlers.""" + if query is None or not usage_info: + return + if query.variables is None: + query.variables = {} + query.variables[LLM_USAGE_QUERY_VARIABLE] = dict(usage_info) + + class RuntimeProvider: """运行时模型提供商""" @@ -67,6 +80,7 @@ class RuntimeProvider: if isinstance(result, tuple): msg, usage_info = result if usage_info: + _store_llm_usage(query, usage_info) input_tokens = usage_info.get('prompt_tokens', 0) output_tokens = usage_info.get('completion_tokens', 0) return msg @@ -146,11 +160,12 @@ class RuntimeProvider: if query: if query.variables is None: query.variables = {} - if '_stream_usage' in query.variables: - usage_info = query.variables['_stream_usage'] + if STREAM_USAGE_QUERY_VARIABLE in query.variables: + usage_info = query.variables[STREAM_USAGE_QUERY_VARIABLE] + _store_llm_usage(query, usage_info) input_tokens = usage_info.get('prompt_tokens', 0) output_tokens = usage_info.get('completion_tokens', 0) - del query.variables['_stream_usage'] + del query.variables[STREAM_USAGE_QUERY_VARIABLE] except Exception as e: status = 'error' error_message = str(e) diff --git a/src/langbot/pkg/provider/modelmgr/requesters/litellmchat.py b/src/langbot/pkg/provider/modelmgr/requesters/litellmchat.py index 63536a2c..8c750bd7 100644 --- a/src/langbot/pkg/provider/modelmgr/requesters/litellmchat.py +++ b/src/langbot/pkg/provider/modelmgr/requesters/litellmchat.py @@ -262,32 +262,82 @@ class LiteLLMRequester(requester.ProviderAPIRequester): - dict with the same keys - missing ``total_tokens`` (derived from prompt + completion) - ``None`` / partially-populated usage (defaults to 0) + - provider-specific token details, including cache token counters """ - if usage is None: - return {'prompt_tokens': 0, 'completion_tokens': 0, 'total_tokens': 0} - def _get(key: str) -> typing.Any: - if isinstance(usage, dict): - return usage.get(key) - return getattr(usage, key, None) + def _plain_value(value: typing.Any) -> typing.Any: + if value is None: + return None + if isinstance(value, dict): + return {k: _plain_value(v) for k, v in value.items() if v is not None} + if isinstance(value, (list, tuple)): + return [_plain_value(v) for v in value] - prompt_tokens = _get('prompt_tokens') or 0 - completion_tokens = _get('completion_tokens') or 0 - total_tokens = _get('total_tokens') or 0 + model_dump = getattr(value, 'model_dump', None) + if callable(model_dump): + try: + dumped = model_dump() + if isinstance(dumped, dict): + return _plain_value(dumped) + except Exception: + pass + + return value + + def _usage_dict(value: typing.Any) -> dict[str, typing.Any]: + if value is None: + return {} + plain = _plain_value(value) + if isinstance(plain, dict): + return plain + + def _is_mock_attr(attr: typing.Any) -> bool: + return type(attr).__module__.startswith('unittest.mock') + + data: dict[str, typing.Any] = {} + for key in ( + 'prompt_tokens', + 'completion_tokens', + 'total_tokens', + 'prompt_tokens_details', + 'completion_tokens_details', + 'cache_creation_input_tokens', + 'cache_read_input_tokens', + 'input_token_details', + 'output_token_details', + ): + attr_value = getattr(value, key, None) + if attr_value is not None and not _is_mock_attr(attr_value): + data[key] = _plain_value(attr_value) + return data + + def _to_int(value: typing.Any) -> int: + try: + return int(value or 0) + except (TypeError, ValueError): + return 0 + + normalized = _usage_dict(usage) + + prompt_tokens = _to_int(normalized.get('prompt_tokens')) + completion_tokens = _to_int(normalized.get('completion_tokens')) + total_tokens = _to_int(normalized.get('total_tokens')) # Some providers omit total_tokens in streaming usage; derive it. if not total_tokens: total_tokens = prompt_tokens + completion_tokens - return { - 'prompt_tokens': int(prompt_tokens), - 'completion_tokens': int(completion_tokens), - 'total_tokens': int(total_tokens), - } + normalized['prompt_tokens'] = prompt_tokens + normalized['completion_tokens'] = completion_tokens + normalized['total_tokens'] = total_tokens + return normalized - def _extract_usage(self, response) -> dict: + def _extract_usage(self, response) -> dict | None: """Extract usage info from a non-streaming LiteLLM response.""" - return self._normalize_usage(getattr(response, 'usage', None)) + usage = getattr(response, 'usage', None) + if usage is None: + return None + return self._normalize_usage(usage) @staticmethod def _as_dict(value: typing.Any) -> dict: @@ -486,7 +536,7 @@ class LiteLLMRequester(requester.ProviderAPIRequester): if query is not None: if query.variables is None: query.variables = {} - query.variables['_stream_usage'] = usage_info + query.variables[requester.STREAM_USAGE_QUERY_VARIABLE] = usage_info if not hasattr(chunk, 'choices') or not chunk.choices: continue diff --git a/tests/unit_tests/provider/test_litellmchat.py b/tests/unit_tests/provider/test_litellmchat.py index 2878d827..abe0cf49 100644 --- a/tests/unit_tests/provider/test_litellmchat.py +++ b/tests/unit_tests/provider/test_litellmchat.py @@ -115,6 +115,15 @@ class TestExtractUsage: assert result['prompt_tokens'] == 0 assert result['completion_tokens'] == 0 + def test_extract_usage_without_provider_usage(self): + """Missing provider usage is not treated as authoritative zero usage.""" + requester = litellmchat.LiteLLMRequester(ap=Mock(), config={}) + + response = Mock() + response.usage = None + + assert requester._extract_usage(response) is None + class TestNormalizeUsage: """Test _normalize_usage helper covering real-world usage shapes""" @@ -131,6 +140,22 @@ class TestNormalizeUsage: ) assert result == {'prompt_tokens': 12, 'completion_tokens': 8, 'total_tokens': 20} + def test_preserves_token_details(self): + """Provider token details such as cache counters are preserved.""" + result = litellmchat.LiteLLMRequester._normalize_usage( + { + 'prompt_tokens': 12, + 'completion_tokens': 8, + 'total_tokens': 20, + 'prompt_tokens_details': {'cached_tokens': 7}, + 'completion_tokens_details': {'reasoning_tokens': 3}, + } + ) + + assert result['prompt_tokens'] == 12 + assert result['prompt_tokens_details'] == {'cached_tokens': 7} + assert result['completion_tokens_details'] == {'reasoning_tokens': 3} + def test_missing_total_is_derived(self): """When total_tokens is absent/zero it is derived from prompt + completion""" usage = Mock() @@ -166,9 +191,7 @@ class TestInvokeLLMStreamUsage: if has_choice: choice = Mock() delta = Mock() - delta.model_dump = Mock( - return_value={'role': 'assistant', 'content': content, 'tool_calls': tool_calls} - ) + delta.model_dump = Mock(return_value={'role': 'assistant', 'content': content, 'tool_calls': tool_calls}) choice.delta = delta choice.finish_reason = finish_reason chunk.choices = [choice] @@ -313,7 +336,8 @@ class TestInvokeLLMStreamUsage: with patch.object(litellmchat, 'acompletion', new=AsyncMock(side_effect=lambda **kw: _aiter())): collected = [ - chunk async for chunk in requester.invoke_llm_stream( + chunk + async for chunk in requester.invoke_llm_stream( query=query, model=model, messages=messages, @@ -788,7 +812,9 @@ class TestInvokeRerank: with patch('httpx.AsyncClient', return_value=mock_client): # arerank must NOT be called on the openai-compatible path with patch.object( - litellmchat, 'arerank', new_callable=AsyncMock, + litellmchat, + 'arerank', + new_callable=AsyncMock, side_effect=AssertionError('arerank must not be used for openai-compatible provider'), ): results = await requester.invoke_rerank( @@ -1068,8 +1094,7 @@ class TestScanModels: with patch.object(litellmchat.litellm, 'supports_function_calling') as mock_supports_function_calling: mock_supports_function_calling.side_effect = ( - lambda model, custom_llm_provider=None: model == 'moonshot/kimi-k2.6' - and custom_llm_provider is None + lambda model, custom_llm_provider=None: model == 'moonshot/kimi-k2.6' and custom_llm_provider is None ) assert requester._supports_function_calling('kimi-k2.6') is True From e9fe2f2d432d1566bf3403ca64c7aa16712f8706 Mon Sep 17 00:00:00 2001 From: huanghuoguoguo <1051233107@qq.com> Date: Sun, 14 Jun 2026 11:29:57 +0800 Subject: [PATCH 08/12] feat(agent-runner): support host tool lookup (#2244) --- src/langbot/pkg/provider/tools/errors.py | 6 ++++++ src/langbot/pkg/provider/tools/loader.py | 10 ++++++++++ src/langbot/pkg/provider/tools/loaders/mcp.py | 7 +++++++ .../pkg/provider/tools/loaders/native.py | 3 ++- .../pkg/provider/tools/loaders/plugin.py | 3 ++- src/langbot/pkg/provider/tools/toolmgr.py | 19 ++++++++++++++++++- .../unit_tests/provider/test_tool_manager.py | 4 ++-- 7 files changed, 47 insertions(+), 5 deletions(-) create mode 100644 src/langbot/pkg/provider/tools/errors.py diff --git a/src/langbot/pkg/provider/tools/errors.py b/src/langbot/pkg/provider/tools/errors.py new file mode 100644 index 00000000..d44b39ba --- /dev/null +++ b/src/langbot/pkg/provider/tools/errors.py @@ -0,0 +1,6 @@ +class ToolNotFoundError(ValueError): + """Raised when a requested tool cannot be found in any active loader.""" + + def __init__(self, name: str): + self.name = name + super().