better-dsh 0.2.3-e → 0.2.3-g

package/dsh-docs/subsystems/workspace.zh.md

@@ -0,0 +1,321 @@
+# 工作区
+
+[English](workspace.md) | 中文
+
+工作区（workspace）是用户工作目录的持久记录：一个建立在规范路径之上的稳定 id、一个显示标题，以及归属于它的会话的有序账本。该子系统是单个包（package）（[dsh-workspace](../../packages/workspace/workspace)，`ctx.workspaceRegistry`）——一项宿主侧可选能力，不属于 agent loop（智能体循环）主干，并且对模型不可见（没有工具、没有提示词文本、没有会话事件）。它通过[存储领域数据形式](storage.zh.md)存储自己的记录，并对照 [`SessionHeader.cwd`](persistence.zh.md#sessionheader--metadata-beside-the-log) 校验会话成员资格，因此 `storageDomain` 与 `sessionPersistence` 是必需的启动依赖：持久化这一依赖不可用时，插件保持 pending，而不是把这种不可用误当作空历史。设计记录：[领域 KV 存储 Agent Note（agent 决策记录）](../../.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.zh.md)；引导与 GUI 顺序：[Workspace UI 产品流程 Agent Note](../../.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.zh.md)。
+
+源码：[`packages/workspace/workspace/src/types.ts`](../../packages/workspace/workspace/src/types.ts)
+
+## 标识
+
+```ts type-equiv
+/**
+ * Identifies one workspace record. A generated uuid, never the path: path
+ * normalization rewrites paths, and a reference anchor must stay stable.
+ */
+type WorkspaceId = Branded<'WorkspaceId'>
+```
+
+`WorkspaceId` 是[品牌化 id](core.zh.md#branded-ids)。路径标识与之分离：`realpathNormalize`（`fs.realpath`；尾部斜杠、`..` 与符号链接全部解析）是唯一的一套唯一性规范——工作区路径以规范化形式存储，唯一性即规范路径的字符串相等（指向已被拥有目录的符号链接会与之冲突），attach 时的会话 cwd 检查也走同一套规范。
+
+## 工作区实体
+
+消费方只看到 `Workspace` 接口；实现保持包内私有。
+
+```ts type-equiv
+/**
+ * One workspace: a stable id over an existing directory, a display title, and
+ * an ordered candidate account of sessions. Membership requires both an id in
+ * that account and a session header whose canonical cwd equals the workspace
+ * path. Consumers only see this interface; the implementation stays private.
+ */
+interface Workspace {
+  /** Stable record id (generated uuid). */
+  readonly id: WorkspaceId
+
+  /**
+   * Canonical directory path: the `fs.realpath` of the path given at create
+   * time (trailing slashes, `..`, and symlinks all resolved). Never rewritten
+   * afterwards, even when the directory disappears (see {@link status}).
+   */
+  readonly path: string
+
+  /** Display title. Defaults to the final path segment, or a filesystem root's own spelling; duplicates are allowed. */
+  readonly title: string
+
+  /** ISO-8601 creation instant, stamped at create and never rewritten. */
+  readonly createdAt: string
+
+  /** ISO-8601 instant of the last durable mutation (create counts as one). */
+  readonly updatedAt: string
+
+  /**
+   * Header-validated sessions in manually owned order: a new session is
+   * prepended at attach, explicit reordering goes through
+   * `insertSessionBefore`, and activity never reorders. The durable candidate
+   * account is filtered synchronously: missing headers, invalid cwd values,
+   * and canonical cwd mismatches are never returned. A subsequent workspace
+   * mutation prunes those filtered candidates durably.
+   */
+  readonly sessionIds: readonly SessionId[]
+
+  /**
+   * Replace the display title durably.
+   * @param title - New title; any string, duplicates across workspaces allowed.
+   * @returns resolution after durability.
+   */
+  setTitle(title: string): Promise<void>
+
+  /**
+   * Prepend a session to this workspace's candidate account. An already
+   * accounted id resolves without writing, aside from the durable
+   * filtered-candidate prune every accepted mutation performs. A new id's
+   * live or persisted
+   * header cwd must resolve to an existing directory equal to {@link path};
+   * unknown ids, missing or invalid cwd values, and mismatches reject without
+   * writing.
+   * @param sessionId - The session to record.
+   * @returns resolution after durability.
+   */
+  attachSession(sessionId: SessionId): Promise<void>
+
+  /**
+   * Move an accounted session within the manual order, DOM-insertBefore-like:
+   * with an anchor the session lands before it, without one it appends to the
+   * end. Only the moved id changes position. A session or anchor absent from
+   * the account rejects without writing; a move to the current position
+   * resolves without writing, aside from the durable filtered-candidate
+   * prune every accepted mutation performs; decided on the domain write
+   * chain.
