From 3bb3875eb164643eb7f3e1d885e53d043bfc0fb0 Mon Sep 17 00:00:00 2001 From: hy Date: Fri, 9 Oct 2026 10:49:26 +0800 Subject: [PATCH] feat(tests): enhance AI service tests for knowledge independence and embedding model handling - Added tests for AI service to ensure it operates independently of knowledge configuration, including scenarios with missing or corrupt embedding models. - Updated existing tests to prepare embedding models before execution to ensure consistent test environments. - Introduced new utility functions for managing embedding models in test setups. - Improved error handling in knowledge retrieval tests to verify behavior when embedding models are unavailable. - Refactored test harness to streamline embedding model preparation and ensure proper initialization before running tests. --- doc/architecture.md | 2 +- doc/prd/settings.md | 2 +- doc/prd/workbench.md | 3 +- doc/test-plan/ai-test.md | 28 ++- doc/test-plan/knowledge-test.md | 16 +- doc/test-plan/workbench-test.md | 9 + src/main/services/ai/AiRunService.ts | 2 - .../human/shared/modelToolResultRenderers.ts | 2 +- .../ai/human/tools/kb/retrievalTools.ts | 23 +- src/main/services/ai/runtime.ts | 3 +- src/main/services/ai/runtimePreflight.ts | 37 --- src/main/services/ai/types.ts | 4 +- src/main/services/model/ModelService.ts | 5 +- .../model/VectorModelDownloadService.ts | 8 +- .../storage/domains/DocumentsStore.ts | 37 ++- src/main/services/vector/EmbeddingService.ts | 1 + .../services/vector/ensureEmbeddingReady.ts | 15 +- .../WorkspaceKnowledgePrepareService.ts | 16 +- ...ai-run-service-embedding-preflight.test.ts | 225 ------------------ ...run-service-knowledge-independence.test.ts | 187 +++++++++++++++ ...pproval-denied-restricted-delivery.test.ts | 1 + .../human-mixed-tool-dispatch.test.ts | 2 + ...human-queued-message-safe-boundary.test.ts | 3 +- .../mock-llm/multi-tool-collaboration.test.ts | 1 + .../kb-availability-contract.test.ts | 163 +++++++++++++ .../kb-indexing-blocks-search.test.ts | 34 ++- .../prepare-workspaces-sequentially.test.ts | 5 +- .../case/unit/ai/kb-retrieval-errors.test.ts | 42 ++++ .../chat-run-service-contract.test.ts | 30 +-- .../vector/embedding-service.test.ts | 26 +- .../vector-download-service-contract.test.ts | 12 +- .../chat-without-knowledge-model.e2e.test.ts | 83 +++++++ tests/harness/backend/aiServiceHarness.ts | 7 +- tests/harness/backend/humanHarness.ts | 4 - tests/harness/backend/modelFixture.ts | 66 +++++ tests/harness/backend/realAiDepsFactory.ts | 12 +- tests/harness/backend/realAiHarness.ts | 5 +- tests/harness/backend/test-types.ts | 1 + 38 files changed, 737 insertions(+), 385 deletions(-) delete mode 100644 src/main/services/ai/runtimePreflight.ts delete mode 100644 tests/case/ai/human/mock-llm/ai-run-service-embedding-preflight.test.ts create mode 100644 tests/case/ai/human/mock-llm/ai-run-service-knowledge-independence.test.ts create mode 100644 tests/case/knowledge/foundation/kb-availability-contract.test.ts create mode 100644 tests/case/unit/ai/kb-retrieval-errors.test.ts create mode 100644 tests/case/workbench/conversation/composer/chat-without-knowledge-model.e2e.test.ts create mode 100644 tests/harness/backend/modelFixture.ts diff --git a/doc/architecture.md b/doc/architecture.md index 91ce3630..58612ceb 100644 --- a/doc/architecture.md +++ b/doc/architecture.md @@ -29,7 +29,7 @@ NCurator-Desktop 是本地优先的 Electron 桌面应用。文档解析、嵌 **检索** -向量搜索（语义）+ LanceDB FTS（关键词）+ RRF 融合。设置页「更新索引」进行中时，知识库工具直接失败；检查更新不拦截检索。 +向量搜索（语义）+ LanceDB FTS（关键词）+ RRF 融合。 ### 分层与主链路 diff --git a/doc/prd/settings.md b/doc/prd/settings.md index c03b7f8f..c038db3c 100644 --- a/doc/prd/settings.md +++ b/doc/prd/settings.md @@ -30,7 +30,7 @@ - 检查更新：读取当前真实数据，判断哪些文件或网页需要重新建立索引。 - 更新索引：只处理可索引或失败资料，把内容写入后续检索可用的本地索引。 - 网页资料：全局一份，由 URL 导入并抓取；`UNIQUE(normalized_url)`。 -- 向量模型：本地检索与知识库能力依赖的嵌入模型。 +- 向量模型：知识库工具与索引依赖的本地嵌入模型；工作空间和向量模型配置均不影响普通 AI run 启动。模型只由用户主动下载或恢复已有下载任务，KB / 索引不隐式下载。删除模型释放已加载运行时；后续 KB 调用返回错误，不终止聊天。 ## 5. 需求规则 diff --git a/doc/prd/workbench.md b/doc/prd/workbench.md index 12dd8485..522c99cd 100644 --- a/doc/prd/workbench.md +++ b/doc/prd/workbench.md @@ -53,7 +53,7 @@ PPT 普通预览和审核需完整显示中文及全角标点，换行测量与 - Composer 附件不限制文件扩展名、文件大小、数量或目录大小；点击 `+` 直接打开可选择文件或目录的系统选择器，聊天区拖放接受文件和目录。文件及目录附件都保留源路径，不复制、不预解析目录，只把附件顺序、名称和绝对路径交给 AI 后续自行处理。附件卡片使用紧凑布局，仅图片显示缩略图；文件夹使用文件夹图标，音频和视频使用对应媒体图标。图片点击保持图片灯箱，支持右侧文件预览的文档点击打开右侧资源 Tab，文件夹继续用系统文件管理器打开，音视频及其他不支持右侧预览的文件定位到系统文件所在位置。粘贴文件因不保证有稳定源路径，保存副本到当前伙伴运行时目录。AI 工具侧仍有各自格式边界（如 `doc` 只读、`pptx` 可交给 PPT 工具读取和编辑、Excel 工具只写 `xlsx`），无法处理的文件会在 AI 工具层报错。 - 其他格式不保证直接写回和回退。AI 可以在审批边界内尝试处理，但不属于受支持文件能力范围。 - 审核权限下，终端副作用规则未命中的命令默认执行；命中的已知文件增删改、明确脚本/程序运行、系统/进程操作或网络写入先由本次运行主模型审核，模型明确判断操作在用户授权范围内时自动执行，否则再由用户审批。完全访问跳过两层审核。默认工作目录是用户主目录；终端改文件不进入修改记录，也不能从馆长回退。详细规则见 `WB-BLOCKER-001`。 -- AI 可通过 `web_search` / `kb_search` 检索；`web_search` 不得自动展开右侧列表。设置页正在「更新索引」时，`kb_search` / `kb_list_documents` 失败并提示正在更新知识库；「检查更新」不拦截。 +- AI 可通过 `web_search` / `kb_search` 检索；`web_search` 不得自动展开右侧列表。所有 KB 工具（含关键词检索与文档列表）统一要求向量模型已安装，调用时按需初始化本地模型；缺失、下载中、初始化或执行失败只返回工具错误，提示 AI 当前状态下停止调用 KB，不终止 run，不下载、不修复、不静默降级。设置页正在「更新索引」时返回错误；「检查更新」不拦截。模型可用时，空库、空范围和查询无命中正常返回空结果，不扩大显式范围。 - `@` 参考资料不能替代「已创建并选中伙伴」这一发送前提。 ## 6. 术语 @@ -309,6 +309,7 @@ PPT 普通预览和审核需完整显示中文及全角标点，换行测量与 - `WB-COMPOSER-001-AC2` 未选中伙伴或当前提交请求尚未返回时，不会重复触发同一次发送；普通 AI run 运行期间仍可提交新的追加消息。 - `WB-COMPOSER-001-AC3` 已选中伙伴但发送按钮因前置条件不可执行时，hover 可见具体禁用原因。未创建或未选中伙伴时 Composer 为空态、不出现可发送按钮（见 `WB-CORE-001-AC2` / `WB-SESSION-001-AC1`），不适用本条 hover 文案。 - `WB-COMPOSER-001-AC4` Composer 空输入占位含当前伙伴名；审批指导输入占位为「告诉{当前伙伴名}该怎么做」；改名后占位与后续 Brain 自称同步新名（可导致 LLM 前缀缓存 miss，本地数据不丢）。 + - `WB-COMPOSER-001-AC5` 未配置工作空间、未下载向量模型或模型初始化失败均不阻止 AI run 启动；普通聊天不准备或下载向量模型。 #### WB-COMPOSER-002 键盘行为 diff --git a/doc/test-plan/ai-test.md b/doc/test-plan/ai-test.md index 1a09b5fe..f94cb279 100644 --- a/doc/test-plan/ai-test.md +++ b/doc/test-plan/ai-test.md @@ -154,7 +154,7 @@ Word、PPT、Excel、普通文本统一由主 run 的文件会话管理。工具 - fixture 可用 `tests/fixtures/workspace`；运行时作为设置页文件地址 + 伙伴，不再「绑定工作区才能跑」。 - AI backend 回归以生产 `createAiRunContext` 为唯一 runtime 入口，使用真实 store、apply service 和 embedding service；文档 worker 经 `AiRunResourceManager` 在 run 结束时释放，释放失败不得覆盖任务结果。 - `mock-llm` 只固定 LLM 输出，其余全部真实；`live` 走真实 `LlmConfigStore` 与生产 LLM executor。 -- 进入 `human` 前必须完成 embedding preflight；KB fixture 走真实导入 / 索引 / 检索。所有支持文件前置「文件名锚点」内容块；Excel 只索引文件名、文档标题与工作表名等元数据。embedding 缺失时走真实生产下载链，不得用测试替身。 +- AI run 与 human harness 不准备 embedding；KB 工具调用时统一检查模型安装与本地初始化，不隐式下载或静默降级。需要 KB 的 fixture 显式通过真实下载 / 索引准备模型和资料；不使用 KB 的回归不准备模型。所有支持文件前置「文件名锚点」内容块；Excel 只索引文件名、文档标题与工作表名等元数据。 - 不得使用旧式 fake API。默认 `testTimeout` / `hookTimeout` 为 `900_000`；少数重型 live case 可覆写更长超时。 ### 3.2 `mock-llm` 与 `live` 设计口径 @@ -789,21 +789,23 @@ Unit `docx-diff` 补重复内容匹配、跨 run 字符、Unicode 分段、大 - How：脚本化 brain 决策调用真实 `kb_list_documents`；在工具结果写入、`context_budget` 已完成检查后模拟一条正在校验的提交，延迟确认入队；验证 Brain 入口等待校验并回到交接边界，再用第二个真实 graph run 捕获首轮 brain messages。 - Oracle：第一轮状态为 `yielded` 且真实工具结果已写入 log；未确认入队前不会启动第二次 brain 决策；第二轮状态为 `completed`，历史中工具结果先于尾部追加 user；第二轮不重复调用中断前工具。 -##### `ai-run-service-embedding-preflight` +##### `ai-run-service-without-knowledge` -- 测试类型：`backend` -- What：`AiRunService` 会在进入 `human` 前执行有界 embedding preflight，知识库语义检索可继续复用该基础设施。 -- Why：知识库 embedding 初始化应在模型可用时提前完成，但不能无限阻塞 AI run 启动。 -- How：通过 `AiRunService.getInstance().run(...)` 启动真实 run，在 preflight 成功后执行普通 DOCX literal 读取链路。 -- Oracle：preflight 被调用一次；任务完成；DOCX literal 搜索返回真实命中且不依赖 embedding。 +- 测试类型：`backend / mock-llm` +- What：未配置文件地址且向量模型缺失或损坏时，主 run、子 run 和续接仍能完成聊天、真实文件读取。 +- Why：普通 AI 运行不能受知识库配置影响，也不能隐式下载模型。 +- How：隔离空模型目录，使用生产 AiRunService 和 scripted LLM 完成 DOCX literal 读取、子任务与续接；另在真实损坏模型目录下完成聊天。不调用 KB，不替换 embedding executor 或就绪检查。 +- Oracle：run 完成；真实文件读取命中；主子运行有 brain 事件；模型目录不变，embedding 保持 uninitialized；不产生模型下载。 +- 最新验证：2026-10-09 本轮通过；原始日志：`tests/logs/ai/human/mock-llm/ai-run-service-without-knowledge/20261009-104153-012-aa92ff73`。 -##### `ai-run-service-embedding-preflight-failure` +##### `ai-run-service-kb-error-continues` -- 测试类型：`backend` -- What：embedding preflight 失败时，`AiRunService` 会在进入 `human` 前直接失败收口。 -- Why：基础服务明确失败时继续进入 human graph 会制造后续工具层噪音，应该在入口阶段明确失败；初始化卡住则由有界 preflight 超时保护。 -- How：注入会抛错的 `ensureEmbeddingReady`，启动一次真实 `AiRunService` run。 -- Oracle：run 状态为 `failed`，只返回统一的用户可见错误，不泄露底层 preflight 原文，事件流中没有任何 `human_step`。 +- 测试类型：`backend / mock-llm` +- What：真实 KB 不可用只产生工具错误，后续文件工具和最终交付仍正常。 +- Why：知识库失败应交给 AI 决策，不能终止整个 run。 +- How：隔离空模型目录，生产 AiRunService 中 scripted LLM 先调用 kb_search，再读取真实文本并交付；捕获下一轮模型上下文。 +- Oracle：KB 结果 ok=false 且上下文含模型缺失原因及停止调用 KB 指引；真实文本读取成功；run completed，无 run_failed，目录无下载产物。 +- 最新验证：2026-10-09 本轮通过；原始日志：`tests/logs/ai/human/mock-llm/ai-run-service-kb-error-continues/20261009-104153-378-156b33dd`。 ##### `learning-hand-mouth-smoke` diff --git a/doc/test-plan/knowledge-test.md b/doc/test-plan/knowledge-test.md index fc848faa..13fa9389 100644 --- a/doc/test-plan/knowledge-test.md +++ b/doc/test-plan/knowledge-test.md @@ -22,7 +22,7 @@ ### 2.1 `foundation` - 目标：守住知识库可回归的功能主链。 -- 约束：走生产 store / job / 扫描 / worker / 嵌入 executor；禁止假 executor 或假 `assertKbSearchAvailable`。索引速度 case 必须在独立 Node 进程里建真实 embedding session，并用操作系统线程数证明档位生效，不测 UI、不测墙钟 / CPU%。 +- 约束：走生产 store / job / 扫描 / worker / 嵌入 executor；禁止假 executor 或假 `assertKbAvailable`。索引速度 case 必须在独立 Node 进程里建真实 embedding session，并用操作系统线程数证明档位生效，不测 UI、不测墙钟 / CPU%。 - 目录：`tests/case/knowledge/foundation/.test.ts` ### 2.2 `optimization` @@ -82,8 +82,18 @@ - 测试类型：`backend` - What：prepare 索引进行中时 `kb_search` / `kb_list_documents` 失败，并投递模型可读错误。 - Why：更新索引期间检索必须明确失败，避免半库结果。 -- How：隔离 sqlite 写入 running prepare job，再走生产 `createAiRunContext` 调用两个工具，并检查 model-facing 投递文案。 -- Oracle：两工具抛出正在更新知识库错误；模型侧结果为 `Error: 正在更新知识库索引，请完成后再检索。`，对齐 `SET-WORKSPACE-004-AC9`、`SET-WEB-004-AC8`。 +- How：隔离 sqlite 写入文件 / 网页 running prepare job，再走生产 `createAiRunContext` 调用两个工具并检查投递文案；显式准备真实模型后，验证 running scan 与 prepare 的 succeeded / failed / cancelled 终态不拦截空库查询。 +- Oracle：两工具抛出正在更新知识库错误；模型侧结果包含正在更新知识库原因及当前状态下停止调用 KB 的指引，对齐 `SET-WORKSPACE-004-AC9`、`SET-WEB-004-AC8`。 +- 最新验证：2026-10-09 本轮通过；原始日志：`tests/logs/knowledge/foundation/kb-indexing-blocks-search/20261009-104411-354-11c9b53e`。 + +#### `kb-availability-contract` + +- 测试类型：`backend` +- What：所有 KB 工具统一检查模型安装 / 初始化，空库和空范围正常返回空结果；索引入口同样不隐式下载。 +- Why：模型缺失不能被关键词或列表绕过；空库不能误判为知识库故障。 +- How：独立模型目录中用真实 ModelService、EmbeddingService / Transformers executor、store 和 createAiRunContext；分别准备空目录、不完整下载目录、文件齐全但内容损坏的模型目录，调用两个 KB 工具与文件 / 网页索引入口。健康模型显式准备后验证空库、限定空范围、无文件地址的全局网页、删除与恢复。不替换执行器和就绪检查；Node 使用同一生产 executor in-process，Electron utilityProcess 由 Workbench E2E 验证。 +- Oracle：缺失 / 不完整模型在所有 strategy 和列表中返回错误且目录不变；损坏模型初始化错误；索引入口缺失模型失败且无资料写入；健康模型空库 / 空范围返回 items=[]、total=0；全局网页能检索；模型删除后下一次 KB 失败，恢复后可用。 +- 最新验证：2026-10-09 本轮通过；原始日志：`tests/logs/knowledge/foundation/kb-availability-contract/20261009-104115-815-12bf90e6`。 #### `index-speed-thread-budget` diff --git a/doc/test-plan/workbench-test.md b/doc/test-plan/workbench-test.md index 393b12a5..7d1a891c 100644 --- a/doc/test-plan/workbench-test.md +++ b/doc/test-plan/workbench-test.md @@ -185,6 +185,15 @@ pnpm test:update:e2e - How：完成一次真实 AI run，读取圆圈可访问名称和 hover 提示。用量环分母为当前所选模型的 effectiveWindow（免费/推荐目录 `contextWindowTokens` × 0.8 再 cap 256k；自定义按 256k 算出）。 - Oracle：圆圈展示已用信息，hover 展示已用百分比与 tokens、不展示剩余，对齐 `WB-COMPOSER-008`。 +#### `chat-without-knowledge-model` + +- 测试类型：`e2e / live` +- What：未配置工作空间、未安装向量模型仍可发送并完成真实聊天。 +- Why：默认 E2E 模型准备不能掩盖首次使用的运行门禁。 +- How：通过既有 NCURATOR_MODELS_PATH 注入独立空模型目录，跳过 harness 默认模型预热；真实 UI 配聊天模型、创建伙伴并发送；只读 observer 收集运行事件、下载状态和 embedding runtime。 +- Oracle：真实 run completed；模型目录没有下载产物；无下载任务；embedding runtime uninitialized 且 pid 为空，对齐 WB-COMPOSER-001-AC5。 +- 最新验证：2026-10-09 本轮通过；原始日志：`tests/logs/workbench/conversation/composer/chat-without-knowledge-model/20261009-104143-882`。 + #### `send-guard-and-preferences` - 测试类型：`e2e` diff --git a/src/main/services/ai/AiRunService.ts b/src/main/services/ai/AiRunService.ts index ab067e86..90d6f154 100644 --- a/src/main/services/ai/AiRunService.ts +++ b/src/main/services/ai/AiRunService.ts @@ -7,7 +7,6 @@ import { releasePdfRunSession } from '../pdf/worker/pdfWorkerClient' import { terminalSessionManager } from './human/tools/terminal/TerminalSessionManager' import { createHumanGraphRunner } from './human/graph/humanGraph' import { createAiRunContext } from './runtime' -import { runAiRuntimePreflight } from './runtimePreflight' import { createCancelledAiRunState, createCompletedAiRunState, @@ -75,7 +74,6 @@ export class AiRunService { } } try { - await runAiRuntimePreflight(deps) const ctx = createAiRunContext(payload, { ...deps, delegateToSubagent: (tasks, toolCallId) => dispatch(tasks, toolCallId) diff --git a/src/main/services/ai/human/shared/modelToolResultRenderers.ts b/src/main/services/ai/human/shared/modelToolResultRenderers.ts index bcfe74d2..04d3b950 100644 --- a/src/main/services/ai/human/shared/modelToolResultRenderers.ts +++ b/src/main/services/ai/human/shared/modelToolResultRenderers.ts @@ -163,7 +163,7 @@ const normalizeKbSearchItems = (data: JsonValue | undefined): JsonObject[] => { export const renderKbModelError: ModelResultRenderer = ({ data }) => { const detail = isObject(data) ? readString(data.error) : '' - return detail ? `Error: ${detail}` : 'Error: kb tool failed.' + return `${detail ? `Error: ${detail}` : 'Error: kb tool failed.'}\n当前状态下不要继续调用 KB 工具；请告知用户原因，可继续使用其他可用能力。` } export const renderKbSearchModelResult: ModelResultRenderer = ({ data }) => { diff --git a/src/main/services/ai/human/tools/kb/retrievalTools.ts b/src/main/services/ai/human/tools/kb/retrievalTools.ts index 2c06f515..8422713e 100644 --- a/src/main/services/ai/human/tools/kb/retrievalTools.ts +++ b/src/main/services/ai/human/tools/kb/retrievalTools.ts @@ -65,9 +65,7 @@ const buildKbResult = (input: { })() const normalizedData = - input.ok === false && input.error - ? ({ error: input.error } satisfies JsonObject) - : data + input.ok === false && input.error ? ({ error: input.error } satisfies JsonObject) : data return { toolName: input.toolName, @@ -165,7 +163,7 @@ export const buildKbCapabilityTools = (input: { args: args as JsonObject, execute: async (session) => { ctx.checkCancelled() - await ctx.assertKbSearchAvailable() + await ctx.assertKbAvailable() const prepared = resolveSearchArgs(args) if (!prepared.queryText) { throw new Error('知识库搜索需要提供查询文本。') @@ -195,20 +193,7 @@ export const buildKbCapabilityTools = (input: { prepared.requestedDocumentIds || undefined ) } - let vec: Float32Array - try { - const embedding = await ctx.embeddingService.embed(prepared.queryText) - vec = embedding.data - } catch (error) { - if (prepared.strategy !== 'auto') throw error - return await ctx.documentsStore.ftsSearch( - prepared.queryText, - prepared.limit, - prepared.filter, - prepared.workspaceId, - prepared.requestedDocumentIds || undefined - ) - } + const { data: vec } = await ctx.embeddingService.embed(prepared.queryText) if (prepared.strategy === 'semantic') { return await ctx.documentsStore.vectorSearch( vec, @@ -273,7 +258,7 @@ export const buildKbCapabilityTools = (input: { args: args as JsonObject, execute: async (session) => { ctx.checkCancelled() - await ctx.assertKbSearchAvailable() + await ctx.assertKbAvailable() const workspaceId = String(ctx.workspace?.workspaceId || '').trim() || undefined const sourceNameQuery = String(args.sourceNameQuery || '').trim() || undefined const page = Math.max(1, Number(args.page ?? 1)) diff --git a/src/main/services/ai/runtime.ts b/src/main/services/ai/runtime.ts index 929895f9..22a6fd19 100644 --- a/src/main/services/ai/runtime.ts +++ b/src/main/services/ai/runtime.ts @@ -201,10 +201,11 @@ export const createAiRunContext = (payload: AiRunStartPayload, deps: AiRunDeps): }, documentsStore: deps.documentsStore, embeddingService: deps.embeddingService, - assertKbSearchAvailable: async () => { + assertKbAvailable: async () => { if (await deps.hasRunningKnowledgeIndexJob?.()) { throw new Error(KB_INDEXING_IN_PROGRESS_ERROR) } + await deps.ensureEmbeddingReady() } } } diff --git a/src/main/services/ai/runtimePreflight.ts b/src/main/services/ai/runtimePreflight.ts deleted file mode 100644 index 5526f2b9..00000000 --- a/src/main/services/ai/runtimePreflight.ts +++ /dev/null @@ -1,37 +0,0 @@ -import type { AiRunDeps } from './types' - -const DEFAULT_EMBEDDING_PREFLIGHT_TIMEOUT_MS = 15_000 - -const readEmbeddingPreflightTimeoutMs = (): number => { - const raw = Number(process.env.NCURATOR_AI_EMBEDDING_PREFLIGHT_TIMEOUT_MS) - if (!Number.isFinite(raw)) return DEFAULT_EMBEDDING_PREFLIGHT_TIMEOUT_MS - return Math.max(0, Math.floor(raw)) -} - -export const runAiRuntimePreflight = async ( - deps: Pick -): Promise => { - const timeoutMs = readEmbeddingPreflightTimeoutMs() - if (timeoutMs === 0) { - await deps.ensureEmbeddingReady() - return - } - - const ensureReadyPromise = deps.ensureEmbeddingReady() - let timeoutHandle: ReturnType | undefined - const timeoutPromise = new Promise<'timeout'>((resolve) => { - timeoutHandle = setTimeout(() => resolve('timeout'), timeoutMs) - }) - - const result = await Promise.race([ - ensureReadyPromise.then(() => 'ready' as const), - timeoutPromise - ]) - if (timeoutHandle) clearTimeout(timeoutHandle) - if (result === 'ready') return - - ensureReadyPromise.catch((error) => { - console.warn('[AI-RUN] embedding preflight completed after timeout with error:', error) - }) - console.warn(`[AI-RUN] embedding preflight timed out after ${timeoutMs}ms; continuing run`) -} diff --git a/src/main/services/ai/types.ts b/src/main/services/ai/types.ts index 1f2e912a..18eed086 100644 --- a/src/main/services/ai/types.ts +++ b/src/main/services/ai/types.ts @@ -450,7 +450,7 @@ export type AiRunContext = { }) => Promise documentsStore: DocumentsStore embeddingService: EmbeddingService - assertKbSearchAvailable: () => Promise + assertKbAvailable: () => Promise } export type AiRunFailureMetadata = { @@ -475,7 +475,7 @@ export type KnowledgeRetrievalContext = Pick< | 'workspace' | 'documentsStore' | 'embeddingService' - | 'assertKbSearchAvailable' + | 'assertKbAvailable' > export type DocxToolContext = AiRunContext diff --git a/src/main/services/model/ModelService.ts b/src/main/services/model/ModelService.ts index fa4b2ffe..f245be97 100644 --- a/src/main/services/model/ModelService.ts +++ b/src/main/services/model/ModelService.ts @@ -144,6 +144,7 @@ export class ModelService { } private isModelDownloadedAtPath(repoId: string, modelPath: string): boolean { + if (fs.existsSync(path.join(modelPath, DOWNLOAD_STATE_FILE))) return false if (!fs.existsSync(modelPath) || !fs.statSync(modelPath).isDirectory()) { return false } @@ -343,9 +344,7 @@ export class ModelService { private resolveSourceEndpoint(source: ModelSource): string { if (source === 'modelscope') { - return ( - String(process.env[MODELSCOPE_ENDPOINT_ENV] || '').trim() || MODELSCOPE_ENDPOINT - ) + return String(process.env[MODELSCOPE_ENDPOINT_ENV] || '').trim() || MODELSCOPE_ENDPOINT } return String(process.env[HF_ENDPOINT_ENV] || '').trim() || HF_ENDPOINT } diff --git a/src/main/services/model/VectorModelDownloadService.ts b/src/main/services/model/VectorModelDownloadService.ts index 34c3bcc5..39024c7d 100644 --- a/src/main/services/model/VectorModelDownloadService.ts +++ b/src/main/services/model/VectorModelDownloadService.ts @@ -150,11 +150,13 @@ export class VectorModelDownloadService { } try { + if (repoId === this.deps.embeddingService.getModelName()) { + await this.deps.embeddingService.close() + } await this.deps.modelService.deleteModel(repoId) if (this.activeSnapshot?.repoId === repoId) { this.clearSnapshot() } - await this.deps.embeddingService.initialize().catch(() => undefined) return { success: true } } catch (error: unknown) { return { @@ -178,10 +180,6 @@ export class VectorModelDownloadService { signal, source ) - .then(async (value) => { - await this.deps.embeddingService.initialize().catch(() => undefined) - return value - }) .catch((error: unknown) => ({ success: false, error: getErrorMessage(error), diff --git a/src/main/services/storage/domains/DocumentsStore.ts b/src/main/services/storage/domains/DocumentsStore.ts index 92e47099..1d7159dd 100644 --- a/src/main/services/storage/domains/DocumentsStore.ts +++ b/src/main/services/storage/domains/DocumentsStore.ts @@ -7,7 +7,14 @@ import type { SearchResult, WebSourceRecord } from '../../../types/store' -import { asRecord, toNumber, toNumberArray, toOptionalNumber, toOptionalString, toString } from '../../../utils/decoder' +import { + asRecord, + toNumber, + toNumberArray, + toOptionalNumber, + toOptionalString, + toString +} from '../../../utils/decoder' import { LanceDbCore, LANCE_TABLES } from '../core/LanceDbCore' import type { SqliteCore } from '../sqlite/SqliteCore' import { @@ -258,9 +265,9 @@ export class DocumentsStore { public async getDocumentByFilePath(filePath: string): Promise { const normalized = String(filePath || '').trim() if (!normalized) return null - const row = this.sqlite.prepare('SELECT * FROM document WHERE file_path = ? LIMIT 1').get(normalized) as - | DocumentRow - | undefined + const row = this.sqlite + .prepare('SELECT * FROM document WHERE file_path = ? LIMIT 1') + .get(normalized) as DocumentRow | undefined if (!row) return null const [document] = await this.attachWebSourceMetadata([toDocumentRecord(row)]) return document || null @@ -348,7 +355,10 @@ export class DocumentsStore { for (let index = 0; index < chunks.length; index += 1) { const chunk = chunks[index] const textBytes = Buffer.byteLength(chunk.text || '', 'utf8') - if (batch.length >= batchSize || (batch.length > 0 && batchTextBytes + textBytes > maxTextBytes)) { + if ( + batch.length >= batchSize || + (batch.length > 0 && batchTextBytes + textBytes > maxTextBytes) + ) { await flush() } batch.push({ @@ -379,6 +389,7 @@ export class DocumentsStore { const table = await this.vector.openTable(LANCE_TABLES.CHUNK) const query = table.query() const where = await this.buildChunkWhere({ workspaceId, sourceType, documentIds }) + if ((await table.countRows(where)) === 0) return [] if (where) query.where(where) const results = await query.nearestTo(queryVector).distanceType('cosine').limit(limit).toArray() return results.map(toSearchResult) @@ -394,6 +405,7 @@ export class DocumentsStore { const table = await this.vector.openTable(LANCE_TABLES.CHUNK) const q = table.query() const where = await this.buildChunkWhere({ workspaceId, sourceType, documentIds }) + if ((await table.countRows(where)) === 0) return [] if (where) q.where(where) const results = await q.fullTextSearch(queryText).limit(limit).toArray() return results.map(toSearchResult) @@ -407,11 +419,12 @@ export class DocumentsStore { workspaceId?: string, documentIds?: string[] ): Promise { - const reranker = await this.getRRFReranker() const table = await this.vector.openTable(LANCE_TABLES.CHUNK) const q = table.query() const where = await this.buildChunkWhere({ workspaceId, sourceType, documentIds }) + if ((await table.countRows(where)) === 0) return [] if (where) q.where(where) + const reranker = await this.getRRFReranker() const results = await q .fullTextSearch(queryText) .nearestTo(queryVector) @@ -469,7 +482,9 @@ export class DocumentsStore { .get(sqlParams) as { count?: unknown } const skip = Math.max(0, (page - 1) * pageSize) const rows = this.sqlite - .prepare(`SELECT * FROM document WHERE ${where} ORDER BY created_at DESC LIMIT @limit OFFSET @offset`) + .prepare( + `SELECT * FROM document WHERE ${where} ORDER BY created_at DESC LIMIT @limit OFFSET @offset` + ) .all({ ...sqlParams, limit: pageSize, offset: skip }) as DocumentRow[] const items = await this.attachWebSourceMetadata(rows.map(toDocumentRecord)) return { items, total: toRequiredNumber(totalRow.count) } @@ -494,7 +509,9 @@ export class DocumentsStore { private async getDocumentsByIds(ids: string[]): Promise { const params: Record = {} const where = buildWhere([buildInClause('id', ids, params, 'document_id')]) - const rows = this.sqlite.prepare(`SELECT * FROM document WHERE ${where}`).all(params) as DocumentRow[] + const rows = this.sqlite + .prepare(`SELECT * FROM document WHERE ${where}`) + .all(params) as DocumentRow[] return await this.attachWebSourceMetadata(rows.map(toDocumentRecord)) } @@ -505,7 +522,9 @@ export class DocumentsStore { if (webDocumentIds.length === 0) return documents const params: Record = {} const where = buildWhere([buildInClause('document_id', webDocumentIds, params, 'document_id')]) - const rows = this.sqlite.prepare(`SELECT * FROM web_source WHERE ${where}`).all(params) as WebSourceRecord[] + const rows = this.sqlite + .prepare(`SELECT * FROM web_source WHERE ${where}`) + .all(params) as WebSourceRecord[] const webSourceMap = new Map( rows.map((row) => { const source = row as WebSourceRecord diff --git a/src/main/services/vector/EmbeddingService.ts b/src/main/services/vector/EmbeddingService.ts index 66be88c3..d4e47cf1 100644 --- a/src/main/services/vector/EmbeddingService.ts +++ b/src/main/services/vector/EmbeddingService.ts @@ -87,6 +87,7 @@ export class EmbeddingService { } public async close(): Promise { + await this.initializationPromise?.catch(() => undefined) await this.executor.close?.() this.status = 'uninitialized' } diff --git a/src/main/services/vector/ensureEmbeddingReady.ts b/src/main/services/vector/ensureEmbeddingReady.ts index 70a96b28..6d055ee8 100644 --- a/src/main/services/vector/ensureEmbeddingReady.ts +++ b/src/main/services/vector/ensureEmbeddingReady.ts @@ -1,21 +1,18 @@ -import type { ModelDownloadProgressReporter } from '../model/ModelService' import { ModelService } from '../model/ModelService' import { EmbeddingService } from './EmbeddingService' +export const EMBEDDING_MODEL_NOT_INSTALLED_ERROR = + '向量模型尚未安装或下载未完成，请在设置页完成模型下载后再使用知识库。' + export const ensureEmbeddingReady = async (input: { embeddingService: EmbeddingService modelService?: ModelService - reporter?: ModelDownloadProgressReporter }): Promise => { - if (input.embeddingService.getStatus() === 'ready') { - return - } - const modelService = input.modelService || ModelService.getInstance() const repoId = input.embeddingService.getModelName() if (!modelService.isModelDownloaded(repoId)) { - await modelService.downloadModel(repoId, input.reporter) + throw new Error(EMBEDDING_MODEL_NOT_INSTALLED_ERROR) } await input.embeddingService.initialize() @@ -24,7 +21,5 @@ export const ensureEmbeddingReady = async (input: { return } - throw new Error( - `embedding bootstrap failed after ensuring model download; model=${repoId}; status=${input.embeddingService.getStatus()}` - ) + throw new Error(`向量模型未就绪：${repoId} (${input.embeddingService.getStatus()})`) } diff --git a/src/main/services/workspace/WorkspaceKnowledgePrepareService.ts b/src/main/services/workspace/WorkspaceKnowledgePrepareService.ts index 28b25b5c..acdc8931 100644 --- a/src/main/services/workspace/WorkspaceKnowledgePrepareService.ts +++ b/src/main/services/workspace/WorkspaceKnowledgePrepareService.ts @@ -2,6 +2,7 @@ import path from 'node:path' import { v4 as uuidv4 } from 'uuid' import type { DocumentsStore } from '../storage/domains/DocumentsStore' import type { EmbeddingService } from '../vector/EmbeddingService' +import { ensureEmbeddingReady } from '../vector/ensureEmbeddingReady' import { isSupportedLocalFilePath } from '../ingestion/loader' import type { WorkspaceKnowledgeChunkInput, @@ -77,6 +78,8 @@ export class WorkspaceKnowledgePrepareService { if (!isSupportedLocalFilePath(input.filePath)) { throw new Error(`Unsupported file type: ${input.filePath}`) } + await ensureEmbeddingReady({ embeddingService: this.deps.embeddingService }) + this.throwIfAborted(input.signal) const stopAbort = this.listenForAbort(input.signal, () => { void this.abortActivePrepare() @@ -146,6 +149,8 @@ export class WorkspaceKnowledgePrepareService { public async indexWebText( input: WorkspaceKnowledgeWebInput ): Promise { + this.throwIfAborted(input.signal) + await ensureEmbeddingReady({ embeddingService: this.deps.embeddingService }) this.throwIfAborted(input.signal) const stopAbort = this.listenForAbort(input.signal, () => { void this.abortActivePrepare() @@ -254,14 +259,6 @@ export class WorkspaceKnowledgePrepareService { vectors: [] } } else { - if (this.deps.embeddingService.getStatus() !