From 6e577843c83d57cc69bc3b4cfa2e843d10f41e53 Mon Sep 17 00:00:00 2001 From: Turtle Date: Fri, 31 Jul 2026 16:09:05 +0800 Subject: [PATCH 01/45] feat(session-query): expose projectSessions batch projection Public SessionQueryService.projectSessions wraps the existing corpus projectMany: one persistence listing, bounded persisted-inspect concurrency, per-id failure isolation, and a synchronous projector over a borrowed source with no replay validation or cloning. readTitleSnapshots now routes through it; LogicalSessionSource and LogicalProjectionResult are exported and documented. --- docs/cordis-catalog/services.md | 21 ++++++++++++-- .../session-query.i18n.yaml | 6 ++-- docs/core-data-structures/session-query.md | 19 +++++++++++++ docs/core-data-structures/session-query.zh.md | 19 +++++++++++++ .../cordis/tool-cordis/src/api-catalog.ts | 12 ++++++++ .../session-query/README.i18n.yaml | 4 +-- .../session-query/session-query/README.md | 3 +- .../session-query/session-query/README.zh.md | 3 +- .../session-query/session-query/src/index.ts | 28 +++++++++++++++++-- .../session-query/tests/session-query.spec.ts | 27 ++++++++++++++++++ scripts/gen-cordis-catalog.ts | 2 ++ scripts/type-equiv.manifest.json | 10 +++++++ 12 files changed, 143 insertions(+), 11 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index d92f467469..000c12f27a 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -1442,6 +1442,23 @@ async readTitleSnapshot( sessionId: SessionId, signal?: AbortSignal, ): Promise< */ async readTitleSnapshots( sessionIds: readonly SessionId[], signal?: AbortSignal, ): Promise +/** + * Project unique logical sessions synchronously from one cancellable corpus + * observation. + * + * Each source is a borrowed raw log without replay validation or cloning, so + * a batch summary costs one bounded read per persisted session instead of a + * full validated copy; the projector must clone anything it retains beyond + * its own call. Results preserve first-occurrence input order. Operational + * failures stay isolated per session, while cancellation rejects the + * complete operation. + * @param sessionIds - live or persisted session ids to observe. + * @param project - synchronous fold that owns/clones every retained value. + * @param signal - optional cancellation shared by all source reads. + * @returns one fulfilled or rejected result per unique requested id. + */ +async projectSessions( sessionIds: readonly SessionId[], project: (source: LogicalSessionSource) => Value, signal?: AbortSignal, ): Promise[]> + /** * List lightweight raw-log event records for one logical session. * @param sessionId - live-preferred session id to read. @@ -1492,9 +1509,9 @@ async traceEvent(request: SessionEventTraceRequest, signal?: AbortSignal): Promi async readEvent(request: SessionEventReadRequest, signal?: AbortSignal): Promise ``` -Types: [SessionEventReadRequest](../core-data-structures/session-query.md) · [SessionEventRecord](../core-data-structures/session-query.md) · [SessionEventResultFilter](../core-data-structures/session-query.md) · [SessionEventSearchDocument](../core-data-structures/session-query.md) · [SessionEventSearchPage](../core-data-structures/session-query.md) · [SessionEventSearchRequest](../core-data-structures/session-query.md) · [SessionEventTraceObservation](../core-data-structures/session-query.md) · [SessionEventTraceRequest](../core-data-structures/session-query.md) · [SessionEventWindow](../core-data-structures/session-query.md) · [SessionId](../core-data-structures/core.md) · [SessionLineageTrace](../core-data-structures/session-query.md) · [SessionLogSnapshot](../core-data-structures/session-query.md) · [SessionRecord](../core-data-structures/session-query.md) · [SessionResultFilter](../core-data-structures/session-query.md) · [SessionSearchExecContext](../core-data-structures/session-query.md) · [SessionSearchHit](../core-data-structures/session-query.md) · [SessionSearchPage](../core-data-structures/session-query.md) · [SessionSearchRequest](../core-data-structures/session-query.md) · [SessionSurfaceSnapshot](../core-data-structures/session-query.md) · [SessionTitleObservation](../core-data-structures/session-query.md) · [SessionTitleObservationResult](../core-data-structures/session-query.md) · [SessionTitleSnapshot](../core-data-structures/session-title.md) +Types: [LogicalProjectionResult](../core-data-structures/session-query.md) · [LogicalSessionSource](../core-data-structures/session-query.md) · [SessionEventReadRequest](../core-data-structures/session-query.md) · [SessionEventRecord](../core-data-structures/session-query.md) · [SessionEventResultFilter](../core-data-structures/session-query.md) · [SessionEventSearchDocument](../core-data-structures/session-query.md) · [SessionEventSearchPage](../core-data-structures/session-query.md) · [SessionEventSearchRequest](../core-data-structures/session-query.md) · [SessionEventTraceObservation](../core-data-structures/session-query.md) · [SessionEventTraceRequest](../core-data-structures/session-query.md) · [SessionEventWindow](../core-data-structures/session-query.md) · [SessionId](../core-data-structures/core.md) · [SessionLineageTrace](../core-data-structures/session-query.md) · [SessionLogSnapshot](../core-data-structures/session-query.md) · [SessionRecord](../core-data-structures/session-query.md) · [SessionResultFilter](../core-data-structures/session-query.md) · [SessionSearchExecContext](../core-data-structures/session-query.md) · [SessionSearchHit](../core-data-structures/session-query.md) · [SessionSearchPage](../core-data-structures/session-query.md) · [SessionSearchRequest](../core-data-structures/session-query.md) · [SessionSurfaceSnapshot](../core-data-structures/session-query.md) · [SessionTitleObservation](../core-data-structures/session-query.md) · [SessionTitleObservationResult](../core-data-structures/session-query.md) · [SessionTitleSnapshot](../core-data-structures/session-title.md) -Source: [`packages/session-query/session-query/src/index.ts:81`](../../packages/session-query/session-query/src/index.ts) +Source: [`packages/session-query/session-query/src/index.ts:82`](../../packages/session-query/session-query/src/index.ts) ## `ctx.sessionReferences` — `SessionReferenceService` diff --git a/docs/core-data-structures/session-query.i18n.yaml b/docs/core-data-structures/session-query.i18n.yaml index f9c7355148..fc00c40e0a 100644 --- a/docs/core-data-structures/session-query.i18n.yaml +++ b/docs/core-data-structures/session-query.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -session-query.md: d92af4bac34f7d41457e9e193111c3a53fe8022e -session-query.zh.md: ecf330b0a361ffae352a91c0d35524444936606d +# pnpm run verify-translation-pairing --write docs/core-data-structures/session-query.md +session-query.md: cffbd792e8cab6e79365ceb4e0b1d996e7e93cf5 +session-query.zh.md: 2b67761ec3bcd96ee9de15511ec44516f1fe525d diff --git a/docs/core-data-structures/session-query.md b/docs/core-data-structures/session-query.md index d92af4bac3..cffbd792e8 100644 --- a/docs/core-data-structures/session-query.md +++ b/docs/core-data-structures/session-query.md @@ -84,6 +84,25 @@ type SessionTitleObservationResult = } ``` +`projectSessions` batches arbitrary synchronous folds over the same live-preferred corpus: each `LogicalSessionSource` is a borrowed raw log — never replay-validated or cloned — that is valid only for the projector call, so a batch summary costs one bounded read per persisted session. Each `LogicalProjectionResult` settles per unique requested id under the same isolation and cancellation rules as batch title reads. + +```ts type-equiv +/** Borrowed source visible only during one synchronous batch projection. */ +interface LogicalSessionSource { + /** Header selected with `events`; callers must clone retained output. */ + readonly header: SessionHeader + /** Raw events selected with `header`; valid only for the projection call. */ + readonly events: readonly SessionEvent[] +} +``` + +```ts type-equiv +/** One source-projection result in a batch logical-corpus observation. */ +type LogicalProjectionResult = + | { sessionId: SessionId; status: 'fulfilled'; value: Value } + | { sessionId: SessionId; status: 'rejected'; reason: unknown } +``` + ```ts type-equiv /** Lightweight metadata for one event within a logical session. */ interface SessionEventRecord { diff --git a/docs/core-data-structures/session-query.zh.md b/docs/core-data-structures/session-query.zh.md index ecf330b0a3..2b67761ec3 100644 --- a/docs/core-data-structures/session-query.zh.md +++ b/docs/core-data-structures/session-query.zh.md @@ -84,6 +84,25 @@ type SessionTitleObservationResult = } ``` +`projectSessions` 在同一实时优先语料库上批量执行任意同步折叠：每个 `LogicalSessionSource` 都是借用的原始日志——从不做回放验证，也从不克隆——仅在投影函数调用期间有效，因此一次批量摘要对每个持久化会话只需一次有界读取。每个 `LogicalProjectionResult` 按唯一请求 id 结算，其失败隔离与取消规则与批量标题读取一致。 + +```ts type-equiv +/** Borrowed source visible only during one synchronous batch projection. */ +interface LogicalSessionSource { + /** Header selected with `events`; callers must clone retained output. */ + readonly header: SessionHeader + /** Raw events selected with `header`; valid only for the projection call. */ + readonly events: readonly SessionEvent[] +} +``` + +```ts type-equiv +/** One source-projection result in a batch logical-corpus observation. */ +type LogicalProjectionResult = + | { sessionId: SessionId; status: 'fulfilled'; value: Value } + | { sessionId: SessionId; status: 'rejected'; reason: unknown } +``` + ```ts type-equiv /** Lightweight metadata for one event within a logical session. */ interface SessionEventRecord { diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index b888f33ed4..10c2a0bdcf 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -678,6 +678,10 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ signature: 'async readTitleSnapshots( sessionIds: readonly SessionId[], signal?: AbortSignal, ): Promise', jsDoc: '/**\n * Fold titles for unique sessions from one cancellable corpus observation.\n *\n * Results preserve first-occurrence input order. Operational failures stay\n * isolated per session, while cancellation rejects the complete operation.\n * @param sessionIds - live or persisted session ids to observe.\n * @param signal - optional cancellation shared by all source reads.\n * @returns one fulfilled or rejected result per unique requested id.\n */', }, + { + signature: 'async projectSessions( sessionIds: readonly SessionId[], project: (source: LogicalSessionSource) => Value, signal?: AbortSignal, ): Promise[]>', + jsDoc: '/**\n * Project unique logical sessions synchronously from one cancellable corpus\n * observation.\n *\n * Each source is a borrowed raw log without replay validation or cloning, so\n * a batch summary costs one bounded read per persisted session instead of a\n * full validated copy; the projector must clone anything it retains beyond\n * its own call. Results preserve first-occurrence input order. Operational\n * failures stay isolated per session, while cancellation rejects the\n * complete operation.\n * @param sessionIds - live or persisted session ids to observe.\n * @param project - synchronous fold that owns/clones every retained value.\n * @param signal - optional cancellation shared by all source reads.\n * @returns one fulfilled or rejected result per unique requested id.\n */', + }, { signature: 'async listEvents(sessionId: SessionId): Promise', jsDoc: '/**\n * List lightweight raw-log event records for one logical session.\n * @param sessionId - live-preferred session id to read.\n * @returns event records in ascending seq order.\n */', @@ -2055,6 +2059,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'LlmResolvedModelInfo', declaration: 'export interface LlmResolvedModelInfo extends LlmModelInfo {\n context?: LlmModelContext;\n defaultMaxTokens?: number;\n reasoning?: LlmModelReasoningInfo;\n}', }, + { + name: 'LogicalProjectionResult', + declaration: 'export type LogicalProjectionResult = {\n sessionId: SessionId;\n status: \'fulfilled\';\n value: Value;\n} | {\n sessionId: SessionId;\n status: \'rejected\';\n reason: unknown;\n};', + }, + { + name: 'LogicalSessionSource', + declaration: 'export interface LogicalSessionSource {\n readonly header: SessionHeader;\n readonly events: readonly SessionEvent[];\n}', + }, { name: 'Message', declaration: 'export interface Message {\n readonly id: MessageId;\n readonly role: \'system\' | \'user\' | \'assistant\';\n readonly content: ContentBlock[];\n readonly source: MessageSource;\n}', diff --git a/packages/session-query/session-query/README.i18n.yaml b/packages/session-query/session-query/README.i18n.yaml index fb266a82de..0ac53ddb14 100644 --- a/packages/session-query/session-query/README.i18n.yaml +++ b/packages/session-query/session-query/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/session-query/session-query/README.md -README.md: df97333be3b2c2cf71dd8c9287959bcbd83a5063 -README.zh.md: 1a3df1ce38360975d88a9f578b071b29cefbba0f +README.md: 15ab403100b45e35808e95f84dcd8ab521854c66 +README.zh.md: 5e3cbfa0d13ba4884d0eb2cc1b4506fbfdef2446 diff --git a/packages/session-query/session-query/README.md b/packages/session-query/session-query/README.md index df97333be3..15ab403100 100644 --- a/packages/session-query/session-query/README.md +++ b/packages/session-query/session-query/README.md @@ -11,13 +11,14 @@ English | [中文](README.zh.md) - `filterSessions(filters, signal?)` applies provider-independent session metadata and availability predicates to that same cloned logical corpus. - `filterEvents(sessionId, filters)` extracts first-party semantic documents and applies provider-independent metadata and literal-text predicates in ascending seq order. - `readTitleSnapshots(sessionIds, signal?)` resolves unique ids from one live-preferred corpus observation, passes cancellation through persisted listing and inspection, and returns ordered per-session settlements so one missing or malformed title source does not discard its peers. Each live source is folded directly, and each persisted worker folds to a detached header/title result and releases the full log before dequeuing another id. Cancellation rejects the whole batch. `readTitleSnapshot(sessionId, signal?)` is the one-observation view; `readTitle(sessionId, signal?)` returns only its optional folded `session/title`. +- `projectSessions(sessionIds, project, signal?)` runs one synchronous caller fold per unique id under the same batched corpus observation, isolation, and cancellation rules as `readTitleSnapshots`. Each source is a borrowed raw log — never replay-validated or cloned — valid only for the projector call, so a batch summary (for example the resume selector) scales with what the projector retains instead of total log size; the projector must clone anything it keeps. - `listEvents(sessionId)` loads the live-preferred raw log and classifies each event as `current`, `shadowed`, or `log-only` with the shared `dsh-session` surface fold. - `readSurface(sessionId)` returns one cloned header, raw-log capture boundary, and the complete folded current surface in model-history order. A live session wins over persistence; compaction is observed before or after its replacement append, never as a synthetic mixture. - `readEvent(request, signal?)` returns a cloned header, the full target event, and a bounded raw-seq window. `before` and `after` default to zero and may not exceed `readWindowMax`. - `traceSession(sessionId, signal?)` reads the corpus once and returns immediate-to-outward ancestors plus deterministic recursive descendant trees. `complete: false` identifies the first missing parent; a target-connected cycle fails with `SESSION_QUERY_INVALID_LINEAGE`. - `traceEvent(request, signal?)` loads the logical log once and returns its cloned source header with direct positional replacements and direct logged provenance. `replacementChain` follows positional replacers to the final replacement; provenance links remain non-transitive. -Persistence is optional and may mount or unmount dynamically. Cross-corpus listing and lineage tracing fail with `SESSION_QUERY_PERSISTENCE_FAILED` while mounted persistence is unreadable. A title read, event trace, or event read targeting a known live session does not consult persistence, so durable backend health cannot make current in-memory state unreadable. Persisted title and event operations list before loading and reject a metadata mismatch rather than combining inconsistent observations. Lineage-trace cancellation is passed to persisted listing; event-trace and event-read cancellation is passed to persisted listing and inspection. Each waits for the started backend call to settle, then rejects with the signal's exact reason even when the backend ignored that signal. A pre-aborted known-live title read, event trace, or event read rejects before folding or snapshotting without consulting persistence. A batch title observation performs one metadata listing, inspects its unique persisted ids with at most `persistedInspectConcurrency` workers, and preserves each title's own observed header for downstream authorization. Cancellation starts no queued inspections and rejects only after already-started workers settle. `listSessions()` remains lightweight and does not load logs or index titles. +Persistence is optional and may mount or unmount dynamically. Cross-corpus listing and lineage tracing fail with `SESSION_QUERY_PERSISTENCE_FAILED` while mounted persistence is unreadable. A title read, event trace, or event read targeting a known live session does not consult persistence, so durable backend health cannot make current in-memory state unreadable. Persisted title and event operations list before loading and reject a metadata mismatch rather than combining inconsistent observations. Lineage-trace cancellation is passed to persisted listing; event-trace and event-read cancellation is passed to persisted listing and inspection. Each waits for the started backend call to settle, then rejects with the signal's exact reason even when the backend ignored that signal. A pre-aborted known-live title read, event trace, or event read rejects before folding or snapshotting without consulting persistence. A batch observation — titles or caller projections — performs one metadata listing, inspects its unique persisted ids with at most `persistedInspectConcurrency` workers, and preserves each result's own observed header for downstream authorization. Cancellation starts no queued inspections and rejects only after already-started workers settle. `listSessions()` remains lightweight and does not load logs or index titles. ## Filtering and extraction diff --git a/packages/session-query/session-query/README.zh.md b/packages/session-query/session-query/README.zh.md index 1a3df1ce38..5e3cbfa0d1 100644 --- a/packages/session-query/session-query/README.zh.md +++ b/packages/session-query/session-query/README.zh.md @@ -11,13 +11,14 @@ - `filterSessions(filters, signal?)` 对同一份克隆逻辑语料库应用与提供方无关的会话元数据和可用性谓词。 - `filterEvents(sessionId, filters)` 提取第一方语义文档，并按 seq 升序应用与提供方无关的元数据和字面文本谓词。 - `readTitleSnapshots(sessionIds, signal?)` 从一次实时优先的语料库观察中解析唯一 id，将取消信号传递给持久化列表查询和检查，并按顺序返回每个会话的结算结果，使某个缺失或格式错误的标题来源不会丢弃其他来源。每个实时来源直接 fold，每个持久化 worker fold 为脱离存储的 header/标题结果，并在出队下一个 id 前释放完整日志。取消会拒绝整个批次。`readTitleSnapshot(sessionId, signal?)` 是单次观察视图；`readTitle(sessionId, signal?)` 只返回其可选的 folded `session/title`。 +- `projectSessions(sessionIds, project, signal?)` 按唯一 id 各执行一次调用方的同步 fold，其批量语料库观察、失败隔离和取消规则与 `readTitleSnapshots` 相同。每个来源都是借用的原始日志——从不做回放验证，也从不克隆——仅在投影函数调用期间有效，因此一次批量摘要（例如恢复选择器）的开销取决于投影函数保留的内容，而不是日志总大小；投影函数必须克隆它要保留的任何值。 - `listEvents(sessionId)` 加载实时优先的原始日志，将每个事件分类为 `current`、`shadowed` 或 `log-only`；该分类使用共享 `dsh-session` 表层 fold。 - `readSurface(sessionId)` 返回一个克隆 header、原始日志捕获边界，以及按模型历史顺序排列的完整折叠后当前表层。实时会话优先于持久化；压缩（compaction）只会在其替换追加之前或之后被观察，绝不会出现合成混合。 - `readEvent(request, signal?)` 返回一个克隆 header、完整目标事件和有界的原始 seq 窗口。`before` 和 `after` 默认为 0，且不得超过 `readWindowMax`。 - `traceSession(sessionId, signal?)` 只读取一次语料库，返回从直接父级向外的祖先，以及确定性的递归后代树。`complete: false` 标识第一个缺失父级；与目标相连的循环会以 `SESSION_QUERY_INVALID_LINEAGE` 失败。 - `traceEvent(request, signal?)` 只加载一次逻辑日志，返回其克隆源 header、直接位置替换和直接已记录来源信息。`replacementChain` 沿位置替换者跟踪到最终替换；来源链接仍不传递。 -持久化是可选的，可动态挂载或卸载。已挂载持久化无法读取时，跨语料库列表和血缘跟踪以 `SESSION_QUERY_PERSISTENCE_FAILED` 失败。针对已知实时会话的标题读取、事件跟踪或事件读取不会查询持久化，因此持久化后端的健康状态无法使当前内存状态变得不可读。持久化标题和事件操作在加载前先执行列表查询，并在元数据不匹配时拒绝，而不会组合不一致的观察。血缘跟踪的取消信号会传递给持久化列表查询；事件跟踪和事件读取的取消信号会传递给持久化列表查询和检查。每项操作都会等待已启动的后端调用结算，然后使用信号的精确原因拒绝，即使后端忽略了该信号。针对已知实时会话且预先中止的标题读取、事件跟踪或事件读取会在 fold 或快照之前拒绝，且不查询持久化。批量标题观察执行一次元数据列表查询，使用最多 `persistedInspectConcurrency` 个 worker 检查唯一持久化 id，并保留每个标题自己观察到的 header，供下游授权使用。取消不会启动已排队检查，且只在已启动 worker 结算后拒绝。`listSessions()` 仍保持轻量，不加载日志或索引标题。 +持久化是可选的，可动态挂载或卸载。已挂载持久化无法读取时，跨语料库列表和血缘跟踪以 `SESSION_QUERY_PERSISTENCE_FAILED` 失败。针对已知实时会话的标题读取、事件跟踪或事件读取不会查询持久化，因此持久化后端的健康状态无法使当前内存状态变得不可读。持久化标题和事件操作在加载前先执行列表查询，并在元数据不匹配时拒绝，而不会组合不一致的观察。血缘跟踪的取消信号会传递给持久化列表查询；事件跟踪和事件读取的取消信号会传递给持久化列表查询和检查。每项操作都会等待已启动的后端调用结算，然后使用信号的精确原因拒绝，即使后端忽略了该信号。针对已知实时会话且预先中止的标题读取、事件跟踪或事件读取会在 fold 或快照之前拒绝，且不查询持久化。批量观察——标题或调用方投影——执行一次元数据列表查询，使用最多 `persistedInspectConcurrency` 个 worker 检查唯一持久化 id，并保留每个结果自己观察到的 header，供下游授权使用。取消不会启动已排队检查，且只在已启动 worker 结算后拒绝。`listSessions()` 仍保持轻量，不加载日志或索引标题。 ## 过滤与提取 diff --git a/packages/session-query/session-query/src/index.ts b/packages/session-query/session-query/src/index.ts index 809971b798..cf3dd95e39 100644 --- a/packages/session-query/session-query/src/index.ts +++ b/packages/session-query/session-query/src/index.ts @@ -36,7 +36,7 @@ import { SessionQueryError, type Config, } from './config.ts' -import { SessionCorpus } from './corpus.ts' +import { SessionCorpus, type LogicalProjectionResult, type LogicalSessionSource } from './corpus.ts' import { buildSessionEventSearchDocuments } from './documents.ts' import { filterSessionEventDocuments, @@ -64,6 +64,7 @@ export { materializeSessionResultFilters, } from './filters.ts' export { assertSessionHeadersCompatible } from './sources.ts' +export type { LogicalProjectionResult, LogicalSessionSource } from './corpus.ts' declare module 'cordis' { interface Context { @@ -205,7 +206,7 @@ export abstract class SessionQueryService extends Service { sessionIds: readonly SessionId[], signal?: AbortSignal, ): Promise { - return this._corpus.projectMany(sessionIds, (source): SessionTitleObservation => { + return this.projectSessions(sessionIds, (source): SessionTitleObservation => { const title = foldSessionTitle(source.events) return { session: structuredClone(source.header), @@ -214,6 +215,29 @@ export abstract class SessionQueryService extends Service { }, signal) } + /** + * Project unique logical sessions synchronously from one cancellable corpus + * observation. + * + * Each source is a borrowed raw log without replay validation or cloning, so + * a batch summary costs one bounded read per persisted session instead of a + * full validated copy; the projector must clone anything it retains beyond + * its own call. Results preserve first-occurrence input order. Operational + * failures stay isolated per session, while cancellation rejects the + * complete operation. + * @param sessionIds - live or persisted session ids to observe. + * @param project - synchronous fold that owns/clones every retained value. + * @param signal - optional cancellation shared by all source reads. + * @returns one fulfilled or rejected result per unique requested id. + */ + async projectSessions( + sessionIds: readonly SessionId[], + project: (source: LogicalSessionSource) => Value, + signal?: AbortSignal, + ): Promise[]> { + return this._corpus.projectMany(sessionIds, project, signal) + } + /** * List lightweight raw-log event records for one logical session. * @param sessionId - live-preferred session id to read. diff --git a/packages/session-query/session-query/tests/session-query.spec.ts b/packages/session-query/session-query/tests/session-query.spec.ts index 2713de9a72..0613673f88 100644 --- a/packages/session-query/session-query/tests/session-query.spec.ts +++ b/packages/session-query/session-query/tests/session-query.spec.ts @@ -548,6 +548,33 @@ describe('session-query exact reads', () => { expect(TestPersistence.inspectSignals).toEqual([signal, signal]) }) + it('projects borrowed raw logs in one corpus scan with per-session failure isolation', async () => { + const persisted = header('project-persisted', 1) + TestPersistence.reset([{ meta: persisted, events: eventLog('persisted-projection') }]) + const ctx = await liveContext() + const live = ctx.sessions.create(SessionId('project-live'), { meta: { createdAt: 2 } }) + live.append('session/title', { + title: 'Live projection', + messageSeqs: [], + source: { kind: 'fallback' }, + }) + await ctx.plugin(TestPersistence) + const missing = SessionId('project-missing') + + const results = await ctx.sessionQuery.projectSessions( + [live.id, persisted.id, missing], + source => ({ id: source.header.id, eventCount: source.events.length }), + ) + + expect(results).toMatchObject([ + { sessionId: live.id, status: 'fulfilled', value: { id: live.id, eventCount: 1 } }, + { sessionId: persisted.id, status: 'fulfilled', value: { id: persisted.id, eventCount: 1 } }, + { sessionId: missing, status: 'rejected' }, + ]) + expect(TestPersistence.listCalls).toBe(1) + expect(TestPersistence.inspectCalls).toEqual([persisted.id]) + }) + it('bounds persisted title inspection concurrency while preserving ordered results', async () => { const entries = Array.from({ length: 12 }, (_, index) => { const meta = header(`bounded-title-${index}`, index) diff --git a/scripts/gen-cordis-catalog.ts b/scripts/gen-cordis-catalog.ts index 86368b03ed..a5a17bbb5a 100644 --- a/scripts/gen-cordis-catalog.ts +++ b/scripts/gen-cordis-catalog.ts @@ -55,6 +55,8 @@ export const LINK_MAP: Readonly> = { SessionEvent: 'core.md', SessionId: 'core.md', SessionStartSource: 'core.md', + LogicalProjectionResult: 'session-query.md', + LogicalSessionSource: 'session-query.md', SessionLogSnapshot: 'session-query.md', SessionSurfaceSnapshot: 'session-query.md', ApprovalOutcome: 'approval.md', diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index d18bd54268..d511bfecaa 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -449,6 +449,16 @@ "symbol": "SessionTitleObservationResult", "source": "packages/session-query/session-query/src/types.ts" }, + { + "doc": "docs/core-data-structures/session-query.md", + "symbol": "LogicalSessionSource", + "source": "packages/session-query/session-query/src/corpus.ts" + }, + { + "doc": "docs/core-data-structures/session-query.md", + "symbol": "LogicalProjectionResult", + "source": "packages/session-query/session-query/src/corpus.ts" + }, { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionEventRecord", From 3c08ca36066da90664b6426513cc4c83518f6057 Mon Sep 17 00:00:00 2001 From: Turtle Date: Fri, 31 Jul 2026 16:09:17 +0800 Subject: [PATCH 02/45] perf(tui): open the /resume selector from one batch projection The selector called readSession per listed session under an unbounded Promise.all: each call re-listed the whole persistence store (O(N^2) listings), decompressed and parsed the complete log, replay-validated every event, and deep-cloned it up to three times, only to derive one row's title, activity time, turn label, route, and goal phase. On a real 185-session / 87 MB store the selector took tens of seconds. Candidate rows now come from one projectSessions batch over borrowed logs; a rejected projection degrades to the same disabled unreadable row. Preflight still replay-validates the single chosen session through readSession, which is already live-preferred, so its redundant live shortcut is gone. --- ...resume-selector-batch-projection.i18n.yaml | 6 ++ ...-07-31-resume-selector-batch-projection.md | 27 ++++++ ...-31-resume-selector-batch-projection.zh.md | 27 ++++++ packages/ui/tui/src/chat/resume.ts | 89 +++++++++++-------- packages/ui/tui/src/components/dialogs.ts | 36 ++++---- packages/ui/tui/tests/tui.spec.ts | 56 ++++++++---- 6 files changed, 173 insertions(+), 68 deletions(-) create mode 100644 .agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml create mode 100644 .agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md create mode 100644 .agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml new file mode 100644 index 0000000000..c0faa37e8d --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# 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/bug-fix/2026-07-31-resume-selector-batch-projection.md +2026-07-31-resume-selector-batch-projection.md: 0aad3d57079819165d345d494071eb04d0b50abd +2026-07-31-resume-selector-batch-projection.zh.md: 055e11c440114987c0c37a2d268bce3328d4b1bd diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md new file mode 100644 index 0000000000..0aad3d5707 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md @@ -0,0 +1,27 @@ +# Agent Note: Resume selector batch projection + +Status: implemented + +English | [中文](2026-07-31-resume-selector-batch-projection.zh.md) + +## Problem + +Opening the TUI `/resume` selector called `sessionQuery.readSession()` once per listed session under an unbounded `Promise.all`. Each call re-listed the whole persistence store inside `SessionCorpus.load()` (O(N²) listings), read and decompressed the complete log, replay-validated every event through the `Session` constructor, and deep-cloned the header and events up to three times — all to derive one selector row's title, last-activity time, last `turn/end` label, provider/model route, and goal phase. On a real store (185 sessions, 87 MB compressed, ~353k events) the selector took tens of seconds to open, and the cost grows with total log size rather than session count. + +## Decision + +`SessionQueryService` exposes the existing internal `SessionCorpus.projectMany` batch as public `projectSessions(sessionIds, project, signal?)`: one persistence listing, at most `persistedInspectConcurrency` concurrent persisted inspections, per-id failure isolation, and a synchronous projector over a borrowed `LogicalSessionSource` with no replay validation and no cloning. `readTitleSnapshots` now routes through it; `LogicalSessionSource` and `LogicalProjectionResult` are exported and documented in the session-query core-data-structures page. + +The `/resume` selector builds all candidate rows from one `projectSessions` batch; a rejected projection degrades to that row's disabled "Unreadable session" fallback exactly as a failed `readSession` did. `summarizeResumeCandidate` takes the borrowed source and retains only the record and derived scalars. The pre-handoff preflight still reads the single chosen session through `readSession`, keeping full replay validation before the process re-execs; its redundant live-session shortcut was dropped because `readSession` is already live-preferred. + +## Alternatives considered + +**Fix only the O(N²) listing inside `SessionCorpus.load()`.** Rejected as the primary fix: the per-candidate full decompress, replay validation, and triple clone dominate on large logs and remain O(total log bytes). The redundant pre-listing in `load()` is still a candidate cleanup, but it changes not-found/consistency error semantics and is not needed once the selector stops calling `readSession` per row. + +**A resume-specific summary method on `sessionQuery`.** Rejected: resume is a TUI concept, and the service seam should not import consumer vocabulary. The generic synchronous projection mirrors the seam `readTitleSnapshots` already used internally and lets the TUI own its fold. + +**A persisted summary index (e.g. in the SQLite query backend).** Rejected for now: one bounded pass over the store (~1–3 s on the measured machine) is acceptable selector latency, and an index adds an invalidation contract. Reintroduce if stores grow to where one bounded pass is still too slow. + +## Consequences + +Opening `/resume` performs one listing plus one bounded-concurrency pass instead of N listings and N validated full copies; memory stays bounded by the concurrency limit because each projected log is released before its worker dequeues another id. Selector rows are no longer replay-validated — a log that lists and parses but would fail replay shows as a normal row until preflight rejects it, which preflight always re-checks before handoff. Fake `sessionQuery` services in TUI tests must now provide `projectSessions` alongside `listSessions`/`readSession`. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md new file mode 100644 index 0000000000..055e11c440 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md @@ -0,0 +1,27 @@ +# Agent Note: 恢复选择器批量投影 + +Status: implemented + +[English](2026-07-31-resume-selector-batch-projection.md) | 中文 + +## Problem + +打开 TUI `/resume` 选择器时，会在一个无界 `Promise.all` 中对每个列出的会话调用一次 `sessionQuery.readSession()`。每次调用都会在 `SessionCorpus.load()` 内部重新列出整个持久化存储（O(N²) 次列表查询）、读取并解压完整日志、通过 `Session` 构造函数对每个事件做回放验证，并将 header 和事件深克隆多达三次——而这一切只为推导一行选择器条目的标题、最近活动时间、最后一个 `turn/end` 标签、提供方/模型路由和目标阶段。在真实存储上（185 个会话、压缩后 87 MB、约 35.3 万个事件），选择器需要数十秒才能打开，且开销随日志总大小而非会话数量增长。 + +## Decision + +`SessionQueryService` 将既有的内部 `SessionCorpus.projectMany` 批量能力公开为 `projectSessions(sessionIds, project, signal?)`：一次持久化列表查询、最多 `persistedInspectConcurrency` 个并发持久化检查、按 id 隔离失败，以及一个在借用的 `LogicalSessionSource` 上运行的同步投影函数——不做回放验证也不克隆。`readTitleSnapshots` 现在经由它实现；`LogicalSessionSource` 和 `LogicalProjectionResult` 被导出，并记录在 session-query 核心数据结构页面中。 + +`/resume` 选择器通过一次 `projectSessions` 批量调用构建全部候选行；被拒绝的投影会退化为该行的禁用"Unreadable session"回退，与之前 `readSession` 失败时的行为完全一致。`summarizeResumeCandidate` 接受借用的来源，且只保留记录和推导出的标量。移交前的预检仍通过 `readSession` 读取用户选中的单个会话，在进程 re-exec 前保留完整回放验证；其中冗余的实时会话捷径被删除，因为 `readSession` 本身已是实时优先。 + +## Alternatives considered + +**只修复 `SessionCorpus.load()` 内部的 O(N²) 列表查询。** 作为主要修复被拒绝：在大日志上，按候选行执行的完整解压、回放验证和三重克隆才是主要开销，且仍是 O(日志总字节数)。`load()` 中的冗余预列表查询仍是一个候选清理项，但它会改变 not-found/一致性错误语义，而且一旦选择器不再按行调用 `readSession`，这项清理就不再必要。 + +**在 `sessionQuery` 上添加恢复专用的摘要方法。** 被拒绝：恢复是 TUI 概念，服务接缝不应引入消费者词汇。通用同步投影复用了 `readTitleSnapshots` 已在内部使用的接缝，并让 TUI 拥有自己的 fold。 + +**持久化摘要索引（例如放在 SQLite 查询后端中）。** 暂时被拒绝：对存储做一次有界扫描（在测量机器上约 1–3 秒）是可接受的选择器延迟，而索引会引入失效契约。若存储增长到一次有界扫描仍然过慢时再重新引入。 + +## Consequences + +打开 `/resume` 只执行一次列表查询加一次有界并发扫描，而不是 N 次列表查询和 N 份经验证的完整副本；内存受并发上限约束，因为每个投影完的日志会在其 worker 出队下一个 id 前被释放。选择器行不再经过回放验证——一份可列出、可解析但回放会失败的日志会显示为普通行，直到预检拒绝它，而预检在移交前总会重新检查。TUI 测试中的伪造 `sessionQuery` 服务现在必须在 `listSessions`/`readSession` 之外提供 `projectSessions`。 diff --git a/packages/ui/tui/src/chat/resume.ts b/packages/ui/tui/src/chat/resume.ts index 18f7944fc2..e6558ee4c3 100644 --- a/packages/ui/tui/src/chat/resume.ts +++ b/packages/ui/tui/src/chat/resume.ts @@ -1,6 +1,6 @@ /** * Session-resume sub-controller for the interactive chat channel: the - * `/resume` selector, per-candidate summary reads that tolerate a corrupt + * `/resume` selector, one batch summary projection that tolerates a corrupt * neighbor, the pre-handoff preflight, and the terminal handoff itself. * @module @deepseek-ai/dsh-tui/chat/resume */ @@ -10,7 +10,7 @@ import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent' import { errorChain } from '@deepseek-ai/dsh-llm' import type { SessionId } from '@deepseek-ai/dsh-session' import type { - SessionLogSnapshot, + LogicalSessionSource, SessionQueryService, SessionRecord, } from '@deepseek-ai/dsh-session-query' @@ -66,44 +66,45 @@ export function createResumeController(deps: ResumeControllerDeps): ResumeContro const workspaceLabel = (cwd: string | undefined): string => runtime.formatCwd?.