__init__(f'Tool not found: {name}') diff --git a/src/langbot/pkg/provider/tools/loader.py b/src/langbot/pkg/provider/tools/loader.py index e90f07b3..f97e8216 100644 --- a/src/langbot/pkg/provider/tools/loader.py +++ b/src/langbot/pkg/provider/tools/loader.py @@ -4,12 +4,15 @@ import abc import typing from typing import TYPE_CHECKING +from langbot_plugin.api.definition.components.manifest import ComponentManifest from langbot_plugin.api.entities.events import pipeline_query import langbot_plugin.api.entities.builtin.resource.tool as resource_tool if TYPE_CHECKING: from ...core import app +ToolLookupResult = resource_tool.LLMTool | ComponentManifest + preregistered_loaders: list[typing.Type[ToolLoader]] = [] @@ -43,6 +46,13 @@ class ToolLoader(abc.ABC): """获取所有工具""" pass + async def get_tool(self, name: str) -> ToolLookupResult | None: + """Get one tool by name.""" + for tool in await self.get_tools(): + if tool.name == name: + return tool + return None + @abc.abstractmethod async def has_tool(self, name: str) -> bool: """检查工具是否存在""" diff --git a/src/langbot/pkg/provider/tools/loaders/mcp.py b/src/langbot/pkg/provider/tools/loaders/mcp.py index 117f29cd..8049b185 100644 --- a/src/langbot/pkg/provider/tools/loaders/mcp.py +++ b/src/langbot/pkg/provider/tools/loaders/mcp.py @@ -567,6 +567,13 @@ class MCPLoader(loader.ToolLoader): return True return False + async def get_tool(self, name: str) -> resource_tool.LLMTool | None: + for session in self.sessions.values(): + for function in session.get_tools(): + if function.name == name: + return function + return None + async def invoke_tool(self, name: str, parameters: dict, query: pipeline_query.Query) -> typing.Any: """执行工具调用""" for session in self.sessions.values(): diff --git a/src/langbot/pkg/provider/tools/loaders/native.py b/src/langbot/pkg/provider/tools/loaders/native.py index d6ef11d1..83390049 100644 --- a/src/langbot/pkg/provider/tools/loaders/native.py +++ b/src/langbot/pkg/provider/tools/loaders/native.py @@ -7,6 +7,7 @@ import langbot_plugin.api.entities.builtin.resource.tool as resource_tool from langbot_plugin.api.entities.events import pipeline_query from .. import loader +from ..errors import ToolNotFoundError from . import skill as skill_loader EXEC_TOOL_NAME = 'exec' @@ -90,7 +91,7 @@ class NativeToolLoader(loader.ToolLoader): return await self._invoke_glob(parameters, query) if name == GREP_TOOL_NAME: return await self._invoke_grep(parameters, query) - raise ValueError(f'未找到工具: {name}') + raise ToolNotFoundError(name) async def shutdown(self): pass diff --git a/src/langbot/pkg/provider/tools/loaders/plugin.py b/src/langbot/pkg/provider/tools/loaders/plugin.py index 5b741848..544882d3 100644 --- a/src/langbot/pkg/provider/tools/loaders/plugin.py +++ b/src/langbot/pkg/provider/tools/loaders/plugin.py @@ -3,6 +3,7 @@ from __future__ import annotations import typing import traceback +from langbot_plugin.api.definition.components.manifest import ComponentManifest from langbot_plugin.api.entities.events import pipeline_query from .. import loader @@ -39,7 +40,7 @@ class PluginToolLoader(loader.ToolLoader): return True return False - async def _get_tool(self, name: str) -> resource_tool.LLMTool: + async def get_tool(self, name: str) -> ComponentManifest | None: for tool in await self.ap.plugin_connector.list_tools(): if tool.metadata.name == name: return tool diff --git a/src/langbot/pkg/provider/tools/toolmgr.py b/src/langbot/pkg/provider/tools/toolmgr.py index fd03b303..38b08aa1 100644 --- a/src/langbot/pkg/provider/tools/toolmgr.py +++ b/src/langbot/pkg/provider/tools/toolmgr.py @@ -6,6 +6,9 @@ from typing import TYPE_CHECKING import langbot_plugin.api.entities.builtin.resource.tool as resource_tool from langbot_plugin.api.entities.events import pipeline_query +from . import loader as tool_loader +from .errors import ToolNotFoundError + if TYPE_CHECKING: from ...core import app from langbot.pkg.provider.tools.loaders import ( @@ -67,6 +70,20 @@ class ToolManager: return all_functions + async def get_tool_by_name(self, name: str) -> tool_loader.ToolLookupResult | None: + """Get tool by name from any active loader.""" + for active_loader in ( + self.native_tool_loader, + self.plugin_tool_loader, + self.mcp_tool_loader, + self.skill_tool_loader, + ): + tool = await active_loader.get_tool(name) + if tool: + return tool + + return None + async def generate_tools_for_openai(self, use_funcs: list[resource_tool.LLMTool]) -> list: tools = [] @@ -98,7 +115,7 @@ class ToolManager: if await self.skill_tool_loader.has_tool(name): telemetry_features.increment(query, 'tool_calls', 'skill') return await self.skill_tool_loader.invoke_tool(name, parameters, query) - raise ValueError(f'未找到工具: {name}') + raise ToolNotFoundError(name) async def shutdown(self): await self.native_tool_loader.shutdown() diff --git a/tests/unit_tests/provider/test_tool_manager.py b/tests/unit_tests/provider/test_tool_manager.py index fbfcb13f..2fcf25fb 100644 --- a/tests/unit_tests/provider/test_tool_manager.py +++ b/tests/unit_tests/provider/test_tool_manager.py @@ -226,7 +226,7 @@ class TestToolManagerExecuteFuncCall: @pytest.mark.asyncio async def test_execute_raises_when_tool_not_found(self, mock_app_with_loaders, sample_query): - """Test that execute_func_call raises ValueError when tool not found.""" + """Test that execute_func_call raises ToolNotFoundError when tool not found.""" toolmgr = get_toolmgr_module() mock_app, mock_plugin_loader, mock_mcp_loader = mock_app_with_loaders @@ -236,7 +236,7 @@ class TestToolManagerExecuteFuncCall: manager = toolmgr.ToolManager(mock_app) self._wire_loaders(manager, mock_app, mock_plugin_loader, mock_mcp_loader) - with pytest.raises(ValueError, match='未找到工具'): + with pytest.raises(toolmgr.ToolNotFoundError, match='Tool not found: unknown_tool'): await manager.execute_func_call('unknown_tool', {}, sample_query) @pytest.mark.asyncio From a60827f2218f198c0993167a09604d7a50a434a4 Mon Sep 17 00:00:00 2001 From: huanghuoguoguo <60681390+huanghuoguoguo@users.noreply.github.com> Date: Sun, 14 Jun 2026 11:07:46 +0800 Subject: [PATCH 09/12] fix(tools): harden agent runner tool runtimes --- .../provider/tools/loaders/availability.py | 18 + .../pkg/provider/tools/loaders/mcp_stdio.py | 104 +++- .../pkg/provider/tools/loaders/native.py | 537 ++++++++++++++++-- .../pkg/provider/tools/loaders/skill.py | 111 ++++ .../provider/tools/loaders/skill_authoring.py | 75 +-- .../provider/test_mcp_box_integration.py | 48 +- tests/unit_tests/provider/test_skill_tools.py | 6 +- 7 files changed, 745 insertions(+), 154 deletions(-) create mode 100644 src/langbot/pkg/provider/tools/loaders/availability.py diff --git a/src/langbot/pkg/provider/tools/loaders/availability.py b/src/langbot/pkg/provider/tools/loaders/availability.py new file mode 100644 index 00000000..58d79586 --- /dev/null +++ b/src/langbot/pkg/provider/tools/loaders/availability.py @@ -0,0 +1,18 @@ +from __future__ import annotations + +from typing import Any + + +async def is_box_backend_available(ap: Any) -> bool: + """Return whether the configured Box backend is ready for tool execution.""" + box_service = getattr(ap, 'box_service', None) + if box_service is None: + return False + if not getattr(box_service, 'available', False): + return False + try: + status = await box_service.get_status() + backend_info = status.get('backend', {}) + return bool(backend_info.get('available', False)) + except Exception: + return False diff --git a/src/langbot/pkg/provider/tools/loaders/mcp_stdio.py b/src/langbot/pkg/provider/tools/loaders/mcp_stdio.py index ff607e66..736dacea 100644 --- a/src/langbot/pkg/provider/tools/loaders/mcp_stdio.py +++ b/src/langbot/pkg/provider/tools/loaders/mcp_stdio.py @@ -5,6 +5,7 @@ import asyncio import os import shutil import shlex +import threading from typing import TYPE_CHECKING, Any import pydantic @@ -18,12 +19,26 @@ from ....box.workspace import ( rewrite_mounted_path, rewrite_venv_command, unwrap_venv_path, + wrap_python_command_with_env, ) if TYPE_CHECKING: from .mcp import RuntimeMCPSession +_WORKSPACE_COPY_LOCKS: dict[str, threading.Lock] = {} +_WORKSPACE_COPY_LOCKS_GUARD = threading.Lock() + + +def _workspace_copy_lock(path: str) -> threading.Lock: + with _WORKSPACE_COPY_LOCKS_GUARD: + lock = _WORKSPACE_COPY_LOCKS.get(path) + if lock is None: + lock = threading.Lock() + _WORKSPACE_COPY_LOCKS[path] = lock + return lock + + class MCPSessionErrorPhase(enum.Enum): """Which phase of the MCP lifecycle failed.""" @@ -49,7 +64,7 @@ class MCPServerBoxConfig(pydantic.BaseModel): host_path: str | None = None host_path_mode: str = 'ro' # MCP servers default to read-write mount only when explicitly requested env: dict[str, str] = pydantic.Field(default_factory=dict) - startup_timeout_sec: int = 120 # Longer default to allow dependency bootstrap + startup_timeout_sec: int = 300 # First Docker bootstrap may need to build a venv and install MCP deps. cpus: float | None = None memory_mb: int | None = None pids_limit: int | None = None @@ -128,6 +143,7 @@ class BoxStdioSessionRuntime: workspace = self._build_workspace(host_path=None) host_path = self.resolve_host_path() process_cwd = '/workspace' + install_cmd: str | None = None try: await workspace.create_session() @@ -168,6 +184,8 @@ class BoxStdioSessionRuntime: env=self.server_config.get('env', {}), cwd=process_cwd, ) + if install_cmd: + payload = self._wrap_process_payload_with_python_env(payload, process_cwd) payload['process_id'] = self.process_id await workspace.box_service.start_managed_process(workspace.session_id, payload) except Exception: @@ -253,14 +271,44 @@ class BoxStdioSessionRuntime: @staticmethod def _copy_workspace_tree(source_path: str, process_host_root: str, process_host_workspace: str) -> None: - shutil.rmtree(process_host_root, ignore_errors=True) - os.makedirs(process_host_root, exist_ok=True) - shutil.copytree( - source_path, - process_host_workspace, - symlinks=True, - ignore=shutil.ignore_patterns('.git', '__pycache__', '.pytest_cache', '.mypy_cache', '.ruff_cache'), - ) + # Docker-backed bootstrap writes root-owned runtime directories such as + # .venv/.tmp into the staged workspace. The host process may not be able + # to delete them, so refresh source files in place and preserve runtime + # directories instead of rmtree'ing the whole staging root. + with _workspace_copy_lock(process_host_root): + preserved_names = {'.venv', 'venv', 'env', '.env', '.cache', '.tmp', '.langbot'} + os.makedirs(process_host_workspace, exist_ok=True) + for name in os.listdir(process_host_workspace): + if name in preserved_names: + continue + path = os.path.join(process_host_workspace, name) + if os.path.isdir(path) and not os.path.islink(path): + shutil.rmtree(path, ignore_errors=True) + else: + try: + os.unlink(path) + except FileNotFoundError: + pass + shutil.copytree( + source_path, + process_host_workspace, + symlinks=True, + dirs_exist_ok=True, + ignore=shutil.ignore_patterns( + '.git', + '__pycache__', + '.pytest_cache', + '.mypy_cache', + '.ruff_cache', + '.venv', + 'venv', + 'env', + '.env', + '.cache', + '.tmp', + '.langbot', + ), + ) async def _cleanup_staged_workspace(self) -> None: if not self.resolve_host_path(): @@ -343,23 +391,31 @@ class BoxStdioSessionRuntime: @staticmethod def detect_install_command(host_path: str, workspace_path: str = '/workspace') -> str | None: workspace_kind = classify_python_workspace(host_path) - quoted_workspace_path = shlex.quote(workspace_path) - if workspace_kind == 'package': - return ( - 'mkdir -p /opt/_lb_src' - f' && tar -C {quoted_workspace_path}' - ' --exclude=.venv --exclude=.git --exclude=__pycache__' - ' --exclude=node_modules --exclude=.tox --exclude=.nox' - ' --exclude="*.egg-info" --exclude=.uv-cache' - ' -cf - .' - ' | tar -C /opt/_lb_src -xf -' - ' && pip install --no-cache-dir /opt/_lb_src' - ' && rm -rf /opt/_lb_src' - ) - if workspace_kind == 'requirements': - return f'pip install --no-cache-dir -r {quoted_workspace_path}/requirements.txt' + if workspace_kind in {'package', 'requirements'}: + return wrap_python_command_with_env('python -c "pass"', mount_path=workspace_path).rstrip() return None + @staticmethod + def _wrap_process_payload_with_python_env(payload: dict[str, Any], workspace_path: str) -> dict[str, Any]: + """Start a prepared Python workspace without writing bootstrap output to MCP stdio.""" + workspace_root = workspace_path.rstrip('/') or '/workspace' + venv_dir = f'{workspace_root}/.venv' + venv_bin = f'{venv_dir}/bin' + command = ' '.join( + [shlex.quote(payload['command']), *[shlex.quote(arg) for arg in payload.get('args', [])]] + ) + wrapped = dict(payload) + wrapped['command'] = 'sh' + wrapped['args'] = [ + '-lc', + ( + f'export VIRTUAL_ENV={shlex.quote(venv_dir)}; ' + f'export PATH={shlex.quote(venv_bin)}:$PATH; ' + f'exec {command}' + ), + ] + return wrapped + def build_box_session_payload(self, session_id: str, host_path: str | None = None) -> dict[str, Any]: workspace = self._build_workspace() workspace.session_id = session_id diff --git a/src/langbot/pkg/provider/tools/loaders/native.py b/src/langbot/pkg/provider/tools/loaders/native.py index 83390049..bf9f357f 100644 --- a/src/langbot/pkg/provider/tools/loaders/native.py +++ b/src/langbot/pkg/provider/tools/loaders/native.py @@ -1,6 +1,7 @@ from __future__ import annotations import json +import mimetypes import os import langbot_plugin.api.entities.builtin.resource.tool as resource_tool @@ -8,6 +9,7 @@ from langbot_plugin.api.entities.events import pipeline_query from .. import loader from ..errors import ToolNotFoundError +from .availability import is_box_backend_available from . import skill as skill_loader EXEC_TOOL_NAME = 'exec' @@ -22,6 +24,15 @@ _ALL_TOOL_NAMES = {EXEC_TOOL_NAME, READ_TOOL_NAME, WRITE_TOOL_NAME, EDIT_TOOL_NA # Skip these dirs during grep walk to avoid noise _SKIP_DIRS = {'.git', 'node_modules', '__pycache__', '.venv', 'venv', '.tox', 'dist', 'build'} +_DEFAULT_READ_MAX_LINES = 2000 +_MAX_READ_MAX_LINES = 10000 +_DEFAULT_TOOL_RESULT_MAX_BYTES = 50 * 1024 +_BOX_FILE_SCRIPT_MAX_BYTES = 2048 +_GLOB_MAX_MATCHES = 100 +_GREP_MAX_MATCHES = 200 +_GREP_MAX_FILES = 5000 +_GREP_MAX_LINE_CHARS = 500 + class NativeToolLoader(loader.ToolLoader): def __init__(self, ap): @@ -43,18 +54,7 @@ class NativeToolLoader(loader.ToolLoader): async def _check_backend_available(self) -> bool: """Check if the box backend is truly available (not just the runtime).""" - box_service = getattr(self.ap, 'box_service', None) - if box_service is None: - return False - if not getattr(box_service, 'available', False): - return False - # Check if backend is truly available via get_status - try: - status = await box_service.get_status() - backend_info = status.get('backend', {}) - return backend_info.get('available', False) - except Exception: - return False + return await is_box_backend_available(self.ap) async def get_tools(self, bound_plugins: list[str] | None = None) -> list[resource_tool.LLMTool]: if not self._is_sandbox_available(): @@ -139,6 +139,7 @@ class NativeToolLoader(loader.ToolLoader): # via execute_tool. Skills are mounted at /workspace/.skills/{name}/ # via extra_mounts built by BoxService. result = await self.ap.box_service.execute_tool(parameters, query) + result = self._normalize_exec_result(result) if selected_skill is not None: self._refresh_skill_from_disk(selected_skill) @@ -227,19 +228,65 @@ class NativeToolLoader(loader.ToolLoader): except Exception: return {'ok': False, 'error': stdout or 'Box file operation returned no result'} - async def _read_workspace_via_box(self, path: str, query: pipeline_query.Query) -> dict: + async def _read_workspace_via_box(self, path: str, parameters: dict, query: pipeline_query.Query) -> dict: + offset = self._positive_int(parameters.get('offset'), default=1) + max_lines = self._positive_int( + parameters.get('limit'), + default=_DEFAULT_READ_MAX_LINES, + max_value=_MAX_READ_MAX_LINES, + ) + # Box file fallback returns through exec stdout, which is already capped + # by BoxService. Keep this payload small enough to remain valid JSON. + max_bytes = min( + self._positive_int(parameters.get('max_bytes'), default=_DEFAULT_TOOL_RESULT_MAX_BYTES), + _BOX_FILE_SCRIPT_MAX_BYTES, + ) script = f""" import json, os path = {json.dumps(path)} +offset = {offset} +max_lines = {max_lines} +max_bytes = {max_bytes} if not path.startswith('/workspace'): print(json.dumps({{'ok': False, 'error': 'Path must be under /workspace.'}})) elif not os.path.exists(path): print(json.dumps({{'ok': False, 'error': f'File not found: {{path}}'}})) elif os.path.isdir(path): - print(json.dumps({{'ok': True, 'content': '\\n'.join(sorted(os.listdir(path))), 'is_directory': True}})) + entries = sorted(os.listdir(path)) + content = '\\n'.join(entries) + print(json.dumps({{'ok': True, 'content': content, 'is_directory': True, 'total': len(entries), 'truncated': False}})) else: + lines = [] + output_bytes = 0 + end_line = offset - 1 + truncated = False + next_offset = None with open(path, 'r', encoding='utf-8', errors='replace') as f: - print(json.dumps({{'ok': True, 'content': f.read()}})) + for line_number, line in enumerate(f, 1): + if line_number < offset: + continue + if len(lines) >= max_lines: + truncated = True + next_offset = line_number + break + line_bytes = len(line.encode('utf-8')) + if output_bytes + line_bytes > max_bytes: + truncated = True + next_offset = line_number + break + lines.append(line.rstrip('\\n')) + output_bytes += line_bytes + end_line = line_number + print(json.dumps({{ + 'ok': True, + 'content': '\\n'.join(lines), + 'truncated': truncated, + 'start_line': offset, + 'end_line': end_line, + 'next_offset': next_offset, + 'max_lines': max_lines, + 'max_bytes': max_bytes, + }})) """.strip() return await self._run_workspace_file_script(script, query) @@ -307,12 +354,27 @@ else: if not any(part in skip_dirs for part in item.parts) ] hits.sort(key=lambda item: item.stat().st_mtime if item.exists() else 0, reverse=True) - shown = hits[:100] + shown = hits[:{_GLOB_MAX_MATCHES}] matches = [] + output_bytes = 0 + truncated_by_bytes = False for item in shown: rel = os.path.relpath(str(item), path) - matches.append(os.path.join(path, rel).replace(os.sep, '/')) - print(json.dumps({{'ok': True, 'matches': matches, 'total': len(hits), 'truncated': len(hits) > 100}})) + sandbox_path = os.path.join(path, rel).replace(os.sep, '/') + entry_bytes = len(sandbox_path.encode('utf-8')) + (1 if matches else 0) + if output_bytes + entry_bytes > {_DEFAULT_TOOL_RESULT_MAX_BYTES}: + truncated_by_bytes = True + break + matches.append(sandbox_path) + output_bytes += entry_bytes + print(json.dumps({{ + 'ok': True, + 'matches': matches, + 'preview': '\\n'.join(matches), + 'total': len(hits), + 'truncated': len(hits) > len(matches) or truncated_by_bytes, + 'truncated_by': 'bytes' if truncated_by_bytes else ('matches' if len(hits) > len(matches) else None), + }})) """.strip() return await self._run_workspace_file_script(script, query) @@ -350,29 +412,54 @@ else: continue if item.is_file(): files.append(item) - if len(files) >= 5000: + if len(files) >= {_GREP_MAX_FILES}: break matches = [] + output_bytes = 0 + truncated_by = None for fp in files: try: - text = fp.read_text(errors='ignore') + handle = fp.open('r', encoding='utf-8', errors='ignore') except OSError: continue - for lineno, line in enumerate(text.splitlines(), 1): - if regex.search(line): - if base.is_file(): - file_path = path - else: - rel = os.path.relpath(str(fp), path) - file_path = os.path.join(path, rel).replace(os.sep, '/') - matches.append({{'file': file_path, 'line': lineno, 'content': line.rstrip()}}) - if len(matches) >= 200: - break - if len(matches) >= 200: + with handle: + for lineno, line in enumerate(handle, 1): + if regex.search(line): + if base.is_file(): + file_path = path + else: + rel = os.path.relpath(str(fp), path) + file_path = os.path.join(path, rel).replace(os.sep, '/') + content = line.rstrip() + line_truncated = False + if len(content) > {_GREP_MAX_LINE_CHARS}: + content = content[:{_GREP_MAX_LINE_CHARS}] + '... [truncated]' + line_truncated = True + entry = {{'file': file_path, 'line': lineno, 'content': content}} + entry_bytes = len(json.dumps(entry, ensure_ascii=False).encode('utf-8')) + 1 + if output_bytes + entry_bytes > {_DEFAULT_TOOL_RESULT_MAX_BYTES}: + truncated_by = 'bytes' + break + if line_truncated and truncated_by is None: + truncated_by = 'line' + matches.append(entry) + output_bytes += entry_bytes + if len(matches) >= {_GREP_MAX_MATCHES}: + truncated_by = truncated_by or 'matches' + break + if truncated_by == 'bytes' or len(matches) >= {_GREP_MAX_MATCHES}: + break + if truncated_by == 'bytes' or len(matches) >= {_GREP_MAX_MATCHES}: break - print(json.dumps({{'ok': True, 'matches': matches, 'total': len(matches), 'truncated': len(matches) >= 200}})) + print(json.dumps({{ + 'ok': True, + 'matches': matches, + 'total': len(matches), + 'truncated': truncated_by is not None, + 'truncated_by': truncated_by, + }})) """.strip() return await self._run_workspace_file_script(script, query) @@ -387,14 +474,22 @@ else: ) if skill_request is not None and hasattr(self.ap.box_service, 'read_skill_file'): selected_skill, relative = skill_request + host_path = self._resolve_skill_host_path(selected_skill, relative) + if host_path and os.path.exists(host_path): + if os.path.isdir(host_path): + return self._build_directory_result(os.listdir(host_path)) + result = self._read_text_file_preview(host_path, parameters) + host_root = str(selected_skill.get('package_root', '') or '') + return await self._attach_file_artifact_ref(result, host_path, host_root, path, query) + try: result = await self.ap.box_service.read_skill_file(selected_skill['name'], relative) - return {'ok': True, 'content': result.get('content', '')} + return self._build_read_result_from_text(str(result.get('content', '')), parameters) except Exception: try: result = await