== 'ready') { - await this.deps.embeddingService.initialize() - } - if (this.deps.embeddingService.getStatus() !== 'ready') { - throw new Error( - `EmbeddingService is not ready. Current status: ${this.deps.embeddingService.getStatus()}` - ) - } vectorSnapshot = { contentHash: preparedSource.contentHash, fileExt: preparedSource.fileExt, @@ -402,8 +399,7 @@ export class WorkspaceKnowledgePrepareService { })) } } catch (error) { - const cancelled = - isIndexPrepareCancelledError(error) || Boolean(input.signal?.aborted) + const cancelled = isIndexPrepareCancelledError(error) || Boolean(input.signal?.aborted) if (wroteChunks && !activated) { await this.deps.documentsStore .deleteChunksByGeneration({ diff --git a/tests/case/ai/human/mock-llm/ai-run-service-embedding-preflight.test.ts b/tests/case/ai/human/mock-llm/ai-run-service-embedding-preflight.test.ts deleted file mode 100644 index ba7f95c5..00000000 --- a/tests/case/ai/human/mock-llm/ai-run-service-embedding-preflight.test.ts +++ /dev/null @@ -1,225 +0,0 @@ -import path from 'node:path' -import { describe, it } from 'vitest' -import { AiRunService } from '../../../../../src/main/services/ai/AiRunService' -import { AiFileChangeService } from '../../../../../src/main/services/ai/fileChanges/AiFileChangeService' -import { runBackendCase } from '../../../../harness/backend/run-backend-case' -import { createScriptedStructuredOutputDriver } from '../../../../harness/backend/scriptedStructuredOutputDriver' -import { writeTestDocxFile } from '../../../../harness/backend/aiToolHarness' -import type { DocxSearchResult } from '../../tool/docx/testUtils' -import { - buildCompleteTaskDecision, - buildLearnSkillsDecision, - buildToolDecision, - filterAiRunEventsByType, - readLatestToolResultDataFromEvents -} from '../testUtils' - -describe('ai human mock-llm backend', () => { - it('ai-run-service-embedding-preflight', async () => { - await runBackendCase({ - caseId: 'ai-run-service-embedding-preflight', - harnessMode: 'mock-llm', - domain: 'ai', - suite: 'human', - groups: ['mock-llm'], - description: - '验证 AiRunService 会在进入 human 前完成 embedding preflight，并支撑后续 docx 读取。', - fixtures: [], - runMode: 'single', - execute: async (runtime) => { - await runtime.chatStore.savePartner({ - id: 'embedding-preflight-session', - name: 'embedding preflight', - avatar_shape: 'circle', - avatar_color: 'blue', - created_at: Date.now(), - updated_at: Date.now(), - last_viewed_at: Date.now(), - pinned: false, - pinned_at: null - }) - await writeTestDocxFile(runtime.workspaceRoot, 'literal-docx.docx', [ - { - type: 'paragraph', - text: '反走样是在采样不足时出现的锯齿现象。' - } - ]) - - let ensureReadyCalls = 0 - const initialEmbeddingStatus = runtime.embeddingService.getStatus() - const aiFileChangeService = new AiFileChangeService(runtime.storageService.aiFileChange) - const result = await AiRunService.getInstance().run( - { - runId: runtime.runId, - partnerId: 'embedding-preflight-session', - input: '请读取 docx，找到反走样相关内容。', - mainModel: { - configId: 'mock-llm-scripted', - modelName: 'scripted-llm' - }, - partnerName: '测试伙伴', - workspaceRoots: [runtime.workspaceRoot] - }, - { - llmStore: runtime.llmStore, - partnerStore: runtime.chatStore, - chatMessageLogStore: runtime.storageService.chatMessageLog, - documentsStore: runtime.documentsStore, - embeddingService: runtime.embeddingService, - ensureEmbeddingReady: async () => { - ensureReadyCalls += 1 - await runtime.ensureEmbeddingReady() - }, - docxApplyService: runtime.docxApplyService, - saveFileChangeRecord: async (record) => { - await aiFileChangeService.saveRecord(record) - }, - listFileChangeRecords: async (request) => - (await aiFileChangeService.listRecords(request)).items, - isCancelled: () => false, - sendEvent: (event) => runtime.eventCollector.add(event), - recordLlmIo: (record) => runtime.eventCollector.addLlmIo(record), - requestApprovalBatch: async () => ({ accepted: true, decisions: [] }), - llmDriver: createScriptedStructuredOutputDriver({ - 'human.brain': [ - { - output: buildLearnSkillsDecision({ - skillIds: ['docx-read'], - summary: '先学习 docx-read' - }) - }, - { - output: buildToolDecision({ - toolName: 'docx_search', - args: { - sourcePath: path.join(runtime.workspaceRoot, 'literal-docx.docx'), - query: '锯齿现象', - mode: 'literal' - }, - summary: '搜索完整原文' - }) - }, - { - output: buildCompleteTaskDecision({ - summary: 'embedding preflight 已验证。', - deliveryMarkdown: '# Embedding Preflight\n\ndocx 读取链路已可用。' - }) - } - ] - }) - } - ) - - return { - result, - ensureReadyCalls, - initialEmbeddingStatus, - events: runtime.eventCollector.snapshot() - } - }, - assert: async (result, runtime) => { - const docxSearchResult = readLatestToolResultDataFromEvents( - result.events, - 'docx_search' - ) - - runtime.assertThat( - result.initialEmbeddingStatus === 'uninitialized' && - result.ensureReadyCalls === 1 && - result.result.status === 'completed' && - docxSearchResult.matches.length === 1 && - docxSearchResult.matches[0]?.matchText === '锯齿现象', - { - name: 'ai-run-service-preflights-embedding-before-human', - message: - 'AiRunService 应在进入 human 前完成 embedding preflight，DOCX literal 搜索不依赖 embedding。', - data: { - initialEmbeddingStatus: result.initialEmbeddingStatus, - ensureReadyCalls: result.ensureReadyCalls, - docxSearchResult, - finalStatus: result.result.status - } - } - ) - } - }) - }) - - it('ai-run-service-embedding-preflight-failure', async () => { - await runBackendCase({ - caseId: 'ai-run-service-embedding-preflight-failure', - harnessMode: 'mock-llm', - domain: 'ai', - suite: 'human', - groups: ['mock-llm'], - description: '验证 embedding preflight 失败时，AiRunService 会在进入 human 前直接失败收口。', - fixtures: [], - runMode: 'single', - execute: async (runtime) => { - const aiFileChangeService = new AiFileChangeService(runtime.storageService.aiFileChange) - const result = await AiRunService.getInstance().run( - { - runId: runtime.runId, - partnerId: 'embedding-preflight-failure-session', - input: '这轮不应该进入 human。', - mainModel: { - configId: 'mock-llm-scripted', - modelName: 'scripted-llm' - }, - partnerName: '测试伙伴', - workspaceRoots: [runtime.workspaceRoot] - }, - { - llmStore: runtime.llmStore, - partnerStore: runtime.chatStore, - chatMessageLogStore: runtime.storageService.chatMessageLog, - documentsStore: runtime.documentsStore, - embeddingService: runtime.embeddingService, - ensureEmbeddingReady: async () => { - throw new Error('embedding preflight failed for test') - }, - docxApplyService: runtime.docxApplyService, - saveFileChangeRecord: async (record) => { - await aiFileChangeService.saveRecord(record) - }, - listFileChangeRecords: async (request) => - (await aiFileChangeService.listRecords(request)).items, - isCancelled: () => false, - sendEvent: (event) => runtime.eventCollector.add(event), - recordLlmIo: (record) => runtime.eventCollector.addLlmIo(record), - requestApprovalBatch: async () => ({ accepted: true, decisions: [] }), - llmDriver: createScriptedStructuredOutputDriver({}) - } - ) - - return { - result, - events: runtime.eventCollector.snapshot() - } - }, - assert: async (result, runtime) => { - const humanSteps = filterAiRunEventsByType(result.events, 'human_step') - - runtime.assertThat( - result.result.status === 'failed' && - result.result.failureCode === 'unexpected_error' && - result.result.error === '运行失败，请重试' && - result.result.failureRawMessage === 'embedding preflight failed for test' && - humanSteps.length === 0, - { - name: 'ai-run-service-aborts-before-human-on-preflight-failure', - message: - 'embedding preflight 失败时，run 应直接失败、不进入 human stage，并保留短标题与原文。', - data: { - status: result.result.status, - failureCode: result.result.failureCode, - error: result.result.error, - failureRawMessage: result.result.failureRawMessage, - humanStepCount: humanSteps.length - } - } - ) - } - }) - }) -}) diff --git a/tests/case/ai/human/mock-llm/ai-run-service-knowledge-independence.test.ts b/tests/case/ai/human/mock-llm/ai-run-service-knowledge-independence.test.ts new file mode 100644 index 00000000..1de601bf --- /dev/null +++ b/tests/case/ai/human/mock-llm/ai-run-service-knowledge-independence.test.ts @@ -0,0 +1,187 @@ +import fs from 'node:fs/promises' +import path from 'node:path' +import { describe, it, expect } from 'vitest' +import { runBackendCase } from '../../../../harness/backend/run-backend-case' +import { createAiServiceTestRunner } from '../../../../harness/backend/aiServiceHarness' +import { + withIsolatedModels, + writeCorruptEmbeddingModel +} from '../../../../harness/backend/modelFixture' +import { writeTestDocxFile } from '../../../../harness/backend/aiToolHarness' +import { + buildCompleteTaskDecision, + buildLearnSkillsDecision, + buildToolDecision, + readLatestToolResultDataFromEvents +} from '../testUtils' +import type { ScriptedLlmStep } from '../../../../harness/backend/test-types' +import { EMBEDDING_MODEL_NOT_INSTALLED_ERROR } from '../../../../../src/main/services/vector/ensureEmbeddingReady' + +describe('AI runs independent of knowledge configuration', () => { + it('ai-run-service-without-knowledge', async () => { + await