(cwd) ?? formatCwd(cwd) - /** Build one display candidate without letting a corrupt neighbor abort the selector. */ + /** Summarize one record from a borrowed source, retaining only the record and derived scalars. */ + const summarize = ( + record: SessionRecord, + source: LogicalSessionSource, + providers: ReadonlySet, + ): ResumeCandidate => summarizeResumeCandidate( + record, + source, + agent.session.id, + agent.session.header.cwd, + providers, + workspaceLabel, + ) + + /** The disabled fallback row for a session whose log cannot be summarized. */ + const unreadableCandidate = (record: SessionRecord, error: unknown): ResumeCandidate => ({ + record, + title: 'Unreadable session', + lastActivityAt: record.header.createdAt, + lastTurn: 'log unavailable', + currentWorkspace: record.header.cwd === agent.session.header.cwd, + workspaceLabel: workspaceLabel(record.header.cwd), + disabledReason: `session cannot be loaded: ${errorChain(error)}`, + }) + + /** Build one exact candidate from a live-preferred read that replay-validates a persisted log. */ const readResumeCandidate = async ( record: SessionRecord, providers: ReadonlySet, ): Promise => { try { - let snapshot: SessionLogSnapshot - const live = ctx.sessions.get(record.header.id) - if (live !== undefined) { - snapshot = { - session: structuredClone(live.header), - events: live.events.map(event => structuredClone(event)), - } - } else { - const readQuery = sessionQuery() - /* v8 ignore start -- caller proves the optional service before mapping records */ - if (readQuery === undefined) throw new Error('session query is unavailable') - /* v8 ignore stop */ - snapshot = await readQuery.readSession(record.header.id) - } - return summarizeResumeCandidate( - record, - snapshot, - agent.session.id, - agent.session.header.cwd, - providers, - workspaceLabel, - ) + const readQuery = sessionQuery() + /* v8 ignore start -- caller proves the optional service before mapping records */ + if (readQuery === undefined) throw new Error('session query is unavailable') + /* v8 ignore stop */ + const snapshot = await readQuery.readSession(record.header.id) + return summarize(record, { header: snapshot.session, events: snapshot.events }, providers) } catch (error: unknown) { - return { - record, - title: 'Unreadable session', - lastActivityAt: record.header.createdAt, - lastTurn: 'log unavailable', - currentWorkspace: record.header.cwd === agent.session.header.cwd, - workspaceLabel: workspaceLabel(record.header.cwd), - disabledReason: `session cannot be loaded: ${errorChain(error)}`, - } + return unreadableCandidate(record, error) } } @@ -199,7 +200,25 @@ export function createResumeController(deps: ResumeControllerDeps): ResumeContro // Every workspace in the store is summarized; the picker owns the // current-workspace/all-workspaces scope split over the whole set. const providers = new Set(ctx.llm.listProviders().map(provider => provider.id)) - const candidates = await Promise.all(records.map(record => readResumeCandidate(record, providers))) + // One bounded batch projection over borrowed logs: unlike a + // per-candidate readSession, it lists persistence once and skips + // replay validation and log cloning, so opening the selector scales + // with session count instead of total log size. A corrupt neighbor + // degrades to one disabled row. + const recordById = new Map(records.map(record => [record.header.id, record])) + const listedRecord = (id: SessionId): SessionRecord => { + const record = recordById.get(id) + /* v8 ignore next 2 -- projection ids come from this map; the corpus verifies each loaded header id */ + if (record === undefined) throw new Error(`resume scan returned unlisted session "${id}"`) + return record + } + const results = await listQuery.projectSessions( + records.map(record => record.header.id), + source => summarize(listedRecord(source.header.id), source, providers), + ) + const candidates = results.map(result => result.status === 'fulfilled' + ? result.value + : unreadableCandidate(listedRecord(result.sessionId), result.reason)) candidates.sort((a, b) => b.lastActivityAt - a.lastActivityAt || a.record.header.id.localeCompare(b.record.header.id)) if (deps.isDisposed() || scan !== resumeScan) return diff --git a/packages/ui/tui/src/components/dialogs.ts b/packages/ui/tui/src/components/dialogs.ts index bad6a5458b..604f1858de 100644 --- a/packages/ui/tui/src/components/dialogs.ts +++ b/packages/ui/tui/src/components/dialogs.ts @@ -28,7 +28,7 @@ import type { SessionId } from '@deepseek-ai/dsh-session' import { foldGoal, type GoalPhase } from '@deepseek-ai/dsh-goal' import { foldSessionTitle } from '@deepseek-ai/dsh-session-title' import type { - SessionLogSnapshot, + LogicalSessionSource, SessionRecord, } from '@deepseek-ai/dsh-session-query' import type { AskUserQuestionItem } from '@deepseek-ai/dsh-user-interaction' @@ -453,8 +453,8 @@ export interface ResumeCandidate { disabledReason?: string } -function resumeTurnLabel(snapshot: SessionLogSnapshot): string { - const event = snapshot.events.findLast(item => item.type === 'turn/end') +function resumeTurnLabel(source: LogicalSessionSource): string { + const event = source.events.findLast(item => item.type === 'turn/end') if (event === undefined) return 'no completed turn' const reason = event.data.reason switch (reason.kind) { @@ -468,24 +468,26 @@ function resumeTurnLabel(snapshot: SessionLogSnapshot): string { } } -function resumeRoute(snapshot: SessionLogSnapshot): ResumeRoute | undefined { - const header = snapshot.events.findLast(item => item.type === 'request/header') +function resumeRoute(source: LogicalSessionSource): ResumeRoute | undefined { + const header = source.events.findLast(item => item.type === 'request/header') if (header?.type === 'request/header') { return { provider: header.data.header.config.provider, model: header.data.header.config.model } } - const assistant = snapshot.events.findLast(item => item.type === 'assistant/message') + const assistant = source.events.findLast(item => item.type === 'assistant/message') return assistant?.type === 'assistant/message' ? { provider: assistant.data.message.source.provider, model: assistant.data.message.source.model } : undefined } /** - * Build one resume selector row from a record and its log snapshot, deriving the - * title, route, goal phase, workspace scope, and any reason the session cannot - * be resumed here. A workspace other than the current one is a scope, not a - * disabled reason: resuming it hands the process off into that directory. + * Build one resume selector row from a record and its borrowed log source, + * deriving the title, route, goal phase, workspace scope, and any reason the + * session cannot be resumed here. A workspace other than the current one is a + * scope, not a disabled reason: resuming it hands the process off into that + * directory. The result retains only the record and derived scalars, so a + * borrowed source stays valid for exactly this call. * @param record - The session record. - * @param snapshot - The session's log snapshot. + * @param source - The session's borrowed header and raw event log. * @param currentId - The current session id. * @param cwd - The CURRENT session's workspace, which decides the picker scope this row falls in. * @param availableProviders - Providers registered in this runtime. @@ -494,15 +496,15 @@ function resumeRoute(snapshot: SessionLogSnapshot): ResumeRoute | undefined { */ export function summarizeResumeCandidate( record: SessionRecord, - snapshot: SessionLogSnapshot, + source: LogicalSessionSource, currentId: SessionId, cwd: string | undefined, availableProviders: ReadonlySet, formatWorkspace: (cwd: string | undefined) => string, ): ResumeCandidate { - const title = foldSessionTitle(snapshot.events)?.title ?? 'Untitled session' - const route = resumeRoute(snapshot) - const foldedGoal = foldGoal(snapshot.events).goal + const title = foldSessionTitle(source.events)?.title ?? 'Untitled session' + const route = resumeRoute(source) + const foldedGoal = foldGoal(source.events).goal let disabledReason: string | undefined if (record.header.id === currentId) disabledReason = 'current session' else if (record.live) disabledReason = 'session is already live in this runtime' @@ -514,8 +516,8 @@ export function summarizeResumeCandidate( record, title, // Excludes a prior pickup's boundary, or every browsed session floats up. - lastActivityAt: lastActivityTime(snapshot.events) ?? snapshot.session.createdAt, - lastTurn: resumeTurnLabel(snapshot), + lastActivityAt: lastActivityTime(source.events) ?? source.header.createdAt, + lastTurn: resumeTurnLabel(source), currentWorkspace: record.header.cwd === cwd, workspaceLabel: formatWorkspace(record.header.cwd), ...route === undefined ? {} : { route }, diff --git a/packages/ui/tui/tests/tui.spec.ts b/packages/ui/tui/tests/tui.spec.ts index 8231dc34d1..3729a1bd5b 100644 --- a/packages/ui/tui/tests/tui.spec.ts +++ b/packages/ui/tui/tests/tui.spec.ts @@ -273,6 +273,20 @@ describe('goodbye message and /resume', () => { { type: 'turn/end', seq: 6, time: time + 6, data: { turn: 1, reason } }, { type: 'session/title', seq: 7, time: time + 7, data: { title, messageSeqs: [1], source: { kind: 'fallback' } } }, ] + /** Derive the selector's batch projection from a fake per-session readSession. */ + const projectViaReadSession = ( + readSession: (id: SessionId) => Promise<{ session: SessionHeader; events: SessionEvent[] }>, + ) => ( + ids: readonly SessionId[], + project: (source: { header: SessionHeader; events: readonly SessionEvent[] }) => unknown, + ) => Promise.all(ids.map(async (sessionId) => { + try { + const snapshot = await readSession(sessionId) + return { sessionId, status: 'fulfilled', value: project({ header: snapshot.session, events: snapshot.events }) } + } catch (reason) { + return { sessionId, status: 'rejected', reason } + } + })) it('prints the host goodbye message on exit', async () => { const result = await setup({ @@ -516,6 +530,7 @@ describe('goodbye message and /resume', () => { queryCtx = child child.provide('sessionQuery', { listSessions: async () => { listCalls++; return [] }, + projectSessions: async () => [], } as never) }, }) @@ -546,16 +561,18 @@ describe('goodbye message and /resume', () => { cwd: '/workspace', async configureContext(ctx) { ctx.provide('tools', { get: () => undefined } as never) + const readSession = () => Promise.resolve({ + session: target, + events: resumeEvents('Query-only persisted session'), + }) ctx.provide('sessionQuery', { listSessions: () => Promise.resolve([{ header: target, live: false, persisted: true, }]), - readSession: () => Promise.resolve({ - session: target, - events: resumeEvents('Query-only persisted session'), - }), + readSession, + projectSessions: projectViaReadSession(readSession), } as never) }, }) @@ -593,6 +610,7 @@ describe('goodbye message and /resume', () => { ctx.provide('tools', { get: () => undefined } as never) ctx.provide('sessionQuery', { listSessions: () => ++calls === 1 ? first.promise : Promise.resolve([]), + projectSessions: async () => [], } as never) }, }) @@ -685,16 +703,18 @@ describe('goodbye message and /resume', () => { handoffResume: handoff, async configureContext(ctx) { ctx.provide('tools', { get: () => undefined } as never) + const readSession = () => Promise.resolve({ + session: target, + events: resumeEvents('Live target'), + }) ctx.provide('sessionQuery', { listSessions: () => Promise.resolve([{ header: target, live: true, persisted: true, }]), - readSession: () => Promise.resolve({ - session: target, - events: resumeEvents('Live target'), - }), + readSession, + projectSessions: projectViaReadSession(readSession), } as never) }, }) @@ -815,12 +835,14 @@ describe('goodbye message and /resume', () => { async configureContext(ctx) { ctx.provide('tools', { get: () => undefined } as never) ctx.on('session/flush', flush) + const readSession = () => Promise.resolve({ + session: target, + events: resumeEvents('Dispose during preflight'), + }) ctx.provide('sessionQuery', { listSessions: () => ++listings === 1 ? Promise.resolve([record]) : secondListing.promise, - readSession: () => Promise.resolve({ - session: target, - events: resumeEvents('Dispose during preflight'), - }), + readSession, + projectSessions: projectViaReadSession(readSession), } as never) }, }) @@ -847,16 +869,18 @@ describe('goodbye message and /resume', () => { handoffResume: handoff, async configureContext(ctx) { ctx.provide('tools', { get: () => undefined } as never) + const readSession = () => Promise.resolve({ + session: target, + events: resumeEvents('Query without persistence'), + }) ctx.provide('sessionQuery', { listSessions: () => Promise.resolve([{ header: target, live: false, persisted: true, }]), - readSession: () => Promise.resolve({ - session: target, - events: resumeEvents('Query without persistence'), - }), + readSession, + projectSessions: projectViaReadSession(readSession), } as never) }, }) From b7ee38fef028167013791a6562378af5f47f0ca6 Mon Sep 17 00:00:00 2001 From: Turtle Date: Fri, 31 Jul 2026 16:39:33 +0800 Subject: [PATCH 03/45] feat(tui): open the /resume picker immediately with a loading state The selector overlay opens as soon as the command dispatches: the picker renders a loading placeholder over an undefined candidate set, owns terminal input from its first frame, answers Enter with a still-loading error, and cancels on Escape exactly like the loaded list. The finished scan swaps rows in through setCandidates without replacing the overlay; a scan failure closes it and keeps the existing notice. --- ...resume-selector-batch-projection.i18n.yaml | 4 +- ...-07-31-resume-selector-batch-projection.md | 4 +- ...-31-resume-selector-batch-projection.zh.md | 4 +- packages/ui/tui/README.i18n.yaml | 4 +- packages/ui/tui/README.md | 2 +- packages/ui/tui/README.zh.md | 2 +- packages/ui/tui/src/chat/resume.ts | 60 ++++++++++++------- packages/ui/tui/src/components/dialogs.ts | 44 ++++++++++---- .../resume-sessions-loading.expected.txt | 47 +++++++++++++++ packages/ui/tui/tests/tui.snapshot.ts | 18 +++++- packages/ui/tui/tests/tui.spec.ts | 36 +++++++++++ 11 files changed, 181 insertions(+), 44 deletions(-) create mode 100644 packages/ui/tui/tests/snapshots/resume-sessions-loading.expected.txt diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml index c0faa37e8d..0e733bbb4d 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.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/bug-fix/2026-07-31-resume-selector-batch-projection.md -2026-07-31-resume-selector-batch-projection.md: 0aad3d57079819165d345d494071eb04d0b50abd -2026-07-31-resume-selector-batch-projection.zh.md: 055e11c440114987c0c37a2d268bce3328d4b1bd +2026-07-31-resume-selector-batch-projection.md: 1120a0777bf6a6ca17dd0704d145a3c742be0695 +2026-07-31-resume-selector-batch-projection.zh.md: 79db30170765925a00be180ba2b56de8a87ba130 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md index 0aad3d5707..1120a0777b 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md +++ b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md @@ -14,6 +14,8 @@ Opening the TUI `/resume` selector called `sessionQuery.readSession()` once per The `/resume` selector builds all candidate rows from one `projectSessions` batch; a rejected projection degrades to that row's disabled "Unreadable session" fallback exactly as a failed `readSession` did. `summarizeResumeCandidate` takes the borrowed source and retains only the record and derived scalars. The pre-handoff preflight still reads the single chosen session through `readSession`, keeping full replay validation before the process re-execs; its redundant live-session shortcut was dropped because `readSession` is already live-preferred. +The selector overlay opens synchronously when `/resume` dispatches, before the scan settles: an `undefined` candidate set renders a "Loading sessions…" placeholder, the picker owns terminal input from its first frame (so keystrokes during a long scan reach the search field rather than the editor), Enter reports that sessions are still loading, and Escape cancels exactly as it does on the loaded list. The finished scan swaps rows in through `setCandidates` without replacing the overlay; a queued activation behind a closing predecessor receives an already-scanned set at construction; a scan failure closes the overlay and reports the existing failure notice. + ## Alternatives considered **Fix only the O(N²) listing inside `SessionCorpus.load()`.** Rejected as the primary fix: the per-candidate full decompress, replay validation, and triple clone dominate on large logs and remain O(total log bytes). The redundant pre-listing in `load()` is still a candidate cleanup, but it changes not-found/consistency error semantics and is not needed once the selector stops calling `readSession` per row. @@ -24,4 +26,4 @@ The `/resume` selector builds all candidate rows from one `projectSessions` batc ## Consequences -Opening `/resume` performs one listing plus one bounded-concurrency pass instead of N listings and N validated full copies; memory stays bounded by the concurrency limit because each projected log is released before its worker dequeues another id. Selector rows are no longer replay-validated — a log that lists and parses but would fail replay shows as a normal row until preflight rejects it, which preflight always re-checks before handoff. Fake `sessionQuery` services in TUI tests must now provide `projectSessions` alongside `listSessions`/`readSession`. +Opening `/resume` performs one listing plus one bounded-concurrency pass instead of N listings and N validated full copies; memory stays bounded by the concurrency limit because each projected log is released before its worker dequeues another id. Selector rows are no longer replay-validated — a log that lists and parses but would fail replay shows as a normal row until preflight rejects it, which preflight always re-checks before handoff. Fake `sessionQuery` services in TUI tests must now provide `projectSessions` alongside `listSessions`/`readSession`. Because the picker takes focus immediately, starting a second scan requires dismissing the current overlay first — a second `/resume` typed during a scan lands in the search field, which is the intended input capture. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md index 055e11c440..79db301707 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md @@ -14,6 +14,8 @@ Status: implemented `/resume` 选择器通过一次 `projectSessions` 批量调用构建全部候选行；被拒绝的投影会退化为该行的禁用"Unreadable session"回退，与之前 `readSession` 失败时的行为完全一致。`summarizeResumeCandidate` 接受借用的来源，且只保留记录和推导出的标量。移交前的预检仍通过 `readSession` 读取用户选中的单个会话，在进程 re-exec 前保留完整回放验证；其中冗余的实时会话捷径被删除，因为 `readSession` 本身已是实时优先。 +选择器 overlay 在 `/resume` 分发时同步打开，早于扫描结算：`undefined` 候选集渲染"Loading sessions…"加载占位符，选择器从第一帧起就拥有终端输入（长扫描期间的按键会进入搜索字段而非编辑器），Enter 提示会话仍在加载，Escape 的取消方式与已加载列表完全相同。扫描完成后通过 `setCandidates` 换入行数据，不替换 overlay；排在正在关闭的前任之后的排队激活会在构造时直接收到已扫描的集合；扫描失败会关闭 overlay 并报告既有的失败通知。 + ## Alternatives considered **只修复 `SessionCorpus.load()` 内部的 O(N²) 列表查询。** 作为主要修复被拒绝：在大日志上，按候选行执行的完整解压、回放验证和三重克隆才是主要开销，且仍是 O(日志总字节数)。`load()` 中的冗余预列表查询仍是一个候选清理项，但它会改变 not-found/一致性错误语义，而且一旦选择器不再按行调用 `readSession`，这项清理就不再必要。 @@ -24,4 +26,4 @@ Status: implemented ## Consequences -打开 `/resume` 只执行一次列表查询加一次有界并发扫描，而不是 N 次列表查询和 N 份经验证的完整副本；内存受并发上限约束，因为每个投影完的日志会在其 worker 出队下一个 id 前被释放。选择器行不再经过回放验证——一份可列出、可解析但回放会失败的日志会显示为普通行，直到预检拒绝它，而预检在移交前总会重新检查。TUI 测试中的伪造 `sessionQuery` 服务现在必须在 `listSessions`/`readSession` 之外提供 `projectSessions`。 +打开 `/resume` 只执行一次列表查询加一次有界并发扫描，而不是 N 次列表查询和 N 份经验证的完整副本；内存受并发上限约束，因为每个投影完的日志会在其 worker 出队下一个 id 前被释放。选择器行不再经过回放验证——一份可列出、可解析但回放会失败的日志会显示为普通行，直到预检拒绝它，而预检在移交前总会重新检查。TUI 测试中的伪造 `sessionQuery` 服务现在必须在 `listSessions`/`readSession` 之外提供 `projectSessions`。由于选择器立即接管焦点，启动第二次扫描需要先关闭当前 overlay——扫描期间输入的第二个 `/resume` 会落入搜索字段，这正是预期的输入捕获行为。 diff --git a/packages/ui/tui/README.i18n.yaml b/packages/ui/tui/README.i18n.yaml index e94be1a857..6cfcd6d8fe 100644 --- a/packages/ui/tui/README.i18n.yaml +++ b/packages/ui/tui/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/ui/tui/README.md -README.md: 63c888b1d51c02fa85a8f0cc1617874debd87c4e -README.zh.md: ca5efc9ae26a9833d271991f73a21c607d8fb09d +README.md: 74dbf0dc26f99d0d7a6586fe6caec1f0ccdb2f36 +README.zh.md: d0ec1acbecf6e82ef35027a72268ba16fee65d6f diff --git a/packages/ui/tui/README.md b/packages/ui/tui/README.md index 63c888b1d5..74dbf0dc26 100644 --- a/packages/ui/tui/README.md +++ b/packages/ui/tui/README.md @@ -32,7 +32,7 @@ The footer sums the session's reported usage as `↑ ↓ `/status` adds a point-in-time diagnostics card to the transcript and remains available while the agent runs. It reports the session id, title, working directory, selected provider/model, selected reasoning effort or default behavior, reasoning-block visibility, agent state, event/turn/step/tool-call counts, exact input/output/cache token buckets, KV-cache hit rate, token-meter context use and capacity, creation time, and latest event time. Missing titles, models, cache input, or context capacity are labeled instead of inferred. The card is terminal-only and does not duplicate the compact footer. -`/resume` opens a full-viewport keyboard selector instead of a centered dialog. Two scopes cover the same candidate set: the current workspace, which it opens on, and all workspaces, which Tab toggles to. The scope line under the search field names the active scope and the count the other holds, and each row in the all-workspaces scope also reports its own workspace. Toggling clears the search and selection so the highlighted row always belongs to the visible list. +`/resume` opens a full-viewport keyboard selector instead of a centered dialog. The selector opens as soon as the command runs and takes input focus while the session scan is still pending, showing a loading placeholder until the rows arrive; Escape cancels an in-flight scan the same way it cancels the loaded list. Two scopes cover the same candidate set: the current workspace, which it opens on, and all workspaces, which Tab toggles to. The scope line under the search field names the active scope and the count the other holds, and each row in the all-workspaces scope also reports its own workspace. Toggling clears the search and selection so the highlighted row always belongs to the visible list. Its focused search field starts immediately after the search glyph and emits pi-tui's cursor marker, so terminal IME composition remains anchored inside the field. Candidates are sorted by last logged activity and searchable by log-backed title or session id, and by workspace label in the all-workspaces scope; each row reports current/live/persisted state, last turn outcome, recent provider/model, and durable goal phase when present. Up/Down and Page Up/Page Down navigate, Enter resumes, Escape clears a non-empty search before a second Escape cancels, and Ctrl+C cancels directly. The current session, a session already live in this runtime, an unreadable log, a session with no recorded workspace to run in, or a session whose logged provider has no current adapter remains visible but disabled; a workspace other than the current one is a scope rather than a disabled reason, because resume enters that directory. diff --git a/packages/ui/tui/README.zh.md b/packages/ui/tui/README.zh.md index ca5efc9ae2..d0ec1acbec 100644 --- a/packages/ui/tui/README.zh.md +++ b/packages/ui/tui/README.zh.md @@ -32,7 +32,7 @@ Footer 将会话报告的用量汇总为 `↑ ↓`；任 `/status` 会向 transcript 添加一张时间点诊断卡片，并在 agent 运行时保持可用。它报告会话 id、标题、工作目录、所选提供方／模型、所选推理强度或默认行为、reasoning 块可见性、agent 状态、事件／轮次／步骤／工具调用计数、精确输入／输出／缓存 token bucket、KV-cache 命中率、token-meter 上下文用量与容量、创建时间和最新事件时间。缺失标题、模型、缓存输入或上下文容量时会明确标记，而非推断。该卡片只存在于终端，不会重复紧凑 footer。 -`/resume` 会打开全 viewport 键盘选择器，而非居中对话框。两个作用域覆盖同一候选项集合：打开时所处的当前工作区，以及按 Tab 切换到的所有工作区。搜索字段下方的作用域行会给出当前作用域的名称以及另一个作用域包含的数量，且在所有工作区作用域中每行还会报告自身所属的工作区。切换会清除搜索与选择，使高亮行始终属于可见列表。 +`/resume` 会打开全 viewport 键盘选择器，而非居中对话框。选择器在命令执行时立即打开并接管输入焦点，会话扫描仍在进行时显示加载占位符，直到行数据就绪；Escape 取消进行中的扫描，方式与取消已加载列表相同。两个作用域覆盖同一候选项集合：打开时所处的当前工作区，以及按 Tab 切换到的所有工作区。搜索字段下方的作用域行会给出当前作用域的名称以及另一个作用域包含的数量，且在所有工作区作用域中每行还会报告自身所属的工作区。切换会清除搜索与选择，使高亮行始终属于可见列表。 获得焦点的搜索字段紧跟搜索 glyph 开始，并发出 pi-tui 的 cursor marker，使终端 IME 组合保持锚定在字段内。候选项按最近记录的活动排序，可按日志支持的标题或会话 id 搜索，在所有工作区作用域中还可按工作区标签搜索；每行报告 current/live/persisted 状态、上一轮次结果、近期提供方／模型，以及存在时的持久目标阶段。Up/Down 与 Page Up/Page Down 导航，Enter 恢复，Escape 会先清除非空搜索，再次按下才取消，Ctrl+C 则直接取消。当前会话、已在本运行时中活跃的会话、不可读日志、没有可运行的已记录工作区的会话，或日志所记提供方没有当前适配器的会话仍会显示，但不可选择；不同于当前工作区的工作区属于作用域而非禁用原因，因为恢复会进入该目录。 diff --git a/packages/ui/tui/src/chat/resume.ts b/packages/ui/tui/src/chat/resume.ts index e6558ee4c3..b1386ba10d 100644 --- a/packages/ui/tui/src/chat/resume.ts +++ b/packages/ui/tui/src/chat/resume.ts @@ -195,6 +195,38 @@ export function createResumeController(deps: ResumeControllerDeps): ResumeContro } const scan = ++resumeScan void resumeOverlay?.close() + // The picker opens before the scan settles so the terminal stops feeding + // the editor immediately; a queued activation (the closing predecessor + // still holds the slot) receives an already-scanned set through + // `scanned` instead of a loading placeholder. + let picker: ResumePicker | undefined + let scanned: ResumeCandidate[] | undefined + const session = overlayManager.open({ + create: (host) => { + picker = new ResumePicker( + scanned, + resolved.maxResumeOptions, + workspaceLabel(agent.session.header.cwd), + () => host.viewport.rows, + palette, + (candidate) => { void handoffResume(candidate, session) }, + () => { void session.close() }, + ) + return picker + }, + options: { + width: '100%', + maxHeight: '100%', + anchor: 'top-left', + margin: 0, + }, + }) + resumeOverlay = session + void session.closed.then(() => { + /* v8 ignore next -- overlay FIFO closes this session before a replacement can become the tracked resume overlay */ + if (resumeOverlay === session) resumeOverlay = undefined + }) + deps.requestRender() void listQuery.listSessions().then(async (records) => { if (deps.isDisposed() || scan !== resumeScan) return // Every workspace in the store is summarized; the picker owns the @@ -222,31 +254,13 @@ export function createResumeController(deps: ResumeControllerDeps): ResumeContro candidates.sort((a, b) => b.lastActivityAt - a.lastActivityAt || a.record.header.id.localeCompare(b.record.header.id)) if (deps.isDisposed() || scan !== resumeScan) return - const session = overlayManager.open({ - create: host => new ResumePicker( - candidates, - resolved.maxResumeOptions, - workspaceLabel(agent.session.header.cwd), - () => host.viewport.rows, - palette, - (candidate) => { void handoffResume(candidate, session) }, - () => { void session.close() }, - ), - options: { - width: '100%', - maxHeight: '100%', - anchor: 'top-left', - margin: 0, - }, - }) - resumeOverlay = session - void session.closed.then(() => { - /* v8 ignore next -- overlay FIFO closes this session before a replacement can become the tracked resume overlay */ - if (resumeOverlay === session) resumeOverlay = undefined - }) + scanned = candidates + picker?.setCandidates(candidates) deps.requestRender() }, (error: unknown) => { - if (!deps.isDisposed() && scan === resumeScan) deps.appendNotice(`Resume session scan failed: ${errorChain(error)}`, 'error') + if (deps.isDisposed() || scan !== resumeScan) return + void session.close() + deps.appendNotice(`Resume session scan failed: ${errorChain(error)}`, 'error') }) }, } diff --git a/packages/ui/tui/src/components/dialogs.ts b/packages/ui/tui/src/components/dialogs.ts index 604f1858de..6139a94773 100644 --- a/packages/ui/tui/src/components/dialogs.ts +++ b/packages/ui/tui/src/components/dialogs.ts @@ -537,6 +537,10 @@ export type ResumeScope = 'workspace' | 'all' * current session's workspace, `all` lists every workspace and labels each row * with its own. Tab toggles between them; the search query and selection reset * on a scope change so the highlighted row always belongs to the visible list. + * + * The picker opens before the session scan settles: an `undefined` candidate + * set renders a loading placeholder that keeps input away from the editor, + * and `setCandidates` swaps the scanned rows in without replacing the overlay. */ export class ResumePicker implements Component, Focusable { private readonly search = new Input() @@ -544,27 +548,41 @@ export class ResumePicker implements Component, Focusable { private selectedIndex = 0 private error = '' private scope: ResumeScope = 'workspace' + private candidates: readonly ResumeCandidate[] | undefined focused = false constructor( - private readonly candidates: readonly ResumeCandidate[], + candidates: readonly ResumeCandidate[] | undefined, private readonly maxVisible: number, private readonly workspaceLabel: string, private readonly viewportRows: () => number, private readonly palette: Palette, private readonly done: (candidate: ResumeCandidate) => void, private readonly cancel: () => void, - ) {} + ) { + this.candidates = candidates + } invalidate(): void { this.search.invalidate() } + /** + * Replace the loading placeholder with the scanned candidate set. + * @param candidates - the summarized rows the finished scan produced. + */ + setCandidates(candidates: readonly ResumeCandidate[]): void { + this.candidates = candidates + this.selectedIndex = 0 + this.invalidate() + } + /** Candidates in the active scope, before the search query narrows them. */ private scoped(): ResumeCandidate[] { + const candidates = this.candidates ?? [] return this.scope === 'all' - ? [...this.candidates] - : this.candidates.filter(candidate => candidate.currentWorkspace) + ? [...candidates] + : candidates.filter(candidate => candidate.currentWorkspace) } private filtered(): ResumeCandidate[] { @@ -646,7 +664,8 @@ export class ResumePicker implements Component, Focusable { this.error = '' } else if (matchesKey(data, Key.enter)) { const selected = filtered[this.selectedIndex] - if (selected === undefined) this.error = 'No session matches this search.' + if (this.candidates === undefined) this.error = 'Sessions are still loading.' + else if (selected === undefined) this.error = 'No session matches this search.' else if (selected.disabledReason !== undefined) this.error = selected.disabledReason else this.done(selected) } else { @@ -666,12 +685,13 @@ export class ResumePicker implements Component, Focusable { * workspace it means, and the inactive scope with the count Tab would reveal. */ private renderScopeLine(): string { - const inWorkspace = this.candidates.filter(candidate => candidate.currentWorkspace).length + const candidates = this.candidates ?? [] + const inWorkspace = candidates.filter(candidate => candidate.currentWorkspace).length const active = this.scope === 'workspace' ? `this workspace ${displayText(this.workspaceLabel)}` - : `all workspaces (${this.candidates.length})` + : `all workspaces (${candidates.length})` const other = this.scope === 'workspace' - ? `all workspaces (${this.candidates.length})` + ? `all workspaces (${candidates.length})` : `this workspace (${inWorkspace})` return `${this.palette.accent(active)}${this.palette.dim(` ⇥ ${other}`)}` } @@ -686,9 +706,12 @@ export class ResumePicker implements Component, Focusable { if (this.selectedIndex >= filtered.length) this.selectedIndex = Math.max(0, filtered.length - 1) const selected = filtered[this.selectedIndex] const position = selected === undefined ? 0 : this.selectedIndex + 1 + const title = this.candidates === undefined + ? 'Resume session' + : `Resume session (${position} of ${filtered.length})` const lines: string[] = [ '', - `${indent}${this.palette.bold(this.palette.accent(`Resume session (${position} of ${filtered.length})`))}`, + `${indent}${this.palette.bold(this.palette.accent(title))}`, '', ] @@ -737,7 +760,8 @@ export class ResumePicker implements Component, Focusable { push(this.palette.warning(` unavailable: ${displayText(candidate.disabledReason)}`)) } } - if (filtered.length === 0) push(this.palette.warning('No matching sessions.')) + if (this.candidates === undefined) push(this.palette.dim('Loading sessions…')) + else if (filtered.length === 0) push(this.palette.warning('No matching sessions.')) if (this.error !== '') { lines.push('') push(this.palette.error(displayText(this.error))) diff --git a/packages/ui/tui/tests/snapshots/resume-sessions-loading.expected.txt b/packages/ui/tui/tests/snapshots/resume-sessions-loading.expected.txt new file mode 100644 index 0000000000..e44621ad60 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/resume-sessions-loading.expected.txt @@ -0,0 +1,47 @@ +terminal 92x32 buffer=normal length=32 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=6 viewportRow=4 bufferRow=4 +buffer +0| " " +1| " Resume session " + style 2-15 fg=bright-magenta bold +2| " " +3| " ╭──────────────────────────────────────────────────────────────────────────────────────╮ " + style 2-89 dim +4| " │ ⌕ │ " + style 2-2 dim + style 6-6 inverse + style 89-89 dim +5| " ╰──────────────────────────────────────────────────────────────────────────────────────╯ " + style 2-89 dim +6| " " +7| " this workspace /workspace/project ⇥ all workspaces (0) " + style 2-34 fg=bright-magenta + style 35-56 dim +8| " " +9| " Loading sessions… " + style 2-18 dim +10| " " +11| " " +12| " " +13| " " +14| " " +15| " " +16| " " +17| " " +18| " " +19| " " +20| " " +21| " " +22| " " +23| " " +24| " " +25| " " +26| " " +27| " " +28| " " +29| " " +30| " Type to search • ↑/↓ navigate • Tab scope • Enter resume • Esc clear/cancel " + style 2-84 dim +31| " " diff --git a/packages/ui/tui/tests/tui.snapshot.ts b/packages/ui/tui/tests/tui.snapshot.ts index 18f0a9a793..91d1a67d78 100644 --- a/packages/ui/tui/tests/tui.snapshot.ts +++ b/packages/ui/tui/tests/tui.snapshot.ts @@ -57,6 +57,7 @@ const CHECKPOINTS = [ 'model-switching', 'errors-and-help', 'disposed-terminal', + 'resume-sessions-loading', 'resume-sessions', 'resume-sessions-all-workspaces', 'status-diagnostics', @@ -883,9 +884,13 @@ describe('TUI terminal-state snapshots', () => { { type: 'session/end-seed', seq: 8, time: Date.parse('2026-07-23T07:59:00.000Z'), data: {} }, ], }) + const listGate = Promise.withResolvers() const harness = await setupSnapshot({ sessionPersistence: { - list: async () => [earlier, elsewhere], + list: async () => { + await listGate.promise + return [earlier, elsewhere] + }, load: async id => id === elsewhere.id ? log(elsewhere, 'Other workspace work', '2024-02-02') : log(earlier, 'Resume selector design', '2024-01-01'), @@ -893,8 +898,15 @@ describe('TUI terminal-state snapshots', () => { }, { columns: 92, rows: 32 }) harness.terminal.send('/resume') harness.terminal.send('\r') - // `/resume` scans persistence asynchronously, so the listing renders a tick - // after submit (the unit suite waits the same way); settle, then flush. + // The picker opens as soon as the command dispatches and owns input while + // the persistence scan is still pending, rendering a loading placeholder + // in place of rows; only the scan is gated, so this settle never lists. + await new Promise(resolve => setTimeout(resolve, 60)) + await harness.terminal.flush() + await checkpoint('resume-sessions-loading', harness.terminal, { includeScrollback: true }) + listGate.resolve(undefined) + // With the scan released, the listing renders a tick later (the unit suite + // waits the same way); settle, then flush. await new Promise(resolve => setTimeout(resolve, 60)) await harness.terminal.flush() await checkpoint('resume-sessions', harness.terminal, { includeScrollback: true }) diff --git a/packages/ui/tui/tests/tui.spec.ts b/packages/ui/tui/tests/tui.spec.ts index 3729a1bd5b..bf7d646e24 100644 --- a/packages/ui/tui/tests/tui.spec.ts +++ b/packages/ui/tui/tests/tui.spec.ts @@ -616,6 +616,11 @@ describe('goodbye message and /resume', () => { }) result.terminal.send('/resume') result.terminal.send('\r') + // The loading picker owns input as soon as /resume runs, so the second + // scan starts after dismissing the first overlay, not by typing a second + // slash command over it. + result.terminal.send('\u001B') + await tick() result.terminal.send('/resume') result.terminal.send('\r') await tick() @@ -646,6 +651,37 @@ describe('goodbye message and /resume', () => { expect(result.terminal.stopped).toBeGreaterThan(0) }) + it('opens a loading picker immediately and swaps in the scanned rows', async () => { + const target = header('late-listing', 10, '/workspace') + const listing = Promise.withResolvers() + const result = await setup({ + cwd: '/workspace', + async configureContext(ctx) { + ctx.provide('tools', { get: () => undefined } as never) + const readSession = () => Promise.resolve({ + session: target, + events: resumeEvents('Late listing'), + }) + ctx.provide('sessionQuery', { + listSessions: () => listing.promise, + readSession, + projectSessions: projectViaReadSession(readSession), + } as never) + }, + }) + result.terminal.send('/resume') + result.terminal.send('\r') + await tick() + expect(result.terminal.output).toContain('Loading sessions…') + result.terminal.send('\r') + await tick() + expect(result.terminal.output).toContain('Sessions are still loading.') + listing.resolve([{ header: target, live: false, persisted: true }]) + await tick(); await tick() + expect(result.terminal.output).toContain('Late listing') + await dispose(result) + }) + it('drops loaded selector summaries when the TUI disposed during log reads', async () => { const target = header('dispose-during-load', 10, '/workspace') const loading = Promise.withResolvers<{ meta: SessionHeader; events: SessionEvent[] }>() From a942c726f5f2551c7ff7413ee028bd879de3d292 Mon Sep 17 00:00:00 2001 From: Turtle Date: Fri, 31 Jul 2026 18:57:24 +0800 Subject: [PATCH 04/45] fix(tui): abort the resume scan with its overlay Review findings from ds-review-bot: closing the loading picker now aborts the scan through the AbortSignal both query methods accept, a signal-ignoring backend's late settlement is dropped by a staleness check, one catch spans listing and projection so a projection failure closes the overlay instead of stranding the loading placeholder, setCandidates clears a stale still-loading error, and the batch comment no longer overstates the win as scaling with session count. --- ...resume-selector-batch-projection.i18n.yaml | 4 +- ...