+   * @param sessionId - The accounted session to move.
+   * @param beforeSessionId - Accounted anchor to insert before; omitted appends.
+   * @returns resolution after durability.
+   */
+  insertSessionBefore(sessionId: SessionId, beforeSessionId?: SessionId): Promise<void>
+
+  /**
+   * Remove a session from this workspace's account. Idempotent: an id not on
+   * the account resolves without writing, aside from the durable
+   * filtered-candidate prune every accepted mutation performs; decided on
+   * the domain write chain like attach. Never touches the session's own stored log.
+   * @param sessionId - The session to remove.
+   * @returns resolution after durability.
+   */
+  detachSession(sessionId: SessionId): Promise<void>
+
+  /**
+   * Live directory check, uncached: whether {@link path} currently exists and
+   * is a directory. A missing directory never mutates the record — the
+   * directory may only be temporarily moved.
+   * @returns `'ok'` when the directory exists, `'missing-dir'` otherwise.
+   */
+  status(): Promise<'ok' | 'missing-dir'>
+}
+```
+
+所有权的真源是记录中有序的 `sessionIds`，绝不从会话 cwd 派生——但成员资格要求两者同时成立：账本上有其 id，且 header 的规范 cwd 等于工作区路径，因此一个会话在结构上至多属于一个工作区。失败的写入会拒绝（`insertSessionBefore` 的账本错误以 `WorkspaceMoveInvalidError` 拒绝，存储失败以普通错误拒绝）；每次被接受的变更都盖上 `updatedAt` 时间戳，并持久修剪不再通过成员资格检查的候选项。
+
+## 注册表：`ctx.workspaceRegistry`
+
+`WorkspaceRegistry`（[签名](#ctxworkspaceregistry--workspaceregistry)）拥有注册与解析。`create(path, title?)` 要求完全限定路径并将其规范化，拒绝不存在的路径（原样传出原始 `ENOENT`）或非目录；当规范路径已被拥有时原样返回既有实体；否则创建一条标题为 `title ?? defaultWorkspaceTitle(path)` 的记录并前插到持久的注册表顺序中（不同规范路径可以共享同一显示标题，没有最终路径段时使用根路径拼写）。`get(id)` 与有序的 `list()` 是同步缓存读取；`resolveByPath(path)` 应用同一套完全限定 realpath 规范但不创建。`delete(id)` 只移除注册记录、顺序条目和会话账本——目录、用户文件、实时会话和已持久化日志一概不动，因此这些会话变为 Ungrouped（[决策](../../.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md)）；未知 id 返回 `false`。create 与 delete 会在其两次写入（记录 + 顺序）可能分叉之前先持久写入一个待定变更标记；启动时恰好解决被标记的那次变更——通过删除被标记的表行：这会补完被中断的 delete，并回滚被中断的 create（注册可以重建，因此回滚是安全方向）——而没有标记的顺序/表不一致则作为损坏大声失败。
+
+会话的 cwd 在创建时由创建者赋予，而不是由本注册表赋予——API 网关从所选工作区的 `path` 解析新会话的 cwd（回退到显式或默认 cwd），先创建会话使 cwd 落入其不可变的 [`SessionHeader`](persistence.zh.md#sessionheader--metadata-beside-the-log)，再调用 `attachSession`，后者会把已存储的 header cwd 与工作区路径重新校验一遍。首次成功启动时，注册表仅凭已持久化的 header（`id`、`cwd`、`createdAt`——绝不读事件正文）引导历史：把规范 cwd 有效的会话按目录分组为工作区，最新的排在最前；「已初始化」标记最后写入，因此被中断的引导可以安全续跑。引导只发生这一次：没有 cwd 的历史遗留会话保持 Ungrouped，此后创建的会话只能通过 `attachSession` 加入工作区。
+
+## 消费方
+
+[`dsh-workspace-controller`](../../packages/api/workspace-controller) 经 `ctx.workspaceRegistry` 向 GUI 客户端提供工作区 CRUD，[`dsh-session-controller`](../../packages/api/session-controller) 执行上文「先建会话再 attach」的流程。[dsh-agent-instructions](../../packages/context/agent-instructions) 尽管名字如此，却**不是**消费方：它在 agent 自己的 cwd 下发现 AGENTS.md 风格的指令文件，从不触碰 `ctx.workspaceRegistry`——两者共用的这个词指的是用户的工作目录，而非本注册表的实体。
+
+<!-- BEGIN GENERATED cordis-surface (gen-cordis-catalog.ts) — do not edit between markers -->
+
+<a id="cordis-surface"></a>
+
+## Cordis API
+
+Generated from source by `scripts/gen-cordis-catalog.ts` (verified fresh by `pnpm run verify-cordis-catalog` in doc-sync; regenerate with `pnpm run gen-cordis-catalog`) — the language sides differ only in locale-specific paired document paths. Signature blocks use a `ts cordis-catalog` fence and keep the original source JSDoc; dispatch modes are defined in the [primer](../cordis-primer.zh.md#dispatch-modes), and the framework-inherited `ctx` API lives in [cordis-api/inherited.md](../cordis-api/inherited.md).
