diff --git a/.agents/notes/implemented/feature/2026-07-27-web-session-search.i18n.yaml b/.agents/notes/implemented/feature/2026-07-27-web-session-search.i18n.yaml index 6124b31fb4..c17f464bc5 100644 --- a/.agents/notes/implemented/feature/2026-07-27-web-session-search.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-27-web-session-search.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-27-web-session-search.md -2026-07-27-web-session-search.md: 8992fdf046c1256ab61278cf5189ba56df8b4ecd -2026-07-27-web-session-search.zh.md: 764e9f3363ae321c55e401cc52b35dcba790a0b4 +2026-07-27-web-session-search.md: a709719a04a787d9bfcbba0d73263abd84fabcc1 +2026-07-27-web-session-search.zh.md: 980e2638e5a2a819433525c26e0f336c08384409 diff --git a/.agents/notes/implemented/feature/2026-07-27-web-session-search.md b/.agents/notes/implemented/feature/2026-07-27-web-session-search.md index 8992fdf046..a709719a04 100644 --- a/.agents/notes/implemented/feature/2026-07-27-web-session-search.md +++ b/.agents/notes/implemented/feature/2026-07-27-web-session-search.md @@ -12,9 +12,9 @@ The Web sidebar exposes session titles and Workspace membership but cannot retri The shared Web/headless composition mounts [`@deepseek-ai/dsh-session-query-sqlite`](../../../../packages/session-query/session-query-sqlite/README.md) with `openAt: first-search` and an in-memory database. The service is ACTIVE at boot, while its `node:sqlite` module and connection-private handle open only on the first content query. This keeps Node 22 startup output free of SQLite's experimental warning before search is used without promising to suppress the warning when search first imports the module. Each service instance owns its index, preserving the SQLite backend's single-owner contract across parallel CLI or Web invocations without leaving process-scoped derived files behind. The database starts empty and lazily reconciles live and persisted sessions on that first query. It remains a disposable derived index, separate from canonical JSONL persistence. -The host gateway exposes `session.search` through the existing typed RPC stack. It derives the authorization set from the same visible summaries as `session.list`, asks `ctx.sessionQuery.searchSessions` for globally ranked current-surface `user/message`, `assistant/message`, and `steering/message` matches in pages capped at 20 hits, and consumes provider pages until it has 20 authorized sessions plus one lookahead or exhausts the stream. Every hit's session id, best-match session id, surface, event type, and snippet type are revalidated before its snippet leaves the Host, and emitted snippets contain at most 240 Unicode code points. Keeping the potentially large authorization set out of SQLite bindings avoids the portable variable ceiling while preserving global ranking. The response remains one bounded page; `hasMore` tells the UI to ask for a narrower query rather than exposing pagination. A stale continuation discards the current attempt's partial results, deduplication entries, and cursors, then restarts from the first page against the original visibility snapshot. Those retries share the limit of 100 provider calls (and therefore at most 2,000 inspected hits); an oversized page, a repeated continuation cursor, or a still-unexhausted stream at that call budget fails closed as an `internal` business error. The carrier signal cancels superseded work, including persistence listing, bounded batches of cold-session metadata stats, and each provider call, and wins over a concurrent stale rejection. A missing query service or an unrecovered indexing/query failure remains a business error and does not mutate the canonical session store. +The host gateway exposes `session.search` through the existing typed RPC stack. It derives the authorization set from the same visible summaries as `session.list`, asks `ctx.sessionQuery.searchSessions` for globally ranked current-surface `user/message`, `assistant/message`, and `steering/message` matches, and consumes provider pages until it has 20 authorized sessions plus one lookahead or exhausts the stream. The first provider page requests 20 hits; a first-page `SESSION_QUERY_INVALID_LIMIT` halves that size through 10, 5, 2, and 1, retaining the learned size across continuations and stale-generation