-07-31-resume-selector-batch-projection.md | 2 +- ...-31-resume-selector-batch-projection.zh.md | 2 +- packages/ui/tui/src/chat/resume.ts | 28 ++++-- packages/ui/tui/src/components/dialogs.ts | 2 + packages/ui/tui/tests/tui.spec.ts | 93 ++++++++++++++++++- 6 files changed, 118 insertions(+), 13 deletions(-) diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml index 0e733bbb4d..9eb6325c04 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.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/bug-fix/2026-07-31-resume-selector-batch-projection.md -2026-07-31-resume-selector-batch-projection.md: 1120a0777bf6a6ca17dd0704d145a3c742be0695 -2026-07-31-resume-selector-batch-projection.zh.md: 79db30170765925a00be180ba2b56de8a87ba130 +2026-07-31-resume-selector-batch-projection.md: e1777d67b6f1822fd11d2d38bc6fe45ed11b179f +2026-07-31-resume-selector-batch-projection.zh.md: 031293a76afbf88c8da16f61ddef65f891c05382 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md index 1120a0777b..e1777d67b6 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md +++ b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md @@ -14,7 +14,7 @@ Opening the TUI `/resume` selector called `sessionQuery.readSession()` once per The `/resume` selector builds all candidate rows from one `projectSessions` batch; a rejected projection degrades to that row's disabled "Unreadable session" fallback exactly as a failed `readSession` did. `summarizeResumeCandidate` takes the borrowed source and retains only the record and derived scalars. The pre-handoff preflight still reads the single chosen session through `readSession`, keeping full replay validation before the process re-execs; its redundant live-session shortcut was dropped because `readSession` is already live-preferred. -The selector overlay opens synchronously when `/resume` dispatches, before the scan settles: an `undefined` candidate set renders a "Loading sessions…" placeholder, the picker owns terminal input from its first frame (so keystrokes during a long scan reach the search field rather than the editor), Enter reports that sessions are still loading, and Escape cancels exactly as it does on the loaded list. The finished scan swaps rows in through `setCandidates` without replacing the overlay; a queued activation behind a closing predecessor receives an already-scanned set at construction; a scan failure closes the overlay and reports the existing failure notice. +The selector overlay opens synchronously when `/resume` dispatches, before the scan settles: an `undefined` candidate set renders a "Loading sessions…" placeholder, the picker owns terminal input from its first frame (so keystrokes during a long scan reach the search field rather than the editor), Enter reports that sessions are still loading, and Escape cancels exactly as it does on the loaded list. Closing the overlay aborts the scan through the `AbortSignal` both service methods accept, so a dismissed picker does not keep decompressing a large store; a signal-ignoring backend's late settlement is dropped by a staleness check instead. The finished scan swaps rows in through `setCandidates` (which also clears a stale still-loading error) without replacing the overlay; a queued activation behind a closing predecessor receives an already-scanned set at construction; one catch spans listing and projection, so any scan failure closes the overlay and reports the existing failure notice rather than stranding the loading placeholder. ## Alternatives considered diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md index 79db301707..031293a76a 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md @@ -14,7 +14,7 @@ Status: implemented `/resume` 选择器通过一次 `projectSessions` 批量调用构建全部候选行；被拒绝的投影会退化为该行的禁用"Unreadable session"回退，与之前 `readSession` 失败时的行为完全一致。`summarizeResumeCandidate` 接受借用的来源，且只保留记录和推导出的标量。移交前的预检仍通过 `readSession` 读取用户选中的单个会话，在进程 re-exec 前保留完整回放验证；其中冗余的实时会话捷径被删除，因为 `readSession` 本身已是实时优先。 -选择器 overlay 在 `/resume` 分发时同步打开，早于扫描结算：`undefined` 候选集渲染"Loading sessions…"加载占位符，选择器从第一帧起就拥有终端输入（长扫描期间的按键会进入搜索字段而非编辑器），Enter 提示会话仍在加载，Escape 的取消方式与已加载列表完全相同。扫描完成后通过 `setCandidates` 换入行数据，不替换 overlay；排在正在关闭的前任之后的排队激活会在构造时直接收到已扫描的集合；扫描失败会关闭 overlay 并报告既有的失败通知。 +选择器 overlay 在 `/resume` 分发时同步打开，早于扫描结算：`undefined` 候选集渲染"Loading sessions…"加载占位符，选择器从第一帧起就拥有终端输入（长扫描期间的按键会进入搜索字段而非编辑器），Enter 提示会话仍在加载，Escape 的取消方式与已加载列表完全相同。关闭 overlay 会通过两个服务方法都接受的 `AbortSignal` 中止扫描，因此被关闭的选择器不会继续解压大型存储；忽略信号的后端在中止后的迟到结算则由过期检查丢弃。扫描完成后通过 `setCandidates`（同时清除过期的仍在加载错误）换入行数据，不替换 overlay；排在正在关闭的前任之后的排队激活会在构造时直接收到已扫描的集合；列表查询与投影共用同一个 catch，因此任何扫描失败都会关闭 overlay 并报告既有的失败通知，而不会让加载占位符悬置。 ## Alternatives considered diff --git a/packages/ui/tui/src/chat/resume.ts b/packages/ui/tui/src/chat/resume.ts index b1386ba10d..aa211f70ef 100644 --- a/packages/ui/tui/src/chat/resume.ts +++ b/packages/ui/tui/src/chat/resume.ts @@ -222,21 +222,28 @@ export function createResumeController(deps: ResumeControllerDeps): ResumeContro }, }) resumeOverlay = session + // Closing the picker — Escape, supersession, disposal — aborts the scan: + // the borrowed-log pass over a large store must not outlive its overlay. + const scanAbort = new AbortController() void session.closed.then(() => { + scanAbort.abort() /* v8 ignore next -- overlay FIFO closes this session before a replacement can become the tracked resume overlay */ if (resumeOverlay === session) resumeOverlay = undefined }) deps.requestRender() - void listQuery.listSessions().then(async (records) => { - if (deps.isDisposed() || scan !== resumeScan) return + /** Whether this scan's overlay, session generation, or TUI is gone. */ + const scanStale = (): boolean => + deps.isDisposed() || scan !== resumeScan || scanAbort.signal.aborted + const scanCandidates = async (): Promise => { + const records = await listQuery.listSessions(scanAbort.signal) + if (scanStale()) return // Every workspace in the store is summarized; the picker owns the // current-workspace/all-workspaces scope split over the whole set. const providers = new Set(ctx.llm.listProviders().map(provider => provider.id)) // One bounded batch projection over borrowed logs: unlike a // per-candidate readSession, it lists persistence once and skips - // replay validation and log cloning, so opening the selector scales - // with session count instead of total log size. A corrupt neighbor - // degrades to one disabled row. + // replay validation and log cloning, bounding memory by what each + // summary retains. A corrupt neighbor degrades to one disabled row. const recordById = new Map(records.map(record => [record.header.id, record])) const listedRecord = (id: SessionId): SessionRecord => { const record = recordById.get(id) @@ -247,18 +254,23 @@ export function createResumeController(deps: ResumeControllerDeps): ResumeContro const results = await listQuery.projectSessions( records.map(record => record.header.id), source => summarize(listedRecord(source.header.id), source, providers), + scanAbort.signal, ) const candidates = results.map(result => result.status === 'fulfilled' ? result.value : unreadableCandidate(listedRecord(result.sessionId), result.reason)) candidates.sort((a, b) => b.lastActivityAt - a.lastActivityAt || a.record.header.id.localeCompare(b.record.header.id)) - if (deps.isDisposed() || scan !== resumeScan) return + if (scanStale()) return scanned = candidates picker?.setCandidates(candidates) deps.requestRender() - }, (error: unknown) => { - if (deps.isDisposed() || scan !== resumeScan) return + } + // One catch covers both stages, so a projection failure cannot strand + // the overlay on its loading placeholder; an aborted scan's rejection + // stays silent because the user already dismissed the picker. + void scanCandidates().catch((error: unknown) => { + if (scanStale()) return void session.close() deps.appendNotice(`Resume session scan failed: ${errorChain(error)}`, 'error') }) diff --git a/packages/ui/tui/src/components/dialogs.ts b/packages/ui/tui/src/components/dialogs.ts index 6139a94773..a5390a97b7 100644 --- a/packages/ui/tui/src/components/dialogs.ts +++ b/packages/ui/tui/src/components/dialogs.ts @@ -574,6 +574,8 @@ export class ResumePicker implements Component, Focusable { setCandidates(candidates: readonly ResumeCandidate[]): void { this.candidates = candidates this.selectedIndex = 0 + // A still-loading error is false the moment rows exist. + this.error = '' this.invalidate() } diff --git a/packages/ui/tui/tests/tui.spec.ts b/packages/ui/tui/tests/tui.spec.ts index bf7d646e24..8bd0e50bd6 100644 --- a/packages/ui/tui/tests/tui.spec.ts +++ b/packages/ui/tui/tests/tui.spec.ts @@ -42,7 +42,8 @@ import { type TuiRuntime, } from '../src/index.ts' import { WorkspaceFileSearch } from '../src/chat/file-autocomplete.ts' -import { ATTRIBUTE_ROLES, COLOR_ROLES, paletteSpec } from '../src/components/theme.ts' +import { ResumePicker } from '../src/components/dialogs.ts' +import { ATTRIBUTE_ROLES, COLOR_ROLES, createPalette, paletteSpec } from '../src/components/theme.ts' import { appendAssistant, appendUser, @@ -651,6 +652,96 @@ describe('goodbye message and /resume', () => { expect(result.terminal.stopped).toBeGreaterThan(0) }) + it('clears the still-loading error the moment scanned rows arrive', () => { + const picker = new ResumePicker( + undefined, + 10, + '/workspace', + () => 30, + createPalette(false), + () => {}, + () => {}, + ) + picker.focused = true + picker.handleInput('\r') + expect(picker.render(80).join('\n')).toContain('Sessions are still loading.') + picker.setCandidates([]) + const rendered = picker.render(80).join('\n') + expect(rendered).not.toContain('Sessions are still loading.') + expect(rendered).toContain('No matching sessions.') + }) + + it('aborts an in-flight scan when the loading picker is dismissed', async () => { + const listing = Promise.withResolvers() + let scanSignal: AbortSignal | undefined + let projections = 0 + const result = await setup({ + async configureContext(ctx) { + ctx.provide('tools', { get: () => undefined } as never) + ctx.provide('sessionQuery', { + listSessions: (signal?: AbortSignal) => { scanSignal = signal; return listing.promise }, + projectSessions: async () => { projections += 1; return [] }, + } as never) + }, + }) + result.terminal.send('/resume') + result.terminal.send('\r') + await tick() + expect(result.terminal.output).toContain('Loading sessions…') + result.terminal.send('\u001B') + await tick() + expect(scanSignal?.aborted).toBe(true) + // A signal-ignoring backend can still fulfill after dismissal: the stale + // scan must neither project nor report. + listing.resolve([]) + await tick() + expect(projections).toBe(0) + expect(result.terminal.output).not.toContain('Resume session scan failed') + await dispose(result) + }) + + it('drops a projection that settles after the picker was dismissed', async () => { + const projecting = Promise.withResolvers() + const result = await setup({ + async configureContext(ctx) { + ctx.provide('tools', { get: () => undefined } as never) + ctx.provide('sessionQuery', { + listSessions: async () => [], + projectSessions: () => projecting.promise, + } as never) + }, + }) + result.terminal.send('/resume') + result.terminal.send('\r') + await tick() + result.terminal.send('\u001B') + await tick() + projecting.resolve([]) + await tick() + expect(result.terminal.output).not.toContain('(0 of 0)') + expect(result.terminal.output).not.toContain('Resume session scan failed') + await dispose(result) + }) + + it('closes the loading picker and reports a scan that fails after listing', async () => { + const target = header('projection-explodes', 10, '/workspace') + const result = await setup({ + async configureContext(ctx) { + ctx.provide('tools', { get: () => undefined } as never) + ctx.provide('sessionQuery', { + listSessions: () => Promise.resolve([{ header: target, live: false, persisted: true }]), + projectSessions: () => Promise.reject(new Error('projection exploded')), + } as never) + }, + }) + result.terminal.send('/resume') + result.terminal.send('\r') + await tick(); await tick() + expect(result.terminal.output).toContain('Resume session scan failed: projection exploded') + expect(result.terminal.stopped).toBe(0) + await dispose(result) + }) + it('opens a loading picker immediately and swaps in the scanned rows', async () => { const target = header('late-listing', 10, '/workspace') const listing = Promise.withResolvers() From 18700f428d5ca8f7b7b778f24815472006ca9f41 Mon Sep 17 00:00:00 2001 From: Huanqi Cao Date: Sat, 1 Aug 2026 18:04:38 +0800 Subject: [PATCH 05/45] feat(fs-search): spawn the packaged ripgrep binary through the subprocess seam glob/grep now run the @vscode/ripgrep binary via ctx.subprocess with a plain argv vector: no system rg install, no shell layer, unconditional registration. The load-time command -v rg probe and the bash-seam coupling are removed; timeouts ride the cooperative exec.signal plus the seam's terminate escalation. The fs-glob-sampling ACP snapshot executes the real packaged binary against an mtime-pinned fixture. Adds the packaged-ripgrep-search Agent Note, updates the roster-note facts and both shipped-composition e2es, and regenerates the doc catalogs and third-party notices (surfacing pre-existing manifest drift plus the new @vscode/ripgrep row; the notices generator also learns pnpm 11's truncated virtual-store names). --- ...26-08-01-packaged-ripgrep-search.i18n.yaml | 6 + .../2026-08-01-packaged-ripgrep-search.md | 34 + .../2026-08-01-packaged-ripgrep-search.zh.md | 34 + ...31-even-out-shipped-tool-rosters.i18n.yaml | 4 +- ...026-07-31-even-out-shipped-tool-rosters.md | 6 +- ...-07-31-even-out-shipped-tool-rosters.zh.md | 4 +- THIRD_PARTY_NOTICES.md | 9 +- apps/cli/tests/shipped-composition.e2e.ts | 12 +- apps/web/tests/shipped-composition.e2e.ts | 12 +- docs/config-catalog.md | 4 +- docs/module-graph.md | 4 +- docs/tool-catalog.md | 4 +- examples/acp-agent/tests/acp.snapshot.ts | 41 +- .../acp-agent/tests/fixtures/fs-search-bin/rg | 10 - .../snapshots/fs-glob-sampling/input.json | 2 +- .../snapshots/fs-glob-sampling/session.jsonl | 12 +- packages/fs/tool-fs-search/README.i18n.yaml | 4 +- packages/fs/tool-fs-search/README.md | 26 +- packages/fs/tool-fs-search/README.zh.md | 54 +- packages/fs/tool-fs-search/package.json | 8 +- packages/fs/tool-fs-search/src/glob.ts | 46 +- packages/fs/tool-fs-search/src/grep.ts | 36 +- packages/fs/tool-fs-search/src/index.ts | 74 +-- packages/fs/tool-fs-search/src/ripgrep.d.ts | 12 + packages/fs/tool-fs-search/src/search-core.ts | 186 +++--- packages/fs/tool-fs-search/src/shell-quote.ts | 13 +- .../tool-fs-search/tests/integration.spec.ts | 71 +- .../fs/tool-fs-search/tests/load-path.spec.ts | 56 +- .../fs/tool-fs-search/tests/tools.spec.ts | 625 ++++++++++-------- pnpm-lock.yaml | 126 +++- scripts/gen-third-party-notices.ts | 31 +- scripts/gen-tool-catalog.ts | 56 +- 32 files changed, 923 insertions(+), 699 deletions(-) create mode 100644 .agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml create mode 100644 .agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md create mode 100644 .agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md delete mode 100755 examples/acp-agent/tests/fixtures/fs-search-bin/rg create mode 100644 packages/fs/tool-fs-search/src/ripgrep.d.ts diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml new file mode 100644 index 0000000000..fe6bb60e68 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# 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/architecture/2026-08-01-packaged-ripgrep-search.md +2026-08-01-packaged-ripgrep-search.md: e43354ff8e4dde0480a6c07816fc112810197234 +2026-08-01-packaged-ripgrep-search.zh.md: 55498d366a2171a178cf9d0d1004b6fe946a7281 diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md new file mode 100644 index 0000000000..e43354ff8e --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md @@ -0,0 +1,34 @@ +# Agent Note: Packaged ripgrep spawn for glob/grep + +Status: implemented + +English | [中文](2026-08-01-packaged-ripgrep-search.zh.md) + +> Supersedes [bash-backed grep/glob discovery](../../archived/feature/2026-07-09-bash-backed-grep-glob-discovery.md): the v1 decision's explicitly deferred alternative — directly spawning ripgrep — is now what ships. + +## Problem + +The `glob`/`grep` tools ran through the bash executor seam, which made a system `rg` install a host dependency. On Windows and container images there is no `rg` on `PATH` by default, so the tools silently vanished there; a deployment could only discover that from the load-time probe warning. The bash seam also forced the whole model-visible argument surface through one shell-quoting helper, because a shell sat between the tool and ripgrep — the [bash-backed note](../../archived/feature/2026-07-09-bash-backed-grep-glob-discovery.md) recorded that coupling as the v1 trade-off and named direct spawn as the reasonable follow-up if the shell-string domain ever proved too sensitive. It did: every model value had to survive POSIX single-quoting, the probe had to be scripted in tests, and the executor's own timeout classification duplicated what the cooperative tool-timeout policy already owns. + +## Decision + +`@deepseek-ai/dsh-tool-fs-search` now runs the PACKAGED ripgrep binary (`@vscode/ripgrep`, an npm dependency whose optional platform packages ship the binary) through the `ctx.subprocess` seam: `runRipgrep()` spawns `rgPath` with a plain argv vector, collect-mode stdout/stderr, `graceMs`, and `exec.signal` forwarded. There is no shell layer, so the shell-quoting boundary is gone from execution; `singleQuote` stays exported as a compatibility surface with its tests. Registration is unconditional — the load-time `command -v rg` probe and the conditional registration decision are deleted, and with them the "rg not found" warning. The package injects `tools`, `systemPrompt`, and `subprocess`. + +Exit semantics stay tool-owned: exit 0 is success with results, exit 1 is a successful empty search, anything else classifies into the existing `SEARCH_*` vocabulary (invalid pattern, launch failure, signal kill, raw-output overflow). Timeout is the cooperative tool-call budget attached to the tool definitions: `@deepseek-ai/dsh-timeout-policy` aborts `exec.signal`, the subprocess seam's terminate escalation provides the hard kill, and the tool reports `SEARCH_ABORTED`. The working directory is the session header cwd when present, else `process.cwd()` — there is no executor config to default through anymore, so the tool owns the fallback. + +The `fs-glob-sampling` ACP snapshot scenario now executes the real packaged binary against a prepared workspace whose fixed mtimes pin the `--sort=modified` order, replacing the PATH-injected `rg` stand-in (POSIX-only, because the displayed paths carry `/` separators the session-log comparison cannot normalize). + +## Alternatives considered + +**Keep the bash seam and probe, but document `rg` as a required host dependency.** Rejected: the host dependency is exactly the failure this change removes, and Windows support for the discovery tools was the point of the exercise; a documented requirement is still a requirement. + +**Make `rgPath` injectable (a config field or env override) so tests and snapshots keep substituting a stand-in binary.** Rejected: it adds a public deployment surface whose only consumer would be test seams, and the real binary is deterministic enough to pin directly through fixture mtimes — the packaged binary is the deployment, so tests should exercise it. + +**Switch to a pure-JS glob/search engine (e.g. `picomatch`/`tinyglobby`).** Rejected: the [dependency-swaps audit](../../rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.md) already rejected that on the "no glob engine exists" evidence; ripgrep semantics (`--sort=modified`, VCS pruning, JSON transport, regex dialect) are the tool contract. + +## Consequences + +- The discovery tools work on every platform the packaged binary covers (darwin/linux/win32, x64/arm64) with no host install; the shipped TUI/Web rosters gain `glob`/`grep` as fixed members ([even-out-shipped-tool-rosters](../feature/2026-07-31-even-out-shipped-tool-rosters.md)). +- The shell-string attack surface is gone: hostile patterns are inert argv elements, pinned by the integration suite, which now runs on Windows too (it previously self-skipped without a system `rg`). +- Load-time failure modes changed: a broken subprocess seam now fails the first search call (`SEARCH_FAILED`) instead of failing plugin load through the probe; a missing binary is a launch failure with the packaged path, not a PATH problem. +- The integration suite's fixture dropped a filename Windows cannot represent (`"` in a name), keeping the suite replayable on every platform. diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md new file mode 100644 index 0000000000..55498d366a --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md @@ -0,0 +1,34 @@ +# Agent Note: glob/grep 改用打包的 ripgrep 二进制直接 spawn + +Status: implemented + +[English](2026-08-01-packaged-ripgrep-search.md) | 中文 + +> 取代 [bash 承载的 grep/glob 发现工具](../../archived/feature/2026-07-09-bash-backed-grep-glob-discovery.md)：v1 决策中明确延期的方案——直接 spawn ripgrep——现在成为实际交付的实现。 + +## 问题 + +`glob`/`grep` 工具经由 bash 执行器 seam 运行，这使系统 `rg` 安装成为宿主依赖。Windows 和容器镜像的 `PATH` 默认没有 `rg`，工具在那里会静默消失；部署方只能从加载期探针警告里发现这一点。bash seam 还迫使整个模型可见参数面经过一个 shell 引号工具，因为工具与 ripgrep 之间隔着一层 shell——[bash 承载决策](../../archived/feature/2026-07-09-bash-backed-grep-glob-discovery.md) 把这种耦合记为 v1 的取舍，并把直接 spawn 列为 shell 字符串域一旦被证明过于敏感时的合理后续。它确实被证明了：每个模型值都要经受 POSIX 单引号转义，探针要在测试里脚本化，执行器自身的超时分类还与协作式工具超时策略已有的职责重复。 + +## 决策 + +`@deepseek-ai/dsh-tool-fs-search` 现在运行 PACKAGED（打包的）ripgrep 二进制（`@vscode/ripgrep`，一个 npm 依赖，其可选平台包随附二进制），经由 `ctx.subprocess` seam：`runRipgrep()` 以纯 argv 向量 spawn `rgPath`，配以 collect 模式 stdout/stderr、`graceMs` 与转发的 `exec.signal`。不再有 shell 层，执行路径上的 shell 引号边界随之消失；`singleQuote` 作为兼容导出与其测试保留。注册变为无条件——加载期 `command -v rg` 探针与条件注册决策被删除，连同那条 "rg not found" 警告。本包注入 `tools`、`systemPrompt` 与 `subprocess`。 + +退出语义仍由工具拥有：退出码 0 为有结果的成功，1 为成功的空搜索，其余归入既有 `SEARCH_*` 词汇（无效模式、启动失败、信号杀死、原始输出溢出）。超时是挂在工具定义上的协作式工具调用预算：`@deepseek-ai/dsh-timeout-policy` 中止 `exec.signal`，subprocess seam 的终止升级提供硬终止，工具报告 `SEARCH_ABORTED`。工作目录为会话 header cwd（存在时），否则为 `process.cwd()`——不再有执行器配置可供默认化，因此回退由工具自己拥有。 + +`fs-glob-sampling` ACP 快照场景改为执行真实的打包二进制，作用于一个用固定 mtime 钉住 `--sort=modified` 顺序的预制工作区，取代 PATH 注入的 `rg` 替身（仅 POSIX：展示路径携带 `/` 分隔符，会话日志比较无法归一化）。 + +## 备选方案 + +**保留 bash seam 与探针，仅把 `rg` 记为必需宿主依赖。** 否决：宿主依赖正是本次改动要消除的失败模式，而让发现工具支持 Windows 正是此举的目的；写进文档的依赖仍是依赖。 + +**让 `rgPath` 可注入（配置字段或环境变量覆盖），让测试与快照继续替换替身二进制。** 否决：这会新增一个只有测试 seam 会消费的公开部署面，而真实二进制本身足够确定——通过 fixture mtime 即可直接钉住；打包二进制就是部署形态，测试应当拿它来测。 + +**改用纯 JS 的 glob/搜索引擎（如 `picomatch`/`tinyglobby`）。** 否决：[依赖替换审计](../../rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.md) 已基于"不存在 glob 引擎"的证据否决过该方向；ripgrep 语义（`--sort=modified`、VCS 剪枝、JSON 传输、正则方言）就是工具契约。 + +## 后果 + +- 发现工具在打包二进制覆盖的每个平台（darwin/linux/win32，x64/arm64）上开箱即用，无需宿主安装；交付的 TUI/Web 工具清单把 `glob`/`grep` 变为固定成员（见 [拉平交付的工具清单](../feature/2026-07-31-even-out-shipped-tool-rosters.md)）。 +- shell 字符串攻击面消失：恶意模式只是惰性 argv 元素，由集成套件钉住；该套件现在也在 Windows 上运行（此前没有系统 `rg` 时它自行跳过）。 +- 加载期失败模式改变：subprocess seam 损坏现在让首次搜索调用失败（`SEARCH_FAILED`），而非通过探针使插件加载失败；二进制缺失是带打包路径的启动失败，而不是 PATH 问题。 +- 集成套件的 fixture 去掉了 Windows 无法表示的文件名（名称含 `"`），保证套件在每个平台都能重放。 diff --git a/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.i18n.yaml b/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.i18n.yaml index 83e965b391..60be2bc25f 100644 --- a/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.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/2026-07-31-even-out-shipped-tool-rosters.md -2026-07-31-even-out-shipped-tool-rosters.md: 316e5045e559e2da162c53d64989ccecfd18b857 -2026-07-31-even-out-shipped-tool-rosters.zh.md: ed39212dc4877f4df1dc1c6e84142b61a866c548 +2026-07-31-even-out-shipped-tool-rosters.md: d5f1d714ab538b740c25bdf148df285567c616ca +2026-07-31-even-out-shipped-tool-rosters.zh.md: b09fb43ab66f3784f1a3a3f2a6ee74e185fbdad8 diff --git a/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.md b/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.md index 316e5045e5..d5f1d714ab 100644 --- a/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.md +++ b/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.md @@ -12,7 +12,7 @@ The result was a user-visible difference nobody had decided: the same model, ask ## Decision -The rows that are not surface-specific move into [`base.cordis.yml`](../../../../apps/cli/config/base.cordis.yml), and three more join them: `tool-session-query`, `tool-str-replace-editor`, and `repeat-tool-guard`. Web search moves there too; its [deployment decision](2026-07-31-web-default-search.md) owns the security boundary while the shared base owns its surface-neutral mount. Both surfaces now assemble the same roster: twenty-five tools on every host, plus `glob` and `grep` when ripgrep is available. +The rows that are not surface-specific move into [`base.cordis.yml`](../../../../apps/cli/config/base.cordis.yml), and three more join them: `tool-session-query`, `tool-str-replace-editor`, and `repeat-tool-guard`. Web search moves there too; its [deployment decision](2026-07-31-web-default-search.md) owns the security boundary while the shared base owns its surface-neutral mount. Both surfaces now assemble the same roster: twenty-seven tools on every host — the twenty-five shared rows plus `glob` and `grep`, which are fixed members because `dsh-tool-fs-search` spawns the [packaged ripgrep binary](../architecture/2026-08-01-packaged-ripgrep-search.md). Two rows stay surface-specific. `tmux-context` is TUI-only because a browser surface has no terminal multiplexer to describe. `session-reference` is TUI-only because it drives the shared session-query index from the launcher's process-local path, and the browser sidebar reconciles that index on its own first search. @@ -46,7 +46,7 @@ The same smoke pins the TUI's unchanged execution posture from the same artifact [`apps/web/tests/shipped-composition.e2e.ts`](../../../../apps/web/tests/shipped-composition.e2e.ts) covers the Web surface in the built lane, asserting its catalog, that its access default is untouched, and that `workspace-write`'s writable roots include the temp directories — a trap that makes sandbox tests lie when the workspace sits under `/tmp` ([`roots.ts`](../../../../packages/sandbox/sandbox/src/roots.ts)). -`glob` and `grep` are asserted as an all-or-nothing pair rather than fixed members: `dsh-tool-fs-search` probes `command -v rg` at load and registers neither tool without ripgrep, which is a host dependency. +`glob` and `grep` are asserted as fixed members rather than a host-dependent pair: `dsh-tool-fs-search` spawns the packaged ripgrep binary and registers both tools unconditionally, so the pair is always present. Beyond the committed tests, both surfaces were driven against a real key from the built `apps/cli/lib/bin.js` under plain Node. Every mounted tool executed successfully, including `ralph` and `web_search`; the model never reached `cordis_*` or `mcp_*`, fell back to `grep` when asked for LSP navigation, and used a background `bash` task when asked for a persistent terminal. @@ -62,7 +62,7 @@ Beyond the committed tests, both surfaces were driven against a real key from th ## Consequences -The same model gets the same tools on both surfaces, and the difference that existed for no recorded reason is gone. The tests assert the twenty-five unconditional names exactly and require the ripgrep-dependent pair to be either present together or absent together on both sides, so a later change that alters only one surface fails a check instead of shipping quietly. +The same model gets the same tools on both surfaces, and the difference that existed for no recorded reason is gone. The tests assert all twenty-seven names exactly on both sides, so a later change that alters only one surface fails a check instead of shipping quietly. `apps/cli` gains five workspace dependencies: four the shipped tree now mounts, plus `dsh-mcp-client`, which it does not mount and which exists so an installed `dsh` can. diff --git a/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.zh.md b/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.zh.md index ed39212dc4..b09fb43ab6 100644 --- a/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.zh.md +++ b/.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -那些并非 surface 专属的行移入 [`base.cordis.yml`](../../../../apps/cli/config/base.cordis.yml),另有三行加入:`tool-session-query`、`tool-str-replace-editor` 和 `repeat-tool-guard`。Web 搜索也一并移入；其[部署决策](2026-07-31-web-default-search.md)负责安全边界，共享 base 则负责与 surface 无关的挂载。两个 surface 现在组装同一份清单：每台宿主上都有二十五个工具，ripgrep 可用时再加上 `glob` 和 `grep`。 +那些并非 surface 专属的行移入 [`base.cordis.yml`](../../../../apps/cli/config/base.cordis.yml),另有三行加入:`tool-session-query`、`tool-str-replace-editor` 和 `repeat-tool-guard`。Web 搜索也一并移入；其[部署决策](2026-07-31-web-default-search.md)负责安全边界，共享 base 则负责与 surface 无关的挂载。两个 surface 现在组装同一份清单：每台宿主上都有二十七个工具——二十五个共享行加上 `glob` 和 `grep`，它们成为固定成员是因为 `dsh-tool-fs-search` 直接 spawn [打包的 ripgrep 二进制](../architecture/2026-08-01-packaged-ripgrep-search.md)。 有两行仍是 surface 专属。`tmux-context` 只在 TUI,因为浏览器 surface 没有终端复用器可描述。`session-reference` 只在 TUI,因为它以 launcher 的进程本地路径驱动共享的 session-query 索引,而浏览器侧边栏会在自己的首次搜索里重建该索引。 @@ -62,7 +62,7 @@ Status: implemented ## 后果 -同一个模型在两个 surface 上拿到同样的工具,那处没有记录理由的差异消失了。测试会精确断言二十五个无条件提供的名称，并要求依赖 ripgrep 的一对工具在两侧要么同时存在、要么同时缺席，因此日后只改一个 surface 都会让检查失败而不是悄悄发出去。 +同一个模型在两个 surface 上拿到同样的工具,那处没有记录理由的差异消失了。测试会精确断言两侧全部二十七个名称，因此日后只改一个 surface 都会让检查失败而不是悄悄发出去。 `apps/cli` 增加五个 workspace 依赖:四个是交付树现在挂载的,外加 `dsh-mcp-client`——它并不被挂载,存在的意义是让已安装的 `dsh` 能挂。 