+
+<a id="ctxdirectorypicker--directorypicker-abstract-seam"></a>
+
+### `ctx.directoryPicker` — `DirectoryPicker` (abstract seam)
+
+Abstract directory-picking service. Subclass, implement `capability()`, and load the subclass as a plugin — it registers as `ctx.directoryPicker` (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior). The capability object must be stable for the service lifetime: consumers may capture it across calls.
+
+```ts cordis-catalog
+/**
+ * The backend's interaction capability.
+ * @returns the discriminated capability consumers switch on.
+ */
+abstract capability(): DirectoryPickerCapability
+```
+
+Source: [`packages/host/directory-picker/src/index.ts`](../../packages/host/directory-picker/src/index.ts)
+
+<a id="ctxdirectorypickercontroller--directorypickercontroller"></a>
+
+### `ctx.directoryPickerController` — `DirectoryPickerController`
+
+Host service backing the generated `ctx.remote.directoryPicker` namespace. The seam it exports is abstract and therefore never a Loader entry of its own, so this controller carries the wire verbs: one composed backend serves either the native chooser or the browse primitives, and a verb the composition cannot serve is refused rather than approximated.
+
+```ts cordis-catalog
+/**
+ * Open the host's OS chooser for a Remote caller.
+ * @param signal - caller lifetime; abort terminates the chooser.
+ * @returns the chosen absolute path, or null when the operator cancels.
+ */
+@Remote('pick') async pick(signal: AbortSignal): Promise<string | null>
+
+/**
+ * List one directory level for a Remote caller's in-app browser.
+ * @param path - absolute directory to list; absent lists the home directory.
+ * @param signal - caller lifetime; abort stops the backend's scan instead of
+ *   letting it outlive a disconnected caller.
+ * @returns the level's listing with its ancestry.
+ */
+@Remote('list') async list(path: string | undefined, signal: AbortSignal): Promise<DirectoryListing>
+
+/**
+ * Create one child directory for a Remote caller's in-app browser.
+ * @param path - absolute existing parent directory.
+ * @param name - single non-blank path segment.
+ * @returns the created directory's absolute path.
+ */
+@Remote('createDirectory') async createDirectory(path: string, name: string): Promise<string>
+```
+
+Source: [`packages/api/workspace-controller/src/directory-picker.ts`](../../packages/api/workspace-controller/src/directory-picker.ts)
+
+<a id="ctxworkspacecontroller--workspacecontroller"></a>
+
+### `ctx.workspaceController` — `WorkspaceController`
+
+Host service backing the generated `ctx.remote.workspace` namespace.
+
+```ts cordis-catalog
+/**
+ * Create or idempotently resolve one Workspace over an existing directory.
+ * @param request - directory path to register.
+ * @returns the Workspace and whether this call created it.
+ */
+@Remote('create') create(request: WorkspaceCreateRequest): Promise<WorkspaceCreateValue>
+
+/**
+ * Rename one Workspace to a unique non-blank title.
+ * @param request - Workspace identity and proposed title.
+ * @returns the updated Workspace projection.
+ */
+@Remote('rename') rename(request: WorkspaceRenameRequest): Promise<WorkspaceValue>
+
+/**
+ * Remove one Workspace registration while retaining files and Sessions.
+ * @param request - Workspace identity to remove.
+ * @returns deletion confirmation.
+ */
+@Remote('delete') delete(request: WorkspaceDeleteRequest): Promise<WorkspaceDeleteValue>
+
+/**
+ * Move one Workspace within the registry display order.
+ * @param request - moved Workspace and optional anchor.
+ * @returns the complete resulting Workspace order.
+ */
+@Remote('insertBefore') insertBefore(request: WorkspaceInsertBeforeRequest): Promise<WorkspaceOrderValue>
+
+/**
+ * Move one accounted Session within a Workspace.
+ * @param request - Workspace, Session, and optional anchor identities.
+ * @returns the updated Workspace projection.
+ */
+@Remote('insertSessionBefore') insertSessionBefore(request: WorkspaceInsertSessionBeforeRequest): Promise<WorkspaceValue>
+
+/**
+ * Hide one known Session from Workspace grouping surfaces.
+ * @param request - Session identity to archive.
+ * @returns the complete resulting archive set.
+ */
+@Remote('archiveSession') archiveSession(request: WorkspaceArchiveSessionRequest): Promise<WorkspaceArchiveValue>
+
+/**
+ * Stream a complete Workspace baseline followed by ordered increments.