self.ap.box_service.list_skill_files(selected_skill['name'], relative) entries = [entry['name'] for entry in result.get('entries', [])] - return {'ok': True, 'content': '\n'.join(sorted(entries)), 'is_directory': True} + return self._build_directory_result(entries) except Exception as exc: return {'ok': False, 'error': str(exc)} @@ -405,15 +500,15 @@ else: include_activated=True, ) if self._should_use_box_workspace_files(selected_skill): - return await self._read_workspace_via_box(path, query) + return await self._read_workspace_via_box(path, parameters, query) if not os.path.exists(host_path): return {'ok': False, 'error': f'File not found: {path}'} if os.path.isdir(host_path): entries = os.listdir(host_path) - return {'ok': True, 'content': '\n'.join(sorted(entries)), 'is_directory': True} - with open(host_path, 'r', errors='replace') as f: - content = f.read() - return {'ok': True, 'content': content} + return self._build_directory_result(entries) + result = self._read_text_file_preview(host_path, parameters) + host_root = self._get_host_root(selected_skill) + return await self._attach_file_artifact_ref(result, host_path, host_root, path, query) async def _invoke_write(self, parameters: dict, query: pipeline_query.Query) -> dict: path = parameters['path'] @@ -584,6 +679,29 @@ else: 'type': 'string', 'description': 'Absolute path to the file (must be under /workspace).', }, + 'offset': { + 'type': 'integer', + 'description': '1-indexed line number to start reading from. Defaults to 1.', + 'default': 1, + 'minimum': 1, + }, + 'limit': { + 'type': 'integer', + 'description': f'Maximum number of lines to return. Defaults to {_DEFAULT_READ_MAX_LINES}.', + 'default': _DEFAULT_READ_MAX_LINES, + 'minimum': 1, + 'maximum': _MAX_READ_MAX_LINES, + }, + 'max_bytes': { + 'type': 'integer', + 'description': ( + 'Maximum bytes of file content to return. ' + f'Defaults to {_DEFAULT_TOOL_RESULT_MAX_BYTES}.' + ), + 'default': _DEFAULT_TOOL_RESULT_MAX_BYTES, + 'minimum': 1, + 'maximum': _DEFAULT_TOOL_RESULT_MAX_BYTES, + }, }, 'required': ['path'], 'additionalProperties': False, @@ -740,22 +858,30 @@ else: hits.sort(key=lambda p: p.stat().st_mtime if p.exists() else 0, reverse=True) total = len(hits) - shown = hits[:100] + shown = hits[:_GLOB_MAX_MATCHES] # Convert back to sandbox paths sandbox_paths = [] + output_bytes = 0 + truncated_by_bytes = False for h in shown: rel = os.path.relpath(str(h), host_path) sandbox_path = os.path.join(path, rel) + entry_bytes = len(sandbox_path.encode('utf-8')) + (1 if sandbox_paths else 0) + if output_bytes + entry_bytes > _DEFAULT_TOOL_RESULT_MAX_BYTES: + truncated_by_bytes = True + break sandbox_paths.append(sandbox_path) + output_bytes += entry_bytes - result_lines = sandbox_paths - result = '\n'.join(result_lines) - - if total > 100: - result += f'\n... ({total} matches, showing first 100)' - - return {'ok': True, 'matches': result_lines, 'total': total, 'truncated': total > 100} + return { + 'ok': True, + 'matches': sandbox_paths, + 'preview': '\n'.join(sandbox_paths), + 'total': total, + 'truncated': total > len(sandbox_paths) or truncated_by_bytes, + 'truncated_by': 'bytes' if truncated_by_bytes else ('matches' if total > len(sandbox_paths) else None), + } async def _invoke_grep(self, parameters: dict, query: pipeline_query.Query) -> dict: pattern = parameters['pattern'] @@ -791,32 +917,46 @@ else: files = self._grep_walk(base, include) matches = [] + output_bytes = 0 + truncated_by = None for fp in files: try: - text = fp.read_text(errors='ignore') + handle = fp.open('r', encoding='utf-8', errors='ignore') except OSError: continue - for lineno, line in enumerate(text.splitlines(), 1): - if regex.search(line): - rel = os.path.relpath(str(fp), host_path) - sandbox_path = os.path.join(path, rel) - matches.append( - { + with handle: + for lineno, line in enumerate(handle, 1): + if regex.search(line): + rel = os.path.relpath(str(fp), host_path) + sandbox_path = os.path.join(path, rel) + content, line_truncated = self._truncate_grep_line(line.rstrip()) + entry = { 'file': sandbox_path, 'line': lineno, - 'content': line.rstrip(), + 'content': content, } - ) - if len(matches) >= 200: - break - if len(matches) >= 200: + entry_bytes = len(json.dumps(entry, ensure_ascii=False).encode('utf-8')) + 1 + if output_bytes + entry_bytes > _DEFAULT_TOOL_RESULT_MAX_BYTES: + truncated_by = 'bytes' + break + if line_truncated and truncated_by is None: + truncated_by = 'line' + matches.append(entry) + output_bytes += entry_bytes + if len(matches) >= _GREP_MAX_MATCHES: + truncated_by = truncated_by or 'matches' + break + if truncated_by == 'bytes' or len(matches) >= _GREP_MAX_MATCHES: + break + if truncated_by == 'bytes' or len(matches) >= _GREP_MAX_MATCHES: break return { 'ok': True, 'matches': matches, 'total': len(matches), - 'truncated': len(matches) >= 200, + 'truncated': truncated_by is not None, + 'truncated_by': truncated_by, } @staticmethod @@ -828,10 +968,285 @@ else: continue if item.is_file(): results.append(item) - if len(results) >= 5000: + if len(results) >= _GREP_MAX_FILES: break return results + @staticmethod + def _resolve_skill_host_path(selected_skill: dict, relative: str) -> str | None: + package_root = str(selected_skill.get('package_root', '') or '').strip() + if not package_root: + return None + + host_root = os.path.realpath(package_root) + host_path = os.path.realpath(os.path.join(host_root, relative)) + if not (host_path == host_root or host_path.startswith(host_root + os.sep)): + raise ValueError('Path escapes the skill package boundary.') + return host_path + + def _get_host_root(self, selected_skill: dict | None) -> str: + if selected_skill is not None: + return str(selected_skill.get('package_root', '') or '') + return str(getattr(self.ap.box_service, 'default_workspace', '') or '') + + async def _attach_file_artifact_ref( + self, + result: dict, + host_path: str, + host_root: str, + sandbox_path: str, + query: pipeline_query.Query, + ) -> dict: + if not result.get('ok') or not result.get('truncated') or result.get('artifact_refs'): + return result + if not host_root or not os.path.isfile(host_path): + return result + + run_session = self._get_agent_run_session(query) + if not run_session: + return result + + persistence_mgr = getattr(self.ap, 'persistence_mgr', None) + get_db_engine = getattr(persistence_mgr, 'get_db_engine', None) + if not callable(get_db_engine): + return result + + try: + from langbot.pkg.agent.runner.artifact_store import ArtifactStore + + authorization = run_session.get('authorization', {}) if isinstance(run_session, dict) else {} + mime_type = mimetypes.guess_type(host_path)[0] or 'text/plain' + size_bytes = os.path.getsize(host_path) + metadata = { + 'tool_name': READ_TOOL_NAME, + 'sandbox_path': sandbox_path, + 'truncated_by': result.get('truncated_by'), + 'start_line': result.get('start_line'), + 'end_line': result.get('end_line'), + 'next_offset': result.get('next_offset'), + } + artifact_id = await ArtifactStore(get_db_engine()).register_file_artifact( + artifact_id=None, + host_path=host_path, + host_root=host_root, + artifact_type='file', + source='tool', + mime_type=mime_type, + name=os.path.basename(host_path), + size_bytes=size_bytes, + conversation_id=authorization.get('conversation_id'), + run_id=run_session.get('run_id') if isinstance(run_session, dict) else None, + runner_id=run_session.get('runner_id') if isinstance(run_session, dict) else None, + bot_id=getattr(query, 'bot_uuid', None), + workspace_id=authorization.get('workspace_id'), + thread_id=authorization.get('thread_id'), + metadata=metadata, + ) + artifact_ref = { + 'artifact_id': artifact_id, + 'artifact_type': 'file', + 'mime_type': mime_type, + 'name': os.path.basename(host_path), + 'size_bytes': size_bytes, + } + enriched = dict(result) + enriched['preview'] = str(result.get('content') or '') + enriched['artifact_refs'] = [artifact_ref] + return enriched + except Exception as exc: + self.ap.logger.warning(f'Failed to register read artifact for {sandbox_path}: {exc}') + return result + + @staticmethod + def _get_agent_run_session(query: pipeline_query.Query) -> dict | None: + session = getattr(query, '_agent_run_session', None) + return session if isinstance(session, dict) else None + + def _normalize_exec_result(self, result: dict) -> dict: + normalized = dict(result) + stdout = str(normalized.get('stdout') or '') + stderr = str(normalized.get('stderr') or '') + stdout, stdout_capped = self._truncate_text_to_bytes_with_flag(stdout, _DEFAULT_TOOL_RESULT_MAX_BYTES) + stderr, stderr_capped = self._truncate_text_to_bytes_with_flag(stderr, _DEFAULT_TOOL_RESULT_MAX_BYTES) + normalized['stdout'] = stdout + normalized['stderr'] = stderr + normalized['stdout_truncated'] = bool(normalized.get('stdout_truncated') or stdout_capped) + normalized['stderr_truncated'] = bool(normalized.get('stderr_truncated') or stderr_capped) + + if stdout and stderr: + preview_raw = f'stdout:\n{stdout}\n\nstderr:\n{stderr}' + else: + preview_raw = stdout or stderr + preview, preview_capped = self._truncate_text_to_bytes_with_flag(preview_raw, _DEFAULT_TOOL_RESULT_MAX_BYTES) + normalized['preview'] = preview + normalized['truncated'] = bool( + normalized['stdout_truncated'] or normalized['stderr_truncated'] or preview_capped + ) + if preview_capped and not normalized.get('truncated_by'): + normalized['truncated_by'] = 'bytes' + return normalized + + def _build_directory_result(self, entries: list[str]) -> dict: + sorted_entries = sorted(str(entry) for entry in entries) + content = '\n'.join(sorted_entries) + preview = self._truncate_text_to_bytes(content, _DEFAULT_TOOL_RESULT_MAX_BYTES) + truncated = preview != content + return { + 'ok': True, + 'content': preview, + 'is_directory': True, + 'total': len(sorted_entries), + 'truncated': truncated, + 'truncated_by': 'bytes' if truncated else None, + } + + def _read_text_file_preview(self, host_path: str, parameters: dict) -> dict: + offset = self._positive_int(parameters.get('offset'), default=1) + max_lines = self._positive_int( + parameters.get('limit'), + default=_DEFAULT_READ_MAX_LINES, + max_value=_MAX_READ_MAX_LINES, + ) + max_bytes = self._positive_int( + parameters.get('max_bytes'), + default=_DEFAULT_TOOL_RESULT_MAX_BYTES, + max_value=_DEFAULT_TOOL_RESULT_MAX_BYTES, + ) + lines: list[str] = [] + output_bytes = 0 + end_line = offset - 1 + truncated = False + truncated_by: str | None = None + next_offset: int | None = None + + with open(host_path, 'r', encoding='utf-8', errors='replace') as f: + for line_number, line in enumerate(f, 1): + if line_number < offset: + continue + if len(lines) >= max_lines: + truncated = True + truncated_by = 'lines' + next_offset = line_number + break + + line_bytes = len(line.encode('utf-8')) + if output_bytes + line_bytes > max_bytes: + truncated = True + truncated_by = 'bytes' + next_offset = line_number + break + + lines.append(line.rstrip('\n')) + output_bytes += line_bytes + end_line = line_number + + if not lines and truncated_by == 'bytes': + content = ( + f'[Line {next_offset or offset} exceeds the {self._format_size(max_bytes)} read limit. ' + 'Use exec with a byte-range command for this line, or read a different offset.]' + ) + else: + content = '\n'.join(lines) + + return { + 'ok': True, + 'content': content, + 'truncated': truncated, + 'truncated_by': truncated_by, + 'start_line': offset, + 'end_line': end_line, + 'next_offset': next_offset, + 'max_lines': max_lines, + 'max_bytes': max_bytes, + } + + def _build_read_result_from_text(self, content: str, parameters: dict) -> dict: + offset = self._positive_int(parameters.get('offset'), default=1) + max_lines = self._positive_int( + parameters.get('limit'), + default=_DEFAULT_READ_MAX_LINES, + max_value=_MAX_READ_MAX_LINES, + ) + max_bytes = self._positive_int( + parameters.get('max_bytes'), + default=_DEFAULT_TOOL_RESULT_MAX_BYTES, + max_value=_DEFAULT_TOOL_RESULT_MAX_BYTES, + ) + all_lines = content.splitlines() + start_index = offset - 1 + if start_index >= len(all_lines) and all_lines: + return {'ok': False, 'error': f'Offset {offset} is beyond end of file ({len(all_lines)} lines total)'} + output_lines: list[str] = [] + output_bytes = 0 + truncated = False + truncated_by: str | None = None + next_offset: int | None = None + for index, line in enumerate(all_lines[start_index:], start_index + 1): + if len(output_lines) >= max_lines: + truncated = True + truncated_by = 'lines' + next_offset = index + break + line_bytes = len(line.encode('utf-8')) + (1 if output_lines else 0) + if output_bytes + line_bytes > max_bytes: + truncated = True + truncated_by = 'bytes' + next_offset = index + break + output_lines.append(line) + output_bytes += line_bytes + + end_line = offset + len(output_lines) - 1 + return { + 'ok': True, + 'content': '\n'.join(output_lines), + 'truncated': truncated, + 'truncated_by': truncated_by, + 'start_line': offset, + 'end_line': end_line, + 'next_offset': next_offset, + 'max_lines': max_lines, + 'max_bytes': max_bytes, + } + + @staticmethod + def _positive_int(value, *, default: int, max_value: int | None = None) -> int: + try: + parsed = int(value) + except (TypeError, ValueError): + parsed = default + if parsed <= 0: + parsed = default + if max_value is not None: + parsed = min(parsed, max_value) + return parsed + + @staticmethod + def _truncate_grep_line(line: str) -> tuple[str, bool]: + if len(line) <= _GREP_MAX_LINE_CHARS: + return line, False + return f'{line[:_GREP_MAX_LINE_CHARS]}... [truncated]', True + + @staticmethod + def _truncate_text_to_bytes(text: str, max_bytes: int) -> str: + return NativeToolLoader._truncate_text_to_bytes_with_flag(text, max_bytes)[0] + + @staticmethod + def _truncate_text_to_bytes_with_flag(text: str, max_bytes: int) -> tuple[str, bool]: + data = text.encode('utf-8') + if len(data) <= max_bytes: + return text, False + truncated = data[:max_bytes] + while truncated and (truncated[-1] & 0xC0) == 0x80: + truncated = truncated[:-1] + return truncated.decode('utf-8', errors='ignore'), True + + @staticmethod + def _format_size(bytes_count: int) -> str: + if bytes_count < 1024: + return f'{bytes_count}B' + return f'{bytes_count / 1024:.1f}KB' + def _summarize_parameters(self, parameters: dict) -> dict: summary = dict(parameters) cmd = str(summary.get('command', '')).strip() diff --git a/src/langbot/pkg/provider/tools/loaders/skill.py b/src/langbot/pkg/provider/tools/loaders/skill.py index 9df94fd2..fbfd72b3 100644 --- a/src/langbot/pkg/provider/tools/loaders/skill.py +++ b/src/langbot/pkg/provider/tools/loaders/skill.py @@ -10,6 +10,7 @@ if typing.TYPE_CHECKING: from langbot_plugin.api.entities.events import pipeline_query ACTIVATED_SKILLS_KEY = '_activated_skills' +ACTIVATED_SKILL_NAMES_STATE_KEY = 'host.activated_skills' PIPELINE_BOUND_SKILLS_KEY = '_pipeline_bound_skills' SKILL_MOUNT_PREFIX = '/workspace/.skills' _SKILL_MOUNT_PATTERN = re.compile(r'/workspace/\.skills/([A-Za-z0-9_-]+)') @@ -72,6 +73,116 @@ def register_activated_skill(query: pipeline_query.Query, skill_data: dict) -> N activated[skill_name] = skill_data +def _normalize_skill_names(value: typing.Any) -> list[str]: + if not isinstance(value, list): + return [] + + names: list[str] = [] + for item in value: + skill_name = str(item or '').strip() + if skill_name and skill_name not in names: + names.append(skill_name) + return names + + +def restore_activated_skills_from_state( + ap: app.Application, + query: pipeline_query.Query, + state: dict[str, dict[str, typing.Any]], +) -> list[str]: + """Restore persisted activated skill names into Query variables. + + The state value stores names only. Full skill metadata is rebuilt from the + current pipeline-visible skill cache so removed or unbound skills remain + unavailable to native exec/write/edit. + """ + conversation_state = state.get('conversation', {}) if isinstance(state, dict) else {} + skill_names = _normalize_skill_names(conversation_state.get(ACTIVATED_SKILL_NAMES_STATE_KEY)) + restored: list[str] = [] + for skill_name in skill_names: + skill_data = get_visible_skill(ap, query, skill_name) + if skill_data is None: + continue + register_activated_skill(query, skill_data) + restored.append(skill_name) + return restored + + +def _get_agent_run_authorization(query: pipeline_query.Query) -> dict[str, typing.Any] | None: + session = getattr(query, '_agent_run_session', None) + if not isinstance(session, dict): + return None + authorization = session.get('authorization') + return authorization if isinstance(authorization, dict) else None + + +def _get_conversation_state_target(query: pipeline_query.Query) -> tuple[str, str, str, dict[str, typing.Any]] | None: + session = getattr(query, '_agent_run_session', None) + if not isinstance(session, dict): + return None + + authorization = _get_agent_run_authorization(query) + if authorization is None: + return None + + state_policy = authorization.get('state_policy') or {} + if not state_policy.get('enable_state', True): + return None + state_scopes = state_policy.get('state_scopes', ['conversation', 'actor']) + if 'conversation' not in state_scopes: + return None + + state_context = authorization.get('state_context') or {} + scope_keys = state_context.get('scope_keys') or {} + scope_key = scope_keys.get('conversation') + if not scope_key: + return None + + runner_id = str(session.get('runner_id') or 'unknown') + binding_identity = str(state_context.get('binding_identity') or 'unknown') + return scope_key, runner_id, binding_identity, state_context + + +async def persist_activated_skill(ap: app.Application, query: pipeline_query.Query, skill_name: str) -> bool: + """Persist activated skill names for the current AgentRunner conversation. + + Returns False when the call is outside an AgentRunner run or state policy + does not expose a conversation scope. The in-memory Query activation still + remains valid for the current turn. + """ + target = _get_conversation_state_target(query) + if target is None: + return False + + persistence_mgr = getattr(ap, 'persistence_mgr', None) + if persistence_mgr is None or not hasattr(persistence_mgr, 'get_db_engine'): + return False + + from ....agent.runner.persistent_state_store import get_persistent_state_store + + scope_key, runner_id, binding_identity, state_context = target + store = get_persistent_state_store(persistence_mgr.get_db_engine()) + existing_names = _normalize_skill_names(await store.state_get(scope_key, ACTIVATED_SKILL_NAMES_STATE_KEY)) + if skill_name not in existing_names: + existing_names.append(skill_name) + + success, error = await store.state_set( + scope_key=scope_key, + state_key=ACTIVATED_SKILL_NAMES_STATE_KEY, + value=existing_names, + runner_id=runner_id, + binding_identity=binding_identity, + scope='conversation', + context=state_context, + logger=getattr(ap, 'logger', None), + ) + if not success: + logger = getattr(ap, 'logger', None) + if logger is not None: + logger.warning(f'Failed to persist activated skill "{skill_name}": {error}') + return success + + def parse_skill_mount_path(sandbox_path: str) -> tuple[str | None, str]: normalized_path = str(sandbox_path or '/workspace').strip() or '/workspace' if normalized_path == SKILL_MOUNT_PREFIX: diff --git a/src/langbot/pkg/provider/tools/loaders/skill_authoring.py b/src/langbot/pkg/provider/tools/loaders/skill_authoring.py index 9d0fe6e9..cde4314b 100644 --- a/src/langbot/pkg/provider/tools/loaders/skill_authoring.py +++ b/src/langbot/pkg/provider/tools/loaders/skill_authoring.py @@ -6,6 +6,7 @@ import typing import langbot_plugin.api.entities.builtin.resource.tool as resource_tool from .. import loader +from .availability import is_box_backend_available # Align with Claude Code's Skill tool design: # - activate: Activate a skill via Tool Call, returns SKILL.md content @@ -45,18 +46,7 @@ class SkillToolLoader(loader.ToolLoader): async def _check_sandbox_available(self) -> bool: """Check if the box backend is truly available (not just the runtime).""" - box_service = getattr(self.ap, 'box_service', None) - if box_service is None: - return False - if not getattr(box_service, 'available', False): - return False - # Check if backend is truly available via get_status - try: - status = await box_service.get_status() - backend_info = status.get('backend', {}) - return backend_info.get('available', False) - except Exception: - return False + return await is_box_backend_available(self.ap) async def get_tools(self, bound_plugins: list[str] | None = None) -> list[resource_tool.LLMTool]: if not self._is_available(): @@ -92,17 +82,17 @@ class SkillToolLoader(loader.ToolLoader): if not skill_name: raise ValueError('skill_name