diff --git a/THIRD_PARTY_NOTICES.md b/THIRD_PARTY_NOTICES.md index 754ae93d82..1b14996c3f 100644 --- a/THIRD_PARTY_NOTICES.md +++ b/THIRD_PARTY_NOTICES.md @@ -47,6 +47,9 @@ External packages that a workspace package resolves at runtime. `scripts/install | [`@opentelemetry/sdk-logs`](https://github.com/open-telemetry/opentelemetry-js) | Apache-2.0 | | [`@shikijs/langs`](https://github.com/shikijs/shiki) | MIT | | [`@standard-schema/spec`](https://github.com/standard-schema/standard-schema) | MIT | +| [`@testing-library/dom`](https://github.com/testing-library/dom-testing-library) | MIT | +| [`@testing-library/react`](https://github.com/testing-library/react-testing-library) | MIT | +| [`@vscode/ripgrep`](https://github.com/microsoft/vscode-ripgrep) | MIT | | [`anser`](https://github.com/IonicaBizau/anser) | MIT | | [`chokidar`](https://github.com/paulmillr/chokidar) | MIT | | [`clsx`](https://github.com/lukeed/clsx) | MIT | @@ -54,6 +57,7 @@ External packages that a workspace package resolves at runtime. `scripts/install | [`diff`](https://github.com/kpdecker/jsdiff) | BSD-3-Clause | | [`dotenv`](https://github.com/motdotla/dotenv) | BSD-2-Clause | | [`eventsource-parser`](https://github.com/rexxars/eventsource-parser) | MIT | +| [`execa`](https://github.com/sindresorhus/execa) | MIT | | [`handlebars`](https://github.com/handlebars-lang/handlebars.js) | MIT | | [`immer`](https://github.com/immerjs/immer) | MIT | | [`js-yaml`](https://github.com/nodeca/js-yaml) | MIT | @@ -79,6 +83,7 @@ External packages that a workspace package resolves at runtime. `scripts/install | [`turndown`](https://github.com/mixmark-io/turndown) | MIT | | [`typescript`](https://github.com/microsoft/TypeScript) | Apache-2.0 | | [`use-sync-external-store`](https://github.com/facebook/react) | MIT | +| [`vitest`](https://github.com/vitest-dev/vitest) | MIT | | [`yaml`](https://github.com/eemeli/yaml) | ISC | | [`zod`](https://github.com/colinhacks/zod) | MIT | | [`zustand`](https://github.com/pmndrs/zustand) | MIT | @@ -98,8 +103,6 @@ External packages **directly declared** only by repository tooling, test infrast | [`@modelcontextprotocol/server-everything`](https://github.com/modelcontextprotocol/servers) | MIT / Apache-2.0 | | [`@modelcontextprotocol/server-filesystem`](https://github.com/modelcontextprotocol/servers) | MIT / Apache-2.0 | | [`@stylistic/eslint-plugin`](https://github.com/eslint-stylistic/eslint-stylistic) | MIT | -| [`@testing-library/dom`](https://github.com/testing-library/dom-testing-library) | MIT | -| [`@testing-library/react`](https://github.com/testing-library/react-testing-library) | MIT | | [`@types/babel__code-frame`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | | [`@types/js-yaml`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | | [`@types/jsdom`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | @@ -122,7 +125,6 @@ External packages **directly declared** only by repository tooling, test infrast | [`esbuild`](https://github.com/evanw/esbuild) | MIT | | [`eslint`](https://github.com/eslint/eslint) | MIT | | [`eslint-plugin-sonarjs`](https://github.com/SonarSource/SonarJS) | LGPL-3.0-only | -| [`execa`](https://github.com/sindresorhus/execa) | MIT | | [`fast-check`](https://github.com/dubzzz/fast-check) | MIT | | [`jscpd`](https://github.com/kucherenko/jscpd) | MIT | | [`jsdom`](https://github.com/jsdom/jsdom) | MIT | @@ -142,7 +144,6 @@ External packages **directly declared** only by repository tooling, test infrast | [`vite-tsconfig-paths`](https://github.com/aleclarson/vite-tsconfig-paths) | MIT | | [`vitepress`](https://github.com/vuejs/vitepress) | MIT | | [`vitepress-plugin-mermaid`](https://github.com/emersonbottero/vitepress-plugin-mermaid) | MIT | -| [`vitest`](https://github.com/vitest-dev/vitest) | MIT | `eslint-plugin-sonarjs` (LGPL-3.0-only) and `lightningcss` (MPL-2.0) run only as development tooling; their code is not linked into or distributed with any DeepSeek Harness artifact. diff --git a/apps/cli/tests/shipped-composition.e2e.ts b/apps/cli/tests/shipped-composition.e2e.ts index ac1e9d5456..82bf698c17 100644 --- a/apps/cli/tests/shipped-composition.e2e.ts +++ b/apps/cli/tests/shipped-composition.e2e.ts @@ -54,10 +54,10 @@ const EXPECTED_TUI_TOOLS = [ ] /** - * `glob` and `grep` come from `dsh-tool-fs-search`, which probes `command -v rg` - * through the mounted bash executor at load and registers neither tool when - * ripgrep is absent. That is a host dependency, not a composition decision, so the - * pair is asserted separately — present together or absent together. + * `glob` and `grep` come from `dsh-tool-fs-search`, which spawns the PACKAGED + * ripgrep binary (`@vscode/ripgrep`) through the subprocess seam, so the pair + * is always present on every host — asserted as fixed members, not a host + * dependency. */ const RIPGREP_TOOLS = ['glob', 'grep'] @@ -117,7 +117,9 @@ describe('shipped dsh composition (real Loader tree in a PTY)', () => { }) expect(output).toContain(COMPOSITION_REPLY_TEXT) expect(observed?.names.filter(name => !RIPGREP_TOOLS.includes(name))).toEqual(EXPECTED_TUI_TOOLS) - expect([[], RIPGREP_TOOLS]).toContainEqual(observed?.names.filter(name => RIPGREP_TOOLS.includes(name))) + // The packaged ripgrep binary ships with the dependency, so the pair is a + // fixed roster member on every host. + expect(observed?.names.filter(name => RIPGREP_TOOLS.includes(name))).toEqual(RIPGREP_TOOLS) // The TUI mounts the unrestricted local executors, so `tool-bash` emits no // escalation pair. Pinning its absence keeps a later sandbox change from // arriving here unannounced. diff --git a/apps/web/tests/shipped-composition.e2e.ts b/apps/web/tests/shipped-composition.e2e.ts index 0cad833303..80adcdd1de 100644 --- a/apps/web/tests/shipped-composition.e2e.ts +++ b/apps/web/tests/shipped-composition.e2e.ts @@ -49,10 +49,10 @@ const EXPECTED_TOOLS = [ ] /** - * `glob` and `grep` come from `dsh-tool-fs-search`, which probes `command -v rg` - * through the mounted bash executor at load and registers neither tool when - * ripgrep is absent. That is a host dependency, not a composition decision, so the - * pair is asserted separately — present together or absent together. + * `glob` and `grep` come from `dsh-tool-fs-search`, which spawns the PACKAGED + * ripgrep binary (`@vscode/ripgrep`) through the subprocess seam, so the pair + * is always present on every host — asserted as fixed members, not a host + * dependency. */ const RIPGREP_TOOLS = ['glob', 'grep'] @@ -67,7 +67,9 @@ it('assembles the shipped Web catalog and keeps its access default', async () => scaffold = await launchWebScaffold() const names = scaffold.ctx.tools.schemas().map(schema => schema.name).sort() expect(names.filter(name => !RIPGREP_TOOLS.includes(name))).toEqual(EXPECTED_TOOLS) - expect([[], RIPGREP_TOOLS]).toContainEqual(names.filter(name => RIPGREP_TOOLS.includes(name))) + // The packaged ripgrep binary ships with the dependency, so the pair is a + // fixed roster member on every host. + expect(names.filter(name => RIPGREP_TOOLS.includes(name))).toEqual(RIPGREP_TOOLS) // `workspace-write` is not "the workspace and nothing else": the shared roots // helper always admits the temp directories too. Pinning it against an // explicit mode keeps the claim independent of this surface's default, and diff --git a/docs/config-catalog.md b/docs/config-catalog.md index a356a151e3..20f835bb7f 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1716,7 +1716,7 @@ Source: [`packages/fs/tool-fs/src/index.ts:24`](../packages/fs/tool-fs/src/index ## `@deepseek-ai/dsh-tool-fs-search` -Requires: `tools` · `systemPrompt` · `bash` +Requires: `tools` · `systemPrompt` · `subprocess` ```ts config-catalog /** Plugin config; over-cap glob sampling is an explicit deployment choice and the remaining fields have defaults. */ @@ -1738,7 +1738,7 @@ export interface Config { } ``` -Source: [`packages/fs/tool-fs-search/src/index.ts:71`](../packages/fs/tool-fs-search/src/index.ts) +Source: [`packages/fs/tool-fs-search/src/index.ts:70`](../packages/fs/tool-fs-search/src/index.ts) ## `@deepseek-ai/dsh-tool-goal` diff --git a/docs/module-graph.md b/docs/module-graph.md index f0f58a18c1..87789c9edb 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -713,12 +713,12 @@ flowchart TD pkg_tool_fs --> pkg_system_prompt pkg_tool_fs --> pkg_tools pkg_tool_fs --> pkg_user_approval - pkg_tool_fs_search --> pkg_bash pkg_tool_fs_search --> pkg_invariants pkg_tool_fs_search --> pkg_llm pkg_tool_fs_search --> pkg_retention pkg_tool_fs_search --> pkg_session pkg_tool_fs_search --> pkg_spill + pkg_tool_fs_search --> pkg_subprocess pkg_tool_fs_search --> pkg_system_prompt pkg_tool_fs_search --> pkg_tools pkg_tool_str_replace_editor --> pkg_fs @@ -1176,7 +1176,7 @@ flowchart TD | [`tool-goal`](../packages/goal/tool-goal) | `goal` | [`agent`](../packages/core/agent), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`paths`](../packages/util/paths), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | -| [`tool-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`bash`](../packages/bash/bash), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | +| [`tool-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`subprocess`](../packages/subprocess/subprocess), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-str-replace-editor`](../packages/fs/tool-str-replace-editor) | `fs` | [`fs`](../packages/fs/fs), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | | [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 7d6fa79dea..d19a7adf52 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -23,7 +23,7 @@ This table connects model-visible tool names to the plugin package and service s | `@deepseek-ai/dsh-tool-bash-persistent` | `bash` | `ctx.tools`, `ctx.pty`, `an owning Agent at execution time` | `tool/call`, `PTY shell state`, `tool/result` | - | One owner-isolated persistent bash tool; deployment composition supplies the PTY backend and may override the model-facing environment description. | | `@deepseek-ai/dsh-tool-str-replace-editor` | `str_replace_editor` | `ctx.tools`, `ctx.fs` | `tool/call`, `fs/observed after successful file operations`, `tool/result` | - | Standalone view/create/unique literal replace/line insert tool over the filesystem seam; it composes with any shell or terminal surface. | | `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after successful file operations`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. | -| `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.bash`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). The catalog uses `sampleOverCapGlobResults: true`; deployments must choose that behavior explicitly. Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. | +| `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.subprocess`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are unconditional discovery tools that spawn the packaged ripgrep binary (`@vscode/ripgrep`) through ctx.subprocess as ordinary foreground calls (never background tasks) — no host `rg` install and no shell layer. The catalog uses `sampleOverCapGlobResults: true`; deployments must choose that behavior explicitly. Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. | | `@deepseek-ai/dsh-tool-pty` | `terminal_close`, `terminal_list`, `terminal_open`, `terminal_read`, `terminal_send`, `terminal_signal` | `ctx.tools`, `ctx.pty`, `ctx.systemPrompt`, `ctx.tasks at call time for run_in_background` | `tool/call`, `tool/result` | - | The six terminal tools are opt-in and complement one-shot bash/filesystem tools. `terminal_send(run_in_background: true)` registers with `ctx.tasks`; TUI, named key sequences, BEL, resize, auto-start, and cross-agent sharing are absent from the schema. | | `@deepseek-ai/dsh-tool-goal` | `create_goal`, `get_goal`, `update_goal` | `ctx.tools`, `ctx.agents`, `ctx.goals`, `ctx.systemPrompt`, `a calling Agent in an authorized open turn` | `tool/call`, `user/message goal snapshot for mutations`, `tool/result` | - | create, edit, pause, and resume require direct-human root authority; complete and blocked also accept the exact current goal round. The default blocked lower bound is three admitted rounds. | | `@deepseek-ai/dsh-tool-lsp` | `lsp` | `ctx.tools`, `ctx.lsp`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | The lsp tool keeps provider selection and language-server subprocesses behind ctx.lsp, so its model-visible schema stays stable across providers. Requires a registered provider (e.g. `@deepseek-ai/dsh-lsp-local`) at runtime; without one, a query returns the structured `LSP_UNAVAILABLE` error rather than changing the schema. | @@ -524,7 +524,7 @@ Search file contents with a ripgrep regular expression. Returns matching lines w Source: [`packages/fs/tool-fs-search/src/index.ts`](../packages/fs/tool-fs-search/src/index.ts) -glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). The catalog uses `sampleOverCapGlobResults: true`; deployments must choose that behavior explicitly. Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. +glob and grep are unconditional discovery tools that spawn the packaged ripgrep binary (`@vscode/ripgrep`) through ctx.subprocess as ordinary foreground calls (never background tasks) — no host `rg` install and no shell layer. The catalog uses `sampleOverCapGlobResults: true`; deployments must choose that behavior explicitly. Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. ## `@deepseek-ai/dsh-tool-pty` diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index b652f09931..277d0b20ca 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -1,6 +1,6 @@ import { fileURLToPath } from 'node:url' import { readFileSync } from 'node:fs' -import { mkdir, writeFile } from 'node:fs/promises' +import { mkdir, utimes, writeFile } from 'node:fs/promises' import { dirname, join } from 'node:path' import { homedir } from 'node:os' import { expect, it } from 'vitest' @@ -44,7 +44,6 @@ const SESSION_TITLE_CONFIG = fileURLToPath(new URL('../session-title.cordis.yml' const LSP_CONFIG = fileURLToPath(new URL('./lsp.cordis.yml', import.meta.url)) const WEB_CONFIG = fileURLToPath(new URL('../web.cordis.yml', import.meta.url)) const FS_SEARCH_CONFIG = fileURLToPath(new URL('./fs-search.cordis.yml', import.meta.url)) -const FS_SEARCH_BIN = fileURLToPath(new URL('./fixtures/fs-search-bin', import.meta.url)) const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') const PACKED_CHUNKS_SOURCE = 'hook-cc-pretool-deny' @@ -57,6 +56,33 @@ async function prepareDelimiterPathWorkspace(cwd: string): Promise { ]) } +/** + * Seed the over-cap glob fixture: eight files under `tree/` with fixed mtimes, + * so the packaged ripgrep's `--sort=modified` order is deterministic — three + * files under `archive/`, one each under `docs/`, `src/`, and `test/`, plus + * two flat files (six top-level entries). Scoping the search to `tree/` keeps + * the harness's own session artifacts out of the listing. + */ +async function prepareFsSearchWorkspace(cwd: string): Promise { + const tree = join(cwd, 'tree') + const files: Array<[relative: string, mtime: Date]> = [ + [join('archive', 'a.ts'), new Date(2000, 0, 1, 0, 0, 0, 1)], + [join('archive', 'b.ts'), new Date(2000, 0, 1, 0, 0, 0, 2)], + [join('archive', 'c.ts'), new Date(2000, 0, 1, 0, 0, 0, 3)], + [join('docs', 'guide.md'), new Date(2000, 0, 1, 0, 0, 0, 4)], + [join('src', 'index.ts'), new Date(2000, 0, 1, 0, 0, 0, 5)], + [join('test', 'spec.ts'), new Date(2000, 0, 1, 0, 0, 0, 6)], + ['top.txt', new Date(2000, 0, 1, 0, 0, 0, 7)], + ['notes.md', new Date(2000, 0, 1, 0, 0, 0, 8)], + ] + for (const [relative, mtime] of files) { + const target = join(tree, relative) + await mkdir(dirname(target), { recursive: true }) + await writeFile(target, 'fixture\n') + await utimes(target, mtime, mtime) + } +} + // FIXME: Migrate backend-oriented scenarios to the headless stream-json suite; // this ACP suite should eventually retain only automation-protocol contracts. @@ -150,9 +176,12 @@ const SCENARIOS: Scenario[] = [ hasModelTurn: true, recorded: true, }, - // The real Loader/app/bash path executes a deterministic rg stand-in at the - // external-process seam, pinning over-cap glob sampling without depending on - // a host-installed ripgrep binary. + // The real Loader/app/subprocess path executes the PACKAGED ripgrep binary + // against a prepared workspace whose fixed mtimes pin the + // `--sort=modified` order, pinning over-cap glob sampling without depending + // on a host-installed ripgrep binary or a PATH stand-in. POSIX-only because + // the displayed paths carry `/` separators the session-log comparison + // cannot normalize. { name: 'fs-glob-sampling', hasModelTurn: true, @@ -160,7 +189,7 @@ const SCENARIOS: Scenario[] = [ pinsHeader: true, headerClass: 'fs-search', configPath: FS_SEARCH_CONFIG, - env: { PATH: `${FS_SEARCH_BIN}:${process.env.PATH ?? ''}` }, + prepareWorkspace: prepareFsSearchWorkspace, posixOnly: true, }, { name: 'fs-read', hasModelTurn: true, recorded: true }, diff --git a/examples/acp-agent/tests/fixtures/fs-search-bin/rg b/examples/acp-agent/tests/fixtures/fs-search-bin/rg deleted file mode 100755 index 181ad68837..0000000000 --- a/examples/acp-agent/tests/fixtures/fs-search-bin/rg +++ /dev/null @@ -1,10 +0,0 @@ -#!/bin/sh -printf '%s\n' \ - 'archive/a.ts' \ - 'archive/b.ts' \ - 'archive/c.ts' \ - 'old\one' \ - 'old\two' \ - 'src/index.ts' \ - 'docs/guide.md' \ - 'test/spec.ts' diff --git a/examples/acp-agent/tests/snapshots/fs-glob-sampling/input.json b/examples/acp-agent/tests/snapshots/fs-glob-sampling/input.json index cc5fc95e59..d615bd4840 100644 --- a/examples/acp-agent/tests/snapshots/fs-glob-sampling/input.json +++ b/examples/acp-agent/tests/snapshots/fs-glob-sampling/input.json @@ -2,6 +2,6 @@ "steps": [ { "op": "initialize" }, { "op": "newSession" }, - { "op": "prompt", "text": "Call glob exactly once with pattern * and no path. Then reply with exactly GLOB_SAMPLED and nothing else." } + { "op": "prompt", "text": "Call glob exactly once with pattern * and path tree. Then reply with exactly GLOB_SAMPLED and nothing else." } ] } diff --git a/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl b/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl index b66ffc36b4..ca51259632 100644 --- a/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl @@ -1,18 +1,18 @@ {"type":"session","version":0,"id":"f5a99d52-3eaa-4ce7-858d-61d4fd77df2a","createdAt":1785218400000,"cwd":"{{cwd}}","delegationDepth":0} {"type":"turn/start","seq":0,"time":1785218400001,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1785218400002,"data":{"content":[{"type":"text","text":"Call glob exactly once with pattern * and no path. Then reply with exactly GLOB_SAMPLED and nothing else."}],"source":{"kind":"user"},"role":"user","id":"6790985f-1de2-42f8-a7f1-24e46d6439c7"},"surfaceOp":"append"} +{"type":"user/message","seq":1,"time":1785218400002,"data":{"content":[{"type":"text","text":"Call glob exactly once with pattern * and path tree. Then reply with exactly GLOB_SAMPLED and nothing else."}],"source":{"kind":"user"},"role":"user","id":"6790985f-1de2-42f8-a7f1-24e46d6439c7"},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1785218400003,"data":{"title":"Call glob exactly once with","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1785218400004,"data":{"turn":1,"step":1}} {"type":"request/header","seq":4,"time":1785218400005,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":5,"time":1785483397569,"data":{"provider":"deepseek","model":"deepseek-v4-pro"}} {"type":"assistant/chunk","seq":6,"time":1785218400007,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":7,"time":1785218400008,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"glob-sampling-call","name":"glob","argumentsDelta":"{\"pattern\":\"*\"}"}}} -{"type":"assistant/chunk","seq":8,"time":1785218400009,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\"}"}}}} +{"type":"assistant/chunk","seq":7,"time":1785218400008,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"glob-sampling-call","name":"glob","argumentsDelta":"{\"pattern\":\"*\",\"path\":\"tree\"}"}}} +{"type":"assistant/chunk","seq":8,"time":1785218400009,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\",\"path\":\"tree\"}"}}}} {"type":"assistant/chunk","seq":9,"time":1785218400010,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1,"outputTokens":1}}}} {"type":"assistant/chunk","seq":10,"time":1785483397579,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":11,"time":1785483397579,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\"}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-pro"},"id":"a127cfe5-39fb-462c-8e5a-a8c79bd0e52b"},"usage":{"inputTokens":1,"outputTokens":1}},"sourceEventSeqs":[6,7,8,9,10],"surfaceOp":"append"} -{"type":"tool/call","seq":12,"time":1785483397579,"data":{"turn":1,"step":1,"callId":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\"}"}} -{"type":"tool/result","seq":13,"time":1785483398062,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"glob-sampling-call"},"content":[{"type":"tool-result","toolCallId":"glob-sampling-call","content":[{"type":"text","text":"archive/a.ts\nold\\one\nold\\two\nsrc/index.ts\n\n(Showing 4 of 8 paths, sampled across 4 of the 6 top-level entries this pattern matched instead of taken in modification-time order. Narrow path to inspect a specific subtree. The complete result could not be saved; narrow pattern or path to see more.)"}],"isError":false}],"role":"user","id":"2beecb2e-627d-43dc-a936-03e1dc874093"},"meta":{"shape":"paths","paths":["archive/a.ts","old\\one","old\\two","src/index.ts"],"truncated":true,"total":8}},"sourceEventSeqs":[12],"surfaceOp":"append"} +{"type":"assistant/message","seq":11,"time":1785483397579,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\",\"path\":\"tree\"}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-pro"},"id":"a127cfe5-39fb-462c-8e5a-a8c79bd0e52b"},"usage":{"inputTokens":1,"outputTokens":1}},"sourceEventSeqs":[6,7,8,9,10],"surfaceOp":"append"} +{"type":"tool/call","seq":12,"time":1785483397579,"data":{"turn":1,"step":1,"callId":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\",\"path\":\"tree\"}"}} +{"type":"tool/result","seq":13,"time":1785483398062,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"glob-sampling-call"},"content":[{"type":"tool-result","toolCallId":"glob-sampling-call","content":[{"type":"text","text":"tree/archive/a.ts\ntree/docs/guide.md\ntree/src/index.ts\ntree/test/spec.ts\n\n(Showing 4 of 8 paths, sampled across 4 of the 6 top-level entries this pattern matched instead of taken in modification-time order. Narrow path to inspect a specific subtree. The complete result could not be saved; narrow pattern or path to see more.)"}],"isError":false}],"role":"user","id":"2beecb2e-627d-43dc-a936-03e1dc874093"},"meta":{"shape":"paths","paths":["tree/archive/a.ts","tree/docs/guide.md","tree/src/index.ts","tree/test/spec.ts"],"truncated":true,"total":8}},"sourceEventSeqs":[12],"surfaceOp":"append"} {"type":"step/end","seq":14,"time":1785483398062,"data":{"turn":1,"step":1}} {"type":"step/start","seq":15,"time":1785483398072,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":16,"time":1785218400017,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} diff --git a/packages/fs/tool-fs-search/README.i18n.yaml b/packages/fs/tool-fs-search/README.i18n.yaml index bedb8289c1..5ed7bfb8bb 100644 --- a/packages/fs/tool-fs-search/README.i18n.yaml +++ b/packages/fs/tool-fs-search/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/fs/tool-fs-search/README.md -README.md: b12ffda9869c7d6bef5ea5b54594781ecf555ff4 -README.zh.md: 7dd6cdf9a209f2fe357b4ffe48d20d574266ce60 +README.md: 0152be017ae15fc83a3d5cb7df927f25d04d2d53 +README.zh.md: 69ce49f3ad1621021dc1d0938cdc07a900d1cda8 diff --git a/packages/fs/tool-fs-search/README.md b/packages/fs/tool-fs-search/README.md index b12ffda986..0152be017a 100644 --- a/packages/fs/tool-fs-search/README.md +++ b/packages/fs/tool-fs-search/README.md @@ -2,21 +2,21 @@ English | [中文](README.zh.md) -The **model-facing filesystem discovery tools**—`glob`, `grep`—are backed by the **bash executor seam**, not by `ctx.fs` provider methods. At load, the package probes `command -v rg` through `ctx.bash`; if the executor cannot find ripgrep on its `PATH`, it logs a warning and registers no tools or prompt sections. Each call assembles a fixed ripgrep command (every model-controlled value through one package-private shell-quoting helper), runs it via `ctx.bash.resolve(request)` → `ctx.bash.run(spec)` as an ordinary foreground tool call, parses the raw `rg` output, and returns a workdir-relative canonical value. The package injects `tools`, `systemPrompt`, and `bash`—deliberately **not** `fs`; `ctx.spillStore` is read opportunistically with `ctx.get()` because formatted-result spill is optional. +The **model-facing filesystem discovery tools**—`glob`, `grep`—are backed by the **packaged ripgrep binary** (`@vscode/ripgrep`), not by `ctx.fs` provider methods and not by a system `rg` install. Registration is unconditional: the binary ships inside the npm dependency, so there is no load-time availability probe. Each call spawns the binary through the `ctx.subprocess` seam with a fixed argv vector (model-controlled values are plain argv elements — no shell layer exists, so no quoting applies), parses the raw `rg` output, and returns a workdir-relative canonical value. The package injects `tools`, `systemPrompt`, and `subprocess`—deliberately **not** `fs`; `ctx.spillStore` is read opportunistically with `ctx.get()` because formatted-result spill is optional. ```ts ignore-check // A deployment chooses how over-cap glob pages are selected. -await ctx.plugin(LocalBashExecutor, { cwd: process.cwd() }) // @deepseek-ai/dsh-bash-local +await ctx.plugin(LocalSubprocessService) // @deepseek-ai/dsh-subprocess-local await ctx.plugin(ToolFsSearch, { sampleOverCapGlobResults: false }) // Optional: a spill backend makes capped results fully recoverable. await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh-spill-local ``` -Why bash-backed: local workspace discovery is naturally a process-backed `rg` workflow, and putting search on `ctx.fs` would force every filesystem backend to grow a search API. The bash executor owns request defaulting/capping, subprocess execution, process-group termination, environment scrubbing, raw output capture, and backend substitution (local, sandboxed, remote); this package owns schemas, argument validation, shell quoting, parsing, retention, formatted-result spill, and timeout declaration. The tools never call `ctx.bash.start()` and never expose a bash task id — the call returns only after `rg` exits, times out, is aborted, or fails. +Why spawn-backed: local workspace discovery is naturally a process-backed `rg` workflow, and putting search on `ctx.fs` would force every filesystem backend to grow a search API. The subprocess seam owns spawn execution, process-tree termination, environment scrubbing, and bounded output capture; this package owns schemas, argument validation, argv construction, parsing, retention, formatted-result spill, and timeout declaration. The tools never expose a background task — the call returns only after `rg` exits, is terminated by the cooperative timeout, is aborted, or fails. -## Deployment requirement: rg + co-located bash/filesystem +## Deployment requirement: no host rg, co-located workdir/filesystem -The mounted bash executor must be able to resolve `rg` from its `PATH` at plugin load; otherwise `glob` and `grep` are absent from the model-visible tool schema. Returned paths are displayed relative to the resolved bash workdir (the calling agent's session cwd when present, else the executor's configured default) and are follow-up-readable with `read` only when the bash workdir and the filesystem root are the same workspace. v1 documents that co-location requirement and performs no runtime cross-service validation; remote or virtual filesystem search waits for a shared workspace contract or a provider-specific search backend. +The binary ships with the package on every supported platform (macOS/Linux/Windows, x64/arm64), so no host `rg` install is required and the tools register on every deployment. Returned paths are displayed relative to the resolved workdir (the calling agent's session cwd when present, else `process.cwd()`) and are follow-up-readable with `read` only when that workdir and the filesystem root are the same workspace. v1 documents that co-location requirement and performs no runtime cross-service validation; remote or virtual filesystem search waits for a shared workspace contract or a provider-specific search backend. ## Config @@ -29,24 +29,24 @@ The mounted bash executor must be able to resolve `rg` from its `PATH` at plugin | `grepMaxMatches` | `250` | Max flat matches one `grep` call retains inline (matches Claude Code's `GrepTool` `head_limit`); later matches go to the formatted spill artifact. | | `grepMaxLineBytes` | `2000` | Byte cap per matched-line preview; the cut preserves UTF-8 boundaries and is marked `(line truncated)`. | | `rawOutputMaxBytes` | `20000000` | Max complete raw `rg` stdout a search will parse (matches Claude Code's ripgrep raw buffer); larger raw output fails with `SEARCH_RAW_OUTPUT_OVERFLOW`. | -| `timeoutMs` | `30000` | Cooperative tool-call budget attached to both tool definitions, enforced by `@deepseek-ai/dsh-timeout-policy` through `exec.signal`; the bash backend's own timeout stays a second safety cap. | +| `timeoutMs` | `30000` | Cooperative tool-call budget attached to both tool definitions, enforced by `@deepseek-ai/dsh-timeout-policy` through `exec.signal`; the subprocess seam's terminate escalation is the hard kill. | ## Tools | Tool | Arguments | Behavior | |---|---|---| -| `glob` | `pattern`, `path?` | `rg --files --glob --sort=modified --no-ignore --hidden` plus VCS metadata excludes (`.git`, `.svn`, `.hg`, `.bzr`, `.jj`, `.sl`). `path` is an optional **directory** search root; omitted means the resolved bash workdir. Returns one FILE path per line; `rg --files` never emits directory entries. The pattern keeps ripgrep semantics: without a `/` it matches the basename at any depth, so `*` matches the whole tree. Complete results stay modification-time ordered; over-cap presentation follows `sampleOverCapGlobResults`. | +| `glob` | `pattern`, `path?` | `rg --files --glob --sort=modified --no-ignore --hidden` plus VCS metadata excludes (`.git`, `.svn`, `.hg`, `.bzr`, `.jj`, `.sl`). `path` is an optional **directory** search root; omitted means the resolved workdir. Returns one FILE path per line; `rg --files` never emits directory entries. The pattern keeps ripgrep semantics: without a `/` it matches the basename at any depth, so `*` matches the whole tree. Complete results stay modification-time ordered; over-cap presentation follows `sampleOverCapGlobResults`. | | `grep` | `pattern`, `path?`, `include?` | Line-oriented `rg --json` parse (no colon-splitting ambiguity). `pattern` is a ripgrep regex; `path` is an optional **file or directory** target; `include` is ONE positive glob filter — a comma-separated list or a negated (`!…`) value is rejected up front (brace alternation like `*.{ts,tsx}` is fine). Returns matches grouped by file as `Line N: `. | Routine budgets stay out of the model-facing schema (no `head_limit`/`offset`/`case_insensitive`/output modes): a model that needs surrounding context reads the matched file with `read`; one that needs later results follows the returned spill locator's retrieval hint. ## Two budgets, two artifacts -Raw `rg` stdout is an internal transport detail. Each search requests `stdoutMaxBytes: rawOutputMaxBytes` from the bash seam and parses only complete retained stdout; if the executor still returns `stdout.truncated`, the search fails with `SEARCH_RAW_OUTPUT_OVERFLOW` and tells the model to narrow the query. A successful `glob` keeps the displayed search root and every acquired path in `{ root, paths }`; when sampling is enabled, `root` lets the Native renderer group an explicit relative or absolute search path by entries beneath that root rather than by its workdir prefix. `grep` keeps every acquired `{ path, lineNumber, line }` in `{ matches }`. Inline item and per-line preview caps apply only in the Native renderer. For a direct surface call with more logical results than the inline cap, post-policy best-effort saves the complete formatted preview through `ctx.spillStore.saveText()` and replaces only presentation with the configured page plus locator. Nested Code dispatches skip that spill because their full canonical value does not enter model context. Missing/failed spill keeps the inline page and reports that the complete result could not be saved—never an `isError`. +Raw `rg` stdout is an internal transport detail. Each search requests a collect-mode stdout budget of `rawOutputMaxBytes` from the subprocess seam and parses only complete retained stdout; if the seam still reports a lossy read, the search fails with `SEARCH_RAW_OUTPUT_OVERFLOW` and tells the model to narrow the query. A successful `glob` keeps the displayed search root and every acquired path in `{ root, paths }`; when sampling is enabled, `root` lets the Native renderer group an explicit relative or absolute search path by entries beneath that root rather than by its workdir prefix. `grep` keeps every acquired `{ path, lineNumber, line }` in `{ matches }`. Inline item and per-line preview caps apply only in the Native renderer. For a direct surface call with more logical results than the inline cap, post-policy best-effort saves the complete formatted preview through `ctx.spillStore.saveText()` and replaces only presentation with the configured page plus locator. Nested Code dispatches skip that spill because their full canonical value does not enter model context. Missing/failed spill keeps the inline page and reports that the complete result could not be saved—never an `isError`. ## Errors -Search failures carry the package-owned `SearchError` (a `HarnessError` subclass), surfaced as `{ name, code }` on `isError` results: `SEARCH_INVALID_PATTERN` (ripgrep rejected the regex/glob), `SEARCH_FAILED` (runtime `rg` disappearance after registration, inaccessible target, signal kill, malformed `--json` output), `SEARCH_RAW_OUTPUT_OVERFLOW` (raw output over `rawOutputMaxBytes`, or still truncated after the requested stdout capture budget), and `SEARCH_ABORTED` (tool timeout, caller cancellation, or the bash executor's own timeout). ripgrep exit semantics are tool-owned: exit 0 is success with results, exit 1 is a successful empty search (`No files found` / `No matches found`), and only other exits are failures. Model argument mistakes (blank pattern, a list-valued `include`) stay ordinary tool argument errors. +Search failures carry the package-owned `SearchError` (a `HarnessError` subclass), surfaced as `{ name, code }` on `isError` results: `SEARCH_INVALID_PATTERN` (ripgrep rejected the regex/glob), `SEARCH_FAILED` (a failed `rg` launch, inaccessible target, signal kill, malformed `--json` output), `SEARCH_RAW_OUTPUT_OVERFLOW` (raw output over `rawOutputMaxBytes`, or still lossy after the requested stdout capture budget), and `SEARCH_ABORTED` (cooperative tool timeout or caller cancellation). ripgrep exit semantics are tool-owned: exit 0 is success with results, exit 1 is a successful empty search (`No files found` / `No matches found`), and only other exits are failures. Model argument mistakes (blank pattern, a list-valued `include`) stay ordinary tool argument errors. ## Model Experience @@ -54,7 +54,7 @@ Search failures carry the package-owned `SearchError` (a `HarnessError` subclass #### What the model sees -After the load-time `rg` probe succeeds, every request in this plugin's registration scope contains the independently registered glob and grep guidance below. Agent-scoped tool restrictions can hide either schema without removing its prompt section. +Every request in this plugin's registration scope contains the independently registered glob and grep guidance below. Agent-scoped tool restrictions can hide either schema without removing its prompt section. ##### Glob guidance with `sampleOverCapGlobResults: true` @@ -86,7 +86,7 @@ Prefix-stable while the plugin scope, sampling choice, and guidance text are unc #### What the model sees -The glob description states the configured over-cap ordering. The generated [`glob` and `grep` schemas](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs-search) use `sampleOverCapGlobResults: true`; schemas are visible only after the load-time `rg` probe succeeds. +The glob description states the configured over-cap ordering. The generated [`glob` and `grep` schemas](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs-search) use `sampleOverCapGlobResults: true`; the tools are registered unconditionally. #### Token effect @@ -126,7 +126,7 @@ Append-only; newly visible content follows the reusable request prefix and does ## Known Limitations and Deferred Work -- **Search and file access have no shared-workspace proof** — returned paths are follow-up-readable only when the bash workdir and filesystem root denote the same workspace; the package performs no runtime cross-service validation. -- **Ripgrep is a deployment dependency** — a missing `rg` executable makes the package register no tools or guidance; an incompatible executable or one that disappears after registration fails calls with `SEARCH_FAILED`. Remote or virtual filesystems need a co-located executor or another search consumer. +- **Search and file access have no shared-workspace proof** — returned paths are follow-up-readable only when the workdir and filesystem root denote the same workspace; the package performs no runtime cross-service validation. +- **The packaged binary is fixed at dependency version** — `@vscode/ripgrep` covers the platforms it ships (macOS/Linux/Windows, x64/arm64); an unsupported platform or a corrupted install fails calls with `SEARCH_FAILED`. Remote or virtual filesystems need a co-located workspace or another search consumer. - **The schemas expose one bounded page** — offset pagination, case-mode switches, alternate output modes, and provider-backed discovery remain outside this package; capped complete output requires a spill backend. - **Sampling, when enabled, groups by first path segment beneath the search root only** — an over-cap `glob` page balances across those top-level entries, so a result concentrated deeper (one busy directory inside an otherwise even tree) is still shown unevenly below that level; recursive balancing is deferred. diff --git a/packages/fs/tool-fs-search/README.zh.md b/packages/fs/tool-fs-search/README.zh.md index 7dd6cdf9a2..69ce49f3ad 100644 --- a/packages/fs/tool-fs-search/README.zh.md +++ b/packages/fs/tool-fs-search/README.zh.md @@ -2,21 +2,21 @@ [English](README.md) | 中文 -**面向模型的文件系统发现工具**（`glob`、`grep`）由 **bash 执行器 seam** 支持，而不是由 `ctx.fs` 提供方方法支持。加载时，本包（package）探测 `command -v rg`，探测通过 `ctx.bash` 进行；如果执行器无法在其 `PATH` 上找到 ripgrep，就记录警告，并且不注册工具或提示词段。每次调用都会组装固定的 ripgrep 命令（所有模型控制的值都经过同一个包私有 shell 引用辅助函数），通过 `ctx.bash.resolve(request)` → `ctx.bash.run(spec)` 作为普通前台工具调用运行，解析原始 `rg` 输出，并返回相对于工作目录的规范值。