+ * @param signal - generation cancellation.
+ * @returns baseline followed by ordered Workspace increments.
+ */
+@Remote({ mode: 'stream' }) follow(signal: AbortSignal): AsyncIterable<WorkspaceFollowFrame>
+```
+
+Source: [`packages/api/workspace-controller/src/index.ts`](../../packages/api/workspace-controller/src/index.ts)
+
+<a id="ctxworkspaceregistry--workspaceregistry"></a>
+
+### `ctx.workspaceRegistry` — `WorkspaceRegistry`
+
+Durable workspace registry. Startup waits for `sessionPersistence`, builds one canonical-cwd header index, and completes the one-time history bootstrap before the service becomes active. The persistence dependency is mandatory so an unavailable peer can never be mistaken for an empty history and commit the initialized marker.
+
+```ts cordis-catalog
+/**
+ * Create or reuse a workspace for an existing directory. The fully qualified
+ * path is canonicalized through `fs.realpath`; a relative, nonexistent, or
+ * non-directory path rejects. Repeated calls for the same canonical path
+ * return the existing entity without changing its title.
+ * A newly created workspace is prepended to the durable registry order.
+ * Different canonical paths may share a display title.
+ * @param path - Existing directory to own, in a fully qualified path spelling.
+ * @param title - Display title used only when a new record is created.
+ * @returns the existing or newly durable workspace.
+ */
+async create(path: string, title?: string): Promise<Workspace>
+
+/**
+ * Look up a workspace by id.
+ * @param id - Workspace id.
+ * @returns the workspace, or `undefined` when unknown.
+ */
+get(id: WorkspaceId): Workspace | undefined
+
+/**
+ * Synchronous workspace projection in durable registry order. Every
+ * entity's `sessionIds` getter is already filtered by the startup/live
+ * canonical-cwd header index; this method performs no persistence reads.
+ * @returns a fresh ordered array of workspace entities.
+ */
+list(): Workspace[]
+
+/**
+ * Delete one workspace registration while retaining its directory and every
+ * session log. The durable order is updated before the table deletion; a
+ * failed table write restores the prior order and keeps the entity
+ * published. Unknown ids are an idempotent no-op for domain callers.
+ * @param id - Workspace registration to remove.
+ * @returns `true` when a record was deleted, `false` when it was unknown.
+ */
+delete(id: WorkspaceId): Promise<boolean>
+
+/**
+ * Move one workspace within the durable display order, DOM-insertBefore-like.
+ * With an anchor it lands before that workspace; without one it appends.
+ * @param id - Workspace to move.
+ * @param beforeId - Workspace anchor; omitted appends.
+ * @returns the complete committed workspace order.
+ */
+insertBefore(id: WorkspaceId, beforeId?: WorkspaceId): Promise<readonly WorkspaceId[]>
+
+/**
+ * Archive one session durably. The session must exist (live or in session
+ * persistence); its workspace accounting — or lack of one — is irrelevant.
+ * An already archived id resolves without writing.
+ * @param sessionId - The session to archive.
+ * @returns resolution after durability.
+ */
+archiveSession(sessionId: SessionId): Promise<void>
+
+/**
+ * Resolve by canonical directory path without creating or mutating a
+ * workspace. A missing path rejects during `realpath`; an existing unowned
+ * directory returns `undefined`.
+ * @param path - Existing directory path in a fully qualified spelling.
+ * @returns the workspace owning the canonical path, when one exists.
+ */
+async resolveByPath(path: string): Promise<Workspace | undefined>
+```
+
+Types: [SessionId](core.zh.md)
+
+Source: [`packages/workspace/workspace/src/index.ts`](../../packages/workspace/workspace/src/index.ts)
+<!-- END GENERATED cordis-surface -->

package/dsh-docs/testing.md

@@ -0,0 +1,54 @@
+# Testing policy
+
+English | [中文](testing.zh.md)
+
+How this repo tests, tier by tier, and the rules that keep a green suite meaningful. Commands live in root [AGENTS.md](../AGENTS.md); linked Agent Notes carry the rationale.
+
+## Tiers
+
+- **Unit** (`pnpm run test`): vitest over package and example specs under their `tests/**` directories plus repository script specs under `scripts/**/*.spec.ts`; tests stay with the code area they exercise. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, concurrency races, and permanent tests for contract regressions (see `packages/core/agent-loop/tests/contract-regressions.spec.ts`).
+- **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate flags for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped. Per-file 100% on `packages/shell/pwsh-local/src` needs a real `pwsh`: without one its executor suites self-skip and `vitest.config.ts` exempts the file so pwsh-less hosts stay green, while CI runners ship pwsh and enforce the full bar.
+- **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e Agent Note](../.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md)).