withIsolatedModels(async (modelsPath) => { + await runBackendCase({ + caseId: 'ai-run-service-without-knowledge', + domain: 'ai', + suite: 'human', + groups: ['mock-llm'], + harnessMode: 'mock-llm', + fixtures: [], + runMode: 'single', + description: '模型缺失或损坏、无工作地址仍能读取真实文件、派发子任务及续接。', + assert: async () => {}, + execute: async (runtime) => { + const sourcePath = path.join(runtime.workspaceRoot, 'local.txt') + await fs.writeFile(sourcePath, 'LOCAL_READ_EVIDENCE') + await writeTestDocxFile(runtime.workspaceRoot, 'literal.docx', [ + { type: 'paragraph', text: '反走样减少锯齿现象。' } + ]) + let parentCalls = 0 + let childCalls = 0 + let childReadConfirmed = false + const script: ScriptedLlmStep[] = Array.from({ length: 10 }, () => (call) => { + if (/用户诉求：\nCHILD_LOCAL_READ/.test(call.user)) { + childCalls += 1 + if (childCalls > 1) childReadConfirmed = call.user.includes('LOCAL_READ_EVIDENCE') + return childCalls === 1 + ? buildToolDecision({ + toolName: 'text_file_read', + args: { sourcePath }, + summary: '读取明确指定的文件' + }) + : buildCompleteTaskDecision({ summary: '子任务已读到真实文件' }) + } + parentCalls += 1 + if (parentCalls === 1) + return buildLearnSkillsDecision({ + skillIds: ['docx-read'], + summary: '学习原文读取能力' + }) + if (parentCalls === 2) + return buildToolDecision({ + toolName: 'docx_search', + args: { + sourcePath: path.join(runtime.workspaceRoot, 'literal.docx'), + query: '锯齿现象', + mode: 'literal' + }, + summary: '读取 DOCX 原文' + }) + if (parentCalls === 3) + return buildToolDecision({ + toolName: 'delegate_to_subagent', + args: { tasks: [{ name: '读取', task: 'CHILD_LOCAL_READ 读取指定本地文本' }] }, + summary: '派发文件读取子任务' + }) + return buildCompleteTaskDecision({ summary: '读取完成' }) + }) + const runner = await createAiServiceTestRunner(runtime, { + bindWorkspace: false, + partnerId: 'knowledge-independent', + llmScript: { 'human.brain': script } + }) + const output = await runner.run() + expect(output.status).toBe('completed') + expect( + readLatestToolResultDataFromEvents<{ totalMatchCount: number }>( + runner.events, + 'docx_search' + ).totalMatchCount + ).toBeGreaterThan(0) + expect(childReadConfirmed).toBe(true) + expect( + runner.events.some( + (e) => e.type === 'subagent_updated' && e.update.status === 'completed' + ) + ).toBe(true) + expect(childCalls).toBeGreaterThan(0) + expect(runtime.embeddingService.getStatus()).toBe('uninitialized') + expect(await fs.readdir(modelsPath)).toEqual([]) + + await writeCorruptEmbeddingModel(modelsPath) + const before = await fs.readdir(modelsPath, { recursive: true }) + const resumed = await createAiServiceTestRunner(runtime, { + bindWorkspace: false, + partnerId: 'knowledge-independent', + runId: `${runtime.runId}-continue`, + userInput: '继续确认刚才的结果', + llmScript: { + 'human.brain': [{ output: buildCompleteTaskDecision({ summary: '续接完成' }) }] + } + }) + expect((await resumed.run()).status).toBe('completed') + expect(runtime.embeddingService.getStatus()).toBe('uninitialized') + expect(await fs.readdir(modelsPath, { recursive: true })).toEqual(before) + runtime.assertThat(true, { + name: 'runs-without-embedding', + message: '主运行、子任务与续接无需 embedding，真实文件读取成功且模型目录不变。' + }) + } + }) + }) + }) + + it('ai-run-service-kb-error-continues', async () => { + await withIsolatedModels(async (modelsPath) => { + await runBackendCase({ + caseId: 'ai-run-service-kb-error-continues', + domain: 'ai', + suite: 'human', + groups: ['mock-llm'], + harnessMode: 'mock-llm', + fixtures: [], + runMode: 'single', + description: '真实 KB 模型缺失错误进入模型上下文，后续真实文件读取与交付继续。', + assert: async () => {}, + execute: async (runtime) => { + const sourcePath = path.join(runtime.workspaceRoot, 'source.txt') + await fs.writeFile(sourcePath, 'KB_FAILURE_CONTINUED') + const runner = await createAiServiceTestRunner(runtime, { + bindWorkspace: false, + llmScript: { + 'human.brain': [ + { + output: buildToolDecision({ + toolName: 'kb_search', + args: { queryText: '资料' }, + summary: '查询资料' + }) + }, + (call) => { + expect(call.user).toContain(EMBEDDING_MODEL_NOT_INSTALLED_ERROR) + expect(call.user).toContain('不要继续调用 KB') + return buildToolDecision({ + toolName: 'text_file_read', + args: { sourcePath }, + summary: '读取明确指定的文件' + }) + }, + { output: buildCompleteTaskDecision({ summary: '已读取文件，知识库暂不可用' }) } + ] + } + }) + expect((await runner.run()).status).toBe('completed') + expect( + runner.events.some( + (e) => + e.type === 'tool_call_result' && + e.toolName === 'kb_search' && + e.result?.ok === false + ) + ).toBe(true) + expect( + readLatestToolResultDataFromEvents<{ content: string }>(runner.events, 'text_file_read') + .content + ).toContain('KB_FAILURE_CONTINUED') + expect(runner.events.some((e) => e.type === 'run_failed')).toBe(false) + expect(runtime.embeddingService.getStatus()).toBe('uninitialized') + expect(await fs.readdir(modelsPath)).toEqual([]) + runtime.assertThat(true, { + name: 'kb-error-does-not-fail-run', + message: 'KB 错误已反馈给模型，文件读取与 run 完成，无隐式下载。' + }) + } + }) + }) + }) +}) diff --git a/tests/case/ai/human/mock-llm/approval-denied-restricted-delivery.test.ts b/tests/case/ai/human/mock-llm/approval-denied-restricted-delivery.test.ts index 8ac9322c..b49f4a87 100644 --- a/tests/case/ai/human/mock-llm/approval-denied-restricted-delivery.test.ts +++ b/tests/case/ai/human/mock-llm/approval-denied-restricted-delivery.test.ts @@ -21,6 +21,7 @@ describe('ai human mock-llm backend', () => { fixtures: [], runMode: 'single', execute: async (runtime) => { + await runtime.prepareEmbeddingModel() const blockedPath = path.join(runtime.workspaceRoot, 'blocked-dir') const runner = createHumanTestRunner(runtime, { approvalPolicy: 'deny-medium-high', diff --git a/tests/case/ai/human/mock-llm/human-mixed-tool-dispatch.test.ts b/tests/case/ai/human/mock-llm/human-mixed-tool-dispatch.test.ts index 4c392a18..b99ff8f7 100644 --- a/tests/case/ai/human/mock-llm/human-mixed-tool-dispatch.test.ts +++ b/tests/case/ai/human/mock-llm/human-mixed-tool-dispatch.test.ts @@ -15,6 +15,7 @@ describe('ai human mock-llm backend', () => { fixtures: [], runMode: 'single', execute: async (runtime) => { + await runtime.prepareEmbeddingModel() const runner = createHumanTestRunner(runtime, { structuredOutputScript: { 'human.brain': [ @@ -80,6 +81,7 @@ describe('ai human mock-llm backend', () => { fixtures: [], runMode: 'single', execute: async (runtime) => { + await runtime.prepareEmbeddingModel() const runner = createHumanTestRunner(runtime, { structuredOutputScript: { 'human.brain': [ diff --git a/tests/case/ai/human/mock-llm/human-queued-message-safe-boundary.test.ts b/tests/case/ai/human/mock-llm/human-queued-message-safe-boundary.test.ts index c93524d6..d3a9ff1a 100644 --- a/tests/case/ai/human/mock-llm/human-queued-message-safe-boundary.test.ts +++ b/tests/case/ai/human/mock-llm/human-queued-message-safe-boundary.test.ts @@ -18,6 +18,7 @@ describe('ai human mock-llm backend', () => { fixtures: [], runMode: 'single', execute: async (runtime) => { + await runtime.prepareEmbeddingModel() let hasQueuedMessage = false let queueSubmissionStarted = false let toolResultRecorded = false @@ -126,7 +127,7 @@ describe('ai human mock-llm backend', () => { const toolResults = filterAiRunEventsByType(result.firstEvents, 'tool_call_result') const toolLogEntries = result.firstLog.filter((record) => record.entry.kind === 'tool') runtime.assertThat( - result.firstOutput.status === 'yielded' && + result.firstOutput.status === 'yielded' && result.firstBrainCallCount === 1 && toolResults.some((event) => event.toolName === 'kb_list_documents') && toolLogEntries.some( diff --git a/tests/case/ai/human/mock-llm/multi-tool-collaboration.test.ts b/tests/case/ai/human/mock-llm/multi-tool-collaboration.test.ts index 0dc66ed8..1608ae7a 100644 --- a/tests/case/ai/human/mock-llm/multi-tool-collaboration.test.ts +++ b/tests/case/ai/human/mock-llm/multi-tool-collaboration.test.ts @@ -15,6 +15,7 @@ describe('ai human mock-llm backend', () => { fixtures: [], runMode: 'single', execute: async (runtime) => { + await runtime.prepareEmbeddingModel() await runtime.seedKb([ { id: 'doc-1', diff --git a/tests/case/knowledge/foundation/kb-availability-contract.test.ts b/tests/case/knowledge/foundation/kb-availability-contract.test.ts new file mode 100644 index 00000000..9e9a0743 --- /dev/null +++ b/tests/case/knowledge/foundation/kb-availability-contract.test.ts @@ -0,0 +1,163 @@ +import fs from 'node:fs/promises' +import path from 'node:path' +import { describe, expect, it } from 'vitest' +import { runBackendCase } from '../../../harness/backend/run-backend-case' +import { createRetrievalToolHarness } from '../../../harness/backend/aiToolHarness' +import { + withIsolatedModels, + copyInstalledEmbeddingModel, + writeCorruptEmbeddingModel +} from '../../../harness/backend/modelFixture' +import { ModelService } from '../../../../src/main/services/model/ModelService' +import { VectorModelDownloadService } from '../../../../src/main/services/model/VectorModelDownloadService' +import { DEFAULT_EMBEDDING_MODEL_NAME } from '../../../../src/main/services/vector/EmbeddingService' +import { EMBEDDING_MODEL_NOT_INSTALLED_ERROR } from '../../../../src/main/services/vector/ensureEmbeddingReady' + +describe('knowledge availability through real services', () => { + it('kb-availability-contract', async () => { + await withIsolatedModels(async (modelsPath, sharedModelsPath) => { + await runBackendCase({ + caseId: 'kb-availability-contract', + domain: 'knowledge', + suite: 'foundation', + harnessMode: 'tool-real', + fixtures: [], + runMode: 'single', + description: '真实模型安装门禁、初始化失败、空库、全局网页、删除恢复及索引入口。', + assert: async () => {}, + execute: async (runtime) => { + const harness = createRetrievalToolHarness(runtime, { bindWorkspace: false }) + const modelPath = path.join(modelsPath, DEFAULT_EMBEDDING_MODEL_NAME) + const modelService = ModelService.getInstance() + const assertAllUnavailable = async () => { + const before = await fs.readdir(modelsPath, { recursive: true }) + for (const strategy of ['auto', 'semantic', 'keyword']) { + await expect( + harness.invoke('kb_search', { queryText: '资料', strategy }) + ).rejects.toThrow(EMBEDDING_MODEL_NOT_INSTALLED_ERROR) + } + await expect(harness.invoke('kb_list_documents', {})).rejects.toThrow( + EMBEDDING_MODEL_NOT_INSTALLED_ERROR + ) + expect(runtime.embeddingService.getStatus()).toBe('uninitialized') + expect(await fs.readdir(modelsPath, { recursive: true })).toEqual(before) + } + await assertAllUnavailable() + await fs.mkdir(modelPath, { recursive: true }) + await fs.writeFile(path.join(modelPath, 'config.json'), '{}') + await assertAllUnavailable() + + const sourcePath = path.join(runtime.workspaceRoot, 'source.txt') + await fs.writeFile(sourcePath, '索引输入') + await expect( + runtime.workspaceKnowledgePrepareService.indexLocalFile({ + workspaceId: 'source', + documentId: 'source', + documentName: 'source.txt', + filePath: sourcePath + }) + ).rejects.toThrow(EMBEDDING_MODEL_NOT_INSTALLED_ERROR) + await expect( + runtime.workspaceKnowledgePrepareService.indexWebText({ + sourceType: 'web', + workspaceId: '', + documentId: 'web-source', + documentName: '网页', + sourceUrl: 'https://example.com/source', + rawText: '网页输入', + contentHash: 'web-hash' + }) + ).rejects.toThrow(EMBEDDING_MODEL_NOT_INSTALLED_ERROR) + expect( + (await runtime.documentsStore.listDocuments({ page: 1, pageSize: 20 })).total + ).toBe(0) + + await writeCorruptEmbeddingModel(modelsPath) + await fs.writeFile( + path.join(modelPath, '.download-state.json'), + JSON.stringify({ repoId: DEFAULT_EMBEDDING_MODEL_NAME, completedFiles: [] }) + ) + expect(modelService.isModelDownloaded(DEFAULT_EMBEDDING_MODEL_NAME)).toBe(false) + await assertAllUnavailable() + await fs.rm(path.join(modelPath, '.download-state.json')) + expect(modelService.isModelDownloaded(DEFAULT_EMBEDDING_MODEL_NAME)).toBe(true) + await expect(harness.invoke('kb_list_documents', {})).rejects.toThrow( + '向量模型初始化失败' + ) + expect(runtime.embeddingService.getStatus()).toBe('error') + await runtime.embeddingService.close() + await fs.rm(modelPath, { recursive: true, force: true }) + + await copyInstalledEmbeddingModel(modelsPath, sharedModelsPath) + for (const strategy of ['auto', 'semantic', 'keyword']) { + expect( + await harness.invoke('kb_search', { queryText: '不存在的资料', strategy }) + ).toEqual({ items: [], total: 0 }) + } + expect(await harness.invoke('kb_list_documents', {})).toEqual({ items: [], total: 0 }) + await runtime.seedKb([ + { + id: 'global-web', + name: '全局网页', + sourceType: 'web', + sourceUrl: 'https://example.com/global', + chunks: [{ id: 'global-chunk', text: '全局网页包含知识库可用性边界资料。' }] + } + ]) + expect((await runtime.storageService.workspace.listWorkspaces()).length).toBe(0) + const webResult = await harness.invoke<{ + items: Array<{ sourceUrl?: string }> + total: number + }>('kb_search', { queryText: '全局网页', strategy: 'auto', sourceType: 'web' }) + expect(webResult.total).toBeGreaterThan(0) + expect(webResult.items[0].sourceUrl).toBe('https://example.com/global') + for (const strategy of ['auto', 'semantic', 'keyword']) { + for (const documentIds of [[], ['missing-document']]) { + expect( + await harness.invoke('kb_search', { queryText: '全局网页', strategy, documentIds }) + ).toEqual({ items: [], total: 0 }) + } + } + expect( + await harness.invoke('kb_search', { + queryText: 'NO_MATCH_XYZ_314159', + strategy: 'keyword' + }) + ).toEqual({ items: [], total: 0 }) + expect( + await harness.invoke('kb_list_documents', { documentIds: ['missing-document'] }) + ).toEqual({ items: [], total: 0 }) + + // A runtime cache must not bypass a fresh installation check. + await fs.rename(modelPath, `${modelPath}-hidden`) + await expect( + harness.invoke('kb_search', { queryText: '全局网页', strategy: 'keyword' }) + ).rejects.toThrow(EMBEDDING_MODEL_NOT_INSTALLED_ERROR) + await fs.rename(`${modelPath}-hidden`, modelPath) + const downloadService = VectorModelDownloadService.getInstance({ + modelService, + embeddingService: runtime.embeddingService + }) + expect(await downloadService.deleteModel(DEFAULT_EMBEDDING_MODEL_NAME)).toEqual({ + success: true + }) + expect(runtime.embeddingService.getStatus()).toBe('uninitialized') + await assertAllUnavailable() + await copyInstalledEmbeddingModel(modelsPath, sharedModelsPath) + expect( + ( + await harness.invoke<{ items: Array<{ id: string }>; total: number }>( + 'kb_list_documents', + {} + ) + ).total + ).toBe(1) + runtime.assertThat(true, { + name: 'kb-availability-boundaries', + message: '模型不可用明确失败；空库正常为空；全局网页与删除恢复可用；未触发隐式下载。' + }) + } + }) + }) + }) +}) diff --git a/tests/case/knowledge/foundation/kb-indexing-blocks-search.test.ts b/tests/case/knowledge/foundation/kb-indexing-blocks-search.test.ts index 0ff3e6a8..7abfde25 100644 --- a/tests/case/knowledge/foundation/kb-indexing-blocks-search.test.ts +++ b/tests/case/knowledge/foundation/kb-indexing-blocks-search.test.ts @@ -1,4 +1,4 @@ -import { describe, it } from 'vitest' +import { describe, expect, it } from 'vitest' import { buildModelToolResultDelivery } from '../../../../src/main/services/ai/human/shared/modelToolResult' import { buildKbCapabilityTools, @@ -65,6 +65,33 @@ describe('knowledge foundation', () => { (error: unknown) => (error instanceof Error ? error.message : String(error)) ) + const jobStore = runtime.storageService.workspaceIndexJob + const baseJob = await jobStore.getJobById('kb-indexing-running-prepare') + if (!baseJob) throw new Error('missing prepare job') + await jobStore.saveJob({ ...baseJob, source_kind: 'web' }) + for (const name of ['kb_search', 'kb_list_documents'] as const) { + await expect( + invokeTool(ctx, name, name === 'kb_search' ? { queryText: '合同' } : {}) + ).rejects.toThrow(KB_INDEXING_IN_PROGRESS_ERROR) + } + await runtime.prepareEmbeddingModel() + for (const action of ['scan', 'prepare'] as const) { + for (const status of ['succeeded', 'failed', 'cancelled'] as const) { + await jobStore.saveJob({ ...baseJob, action, status }) + expect(await invokeTool(ctx, 'kb_search', { queryText: '合同' })).toEqual({ + items: [], + total: 0 + }) + expect(await invokeTool(ctx, 'kb_list_documents', {})).toEqual({ items: [], total: 0 }) + } + } + await jobStore.saveJob({ ...baseJob, action: 'scan', status: 'running' }) + expect(await invokeTool(ctx, 'kb_search', { queryText: '合同' })).toEqual({ + items: [], + total: 0 + }) + expect(await invokeTool(ctx, 'kb_list_documents', {})).toEqual({ items: [], total: 0 }) + const deliveries = [] for (const toolName of ['kb_search', 'kb_list_documents'] as const) { const delivery = await buildModelToolResultDelivery({ @@ -100,7 +127,10 @@ describe('knowledge foundation', () => { runtime.assertThat( result.deliveries.length === 2 && result.deliveries.every( - (item) => item.ok === false && item.content === MODEL_FACING_INDEXING_ERROR + (item) => + item.ok === false && + item.content.startsWith(MODEL_FACING_INDEXING_ERROR) && + item.content.includes('不要继续调用 KB') ), { name: 'indexing-error-is-model-facing', diff --git a/tests/case/knowledge/foundation/prepare-workspaces-sequentially.test.ts b/tests/case/knowledge/foundation/prepare-workspaces-sequentially.test.ts index 9701fe6f..8e4b7da3 100644 --- a/tests/case/knowledge/foundation/prepare-workspaces-sequentially.test.ts +++ b/tests/case/knowledge/foundation/prepare-workspaces-sequentially.test.ts @@ -17,7 +17,7 @@ describe('knowledge foundation', () => { fixtures: [], runMode: 'single', execute: async (runtime) => { - await runtime.ensureEmbeddingReady() + await runtime.prepareEmbeddingModel() const prepareService = new WorkspaceKnowledgePrepareService({ embeddingService: runtime.embeddingService, documentsStore: runtime.documentsStore, @@ -73,8 +73,7 @@ describe('knowledge foundation', () => { ) runtime.assertThat(result.cancelCalls.join(',') === 'ws-a', { name: 'prepare-stops-after-cancelled', - message: - '首个地址 cancelled 后不得再启动后续地址，对齐 SET-WORKSPACE-004-AC15。', + message: '首个地址 cancelled 后不得再启动后续地址，对齐 SET-WORKSPACE-004-AC15。', data: result }) } diff --git a/tests/case/unit/ai/kb-retrieval-errors.test.ts b/tests/case/unit/ai/kb-retrieval-errors.test.ts new file mode 100644 index 00000000..cc720841 --- /dev/null +++ b/tests/case/unit/ai/kb-retrieval-errors.test.ts @@ -0,0 +1,42 @@ +import { describe, expect, it, vi } from 'vitest' +import { buildKbCapabilityTools } from '../../../../src/main/services/ai/human/tools/kb/retrievalTools' +import { runBackendCase } from '../../../harness/backend/run-backend-case' + +describe('KB query failures', () => { + it('never falls back to keyword search after an embedding failure', async () => { + await runBackendCase({ + caseId: 'kb-retrieval-errors', + domain: 'unit', + suite: 'ai', + harnessMode: 