本包注入 `tools`、`systemPrompt` 和 `bash`，有意**不**注入 `fs`；格式化结果 spill 为可选功能，因此机会性读取 `ctx.spillStore`，调用方式为 `ctx.get()`。 +**面向模型的文件系统发现工具**（`glob`、`grep`）由 **打包的 ripgrep 二进制**（`@vscode/ripgrep`）支持，而不是由 `ctx.fs` 提供方方法或系统 `rg` 安装支持。注册是无条件的：二进制随 npm 依赖一起交付，因此没有加载期可用性探针。每次调用都通过 `ctx.subprocess` seam 以固定 argv 向量 spawn 该二进制（模型控制的值是普通 argv 元素——不存在 shell 层，因此无需引号），解析原始 `rg` 输出，并返回相对于工作目录的规范值。本包注入 `tools`、`systemPrompt` 和 `subprocess`，有意**不**注入 `fs`；格式化结果 spill 为可选功能，因此机会性读取 `ctx.spillStore`，调用方式为 `ctx.get()`。 ```ts ignore-check // A deployment chooses how over-cap glob pages are selected. -await ctx.plugin(LocalBashExecutor, { cwd: process.cwd() }) // @deepseek-ai/dsh-bash-local +await ctx.plugin(LocalSubprocessService) // @deepseek-ai/dsh-subprocess-local await ctx.plugin(ToolFsSearch, { sampleOverCapGlobResults: false }) // Optional: a spill backend makes capped results fully recoverable. await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh-spill-local ``` -采用 bash 支持的原因：本地工作区发现天然是由进程支持的 `rg` 工作流；如果把搜索放到 `ctx.fs` 上，就会迫使每个文件系统后端扩展搜索 API。bash 执行器负责请求默认值/上限、子进程执行、进程组终止、环境清理、原始输出捕获和后端替换（本地、沙箱化、远程）；本包负责 schema、参数校验、shell 引用、解析、保留、格式化结果 spill 和超时声明。工具绝不调用 `ctx.bash.start()`，也不公开 bash task id；只有在 `rg` 退出、超时、中止或失败后，调用才会返回。 +采用 spawn 支持的原因：本地工作区发现天然是由进程支持的 `rg` 工作流；如果把搜索放到 `ctx.fs` 上，就会迫使每个文件系统后端扩展搜索 API。subprocess seam 负责 spawn 执行、进程树终止、环境清理和有界输出捕获；本包负责 schema、参数校验、argv 构造、解析、保留、格式化结果 spill 和超时声明。工具绝不暴露后台任务——只有在 `rg` 退出、被协作式超时终止、被中止或失败后，调用才会返回。 -## 部署要求：rg 与共置的 bash/文件系统 +## 部署要求：无需宿主 rg，但工作目录与文件系统需共置 -已挂载的 bash 执行器必须能在插件加载时解析 `rg`，其来源是执行器的 `PATH`；否则面向模型的工具 schema 中不会出现 `glob` 和 `grep`。返回路径会相对于解析后的 bash 工作目录显示（调用方 agent（智能体）有会话 cwd 时使用该 cwd，否则使用执行器配置的默认值）；只有 bash 工作目录与文件系统根目录是同一工作区时，才能用 `read` 继续读取。v1 只记录这项共置要求，不执行运行时跨服务校验；远程或虚拟文件系统搜索需等待共享工作区契约或特定提供方的搜索后端。 +二进制随包交付，覆盖所有受支持平台（macOS/Linux/Windows，x64/arm64），因此无需宿主 `rg` 安装，工具在每个部署上都注册。返回路径会相对于解析后的工作目录显示（调用方 agent（智能体）有会话 cwd 时使用该 cwd，否则使用 `process.cwd()`）；只有该工作目录与文件系统根目录是同一工作区时，才能用 `read` 继续读取。v1 只记录这项共置要求，不执行运行时跨服务校验；远程或虚拟文件系统搜索需等待共享工作区契约或特定提供方的搜索后端。 ## 配置 @@ -29,24 +29,24 @@ await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh- | `grepMaxMatches` | `250` | 一次 `grep` 调用内联保留的最大平铺匹配数（与 Claude Code 的 `GrepTool` `head_limit` 相同）；后续匹配写入格式化 spill 产物。 | | `grepMaxLineBytes` | `2000` | 每条匹配行预览的字节上限；截断会保留 UTF-8 边界，并标记为 `(line truncated)`。 | | `rawOutputMaxBytes` | `20000000` | 搜索将解析的完整原始 `rg` stdout 上限（与 Claude Code 的 ripgrep 原始 buffer 相同）；更大的原始输出以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败。 | -| `timeoutMs` | `30000` | 附加到两个工具定义上的协作式工具调用预算，由 `@deepseek-ai/dsh-timeout-policy` 通过 `exec.signal` 强制执行；bash 后端自身的超时仍作为第二道安全上限。 | +| `timeoutMs` | `30000` | 附加到两个工具定义上的协作式工具调用预算，由 `@deepseek-ai/dsh-timeout-policy` 通过 `exec.signal` 强制执行；subprocess seam 的终止升级提供硬终止。 | ## 工具 | 工具 | 参数 | 行为 | |---|---|---| -| `glob` | `pattern`、`path?` | 运行 `rg --files --glob --sort=modified --no-ignore --hidden`，并排除 VCS 元数据（`.git`、`.svn`、`.hg`、`.bzr`、`.jj`、`.sl`）。`path` 是可选的**目录**搜索根；省略时使用解析后的 bash 工作目录。每行返回一个**文件**路径；`rg --files` 从不输出目录条目。pattern 保留 ripgrep 语义：不含 `/` 时匹配任意深度的基名，因此 `*` 匹配整棵树。完整结果保持按修改时间排序；超过上限时的呈现方式遵循 `sampleOverCapGlobResults`。 | +| `glob` | `pattern`、`path?` | 运行 `rg --files --glob --sort=modified --no-ignore --hidden`，并排除 VCS 元数据（`.git`、`.svn`、`.hg`、`.bzr`、`.jj`、`.sl`）。`path` 是可选的**目录**搜索根；省略时使用解析后的工作目录。每行返回一个**文件**路径；`rg --files` 从不输出目录条目。pattern 保留 ripgrep 语义：不含 `/` 时匹配任意深度的基名，因此 `*` 匹配整棵树。完整结果保持按修改时间排序；超过上限时的呈现方式遵循 `sampleOverCapGlobResults`。 | | `grep` | `pattern`、`path?`、`include?` | 按行解析 `rg --json`，避免按冒号拆分的歧义。`pattern` 是 ripgrep 正则表达式；`path` 是可选的**文件或目录**目标；`include` 是一个正向 glob 过滤器，前置拒绝逗号分隔列表或否定值（`!…`），但允许 `*.{ts,tsx}` 等花括号交替。返回按文件分组、形如 `Line N: ` 的匹配。 | 常规预算不进入面向模型的 schema（没有 `head_limit`/`offset`/`case_insensitive`/输出模式）：模型需要周边上下文时，用 `read` 读取匹配文件；需要后续结果时，遵循返回的 spill locator 检索提示。 ## 两类预算、两类产物 -原始 `rg` stdout 是内部传输细节。每次搜索从 bash seam 请求 `stdoutMaxBytes: rawOutputMaxBytes`，且只解析完整保留的 stdout；如果执行器仍返回 `stdout.truncated`，搜索会以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败，并要求模型缩小查询。成功的 `glob` 在 `{ root, paths }` 中保留所显示的搜索根及所有已取得路径；启用采样时，借助 `root`，原生渲染器能以显式的相对或绝对搜索路径为根，按该根下的条目分组，而不是按其工作目录前缀分组。`grep` 保留所有已取得的 `{ path, lineNumber, line }`，并将其存入 `{ matches }`。内联条目和每行预览上限只应用于原生渲染器。直接接口调用的逻辑结果超过内联上限时，后置策略会尽力通过 `ctx.spillStore.saveText()` 保存完整格式化预览，并只把呈现替换为配置指定的页面与 locator。嵌套 Code 分派会跳过 spill，因为其完整规范值不会进入模型上下文。spill 缺失/失败时保留内联页面，并报告完整结果无法保存，绝不会成为 `isError`。 +原始 `rg` stdout 是内部传输细节。每次搜索从 subprocess seam 请求 `rawOutputMaxBytes` 的 collect 模式 stdout 预算，且只解析完整保留的 stdout；如果 seam 仍报告 lossy 读取，搜索会以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败，并要求模型缩小查询。成功的 `glob` 在 `{ root, paths }` 中保留所显示的搜索根及所有已取得路径；启用采样时，借助 `root`，原生渲染器能以显式的相对或绝对搜索路径为根，按该根下的条目分组，而不是按其工作目录前缀分组。`grep` 保留所有已取得的 `{ path, lineNumber, line }`，并将其存入 `{ matches }`。内联条目和每行预览上限只应用于原生渲染器。直接接口调用的逻辑结果超过内联上限时，后置策略会尽力通过 `ctx.spillStore.saveText()` 保存完整格式化预览，并只把呈现替换为配置指定的页面与 locator。嵌套 Code 分派会跳过 spill，因为其完整规范值不会进入模型上下文。spill 缺失/失败时保留内联页面，并报告完整结果无法保存，绝不会成为 `isError`。 ## 错误 -搜索失败携带本包拥有的 `SearchError`（`HarnessError` 子类），以 `{ name, code }` 公开在 `isError` 结果上：`SEARCH_INVALID_PATTERN`（ripgrep 拒绝正则/glob）、`SEARCH_FAILED`（注册后 `rg` 在运行时消失、目标不可访问、信号终止、`--json` 输出格式错误）、`SEARCH_RAW_OUTPUT_OVERFLOW`（原始输出超过 `rawOutputMaxBytes`，或在请求 stdout 捕获预算后仍被截断）和 `SEARCH_ABORTED`（工具超时、调用方取消或 bash 执行器自身超时）。ripgrep 退出语义由工具拥有：退出 0 表示成功且有结果，退出 1 表示成功的空搜索（`No files found` / `No matches found`），只有其他退出值表示失败。模型参数错误（空白 pattern、列表值 `include`）仍是普通工具参数错误。 +搜索失败携带本包拥有的 `SearchError`（`HarnessError` 子类），以 `{ name, code }` 公开在 `isError` 结果上：`SEARCH_INVALID_PATTERN`（ripgrep 拒绝正则/glob）、`SEARCH_FAILED`（`rg` 启动失败、目标不可访问、信号终止、`--json` 输出格式错误）、`SEARCH_RAW_OUTPUT_OVERFLOW`（原始输出超过 `rawOutputMaxBytes`，或在请求 stdout 捕获预算后仍 lossy）和 `SEARCH_ABORTED`（协作式工具超时或调用方取消）。ripgrep 退出语义由工具拥有：退出 0 表示成功且有结果，退出 1 表示成功的空搜索（`No files found` / `No matches found`），只有其他退出值表示失败。模型参数错误（空白 pattern、列表值 `include`）仍是普通工具参数错误。 ## 模型体验 @@ -54,7 +54,7 @@ await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh- #### 模型看到的内容 -加载时 `rg` 探测成功后，该插件注册作用域内的每个请求都包含下方独立注册的 glob 与 grep 指导。agent 作用域的工具限制可以隐藏任一 schema，而不移除其提示词段。 +该插件注册作用域内的每个请求都包含下方独立注册的 glob 与 grep 指导。agent 作用域的工具限制可以隐藏任一 schema，而不移除其提示词段。 ##### 启用 `sampleOverCapGlobResults: true` 时的 Glob 指导 @@ -76,57 +76,57 @@ Use the grep tool — not shell grep or rg — to search file contents. Use read #### Token 影响 -工具注册期间，每个请求支付固定指导成本；必填的采样选项决定采用哪个 glob 变体。 +工具注册期间每个请求有固定的指导成本；必填的采样选择决定采用哪一个 glob 变体。 #### KV Cache 影响 -只要插件作用域、采样选项和指导文本不变，前缀就保持稳定。启用、dispose（资源释放）或更改该选项，可能从该提示词段开始使复用失效。 +插件作用域、采样选择与指导文本不变时前缀稳定。激活、销毁或改变选择可能使该提示词段的复用失效。 ### 工具 schema #### 模型看到的内容 -glob 描述会说明配置所指定的超限结果排序方式。已生成的 [`glob` 和 `grep` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs-search) 使用 `sampleOverCapGlobResults: true`；只有加载时 `rg` 探测成功后，这些 schema 才可见。 +glob 描述声明了配置的超过上限排序方式。生成的 [`glob` 和 `grep` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs-search) 使用 `sampleOverCapGlobResults: true`；工具无条件注册。 #### Token 影响 -工具可见的每个请求都支付固定 schema 成本。 +工具可见时每个请求有固定的 schema 成本。 #### KV Cache 影响 -只要工具可见性和定义不变，前缀就保持稳定。注册生命周期或作用域限制可能从首个变化的 schema token 开始使复用失效。 +工具可见性与定义不变时前缀稳定。注册生命周期或作用域限制可能从第一个改变的 schema token 起使复用失效。 -### 结果与 spill 通知 +### 结果与 spill 提示 #### 模型看到的内容 -`glob` 每行返回一个路径；`grep` 在每个路径下对 `Line : ` 匹配分组。空搜索返回 `No files found` 或 `No matches found`。达到上限的结果末尾会附加省略数量、spill locator 和后端检索提示，或说明完整结果无法保存。`sampleOverCapGlobResults: true` 时，超过上限的 `glob` 页面会在实际搜索根正下方的条目之间按轮转方式取路径，footer 会说明采样依据和触达的顶层条目数；若无法触达全部条目，footer 会要求模型缩小 `path`。设为 `false` 时，页面保留按修改时间排序的前部，并沿用通常用于达到上限结果的 footer。未超过上限的结果原样不动；扁平的采样结果也沿用普通 footer，因为其样本等同于按修改时间排序的前部。spill 产物始终保存按修改时间排序的完整列表。 +`glob` 每行返回一个路径；`grep` 在每个路径下分组展示 `Line : ` 匹配。空搜索返回 `No files found` 或 `No matches found`。达到上限的结果以省略计数结尾，并附 spill locator 与后端检索提示；否则说明完整结果无法保存。启用 `sampleOverCapGlobResults: true` 时，超过上限的 `glob` 页面按实际搜索根正下方的条目轮转取路径，页脚说明采样依据及其覆盖的顶层条目数；无法覆盖全部条目时，页脚提示模型收窄 `path`。`false` 时页面是按修改时间排序的前部，并保留普通的上限结果页脚。未超过上限的结果原样呈现；扁平采样的结果也保留普通页脚，因为其采样等于按修改时间排序的前部。spill 产物始终持有按修改时间排序的完整列表。 #### Token 影响 -内联路径和匹配受 `globMaxResults`、`grepMaxMatches` 与 `grepMaxLineBytes` 限制；调用和保留结果会留在历史中，直到上下文压缩（compaction）。 +内联路径与匹配受 `globMaxResults`、`grepMaxMatches` 与 `grepMaxLineBytes` 约束；调用与保留结果在压缩前留在历史中。 #### KV Cache 影响 -仅追加；新增可见内容位于可复用请求前缀之后，不会使现有 KV-cache 条目失效。 +只追加；新可见内容跟在可复用请求前缀之后，不会使既有 KV-cache 条目失效。 ### 工具错误 #### 模型看到的内容 -失败会规范化为 `Error: `，并向调用方提供结构化的 `SEARCH_INVALID_PATTERN`、`SEARCH_FAILED`、`SEARCH_RAW_OUTPUT_OVERFLOW` 或 `SEARCH_ABORTED` 元数据。 +失败被规范化为 `Error: `，并携带结构化 `SEARCH_INVALID_PATTERN`、`SEARCH_FAILED`、`SEARCH_RAW_OUTPUT_OVERFLOW` 或 `SEARCH_ABORTED` 元数据供调用方使用。 #### Token 影响 -只有失败调用会添加这些保留 token。 +只有失败的调用会增加这些保留 token。 #### KV Cache 影响 -仅追加；新增可见内容位于可复用请求前缀之后，不会使现有 KV-cache 条目失效。 +只追加；新可见内容跟在可复用请求前缀之后，不会使既有 KV-cache 条目失效。 -## 已知限制与暂缓事项 +## 已知局限与延期工作 -- **搜索和文件访问没有共享工作区证明**：只有 bash 工作目录和文件系统根目录表示同一工作区时，返回路径才能继续读取；本包不执行运行时跨服务校验。 -- **Ripgrep 是部署依赖**：缺失 `rg` 可执行文件时，本包不注册工具或指导；可执行文件不兼容或注册后消失时，调用以 `SEARCH_FAILED` 失败。远程或虚拟文件系统需要共置执行器或其他搜索消费方。 -- **schema 只公开一个有界页面**：offset 分页、大小写模式开关、其他输出模式和提供方支持的发现均不在本包内；达到上限的完整输出需要 spill 后端。 -- **启用采样时，只按搜索根下的路径首段分组**：超过上限的 `glob` 页面在这些顶层条目之间做均衡，因此集中在更深层的结果（一棵总体均匀的树里某个特别庞大的子目录）在该层级以下仍然分布不均；递归均衡已延期。 +- **搜索与文件访问没有共享工作区证明**——只有当工作目录与文件系统根目录指向同一工作区时，返回路径才保证可继续读取；本包不执行运行时跨服务校验。 +- **打包二进制固定在依赖版本上**——`@vscode/ripgrep` 覆盖其随附的平台（macOS/Linux/Windows，x64/arm64）；不支持的平台或损坏的安装会以 `SEARCH_FAILED` 使调用失败。远程或虚拟文件系统需要共置的工作区或另一个搜索消费方。 +- **schema 只暴露一个有界页面**——偏移分页、大小写开关、替代输出模式与提供方支撑的发现仍不在本包范围内；达到上限的完整输出需要 spill 后端。 +- **启用采样时仅按搜索根正下方的第一段路径分组**——超过上限的 `glob` 页面在这些顶层条目之间平衡，因此集中在更深处的结果（一棵均匀树里某个繁忙目录）在该层级之下仍会呈现不均；递归平衡被延期。 diff --git a/packages/fs/tool-fs-search/package.json b/packages/fs/tool-fs-search/package.json index bf9cf15aa0..8953aea77a 100644 --- a/packages/fs/tool-fs-search/package.json +++ b/packages/fs/tool-fs-search/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-tool-fs-search", - "description": "Model-facing filesystem discovery tools (glob, grep) backed by the DeepSeek Harness bash seam (ctx.bash)", + "description": "Model-facing filesystem discovery tools (glob, grep) backed by the packaged ripgrep binary (@vscode/ripgrep)", "version": "0.0.1", "private": true, "type": "module", @@ -27,23 +27,23 @@ ], "license": "BSD-3-Clause", "dependencies": { + "@vscode/ripgrep": "^1.18.0", "schemastery": "^3.18.0" }, "peerDependencies": { - "@deepseek-ai/dsh-bash": "^0.0.1", "@deepseek-ai/dsh-invariants": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-retention": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-spill": "^0.0.1", + "@deepseek-ai/dsh-subprocess": "^0.0.1", "@deepseek-ai/dsh-system-prompt": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", - "@deepseek-ai/dsh-bash": "workspace:^", - "@deepseek-ai/dsh-bash-local": "workspace:^", + "@deepseek-ai/dsh-subprocess": "workspace:^", "@deepseek-ai/dsh-subprocess-local": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", diff --git a/packages/fs/tool-fs-search/src/glob.ts b/packages/fs/tool-fs-search/src/glob.ts index 2670ab57c4..6e7d411a01 100644 --- a/packages/fs/tool-fs-search/src/glob.ts +++ b/packages/fs/tool-fs-search/src/glob.ts @@ -1,10 +1,11 @@ /** * The model-facing `glob` tool: discover files whose paths match a glob - * pattern, sorted by modification time. Execution goes through the bash seam - * (`ctx.bash`) with a fixed `rg --files` command — this module owns the - * model-facing schema, argument validation, shell-safe command construction, - * result parsing, inline sampling, and formatting; process concerns (defaulting, - * scrubbing, kill, backend substitution) stay behind `ctx.bash`. + * pattern, sorted by modification time. Execution spawns the packaged + * ripgrep binary (`@vscode/ripgrep`) directly through the subprocess seam + * with a plain argv vector — this module owns the model-facing schema, + * argument validation, argv construction, result parsing, inline sampling, + * and formatting; process concerns (spawn execution, tree termination, + * environment scrubbing, output capture) stay behind `ctx.subprocess`. * @module @deepseek-ai/dsh-tool-fs-search/glob */ @@ -13,11 +14,9 @@ import { sep } from 'node:path' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView, SearchResultView, ToolResult } from '@deepseek-ai/dsh-tools' import type { SpillRef } from '@deepseek-ai/dsh-spill' -import type {} from '@deepseek-ai/dsh-bash' import type {} from '@deepseek-ai/dsh-system-prompt' import { runRipgrep, toWorkdirRelative, trySaveFormattedResult } from './search-core.ts' import { globSearchMeta, searchViewFromMeta } from './presentation.ts' -import { singleQuote } from './shell-quote.ts' import { acceptedSurfaceValue } from './surface.ts' /** @@ -73,32 +72,35 @@ export function parseGlobArgs(args: { pattern: string; path?: string }): GlobInp } /** - * Build the fixed `rg --files` command for one `glob` call. Every + * Build the fixed `rg --files` argv for one `glob` call. Every * model-controlled value ({@link GlobInput.pattern}, {@link GlobInput.path}) - * passes through {@link singleQuote}; the search root rides behind `--` so a - * leading-dash path can never be parsed as a flag. `--sort=modified` orders by - * modification time, `--no-ignore --hidden` searches ignored and hidden files, - * and {@link GLOB_VCS_EXCLUDES} keeps VCS metadata out. + * is a plain argv element — no shell layer exists, so no quoting applies; the + * search root rides behind `--` so a leading-dash path can never be parsed as + * a flag. `--sort=modified` orders by modification time, `--no-ignore + * --hidden` searches ignored and hidden files, and + * {@link GLOB_VCS_EXCLUDES} keeps VCS metadata out. * * @param input - the validated arguments. - * @returns the complete, shell-safe command string. + * @returns the complete ripgrep argument vector (excluding the binary itself). */ -export function buildGlobCommand(input: GlobInput): string { +export function buildGlobCommand(input: GlobInput): string[] { const parts = [ - 'rg --files', - `--glob=${singleQuote(input.pattern)}`, - '--sort=modified --no-ignore --hidden', + '--files', + `--glob=${input.pattern}`, + '--sort=modified', + '--no-ignore', + '--hidden', // Two negated globs per VCS name: the bare form prunes the directory // during traversal; the /** form still excludes the contents when the // search root is AT or INSIDE the directory (where the bare form, // matched against root-prefixed paths, never fires). ...GLOB_VCS_EXCLUDES.flatMap(name => [ - `--glob=${singleQuote(`!**/${name}`)}`, - `--glob=${singleQuote(`!**/${name}/**`)}`, + `--glob=!**/${name}`, + `--glob=!**/${name}/**`, ]), ] - if (input.path !== undefined) parts.push('--', singleQuote(input.path)) - return parts.join(' ') + if (input.path !== undefined) parts.push('--', input.path) + return parts } /** @@ -285,7 +287,7 @@ export function presentGlobResult(_args: { pattern: string; path?: string }, res * Register the `glob` tool and its system-prompt guidance. * * @param ctx - the plugin context; registrations are effects scoped to it, and - * execution uses its `bash` service. + * execution uses its `subprocess` service. * @param caps - the deployment's resolved glob caps (plugin config after defaulting). */ export function applyGlobTool(ctx: Context, caps: GlobToolCaps): void { diff --git a/packages/fs/tool-fs-search/src/grep.ts b/packages/fs/tool-fs-search/src/grep.ts index b7e67ea153..03b49f01e8 100644 --- a/packages/fs/tool-fs-search/src/grep.ts +++ b/packages/fs/tool-fs-search/src/grep.ts @@ -1,11 +1,12 @@ /** * The model-facing `grep` tool: search file contents with a ripgrep regular - * expression. Execution goes through the bash seam (`ctx.bash`) with a fixed - * line-oriented `rg --json` command so file path, line number, and line text - * parse without colon-splitting ambiguity — this module owns the model-facing - * schema, argument validation, shell-safe command construction, `--json` - * record parsing, per-line preview retention, match retention, grouping, and - * formatting; process concerns stay behind `ctx.bash`. + * expression. Execution spawns the packaged ripgrep binary + * (`@vscode/ripgrep`) directly through the subprocess seam with a plain argv + * vector using a fixed line-oriented `rg --json` command so file path, line + * number, and line text parse without colon-splitting ambiguity — this module + * owns the model-facing schema, argument validation, argv construction, + * `--json` record parsing, per-line preview retention, match retention, + * grouping, and formatting; process concerns stay behind `ctx.subprocess`. * * @module @deepseek-ai/dsh-tool-fs-search/grep */ @@ -15,12 +16,10 @@ import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView, SearchResultView, ToolResult } from '@deepseek-ai/dsh-tools' import type { RetainedItems } from '@deepseek-ai/dsh-retention' import type { SpillRef } from '@deepseek-ai/dsh-spill' -import type {} from '@deepseek-ai/dsh-bash' import type {} from '@deepseek-ai/dsh-system-prompt' import type { GrepMatch } from './search-core.ts' import { SearchError, previewLine, retainGrepMatches, runRipgrep, toWorkdirRelative, trySaveFormattedResult } from './search-core.ts' import { grepSearchMeta, searchViewFromMeta } from './presentation.ts' -import { singleQuote } from './shell-quote.ts' import { acceptedSurfaceValue } from './surface.ts' /** @@ -96,20 +95,21 @@ export function parseGrepArgs(args: { pattern: string; path?: string; include?: } /** - * Build the fixed line-oriented `rg --json` command for one `grep` call. Every + * Build the fixed line-oriented `rg --json` argv for one `grep` call. Every * model-controlled value ({@link GrepInput.pattern}, {@link GrepInput.path}, - * {@link GrepInput.include}) passes through {@link singleQuote}; the pattern - * and include ride in `--flag=value` form and the target behind `--`, so a - * leading-dash value can never be parsed as a flag. + * {@link GrepInput.include}) is a plain argv element — no shell layer exists, + * so no quoting applies; the pattern and include ride in `--flag=value` form + * and the target behind `--`, so a leading-dash value can never be parsed as + * a flag. * * @param input - the validated arguments. - * @returns the complete, shell-safe command string. + * @returns the complete ripgrep argument vector (excluding the binary itself). */ -export function buildGrepCommand(input: GrepInput): string { - const parts = ['rg --json', `--regexp=${singleQuote(input.pattern)}`] - if (input.include !== undefined) parts.push(`--glob=${singleQuote(input.include)}`) - if (input.path !== undefined) parts.push('--', singleQuote(input.path)) - return parts.join(' ') +export function buildGrepCommand(input: GrepInput): string[] { + const parts = ['--json', `--regexp=${input.pattern}`] + if (input.include !== undefined) parts.push(`--glob=${input.include}`) + if (input.path !== undefined) parts.push('--', input.path) + return parts } /** diff --git a/packages/fs/tool-fs-search/src/index.ts b/packages/fs/tool-fs-search/src/index.ts index 072865d568..e596ae3ca1 100644 --- a/packages/fs/tool-fs-search/src/index.ts +++ b/packages/fs/tool-fs-search/src/index.ts @@ -1,28 +1,27 @@ /** * The model-facing filesystem discovery tool suite (`glob`, `grep`) over the - * bash executor seam (`ctx.bash`). This single plugin registers both tools - * only when the mounted bash executor can find `rg` on its `PATH`. + * packaged ripgrep binary (`@vscode/ripgrep`). This single plugin registers + * both tools; the binary ships inside the npm dependency, so no system `rg` + * install and no shell layer is involved. * - * ## Bash-backed, not a `ctx.fs` provider method + * ## Spawn-backed, not a `ctx.fs` provider method * * Local workspace discovery is a process-backed `rg` workflow, so these tools - * execute through `ctx.bash.resolve(request)` → `ctx.bash.run(spec)` with fixed - * ripgrep command templates — never `ctx.bash.start()`, never a model-visible - * background task. The tool layer owns schemas, argument validation, shell - * quoting ({@link module:@deepseek-ai/dsh-tool-fs-search/shell-quote}), result - * parsing, retention, formatted-result spill, and timeout declaration; the - * bash executor owns request defaulting/capping, subprocess execution, - * process-group termination, environment scrubbing, raw output capture, and - * backend substitution. At load, the package probes `command -v rg` through the - * same bash seam; if ripgrep is absent, `glob` / `grep` and their prompt - * sections are not registered. The package injects `tools`, `systemPrompt`, - * and `bash` — deliberately NOT `fs`, and `ctx.spillStore` is read + * execute through `ctx.subprocess.spawn()` with fixed ripgrep argv templates — + * never `ctx.bash`, never `ctx.bash.start()`, never a model-visible background + * task. The tool layer owns schemas, argument validation, argv construction + * ({@link module:@deepseek-ai/dsh-tool-fs-search/glob} / + * {@link module:@deepseek-ai/dsh-tool-fs-search/grep}), result parsing, + * retention, formatted-result spill, and timeout declaration; the subprocess + * seam owns spawn execution, process-tree termination, environment scrubbing, + * and raw output capture. The package injects `tools`, `systemPrompt`, and + * `subprocess` — deliberately NOT `fs`, and `ctx.spillStore` is read * opportunistically with `ctx.get()` because formatted-result spill is optional. * - * Returned paths are displayed relative to the resolved bash workdir and are - * follow-up-readable only in co-located deployments where the bash workdir and - * the filesystem `read` root are the same workspace — a documented v1 - * deployment requirement, not runtime-validated. + * Returned paths are displayed relative to the resolved workdir and are + * follow-up-readable only in co-located deployments where the workdir and the + * filesystem `read` root are the same workspace — a documented v1 deployment + * requirement, not runtime-validated. * * @module @deepseek-ai/dsh-tool-fs-search */ @@ -65,7 +64,7 @@ export { singleQuote } from './shell-quote.ts' export const name = 'tool-fs-search' /** Services required by the search tool suite (`spillStore` is optional, read via `ctx.get()`). */ -export const inject = ['tools', 'systemPrompt', 'bash'] +export const inject = ['tools', 'systemPrompt', 'subprocess'] /** Plugin config; over-cap glob sampling is an explicit deployment choice and the remaining fields have defaults. */ export interface Config { @@ -98,9 +97,6 @@ export const Config: z = z.object({ /** The shape after schemastery applied the defaults. */ type ResolvedConfig = Required -/** POSIX-shell builtin probe for the ripgrep binary in the bash executor environment. */ -const RG_PROBE_COMMAND = 'command -v rg >/dev/null 2>&1' - /** Every search cap counts items/bytes/milliseconds — a positive integer, or retention and timeout arithmetic misbehaves silently. */ function assertPositiveInteger(name: string, value: number): void { if (!Number.isInteger(value) || value < 1) { @@ -109,36 +105,14 @@ function assertPositiveInteger(name: string, value: number): void { } /** - * Check whether the mounted bash executor can find `rg`. - * - * Nonzero exit means "not available" and disables this optional tool suite. - * Infrastructure failures stay loud: a deployment with a broken bash executor - * should not silently lose tools in a way that looks like a deliberate skip. - * - * @param ctx - plugin context whose `bash` service is the executor the tools will use. - * @returns true when `command -v rg` exits 0, false when it exits nonzero. - */ -async function ripgrepAvailable(ctx: Context): Promise { - const spec = ctx.bash.resolve({ command: RG_PROBE_COMMAND }) - let result - try { - result = await ctx.bash.run(spec) - } catch (error: unknown) { - throw new Error(`tool-fs-search: ripgrep availability probe could not start: ${String(error)}`, { cause: error }) - } - if (result.aborted || result.timedOut || result.signal !== null || result.exitCode === null) { - throw new Error('tool-fs-search: ripgrep availability probe did not complete') - } - return result.exitCode === 0 -} - -/** - * Register the `glob`/`grep` filesystem discovery tool suite when `rg` exists. + * Register the `glob`/`grep` filesystem discovery tool suite. The packaged + * ripgrep binary is always available (an npm dependency), so registration is + * unconditional. * * @param ctx - plugin context; registrations are effects scoped to this plugin. * @param config - resolved plugin configuration from schemastery. - * @returns when ripgrep is unavailable, resolves without registering any tools. */ +// oxlint-disable-next-line typescript/require-await -- async keeps a load-time config rejection a rejection, not a synchronous throw export async function apply(ctx: Context, config: Config): Promise { // schemastery (Config) has already filled every defaulted field. const resolved = config as ResolvedConfig @@ -148,10 +122,6 @@ export async function apply(ctx: Context, config: Config): Promise { assertPositiveInteger('searchMetaMaxBytes', resolved.searchMetaMaxBytes) assertPositiveInteger('rawOutputMaxBytes', resolved.rawOutputMaxBytes) assertPositiveInteger('timeoutMs', resolved.timeoutMs) - if (!await ripgrepAvailable(ctx)) { - ctx.logger.warn('tool-fs-search: ripgrep (rg) not found on the bash executor PATH; glob/grep tools not registered') - return - } applyGlobTool(ctx, { sampleOverCapGlobResults: resolved.sampleOverCapGlobResults, maxResults: resolved.globMaxResults, diff --git a/packages/fs/tool-fs-search/src/ripgrep.d.ts b/packages/fs/tool-fs-search/src/ripgrep.d.ts new file mode 100644 index 0000000000..25d268471e --- /dev/null +++ b/packages/fs/tool-fs-search/src/ripgrep.d.ts @@ -0,0 +1,12 @@ +/** + * Minimal type surface for the `@vscode/ripgrep` package: an ESM module that + * resolves the platform ripgrep binary (`@vscode/ripgrep--` + * optional dependency) and exports its absolute path as the named export + * `rgPath` (no bundled type declarations). + * @module @deepseek-ai/dsh-tool-fs-search/ripgrep-types + */ + +declare module '@vscode/ripgrep' { + /** Absolute path to the packaged ripgrep executable for the current platform. */ + export const rgPath: string +} diff --git a/packages/fs/tool-fs-search/src/search-core.ts b/packages/fs/tool-fs-search/src/search-core.ts index 402fc9d655..c9f5f80b5b 100644 --- a/packages/fs/tool-fs-search/src/search-core.ts +++ b/packages/fs/tool-fs-search/src/search-core.ts @@ -1,16 +1,19 @@ /** * Shared execution plumbing for the `glob` / `grep` search tools: the - * package-owned `SEARCH_*` error vocabulary, one bash-seam run helper that - * turns a fixed `rg` command into complete raw stdout, the best-effort - * formatted-result spill handoff, and workdir-relative path display. + * package-owned `SEARCH_*` error vocabulary, one spawn helper that runs the + * PACKAGED ripgrep binary (`@vscode/ripgrep`) with a plain argv vector and + * returns complete raw stdout, the best-effort formatted-result spill handoff, + * and workdir-relative path display. * - * Both tools execute through `ctx.bash.resolve(request)` → `ctx.bash.run(spec)` - * as ordinary foreground tool calls — never `ctx.bash.start()`, never a - * model-visible background task. Raw `rg` stdout is an internal transport - * detail: the tools request a per-run stdout capture budget from the bash seam, - * parse only complete in-memory stdout within `rawOutputMaxBytes`, and never - * read executor spill files. The model-facing recovery artifact is the - * formatted result saved through `ctx.spillStore.saveText()` + * Both tools execute as ordinary foreground spawns through `ctx.subprocess` — + * never `ctx.bash`, never `ctx.bash.start()`, never a model-visible background + * task. The ripgrep binary ships inside the npm package, so no system `rg` + * install is required, and no shell layer exists between the argv vector and + * ripgrep, so no shell quoting is involved. Raw `rg` stdout is an internal + * transport detail: the tools request a per-run stdout capture budget from the + * subprocess seam, parse only complete in-memory stdout within + * `rawOutputMaxBytes`, and never read spill files. The model-facing recovery + * artifact is the formatted result saved through `ctx.spillStore.saveText()` * ({@link trySaveFormattedResult}). * * @module @deepseek-ai/dsh-tool-fs-search/search-core @@ -18,10 +21,11 @@ import { isAbsolute, relative, sep } from 'node:path' import type { Context } from 'cordis' +import { rgPath } from '@vscode/ripgrep' import { HarnessError } from '@deepseek-ai/dsh-llm' import { ItemRetainer, TextRetainer } from '@deepseek-ai/dsh-retention' import type { RetainedItems } from '@deepseek-ai/dsh-retention' -import type { BashRunResult, CollectedOutput } from '@deepseek-ai/dsh-bash' +import type { SubprocessCollect, SubprocessOutcome, SubprocessOutputRead, SubprocessSpawnSpec } from '@deepseek-ai/dsh-subprocess' import type { SaveTextSpill, SpillRef } from '@deepseek-ai/dsh-spill' import type { ToolExecution } from '@deepseek-ai/dsh-tools' @@ -38,6 +42,18 @@ export const RAW_OUTPUT_MAX_BYTES = 20_000_000 */ export const SEARCH_TIMEOUT_MS = 30_000 +/** + * Default cap in bytes on the retained stderr tail of one search run — a + * diagnostic excerpt only (the tool never reads `stderr.spillPath`). + */ +const SEARCH_STDERR_MAX_BYTES = 64 * 1024 + +/** Default whole-stream spill cap for search output (the subprocess seam requires an explicit budget). */ +const SEARCH_SPILL_MAX_BYTES = 64 * 1024 * 1024 + +/** Default terminate grace period for a search process (ms). */ +const SEARCH_GRACE_MS = 3_000 + /** * Default cap in bytes on one search's serialized `presentationMeta` (the * `searchMetaMaxBytes` config). The inline match/path caps already bound the item @@ -52,14 +68,14 @@ export const SEARCH_META_MAX_BYTES = 65_536 /** * Stable, machine-routable codes for search failures. Package-owned (not - * `FsErrorCode`) because these tools are bash-backed discovery, not `ctx.fs` + * `FsErrorCode`) because these tools are spawn-backed discovery, not `ctx.fs` * provider operations: `SEARCH_INVALID_PATTERN` — ripgrep rejected the regex or * glob; `SEARCH_FAILED` — the search could not run or its output could not be - * parsed (missing `rg`, inaccessible target, signal kill, malformed `--json`); - * `SEARCH_RAW_OUTPUT_OVERFLOW` — raw `rg` output exceeded `rawOutputMaxBytes` - * or stayed truncated after that requested stdout budget; `SEARCH_ABORTED` — the tool - * timeout, caller cancellation, or the bash executor's own timeout cut the - * search short. + * parsed (a failed `rg` launch, inaccessible target, signal kill, malformed + * `--json`); `SEARCH_RAW_OUTPUT_OVERFLOW` — raw `rg` output exceeded + * `rawOutputMaxBytes` or stayed truncated after that requested stdout budget; + * `SEARCH_ABORTED` — the cooperative tool timeout or caller cancellation cut + * the search short. */ export type SearchErrorCode = | 'SEARCH_INVALID_PATTERN' @@ -84,7 +100,7 @@ export class SearchError extends HarnessError { /** The completed acquisition of one `rg` run: complete stdout plus the resolved workdir. */ export interface RipgrepRun { - /** Complete raw stdout retained by the bash executor within the requested cap. */ + /** Complete raw stdout retained by the subprocess seam within the requested cap. */ stdout: string /** True when ripgrep exited 1: a successful search with zero results. */ noMatches: boolean @@ -94,73 +110,71 @@ export interface RipgrepRun { /** * The retained stderr tail as a diagnostic excerpt, with a truncation note when - * the executor dropped bytes (the tool never reads `stderr.spillPath`). + * the subprocess seam dropped bytes (the tool never reads `stderr.spillPath`). */ -function stderrExcerpt(stderr: CollectedOutput): string { - const text = stderr.text.trim() +function stderrExcerpt(stderrText: string, truncated: boolean): string { + const text = stderrText.trim() if (text.length === 0) return '' - return stderr.truncated ? `${text} [stderr truncated]` : text + return truncated ? `${text} [stderr truncated]` : text } /** Classify a nonzero-exit `rg` run into the search error vocabulary (invalid pattern vs missing `rg` vs everything else). */ -function classifyRunFailure(toolName: string, result: BashRunResult): SearchError { - const stderr = stderrExcerpt(result.stderr) +function classifyRunFailure(toolName: string, exitCode: number, stderrText: string, stderrTruncated: boolean): SearchError { + const stderr = stderrExcerpt(stderrText, stderrTruncated) if (/regex parse error|error parsing glob/i.test(stderr)) { return new SearchError(`${toolName} pattern rejected by ripgrep: ${stderr}`, 'SEARCH_INVALID_PATTERN') } - if (result.exitCode === 127 || /command not found/i.test(stderr)) { - return new SearchError(`${toolName} requires ripgrep (rg) on the bash executor's PATH${stderr.length > 0 ? `: ${stderr}` : ''}`, 'SEARCH_FAILED') + if (exitCode === 127 || /command not found/i.test(stderr)) { + return new SearchError(`${toolName} requires ripgrep (rg) to launch${stderr.length > 0 ? `: ${stderr}` : ''}`, 'SEARCH_FAILED') } - return new SearchError(`${toolName} search failed (exit ${result.exitCode})${stderr.length > 0 ? `: ${stderr}` : ''}`, 'SEARCH_FAILED') + return new SearchError(`${toolName} search failed (exit ${exitCode})${stderr.length > 0 ? `: ${stderr}` : ''}`, 'SEARCH_FAILED') } /** * Acquire the COMPLETE raw stdout of a finished run, enforcing * `rawOutputMaxBytes` on the in-memory transport. A truncated result means the - * bash backend could not retain complete stdout within the requested budget, so - * the tool fails clearly instead of parsing a silently-partial stream. + * subprocess seam could not retain complete stdout within the requested + * budget, so the tool fails clearly instead of parsing a silently-partial + * stream. */ -function completeStdout(toolName: string, result: BashRunResult, rawOutputMaxBytes: number): string { +function completeStdout(toolName: string, stdout: SubprocessOutputRead, rawOutputMaxBytes: number): string { const narrow = 'narrow pattern, path, or include and retry' - if (!result.stdout.truncated) { - const inlineBytes = Buffer.byteLength(result.stdout.text, 'utf8') + if (!stdout.lossy) { + const inlineBytes = Buffer.byteLength(stdout.text, 'utf8') if (inlineBytes > rawOutputMaxBytes) { throw new SearchError( `${toolName} produced ${inlineBytes} bytes of raw output, over the ${rawOutputMaxBytes}-byte cap; ${narrow}`, 'SEARCH_RAW_OUTPUT_OVERFLOW', ) } - return result.stdout.text + return stdout.text } throw new SearchError( - `${toolName} produced more raw output than the bash executor retained within the ${rawOutputMaxBytes}-byte cap; ${narrow}`, + `${toolName} produced more raw output than the subprocess seam retained within the ${rawOutputMaxBytes}-byte cap; ${narrow}`, 'SEARCH_RAW_OUTPUT_OVERFLOW', ) } /** - * Run one fixed `rg` command through the bash seam and return its complete raw - * stdout. The bash request workdir is the calling agent's session cwd - * (`exec.agent.session.header.cwd`) when available — mirroring `dsh-tool-bash` / - * `dsh-tool-fs` — else omitted so the implementation's `resolve()` applies its - * configured default. `exec.signal` is forwarded so the cooperative tool - * timeout (`@deepseek-ai/dsh-timeout-policy`) and caller cancellation kill the - * command; the bash backend's own timeout stays a second safety cap. + * Run the packaged ripgrep binary with a plain argv vector and return its + * complete raw stdout. The working directory is the calling agent's session + * cwd (`exec.agent.session.header.cwd`) when available, else + * `process.cwd()`. `exec.signal` is forwarded so the cooperative tool timeout + * (`@deepseek-ai/dsh-timeout-policy`) and caller cancellation terminate the + * process tree. * * Exit semantics are tool-owned: exit 0 is success with results, exit 1 is * success with zero results (`noMatches`), anything else throws a * {@link SearchError} (abort/timeout → `SEARCH_ABORTED`, invalid pattern → * `SEARCH_INVALID_PATTERN`, the rest → `SEARCH_FAILED` / - * `SEARCH_RAW_OUTPUT_OVERFLOW`). A `run()` REJECTION — the seam's - * infrastructure failures (pre-aborted signal, unusable workdir, missing - * shell) — is translated into the same taxonomy: a pre-aborted signal becomes - * `SEARCH_ABORTED`, everything else `SEARCH_FAILED`, with the original as - * `cause`. + * `SEARCH_RAW_OUTPUT_OVERFLOW`). A spawn REJECTION — the seam's + * infrastructure failures — is translated into `SEARCH_FAILED` with the + * original as `cause`; a pre-aborted signal becomes `SEARCH_ABORTED`. * - * @param ctx - the plugin context; execution uses its `bash` service. + * @param ctx - the plugin context; execution uses its `subprocess` service. * @param exec - the tool-execution context; supplies the session cwd and the abort signal. * @param toolName - `glob` or `grep`, used in error messages. - * @param command - the fully-quoted `rg` command string (every model value already through `singleQuote`). + * @param argv - the ripgrep arguments (every model value an unquoted argv element; no shell layer exists). * @param rawOutputMaxBytes - cap on the complete raw stdout the tool will parse. * @returns the complete stdout, the zero-result flag, and the resolved workdir. */ @@ -168,54 +182,64 @@ export async function runRipgrep( ctx: Context, exec: ToolExecution, toolName: string, - command: string, + argv: readonly string[], rawOutputMaxBytes: number, ): Promise { - const cwd = exec.agent?.session.header.cwd - const spec = ctx.bash.resolve({ - command, - stdoutMaxBytes: rawOutputMaxBytes, - ...cwd !