+- **Owner-local expected output** (`pnpm run test:expected`): keyless assembled CLI/process expectations without a recorded-session round trip. Drivers use `*.expected.e2e.ts` beside `tests/expected/`; CI runs built exports. Package/script expectations use `test`, while browser expectations use `test:web`.
+- **Snapshot** (`pnpm run test:snapshot`): a top-level scenario's highest recorded parent generation supplies user input and model replay, then serves as the expected persisted result. Parent filenames are `session[.vN].jsonl`; child roles are `session.<ordinal>[.vN].jsonl`; v0 omits `.v0`, positive versions require lowercase `.vN`, and each filename must agree with its header. Process scenarios start through `dsh`: headless owns one-shot behavior, the SDK owns persistent control, ACP owns automation-protocol behavior, and Web retains browser/ARIA evidence beside the same Session. `snapshot.yml` declares the profile, composition/header class, recording policy, exceptional replay or input metadata, and workspace facts. Typed tokens preserve parent/child identity relationships; only header pins own prompt/schema sidecars. A mutating scenario independently compares the complete `workspace.expected/` tree, which record and refresh never rewrite. Use `test:snapshot:record` when a model transcript changes and `test:snapshot:refresh` when replay input remains valid; review every resulting diff.
+- **Web browser snapshot** (`pnpm run test:web`; required Linux PR gate): Chromium compares session-driven output under `snapshots/web/` and UI-only output under `apps/web/tests/expected/`. CI forces read-only `DSH_SNAPSHOT=replay`, never writing expected outputs; record/refresh stay local and every diff is reviewed ([web e2e lane](../.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md), [CI gate decision](../.agents/notes/implemented/testing/2026-07-30-web-browser-snapshot-ci-gate.md)). `test:web` [builds first](../.agents/notes/implemented/bug-fix/2026-07-28-themed-scrollbars-and-reserved-gutter.md) for plugin CSS.
+
+Session fixtures retain headers and payloads but omit body sequence/time envelopes; replay synthesizes them. Replay, record, and refresh select each parent/child role's highest generation. Current v2 uses `.v2`, one row per event, and embedded compact Assistant streams; retained v0 (suffixless) and v1 (`.v1`) may keep canonical packed rows for migration coverage. [The migrator](../scripts/migrate-packed-session-fixtures.ts) rewrites older historical layouts.
+
+## How specs execute
+
+Forked workers run several spec files at once, the coverage gate splits into concurrent partitions beside the other gates in its job, and the self-hosted runners share one host and one volume. Only the process is isolated: ports, predictable paths, external namespaces, and inherited children are not. Own each acquired resource through its teardown, and read a spec that passes only when it runs alone as a defect in the spec rather than an unstable runner. [dsh-ci-test-reliability](../.agents/skills/dsh-ci-test-reliability/SKILL.md) owns the allocation, restoration, synchronization, timeout-budget, platform, and teardown rules; its [flake diagnosis workflow](../.agents/skills/dsh-ci-test-reliability/references/ci-flake-diagnosis.md) classifies an existing probabilistic failure.
+
+## The with-key policy: inference is cheap here
+
+We are DeepSeek — do not ration real-API tests. A no-key test proves plumbing; only a with-key run proves the agent works against a real model. Cover file-writing prompts, multi-turn conversations, tool use, and mid-stream cancellation. Highest-value are **smoke tests** that boot a shipped `dsh` profile, send one prompt, and check the world — they catch the "green unit tests, broken product" class that mocks cannot ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md)). Self-skip keeps secretless CI and keyless contributors unblocked; it is not a cost signal. Profile-level integration tests live under `apps/cli/tests/profiles/`; package-specific compositions stay with their package tests.
+
+## Prefer the real implementation over a mock
+
+Mock only the expensive or non-deterministic boundary (LLM adapter, network, clock); keep everything downstream real. A hand-rolled stand-in proves the bridge moves bytes, not that the shipping tool behaves as asserted. Bridge tool-call tests keep the real tool registry and pipeline behind the scripted mock model: `makeBridgeHarness()` mounts the loop, session store, tool registry, and JSONL persistence with a `MockAdapter` as the only mock (packages/acp/acp/tests/harness.ts).
+
+Recovery tests separate pre/post-chunk failures by step and prove failed chunks derive no message or tool side effect. Cover exhaustion, cancellation, policy composition, persistence, status, wire counts, transport-closing idle timeouts, and shipping Loader composition.
+
+## Verify the world, not the self-report
+
+An e2e assertion re-runs the command or re-reads the file externally; a keyword probe on the agent's own output lets a cheating agent pass. Assert untouched files are byte-identical. e2e tests own their resources: create it in the test, dispose in `afterEach` (even on failure/retry/timeout); shared fixtures live in a plain `tests/harness.ts`, never another `*.e2e.ts` (importing a spec re-registers its `describe` and duplicates real API calls).