'tool-real', + fixtures: [], + runMode: 'single', + description: '向量计算故障不能变成关键词结果。', + assert: async () => {}, + execute: async (runtime) => { + const ctx = runtime.createAiRunContext() + // Unit-only fault injection isolates the query failure from availability checks. + const available = vi.spyOn(ctx, 'assertKbAvailable').mockResolvedValue(undefined) + const embed = vi + .spyOn(runtime.embeddingService, 'embed') + .mockRejectedValue(new Error('embedding computation failed')) + const keyword = vi.spyOn(runtime.documentsStore, 'ftsSearch') + try { + const search = buildKbCapabilityTools({ ctx, runId: runtime.runId }).find( + (tool) => tool.name === 'kb_search' + )! + for (const strategy of ['auto', 'semantic']) { + await expect(search.invoke({ queryText: 'query', strategy })).rejects.toThrow( + 'embedding computation failed' + ) + } + expect(keyword).not.toHaveBeenCalled() + } finally { + available.mockRestore() + embed.mockRestore() + keyword.mockRestore() + } + } + }) + }) +}) diff --git a/tests/case/unit/ai/persistence/chat-run-service-contract.test.ts b/tests/case/unit/ai/persistence/chat-run-service-contract.test.ts index 2090aac7..7c724f10 100644 --- a/tests/case/unit/ai/persistence/chat-run-service-contract.test.ts +++ b/tests/case/unit/ai/persistence/chat-run-service-contract.test.ts @@ -1045,29 +1045,19 @@ describe('unit ai persistence backend', () => { ) it('autostart-run-emits-process-events-after-run-started', async () => { - const previousTimeout = process.env.NCURATOR_AI_EMBEDDING_PREFLIGHT_TIMEOUT_MS - process.env.NCURATOR_AI_EMBEDDING_PREFLIGHT_TIMEOUT_MS = '10' - try { - const setup = await createTestService({ autoStartRuns: true }) - const run = await submitAiRun(setup) + const setup = await createTestService({ autoStartRuns: true }) + const run = await submitAiRun(setup) - await waitForCondition(() => - setup.events.some((event) => event.type === 'assistant_process_group_started') - ) - await waitForCondition(() => setup.events.some((event) => event.type === 'run_failed')) + await waitForCondition(() => + setup.events.some((event) => event.type === 'assistant_process_group_started') + ) + await waitForCondition(() => setup.events.some((event) => event.type === 'run_failed')) - const storedRun = await setup.storage.aiRun.getRun(run.id) + const storedRun = await setup.storage.aiRun.getRun(run.id) - expect(setup.events.map((event) => event.type)).toContain('run_started') - expect(setup.events.map((event) => event.type)).toContain('assistant_process_group_started') - expect(storedRun?.status).toBe('failed') - } finally { - if (previousTimeout === undefined) { - delete process.env.NCURATOR_AI_EMBEDDING_PREFLIGHT_TIMEOUT_MS - } else { - process.env.NCURATOR_AI_EMBEDDING_PREFLIGHT_TIMEOUT_MS = previousTimeout - } - } + expect(setup.events.map((event) => event.type)).toContain('run_started') + expect(setup.events.map((event) => event.type)).toContain('assistant_process_group_started') + expect(storedRun?.status).toBe('failed') }) it('does-not-attribute-uncontrolled-workspace-changes-when-a-run-finishes', async () => { diff --git a/tests/case/unit/knowledge/vector/embedding-service.test.ts b/tests/case/unit/knowledge/vector/embedding-service.test.ts index a995256d..982639df 100644 --- a/tests/case/unit/knowledge/vector/embedding-service.test.ts +++ b/tests/case/unit/knowledge/vector/embedding-service.test.ts @@ -1,5 +1,8 @@ import { describe, expect, it, vi } from 'vitest' -import { EmbeddingService, type EmbeddingExecutor } from '../../../../../src/main/services/vector/EmbeddingService' +import { + EmbeddingService, + type EmbeddingExecutor +} from '../../../../../src/main/services/vector/EmbeddingService' const result = { data: new Float32Array([1, 2]), @@ -79,3 +82,24 @@ describe('EmbeddingService', () => { expect(initialize).toHaveBeenCalledTimes(2) }) }) + +it('waits for initialization before closing and clears the ready cache', async () => { + let finish!: () => void + const executor: EmbeddingExecutor = { + initialize: () => + new Promise((resolve) => { + finish = resolve + }), + embed: async () => result, + close: vi.fn(async () => undefined) + } + const service = new EmbeddingService({ executor }) + const loading = service.initialize() + const closing = service.close() + expect(executor.close).not.toHaveBeenCalled() + finish() + await loading + await closing + expect(executor.close).toHaveBeenCalledTimes(1) + expect(service.getStatus()).toBe('uninitialized') +}) diff --git a/tests/case/unit/knowledge/vector/vector-download-service-contract.test.ts b/tests/case/unit/knowledge/vector/vector-download-service-contract.test.ts index 8e7b8206..c8491e50 100644 --- a/tests/case/unit/knowledge/vector/vector-download-service-contract.test.ts +++ b/tests/case/unit/knowledge/vector/vector-download-service-contract.test.ts @@ -101,7 +101,7 @@ describe('unit vector download service contract', () => { return { success: true } } ) - vi.spyOn(embeddingService, 'initialize').mockResolvedValue() + const initializeSpy = vi.spyOn(embeddingService, 'initialize') const unsubscribe = service.onProgress((payload) => { progressEvents.push(payload) @@ -112,6 +112,8 @@ describe('unit vector download service contract', () => { releaseFirstDownload?.() const firstResult = await firstTask unsubscribe() + if (initializeSpy.mock.calls.length !== 0) + throw new Error('download must not initialize embedding') return { firstResult, @@ -234,7 +236,7 @@ describe('unit vector download service contract', () => { } ) const deleteSpy = vi.spyOn(modelService, 'deleteModel').mockResolvedValue({ success: true }) - vi.spyOn(embeddingService, 'initialize').mockResolvedValue() + const initializeSpy = vi.spyOn(embeddingService, 'initialize') const unsubscribe = service.onProgress((payload) => { progressEvents.push(payload) @@ -246,6 +248,8 @@ describe('unit vector download service contract', () => { const deleteResult = await service.deleteModel(REPO_A) const downloadResult = await downloadTask unsubscribe() + if (initializeSpy.mock.calls.length !== 0) + throw new Error('download must not initialize embedding') return { downloadResult, @@ -375,7 +379,7 @@ describe('unit vector download service contract', () => { return { success: true } }) vi.spyOn(modelService, 'isModelDownloaded').mockReturnValue(false) - vi.spyOn(embeddingService, 'initialize').mockResolvedValue() + const initializeSpy = vi.spyOn(embeddingService, 'initialize') const unsubscribe = service.onProgress((payload) => { progressEvents.push(payload) @@ -395,6 +399,8 @@ describe('unit vector download service contract', () => { } await waitForCondition(() => service.getActiveDownload() === null) unsubscribe() + if (initializeSpy.mock.calls.length !== 0) + throw new Error('download must not initialize embedding') return { resumedRepoId: downloadSpy.mock.calls[0]?.[0] || '', diff --git a/tests/case/workbench/conversation/composer/chat-without-knowledge-model.e2e.test.ts b/tests/case/workbench/conversation/composer/chat-without-knowledge-model.e2e.test.ts new file mode 100644 index 00000000..af72df12 --- /dev/null +++ b/tests/case/workbench/conversation/composer/chat-without-knowledge-model.e2e.test.ts @@ -0,0 +1,83 @@ +import fs from 'node:fs/promises' +import os from 'node:os' +import path from 'node:path' +import { describe, it } from 'vitest' +import { runE2ECase } from '../../../../harness/e2e/run-e2e-case' +import { + WORKBENCH_LIVE_AI_E2E_TIMEOUT_MS, + configureLiveModelThroughSettingsUi, + createPartnerThroughWorkbenchUi, + navigateToWorkbench, + selectWorkbenchModel, + sendWorkbenchMessage, + waitForWorkbenchAiRunCompletion, + loadWorkbenchLiveModelEnv +} from '../../../../harness/e2e/workbench' + +const CASE_ID = 'chat-without-knowledge-model' + +describe('workbench conversation', () => { + it( + CASE_ID, + async () => { + const modelsPath = await fs.mkdtemp(path.join(os.tmpdir(), 'ncurator-chat-empty-models-')) + try { + await runE2ECase({ + caseId: CASE_ID, + domain: 'workbench', + suite: 'conversation', + groups: ['composer'], + description: '无工作空间、无向量模型仍可完成真实聊天，且不下载或启动 embedding。', + fixtures: [], + serviceMode: 'real', + execution: 'live', + windowMode: 'background', + runMode: 'single', + extraEnv: { NCURATOR_MODELS_PATH: modelsPath }, + execute: async (runtime) => { + const { page } = runtime + const target = loadWorkbenchLiveModelEnv() + await configureLiveModelThroughSettingsUi(page, target) + await navigateToWorkbench(page) + await createPartnerThroughWorkbenchUi(page, '普通聊天') + await selectWorkbenchModel(page, target.modelName) + const startedAt = Date.now() + await sendWorkbenchMessage(page, '你好，请用一句话回复我。') + const evidence = await waitForWorkbenchAiRunCompletion( + runtime, + startedAt, + target.modelName + ) + const state = await page.evaluate(async () => ({ + embedding: await window.api.getEmbeddingStatus(), + download: await window.api.getActiveDownload() + })) + return { + state, + files: await fs.readdir(modelsPath, { recursive: true }), + completed: evidence.events.some((event) => event.type === 'run_completed') + } + }, + assert: async (result, runtime) => { + await runtime.assertThat( + result.completed && + result.files.length === 0 && + result.state.download === null && + result.state.embedding.status === 'uninitialized' && + result.state.embedding.pid === null, + { + name: 