== undefined ? { workdir: cwd } : {}, - signal: exec.signal, - }) - let result: BashRunResult - try { - result = await ctx.bash.run(spec) - } catch (error: unknown) { - // The seam contract: run() REJECTS only for infrastructure failures — a - // pre-aborted signal, an unusable workdir, a missing shell. Translate them - // so these failures stay machine-routable under the SEARCH_* taxonomy. - if (spec.signal?.aborted === true) { - throw new SearchError(`${toolName} was aborted before completion (tool timeout or caller cancellation)`, 'SEARCH_ABORTED', { cause: error }) - } - throw new SearchError(`${toolName} could not start its search command (unusable working directory or missing shell)`, 'SEARCH_FAILED', { cause: error }) - } - if (result.aborted) { + if (exec.signal.aborted) { throw new SearchError(`${toolName} was aborted before completion (tool timeout or caller cancellation)`, 'SEARCH_ABORTED') } - if (result.timedOut) { - throw new SearchError(`${toolName} timed out after ${result.timeoutMs}ms in the bash executor; narrow pattern, path, or include and retry`, 'SEARCH_ABORTED') + const cwd = exec.agent?.session.header.cwd + const workdir = cwd ?? process.cwd() + const collect = (maxBytes: number): SubprocessCollect => + ({ maxBytes, spill: { maxBytes: SEARCH_SPILL_MAX_BYTES } }) + const handle = ctx.subprocess.spawn({ + argv: [rgPath, ...argv], + cwd: workdir, + stdio: { + stdin: 'ignore', + stdout: collect(rawOutputMaxBytes), + stderr: collect(SEARCH_STDERR_MAX_BYTES), + }, + graceMs: SEARCH_GRACE_MS, + signal: exec.signal, + } satisfies SubprocessSpawnSpec) + let outcome: SubprocessOutcome + try { + outcome = await handle.done + } catch (error: unknown) { + throw new SearchError(`${toolName} could not start its search command (ripgrep launch failed)`, 'SEARCH_FAILED', { cause: error }) } - if (result.signal !== null || result.exitCode === null) { - throw new SearchError(`${toolName} search command was killed by signal ${result.signal ?? '(unknown)'}`, 'SEARCH_FAILED') + const stdout = handle.collected.stdout?.readFrom(0) + const stderr = handle.collected.stderr?.readFrom(0) + if (stdout === undefined || stderr === undefined) { + throw new SearchError(`${toolName} search command produced no collected output streams`, 'SEARCH_FAILED') } - if (result.exitCode !== 0 && result.exitCode !== 1) { - throw classifyRunFailure(toolName, result) + // The signal can abort while the spawn is awaited; the static narrowing that + // proves this re-check "always false" cannot see AbortSignal state changes. + // oxlint-disable-next-line typescript/no-unnecessary-condition + if (exec.signal.aborted) { + throw new SearchError(`${toolName} was aborted before completion (tool timeout or caller cancellation)`, 'SEARCH_ABORTED') } - const stdout = completeStdout(toolName, result, rawOutputMaxBytes) - return { stdout, noMatches: result.exitCode === 1, workdir: spec.workdir } + if (outcome.signal !== null || outcome.exitCode === null) { + throw new SearchError(`${toolName} search command was killed by signal ${outcome.signal ?? '(unknown)'}`, 'SEARCH_FAILED') + } + if (outcome.exitCode !== 0 && outcome.exitCode !== 1) { + throw classifyRunFailure(toolName, outcome.exitCode, stderr.text, stderr.lossy) + } + const text = completeStdout(toolName, stdout, rawOutputMaxBytes) + return { stdout: text, noMatches: outcome.exitCode === 1, workdir } } /** * Map an `rg` output path to its display form: absolute paths inside the - * resolved bash workdir become workdir-relative; everything else (relative - * output, paths outside the workdir) passes through unchanged. Display-only — - * returned paths are follow-up-readable in co-located bash/filesystem + * resolved workdir become workdir-relative; everything else (relative output, + * paths outside the workdir) passes through unchanged. Display-only — + * returned paths are follow-up-readable in co-located workdir/filesystem * deployments where both resolve the same workspace (the documented v1 * deployment requirement). * * @param path - one path as ripgrep printed it. - * @param workdir - the resolved bash workdir the command ran in. + * @param workdir - the resolved workdir the command ran in. * @returns the workdir-relative display path when possible, else `path` unchanged. */ export function toWorkdirRelative(path: string, workdir: string): string { diff --git a/packages/fs/tool-fs-search/src/shell-quote.ts b/packages/fs/tool-fs-search/src/shell-quote.ts index 9453b8e255..ea67abf449 100644 --- a/packages/fs/tool-fs-search/src/shell-quote.ts +++ b/packages/fs/tool-fs-search/src/shell-quote.ts @@ -1,12 +1,9 @@ /** - * The one shell-quoting helper both search tools MUST route every - * model-controlled value through before it enters an `rg` command string. The - * bash seam (`ctx.bash`) accepts a command STRING, not an argv vector, so this - * is the safety boundary that stops a `pattern`, `path`, or `include` from - * breaking out of its argument and injecting shell syntax. - * - * Command builders in `glob.ts` / `grep.ts` must never hand-roll quoting or - * concatenate an unquoted model value — they call {@link singleQuote}. + * POSIX single-quoting helper retained for compatibility with older + * deployments and tests. The current `glob`/`grep` command builders spawn the + * packaged ripgrep binary with a plain argv vector — no shell layer exists — + * so no quoting is involved; this module is kept because its export is part + * of the package surface. * * @module @deepseek-ai/dsh-tool-fs-search/shell-quote */ diff --git a/packages/fs/tool-fs-search/tests/integration.spec.ts b/packages/fs/tool-fs-search/tests/integration.spec.ts index 8cb96e7e66..dc7a88b30f 100644 --- a/packages/fs/tool-fs-search/tests/integration.spec.ts +++ b/packages/fs/tool-fs-search/tests/integration.spec.ts @@ -1,15 +1,16 @@ /** - * Integration tests: the REAL local bash executor (`dsh-bash-local`) plus a - * REAL ripgrep binary, exercised through `ctx.tools.execute()`. These verify - * the WORLD — actual files on disk are discovered and grepped, hostile - * patterns stay inert in a real shell, and real `rg` stderr classifies into - * the `SEARCH_*` vocabulary. The whole suite self-skips when `rg` is not on - * PATH (a CI accommodation mirroring the keyless e2e skip); the fake-executor - * suite (tools.spec.ts) carries the coverage gate. + * Integration tests: the REAL local subprocess service plus the PACKAGED + * ripgrep binary (`@vscode/ripgrep`), exercised through `ctx.tools.execute()`. + * These verify the WORLD — actual files on disk are discovered and grepped, + * hostile patterns stay inert (they are plain argv elements; there is no + * shell layer to escape), and real `rg` stderr classifies into the + * `SEARCH_*` vocabulary. The binary ships inside the npm dependency, so the + * suite runs on every platform without a system `rg` install; the + * fake-service suite (tools.spec.ts) carries the coverage gate. */ import { afterEach, beforeEach, describe, expect, it } from 'vitest' -import { spawnSync } from 'node:child_process' +import { existsSync } from 'node:fs' import { mkdir, mkdtemp, rm, utimes, writeFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' @@ -17,14 +18,11 @@ import { Context } from 'cordis' import { CallId } from '@deepseek-ai/dsh-llm' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { TOOL_ABORTED_BEFORE_DISPATCH } from '@deepseek-ai/dsh-tools' -import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local' import * as ToolFsSearch from '@deepseek-ai/dsh-tool-fs-search' const testToolSignal = new AbortController().signal -const hasRg = spawnSync('rg', ['--version'], { encoding: 'utf8' }).status === 0 - let dir: string let ctx: Context @@ -43,7 +41,10 @@ function text(result: { content: { type: string; text?: string }[] }): string { return result.content.filter(b => b.type === 'text').map(b => b.text).join('') } -describe.skipIf(!hasRg)('search tools over the real bash executor + real rg', () => { +/** The fixture workspace as a session cwd, so relative paths resolve inside `dir`. */ +const agent = () => ({ session: { header: { id: 'session-int', cwd: dir } } }) + +describe('search tools over the real subprocess service + the packaged rg', () => { beforeEach(async () => { dir = await mkdtemp(join(tmpdir(), 'dsh-search-int-')) await mkdir(join(dir, 'src'), { recursive: true }) @@ -54,7 +55,7 @@ describe.skipIf(!hasRg)('search tools over the real bash executor + real rg', () await writeFile(join(dir, 'notes.md'), 'alpha appears here too\n') await writeFile(join(dir, '.hidden.ts'), 'export const hidden = 3\n') await writeFile(join(dir, '.git', 'config.ts'), 'never listed\n') - await writeFile(join(dir, 'spaced dir', "wei'rd \"name\".ts"), 'const inside = true\n') + await writeFile(join(dir, 'spaced dir', "wei'rd name.ts"), 'const inside = true\n') // Deterministic --sort=modified order: alpha oldest, beta newest. await utimes(join(dir, 'src', 'alpha.ts'), new Date(2000, 0, 1), new Date(2000, 0, 1)) await utimes(join(dir, 'src', 'beta.ts'), new Date(2020, 0, 1), new Date(2020, 0, 1)) @@ -63,7 +64,6 @@ describe.skipIf(!hasRg)('search tools over the real bash executor + real rg', () await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(LocalSubprocessService) - await ctx.plugin(LocalBashExecutor, { cwd: dir, timeoutMs: 20_000 }) await ctx.plugin(ToolFsSearch, { sampleOverCapGlobResults: true }) }) @@ -73,33 +73,33 @@ describe.skipIf(!hasRg)('search tools over the real bash executor + real rg', () describe('glob', () => { it('discovers files by pattern, sorted by modification time, hidden included, .git excluded', async () => { - const result = await call('glob', { pattern: '**/*.ts' }) + const result = await call('glob', { pattern: '**/*.ts' }, agent()) expect(result.isError).toBe(false) const paths = text(result).split('\n') - expect(paths.indexOf('src/alpha.ts')).toBeLessThan(paths.indexOf('src/beta.ts')) + expect(paths.indexOf(join('src', 'alpha.ts'))).toBeLessThan(paths.indexOf(join('src', 'beta.ts'))) expect(paths).toContain('.hidden.ts') - expect(paths).toContain("spaced dir/wei'rd \"name\".ts") - expect(paths).not.toContain('.git/config.ts') + expect(paths).toContain(join('spaced dir', "wei'rd name.ts")) + expect(paths).not.toContain(join('.git', 'config.ts')) expect(paths).not.toContain('notes.md') }) it('scopes to a directory search root (path arg)', async () => { - const result = await call('glob', { pattern: '*.ts', path: 'src' }) - expect(text(result).split('\n').sort()).toEqual(['src/alpha.ts', 'src/beta.ts']) + const result = await call('glob', { pattern: '*.ts', path: 'src' }, agent()) + expect(text(result).split('\n').sort()).toEqual([join('src', 'alpha.ts'), join('src', 'beta.ts')]) }) it('reports zero discoveries as No files found', async () => { - expect(text(await call('glob', { pattern: '*.nomatch' }))).toBe('No files found') + expect(text(await call('glob', { pattern: '*.nomatch' }, agent()))).toBe('No files found') }) it('excludes VCS internals even when the search root IS the VCS directory', async () => { // The prune glob alone never matches root-prefixed paths when rg is // rooted at .git; the paired contents glob keeps the exclusion airtight. - expect(text(await call('glob', { pattern: '*', path: '.git' }))).toBe('No files found') + expect(text(await call('glob', { pattern: '*', path: '.git' }, agent()))).toBe('No files found') }) it('classifies an invalid glob as SEARCH_INVALID_PATTERN', async () => { - const result = await call('glob', { pattern: '[' }) + const result = await call('glob', { pattern: '[' }, agent()) expect(result.isError).toBe(true) expect(result.error).toMatchObject({ info: { name: 'SearchError', code: 'SEARCH_INVALID_PATTERN' } }) }) @@ -107,37 +107,42 @@ describe.skipIf(!hasRg)('search tools over the real bash executor + real rg', () describe('grep', () => { it('greps a directory tree with grouped, line-numbered output', async () => { - const result = await call('grep', { pattern: 'alpha' }) + const result = await call('grep', { pattern: 'alpha' }, agent()) expect(result.isError).toBe(false) const output = text(result) expect(output).toContain('Found 3 matches') - expect(output).toContain('src/alpha.ts\nLine 1: export const alpha = 1\nLine 2: // TODO: refit alpha') + expect(output).toContain(`${join('src', 'alpha.ts')}\nLine 1: export const alpha = 1\nLine 2: // TODO: refit alpha`) expect(output).toContain('notes.md\nLine 1: alpha appears here too') }) it('greps a single FILE target', async () => { - const result = await call('grep', { pattern: 'alpha', path: 'notes.md' }) + const result = await call('grep', { pattern: 'alpha', path: 'notes.md' }, agent()) expect(text(result)).toBe('Found 1 match\n\nnotes.md\nLine 1: alpha appears here too') }) it('greps a directory target with an include filter', async () => { - const result = await call('grep', { pattern: 'alpha', path: '.', include: '*.ts' }) + const result = await call('grep', { pattern: 'alpha', path: '.', include: '*.ts' }, agent()) const output = text(result) expect(output).toContain('alpha.ts') expect(output).not.toContain('notes.md') }) - it('a hostile pattern stays inert (no command substitution, the world untouched)', async () => { + it('a hostile pattern stays inert (a plain argv element, the world untouched)', async () => { + // There is no shell layer between the argv vector and rg, so the pattern + // is a literal regex — but the world-untouched guarantee is the shipped + // contract, and a future shell-wrapping change must not reintroduce it. + // The canary name carries no path so the regex stays valid on every + // platform (a Windows path's backslashes would be regex escapes). const canary = join(dir, 'pwned') - const result = await call('grep', { pattern: `$(touch ${canary})` }) + const result = await call('grep', { pattern: '$(touch pwned)' }, agent()) expect(result.isError).toBe(false) // exit 1: found nothing, executed nothing expect(text(result)).toBe('No matches found') - expect(spawnSync('test', ['-e', canary]).status).not.toBe(0) + expect(existsSync(canary)).toBe(false) }) it('a leading-dash pattern is a pattern, not a flag', async () => { await writeFile(join(dir, 'dashes.txt'), 'value --flag value\n') - const result = await call('grep', { pattern: '--flag', path: 'dashes.txt' }) + const result = await call('grep', { pattern: '--flag', path: 'dashes.txt' }, agent()) expect(text(result)).toBe('Found 1 match\n\ndashes.txt\nLine 1: value --flag value') }) @@ -155,7 +160,7 @@ describe.skipIf(!hasRg)('search tools over the real bash executor + real rg', () }) describe('per-session cwd', () => { - it('resolves the search in the SESSION workspace, not the executor config cwd', async () => { + it('resolves the search in the SESSION workspace, not the process cwd', async () => { const sessionDir = await mkdtemp(join(tmpdir(), 'dsh-search-session-')) try { await writeFile(join(sessionDir, 'only-here.ts'), 'const sessionFile = true\n') @@ -170,7 +175,7 @@ describe.skipIf(!hasRg)('search tools over the real bash executor + real rg', () }) }) - describe('pre-dispatch cancellation and bash-start failures', () => { + describe('pre-dispatch cancellation and spawn failures', () => { it('a pre-aborted registry call is ABORTED_BEFORE_DISPATCH', async () => { const controller = new AbortController() controller.abort() diff --git a/packages/fs/tool-fs-search/tests/load-path.spec.ts b/packages/fs/tool-fs-search/tests/load-path.spec.ts index 71022720fc..1d1e348c09 100644 --- a/packages/fs/tool-fs-search/tests/load-path.spec.ts +++ b/packages/fs/tool-fs-search/tests/load-path.spec.ts @@ -3,14 +3,15 @@ * a NAMESPACE plugin with `inject` — so a stray `export default apply` would * make the cordis Loader's `unwrapExports` (`exports.default ?? exports`) * collapse the module to the bare `apply` function, DROPPING `inject`. The - * plugin would then read `ctx.bash` without having injected it and throw + * plugin would then read `ctx.subprocess` without having injected it and throw * `cannot get property … without inject` the moment it loads (postmortem 0001). * * A hand-built `ctx.plugin({ apply, inject })` mount CANNOT catch that — it * bypasses `unwrapExports`. So this test unwraps the module through the REAL - * `Loader.prototype.unwrapExports` and mounts the result over a bash executor, - * exercising the exact path the Loader uses. Prove the guard bites: add - * `export default apply` to `src/index.ts`, watch this go red, revert. + * `Loader.prototype.unwrapExports` and mounts the result over the real local + * subprocess service, exercising the exact path the Loader uses. Prove the + * guard bites: add `export default apply` to `src/index.ts`, watch this go + * red, revert. */ import { describe, expect, it } from 'vitest' @@ -18,48 +19,9 @@ import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import { BashExecutor } from '@deepseek-ai/dsh-bash' -import type { BashExecRequest, BashExecSpec, BashProcess, BashRunResult } from '@deepseek-ai/dsh-bash' +import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local' import * as toolFsSearch from '@deepseek-ai/dsh-tool-fs-search' -const RG_PROBE_COMMAND = 'command -v rg >/dev/null 2>&1' - -/** - * Deterministic bash service for this Loader guard: the test wants to exercise - * the real unwrap/inject path, not depend on whether the host image has rg. - */ -class ProbeSuccessBashExecutor extends BashExecutor { - override resolve(request: BashExecRequest): BashExecSpec { - return { - command: request.command, - workdir: request.workdir ?? '/work', - timeoutMs: request.timeoutMs ?? 60_000, - stdoutMaxBytes: request.stdoutMaxBytes ?? 64_000, - signal: request.signal, - sandboxPolicy: request.sandboxPolicy, - } - } - - override run(spec: BashExecSpec): Promise { - if (spec.command !== RG_PROBE_COMMAND) { - throw new Error(`unexpected command in load-path guard: ${spec.command}`) - } - return Promise.resolve({ - exitCode: 0, - signal: null, - timedOut: false, - aborted: false, - timeoutMs: spec.timeoutMs, - stdout: { text: '', truncated: false }, - stderr: { text: '', truncated: false }, - }) - } - - override start(): BashProcess { - throw new Error('load-path guard must not start background processes') - } -} - describe('dsh-tool-fs-search real-load-path guard', () => { it('has no default export and keeps name/inject/Config through unwrapExports', () => { expect('default' in toolFsSearch).toBe(false) @@ -68,16 +30,16 @@ describe('dsh-tool-fs-search real-load-path guard', () => { const unwrapped = loader.unwrapExports(toolFsSearch) as Record expect(unwrapped).toBe(toolFsSearch) expect(unwrapped.name).toBe('tool-fs-search') - expect(unwrapped.inject).toEqual(['tools', 'systemPrompt', 'bash']) + expect(unwrapped.inject).toEqual(['tools', 'systemPrompt', 'subprocess']) expect(typeof unwrapped.Config).toBe('function') expect(typeof unwrapped.apply).toBe('function') }) - it('boots over ctx.bash through the unwrapped module without an inject error', async () => { + it('boots over ctx.subprocess through the unwrapped module without an inject error', async () => { const ctx = new Context() await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) - await ctx.plugin(ProbeSuccessBashExecutor) + await ctx.plugin(LocalSubprocessService) const loader = Object.create(Loader.prototype) as Loader const unwrapped = loader.unwrapExports(toolFsSearch) as Parameters[0] diff --git a/packages/fs/tool-fs-search/tests/tools.spec.ts b/packages/fs/tool-fs-search/tests/tools.spec.ts index 389d8dbe05..d786fa3181 100644 --- a/packages/fs/tool-fs-search/tests/tools.spec.ts +++ b/packages/fs/tool-fs-search/tests/tools.spec.ts @@ -1,23 +1,24 @@ /** - * Consumer-surface tests for the search tools over a FAKE bash executor and a - * FAKE spill backend, exercised through `ctx.tools.execute()` so nothing - * bypasses the tool registry. The fake executor makes every seam outcome - * scriptable — registration-time `rg` probing, truncated stdout with/without a - * raw spill path, abort/timeout, signal kills, ripgrep exit codes — so these - * tests verify schemas, argument validation, shell-safe command construction, - * workdir derivation, signal forwarding, `SEARCH_*` error classification, - * retention, formatted-result spill handoff, and the no-background-task - * invariant. Real-`rg` behavior is pinned separately in integration.spec.ts. + * Consumer-surface tests for the search tools over a FAKE subprocess service + * and a FAKE spill backend, exercised through `ctx.tools.execute()` so nothing + * bypasses the tool registry. The fake service makes every seam outcome + * scriptable — spawn failure, truncated stdout with/without a raw spill path, + * abort/timeout kills, signal kills, ripgrep exit codes — so these tests + * verify schemas, argument validation, argv construction, workdir derivation, + * signal forwarding, `SEARCH_*` error classification, retention, + * formatted-result spill handoff, and the no-background-task invariant. + * Real-`rg` behavior is pinned separately in integration.spec.ts. */ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import { join, sep } from 'node:path' -import { createUserMessage, CallId } from '@deepseek-ai/dsh-llm' +import { createUserMessage, CallId } from '@deepseek-ai/dsh-llm' import SystemPrompt, { renderPrompt } from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry, { TOOL_ABORTED_BEFORE_DISPATCH, type ToolExecutionToken } from '@deepseek-ai/dsh-tools' -import { BashExecutor } from '@deepseek-ai/dsh-bash' -import type { BashExecRequest, BashExecSpec, BashProcess, BashRunResult } from '@deepseek-ai/dsh-bash' +import ToolRegistry, { TOOL_ABORTED_BEFORE_DISPATCH, type ToolExecution, type ToolExecutionToken } from '@deepseek-ai/dsh-tools' +import { SubprocessService } from '@deepseek-ai/dsh-subprocess' +import type { SubprocessCollectedOutputs, SubprocessHandle, SubprocessOutcome, SubprocessOutputRead, SubprocessOutputReader, SubprocessSpawnSpec } from '@deepseek-ai/dsh-subprocess' +import { rgPath } from '@vscode/ripgrep' import { SpillLocator, SpillStore } from '@deepseek-ai/dsh-spill' import type { SaveTextSpill, SpillRef } from '@deepseek-ai/dsh-spill' import * as ToolFsSearch from '@deepseek-ai/dsh-tool-fs-search' @@ -31,68 +32,124 @@ import { presentGrepCall, presentGrepResult, previewLine, + runRipgrep, sampleAcrossTopLevel, toWorkdirRelative, } from '@deepseek-ai/dsh-tool-fs-search' const testToolSignal = new AbortController().signal -const RG_PROBE_COMMAND = 'command -v rg >/dev/null 2>&1' -/** A successful run result over the given stdout; overrides script the failure shapes. */ -function runResult(stdout: string, overrides?: Partial): BashRunResult { +/** One scripted collect-mode stream, returned by `readFrom(0)` after settlement. */ +interface ScriptedStream { + text: string + lossy?: boolean + spillPath?: string +} + +/** One scripted spawn: exit facts plus the collected streams the tool reads. */ +interface ScriptedRun { + outcome: SubprocessOutcome + stdout: ScriptedStream + stderr: ScriptedStream +} + +/** A successful run over the given stdout; overrides script the failure shapes. */ +function runResult( + stdout: string, + overrides?: Partial & { stdout?: Partial; stderr?: ScriptedStream }, +): ScriptedRun { + const { stdout: stdoutOverrides, stderr: stderrOverrides, ...outcome } = overrides ?? {} return { - exitCode: 0, - signal: null, - timedOut: false, - aborted: false, - timeoutMs: 60_000, - stdout: { text: stdout, truncated: false }, - stderr: { text: '', truncated: false }, - ...overrides, + outcome: { exitCode: 0, signal: null, ...outcome }, + stdout: { text: stdout, ...stdoutOverrides }, + stderr: { text: '', ...stderrOverrides }, + } +} + +/** A fixed-response collect-mode reader: the tools read each stream once, from 0, after settlement. */ +class FakeReader implements SubprocessOutputReader { + constructor(private readonly read: ScriptedStream) {} + + readFrom(_fromByte: number): SubprocessOutputRead { + return { + text: this.read.text, + nextOffset: 0, + lossy: this.read.lossy ?? false, + ...this.read.spillPath !== undefined ? { spillPath: this.read.spillPath } : {}, + } } } /** - * A scriptable fake executor: `resolve()` mirrors the real request→spec - * defaulting (workdir falls back to `/work`), `run()` returns whatever the - * test armed via `handler`, and `start()` throws — the search tools must NEVER - * create a background task. + * A scriptable subprocess handle: `done` resolves with the scripted outcome + * (or rejects with the scripted error), `terminate()` records the call, and + * the spec's abort signal marks the handle terminated — mirroring the seam's + * abort→terminate escalation. */ -class FakeBash extends BashExecutor { - probeRequests: BashExecRequest[] = [] - probeSpecs: BashExecSpec[] = [] - requests: BashExecRequest[] = [] - specs: BashExecSpec[] = [] - startCalls = 0 - forwardSignal = true - probeResult: BashRunResult = runResult('') - probeError?: Error - handler: (spec: BashExecSpec) => BashRunResult = () => runResult('') +class FakeHandle implements SubprocessHandle { + readonly pid = 4242 + readonly stdin = undefined + readonly stdout = undefined + readonly stderr = undefined + readonly collected: SubprocessCollectedOutputs + readonly done: Promise + /** True once `done` settled — the search tools must never leave a spawn running. */ + settled = false + /** True when the handle's termination path ran (abort signal or explicit terminate). */ + terminated = false + /** Scripted handle that drops one requested collect reader (the defensive branch). */ + readonly dropReaders: boolean - override resolve(request: BashExecRequest): BashExecSpec { - if (request.command === RG_PROBE_COMMAND) this.probeRequests.push(request) - else this.requests.push(request) - return { - command: request.command, - workdir: request.workdir ?? '/work', - timeoutMs: request.timeoutMs ?? 60_000, - stdoutMaxBytes: request.stdoutMaxBytes ?? 64_000, - ...this.forwardSignal ? { signal: request.signal } : {}, - sandboxPolicy: request.sandboxPolicy, + constructor(spec: SubprocessSpawnSpec, script: () => ScriptedRun | { reject: Error }, dropReaders = false) { + this.dropReaders = dropReaders + // The abort listener attaches BEFORE the scripted run resolves, mirroring + // a real spawn: the escalation is armed when the process starts. + spec.signal?.addEventListener('abort', () => { this.terminated = true }, { once: true }) + const scripted = script() + if ('reject' in scripted) { + // A spawn failure produces no process output, so no readers exist. + this.collected = {} + this.done = Promise.reject(scripted.reject) + } else { + this.collected = { + ...dropReaders ? {} : { stdout: new FakeReader(scripted.stdout), stderr: new FakeReader(scripted.stderr) }, + } + this.done = Promise.resolve(scripted.outcome) } + this.done.then( + () => { this.settled = true }, + () => { this.settled = true }, + ) } - override async run(spec: BashExecSpec): Promise { - if (spec.command === RG_PROBE_COMMAND) { - this.probeSpecs.push(spec) - if (this.probeError) throw this.probeError - return this.probeResult - } - this.specs.push(spec) - return this.handler(spec) + + terminate(): void { + this.terminated = true } - override start(): BashProcess { - this.startCalls++ - throw new Error('search tools must never start a background task') + + waitForExit(_signal?: AbortSignal): Promise { + return Promise.resolve(true) + } +} + +/** + * A scriptable fake subprocess service: `spawn()` records every spec and + * returns a handle scripted by the armed `handler`. The search tools must + * never spawn outside a single awaited foreground call, so every test can + * assert on the exact spawn specs and settled handles. + */ +class FakeSubprocess extends SubprocessService { + spawns: SubprocessSpawnSpec[] = [] + handles: FakeHandle[] = [] + /** Arms the per-spawn script; a `{ reject }` return scripts a spawn-level failure. */ + handler: (spec: SubprocessSpawnSpec) => ScriptedRun | { reject: Error } = () => runResult('') + /** When true, spawned handles drop their collect readers (the defensive branch). */ + dropReaders = false + + override spawn(spec: SubprocessSpawnSpec): SubprocessHandle { + this.spawns.push(spec) + const handle = new FakeHandle(spec, () => this.handler(spec), this.dropReaders) + this.handles.push(handle) + return handle } } @@ -115,8 +172,6 @@ class FakeSpill extends SpillStore { interface SetupOptions { config?: Partial spill?: boolean - probeError?: Error - probeResult?: BashRunResult } const DEFAULT_CONFIG = { sampleOverCapGlobResults: true } satisfies ToolFsSearch.Config @@ -127,26 +182,12 @@ async function setup(options: SetupOptions = {}) { ctx.logger.warn = ((message: unknown) => { warnings.push(String(message)) }) as typeof ctx.logger.warn await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) - await ctx.plugin(FakeBash) - const bash = ctx.bash as FakeBash - if (options.probeResult) bash.probeResult = options.probeResult - if (options.probeError) bash.probeError = options.probeError + await ctx.plugin(FakeSubprocess) + const subprocess = ctx.subprocess as FakeSubprocess if (options.spill === true) await ctx.plugin(FakeSpill) const fiber = await ctx.plugin(ToolFsSearch, { ...DEFAULT_CONFIG, ...options.config }) const spill = options.spill === true ? ctx.get('spillStore') as FakeSpill : undefined - return { ctx, bash, spill, fiber, warnings } -} - -/** Assert plugin setup rejects without letting Vitest pretty-print a live Context on failure. */ -async function expectSetupRejects(options: SetupOptions, message: RegExp): Promise { - let thrown: string | undefined - try { - const loaded = await setup(options) - await loaded.fiber.dispose() - } catch (error: unknown) { - thrown = error instanceof Error ? error.message : String(error) - } - expect(thrown).toMatch(message) + return { ctx, subprocess, spill, fiber, warnings } } /** A stand-in agent whose session header carries the given cwd (and a stable id). */ @@ -180,11 +221,11 @@ function matchLine(path: string, lineNumber: number, lineText: string): string { } describe('registration', () => { - it('registers glob and grep with their prompt sections', async () => { - const { ctx, bash } = await setup() - expect(bash.probeRequests).toHaveLength(1) - expect(bash.probeRequests[0]?.command).toBe(RG_PROBE_COMMAND) - expect(bash.probeRequests[0]).not.toHaveProperty('workdir') + it('registers glob and grep unconditionally with their prompt sections', async () => { + const { ctx, subprocess } = await setup() + // Registration performs NO load-time probe: the packaged binary is always + // available, so nothing spawns until a tool call. + expect(subprocess.spawns).toHaveLength(0) expect(ctx.tools.schemas().map(s => s.name).sort()).toEqual(['glob', 'grep']) const prompt = renderPrompt(await ctx.systemPrompt.assemble()) expect(prompt).toContain('Use the glob tool') @@ -195,32 +236,11 @@ describe('registration', () => { expect(glob?.description).toContain('sampled across top-level entries') }) - it('does not register glob or grep when the bash executor cannot find rg', async () => { - const { ctx, warnings } = await setup({ probeResult: runResult('', { exitCode: 1 }) }) - expect(ctx.tools.schemas()).toHaveLength(0) - const sections = (await ctx.systemPrompt.assemble()).sections.map(s => s.name) - expect(sections).not.toContain('tool:glob') - expect(sections).not.toContain('tool:grep') - expect(warnings).toEqual([ - 'tool-fs-search: ripgrep (rg) not found on the bash executor PATH; glob/grep tools not registered', - ]) - }) - - it('rejects plugin load when the rg availability probe cannot run', async () => { - await expectSetupRejects({ probeError: new Error('spawn bash ENOENT') }, /spawn bash ENOENT/) - }) - - it('rejects plugin load when the rg availability probe is aborted or killed', async () => { - await expectSetupRejects({ - probeResult: runResult('', { aborted: true, exitCode: null, signal: 'SIGTERM' }), - }, /tool-fs-search: ripgrep availability probe did not complete/) - }) - - it('stays pending until ctx.bash exists (inject)', async () => { + it('stays pending until ctx.subprocess exists (inject)', async () => { const ctx = new Context() await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) - await ctx.plugin(ToolFsSearch, DEFAULT_CONFIG) // no bash executor + await ctx.plugin(ToolFsSearch, DEFAULT_CONFIG) // no subprocess service expect(ctx.tools.schemas()).toHaveLength(0) }) @@ -276,139 +296,176 @@ describe('config validation', () => { const ctx = new Context() await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) - await ctx.plugin(FakeBash) + await ctx.plugin(FakeSubprocess) await expect(ctx.plugin(ToolFsSearch, { ...DEFAULT_CONFIG, ...config })).rejects.toThrow(new RegExp(`tool-fs-search: ${name} must be a positive integer`)) }) }) -describe('command construction (shell-safe)', () => { - it('glob: fixed rg --files template with quoted pattern and paired VCS excludes', () => { - const command = buildGlobCommand({ pattern: '**/*.ts' }) - expect(command).toBe( - "rg --files --glob='**/*.ts' --sort=modified --no-ignore --hidden " - + "--glob='!**/.git' --glob='!**/.git/**' --glob='!**/.svn' --glob='!**/.svn/**' " - + "--glob='!**/.hg' --glob='!**/.hg/**' --glob='!**/.bzr' --glob='!**/.bzr/**' " - + "--glob='!**/.jj' --glob='!**/.jj/**' --glob='!**/.sl' --glob='!**/.sl/**'", - ) +describe('command construction (plain argv)', () => { + it('glob: fixed rg --files argv with the pattern and paired VCS excludes', () => { + expect(buildGlobCommand({ pattern: '**/*.ts' })).toEqual([ + '--files', + '--glob=**/*.ts', + '--sort=modified', + '--no-ignore', + '--hidden', + '--glob=!**/.git', '--glob=!**/.git/**', + '--glob=!**/.svn', '--glob=!**/.svn/**', + '--glob=!**/.hg', '--glob=!**/.hg/**', + '--glob=!**/.bzr', '--glob=!**/.bzr/**', + '--glob=!**/.jj', '--glob=!**/.jj/**', + '--glob=!**/.sl', '--glob=!