+
+## Test the real entry path
+
+- Product-visible plugins require a non-unit REAL-composition test. Hand-built `ctx.plugin(...)` suites are insufficient: boot test-only `cordis.yml` through Loader and app/process, mock only external services or nondeterministic inputs, and assert model-visible request/log, durable state, or user-visible output. Keep opt-ins out of shipped defaults.
+- A guard only guards if the regression fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green when a default export replaces the required named exports — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert.
+- "Real entry path" means the published artifact: a package `bin` runs built `lib/bin.js` under plain `node`, exposing failures tsx masks (settle races, module resolution, swallowed load failures). The same applies to non-index runtime entries (the worker-thread sibling `lib/worker.cjs`) and singleton modules shared across bundles (`packages/sdk/server/tests/built-scope-carrier.e2e.ts`). Keep the built-artifact smokes green (`packages/examples/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker-thread/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero.
+
+## Test resolution: source plane only
+
+- Every vitest config points vite-tsconfig-paths at `tsconfig.base.json`; bare workspace imports resolve to `src` ([layout](development.md#typescript-project-layout)), never through package `exports` to built `lib/` — stale artifacts there load a second copy of module singletons. Built artifacts are consumed only explicitly: `lib`-mode subprocesses and the built smokes below.
+
+## Test subprocess launch modes
+
+- CI and build-having test lanes run every profile or Cordis-config subprocess from built `lib/` through the shared dual-mode launcher. Do not hand-write `--import tsx` for these subprocesses.
+- Protocol and operating-system fixtures that do not load Cordis run erasable `.ts` directly with Node, without tsx or the root paths map.
+- Only a test whose subject is source-path resolution may select `src`; state that contract in the test.
+
+## When a snapshot test is required
+
+Every non-trivial model-, protocol-, or human-visible change adds or updates a keyless recorded-session scenario in the same PR; package, e2e, mock-only, and rationale evidence does not replace the assembled transcript. Headless, SDK, ACP, and Web recordings live under `snapshots/session/`, `snapshots/sdk/`, `snapshots/acp/`, and `snapshots/web/`; a Web rendering may explicitly borrow another scenario's canonical session. Expected output that is not driven by a recorded session stays with its owning app, package, or script under `tests/expected/` and does not use the `*.snapshot.ts` suffix. [`dsh-session-snapshot`](../packages/test-support/session-snapshot/README.md) owns the shared storage rules and profile adapters. Agent-loop, session-lifecycle, and `SessionEventMap` changes update both SDK projections: `snapshots/sdk/` owns TypeScript, while required Python-runtime CI owns `scripts/snapshots/python-sdk-single-exe/`. New capability seams and lifecycle or transcript variants name every required tier at plan time.