'chat-without-knowledge-model', + message: + '真实聊天完成，空模型目录未变化、无下载任务或 embedding 进程，对齐 WB-COMPOSER-001-AC5。', + data: result + } + ) + } + }) + } finally { + await fs.rm(modelsPath, { recursive: true, force: true }) + } + }, + WORKBENCH_LIVE_AI_E2E_TIMEOUT_MS + ) +}) diff --git a/tests/harness/backend/aiServiceHarness.ts b/tests/harness/backend/aiServiceHarness.ts index a1ae7414..16f8de54 100644 --- a/tests/harness/backend/aiServiceHarness.ts +++ b/tests/harness/backend/aiServiceHarness.ts @@ -5,6 +5,7 @@ import { AiRunService } from '../../../src/main/services/ai/AiRunService' import { AiFileChangeService } from '../../../src/main/services/ai/fileChanges/AiFileChangeService' import { createScriptedStructuredOutputDriver } from './scriptedStructuredOutputDriver' import type { BackendTestRuntime, CreateAiRunContextInput } from './test-types' +import { ensureEmbeddingReady } from '../../../src/main/services/vector/ensureEmbeddingReady' import type { AiRunStartPayload, AiRunDeps } from '../../../src/main/services/ai/types' /** Uses the same top-level runtime as ChatRunService, including subagent dispatch and cleanup. */ @@ -39,7 +40,8 @@ export const createAiServiceTestRunner = async ( chatMessageLogStore: runtime.storageService.chatMessageLog, documentsStore: runtime.documentsStore, embeddingService: runtime.embeddingService, - ensureEmbeddingReady: runtime.ensureEmbeddingReady, + ensureEmbeddingReady: () => + ensureEmbeddingReady({ embeddingService: runtime.embeddingService }), docxApplyService: runtime.docxApplyService, saveFileChangeRecord: (record) => files.saveRecord(record), listFileChangeRecords: async (request) => (await files.listRecords(request)).items, @@ -91,7 +93,8 @@ export const createChatServiceTestRunner = async ( workspaceStore: runtime.storageService.workspace, workspaceIndexJobStore: runtime.storageService.workspaceIndexJob, webSourceStore: runtime.storageService.webSource, - ensureEmbeddingReady: runtime.ensureEmbeddingReady, + ensureEmbeddingReady: () => + ensureEmbeddingReady({ embeddingService: runtime.embeddingService }), docxApplyService: runtime.docxApplyService, aiFileChangeService: files, runResourceManager: new AiRunResourceManager(), diff --git a/tests/harness/backend/humanHarness.ts b/tests/harness/backend/humanHarness.ts index 706cca48..b137f158 100644 --- a/tests/harness/backend/humanHarness.ts +++ b/tests/harness/backend/humanHarness.ts @@ -1,5 +1,4 @@ import { createHumanGraphRunner } from '../../../src/main/services/ai/human/graph/humanGraph' -import { runAiRuntimePreflight } from '../../../src/main/services/ai/runtimePreflight' import { AiRunResourceManager } from '../../../src/main/services/ai/run/AiRunResourceManager' import { releaseDocxRunSession } from '../../../src/main/services/ai/human/tools/docx/worker/docxWorkerClient' import { releasePdfRunSession } from '../../../src/main/services/pdf/worker/pdfWorkerClient' @@ -27,9 +26,6 @@ export const createHumanTestRunner = ( ctx, runner: run, run: async (taskInput: HumanTaskInput, dispatchOptions?: HumanRunDispatchOptions) => { - await runAiRuntimePreflight({ - ensureEmbeddingReady: runtime.ensureEmbeddingReady - }) try { return (await run(taskInput, dispatchOptions)) as HumanTaskOutput } finally { diff --git a/tests/harness/backend/modelFixture.ts b/tests/harness/backend/modelFixture.ts new file mode 100644 index 00000000..41efa64d --- /dev/null +++ b/tests/harness/backend/modelFixture.ts @@ -0,0 +1,66 @@ +import fs from 'node:fs/promises' +import { constants } from 'node:fs' +import os from 'node:os' +import path from 'node:path' +import { getModelsPath } from '../../../src/main/utils/paths' +import { ModelService } from '../../../src/main/services/model/ModelService' +import { DEFAULT_EMBEDDING_MODEL_NAME } from '../../../src/main/services/vector/EmbeddingService' + +/** Isolates real model files without replacing production availability checks. */ +export const withIsolatedModels = async ( + run: (modelsPath: string, sharedModelsPath: string) => Promise +): Promise => { + const previous = process.env.NCURATOR_MODELS_PATH + const sharedModelsPath = getModelsPath() + const modelsPath = await fs.mkdtemp(path.join(os.tmpdir(), 'ncurator-model-boundary-')) + process.env.NCURATOR_MODELS_PATH = modelsPath + try { + await run(modelsPath, sharedModelsPath) + } finally { + if (previous === undefined) delete process.env.NCURATOR_MODELS_PATH + else process.env.NCURATOR_MODELS_PATH = previous + await fs.rm(modelsPath, { recursive: true, force: true }) + } +} + +/** Explicit test setup; KB calls never download a missing model. */ +export const copyInstalledEmbeddingModel = async ( + modelsPath: string, + sharedModelsPath: string +): Promise => { + process.env.NCURATOR_MODELS_PATH = sharedModelsPath + try { + const service = ModelService.getInstance() + if (!service.isModelDownloaded(DEFAULT_EMBEDDING_MODEL_NAME)) { + await service.downloadModel(DEFAULT_EMBEDDING_MODEL_NAME) + } + await fs.cp( + path.join(sharedModelsPath, DEFAULT_EMBEDDING_MODEL_NAME), + path.join(modelsPath, DEFAULT_EMBEDDING_MODEL_NAME), + { recursive: true, mode: constants.COPYFILE_FICLONE } + ) + } finally { + process.env.NCURATOR_MODELS_PATH = modelsPath + } +} + +/** Non-empty required files pass installation checks but fail real Transformers initialization. */ +export const writeCorruptEmbeddingModel = async (modelsPath: string): Promise => { + for (const name of [ + '1_Pooling/config.json', + 'config.json', + 'config_sentence_transformers.json', + 'merges.txt', + 'modules.json', + 'onnx/model.onnx', + 'sentence_bert_config.json', + 'special_tokens_map.json', + 'tokenizer.json', + 'tokenizer_config.json', + 'vocab.json' + ]) { + const target = path.join(modelsPath, DEFAULT_EMBEDDING_MODEL_NAME, name) + await fs.mkdir(path.dirname(target), { recursive: true }) + await fs.writeFile(target, 'invalid model file') + } +} diff --git a/tests/harness/backend/realAiDepsFactory.ts b/tests/harness/backend/realAiDepsFactory.ts index a32cfe94..17887611 100644 --- a/tests/harness/backend/realAiDepsFactory.ts +++ b/tests/harness/backend/realAiDepsFactory.ts @@ -5,7 +5,6 @@ import { AiFileChangeService } from '../../../src/main/services/ai/fileChanges/A import { DocxApplyService } from '../../../src/main/services/ai/human/tools/docx/review/DocxApplyService' import { terminalSessionManager } from '../../../src/main/services/ai/human/tools/terminal/TerminalSessionManager' import { createAiRunContext } from '../../../src/main/services/ai/runtime' -import { runAiRuntimePreflight } from '../../../src/main/services/ai/runtimePreflight' import type { AiApprovalBatchRequest, AiApprovalBatchResult @@ -107,6 +106,7 @@ export type RealAiDepsFactory = { workspaceKnowledgePrepareService: WorkspaceKnowledgePrepareService docxApplyService: DocxApplyService ensureEmbeddingReady: () => Promise + prepareEmbeddingModel: () => Promise createAiRunContext: (input?: CreateAiRunContextInput) => AiRunContext createHumanTaskRunner: ( input?: CreateAiRunContextInput @@ -324,14 +324,18 @@ export const createRealAiDepsFactory = async (input: { workspaceKnowledgePrepareService, docxApplyService, ensureEmbeddingReady: ensureReady, + prepareEmbeddingModel: async () => { + const modelName = embeddingService.getModelName() + if (!modelService.isModelDownloaded(modelName)) { + await modelService.downloadModel(modelName) + } + await ensureReady() + }, createAiRunContext: createContext, createHumanTaskRunner: (contextInput = {}) => { const ctx = createContext(contextInput) const run = createHumanGraphRunner({ ctx }) return async (taskInput, options) => { - await runAiRuntimePreflight({ - ensureEmbeddingReady: ensureReady - }) return await run(taskInput, options) } }, diff --git a/tests/harness/backend/realAiHarness.ts b/tests/harness/backend/realAiHarness.ts index 1e46ac8c..e230f733 100644 --- a/tests/harness/backend/realAiHarness.ts +++ b/tests/harness/backend/realAiHarness.ts @@ -87,8 +87,9 @@ export const createRealAiHarness = async (input: { ensureEmbeddingReady: async () => { await depsFactory.ensureEmbeddingReady() }, + prepareEmbeddingModel: depsFactory.prepareEmbeddingModel, seedKb: async (documents) => { - await depsFactory.ensureEmbeddingReady() + await depsFactory.prepareEmbeddingModel() await seedKbFixture({ documentsStore: depsFactory.storageService.documents, embeddingService: depsFactory.embeddingService, @@ -97,7 +98,7 @@ export const createRealAiHarness = async (input: { appendSeedKbDocuments(seedManifest, documents) }, seedWorkspaceKb: async (params) => { - await depsFactory.ensureEmbeddingReady() + await depsFactory.prepareEmbeddingModel() const seeded = await seedWorkspaceKb({ runtime, params diff --git a/tests/harness/backend/test-types.ts b/tests/harness/backend/test-types.ts index 50485e37..cb457681 100644 --- a/tests/harness/backend/test-types.ts +++ b/tests/harness/backend/test-types.ts @@ -239,6 +239,7 @@ export type BackendTestRuntime = { createAiRunContext: (input?: CreateAiRunContextInput) => AiRunContext createHumanTaskRunner: (input?: CreateAiRunContextInput) => HumanTaskRunner ensureEmbeddingReady: () => Promise + prepareEmbeddingModel: () => Promise seedKb: (input: readonly SeedKbDocumentInput[]) => Promise seedWorkspaceKb: (input: WorkspaceKbSeedInput) => Promise seedChatHistory: (input: SeedChatHistoryInput) => Promise