restarts. Every hit's session id, best-match session id, surface, event type, and snippet type are revalidated before its snippet leaves the Host, and emitted snippets contain at most 240 Unicode code points; the wire response schema independently enforces the same code-point bound at client parse. Keeping the potentially large authorization set out of SQLite bindings avoids the portable variable ceiling while preserving global ranking. The response remains one bounded page; `hasMore` tells the UI to ask for a narrower query rather than exposing pagination. A stale continuation discards the current attempt's partial results, deduplication entries, and cursors, then restarts from the first page against the original visibility snapshot. Limit probes and stale retries share the limit of 100 provider calls (and therefore at most 2,000 inspected hits); a page larger than its requested limit, a repeated continuation cursor, or a still-unexhausted stream at that call budget fails closed as an `internal` business error. The carrier signal cancels superseded work, including persistence listing, bounded batches of cold-session metadata stats, and each provider call, and wins over a concurrent limit or stale rejection. A missing query service or an unrecovered indexing/query failure remains a business error and does not mutate the canonical session store. -[`WorkspaceBrowser`](../../../../packages/client/ui-workspace/README.md) keeps metadata and content search deliberately separate. A non-blank query immediately computes case-insensitive title and Workspace substring matches from the Session list, starts a 250 ms debounced content request, aborts the preceding request when the query changes, and ignores stale completions. It merges local matches first in recency order with backend-ranked content-only matches, deduplicates by session id, and renders a flat list regardless of the normal grouping mode. Each row shows the title, Workspace, and an available one-line snippet. Selecting a row opens the Session only and preserves the query; it does not navigate to an exact event. +[`WorkspaceBrowser`](../../../../packages/client/ui-workspace/README.md) keeps metadata and content search deliberately separate. Its default copy is English, and its input plus defensive request path remove NUL and cap queries at the request schema's 500 UTF-16 code units without splitting a surrogate pair. A non-blank query immediately computes case-insensitive title and Workspace substring matches from the Session list, starts a 250 ms debounced content request, aborts the preceding request when the query changes, and ignores stale completions. It merges local matches first in recency order with backend-ranked content-only matches, deduplicates by session id, and renders a flat list regardless of the normal grouping mode. Each row shows the title, Workspace, and an available one-line snippet. Selecting a row opens the Session only and preserves the query; it does not navigate to an exact event. Content matching inherits the SQLite backend's normalized literal token/phrase semantics. FTS5 operators are inert data, and this surface adds no typo, fuzzy, prefix, or arbitrary-substring expansion. In particular, the `unicode61` tokenizer may treat an uninterrupted Chinese sequence as one token, so a shorter query such as `搜索` is not guaranteed to match inside `会话搜索功能`. Title and Workspace matching remains ordinary client-side substring matching. @@ -39,4 +39,4 @@ The first content query can take longer because it imports and opens SQLite befo ## Testing -Host tests pin request validation, visible-session filtering, event/surface filters, result and snippet bounds, the shared provider-call budget, stale-generation restarts, cursor and cross-page deduplication behavior, continuation-page cancellation, and failure mapping. SQLite lifecycle tests pin eager activation, first-search opening and failure, shared readiness, and unopened disposal; a Node 22 compatibility subprocess pins warning-free mount and disposal before the first search. Runtime and UI tests pin stateless delegation, debounce/abort/stale-response behavior, local fallback, merge order, deduplication, row rendering, and navigation semantics. A keyless assembled Web test seeds an unopened persisted conversation, finds