package/dsh-docs/testing.zh.md

@@ -0,0 +1,54 @@
+# 测试策略
+
+[English](testing.md) | 中文
+
+本文说明本仓库的分层测试方式，以及保持绿色测试套件有意义的规则。命令见根目录 [AGENTS.md](../AGENTS.md)；相关 Agent Note 承载设计动机。
+
+## 层级
+
+- **单元测试**（`pnpm run test`）：vitest 运行包和示例各自的 `tests/**` 目录下的测试，以及匹配 `scripts/**/*.spec.ts` 的仓库脚本测试；测试文件与其所覆盖的代码区域放在一起。每个注册表都有一个 HMR（热模块替换）安全测试（对向该注册表贡献内容的 fiber 执行 dispose（资源释放），并断言清理完成）。优先覆盖边界情况、错误路径、事件顺序、并发竞态，以及针对约定回归的永久测试（见 `packages/core/agent-loop/tests/contract-regressions.spec.ts`）。
+- **覆盖率门禁**（`pnpm run test:coverage`）：门禁级运行，对 `packages/*/*/src` 按文件 100% 覆盖。未覆盖的行往往是门禁正确标记出的死代码（应删除），而非需要补写的测试。行覆盖率是必要条件，但永远不是充分条件：它证明行被执行过，不证明功能按交付预期工作。`packages/shell/pwsh-local/src` 的按文件 100% 覆盖需要真实的 `pwsh`：缺少它时其执行器套件会自动跳过，`vitest.config.ts` 会豁免该文件以使无 pwsh 的主机保持绿色，而 CI runner 自带 pwsh，仍按完整标准执行门禁。
+- **真实 API e2e**（`pnpm run test:e2e`）：带密钥测试调用真实提供方 API，包括 DeepSeek 模型以及各提供方特有的冒烟测试；这些测试各自由自己的密钥控制（`EXA_API_KEY`、`PERPLEXITY_API_KEY` 等），缺少密钥时套件会自动跳过，使 keyless CI 保持绿色（[真实 API e2e Agent Note](../.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.zh.md)）。
+- **所属位置的预期输出**（`pnpm run test:expected`）：无录制会话往返的无密钥组装 CLI/进程预期。驱动使用 `*.expected.e2e.ts`，并与 `tests/expected/` 同属一处；CI 针对构建产物运行。包/脚本预期使用 `test`，浏览器预期使用 `test:web`。
+- **快照**（`pnpm run test:snapshot`）：顶层场景数值最高的已录制 parent generation 同时提供用户输入和模型回放，并作为持久化结果的预期值。parent 文件名是 `session[.vN].jsonl`；child 角色使用 `session.<ordinal>[.vN].jsonl`；v0 省略 `.v0`，正版本必须使用小写 `.vN`，且每个文件名必须与其 header 一致。进程级场景都通过 `dsh` 启动：headless 负责一次性行为，SDK 负责持久控制，ACP 负责自动化协议行为，Web 在同一 Session 旁保留浏览器与 ARIA 证据。`snapshot.yml` 声明 profile、组合与请求头类别、录制策略、例外回放或输入元数据以及 workspace 事实。带类型的 token 保留父子身份关系；只有请求头 pin 拥有 prompt/schema sidecar。变更 workspace 的场景会独立比较完整的 `workspace.expected/` 目录，record 与 refresh 绝不改写该目录。当模型 transcript（文本记录）变化时使用 `test:snapshot:record`，回放输入仍有效时使用 `test:snapshot:refresh`；请审查所有结果差异。
+- **Web 浏览器快照**（`pnpm run test:web`；必需的 Linux PR（Pull Request）门禁）：Chromium 比较 `snapshots/web/` 下由会话驱动的输出，以及 `apps/web/tests/expected/` 下仅含 UI 的输出。CI 强制只读的 `DSH_SNAPSHOT=replay`，绝不写入预期输出；record/refresh 留在本地，每处 diff 都须评审（[web e2e 车道](../.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.zh.md)、[CI 门禁决策](../.agents/notes/implemented/testing/2026-07-30-web-browser-snapshot-ci-gate.zh.md)）。`test:web` 会[先构建](../.agents/notes/implemented/bug-fix/2026-07-28-themed-scrollbars-and-reserved-gutter.zh.md)以交付插件 CSS。
+
+Session fixture 保留 header 与 payload，但省略正文 seq/time envelope；replay 会合成这些 envelope。Replay、record 与 refresh 会选择每个 parent/child 角色的最高 generation。当前 v2 使用 `.v2`、每个事件一行，并嵌入紧凑 Assistant stream；保留的 v0（无后缀）与 v1（`.v1`）可以为迁移覆盖保留规范 packed row。[迁移器](../scripts/migrate-packed-session-fixtures.ts)会改写更旧的历史布局。
+
+## spec 如何被执行
+
+fork 出的 worker 会同时运行多个 spec 文件，coverage gate 会拆成并发的 partition，与同一个 job 中的其它 gate 并排运行，而自托管 runner 共用同一台宿主机和同一个卷。被隔离的只有进程：端口、可预测路径、外部命名空间和继承而来的子进程都不隔离。为每个占用的资源负责到它的 teardown，并把「只有单独运行时才通过」的 spec 读作该 spec 的缺陷，而不是 runner 不稳定。[dsh-ci-test-reliability](../.agents/skills/dsh-ci-test-reliability/SKILL.md) 负责资源分配、状态恢复、同步、超时预算、平台差异与 teardown 规则；它的 [flake 诊断流程](../.agents/skills/dsh-ci-test-reliability/references/ci-flake-diagnosis.md)用于归类已经存在的概率性失败。