is required') - skill_mgr = self.ap.skill_mgr - skill_data = skill_mgr.get_skill_by_name(skill_name) + from . import skill as skill_loader + + skill_data = skill_loader.get_visible_skill(self.ap, query, skill_name) if skill_data is None: - visible_skills = getattr(skill_mgr, 'skills', {}) + visible_skills = skill_loader.get_visible_skills(self.ap, query) available_names = ', '.join(sorted(visible_skills.keys())) or 'none' raise ValueError(f'Skill "{skill_name}" not found. Available skills: {available_names}') # Register activated skill for sandbox mount path resolution - from . import skill as skill_loader - skill_loader.register_activated_skill(query, skill_data) + await skill_loader.persist_activated_skill(self.ap, query, skill_name) # Return SKILL.md content as Tool Result (injects into context) instructions = skill_data.get('instructions', '') @@ -201,13 +191,13 @@ class SkillToolLoader(loader.ToolLoader): return resource_tool.LLMTool( name=ACTIVATE_SKILL_TOOL_NAME, human_desc='Activate a skill', - description=self._build_activate_tool_description(), + description='Activate a pipeline-visible skill by name and return its instructions as a tool result.', parameters={ 'type': 'object', 'properties': { 'skill_name': { 'type': 'string', - 'description': 'The skill name to activate (no arguments). E.g., "pdf" or "data-analysis"', + 'description': 'The skill name to activate.', }, }, 'required': ['skill_name'], @@ -255,50 +245,3 @@ class SkillToolLoader(loader.ToolLoader): }, func=lambda parameters: parameters, ) - - def _build_activate_tool_description(self) -> str: - """Build tool description with embedded available_skills list.""" - skill_mgr = getattr(self.ap, 'skill_mgr', None) - if skill_mgr is None: - return 'Activate a skill. No skills are currently available.' - - skills = getattr(skill_mgr, 'skills', {}) - if not skills: - return 'Activate a skill. No skills are currently available.' - - # Build section - available_skills_lines = [''] - for skill_name, skill_data in sorted(skills.items()): - description = skill_data.get('description', '') - available_skills_lines.append('') - available_skills_lines.append(f'{skill_name}') - available_skills_lines.append(f'{description}') - available_skills_lines.append('') - available_skills_lines.append('') - - available_skills_block = '\n'.join(available_skills_lines) - - return f"""Activate a skill within the main conversation. - - -When users ask you to perform tasks, check if any of the available skills -below can help complete the task more effectively. Skills provide specialized -capabilities and domain knowledge. - -How to use skills: -- Invoke skills using this tool with the skill name only (no arguments) -- When you invoke a skill, you will see -The skill is activated - -- The skill's instructions will be provided in the tool result -- Examples: - - skill_name: "pdf" - invoke the pdf skill - - skill_name: "data-analysis" - invoke the data-analysis skill - -Important: -- Only use skills listed in below -- Do not invoke a skill that is already running -- To create a new skill: prepare it in /workspace, then use register_skill tool - - -{available_skills_block}""" diff --git a/tests/unit_tests/provider/test_mcp_box_integration.py b/tests/unit_tests/provider/test_mcp_box_integration.py index 3e3a7a4d..db1aa542 100644 --- a/tests/unit_tests/provider/test_mcp_box_integration.py +++ b/tests/unit_tests/provider/test_mcp_box_integration.py @@ -180,7 +180,7 @@ class TestMCPServerBoxConfig: assert cfg.host_path is None assert cfg.host_path_mode == 'ro' assert cfg.env == {} - assert cfg.startup_timeout_sec == 120 + assert cfg.startup_timeout_sec == 300 assert cfg.cpus is None assert cfg.memory_mb is None assert cfg.pids_limit is None @@ -494,6 +494,52 @@ class TestBuildBoxProcessPayload: assert payload['args'] == ['/opt/other/server.py', '--flag'] +# ── Python Workspace Preparation ──────────────────────────────────── + + +class TestPythonWorkspacePreparation: + def test_requirements_workspace_uses_venv_bootstrap(self, mcp_module, tmp_path): + host_path = tmp_path / 'mcp-source' + host_path.mkdir() + (host_path / 'requirements.txt').write_text('mcp==1.26.0\n', encoding='utf-8') + + command = mcp_module.BoxStdioSessionRuntime.detect_install_command( + str(host_path), + '/workspace/.mcp/u1/workspace', + ) + + assert command is not None + assert 'python -m venv "$_LB_VENV_DIR"' in command + assert 'python -m pip install -r "/workspace/.mcp/u1/workspace/requirements.txt"' in command + assert 'pip install --no-cache-dir -r' not in command + + def test_staging_refresh_removes_stale_source_files_but_preserves_runtime_dirs(self, mcp_module, tmp_path): + source = tmp_path / 'source' + source.mkdir() + (source / 'server.py').write_text('print("new")\n', encoding='utf-8') + (source / 'requirements.txt').write_text('mcp==1.26.0\n', encoding='utf-8') + + process_root = tmp_path / 'shared' / '.mcp' / 'u1' + workspace = process_root / 'workspace' + (workspace / '.venv' / 'bin').mkdir(parents=True) + (workspace / '.venv' / 'bin' / 'python').write_text('', encoding='utf-8') + (workspace / '.langbot').mkdir() + (workspace / '.langbot' / 'python-env.lock').mkdir() + (workspace / 'server.py').write_text('print("old")\n', encoding='utf-8') + (workspace / 'removed.py').write_text('stale\n', encoding='utf-8') + (workspace / 'removed_dir').mkdir() + (workspace / 'removed_dir' / 'old.txt').write_text('stale\n', encoding='utf-8') + + mcp_module.BoxStdioSessionRuntime._copy_workspace_tree(str(source), str(process_root), str(workspace)) + + assert (workspace / 'server.py').read_text(encoding='utf-8') == 'print("new")\n' + assert (workspace / 'requirements.txt').read_text(encoding='utf-8') == 'mcp==1.26.0\n' + assert not (workspace / 'removed.py').exists() + assert not (workspace / 'removed_dir').exists() + assert (workspace / '.venv' / 'bin' / 'python').exists() + assert (workspace / '.langbot' / 'python-env.lock').is_dir() + + # ── get_runtime_info_dict ─────────────────────────────────────────── diff --git a/tests/unit_tests/provider/test_skill_tools.py b/tests/unit_tests/provider/test_skill_tools.py index 847480c1..96316ee5 100644 --- a/tests/unit_tests/provider/test_skill_tools.py +++ b/tests/unit_tests/provider/test_skill_tools.py @@ -456,7 +456,9 @@ class TestNativeToolLoaderSkillPaths: SimpleNamespace(query_id='q1', variables={PIPELINE_BOUND_SKILLS_KEY: ['demo']}), ) - assert result == {'ok': True, 'content': 'demo instructions'} + assert result['ok'] is True + assert result['content'] == 'demo instructions' + assert result['truncated'] is False @pytest.mark.asyncio async def test_exec_in_activated_skill_mount_rewrites_command_and_refreshes(self): @@ -485,7 +487,7 @@ class TestNativeToolLoaderSkillPaths: query, ) - assert result == {'ok': True} + assert result['ok'] is True tool_parameters = ap.box_service.execute_tool.await_args.args[0] assert tool_parameters['command'] == 'python /workspace/.skills/demo/scripts/run.py' assert tool_parameters['workdir'] == '/workspace/.skills/demo' From 7b67dcc302b62cb5329719903566d6ff03496282 Mon Sep 17 00:00:00 2001 From: huanghuoguoguo <60681390+huanghuoguoguo@users.noreply.github.com> Date: Sun, 14 Jun 2026 11:23:09 +0800 Subject: [PATCH 10/12] fix(tools): bootstrap Python workspaces with available interpreter --- src/langbot/pkg/box/workspace.py | 10 ++++++++-- tests/unit_tests/provider/test_mcp_box_integration.py | 3 ++- tests/unit_tests/provider/test_skill_tools.py | 3 ++- 3 files changed, 12 insertions(+), 4 deletions(-) diff --git a/src/langbot/pkg/box/workspace.py b/src/langbot/pkg/box/workspace.py index 948622ef..06df6b22 100644 --- a/src/langbot/pkg/box/workspace.py +++ b/src/langbot/pkg/box/workspace.py @@ -151,8 +151,14 @@ def wrap_python_command_with_env(command: str, *, mount_path: str = '/workspace' export TMP="$_LB_TMP_DIR" export PIP_CACHE_DIR="$_LB_PIP_CACHE_DIR" + _LB_SYSTEM_PYTHON="$(command -v python3 || command -v python || true)" + if [ -z "$_LB_SYSTEM_PYTHON" ]; then + echo "No Python interpreter found for workspace bootstrap" >&2 + exit 1 + fi + _lb_python_meta() {{ - python - <<'PY' + "$_LB_SYSTEM_PYTHON" - <<'PY' import hashlib import json import os @@ -225,7 +231,7 @@ def wrap_python_command_with_env(command: str, *, mount_path: str = '/workspace' if [ "$_LB_NEEDS_BOOTSTRAP" -eq 1 ]; then rm -rf "$_LB_VENV_DIR" - python -m venv "$_LB_VENV_DIR" + "$_LB_SYSTEM_PYTHON" -m venv "$_LB_VENV_DIR" . "$_LB_VENV_DIR/bin/activate" python -m pip install --upgrade pip setuptools wheel if [ -f "{mount_path}/requirements.txt" ]; then diff --git a/tests/unit_tests/provider/test_mcp_box_integration.py b/tests/unit_tests/provider/test_mcp_box_integration.py index db1aa542..c7e080c0 100644 --- a/tests/unit_tests/provider/test_mcp_box_integration.py +++ b/tests/unit_tests/provider/test_mcp_box_integration.py @@ -509,7 +509,8 @@ class TestPythonWorkspacePreparation: ) assert command is not None - assert 'python -m venv "$_LB_VENV_DIR"' in command + assert '_LB_SYSTEM_PYTHON="$(command -v python3 || command -v python || true)"' in command + assert '"$_LB_SYSTEM_PYTHON" -m venv "$_LB_VENV_DIR"' in command assert 'python -m pip install -r "/workspace/.mcp/u1/workspace/requirements.txt"' in command assert 'pip install --no-cache-dir -r' not in command diff --git a/tests/unit_tests/provider/test_skill_tools.py b/tests/unit_tests/provider/test_skill_tools.py index 96316ee5..7a9cde66 100644 --- a/tests/unit_tests/provider/test_skill_tools.py +++ b/tests/unit_tests/provider/test_skill_tools.py @@ -245,7 +245,8 @@ class TestSkillPathHelpers: command = wrap_skill_command_with_python_env('python scripts/run.py') - assert 'python -m venv "$_LB_VENV_DIR"' in command + assert '_LB_SYSTEM_PYTHON="$(command -v python3 || command -v python || true)"' in command + assert '"$_LB_SYSTEM_PYTHON" -m venv "$_LB_VENV_DIR"' in command assert 'export VIRTUAL_ENV="$_LB_VENV_DIR"' in command assert command.rstrip().endswith('python scripts/run.py') From 64b7e9c509a6aa7981fe0421c096163345721b5c Mon Sep 17 00:00:00 2001 From: huanghuoguoguo <60681390+huanghuoguoguo@users.noreply.github.com> Date: Sun, 14 Jun 2026 11:25:09 +0800 Subject: [PATCH 11/12] fix(tools): clear stale Python workspace env locks --- src/langbot/pkg/box/workspace.py | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/src/langbot/pkg/box/workspace.py