it by message content through the lazy SQLite index, captures the sidebar result, opens it, and verifies that the query remains. +Host tests pin request and response validation, visible-session filtering, event/surface filters, result and snippet bounds, adaptive provider limits inside the shared call budget, learned-limit stale restarts, cursor and cross-page deduplication behavior, cancellation precedence, and failure mapping. SQLite lifecycle tests pin eager activation, first-search opening and failure, shared readiness, and unopened disposal; the Node 22 compatibility gate builds the CLI and Web artifacts, boots the shipped `dsh web`/`AppCLIEntry` composition under plain Node with ambient warning suppression removed and an isolated temporary home/provider environment, waits for settled startup, and disposes it through the shipped signal path. Fixture, runtime, and UI tests pin match-centered bounded snippets, stateless delegation, the 500-code-unit query boundary, debounce/abort/stale-response behavior, local fallback, merge order, deduplication, English copy, row rendering, and navigation semantics. A keyless assembled Web test preserves the lazy-open config while seeding an unopened persisted conversation, finds it by message content through the SQLite index, captures the sidebar result, opens it, and verifies that the query remains. diff --git a/.agents/notes/implemented/feature/2026-07-27-web-session-search.zh.md b/.agents/notes/implemented/feature/2026-07-27-web-session-search.zh.md index 764e9f3363..980e2638e5 100644 --- a/.agents/notes/implemented/feature/2026-07-27-web-session-search.zh.md +++ b/.agents/notes/implemented/feature/2026-07-27-web-session-search.zh.md @@ -12,9 +12,9 @@ Web 侧边栏会展示会话标题及其 Workspace 归属，但无法根据只 Web 与 headless 共用的组合会使用 `openAt: first-search` 和内存数据库挂载 [`@deepseek-ai/dsh-session-query-sqlite`](../../../../packages/session-query/session-query-sqlite/README.md)。服务启动时处于 ACTIVE 状态，而其 `node:sqlite` 模块与连接私有句柄分别要到首次内容查询才会导入和打开。这让 Node 22 的启动输出在使用搜索前不会出现 SQLite 实验性警告，但并不承诺在首次搜索导入该模块时抑制警告。每个服务实例都独占自己的索引，因此并行 CLI 或 Web 调用可维持 SQLite 后端的单一所有者契约，又不会留下进程级派生文件。数据库从空状态启动，并在该首次查询时惰性对齐实时会话与持久化会话。它仍是与规范 JSONL 持久化相互独立的可丢弃派生索引。 -宿主网关通过现有的类型化 RPC 栈公开 `session.search`。它根据 `session.list` 使用的同一组可见摘要推导授权集合，向 `ctx.sessionQuery.searchSessions` 请求全局排序后的当前 surface `user/message`、`assistant/message` 和 `steering/message` 匹配项（每页最多 20 个命中），并持续消费提供方分页，直到获得 20 个已授权会话及一个前瞻项，或结果流耗尽。每个命中的会话 id、最佳匹配会话 id、surface、事件类型和 snippet 类型都会经过重新校验，其 snippet 才能离开宿主，且发出的 snippet 最多包含 240 个 Unicode 码点。将可能很大的授权集合排除在 SQLite 绑定之外，可避开可移植变量上限，同时保持全局排序。响应仍只有一个有界页面；`hasMore` 会指示 UI 提示用户缩小查询范围，而不是公开分页能力。陈旧的续传会丢弃当前尝试的部分结果、去重条目和游标，然后依据原始可见性快照从第一页重新开始。这些重试共用 100 次提供方调用的限制（因此最多检查 2,000 个命中）；如果单页命中数超限、续传游标重复，或用尽该调用预算后结果流仍未耗尽，都会直接返回 `internal` 业务错误，不返回部分结果。载体信号会取消已被取代的工作，包括持久化列表枚举、分批受限执行的冷会话元数据 stat，以及每一次提供方调用；即使同时收到陈旧拒绝，也以取消为准。查询服务缺失或索引／查询故障无法恢复时，仍作为业务错误处理，不会修改规范会话存储。 +宿主网关通过现有的类型化 RPC 栈公开 `session.search`。它根据 `session.list` 使用的同一组可见摘要推导授权集合，向 `ctx.sessionQuery.searchSessions` 请求全局排序后的当前 surface `user/message`、`assistant/message` 和 `steering/message` 匹配项，并持续消费提供方分页，直到获得 20 个已授权会话及一个前瞻项，或结果流耗尽。首个提供方页面请求 20 个命中；如果第一页返回 `SESSION_QUERY_INVALID_LIMIT`，页面大小会依次折半为 10、5、2、1，并在续传和陈旧世代重启中沿用探测所得的大小。每个命中的会话 id、最佳匹配会话 id、surface、事件类型和 snippet 类型都会经过重新校验，其 snippet 才能离开宿主，且发出的 snippet 最多包含 240 个 Unicode 码点；传输响应 schema 会在客户端解析时独立强制执行相同的码点上限。将可能很大的授权集合排除在 SQLite 绑定之外，可避开可移植变量上限，同时保持全局排序。响应仍只有一个有界页面；`hasMore` 会指示 UI 提示用户缩小查询范围，而不是公开分页能力。陈旧的续传会丢弃当前尝试的部分结果、去重条目和游标，然后依据原始可见性快照从第一页重新开始。上限探测与陈旧重试共用 100 次提供方调用的限制（因此最多检查 2,000 个命中）；如果某页命中数超过其请求的上限、续传游标重复，或用尽该调用预算后结果流仍未耗尽，都会直接返回 `internal` 业务错误，不返回部分结果。载体信号会取消已被取代的工作，包括持久化列表枚举、分批受限执行的冷会话元数据 stat，以及每一次提供方调用；即使同时收到上限拒绝或陈旧拒绝，也以取消为准。查询服务缺失或索引／查询故障无法恢复时，仍作为业务错误处理，不会修改规范会话存储。 -[`WorkspaceBrowser`](../../../../packages/client/ui-workspace/README.md) 有意将元数据搜索与内容搜索保持独立。非空白查询会立即从会话列表中计算不区分大小写的标题和 Workspace 子串匹配，在 250 ms 防抖后发起内容请求，在查询变化时中止前一请求，并忽略陈旧的完成结果。它先按新近程度排列本地匹配，再合并由后端排序且仅匹配内容的结果，按会话 id 去重；无论常规分组模式如何，最终都渲染为扁平列表。每一行显示标题、Workspace，并在存在时显示一行摘要片段。选择某一行只会打开对应会话，并保留查询条件；不会跳转至确切事件。 +[`WorkspaceBrowser`](../../../../packages/client/ui-workspace/README.md) 有意将元数据搜索与内容搜索保持独立。其默认界面文案为英文；输入框及防御性请求路径会移除 NUL，将查询限制在请求 schema 规定的 500 个 UTF-16 code unit 内且不会拆分 surrogate pair。非空白查询会立即从会话列表中计算不区分大小写的标题和 Workspace 子串匹配，在 250 ms 防抖后发起内容请求，在查询变化时中止前一请求，并忽略陈旧的完成结果。