+
+## 带密钥策略：推理（inference）在这里很便宜
+
+我们是 DeepSeek，不要吝惜真实 API 测试。无密钥测试只能证明底层通路；只有带密钥运行才能证明 agent（智能体）能对接真实模型正常工作。覆盖文件写入提示词、包含多个轮次的对话、工具使用和流中取消。价值最高的是**冒烟测试**：启动已交付的 `dsh` profile、发送一条提示词，并检查外部世界；它们能捕获「单元测试全绿、产品却坏了」这一类 mock 无法发现的问题（[事故复盘 0001](postmortem/0001-acp-default-export-drops-inject.zh.md)）。自动跳过让无密钥 CI 和无密钥贡献者不受阻塞；它不是成本信号。Profile 级集成测试位于 `apps/cli/tests/profiles/`；包专属组合留在对应包的测试目录中。
+
+## 优先使用真实实现而非 mock
+
+只 mock 开销高或不确定的边界（LLM（大语言模型）适配器、网络、时钟）；下游一切保持真实。手写替身只能证明桥接层在搬运字节，不能证明交付的工具行为符合断言。桥接工具调用测试把真实的工具注册表与执行管线保留在脚本化 mock 模型下游：`makeBridgeHarness()`（packages/acp/acp/tests/harness.ts）挂载 agent loop、会话存储、工具注册表与 JSONL 持久化，唯一 mock 是脚本化 `MockAdapter`。
+
+恢复测试按步骤区分分片前与分片后的失败，并证明失败分片不会派生出消息或工具副作用。覆盖耗尽、取消、策略组合、持久化、状态、协议计数、会关闭传输的空闲超时，以及交付的 Loader 组合。
+
+## 验证外部世界，而非自我报告
+
+e2e 断言应重新运行命令或从外部重新读取文件；对 agent 自身输出做关键词探测会让作弊的 agent 通过。断言未修改的文件逐字节一致。e2e 测试自行管理资源：在测试中创建 harness，在 `afterEach` 中 dispose（即使失败/重试/超时也要释放）；共享 fixture 放在普通的 `tests/harness.ts` 中，绝不放在另一个 `*.e2e.ts` 中（导入一个 spec 会重新注册其 `describe`，导致真实 API 调用重复执行）。
+
+## 测试真实入口路径
+
+- 产品可见的插件必须有一个非单元的真实组合测试。手动构建的 `ctx.plugin(...)` 套件不够：通过 Loader 和 app/process 启动仅用于测试的 `cordis.yml`，只 mock 外部服务或非确定性输入，断言模型可见的请求/日志、持久状态或用户可见输出。不要把 opt-in 选项混入交付默认值。
+- 一个守卫只有在回归能让它失败时才有效。对于没有 `inject` 的插件（bundle/组合插件），Loader 冒烟测试在默认导出替换必需的具名导出时仍然绿着——需要添加显式的 `expect('default' in mod).toBe(false)` 加 `unwrapExports` 往返断言，并证明它有效：引入回归、观察变红、回退。
+- 「真实入口路径」指已发布的产物：包的 `bin` 所运行的是构建后的 `lib/bin.js`，并由普通 `node` 执行，从而暴露 tsx 会掩盖的失败（结算竞态、模块解析、被吞掉的加载失败）。同样的规则适用于非 index 运行时入口（worker-thread 的同级文件 `lib/worker.cjs`），也适用于多个 bundle 共享的单例模块（`packages/sdk/server/tests/built-scope-carrier.e2e.ts`）。保持构建产物冒烟测试绿色（`packages/examples/*/tests/built-bin.e2e.ts`、`packages/code-runtime/code-runtime-worker-thread/tests/built-lib.e2e.ts`），并断言真正缺失的配置以非零状态退出。
+
+## 测试解析：仅限源码
+
+- 每个 vitest 配置都将 vite-tsconfig-paths 指向 `tsconfig.base.json`；工作区包的裸导入解析到 `src`（[布局](development.zh.md#typescript-project-layout)），绝不会经由包的 `exports` 解析到构建后的 `lib/`，因为其中的陈旧产物会加载第二份模块单例。构建产物只在显式指定时使用：以 `lib` 模式运行的子进程，以及下文的构建产物冒烟测试。
+
+## 测试子进程启动模式
+
+- CI 与已有构建产物的测试通道通过共享双模式启动器，从构建后的 `lib/` 运行每个 profile 或 Cordis 配置子进程。不要为这些子进程手写 `--import tsx`。
+- 不加载 Cordis 的协议与操作系统 fixture 直接通过 Node 运行使用可擦除语法的 `.ts` 文件，不经过 tsx 或根路径映射。
+- 只有测试对象本身是源码路径解析时，才可以选择 `src`；在测试中写明这一约定。
+
+## 何时需要快照测试
+
+每项非平凡的模型可见、协议可见或人类可见变更，都在同一 PR 中添加或更新无密钥录制会话场景；包级、e2e、仅 mock 和 PR 理由证据不能取代组装后的 transcript。Headless、SDK、ACP 和 Web 录制分别位于 `snapshots/session/`、`snapshots/sdk/`、`snapshots/acp/` 和 `snapshots/web/`；Web 渲染可以显式借用另一个场景的规范会话。不由录制会话驱动的预期输出保留在所属应用、包或脚本的 `tests/expected/` 下，并且不使用 `*.snapshot.ts` 后缀。[`dsh-session-snapshot`](../packages/test-support/session-snapshot/README.zh.md) 拥有共享存储规则和 profile 适配器。Agent loop、会话生命周期和 `SessionEventMap` 变更应更新两个 SDK 投影：`snapshots/sdk/` 拥有 TypeScript，必需的 Python 运行时 CI 拥有 `scripts/snapshots/python-sdk-single-exe/`。新增 capability seam、生命周期或 transcript 变体应在计划阶段列出每个必需层级。