**/.sl/**', + ]) }) - it('glob: the search root rides behind -- and is quoted', () => { - const command = buildGlobCommand({ pattern: '*.md', path: 'docs dir' }) - expect(command).toContain("-- 'docs dir'") + it('glob: the search root rides behind -- as a plain element', () => { + expect(buildGlobCommand({ pattern: '*.md', path: 'docs dir' })).toEqual(['--files', '--glob=*.md', '--sort=modified', '--no-ignore', '--hidden', + '--glob=!**/.git', '--glob=!**/.git/**', + '--glob=!**/.svn', '--glob=!**/.svn/**', + '--glob=!**/.hg', '--glob=!**/.hg/**', + '--glob=!**/.bzr', '--glob=!**/.bzr/**', + '--glob=!**/.jj', '--glob=!**/.jj/**', + '--glob=!**/.sl', '--glob=!**/.sl/**', + '--', 'docs dir']) }) - it('grep: fixed rg --json template with the pattern in --regexp= form', () => { - expect(buildGrepCommand({ pattern: 'foo.*bar' })).toBe("rg --json --regexp='foo.*bar'") + it('grep: fixed rg --json argv with the pattern in --regexp= form', () => { + expect(buildGrepCommand({ pattern: 'foo.*bar' })).toEqual(['--json', '--regexp=foo.*bar']) }) - it('grep: include and path are quoted, include in --glob= form, path behind --', () => { - const command = buildGrepCommand({ pattern: 'x', path: '-leading-dash', include: '*.{ts,tsx}' }) - expect(command).toBe("rg --json --regexp='x' --glob='*.{ts,tsx}' -- '-leading-dash'") + it('grep: include in --glob= form, path behind --, both plain elements', () => { + expect(buildGrepCommand({ pattern: 'x', path: '-leading-dash', include: '*.{ts,tsx}' })) + .toEqual(['--json', '--regexp=x', '--glob=*.{ts,tsx}', '--', '-leading-dash']) }) it.each([ - ['a command-substitution pattern', '$(rm -rf /)', "'$(rm -rf /)'"], - ['a backtick pattern', '`touch pwned`', "'`touch pwned`'"], - ['a pattern with double quotes and spaces', 'say "hi there"', '\'say "hi there"\''], - ['a pattern with single quotes', "it's", '\'it\'\\\'\'s\''], - ['a pattern with newlines', 'a\nb', "'a\nb'"], - ['a leading-dash pattern', '--flag', "'--flag'"], - ['glob metacharacters', '*?[a-z]{x,y}', "'*?[a-z]{x,y}'"], - ])('quotes %s into one inert shell word', (_label, raw, quoted) => { - expect(buildGrepCommand({ pattern: raw })).toBe(`rg --json --regexp=${quoted}`) + ['a command-substitution pattern', '$(rm -rf /)'], + ['a backtick pattern', '`touch pwned`'], + ['a pattern with double quotes and spaces', 'say "hi there"'], + ['a pattern with single quotes', "it's"], + ['a pattern with newlines', 'a\nb'], + ['a leading-dash pattern', '--flag'], + ['glob metacharacters', '*?[a-z]{x,y}'], + ])('keeps %s as ONE inert argv element (no shell layer to escape)', (_label, raw) => { + // The argv vector is handed to rg verbatim: hostile text cannot break out + // of its argument because there is no shell between the vector and rg. + expect(buildGrepCommand({ pattern: raw })).toEqual(['--json', `--regexp=${raw}`]) + expect(buildGlobCommand({ pattern: raw })[1]).toBe(`--glob=${raw}`) }) }) describe('workdir derivation and signal forwarding', () => { - it('forwards the session cwd as the request workdir', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('a.ts\n') + it('forwards the session cwd as the spawn cwd', async () => { + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('a.ts\n') await call(ctx, 'glob', { pattern: '*' }, { agent: agent('/sessions/s1') }) - expect(bash.requests[0]?.workdir).toBe('/sessions/s1') - expect(bash.specs[0]?.workdir).toBe('/sessions/s1') + expect(subprocess.spawns[0]?.cwd).toBe('/sessions/s1') }) - it('omits the request workdir without a session cwd so resolve() defaults apply', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('a.ts\n') + it('defaults the spawn cwd to process.cwd() without a session cwd', async () => { + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('a.ts\n') await call(ctx, 'glob', { pattern: '*' }, { agent: agent() }) - expect(bash.requests[0]).not.toHaveProperty('workdir') - expect(bash.specs[0]?.workdir).toBe('/work') - // A non-agent caller takes the same default path. + expect(subprocess.spawns[0]?.cwd).toBe(process.cwd()) + // A non-agent caller takes the same default. await call(ctx, 'grep', { pattern: 'x' }) - expect(bash.requests[1]).not.toHaveProperty('workdir') + expect(subprocess.spawns[1]?.cwd).toBe(process.cwd()) }) - it('forwards exec.signal into the bash spec', async () => { - const { ctx, bash } = await setup() + it('spawns the packaged ripgrep binary with the fixed argv and budgeted collect streams', async () => { + const { ctx, subprocess } = await setup({ config: { rawOutputMaxBytes: 1234 } }) + subprocess.handler = () => runResult('', { exitCode: 1 }) + await call(ctx, 'grep', { pattern: 'needle' }) + const spec = subprocess.spawns[0] + expect(spec?.argv[0]).toBe(rgPath) + expect(spec?.argv).toEqual([rgPath, '--json', '--regexp=needle']) + expect(spec?.stdio.stdin).toBe('ignore') + // stdout gets the tool's parse budget; stderr is a diagnostic excerpt. + expect((spec?.stdio.stdout as { maxBytes: number }).maxBytes).toBe(1234) + expect(spec?.graceMs).toBe(3_000) + }) + + it('forwards exec.signal into the spawn spec', async () => { + const { ctx, subprocess } = await setup() const controller = new AbortController() - bash.handler = () => runResult('') + subprocess.handler = () => runResult('') const result = await call(ctx, 'grep', { pattern: 'x' }, { signal: controller.signal }) - expect(bash.specs[0]?.signal).toBe(controller.signal) + expect(subprocess.spawns[0]?.signal).toBe(controller.signal) expect(result.isError).toBe(false) }) - it('reports the bash executor timeout as SEARCH_ABORTED with the budget', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { timedOut: true, timeoutMs: 1234, exitCode: null, signal: 'SIGTERM' }) - const result = await call(ctx, 'glob', { pattern: '*' }) + it('reports an abort fired during the run as SEARCH_ABORTED', async () => { + // The cooperative tool timeout or caller cancellation aborts exec.signal; + // the subprocess seam then kills the process tree. The tool classifies + // the first cause it owns: the abort. + const { ctx, subprocess } = await setup() + const controller = new AbortController() + subprocess.handler = () => { + controller.abort('timeout') + return runResult('', { exitCode: null, signal: 'SIGTERM' }) + } + const result = await call(ctx, 'glob', { pattern: '*' }, { signal: controller.signal }) expect(result.isError).toBe(true) expect(result.error).toMatchObject({ info: { code: 'SEARCH_ABORTED' } }) - expect(text(result)).toContain('timed out after 1234ms') + expect(text(result)).toContain('aborted before completion') + expect(subprocess.handles[0]?.terminated).toBe(true) }) - it('skips a pre-aborted registry call before run()', async () => { - const { ctx, bash } = await setup() + it('skips a pre-aborted registry call before spawn()', async () => { + const { ctx, subprocess } = await setup() const controller = new AbortController() controller.abort() - bash.handler = () => { throw new Error('aborted before spawn') } + subprocess.handler = () => { throw new Error('aborted before spawn') } const result = await call(ctx, 'grep', { pattern: 'x' }, { signal: controller.signal }) expect(result.isError).toBe(true) expect(result.error).toMatchObject({ info: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH } }) - expect(bash.specs).toHaveLength(0) + expect(subprocess.spawns).toHaveLength(0) }) - it('translates a run() rejection after the forwarded signal aborts', async () => { - const { ctx, bash } = await setup() + it('fails a pre-aborted exec.signal before spawn with SEARCH_ABORTED', async () => { + // Direct unit check of runRipgrep's own pre-spawn guard: the registry + // intercepts most pre-aborted calls, but a signal that aborts between the + // registry check and execute reaches this branch. + const { ctx } = await setup() const controller = new AbortController() - bash.handler = () => { + controller.abort() + const exec = { signal: controller.signal, name: 'glob', callId: CallId('direct-pre-abort') } as unknown as ToolExecution + await expect(runRipgrep(ctx, exec, 'glob', ['--files'], 1_000_000)).rejects + .toMatchObject({ name: 'SearchError', code: 'SEARCH_ABORTED' }) + }) + + it('translates a spawn rejection into SEARCH_FAILED even when the signal aborts concurrently', async () => { + // The seam rejects only for infrastructure failures (unusable workdir, + // missing binary); the abort happened after dispatch, so the launch + // failure is the reportable cause with the original error chained. + const { ctx, subprocess } = await setup() + const controller = new AbortController() + subprocess.handler = () => { controller.abort('cancel search') - throw new Error('executor stopped on abort') + return { reject: new Error('spawn ENOENT') } } const result = await call(ctx, 'grep', { pattern: 'x' }, { signal: controller.signal }) expect(result.isError).toBe(true) - expect(result.error).toMatchObject({ info: { name: 'SearchError', code: 'SEARCH_ABORTED' } }) - expect(text(result)).toContain('aborted before completion') + expect(result.error).toMatchObject({ info: { name: 'SearchError', code: 'SEARCH_FAILED' } }) + expect(text(result)).toContain('could not start') }) - it('translates an aborted executor result after dispatch starts', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { aborted: true, exitCode: null }) - - const result = await call(ctx, 'glob', { pattern: '*' }) - - expect(result.isError).toBe(true) - expect(result.error).toMatchObject({ info: { name: 'SearchError', code: 'SEARCH_ABORTED' } }) - expect(text(result)).toContain('aborted before completion') - }) - - it('translates a run() rejection without an abort (unusable workdir) into SEARCH_FAILED', async () => { - const { ctx, bash } = await setup() - bash.forwardSignal = false - bash.handler = () => { throw new Error('spawn bash ENOENT') } + it('rejects when the subprocess implementation drops a requested collect stream', async () => { + const { ctx, subprocess } = await setup() + subprocess.dropReaders = true const result = await call(ctx, 'glob', { pattern: '*' }) expect(result.isError).toBe(true) expect(result.error).toMatchObject({ info: { name: 'SearchError', code: 'SEARCH_FAILED' } }) - expect(text(result)).toContain('could not start') + expect(text(result)).toContain('no collected output streams') }) }) describe('exit semantics and failure classification', () => { it('exit 1 is a successful empty search', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { exitCode: 1 }) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('', { exitCode: 1 }) const glob = await call(ctx, 'glob', { pattern: '*.nope' }) expect(glob.isError).toBe(false) expect(text(glob)).toBe('No files found') @@ -418,108 +475,100 @@ describe('exit semantics and failure classification', () => { }) it('a regex parse error classifies as SEARCH_INVALID_PATTERN', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { exitCode: 2, stderr: { text: 'rg: regex parse error:\n (\nerror: unclosed group', truncated: false } }) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('', { exitCode: 2, stderr: { text: 'rg: regex parse error:\n (\nerror: unclosed group' } }) const result = await call(ctx, 'grep', { pattern: '(' }) expect(result.error).toMatchObject({ info: { code: 'SEARCH_INVALID_PATTERN' } }) expect(text(result)).toContain('regex parse error') }) it('a glob parse error classifies as SEARCH_INVALID_PATTERN', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { exitCode: 2, stderr: { text: 'rg: error parsing glob \'[\': unclosed character class', truncated: false } }) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('', { exitCode: 2, stderr: { text: 'rg: error parsing glob \'[\': unclosed character class' } }) const result = await call(ctx, 'glob', { pattern: '[' }) expect(result.error).toMatchObject({ info: { code: 'SEARCH_INVALID_PATTERN' } }) }) - it('a missing rg binary classifies as SEARCH_FAILED naming ripgrep', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { exitCode: 127, stderr: { text: 'bash: line 1: rg: command not found', truncated: false } }) + it('a failed ripgrep launch classifies as SEARCH_FAILED naming ripgrep', async () => { + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('', { exitCode: 127, stderr: { text: 'sh: rg: command not found' } }) const result = await call(ctx, 'glob', { pattern: '*' }) expect(result.error).toMatchObject({ info: { code: 'SEARCH_FAILED' } }) expect(text(result)).toContain('requires ripgrep (rg)') // The same classification holds from either evidence alone: the 127 exit // with silent stderr, or a shell's command-not-found text on another exit. - bash.handler = () => runResult('', { exitCode: 127 }) + subprocess.handler = () => runResult('', { exitCode: 127 }) expect(text(await call(ctx, 'glob', { pattern: '*' }))).toContain('requires ripgrep (rg)') - bash.handler = () => runResult('', { exitCode: 2, stderr: { text: 'sh: rg: command not found', truncated: false } }) + subprocess.handler = () => runResult('', { exitCode: 2, stderr: { text: 'sh: rg: command not found' } }) expect(text(await call(ctx, 'grep', { pattern: 'x' }))).toContain('requires ripgrep (rg)') }) it('other nonzero exits are SEARCH_FAILED carrying the stderr excerpt', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { exitCode: 2, stderr: { text: 'rg: missing.dir: IO error: no such file or directory', truncated: false } }) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('', { exitCode: 2, stderr: { text: 'rg: missing.dir: IO error: no such file or directory' } }) const result = await call(ctx, 'grep', { pattern: 'x', path: 'missing.dir' }) expect(result.error).toMatchObject({ info: { code: 'SEARCH_FAILED' } }) expect(text(result)).toContain('IO error') }) it('a nonzero exit with EMPTY stderr still reports the exit code', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { exitCode: 3 }) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('', { exitCode: 3 }) const result = await call(ctx, 'glob', { pattern: '*' }) expect(result.error).toMatchObject({ info: { code: 'SEARCH_FAILED' } }) expect(text(result)).toContain('exit 3') }) it('truncated stderr gains a truncation note and stderr.spillPath is never read', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('', { exitCode: 2, - stderr: { text: 'tail of diagnostics', truncated: true, spillPath: '/does/not/exist-and-never-read' }, + stderr: { text: 'tail of diagnostics', lossy: true, spillPath: '/does/not/exist-and-never-read' }, }) const result = await call(ctx, 'grep', { pattern: 'x' }) expect(text(result)).toContain('tail of diagnostics [stderr truncated]') }) it('a signal kill (not timeout, not abort) is SEARCH_FAILED', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { exitCode: null, signal: 'SIGKILL' }) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('', { exitCode: null, signal: 'SIGKILL' }) const result = await call(ctx, 'grep', { pattern: 'x' }) expect(result.error).toMatchObject({ info: { code: 'SEARCH_FAILED' } }) expect(text(result)).toContain('SIGKILL') }) it('a null exit with no signal (defensive) is SEARCH_FAILED', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { exitCode: null, signal: null }) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('', { exitCode: null, signal: null }) const result = await call(ctx, 'glob', { pattern: '*' }) expect(result.error).toMatchObject({ info: { code: 'SEARCH_FAILED' } }) + expect(text(result)).toContain('killed by signal (unknown)') }) }) describe('raw output acquisition', () => { - it('passes rawOutputMaxBytes to bash as the stdout capture budget', async () => { - const { ctx, bash } = await setup({ config: { rawOutputMaxBytes: 1234 } }) - bash.handler = () => runResult('', { exitCode: 1 }) - await call(ctx, 'glob', { pattern: '*.ts' }) - await call(ctx, 'grep', { pattern: 'needle' }) - expect(bash.requests.map(request => request.stdoutMaxBytes)).toEqual([1234, 1234]) - expect(bash.specs.map(spec => spec.stdoutMaxBytes)).toEqual([1234, 1234]) - }) - it('fails with SEARCH_RAW_OUTPUT_OVERFLOW when truncated stdout has a raw spill path', async () => { - const { ctx, bash } = await setup({ config: { rawOutputMaxBytes: 16 } }) - bash.handler = () => runResult('', { stdout: { text: 'x', truncated: true, spillPath: '/does/not/get-read' } }) + const { ctx, subprocess } = await setup({ config: { rawOutputMaxBytes: 16 } }) + subprocess.handler = () => runResult('', { stdout: { text: 'x', lossy: true, spillPath: '/does/not/get-read' } }) const result = await call(ctx, 'glob', { pattern: '*' }) expect(result.error).toMatchObject({ info: { code: 'SEARCH_RAW_OUTPUT_OVERFLOW' } }) expect(text(result)).toContain('narrow pattern, path, or include') }) it('fails with SEARCH_RAW_OUTPUT_OVERFLOW when UNTRUNCATED inline stdout exceeds the cap', async () => { - // An executor retaining more inline than this package's cap (or a - // deployment lowering rawOutputMaxBytes below the bash retention) must not - // smuggle an over-cap parse through the untruncated path. - const { ctx, bash } = await setup({ config: { rawOutputMaxBytes: 16 } }) - bash.handler = () => runResult(`${'x'.repeat(64)}\n`) + // A subprocess implementation retaining more inline than this package's + // cap (or a deployment lowering rawOutputMaxBytes below the retention + // budget) must not smuggle an over-cap parse through the untruncated path. + const { ctx, subprocess } = await setup({ config: { rawOutputMaxBytes: 16 } }) + subprocess.handler = () => runResult(`${'x'.repeat(64)}\n`) const result = await call(ctx, 'grep', { pattern: 'x' }) expect(result.error).toMatchObject({ info: { name: 'SearchError', code: 'SEARCH_RAW_OUTPUT_OVERFLOW' } }) expect(text(result)).toContain('narrow pattern, path, or include') }) it('fails with SEARCH_RAW_OUTPUT_OVERFLOW when truncated stdout has no spill path', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { stdout: { text: 'partial', truncated: true } }) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('', { stdout: { text: 'partial', lossy: true } }) const result = await call(ctx, 'grep', { pattern: 'x' }) expect(result.error).toMatchObject({ info: { code: 'SEARCH_RAW_OUTPUT_OVERFLOW' } }) }) @@ -614,8 +663,8 @@ describe('cross-directory sampling', () => { describe('glob results', () => { it('lists workdir-relative paths (absolute output under the workdir is relativized)', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('/sessions/s1/src/a.ts\n/elsewhere/b.ts\nrel/c.ts\n') + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('/sessions/s1/src/a.ts\n/elsewhere/b.ts\nrel/c.ts\n') const result = await call(ctx, 'glob', { pattern: '*' }, { agent: agent('/sessions/s1') }) if (result.isError) throw new Error('expected glob success') expect(result.value).toEqual({ root: '.', paths: [join('src', 'a.ts'), '/elsewhere/b.ts', 'rel/c.ts'] }) @@ -628,23 +677,30 @@ describe('glob results', () => { expect(text(await call(ctx, 'glob', { pattern: '*', path: ' ' }))).toContain('path must be a non-empty string') }) - it('threads a valid path through to the command as the quoted search root', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('sub/a.ts\n') + it('threads a valid path through to the spawn as the plain search root element', async () => { + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('sub/a.ts\n') const result = await call(ctx, 'glob', { pattern: '*.ts', path: 'sub' }) expect(result.isError).toBe(false) - expect(bash.specs[0]?.command).toContain("-- 'sub'") + expect(subprocess.spawns[0]?.argv).toEqual([rgPath, '--files', '--glob=*.ts', '--sort=modified', '--no-ignore', '--hidden', + '--glob=!**/.git', '--glob=!**/.git/**', + '--glob=!**/.svn', '--glob=!**/.svn/**', + '--glob=!**/.hg', '--glob=!**/.hg/**', + '--glob=!**/.bzr', '--glob=!**/.bzr/**', + '--glob=!**/.jj', '--glob=!**/.jj/**', + '--glob=!**/.sl', '--glob=!**/.sl/**', + '--', 'sub']) }) it('caps at globMaxResults and saves the FULL sorted list through spillStore', async () => { - const { ctx, bash, spill } = await setup({ config: { globMaxResults: 2 }, spill: true }) + const { ctx, subprocess, spill } = await setup({ config: { globMaxResults: 2 }, spill: true }) ctx.on('tools/post-execute', async () => ({ kind: 'accept', additionalContexts: [createUserMessage({ content: [{ type: 'text', text: 'glob context' }], source: { kind: 'plugin', plugin: 'test' }, })], })) - bash.handler = () => runResult('a.ts\nb.ts\nc.ts\nd.ts\n') + subprocess.handler = () => runResult('a.ts\nb.ts\nc.ts\nd.ts\n') const result = await call(ctx, 'glob', { pattern: '*.ts' }, { agent: agent('/w') }) expect(result.isError).toBe(false) if (result.isError) throw new Error('expected glob success') @@ -665,8 +721,8 @@ describe('glob results', () => { // The shipped failure: `*` matches the whole tree, mtime order puts one // freshly-unpacked subtree first, and a head-of-3 reads like the entire // workspace. The sample reaches every top-level entry instead. - const { ctx, bash } = await setup({ config: { globMaxResults: 3 } }) - bash.handler = () => runResult(['vendor/a.ts', 'vendor/b.ts', 'vendor/c.ts', 'src/d.ts', 'guide/e.md', 'top.txt'].join('\n')) + const { ctx, subprocess } = await setup({ config: { globMaxResults: 3 } }) + subprocess.handler = () => runResult(['vendor/a.ts', 'vendor/b.ts', 'vendor/c.ts', 'src/d.ts', 'guide/e.md', 'top.txt'].join('\n')) const result = await call(ctx, 'glob', { pattern: '*' }, { agent: agent('/w') }) expect(text(result)).toBe('vendor/a.ts\nsrc/d.ts\nguide/e.md\n\n' + '(Showing 3 of 6 paths, sampled across 3 of the 4 top-level entries this pattern matched ' @@ -675,18 +731,18 @@ describe('glob results', () => { }) it('keeps the modification-time head when over-cap sampling is disabled', async () => { - const { ctx, bash } = await setup({ + const { ctx, subprocess } = await setup({ config: { globMaxResults: 3, sampleOverCapGlobResults: false }, }) - bash.handler = () => runResult(['vendor/a.ts', 'vendor/b.ts', 'vendor/c.ts', 'src/d.ts', 'guide/e.md'].join('\n')) + subprocess.handler = () => runResult(['vendor/a.ts', 'vendor/b.ts', 'vendor/c.ts', 'src/d.ts', 'guide/e.md'].join('\n')) expect(text(await call(ctx, 'glob', { pattern: '*' }, { agent: agent('/w') }))) .toBe('vendor/a.ts\nvendor/b.ts\nvendor/c.ts\n\n' + '(Showing 3 of 5 paths. The complete result could not be saved; narrow pattern or path to see more.)') }) it('samples relative to the explicit search root instead of its workdir prefix', async () => { - const { ctx, bash } = await setup({ config: { globMaxResults: 3 } }) - bash.handler = () => runResult([ + const { ctx, subprocess } = await setup({ config: { globMaxResults: 3 } }) + subprocess.handler = () => runResult([ 'workspace/vendor/a.ts', 'workspace/vendor/b.ts', 'workspace/source/c.ts', @@ -698,8 +754,8 @@ describe('glob results', () => { }) it('samples relative to an absolute search root after workdir display conversion', async () => { - const { ctx, bash } = await setup({ config: { globMaxResults: 3 } }) - bash.handler = () => runResult([ + const { ctx, subprocess } = await setup({ config: { globMaxResults: 3 } }) + subprocess.handler = () => runResult([ '/w/workspace/vendor/a.ts', '/w/workspace/vendor/b.ts', '/w/workspace/source/c.ts', @@ -711,8 +767,8 @@ describe('glob results', () => { }) it('drops the narrowing hint when the sample reaches every top-level entry', async () => { - const { ctx, bash } = await setup({ config: { globMaxResults: 3 } }) - bash.handler = () => runResult(['vendor/a.ts', 'vendor/b.ts', 'vendor/c.ts', 'src/d.ts'].join('\n')) + const { ctx, subprocess } = await setup({ config: { globMaxResults: 3 } }) + subprocess.handler = () => runResult(['vendor/a.ts', 'vendor/b.ts', 'vendor/c.ts', 'src/d.ts'].join('\n')) expect(text(await call(ctx, 'glob', { pattern: '*' }, { agent: agent('/w') }))) .toBe('vendor/a.ts\nvendor/b.ts\nsrc/d.ts\n\n' + '(Showing 3 of 4 paths, sampled across 2 of the 2 top-level entries this pattern matched ' @@ -721,34 +777,34 @@ describe('glob results', () => { }) it('keeps modification-time order untouched when the whole result fits', async () => { - const { ctx, bash } = await setup({ config: { globMaxResults: 4 } }) - bash.handler = () => runResult('vendor/a.ts\nvendor/b.ts\nsrc/c.ts\n') + const { ctx, subprocess } = await setup({ config: { globMaxResults: 4 } }) + subprocess.handler = () => runResult('vendor/a.ts\nvendor/b.ts\nsrc/c.ts\n') expect(text(await call(ctx, 'glob', { pattern: '*' }, { agent: agent('/w') }))) .toBe('vendor/a.ts\nvendor/b.ts\nsrc/c.ts') }) it('keeps the plain footer for a flat result, where the sample is the modification-time head', async () => { - const { ctx, bash } = await setup({ config: { globMaxResults: 2 } }) - bash.handler = () => runResult('a.ts\nb.ts\nc.ts\n') + const { ctx, subprocess } = await setup({ config: { globMaxResults: 2 } }) + subprocess.handler = () => runResult('a.ts\nb.ts\nc.ts\n') expect(text(await call(ctx, 'glob', { pattern: '*' }, { agent: agent('/w') }))) .toBe('a.ts\nb.ts\n\n(Showing 2 of 3 paths. The complete result could not be saved; narrow pattern or path to see more.)') }) it('does not create a spill file when the result fits inline', async () => { - const { ctx, bash, spill } = await setup({ spill: true }) - bash.handler = () => runResult('a.ts\nb.ts\n') + const { ctx, subprocess, spill } = await setup({ spill: true }) + subprocess.handler = () => runResult('a.ts\nb.ts\n') const result = await call(ctx, 'glob', { pattern: '*' }, { agent: agent('/w') }) expect(text(result)).toBe('a.ts\nb.ts') expect(spill?.saves).toHaveLength(0) }) it('preserves a downstream canonical value replacement instead of spilling the old value', async () => { - const { ctx, bash, spill } = await setup({ config: { globMaxResults: 1 }, spill: true }) + const { ctx, subprocess, spill } = await setup({ config: { globMaxResults: 1 }, spill: true }) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, value: { root: '.', paths: ['replacement-a.ts', 'replacement-b.ts'] }, })) - bash.handler = () => runResult('old-a.ts\nold-b.ts\n') + subprocess.handler = () => runResult('old-a.ts\nold-b.ts\n') const result = await call(ctx, 'glob', { pattern: '*.ts' }, { agent: agent('/w') }) @@ -760,8 +816,8 @@ describe('glob results', () => { }) it('keeps the full nested Code value without creating a surface spill', async () => { - const { ctx, bash, spill } = await setup({ config: { globMaxResults: 2 }, spill: true }) - bash.handler = () => runResult('a.ts\nb.ts\nc.ts\nd.ts\n') + const { ctx, subprocess, spill } = await setup({ config: { globMaxResults: 2 }, spill: true }) + subprocess.handler = () => runResult('a.ts\nb.ts\nc.ts\nd.ts\n') const result = await call(ctx, 'glob', { pattern: '*.ts' }, { agent: agent('/w'), parent: Symbol('run_code') as ToolExecutionToken, @@ -777,9 +833,9 @@ describe('glob results', () => { ['saveText fails', { fail: true, spill: true, ownerless: false }], ['no session owner', { fail: false, spill: true, ownerless: true }], ])('keeps the inline page and reports the unsaved remainder when %s', async (_label, mode) => { - const { ctx, bash, spill } = await setup({ config: { globMaxResults: 1 }, spill: mode.spill }) + const { ctx, subprocess, spill } = await setup({ config: { globMaxResults: 1 }, spill: mode.spill }) if (mode.fail && spill) spill.failWith = new Error('disk full') - bash.handler = () => runResult('a.ts\nb.ts\n') + subprocess.handler = () => runResult('a.ts\nb.ts\n') const result = await call(ctx, 'glob', { pattern: '*' }, mode.ownerless ? {} : { agent: agent('/w') }) expect(result.isError).toBe(false) // spill unavailability never fails the search expect(text(result)).toBe('a.ts\n\n(Showing 1 of 2 paths. The complete result could not be saved; narrow pattern or path to see more.)') @@ -788,8 +844,8 @@ describe('glob results', () => { describe('grep results', () => { it('groups matches by file with line numbers', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult([ + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult([ JSON.stringify({ type: 'begin', data: { path: { text: 'a.ts' } } }), matchLine('a.ts', 3, 'const x = 1\n'), matchLine('a.ts', 9, 'const y = 2\n'), @@ -812,23 +868,23 @@ describe('grep results', () => { }) it('reports a single match in the singular', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult(`${matchLine('a.ts', 1, 'hit')}\n`) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult(`${matchLine('a.ts', 1, 'hit')}\n`) expect(text(await call(ctx, 'grep', { pattern: 'hit' }))).toBe('Found 1 match\n\na.ts\nLine 1: hit') }) it('relativizes absolute match paths against the resolved workdir', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult(`${matchLine('/sessions/s1/deep/a.ts', 2, 'hit')}\n`) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult(`${matchLine('/sessions/s1/deep/a.ts', 2, 'hit')}\n`) const result = await call(ctx, 'grep', { pattern: 'hit', path: '/sessions/s1' }, { agent: agent('/sessions/s1') }) expect(text(result)).toContain(`${join('deep', 'a.ts')}\nLine 2: hit`) }) it('previews a long matched line at grepMaxLineBytes preserving UTF-8', async () => { - const { ctx, bash } = await setup({ config: { grepMaxLineBytes: 7 } }) + const { ctx, subprocess } = await setup({ config: { grepMaxLineBytes: 7 } }) // 'héllo wörld' cut at 7 bytes lands mid-'é'? h(1)é(2)l(1)l(1)o(1)=6, space=7 → clean cut at 7. // Use a multibyte straddle instead: 'aé' repeated — cut at 7 bytes: a(1)é(2)a(1)é(2)=6 +a(1)=7 → next é straddles: trimmed. - bash.handler = () => runResult(`${matchLine('a.txt', 1, 'aéaéaéaé')}\n`) + subprocess.handler = () => runResult(`${matchLine('a.txt', 1, 'aéaéaéaé')}\n`) const result = await call(ctx, 'grep', { pattern: 'a' }) if (result.isError) throw new Error('expected grep success') expect(result.value).toEqual({ matches: [{ path: 'a.txt', lineNumber: 1, line: 'aéaéaéaé' }] }) @@ -836,9 +892,9 @@ describe('grep results', () => { }) it('renders a non-UTF-8 line (rg bytes form) as a placeholder instead of failing', async () => { - const { ctx, bash } = await setup() + const { ctx, subprocess } = await setup() const record = JSON.stringify({ type: 'match', data: { path: { text: 'bin.dat' }, lines: { bytes: 'AAECww==' }, line_number: 4 } }) - bash.handler = () => runResult(`${record}\n`) + subprocess.handler = () => runResult(`${record}\n`) expect(text(await call(ctx, 'grep', { pattern: 'x' }))).toContain('Line 4: (line is not valid UTF-8)') }) @@ -848,14 +904,14 @@ describe('grep results', () => { }) it('caps at grepMaxMatches and spills the full formatted match list', async () => { - const { ctx, bash, spill } = await setup({ config: { grepMaxMatches: 2 }, spill: true }) + const { ctx, subprocess, spill } = await setup({ config: { grepMaxMatches: 2 }, spill: true }) ctx.on('tools/post-execute', async () => ({ kind: 'accept', additionalContexts: [createUserMessage({ content: [{ type: 'text', text: 'grep context' }], source: { kind: 'plugin', plugin: 'test' }, })], })) - bash.handler = () => runResult([ + subprocess.handler = () => runResult([ matchLine('a.ts', 1, 'one'), matchLine('a.ts', 2, 'two'), matchLine('b.ts', 3, 'three'), @@ -880,7 +936,7 @@ describe('grep results', () => { }) it('preserves a downstream canonical value replacement instead of spilling the old matches', async () => { - const { ctx, bash, spill } = await setup({ config: { grepMaxMatches: 1 }, spill: true }) + const { ctx, subprocess, spill } = await setup({ config: { grepMaxMatches: 1 }, spill: true }) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, value: { @@ -890,7 +946,7 @@ describe('grep results', () => { ], }, })) - bash.handler = () => runResult(`${matchLine('old.ts', 1, 'old')}\n`) + subprocess.handler = () => runResult(`${matchLine('old.ts', 1, 'old')}\n`) const result = await call(ctx, 'grep', { pattern: 'old' }, { agent: agent('/w') }) @@ -907,8 +963,8 @@ describe('grep results', () => { }) it('keeps every nested Code match in the value without creating a surface spill', async () => { - const { ctx, bash, spill } = await setup({ config: { grepMaxMatches: 1 }, spill: true }) - bash.handler = () => runResult(`${matchLine('a.ts', 1, 'one')}\n${matchLine('b.ts', 2, 'two')}\n`) + const { ctx, subprocess, spill } = await setup({ config: { grepMaxMatches: 1 }, spill: true }) + subprocess.handler = () => runResult(`${matchLine('a.ts', 1, 'one')}\n${matchLine('b.ts', 2, 'two')}\n`) const result = await call(ctx, 'grep', { pattern: 'o' }, { agent: agent('/w'), parent: Symbol('run_code') as ToolExecutionToken, @@ -925,8 +981,8 @@ describe('grep results', () => { }) it('reports the unsaved remainder when capped with no spill backend', async () => { - const { ctx, bash } = await setup({ config: { grepMaxMatches: 1 } }) - bash.handler = () => runResult(`${matchLine('a.ts', 1, 'one')}\n${matchLine('a.ts', 2, 'two')}\n`) + const { ctx, subprocess } = await setup({ config: { grepMaxMatches: 1 } }) + subprocess.handler = () => runResult(`${matchLine('a.ts', 1, 'one')}\n${matchLine('a.ts', 2, 'two')}\n`) const result = await call(ctx, 'grep', { pattern: 'o' }, { agent: agent('/w') }) expect(result.isError).toBe(false) expect(text(result)).toBe('Found 1 of 2 matches\n\na.ts\nLine 1: one\n\n(The complete result could not be saved; narrow pattern, path, or include to see more.)') @@ -942,8 +998,8 @@ describe('grep results', () => { }) it('accepts a whitespace-only pattern (a legitimate regex) and brace alternation in include', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('', { exitCode: 1 }) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('', { exitCode: 1 }) const result = await call(ctx, 'grep', { pattern: ' ', include: '*.