它先按新近程度排列本地匹配，再合并由后端排序且仅匹配内容的结果，按会话 id 去重；无论常规分组模式如何，最终都渲染为扁平列表。每一行显示标题、Workspace，并在存在时显示一行摘要片段。选择某一行只会打开对应会话，并保留查询条件；不会跳转至确切事件。 内容匹配沿用 SQLite 后端经过规范化的字面 token／短语语义。FTS5 运算符只作为数据处理，此搜索界面不提供拼写错误纠正、模糊匹配、前缀匹配或任意子串扩展。特别是，`unicode61` 分词器可能将一段连续中文视作单个 token，因此不保证 `搜索` 之类的较短查询能匹配 `会话搜索功能` 的内部片段。标题与 Workspace 匹配仍采用普通的客户端子串匹配。 @@ -39,4 +39,4 @@ Web 与 headless 共用的组合会使用 `openAt: first-search` 和内存数据 ## 测试 -宿主测试将请求校验、可见会话过滤、事件和 surface 过滤、结果与 snippet 边界、共享提供方调用预算、陈旧世代重启、游标与跨页去重行为、后续页取消及故障映射固定为契约。SQLite 生命周期测试将启动时激活、首次搜索时的打开与失败、共享就绪状态以及未打开状态下的处置固定为契约；一个 Node 22 兼容性子进程将首次搜索前无警告挂载与处置固定为契约。运行时与 UI 测试将无状态委托、防抖／中止／陈旧响应行为、本地回退、合并顺序、去重、行渲染与导航语义固定为契约。无密钥的组装层 Web 测试会播种一段尚未打开的持久化对话，通过惰性 SQLite 索引按消息内容找到它，捕获侧边栏结果，打开该会话，并验证查询条件仍然保留。 +宿主测试将请求与响应校验、可见会话过滤、事件和 surface 过滤、结果与 snippet 边界、共享调用预算内的自适应提供方上限、沿用探测所得上限的陈旧世代重启、游标与跨页去重行为、取消优先级及故障映射固定为契约。SQLite 生命周期测试将启动时激活、首次搜索时的打开与失败、共享就绪状态以及未打开状态下的处置固定为契约；Node 22 兼容性门禁会构建 CLI 与 Web 产物，在移除环境级警告抑制并采用隔离的临时 home／提供方环境后，以普通 Node 启动随产品交付的 `dsh web`／`AppCLIEntry` 组合，等待启动完成并稳定，再沿随产品交付的信号路径对其执行 dispose（资源释放）。fixture（测试前置数据）、运行时与 UI 测试将以匹配位置为中心的有界 snippet、无状态委托、500 个 code unit 的查询边界、防抖／中止／陈旧响应行为、本地回退、合并顺序、去重、英文文案、行渲染与导航语义固定为契约。无密钥的组装层 Web 测试会在保留惰性打开配置的同时，播种一段尚未打开的持久化对话，通过 SQLite 索引按消息内容找到它，捕获侧边栏结果，打开该会话，并验证查询条件仍然保留。 diff --git a/apps/cli/tests/lazy-search-startup.compat.spec.ts b/apps/cli/tests/lazy-search-startup.compat.spec.ts new file mode 100644 index 0000000000..96e9d24e1c --- /dev/null +++ b/apps/cli/tests/lazy-search-startup.compat.spec.ts @@ -0,0 +1,109 @@ +/** + * Node 22 startup-output smoke for the shipped Web CLI composition. + * + * The child runs built artifacts under plain Node with the real cordis.yml. + * Its URL line follows AppCLIEntry's settled boot; SIGTERM then exercises the + * shipped quiescent disposer. + */ + +import { spawn } from 'node:child_process' +import { existsSync } from 'node:fs' +import { mkdtemp, readFile, rm } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join, resolve } from 'node:path' +import { fileURLToPath } from 'node:url' +import yaml from 'js-yaml' +import { describe, expect, it } from 'vitest' + +const repoRoot = fileURLToPath(new URL('../../../', import.meta.url)) +const builtBin = join(repoRoot, 'apps/cli/lib/bin.js') +const webDist = join(repoRoot, 'apps/web/dist/index.html') +const configPath = join(repoRoot, 'apps/cli/cordis.yml') +const requireBuiltArtifacts = process.env.DSH_REQUIRE_BUILT_CLI_SMOKE === '1' +const builtArtifactsPresent = existsSync(builtBin) && existsSync(webDist) + +interface ConfigRow { + id?: string + config?: { openAt?: unknown } +} + +const jsExprType = new yaml.Type('tag:yaml.org,2002:js', { + kind: 'scalar', + construct: value => String(value), +}) +const configSchema = yaml.JSON_SCHEMA.extend(jsExprType) + +/** Boot the built Web CLI, wait for its settled URL, then dispose through SIGTERM. */ +function runBuiltWeb(cwd: string): Promise<{ stdout: string; stderr: string; code: number }> { + return new Promise((resolveRun, rejectRun) => { + const env: NodeJS.ProcessEnv = { + ...process.env, + DEEPSEEK_API_KEY: 'dsh-cli-smoke-dummy-key', + DSH_HOME: join(cwd, '.dsh'), + } + delete env.DEEPSEEK_BASE_URL + delete env.NODE_OPTIONS + delete env.NODE_NO_WARNINGS + const child = spawn(process.execPath, [ + builtBin, + 'web', + '--host', + '127.0.0.1', + '--port', + '0', + ], { + cwd, + env, + stdio: ['ignore', 'pipe', 'pipe'], + }) + let stdout = '' + let stderr = '' + let settled = false + child.stdout.setEncoding('utf8') + child.stderr.setEncoding('utf8') + child.stdout.on('data', (chunk: string) => { + stdout += chunk + if (!settled && /dsh web: http:\/\/127\.0\.0\.1:\d+/u.test(stdout)) { + settled = true + child.kill('SIGTERM') + } + }) + child.stderr.on('data', (chunk: string) => { stderr += chunk }) + const timer = setTimeout(() => { + child.kill('SIGKILL') + rejectRun(new Error(`built Web CLI did not settle and dispose within 60s\nstdout:\n${stdout}\nstderr:\n${stderr}`)) + }, 60_000) + child.on('error', (error) => { + clearTimeout(timer) + rejectRun(error) + }) + child.on('close', (code) => { + clearTimeout(timer) + if (!settled) { + rejectRun(new Error(`built Web CLI exited before settled startup (code ${String(code)})\nstdout:\n${stdout}\nstderr:\n${stderr}`)) + return + } + resolveRun({ stdout, stderr, code: code ?? -1 }) + }) + }) +} + +describe.skipIf(!requireBuiltArtifacts && !builtArtifactsPresent)('built CLI lazy-search startup', () => { + it('boots and disposes the shipped composition without a SQLite startup warning', async () => { + expect(existsSync(builtBin), `missing built CLI ${resolve(builtBin)}; run pnpm build`).toBe(true) + expect(existsSync(webDist), `missing Web dist ${resolve(webDist)}; run pnpm run build:web`).toBe(true) + const rows = yaml.load(await readFile(configPath, 'utf8'), { schema: configSchema }) as ConfigRow[] + const searchRow = rows.find(row => row.id === 'session-query-sqlite') + expect(searchRow?.config?.openAt).toBe('first-search') + + const cwd = await mkdtemp(join(tmpdir(), 'dsh-cli-lazy-search-')) + try { + const result = await runBuiltWeb(cwd) + expect(result.stdout).toMatch(/dsh web: http:\/\/127\.0\.0\.1:\d+/u) + expect(result.code).toBe(0) + expect(result.stderr).not.toMatch(/ExperimentalWarning: SQLite/u) + } finally { + await rm(cwd, { recursive: true, force: true }) + } + }, 70_000) +}) diff --git a/apps/web/tests/navigation-panes.e2e.ts b/apps/web/tests/navigation-panes.e2e.ts index 7744ad5c55..d5acb3ee04 100644 --- a/apps/web/tests/navigation-panes.e2e.ts +++ b/apps/web/tests/navigation-panes.e2e.ts @@ -93,18 +93,18 @@ describe('web e2e: navigation & panes over a rich seeded session', () => { it.skipIf(MODE === 'record')('finds an unopened seeded session by message content and opens it', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-search')) - const search = page.getByPlaceholder('搜索名称或关键词', { exact: false }) + const search = page.getByPlaceholder('Search names or content', { exact: false }) // The cold row has not been opened, so only the persisted log can satisfy // this query. First search lazily reconciles the SQLite content index. await search.fill('zzzqx-no-such-session') - await page.getByText('没有匹配结果').waitFor({ timeout: 30_000 }) + await page.getByText('No matching sessions').waitFor({ timeout: 30_000 }) await expect.poll( - () => page.getByRole('tree', { name: '搜索结果' }).getByRole('treeitem').count(), + () => page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem').count(), { timeout: 10_000 }, ).toBe(0) await search.fill('WATERFALL') - const resultTree = page.getByRole('tree', { name: '搜索结果' }) + const resultTree = page.getByRole('tree', { name: 'Search results' }) const result = resultTree.getByRole('treeitem') await expect.poll(() => result.count(), { timeout: 30_000 }).toBe(1) await expect.poll(() => result.getByText('WATERFALL', { exact: false }).count(), { @@ -120,7 +120,7 @@ describe('web e2e: navigation & panes over a rich seeded session', () => { await expect.poll(() => search.inputValue(), { timeout: 5_000 }).toBe('WATERFALL') await expect.poll(() => page.getByText('FIRST_DONE', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1) await expect.poll(() => page.getByRole('heading', { name: 'Navigation Summary' }).count(), { timeout: 15_000 }).toBe(1) - await page.getByRole('button', { name: '清除搜索' }).click() + await page.getByRole('button', { name: 'Clear search' }).click() await expect.poll(() => search.inputValue(), { timeout: 5_000 }).toBe('') await expect.poll(() => page.locator('[role="treeitem"]').count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1) }, 90_000) diff --git a/apps/web/tests/scaffold.ts b/apps/web/tests/scaffold.ts index eb61619de0..c9390af80d 100644 --- a/apps/web/tests/scaffold.ts +++ b/apps/web/tests/scaffold.ts @@ -163,7 +163,7 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise part.trim()).filter(Boolean).join('\n') } +interface FixtureSearchToken { + value: string + /** Inclusive code-point offset in the whitespace-normalized display text. */ + start: number + /** Exclusive code-point offset in the whitespace-normalized display text. */ + end: number +} + /** * Browser-safe approximation of SQLite FTS5 unicode61 token boundaries. * Keeping phrase matching token-based prevents the development fixture from * promising arbitrary within-token substring behavior that production lacks. */ -function searchTokens(value: string): string[] { - return value - .normalize('NFD') - .replace(/\p{M}+/gu, '') - .toLowerCase() - .match(/[\p{L}\p{N}\p{Co}]+/gu) ?? [] -} - -/** Count exact contiguous token-phrase occurrences in one fixture document. */ -function