b/src/langbot/pkg/box/workspace.py index 06df6b22..41fca039 100644 --- a/src/langbot/pkg/box/workspace.py +++ b/src/langbot/pkg/box/workspace.py @@ -146,17 +146,17 @@ def wrap_python_command_with_env(command: str, *, mount_path: str = '/workspace' _LB_PIP_CACHE_DIR="{mount_path}/.cache/pip" mkdir -p "$_LB_META_DIR" "$_LB_TMP_DIR" "$_LB_PIP_CACHE_DIR" + _LB_SYSTEM_PYTHON="$(command -v python3 || command -v python || true)" + if [ -z "$_LB_SYSTEM_PYTHON" ]; then + echo "python3 or python is required to prepare the workspace Python environment" >&2 + exit 127 + fi + export TMPDIR="$_LB_TMP_DIR" export TEMP="$_LB_TMP_DIR" export TMP="$_LB_TMP_DIR" export PIP_CACHE_DIR="$_LB_PIP_CACHE_DIR" - _LB_SYSTEM_PYTHON="$(command -v python3 || command -v python || true)" - if [ -z "$_LB_SYSTEM_PYTHON" ]; then - echo "No Python interpreter found for workspace bootstrap" >&2 - exit 1 - fi - _lb_python_meta() {{ "$_LB_SYSTEM_PYTHON" - <<'PY' import hashlib @@ -204,18 +204,29 @@ def wrap_python_command_with_env(command: str, *, mount_path: str = '/workspace' fi if [ "$_LB_NEEDS_BOOTSTRAP" -eq 1 ]; then + if [ -d "$_LB_LOCK_DIR" ] && [ ! -f "$_LB_LOCK_DIR/pid" ]; then + echo "Clearing stale Python environment lock without owner: $_LB_LOCK_DIR" >&2 + rm -rf "$_LB_LOCK_DIR" 2>/dev/null || true + fi + _LB_LOCK_WAIT=0 while ! mkdir "$_LB_LOCK_DIR" 2>/dev/null; do if [ "$_LB_LOCK_WAIT" -ge 120 ]; then + echo "Timed out waiting for Python environment lock, clearing stale lock: $_LB_LOCK_DIR" >&2 + rm -rf "$_LB_LOCK_DIR" 2>/dev/null || true + if mkdir "$_LB_LOCK_DIR" 2>/dev/null; then + break + fi echo "Timed out waiting for Python environment lock: $_LB_LOCK_DIR" >&2 exit 1 fi sleep 1 _LB_LOCK_WAIT=$((_LB_LOCK_WAIT + 1)) done + printf '%s\\n' "$$" > "$_LB_LOCK_DIR/pid" 2>/dev/null || true _lb_cleanup_lock() {{ - rmdir "$_LB_LOCK_DIR" >/dev/null 2>&1 || true + rm -rf "$_LB_LOCK_DIR" >/dev/null 2>&1 || true }} trap _lb_cleanup_lock EXIT INT TERM From 9fa3251f3d3a58067753fd9ed34b8152d2e722bd Mon Sep 17 00:00:00 2001 From: huanghuoguoguo <60681390+huanghuoguoguo@users.noreply.github.com> Date: Sun, 14 Jun 2026 21:15:21 +0800 Subject: [PATCH 12/12] fix(tools): decouple runtime from agent runner --- src/langbot/pkg/box/workspace.py | 10 +- .../pkg/provider/tools/loaders/mcp_stdio.py | 14 +-- .../pkg/provider/tools/loaders/native.py | 90 +--------------- .../pkg/provider/tools/loaders/skill.py | 100 +++--------------- .../provider/tools/loaders/skill_authoring.py | 2 +- tests/unit_tests/box/test_workspace.py | 4 +- .../provider/test_mcp_box_integration.py | 3 + tests/unit_tests/provider/test_skill_tools.py | 24 +++++ 8 files changed, 57 insertions(+), 190 deletions(-) diff --git a/src/langbot/pkg/box/workspace.py b/src/langbot/pkg/box/workspace.py index 41fca039..26d1a41e 100644 --- a/src/langbot/pkg/box/workspace.py +++ b/src/langbot/pkg/box/workspace.py @@ -204,14 +204,14 @@ def wrap_python_command_with_env(command: str, *, mount_path: str = '/workspace' fi if [ "$_LB_NEEDS_BOOTSTRAP" -eq 1 ]; then - if [ -d "$_LB_LOCK_DIR" ] && [ ! -f "$_LB_LOCK_DIR/pid" ]; then - echo "Clearing stale Python environment lock without owner: $_LB_LOCK_DIR" >&2 - rm -rf "$_LB_LOCK_DIR" 2>/dev/null || true - fi - _LB_LOCK_WAIT=0 while ! mkdir "$_LB_LOCK_DIR" 2>/dev/null; do if [ "$_LB_LOCK_WAIT" -ge 120 ]; then + _LB_LOCK_OWNER="$(cat "$_LB_LOCK_DIR/pid" 2>/dev/null || true)" + if [ -n "$_LB_LOCK_OWNER" ] && kill -0 "$_LB_LOCK_OWNER" 2>/dev/null; then + echo "Timed out waiting for active Python environment lock: $_LB_LOCK_DIR" >&2 + exit 1 + fi echo "Timed out waiting for Python environment lock, clearing stale lock: $_LB_LOCK_DIR" >&2 rm -rf "$_LB_LOCK_DIR" 2>/dev/null || true if mkdir "$_LB_LOCK_DIR" 2>/dev/null; then diff --git a/src/langbot/pkg/provider/tools/loaders/mcp_stdio.py b/src/langbot/pkg/provider/tools/loaders/mcp_stdio.py index 736dacea..b74b077b 100644 --- a/src/langbot/pkg/provider/tools/loaders/mcp_stdio.py +++ b/src/langbot/pkg/provider/tools/loaders/mcp_stdio.py @@ -276,7 +276,7 @@ class BoxStdioSessionRuntime: # to delete them, so refresh source files in place and preserve runtime # directories instead of rmtree'ing the whole staging root. with _workspace_copy_lock(process_host_root): - preserved_names = {'.venv', 'venv', 'env', '.env', '.cache', '.tmp', '.langbot'} + preserved_names = {'.venv', 'venv', 'env', '.cache', '.tmp', '.langbot'} os.makedirs(process_host_workspace, exist_ok=True) for name in os.listdir(process_host_workspace): if name in preserved_names: @@ -288,6 +288,7 @@ class BoxStdioSessionRuntime: try: os.unlink(path) except FileNotFoundError: + # The entry may disappear between listdir and unlink if cleanup races us. pass shutil.copytree( source_path, @@ -303,7 +304,6 @@ class BoxStdioSessionRuntime: '.venv', 'venv', 'env', - '.env', '.cache', '.tmp', '.langbot', @@ -401,18 +401,12 @@ class BoxStdioSessionRuntime: workspace_root = workspace_path.rstrip('/') or '/workspace' venv_dir = f'{workspace_root}/.venv' venv_bin = f'{venv_dir}/bin' - command = ' '.join( - [shlex.quote(payload['command']), *[shlex.quote(arg) for arg in payload.get('args', [])]] - ) + command = ' '.join([shlex.quote(payload['command']), *[shlex.quote(arg) for arg in payload.get('args', [])]]) wrapped = dict(payload) wrapped['command'] = 'sh' wrapped['args'] = [ '-lc', - ( - f'export VIRTUAL_ENV={shlex.quote(venv_dir)}; ' - f'export PATH={shlex.quote(venv_bin)}:$PATH; ' - f'exec {command}' - ), + (f'export VIRTUAL_ENV={shlex.quote(venv_dir)}; export PATH={shlex.quote(venv_bin)}:$PATH; exec {command}'), ] return wrapped diff --git a/src/langbot/pkg/provider/tools/loaders/native.py b/src/langbot/pkg/provider/tools/loaders/native.py index bf9f357f..f10335e6 100644 --- a/src/langbot/pkg/provider/tools/loaders/native.py +++ b/src/langbot/pkg/provider/tools/loaders/native.py @@ -1,7 +1,6 @@ from __future__ import annotations import json -import mimetypes import os import langbot_plugin.api.entities.builtin.resource.tool as resource_tool @@ -478,9 +477,7 @@ else: if host_path and os.path.exists(host_path): if os.path.isdir(host_path): return self._build_directory_result(os.listdir(host_path)) - result = self._read_text_file_preview(host_path, parameters) - host_root = str(selected_skill.get('package_root', '') or '') - return await self._attach_file_artifact_ref(result, host_path, host_root, path, query) + return self._read_text_file_preview(host_path, parameters) try: result = await self.ap.box_service.read_skill_file(selected_skill['name'], relative) @@ -506,9 +503,7 @@ else: if os.path.isdir(host_path): entries = os.listdir(host_path) return self._build_directory_result(entries) - result = self._read_text_file_preview(host_path, parameters) - host_root = self._get_host_root(selected_skill) - return await self._attach_file_artifact_ref(result, host_path, host_root, path, query) + return self._read_text_file_preview(host_path, parameters) async def _invoke_write(self, parameters: dict, query: pipeline_query.Query) -> dict: path = parameters['path'] @@ -695,8 +690,7 @@ else: 'max_bytes': { 'type': 'integer', 'description': ( - 'Maximum bytes of file content to return. ' - f'Defaults to {_DEFAULT_TOOL_RESULT_MAX_BYTES}.' + f'Maximum bytes of file content to return. Defaults to {_DEFAULT_TOOL_RESULT_MAX_BYTES}.' ), 'default': _DEFAULT_TOOL_RESULT_MAX_BYTES, 'minimum': 1, @@ -984,84 +978,6 @@ else: raise ValueError('Path escapes the skill package boundary.') return host_path - def _get_host_root(self, selected_skill: dict | None) -> str: - if selected_skill is not None: - return str(selected_skill.get('package_root', '') or '') - return str(getattr(self.ap.box_service, 'default_workspace', '') or '') - - async def _attach_file_artifact_ref( - self, - result: dict, - host_path: str, - host_root: str, - sandbox_path: str, - query: pipeline_query.Query, - ) -> dict: - if not result.get('ok') or not result.get('truncated') or result.get('artifact_refs'): - return result - if not host_root or not os.path.isfile(host_path): - return result - - run_session = self._get_agent_run_session(query) - if not run_session: - return result - - persistence_mgr = getattr(self.ap, 'persistence_mgr', None) - get_db_engine = getattr(persistence_mgr, 'get_db_engine', None) - if not callable(get_db_engine): - return result - - try: - from langbot.pkg.agent.runner.artifact_store import ArtifactStore - - authorization = run_session.get('authorization', {}) if isinstance(run_session, dict) else {} - mime_type = mimetypes.guess_type(host_path)[0] or 'text/plain' - size_bytes = os.path.getsize(host_path) - metadata = { - 'tool_name': READ_TOOL_NAME, - 'sandbox_path': sandbox_path, - 'truncated_by': result.get('truncated_by'), - 'start_line': result.get('start_line'), - 'end_line': result.get('end_line'), - 'next_offset': result.get('next_offset'), - } - artifact_id = await ArtifactStore(get_db_engine()).register_file_artifact( - artifact_id=None, - host_path=host_path, - host_root=host_root, - artifact_type='file', - source='tool', - mime_type=mime_type, - name=os.path.basename(host_path), - size_bytes=size_bytes, - conversation_id=authorization.get('conversation_id'), - run_id=run_session.get('run_id') if isinstance(run_session, dict) else None, - runner_id=run_session.get('runner_id') if isinstance(run_session, dict) else None, - bot_id=getattr(query, 'bot_uuid', None), - workspace_id=authorization.get('workspace_id'), - thread_id=authorization.get('thread_id'), - metadata=metadata, - ) - artifact_ref = { - 'artifact_id': artifact_id, - 'artifact_type': 'file', - 'mime_type': mime_type, - 'name': os.path.basename(host_path), - 'size_bytes': size_bytes, - } - enriched = dict(result) - enriched['preview'] = str(result.get('content') or '') - enriched['artifact_refs'] = [artifact_ref] - return enriched - except Exception as exc: - self.ap.logger.warning(f'Failed to register read artifact for {sandbox_path}: {exc}') - return result - - @staticmethod - def _get_agent_run_session(query: pipeline_query.Query) -> dict | None: - session = getattr(query, '_agent_run_session', None) - return session if isinstance(session, dict) else None - def _normalize_exec_result(self, result: dict) -> dict: normalized = dict(result) stdout = str(normalized.get('stdout') or '') diff --git