phraseMatchCount(document: readonly string[], phrase: readonly string[]): number { - if (phrase.length === 0 || phrase.length > document.length) return 0 - let count = 0 - for (let start = 0; start <= document.length - phrase.length; start++) { - if (phrase.every((token, offset) => document[start + offset] === token)) count++ +function searchTokenSpans(value: string): { text: string; tokens: FixtureSearchToken[] } { + const text = value.replace(/\s+/gu, ' ').trim() + const characters = Array.from(text) + const tokens: FixtureSearchToken[] = [] + let start: number | undefined + let raw = '' + const flush = (end: number): void => { + if (start !== undefined) { + const folded = raw.normalize('NFD').replace(/\p{M}+/gu, '').toLowerCase() + if (folded !== '') tokens.push({ value: folded, start, end }) + } + start = undefined + raw = '' } - return count + for (let index = 0; index < characters.length; index++) { + const character = characters[index] as string + const tokenBase = character.normalize('NFD').replace(/\p{M}+/gu, '') + if (tokenBase === '') { + if (start !== undefined) raw += character + continue + } + if (/^[\p{L}\p{N}\p{Co}]+$/u.test(tokenBase)) { + start ??= index + raw += character + } else { + flush(index) + } + } + flush(characters.length) + return { text, tokens } } -/** One-line fixture excerpt, bounded so the sidebar remains readable. */ -function searchSnippet(value: string): string { - const oneLine = value.replace(/\s+/gu, ' ').trim() - return oneLine.length <= 120 ? oneLine : `${oneLine.slice(0, 117)}…` +interface FixturePhraseMatch { + count: number + start: number + end: number +} + +/** Count exact contiguous token-phrase occurrences and retain the first display span. */ +function phraseMatch(document: readonly FixtureSearchToken[], phrase: readonly string[]): FixturePhraseMatch { + if (phrase.length === 0 || phrase.length > document.length) return { count: 0, start: 0, end: 0 } + let count = 0 + let firstStart = 0 + let firstEnd = 0 + for (let start = 0; start <= document.length - phrase.length; start++) { + if (!phrase.every((token, offset) => document[start + offset]?.value === token)) continue + count++ + if (count === 1) { + firstStart = document[start]?.start ?? 0 + firstEnd = document[start + phrase.length - 1]?.end ?? firstStart + } + } + return { count, start: firstStart, end: firstEnd } +} + +/** Match-centered fixture excerpt, bounded by Unicode code points for the sidebar. */ +function searchSnippet(value: string, matchStart: number, matchEnd: number): string { + const characters = Array.from(value) + if (characters.length <= 120) return value + const boundedStart = Math.min(Math.max(0, matchStart), characters.length - 1) + const boundedEnd = Math.min( + characters.length, + Math.max(boundedStart + 1, matchEnd), + ) + const center = Math.floor((boundedStart + boundedEnd) / 2) + let start = Math.min( + characters.length - 118, + Math.max(0, center - Math.floor(118 / 2)), + ) + let end = start + 118 + if (start === 0) { + end = 119 + } else if (end === characters.length) { + start = characters.length - 119 + } + return `${start > 0 ? '…' : ''}${characters.slice(start, end).join('')}${end < characters.length ? '…' : ''}` } interface FixtureSearchCandidate { @@ -342,6 +404,8 @@ interface FixtureSearchCandidate { time: number text: string matchCount: number + matchStart: number + matchEnd: number documentLength: number } @@ -628,21 +692,24 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy { details: {}, }) } - const query = searchTokens(request.payload.query) + const query = searchTokenSpans(request.payload.query).tokens.map(token => token.value) const matches = sessions.flatMap((summary) => { const log = logs.get(summary.sessionId) ?? [] const current = new Set(foldSurface(log).nodes) const best = log.flatMap((event): FixtureSearchCandidate[] => { if (!current.has(event.seq)) return [] const eventText = searchEventText(event) - const matchCount = phraseMatchCount(searchTokens(eventText), query) - if (matchCount === 0) return [] + const document = searchTokenSpans(eventText) + const match = phraseMatch(document.tokens, query) + if (match.count === 0) return [] return [{ sessionId: summary.sessionId, seq: event.seq, time: event.time, - text: eventText, - matchCount, + text: document.text, + matchCount: match.count, + matchStart: match.start, + matchEnd: match.end, documentLength: Array.from(eventText).length, }] }).sort(compareSearchCandidates)[0] @@ -651,7 +718,7 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy { return ok(request, { items: matches.slice(0, 20).map(match => ({ sessionId: match.sessionId, - snippet: searchSnippet(match.text), + snippet: searchSnippet(match.text, match.matchStart, match.matchEnd), })), hasMore: matches.length > 20, }) diff --git a/packages/client/connection/tests/fixture.spec.ts b/packages/client/connection/tests/fixture.spec.ts index 9bf0173237..71d171ee0c 100644 --- a/packages/client/connection/tests/fixture.spec.ts +++ b/packages/client/connection/tests/fixture.spec.ts @@ -62,6 +62,23 @@ describe('createFixtureApi', () => { if (!phrase.result.ok) throw new Error('search failed') expect(phrase.result.value.items[0]?.snippet).toContain('fixture 历史消息') + timing().appendUser( + 'fx-alpha', + `${'leading context '.repeat(20)}late café token${' trailing context'.repeat(20)}`, + ) + const late = await api.sessions.search(req({ query: 'LATE CAFE TOKEN' }), signal) + if (!late.result.ok) throw new Error('late search failed') + const lateSnippet = late.result.value.items[0]?.snippet ?? '' + expect(lateSnippet).toContain('late café token') + expect(lateSnippet.startsWith('…')).toBe(true) + expect(lateSnippet.endsWith('…')).toBe(true) + expect(Array.from(lateSnippet).length).toBeLessThanOrEqual(120) + + timing().appendUser('fx-alpha', 'Greek final sigma: ος') + const finalSigma = await api.sessions.search(req({ query: 'ΟΣ' }), signal) + if (!finalSigma.result.ok) throw new Error('final sigma search failed') + expect(finalSigma.result.value.items[0]?.snippet).toContain('ος') + const substring = await api.sessions.search(req({ query: 'ixtur' }), signal) expect(substring.result).toEqual({ ok: true, diff --git a/packages/client/ui-workspace/README.i18n.yaml b/packages/client/ui-workspace/README.i18n.yaml index f89fbee5d4..f2da1e952a 100644 --- a/packages/client/ui-workspace/README.i18n.yaml +++ b/packages/client/ui-workspace/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-workspace/README.md -README.md: 9cb919a1a64394d5e116d35bdddfdee738994a02 -README.zh.md: b3add7f89cb0feb7f44238b7199d0633cdfbf641 +README.md: badcfc704b456a62a921cb93f6cf637f255fca1f +README.zh.md: 53c43f880ea4ce4f0cfbf633d32f163662e9271f diff --git a/packages/client/ui-workspace/README.md b/packages/client/ui-workspace/README.md index 9cb919a1a6..badcfc704b 100644 --- a/packages/client/ui-workspace/README.md +++ b/packages/client/ui-workspace/README.md @@ -4,7 +4,7 @@ English | [中文](README.zh.md) Shared Workspace browser and picker plugin. `WorkspaceBrowser` fills the sidebar's `sidebar.workspaces` slot, while `WorkspacePicker` fills the page-local Session Intent hero's `conversation.hero.workspace` slot; both surfaces use the same Workspace menu and creation modals. -The browser renders grouped or flat Session rows from the global runtime hooks and owns the Workspace create/rename and in-Workspace reorder flows. A non-blank search query replaces either browsing mode with one flat result list: case-insensitive title and Workspace substring matches appear immediately, while a 250 ms debounced Host request adds ranked current-conversation content matches and snippets. Each new query aborts the preceding request; a failed content search leaves metadata matches visible with a warning. The list is capped at 20, asks the user to narrow broader queries, and opens the selected Session without clearing the query or jumping to a specific event. +The browser renders grouped or flat Session rows from the global runtime hooks and owns the Workspace create/rename and in-Workspace reorder flows. A non-blank search query replaces either browsing mode with one flat result list: case-insensitive title and Workspace substring matches appear immediately, while a 250 ms debounced Host request adds ranked current-conversation content matches and snippets. The English search input and its defensive request path remove NUL, cap the query at the wire schema's 500 UTF-16 code units without splitting a surrogate pair, and preserve the existing debounce and cancellation behavior. Each new query aborts the preceding request; a failed content search leaves