a/src/langbot/pkg/provider/tools/loaders/skill.py b/src/langbot/pkg/provider/tools/loaders/skill.py index fbfd72b3..b62f3e7d 100644 --- a/src/langbot/pkg/provider/tools/loaders/skill.py +++ b/src/langbot/pkg/provider/tools/loaders/skill.py @@ -10,7 +10,6 @@ if typing.TYPE_CHECKING: from langbot_plugin.api.entities.events import pipeline_query ACTIVATED_SKILLS_KEY = '_activated_skills' -ACTIVATED_SKILL_NAMES_STATE_KEY = 'host.activated_skills' PIPELINE_BOUND_SKILLS_KEY = '_pipeline_bound_skills' SKILL_MOUNT_PREFIX = '/workspace/.skills' _SKILL_MOUNT_PATTERN = re.compile(r'/workspace/\.skills/([A-Za-z0-9_-]+)') @@ -73,7 +72,8 @@ def register_activated_skill(query: pipeline_query.Query, skill_data: dict) -> N activated[skill_name] = skill_data -def _normalize_skill_names(value: typing.Any) -> list[str]: +def normalize_skill_names(value: typing.Any) -> list[str]: + """Return a de-duplicated list of non-empty skill names.""" if not isinstance(value, list): return [] @@ -85,21 +85,24 @@ def _normalize_skill_names(value: typing.Any) -> list[str]: return names -def restore_activated_skills_from_state( +def get_activated_skill_names(query: pipeline_query.Query) -> list[str]: + """Return activated skill names for callers that own persistence policy.""" + return normalize_skill_names(list(get_activated_skills(query).keys())) + + +def restore_activated_skills( ap: app.Application, query: pipeline_query.Query, - state: dict[str, dict[str, typing.Any]], + skill_names: typing.Any, ) -> list[str]: - """Restore persisted activated skill names into Query variables. + """Restore caller-provided activated skill names into Query variables. - The state value stores names only. Full skill metadata is rebuilt from the - current pipeline-visible skill cache so removed or unbound skills remain - unavailable to native exec/write/edit. + Persistence and state scope ownership belong to higher-level flows. This + helper only rebuilds current Query state from pipeline-visible skills, so + removed or unbound skills stay unavailable to native exec/write/edit. """ - conversation_state = state.get('conversation', {}) if isinstance(state, dict) else {} - skill_names = _normalize_skill_names(conversation_state.get(ACTIVATED_SKILL_NAMES_STATE_KEY)) restored: list[str] = [] - for skill_name in skill_names: + for skill_name in normalize_skill_names(skill_names): skill_data = get_visible_skill(ap, query, skill_name) if skill_data is None: continue @@ -108,81 +111,6 @@ def restore_activated_skills_from_state( return restored -def _get_agent_run_authorization(query: pipeline_query.Query) -> dict[str, typing.Any] | None: - session = getattr(query, '_agent_run_session', None) - if not isinstance(session, dict): - return None - authorization = session.get('authorization') - return authorization if isinstance(authorization, dict) else None - - -def _get_conversation_state_target(query: pipeline_query.Query) -> tuple[str, str, str, dict[str, typing.Any]] | None: - session = getattr(query, '_agent_run_session', None) - if not isinstance(session, dict): - return None - - authorization = _get_agent_run_authorization(query) - if authorization is None: - return None - - state_policy = authorization.get('state_policy') or {} - if not state_policy.get('enable_state', True): - return None - state_scopes = state_policy.get('state_scopes', ['conversation', 'actor']) - if 'conversation' not in state_scopes: - return None - - state_context = authorization.get('state_context') or {} - scope_keys = state_context.get('scope_keys') or {} - scope_key = scope_keys.get('conversation') - if not scope_key: - return None - - runner_id = str(session.get('runner_id') or 'unknown') - binding_identity = str(state_context.get('binding_identity') or 'unknown') - return scope_key, runner_id, binding_identity, state_context - - -async def persist_activated_skill(ap: app.Application, query: pipeline_query.Query, skill_name: str) -> bool: - """Persist activated skill names for the current AgentRunner conversation. - - Returns False when the call is outside an AgentRunner run or state policy - does not expose a conversation scope. The in-memory Query activation still - remains valid for the current turn. - """ - target = _get_conversation_state_target(query) - if target is None: - return False - - persistence_mgr = getattr(ap, 'persistence_mgr', None) - if persistence_mgr is None or not hasattr(persistence_mgr, 'get_db_engine'): - return False - - from ....agent.runner.persistent_state_store import get_persistent_state_store - - scope_key, runner_id, binding_identity, state_context = target - store = get_persistent_state_store(persistence_mgr.get_db_engine()) - existing_names = _normalize_skill_names(await store.state_get(scope_key, ACTIVATED_SKILL_NAMES_STATE_KEY)) - if skill_name not in existing_names: - existing_names.append(skill_name) - - success, error = await store.state_set( - scope_key=scope_key, - state_key=ACTIVATED_SKILL_NAMES_STATE_KEY, - value=existing_names, - runner_id=runner_id, - binding_identity=binding_identity, - scope='conversation', - context=state_context, - logger=getattr(ap, 'logger', None), - ) - if not success: - logger = getattr(ap, 'logger', None) - if logger is not None: - logger.warning(f'Failed to persist activated skill "{skill_name}": {error}') - return success - - def parse_skill_mount_path(sandbox_path: str) -> tuple[str | None, str]: normalized_path = str(sandbox_path or '/workspace').strip() or '/workspace' if normalized_path == SKILL_MOUNT_PREFIX: diff --git a/src/langbot/pkg/provider/tools/loaders/skill_authoring.py b/src/langbot/pkg/provider/tools/loaders/skill_authoring.py index cde4314b..d5372178 100644 --- a/src/langbot/pkg/provider/tools/loaders/skill_authoring.py +++ b/src/langbot/pkg/provider/tools/loaders/skill_authoring.py @@ -92,7 +92,6 @@ class SkillToolLoader(loader.ToolLoader): # Register activated skill for sandbox mount path resolution skill_loader.register_activated_skill(query, skill_data) - await skill_loader.persist_activated_skill(self.ap, query, skill_name) # Return SKILL.md content as Tool Result (injects into context) instructions = skill_data.get('instructions', '') @@ -117,6 +116,7 @@ class SkillToolLoader(loader.ToolLoader): 'activated': True, 'skill_name': skill_name, 'mount_path': mount_path, + 'activated_skill_names': skill_loader.get_activated_skill_names(query), 'content': result_content, } diff --git a/tests/unit_tests/box/test_workspace.py b/tests/unit_tests/box/test_workspace.py index 809347e5..e4620ad3 100644 --- a/tests/unit_tests/box/test_workspace.py +++ b/tests/unit_tests/box/test_workspace.py @@ -54,7 +54,9 @@ def test_classify_python_workspace_detects_package_and_requirements(): def test_wrap_python_command_with_env_contains_bootstrap_and_command(): command = wrap_python_command_with_env('python script.py') - assert 'python -m venv "$_LB_VENV_DIR"' in command + assert '_LB_SYSTEM_PYTHON="$(command -v python3 || command -v python || true)"' in command + assert '"$_LB_SYSTEM_PYTHON" -m venv "$_LB_VENV_DIR"' in command + assert 'kill -0 "$_LB_LOCK_OWNER"' in command assert 'export VIRTUAL_ENV="$_LB_VENV_DIR"' in command assert command.rstrip().endswith('python script.py') diff --git a/tests/unit_tests/provider/test_mcp_box_integration.py b/tests/unit_tests/provider/test_mcp_box_integration.py index c7e080c0..598f7dce 100644 --- a/tests/unit_tests/provider/test_mcp_box_integration.py +++ b/tests/unit_tests/provider/test_mcp_box_integration.py @@ -519,6 +519,7 @@ class TestPythonWorkspacePreparation: source.mkdir() (source / 'server.py').write_text('print("new")\n', encoding='utf-8') (source / 'requirements.txt').write_text('mcp==1.26.0\n', encoding='utf-8') + (source / '.env').write_text('TOKEN=new\n', encoding='utf-8') process_root = tmp_path / 'shared' / '.mcp' / 'u1' workspace = process_root / 'workspace' @@ -526,6 +527,7 @@ class TestPythonWorkspacePreparation: (workspace / '.venv' / 'bin' / 'python').write_text('', encoding='utf-8') (workspace / '.langbot').mkdir() (workspace / '.langbot' / 'python-env.lock').mkdir() + (workspace / '.env').write_text('TOKEN=old\n', encoding='utf-8') (workspace / 'server.py').write_text('print("old")\n', encoding='utf-8') (workspace / 'removed.py').write_text('stale\n', encoding='utf-8') (workspace / 'removed_dir').mkdir() @@ -535,6 +537,7 @@ class TestPythonWorkspacePreparation: assert (workspace / 'server.py').read_text(encoding='utf-8') == 'print("new")\n' assert (workspace / 'requirements.txt').read_text(encoding='utf-8') == 'mcp==1.26.0\n' + assert (workspace / '.env').read_text(encoding='utf-8') == 'TOKEN=new\n' assert not (workspace / 'removed.py').exists() assert not (workspace / 'removed_dir').exists() assert (workspace / '.venv' / 'bin' / 'python').exists() diff --git a/tests/unit_tests/provider/test_skill_tools.py b/tests/unit_tests/provider/test_skill_tools.py index 7a9cde66..9db7b945 100644 --- a/tests/unit_tests/provider/test_skill_tools.py +++ b/tests/unit_tests/provider/test_skill_tools.py @@ -193,6 +193,29 @@ class TestSkillPathHelpers: assert list(result.keys()) == ['visible'] + def test_restore_activated_skills_uses_caller_provided_names_and_visibility(self): + from langbot.pkg.provider.tools.loaders.skill import ( + ACTIVATED_SKILLS_KEY, + PIPELINE_BOUND_SKILLS_KEY, + get_activated_skill_names, + restore_activated_skills, + ) + + ap = _make_ap() + ap.skill_mgr = SimpleNamespace( + skills={ + 'visible': _make_skill_data(name='visible'), + 'hidden': _make_skill_data(name='hidden'), + } + ) + query = SimpleNamespace(variables={PIPELINE_BOUND_SKILLS_KEY: ['visible']}) + + restored = restore_activated_skills(ap, query, ['visible', 'hidden', 'visible', '']) + + assert restored == ['visible'] + assert list(query.variables[ACTIVATED_SKILLS_KEY].keys()) == ['visible'] + assert get_activated_skill_names(query) == ['visible'] + def test_resolve_virtual_skill_path_allows_visible_skill_reads(self): from langbot.pkg.provider.tools.loaders.skill import ( PIPELINE_BOUND_SKILLS_KEY, @@ -282,6 +305,7 @@ class TestSkillToolLoader: assert result['activated'] is True assert result['skill_name'] == 'demo' assert result['mount_path'] == '/workspace/.skills/demo' + assert result['activated_skill_names'] == ['demo'] assert 'Step 1' in result['content'] assert set(query.variables[ACTIVATED_SKILLS_KEY].keys()) == {'demo'}