metadata matches visible with a warning. The list is capped at 20, asks the user to narrow broader queries, and opens the selected Session without clearing the query or jumping to a specific event. The picker lists real Host Workspace entities through the global `useWorkspaces` hook. Selecting a Workspace invokes the slot owner's `onPick` callback to retarget the frontend Session object; the existing-folder and create-new actions first create a real Workspace through the object layer, then select it. Create-new disables names already present in that list, while the Host remains authoritative for concurrent or non-UI callers. The runtime Session and Workspace services own materialization. diff --git a/packages/client/ui-workspace/README.zh.md b/packages/client/ui-workspace/README.zh.md index b3add7f89c..53c43f880e 100644 --- a/packages/client/ui-workspace/README.zh.md +++ b/packages/client/ui-workspace/README.zh.md @@ -4,7 +4,7 @@ 共享 Workspace 浏览器与选择器插件。`WorkspaceBrowser` 填充侧边栏的 `sidebar.workspaces` slot，`WorkspacePicker` 则填充页面局部 Session Intent 主视觉区的 `conversation.hero.workspace` slot；两个表层使用同一套 Workspace 菜单和创建模态框。 -该浏览器通过全局运行时钩子将 Session 行渲染为分组或扁平形式，并负责 Workspace 创建／重命名和 Workspace 内的重排序流程。非空白查询会以单一扁平结果列表替代任一浏览模式：不区分大小写的标题和 Workspace 子串匹配项会立即显示，经 250 ms 防抖的 Host 请求则会加入经过排序的当前对话内容匹配项及其摘要片段。每次新查询都会中止前一个请求；内容搜索失败时，元数据匹配项仍会显示，同时给出警告。列表最多显示 20 条结果，并会在查询过宽时提示用户缩小范围；打开所选 Session 时既不会清除查询，也不会跳转至特定事件。 +该浏览器通过全局运行时钩子将 Session 行渲染为分组或扁平形式，并负责 Workspace 创建／重命名和 Workspace 内的重排序流程。非空白查询会以单一扁平结果列表替代任一浏览模式：不区分大小写的标题和 Workspace 子串匹配项会立即显示，经 250 ms 防抖的 Host 请求则会加入经过排序的当前对话内容匹配项及其摘要片段。英文搜索输入框及其防御性请求路径会移除 NUL，将查询限制在传输 schema 规定的 500 个 UTF-16 code unit 内且不会拆分 surrogate pair，并保留现有的防抖与取消行为。每次新查询都会中止前一个请求；内容搜索失败时，元数据匹配项仍会显示，同时给出警告。列表最多显示 20 条结果，并会在查询过宽时提示用户缩小范围；打开所选 Session 时既不会清除查询，也不会跳转至特定事件。 该选择器通过全局 `useWorkspaces` hook 列出真实的 Host Workspace 实体。选择 Workspace 会调用 slot owner 的 `onPick` 回调，重新定位前端 Session 对象；使用现有文件夹和新建操作时，系统会先通过对象层创建真实 Workspace，再将其选中。新建操作会禁用列表中已有的名称，而 Host 对并发或非 UI 调用方仍具有最终决定权。运行时 Session 与 Workspace 服务负责物化。 diff --git a/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx b/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx index d703674c01..c2b73165f3 100644 --- a/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx +++ b/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx @@ -27,6 +27,19 @@ import css from './WorkspaceBrowser.module.css' const EXPAND_SLIDE_MS = 300 /** Pause between the latest keystroke and a Host content-search request. */ const SEARCH_DEBOUNCE_MS = 250 +/** `session.search` wire bound, measured in JavaScript UTF-16 code units. */ +const SEARCH_QUERY_MAX_CODE_UNITS = 500 + +/** Keep controlled input and RPC payload inside the session.search wire contract. */ +function sanitizeSearchQuery(value: string): string { + const withoutNul = value.replaceAll('\0', '') + if (withoutNul.length <= SEARCH_QUERY_MAX_CODE_UNITS) return withoutNul + let end = SEARCH_QUERY_MAX_CODE_UNITS + const last = withoutNul.charCodeAt(end - 1) + const next = withoutNul.charCodeAt(end) + if (last >= 0xD800 && last <= 0xDBFF && next >= 0xDC00 && next <= 0xDFFF) end-- + return withoutNul.slice(0, end) +} const GROUP_BY_ITEMS = [ { type: 'label' as const, id: 'group-by', text: 'Group by' }, @@ -255,7 +268,7 @@ function SearchResults({ return (
-
+
{results.items.map(result => ( ))} {pending && ( -
正在搜索历史…
+
Searching session history…
)} {failed && (
- 历史内容搜索暂时不可用，仍显示名称匹配。 + Content search is temporarily unavailable. Showing name matches.
)} {!pending && results.items.length === 0 && ( -
没有匹配结果
+
No matching sessions
)} {results.hasMore && ( -
仅显示前 20 项，请缩小搜索范围。
+
Showing the first 20 results. Narrow your search.
)}
@@ -308,7 +321,7 @@ export function WorkspaceBrowser({ // The query outlives the tree and the input (both wide-only) so collapsing // does not silently drop an in-progress filter. const [query, setQuery] = useState('') - const normalizedQuery = query.trim() + const normalizedQuery = sanitizeSearchQuery(query).trim() const [remoteSearch, setRemoteSearch] = useState({ query: '', status: 'idle', @@ -439,11 +452,11 @@ export function WorkspaceBrowser({ {/* Expanded: the row is a click-to-focus field (the leading icon is decorative). Rail: the icon is the region's search control. */}
{ if (wide) searchInput.current?.focus() }}> - +