{ts,tsx}' }) expect(result.isError).toBe(false) }) @@ -960,8 +1016,8 @@ describe('rg --json transport failures (SEARCH_FAILED)', () => { ['a match record with no line content', JSON.stringify({ type: 'match', data: { path: { text: 'a.ts' }, line_number: 1 } })], ['a match record with neither text nor bytes', JSON.stringify({ type: 'match', data: { path: { text: 'a.ts' }, lines: {}, line_number: 1 } })], ])('%s fails the search', async (_label, line) => { - const { ctx, bash } = await setup() - bash.handler = () => runResult(`${line}\n`) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult(`${line}\n`) const result = await call(ctx, 'grep', { pattern: 'x' }) expect(result.isError).toBe(true) expect(result.error).toMatchObject({ info: { name: 'SearchError', code: 'SEARCH_FAILED' } }) @@ -969,13 +1025,16 @@ describe('rg --json transport failures (SEARCH_FAILED)', () => { }) describe('the no-background-task invariant', () => { - it('never calls ctx.bash.start() across successful and failed searches', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult('a.ts\n') + it('settles every spawned search handle across successful and failed searches', async () => { + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('a.ts\n') await call(ctx, 'glob', { pattern: '*' }) - bash.handler = () => runResult('', { exitCode: 2, stderr: { text: 'boom', truncated: false } }) + subprocess.handler = () => runResult('', { exitCode: 2, stderr: { text: 'boom' } }) await call(ctx, 'grep', { pattern: 'x' }) - expect(bash.startCalls).toBe(0) + // One foreground spawn per call, each awaited to settlement before the + // tool returns — the searches never leave a background handle running. + expect(subprocess.spawns).toHaveLength(2) + expect(subprocess.handles.every(handle => handle.settled)).toBe(true) }) }) @@ -991,8 +1050,8 @@ describe('presentation', () => { }) it('grep projects a search card from a real execute, grouped by file with total and truncation', async () => { - const { ctx, bash } = await setup({ config: { grepMaxMatches: 2 } }) - bash.handler = () => runResult([ + const { ctx, subprocess } = await setup({ config: { grepMaxMatches: 2 } }) + subprocess.handler = () => runResult([ matchLine('a.ts', 1, 'one'), matchLine('a.ts', 2, 'two'), matchLine('b.ts', 3, 'three'), @@ -1018,8 +1077,8 @@ describe('presentation', () => { }) it('glob projects a search card from a real execute, a flat path list with total and truncation', async () => { - const { ctx, bash } = await setup({ config: { globMaxResults: 2 } }) - bash.handler = () => runResult('a.ts\nb.ts\nc.ts\n') + const { ctx, subprocess } = await setup({ config: { globMaxResults: 2 } }) + subprocess.handler = () => runResult('a.ts\nb.ts\nc.ts\n') const result = await call(ctx, 'glob', { pattern: '*.ts' }, { agent: agent('/w') }) if (result.isError) throw new Error('expected glob success') expect(result.meta).toEqual({ shape: 'paths', paths: ['a.ts', 'b.ts'], truncated: true, total: 3 }) @@ -1028,8 +1087,8 @@ describe('presentation', () => { }) it('nested Code dispatch computes no meta, so presentResult falls back to the generic card', async () => { - const { ctx, bash } = await setup() - bash.handler = () => runResult(`${matchLine('a.ts', 1, 'one')}\n`) + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult(`${matchLine('a.ts', 1, 'one')}\n`) const result = await call(ctx, 'grep', { pattern: 'o' }, { agent: agent('/w'), parent: Symbol('run_code') as ToolExecutionToken, diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 34eb7b8f87..8b38715d30 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -2931,6 +2931,9 @@ importers: packages/fs/tool-fs-search: dependencies: + '@vscode/ripgrep': + specifier: ^1.18.0 + version: 1.18.0 schemastery: specifier: ^3.18.0 version: 3.18.0 @@ -2938,12 +2941,6 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent - '@deepseek-ai/dsh-bash': - specifier: workspace:^ - version: link:../../bash/bash - '@deepseek-ai/dsh-bash-local': - specifier: workspace:^ - version: link:../../bash/bash-local '@deepseek-ai/dsh-invariants': specifier: workspace:^ version: link:../../support/invariants @@ -2959,6 +2956,9 @@ importers: '@deepseek-ai/dsh-spill': specifier: workspace:^ version: link:../../spill/spill + '@deepseek-ai/dsh-subprocess': + specifier: workspace:^ + version: link:../../subprocess/subprocess '@deepseek-ai/dsh-subprocess-local': specifier: workspace:^ version: link:../../subprocess/subprocess-local @@ -9010,6 +9010,69 @@ packages: '@vitest/utils@4.1.8': resolution: {integrity: sha512-uOJamYALNhfJ6iolExyQM40yIQwDqYnkKtQ5VCiSe17E33H0aQ/u+1GlRuz4LZBk6Mm3sg90G9hEbmEt37C1Zg==} + '@vscode/ripgrep-darwin-arm64@1.18.0': + resolution: {integrity: sha512-r3ktHSvbFycQNF6sl7sNDPocpsI7J+mEzh1IaZFkY0spm3k2Z9t8hPAeOK7+p0l6p6/swkQC14XWX01low+94Q==} + cpu: [arm64] + os: [darwin] + + '@vscode/ripgrep-darwin-x64@1.18.0': + resolution: {integrity: sha512-25b4gWbL138dGuQU244ebCKKc0q05ULBMoFSz9oAEUHNeqK/lOJViDS7DRvbDazzAzSEdan391Znks/R5mkaTQ==} + cpu: [x64] + os: [darwin] + + '@vscode/ripgrep-linux-arm64@1.18.0': + resolution: {integrity: sha512-lQ/5zTG++U0E3IhVgS4EPTTn/U4okncaRMM5GOFfOYZywS4nuD31GhkHbNYlDk5CuDC68+hYJ0/eQeyCKJDA+g==} + cpu: [arm64] + os: [linux] + + '@vscode/ripgrep-linux-arm@1.18.0': + resolution: {integrity: sha512-GDAvufNDHu8zqLEmXstalQF0Wh6wQvdsBi/Vg3Yi3CK4a8XoFXqqXVEHEZ9xQz3t0NfoSEc9JbvK9DDS6FxyxQ==} + cpu: [arm] + os: [linux] + + '@vscode/ripgrep-linux-ia32@1.18.0': + resolution: {integrity: sha512-YWLkSUtFd4Jh5EepIhA9RJSfv3uMAVMo+2rBIGHPBnvgLrZciIs2cDKei1/p6Wc/aCzUoHyMAg2R6tw4ZCBKGg==} + cpu: [ia32] + os: [linux] + + '@vscode/ripgrep-linux-ppc64@1.18.0': + resolution: {integrity: sha512-quXVY8fwQ8O/lvU1yrSqSl3jlUzysRSb+AfUfCL/tRtphxsKlFvPAejryZ6vg4Bgvn8XL74xb4qMCDmWgYrT5w==} + cpu: [ppc64] + os: [linux] + + '@vscode/ripgrep-linux-riscv64@1.18.0': + resolution: {integrity: sha512-f5kBQBrWfQt8Q7OhSORuNDei5dkYagBj3y4jImSUXGMy8B/Ke7SltSRcUtjPv166FAFfHCAmWuZp3+cWnX2/Vw==} + cpu: [riscv64] + os: [linux] + + '@vscode/ripgrep-linux-s390x@1.18.0': + resolution: {integrity: sha512-rTOcJFGGcl2c07RUOWUo4U1ndnemKhY6A9hnMB18uk7jSgJc0d/QLBGWMWpumdtoJtpizn/wIv5mXIisJukusQ==} + cpu: [s390x] + os: [linux] + + '@vscode/ripgrep-linux-x64@1.18.0': + resolution: {integrity: sha512-mQ3bVrUpnD2vs7QT0vX90Lt0cnUq467uFtEktIdsJJmW296RoSULRGqWgzG1AKxyBpNDD6l4ZO4qKf6SgyC23Q==} + cpu: [x64] + os: [linux] + + '@vscode/ripgrep-win32-arm64@1.18.0': + resolution: {integrity: sha512-vfTIjq1OHnzUjxZcHVQAMbnggp8dpGf+0QKFOZHwWPqFwXxQC8eCWM+5NUdoJ6yrElCeMzoUTXoK/LdZaniB+Q==} + cpu: [arm64] + os: [win32] + + '@vscode/ripgrep-win32-ia32@1.18.0': + resolution: {integrity: sha512-//rfAE+BOw5AC2EMmepmiE36jUuevtQYNQqqlw1s3m9FlRxjxEut97RkRPHAu9BG4mSojatZx+kXZXNdyI9caQ==} + cpu: [ia32] + os: [win32] + + '@vscode/ripgrep-win32-x64@1.18.0': + resolution: {integrity: sha512-KNPvtElldqILHdnAetujPaowkNbpqJy3ssIGGN6F6Kve9Qi+nNLI2DN01O83JjCEVQbCzl8Ov3QZ9Eov3BR8Dg==} + cpu: [x64] + os: [win32] + + '@vscode/ripgrep@1.18.0': + resolution: {integrity: sha512-ns5lWe44tSfbTMbVUsyB+I1819PVSw4AdpgK0RNkzfWfwy6+3IUNSxwSrfTno1/oWaS/hERNz+XLWVyga2aJBQ==} + '@vue/compiler-core@3.5.39': resolution: {integrity: sha512-16KBTEXAJCpDr0mwlw+AZyhu8iyC7R3S2vBwsI7QnWJU6X3WKc9VKeNEZpiMdZ569qWhz9574L3vV55qRL0Vtw==} @@ -14110,6 +14173,57 @@ snapshots: convert-source-map: 2.0.0 tinyrainbow: 3.1.0 + '@vscode/ripgrep-darwin-arm64@1.18.0': + optional: true + + '@vscode/ripgrep-darwin-x64@1.18.0': + optional: true + + '@vscode/ripgrep-linux-arm64@1.18.0': + optional: true + + '@vscode/ripgrep-linux-arm@1.18.0': + optional: true + + '@vscode/ripgrep-linux-ia32@1.18.0': + optional: true + + '@vscode/ripgrep-linux-ppc64@1.18.0': + optional: true + + '@vscode/ripgrep-linux-riscv64@1.18.0': + optional: true + + '@vscode/ripgrep-linux-s390x@1.18.0': + optional: true + + '@vscode/ripgrep-linux-x64@1.18.0': + optional: true + + '@vscode/ripgrep-win32-arm64@1.18.0': + optional: true + + '@vscode/ripgrep-win32-ia32@1.18.0': + optional: true + + '@vscode/ripgrep-win32-x64@1.18.0': + optional: true + + '@vscode/ripgrep@1.18.0': + optionalDependencies: + '@vscode/ripgrep-darwin-arm64': 1.18.0 + '@vscode/ripgrep-darwin-x64': 1.18.0 + '@vscode/ripgrep-linux-arm': 1.18.0 + '@vscode/ripgrep-linux-arm64': 1.18.0 + '@vscode/ripgrep-linux-ia32': 1.18.0 + '@vscode/ripgrep-linux-ppc64': 1.18.0 + '@vscode/ripgrep-linux-riscv64': 1.18.0 + '@vscode/ripgrep-linux-s390x': 1.18.0 + '@vscode/ripgrep-linux-x64': 1.18.0 + '@vscode/ripgrep-win32-arm64': 1.18.0 + '@vscode/ripgrep-win32-ia32': 1.18.0 + '@vscode/ripgrep-win32-x64': 1.18.0 + '@vue/compiler-core@3.5.39': dependencies: '@babel/parser': 7.29.7 diff --git a/scripts/gen-third-party-notices.ts b/scripts/gen-third-party-notices.ts index 5306f9a003..5cb912c9ff 100644 --- a/scripts/gen-third-party-notices.ts +++ b/scripts/gen-third-party-notices.ts @@ -157,6 +157,30 @@ function loadWorkspaceManifests(): { manifests: Map; names: Se return { manifests, names } } +type VirtualManifest = Manifest & { license?: string; repository?: string | { url?: string }; homepage?: string } + +/** + * Resolve one package's manifest inside a pnpm virtual store. The prefix scan + * matches ordinary `@scope+name@version` directory names; pnpm 11 truncates + * long names (a peer-suffixed name past the length limit becomes + * `_`), so a content scan falls back over the whole store when + * the prefix misses. + */ +function virtualManifest(virtual: string, name: string): VirtualManifest | undefined { + const prefix = `${name.replace('/', '+')}@` + const entry = readdirSync(virtual).find(dir => dir.startsWith(prefix)) + if (entry !== undefined) { + return JSON.parse(readFileSync(resolve(virtual, entry, 'node_modules', name, 'package.json'), 'utf8')) as VirtualManifest + } + for (const dir of readdirSync(virtual)) { + const candidate = resolve(virtual, dir, 'node_modules', name, 'package.json') + if (existsSync(candidate)) { + return JSON.parse(readFileSync(candidate, 'utf8')) as VirtualManifest + } + } + return undefined +} + /** License and repository URL for an installed external package, from the pnpm store. */ function installedMetadata(name: string): { license: string; repo: string } { const override = OVERRIDES[name] @@ -171,11 +195,8 @@ function installedMetadata(name: string): { license: string; repo: string } { } const virtual = resolve(root, store, '.pnpm') if (!existsSync(virtual)) continue - const prefix = `${name.replace('/', '+')}@` - const entry = readdirSync(virtual).find(dir => dir.startsWith(prefix)) - if (entry === undefined) continue - manifest = JSON.parse(readFileSync(resolve(virtual, entry, 'node_modules', name, 'package.json'), 'utf8')) as typeof manifest - break + manifest = virtualManifest(virtual, name) + if (manifest !== undefined) break } const license = override?.license ?? manifest?.license const rawRepo = typeof manifest?.repository === 'string' ? manifest.repository : manifest?.repository?.url ?? manifest?.homepage diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index a77bdb6d95..3db63b4271 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -16,8 +16,6 @@ import SessionQuerySqlite from '@deepseek-ai/dsh-session-query-sqlite' import GoalService from '@deepseek-ai/dsh-goal' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools' -import { BashExecutor } from '@deepseek-ai/dsh-bash' -import type { BashExecRequest, BashExecSpec, BashProcess, BashRunResult } from '@deepseek-ai/dsh-bash' import LocalBashExecutor from '@deepseek-ai/dsh-bash-local' import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local' import LocalFileSystem from '@deepseek-ai/dsh-fs-local' @@ -55,44 +53,6 @@ import * as ToolWorkflow from '@deepseek-ai/dsh-tool-workflow' const root = resolve(import.meta.dirname, '..') const OUT = 'docs/tool-catalog.md' -const CATALOG_RG_PROBE_COMMAND = 'command -v rg >/dev/null 2>&1' - -/** - * Minimal bash service for harvesting `dsh-tool-fs-search` schemas. The search - * plugin now probes `rg` at registration time, but the generated catalog must - * remain independent of the host PATH and never execute a real search. - */ -class CatalogSearchBashExecutor extends BashExecutor { - override resolve(request: BashExecRequest): BashExecSpec { - return { - command: request.command, - workdir: request.workdir ?? root, - timeoutMs: request.timeoutMs ?? 60_000, - stdoutMaxBytes: request.stdoutMaxBytes ?? 64_000, - signal: request.signal, - sandboxPolicy: request.sandboxPolicy, - } - } - - override run(spec: BashExecSpec): Promise { - if (spec.command !== CATALOG_RG_PROBE_COMMAND) { - throw new Error(`gen-tool-catalog: unexpected search bash command during schema harvest: ${spec.command}`) - } - return Promise.resolve({ - exitCode: 0, - signal: null, - timedOut: false, - aborted: false, - timeoutMs: spec.timeoutMs, - stdout: { text: '', truncated: false }, - stderr: { text: '', truncated: false }, - }) - } - - override start(): BashProcess { - throw new Error('gen-tool-catalog: search schema harvest must not start background processes') - } -} /** * Register the descriptor needed to mount schema-producing consumers. Declares @@ -264,19 +224,19 @@ const TOOL_PACKAGES: ToolPackage[] = [ pkg: '@deepseek-ai/dsh-tool-fs-search', dir: 'tool-fs-search', source: 'packages/fs/tool-fs-search/src/index.ts', - requires: ['ctx.tools', 'ctx.bash', 'ctx.systemPrompt'], + requires: ['ctx.tools', 'ctx.subprocess', 'ctx.systemPrompt'], writes: ['tool/call', 'tool/result'], async mount(ctx) { - // The tools inject `bash` (search executes fixed `rg` commands through - // the executor seam, not ctx.fs). Use a catalog-only executor so the - // registration-time `rg` probe stays deterministic and the generator - // never depends on the host PATH. `ctx.spillStore` is optional (read via - // ctx.get) and does not affect the schemas, so no spill backend is mounted. - await ctx.plugin(CatalogSearchBashExecutor) + // The tools inject `subprocess` (search spawns the packaged ripgrep + // binary through the seam, not ctx.fs); registration itself never + // spawns, so the real local service is inert here. `ctx.spillStore` is + // optional (read via ctx.get) and does not affect the schemas, so no + // spill backend is mounted. + await ctx.plugin(LocalSubprocessService) await ctx.plugin(ToolFsSearch, { sampleOverCapGlobResults: true }) }, note: - 'glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). The catalog uses `sampleOverCapGlobResults: true`; deployments must choose that behavior explicitly. Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments.', + 'glob and grep are unconditional discovery tools that spawn the packaged ripgrep binary (`@vscode/ripgrep`) through ctx.subprocess as ordinary foreground calls (never background tasks) — no host `rg` install and no shell layer. The catalog uses `sampleOverCapGlobResults: true`; deployments must choose that behavior explicitly. Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments.', }, { pkg: '@deepseek-ai/dsh-tool-pty', From 7206c6019a1be093a0f9aca293a34f577494ceb8 Mon Sep 17 00:00:00 2001 From: Huanqi Cao Date: Sat, 1 Aug 2026 18:15:11 +0800 Subject: [PATCH 06/45] chore(knip): drop the now-unused rg binary exemption tool-fs-search no longer spawns rg from PATH after the packaged-binary switch, so its per-workspace ignoreBinaries entry is stale. --- knip.json | 3 --- 1 file changed, 3 deletions(-) diff --git a/knip.json b/knip.json index 99b152738d..30b1821cd3 100644 --- a/knip.json +++ b/knip.json @@ -566,9 +566,6 @@ "project": [ "src/**/*.ts", "tests/**/*.ts" - ], - "ignoreBinaries": [ - "rg" ] }, "packages/mcp/mcp-client": { From 00148eea9732fe73ae4fdaf2932d35c4e708bf81 Mon Sep 17 00:00:00 2001 From: Huanqi Cao Date: Sat, 1 Aug 2026 19:13:42 +0800 Subject: [PATCH 07/45] fix(scripts): normalize manifest glob paths in the notices generator Node's fs.globSync returns OS-native separators: on Windows the backslash paths failed the /-suffixed DEV_ONLY_AREAS prefix match in tierExternalDeps, silently tiering dev-area manifests (test-runtime, support/*, apps/*) as runtime dependencies. Normalize to / at ingestion so the generated notices are platform-independent. --- THIRD_PARTY_NOTICES.md | 8 ++++---- scripts/gen-third-party-notices.ts | 13 ++++++++++--- 2 files changed, 14 insertions(+), 7 deletions(-) diff --git a/THIRD_PARTY_NOTICES.md b/THIRD_PARTY_NOTICES.md index 1b14996c3f..f4152cb8a0 100644 --- a/THIRD_PARTY_NOTICES.md +++ b/THIRD_PARTY_NOTICES.md @@ -47,8 +47,6 @@ External packages that a workspace package resolves at runtime. `scripts/install | [`@opentelemetry/sdk-logs`](https://github.com/open-telemetry/opentelemetry-js) | Apache-2.0 | | [`@shikijs/langs`](https://github.com/shikijs/shiki) | MIT | | [`@standard-schema/spec`](https://github.com/standard-schema/standard-schema) | MIT | -| [`@testing-library/dom`](https://github.com/testing-library/dom-testing-library) | MIT | -| [`@testing-library/react`](https://github.com/testing-library/react-testing-library) | MIT | | [`@vscode/ripgrep`](https://github.com/microsoft/vscode-ripgrep) | MIT | | [`anser`](https://github.com/IonicaBizau/anser) | MIT | | [`chokidar`](https://github.com/paulmillr/chokidar) | MIT | @@ -57,7 +55,6 @@ External packages that a workspace package resolves at runtime. `scripts/install | [`diff`](https://github.com/kpdecker/jsdiff) | BSD-3-Clause | | [`dotenv`](https://github.com/motdotla/dotenv) | BSD-2-Clause | | [`eventsource-parser`](https://github.com/rexxars/eventsource-parser) | MIT | -| [`execa`](https://github.com/sindresorhus/execa) | MIT | | [`handlebars`](https://github.com/handlebars-lang/handlebars.js) | MIT | | [`immer`](https://github.com/immerjs/immer) | MIT | | [`js-yaml`](https://github.com/nodeca/js-yaml) | MIT | @@ -83,7 +80,6 @@ External packages that a workspace package resolves at runtime. `scripts/install | [`turndown`](https://github.com/mixmark-io/turndown) | MIT | | [`typescript`](https://github.com/microsoft/TypeScript) | Apache-2.0 | | [`use-sync-external-store`](https://github.com/facebook/react) | MIT | -| [`vitest`](https://github.com/vitest-dev/vitest) | MIT | | [`yaml`](https://github.com/eemeli/yaml) | ISC | | [`zod`](https://github.com/colinhacks/zod) | MIT | | [`zustand`](https://github.com/pmndrs/zustand) | MIT | @@ -103,6 +99,8 @@ External packages **directly declared** only by repository tooling, test infrast | [`@modelcontextprotocol/server-everything`](https://github.com/modelcontextprotocol/servers) | MIT / Apache-2.0 | | [`@modelcontextprotocol/server-filesystem`](https://github.com/modelcontextprotocol/servers) | MIT / Apache-2.0 | | [`@stylistic/eslint-plugin`](https://github.com/eslint-stylistic/eslint-stylistic) | MIT | +| [`@testing-library/dom`](https://github.com/testing-library/dom-testing-library) | MIT | +| [`@testing-library/react`](https://github.com/testing-library/react-testing-library) | MIT | | [`@types/babel__code-frame`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | | [`@types/js-yaml`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | | [`@types/jsdom`](https://github.com/DefinitelyTyped/DefinitelyTyped) | MIT | @@ -125,6 +123,7 @@ External packages **directly declared** only by repository tooling, test infrast | [`esbuild`](https://github.com/evanw/esbuild) | MIT | | [`eslint`](https://github.com/eslint/eslint) | MIT | | [`eslint-plugin-sonarjs`](https://github.com/SonarSource/SonarJS) | LGPL-3.0-only | +| [`execa`](https://github.com/sindresorhus/execa) | MIT | | [`fast-check`](https://github.com/dubzzz/fast-check) | MIT | | [`jscpd`](https://github.com/kucherenko/jscpd) | MIT | | [`jsdom`](https://github.com/jsdom/jsdom) | MIT | @@ -144,6 +143,7 @@ External packages **directly declared** only by repository tooling, test infrast | [`vite-tsconfig-paths`](https://github.com/aleclarson/vite-tsconfig-paths) | MIT | | [`vitepress`](https://github.com/vuejs/vitepress) | MIT | | [`vitepress-plugin-mermaid`](https://github.com/emersonbottero/vitepress-plugin-mermaid) | MIT | +| [`vitest`](https://github.com/vitest-dev/vitest) | MIT | `eslint-plugin-sonarjs` (LGPL-3.0-only) and `lightningcss` (MPL-2.0) run only as development tooling; their code is not linked into or distributed with any DeepSeek Harness artifact. diff --git a/scripts/gen-third-party-notices.ts b/scripts/gen-third-party-notices.ts index 5cb912c9ff..a4a1f4c343 100644 --- a/scripts/gen-third-party-notices.ts +++ b/scripts/gen-third-party-notices.ts @@ -141,15 +141,22 @@ function workspaceMembers(rel: string): string[] { return declared.map(member => String(member)) } -/** Every workspace manifest, keyed by path, plus the set of workspace package names. */ +/** + * Every workspace manifest, keyed by repository-relative path, plus the set of + * workspace package names. Paths are normalized to `/` at ingestion: Node's + * `fs.globSync` returns OS-native separators, and the area matching in + * `tierExternalDeps` compares `/`-suffixed prefixes, so Windows backslashes + * would silently push dev-area manifests into the runtime tier. + */ function loadWorkspaceManifests(): { manifests: Map; names: Set } { const patterns = manifestPatterns(workspaceMembers('pnpm-workspace.yaml'), workspaceMembers('native/landlock-run/pnpm-workspace.yaml')) const manifests = new Map() const names = new Set() for (const pattern of patterns) { for (const path of globSync(pattern, { cwd: root })) { - const manifest = readManifest(path) - manifests.set(path, manifest) + const normalized = path.replaceAll('\\', '/') + const manifest = readManifest(normalized) + manifests.set(normalized, manifest) if (manifest.name !== undefined) names.add(manifest.name) } } From 36700f69169d4ea7d557c634f62581c8d852782d Mon Sep 17 00:00:00 2001 From: Huanqi Cao Date: Sat, 1 Aug 2026 19:17:59 +0800 Subject: [PATCH 08/45] docs(note): record the notices-generator fixes behind the new dependency --- .../architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml | 4 ++-- .../architecture/2026-08-01-packaged-ripgrep-search.md | 2 ++ .../architecture/2026-08-01-packaged-ripgrep-search.zh.md | 2 ++ 3 files changed, 6 insertions(+), 2 deletions(-) diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml index fe6bb60e68..df6948209a 100644 --- a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-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/architecture/2026-08-01-packaged-ripgrep-search.md -2026-08-01-packaged-ripgrep-search.md: e43354ff8e4dde0480a6c07816fc112810197234 -2026-08-01-packaged-ripgrep-search.zh.md: 55498d366a2171a178cf9d0d1004b6fe946a7281 +2026-08-01-packaged-ripgrep-search.md: 0470623163ff7686bdd77ca715bac68c9a466d2b +2026-08-01-packaged-ripgrep-search.zh.md: fe53643aff139615d49edd2e3b27d14428cd2029 diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md index e43354ff8e..0470623163 100644 --- a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md @@ -32,3 +32,5 @@ The `fs-glob-sampling` ACP snapshot scenario now executes the real packaged bina - The shell-string attack surface is gone: hostile patterns are inert argv elements, pinned by the integration suite, which now runs on Windows too (it previously self-skipped without a system `rg`). - Load-time failure modes changed: a broken subprocess seam now fails the first search call (`SEARCH_FAILED`) instead of failing plugin load through the probe; a missing binary is a launch failure with the packaged path, not a PATH problem. - The integration suite's fixture dropped a filename Windows cannot represent (`"` in a name), keeping the suite replayable on every platform. +- Regenerating `THIRD_PARTY_NOTICES.md` surfaced a latent generator bug the new dependency made visible: Node's `fs.globSync` returns OS-native separators, so on Windows the `/`-suffixed dev-area prefixes in the notices tiering never matched and dev-only packages (test tooling, support leaves) were mis-tiered as runtime. The generator now normalizes manifest paths at ingestion, and the notices are platform-independent. +- The `@vscode/ripgrep` dependency adds its MIT row to the runtime tier, and pnpm 11's truncated virtual-store directory names needed a content-scan fallback in the notices generator's metadata lookup. diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md index 55498d366a..fe53643aff 100644 --- a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md @@ -32,3 +32,5 @@ Status: implemented - shell 字符串攻击面消失：恶意模式只是惰性 argv 元素，由集成套件钉住；该套件现在也在 Windows 上运行（此前没有系统 `rg` 时它自行跳过）。 - 加载期失败模式改变：subprocess seam 损坏现在让首次搜索调用失败（`SEARCH_FAILED`），而非通过探针使插件加载失败；二进制缺失是带打包路径的启动失败，而不是 PATH 问题。 - 集成套件的 fixture 去掉了 Windows 无法表示的文件名（名称含 `"`），保证套件在每个平台都能重放。 +- 重新生成 `THIRD_PARTY_NOTICES.md` 暴露了一个由新依赖带出的潜在生成器 bug：Node 的 `fs.globSync` 返回操作系统原生分隔符，因此在 Windows 上 notices 分层中带 `/` 后缀的 dev 区前缀永远匹配不上，dev-only 包（测试工具、support 叶子）被错分为 runtime。生成器现在在入口处归一化清单路径，notices 与平台无关。 +- `@vscode/ripgrep` 依赖为 runtime 层增加其 MIT 行；pnpm 11 截断的虚拟存储目录名需要在 notices 生成器的元数据查找中增加内容扫描回退。 From a9871d4af1760d7564c934185fac19f426c3aae5 Mon Sep 17 00:00:00 2001 From: Huanqi Cao Date: Sat, 1 Aug 2026 21:56:16 +0800 Subject: [PATCH 09/45] refactor(fs-search): apply #1119 review fixes to the packaged-rg spawn - delete the singleQuote shell-quoting helper and its bash-spawning tests (no in-repo consumers; no shell layer exists anymore) - drop spill from both collect streams: the tool never reads a raw spill path, and a lossy stdout read is a pure SEARCH_RAW_OUTPUT_OVERFLOW error - prepend --no-config so a host RIPGREP_CONFIG_PATH cannot inject a --pre preprocessor into the unconfined spawn - promote graceMs and stderrMaxBytes to validated Config fields (defaults SEARCH_GRACE_MS / SEARCH_STDERR_MAX_BYTES) instead of inheriting bash-local's config - correct the grep tool's JSDoc seam reference (bash -> subprocess) - drop the dead exit-127/command-not-found classification branch --- ...26-08-01-packaged-ripgrep-search.i18n.yaml | 4 +- .../2026-08-01-packaged-ripgrep-search.md | 4 +- .../2026-08-01-packaged-ripgrep-search.zh.md | 4 +- docs/config-catalog.md | 6 +- packages/fs/tool-fs-search/README.i18n.yaml | 4 +- packages/fs/tool-fs-search/README.md | 6 +- packages/fs/tool-fs-search/README.zh.md | 6 +- packages/fs/tool-fs-search/src/glob.ts | 6 +- packages/fs/tool-fs-search/src/grep.ts | 8 ++- packages/fs/tool-fs-search/src/index.ts | 17 +++++- packages/fs/tool-fs-search/src/search-core.ts | 40 ++++++++----- packages/fs/tool-fs-search/src/shell-quote.ts | 24 -------- .../tool-fs-search/tests/shell-quote.spec.ts | 59 ------------------- .../fs/tool-fs-search/tests/tools.spec.ts | 44 +++++++------- 14 files changed, 97 insertions(+), 135 deletions(-) delete mode 100644 packages/fs/tool-fs-search/src/shell-quote.ts delete mode 100644 packages/fs/tool-fs-search/tests/shell-quote.spec.ts diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml index df6948209a..3647587fa5 100644 --- a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-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/architecture/2026-08-01-packaged-ripgrep-search.md -2026-08-01-packaged-ripgrep-search.md: 0470623163ff7686bdd77ca715bac68c9a466d2b -2026-08-01-packaged-ripgrep-search.zh.md: fe53643aff139615d49edd2e3b27d14428cd2029 +2026-08-01-packaged-ripgrep-search.md: 849cc0804a2081492297649ac8f13236e2ac60fe +2026-08-01-packaged-ripgrep-search.zh.md: 4381c3a8bca8e6bb9ab375ad352fec5a5ddb9f99 diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md index 0470623163..849cc0804a 100644 --- a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md @@ -12,7 +12,7 @@ The `glob`/`grep` tools ran through the bash executor seam, which made a system ## Decision -`@deepseek-ai/dsh-tool-fs-search` now runs the PACKAGED ripgrep binary (`@vscode/ripgrep`, an npm dependency whose optional platform packages ship the binary) through the `ctx.subprocess` seam: `runRipgrep()` spawns `rgPath` with a plain argv vector, collect-mode stdout/stderr, `graceMs`, and `exec.signal` forwarded. There is no shell layer, so the shell-quoting boundary is gone from execution; `singleQuote` stays exported as a compatibility surface with its tests. Registration is unconditional — the load-time `command -v rg` probe and the conditional registration decision are deleted, and with them the "rg not found" warning. The package injects `tools`, `systemPrompt`, and `subprocess`. +`@deepseek-ai/dsh-tool-fs-search` now runs the PACKAGED ripgrep binary (`@vscode/ripgrep`, an npm dependency whose optional platform packages ship the binary) through the `ctx.subprocess` seam: `runRipgrep()` spawns `rgPath` with a plain argv vector prefixed by `--no-config`, collect-mode stdout/stderr, `graceMs`, and `exec.signal` forwarded. There is no shell layer, so the shell-quoting boundary is gone from execution; the `singleQuote` helper and its shell-spawning tests are deleted with it. The raw streams request the seam's diagnostic-tail collect shape (no spill files — the tool never reads a raw spill path; a lossy stdout read fails as `SEARCH_RAW_OUTPUT_OVERFLOW`). The terminate grace and the stderr tail budget are validated `Config` fields (`graceMs` default 3000, `stderrMaxBytes` default 64 KiB), no longer inherited from bash-local's config. Registration is unconditional — the load-time `command -v rg` probe and the conditional registration decision are deleted, and with them the "rg not found" warning. The package injects `tools`, `systemPrompt`, and `subprocess`. Exit semantics stay tool-owned: exit 0 is success with results, exit 1 is a successful empty search, anything else classifies into the existing `SEARCH_*` vocabulary (invalid pattern, launch failure, signal kill, raw-output overflow). Timeout is the cooperative tool-call budget attached to the tool definitions: `@deepseek-ai/dsh-timeout-policy` aborts `exec.signal`, the subprocess seam's terminate escalation provides the hard kill, and the tool reports `SEARCH_ABORTED`. The working directory is the session header cwd when present, else `process.cwd()` — there is no executor config to default through anymore, so the tool owns the fallback. @@ -30,6 +30,8 @@ The `fs-glob-sampling` ACP snapshot scenario now executes the real packaged bina - The discovery tools work on every platform the packaged binary covers (darwin/linux/win32, x64/arm64) with no host install; the shipped TUI/Web rosters gain `glob`/`grep` as fixed members ([even-out-shipped-tool-rosters](../feature/2026-07-31-even-out-shipped-tool-rosters.md)). - The shell-string attack surface is gone: hostile patterns are inert argv elements, pinned by the integration suite, which now runs on Windows too (it previously self-skipped without a system `rg`). +- The spawn is unconfined (a plain `ctx.subprocess` call), so `--no-config` is prepended: a host `RIPGREP_CONFIG_PATH` (or an `rg.conf` beside the binary) can otherwise inject a `--pre` preprocessor that executes an arbitrary command for every matched file. With `--no-config`, no config file — and therefore no preprocessor — can reach the search. +- The raw-output overflow path changed shape: the old bash-backed route inherited bash-local's always-on spill and could leave an unread multi-megabyte temp file; the subprocess seam now collects without spill, and overflow is a pure error (`SEARCH_RAW_OUTPUT_OVERFLOW`, "narrow pattern, path, or include and retry") with zero content returned. - Load-time failure modes changed: a broken subprocess seam now fails the first search call (`SEARCH_FAILED`) instead of failing plugin load through the probe; a missing binary is a launch failure with the packaged path, not a PATH problem. - The integration suite's fixture dropped a filename Windows cannot represent (`"` in a name), keeping the suite replayable on every platform. - Regenerating `THIRD_PARTY_NOTICES.md` surfaced a latent generator bug the new dependency made visible: Node's `fs.globSync` returns OS-native separators, so on Windows the `/`-suffixed dev-area prefixes in the notices tiering never matched and dev-only packages (test tooling, support leaves) were mis-tiered as runtime. The generator now normalizes manifest paths at ingestion, and the notices are platform-independent. diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md index fe53643aff..4381c3a8bc 100644 --- a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -`@deepseek-ai/dsh-tool-fs-search` 现在运行 PACKAGED（打包的）ripgrep 二进制（`@vscode/ripgrep`，一个 npm 依赖，其可选平台包随附二进制），经由 `ctx.subprocess` seam：`runRipgrep()` 以纯 argv 向量 spawn `rgPath`，配以 collect 模式 stdout/stderr、`graceMs` 与转发的 `exec.signal`。不再有 shell 层，执行路径上的 shell 引号边界随之消失；`singleQuote` 作为兼容导出与其测试保留。注册变为无条件——加载期 `command -v rg` 探针与条件注册决策被删除，连同那条 "rg not found" 警告。本包注入 `tools`、`systemPrompt` 与 `subprocess`。 +`@deepseek-ai/dsh-tool-fs-search` 现在运行 PACKAGED（打包的）ripgrep 二进制（`@vscode/ripgrep`，一个 npm 依赖，其可选平台包随附二进制），经由 `ctx.subprocess` seam：`runRipgrep()` 以纯 argv 向量 spawn `rgPath`，向量前缀 `--no-config`，配以 collect 模式 stdout/stderr、`graceMs` 与转发的 `exec.signal`。不再有 shell 层，执行路径上的 shell 引号边界随之消失；`singleQuote` 工具与其 shell spawn 测试一并删除。原始流使用 seam 的诊断尾部 collect 形态（无 spill 文件——工具从不读取原始 spill 路径；lossy stdout 读取以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败）。终止宽限与 stderr 尾部预算成为经校验的 `Config` 字段（`graceMs` 默认 3000，`stderrMaxBytes` 默认 64 KiB），不再继承自 bash-local 的配置。注册变为无条件——加载期 `command -v rg` 探针与条件注册决策被删除，连同那条 "rg not found" 警告。本包注入 `tools`、`systemPrompt` 与 `subprocess`。 退出语义仍由工具拥有：退出码 0 为有结果的成功，1 为成功的空搜索，其余归入既有 `SEARCH_*` 词汇（无效模式、启动失败、信号杀死、原始输出溢出）。超时是挂在工具定义上的协作式工具调用预算：`@deepseek-ai/dsh-timeout-policy` 中止 `exec.signal`，subprocess seam 的终止升级提供硬终止，工具报告 `SEARCH_ABORTED`。工作目录为会话 header cwd（存在时），否则为 `process.cwd()`——不再有执行器配置可供默认化，因此回退由工具自己拥有。 @@ -30,6 +30,8 @@ Status: implemented - 发现工具在打包二进制覆盖的每个平台（darwin/linux/win32，x64/arm64）上开箱即用，无需宿主安装；交付的 TUI/Web 工具清单把 `glob`/`grep` 变为固定成员（见 [拉平交付的工具清单](../feature/2026-07-31-even-out-shipped-tool-rosters.md)）。 - shell 字符串攻击面消失：恶意模式只是惰性 argv 元素，由集成套件钉住；该套件现在也在 Windows 上运行（此前没有系统 `rg` 时它自行跳过）。 +- spawn 不受沙箱约束（普通的 `ctx.subprocess` 调用），因此前缀 `--no-config`：宿主的 `RIPGREP_CONFIG_PATH`（或二进制旁的 `rg.conf`）否则可注入 `--pre` 预处理器，对每个匹配文件执行任意命令。加上 `--no-config` 后，任何配置文件——因而任何预处理器——都无法触及搜索。 +- 原始输出溢出路径的形态改变：旧的 bash 承载路径继承了 bash-local 常开的 spill，可能留下没人读的多 MB 临时文件；subprocess seam 现在无 spill 收集，溢出是纯粹的错误（`SEARCH_RAW_OUTPUT_OVERFLOW`，"narrow pattern, path, or include and retry"），不返回任何内容。 - 加载期失败模式改变：subprocess seam 损坏现在让首次搜索调用失败（`SEARCH_FAILED`），而非通过探针使插件加载失败；二进制缺失是带打包路径的启动失败，而不是 PATH 问题。 - 集成套件的 fixture 去掉了 Windows 无法表示的文件名（名称含 `"`），保证套件在每个平台都能重放。 - 重新生成 `THIRD_PARTY_NOTICES.md` 暴露了一个由新依赖带出的潜在生成器 bug：Node 的 `fs.globSync` 返回操作系统原生分隔符，因此在 Windows 上 notices 分层中带 `/` 后缀的 dev 区前缀永远匹配不上，dev-only 包（测试工具、support 叶子）被错分为 runtime。生成器现在在入口处归一化清单路径，notices 与平台无关。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 20f835bb7f..1151f0ff0d 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1733,12 +1733,16 @@ export interface Config { searchMetaMaxBytes?: number /** Max complete raw `rg` stdout bytes a search will parse; larger raw output fails with `SEARCH_RAW_OUTPUT_OVERFLOW`. */ rawOutputMaxBytes?: number + /** Terminate-escalation grace period (ms) for one search process, handed to the subprocess seam. */ + graceMs?: number + /** Max bytes retained for one search's stderr diagnostic tail (never surfaced to the model). */ + stderrMaxBytes?: number /** Cooperative tool-call timeout budget (ms) on both tools, enforced by `@deepseek-ai/dsh-timeout-policy` through `exec.signal`. */ timeoutMs?: number } ``` -Source: [`packages/fs/tool-fs-search/src/index.ts:70`](../packages/fs/tool-fs-search/src/index.ts) +Source: [`packages/fs/tool-fs-search/src/index.ts:71`](../packages/fs/tool-fs-search/src/index.ts) ## `@deepseek-ai/dsh-tool-goal` diff --git a/packages/fs/tool-fs-search/README.i18n.yaml b/packages/fs/tool-fs-search/README.i18n.yaml index 5ed7bfb8bb..a8e2222998 100644 --- a/packages/fs/tool-fs-search/README.i18n.yaml +++ b/packages/fs/tool-fs-search/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/fs/tool-fs-search/README.md -README.md: 0152be017ae15fc83a3d5cb7df927f25d04d2d53 -README.zh.md: 69ce49f3ad1621021dc1d0938cdc07a900d1cda8 +README.md: 78ffa069e56da5fc987913acf761eb5c6ae15b1a +README.zh.md: 42b123d5c47d8f48bc21b6f9bed4905372ca8625 diff --git a/packages/fs/tool-fs-search/README.md b/packages/fs/tool-fs-search/README.md index 0152be017a..78ffa069e5 100644 --- a/packages/fs/tool-fs-search/README.md +++ b/packages/fs/tool-fs-search/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -The **model-facing filesystem discovery tools**—`glob`, `grep`—are backed by the **packaged ripgrep binary** (`@vscode/ripgrep`), not by `ctx.fs` provider methods and not by a system `rg` install. Registration is unconditional: the binary ships inside the npm dependency, so there is no load-time availability probe. Each call spawns the binary through the `ctx.subprocess` seam with a fixed argv vector (model-controlled values are plain argv elements — no shell layer exists, so no quoting applies), parses the raw `rg` output, and returns a workdir-relative canonical value. The package injects `tools`, `systemPrompt`, and `subprocess`—deliberately **not** `fs`; `ctx.spillStore` is read opportunistically with `ctx.get()` because formatted-result spill is optional. +The **model-facing filesystem discovery tools**—`glob`, `grep`—are backed by the **packaged ripgrep binary** (`@vscode/ripgrep`), not by `ctx.fs` provider methods and not by a system `rg` install. Registration is unconditional: the binary ships inside the npm dependency, so there is no load-time availability probe. Each call spawns the binary through the `ctx.subprocess` seam with a fixed argv vector (`--no-config` prepended so a host `RIPGREP_CONFIG_PATH` cannot inject a `--pre` preprocessor into the unconfined spawn; model-controlled values are plain argv elements — no shell layer exists, so no quoting applies), parses the raw `rg` output, and returns a workdir-relative canonical value. The package injects `tools`, `systemPrompt`, and `subprocess`—deliberately **not** `fs`; `ctx.spillStore` is read opportunistically with `ctx.get()` because formatted-result spill is optional. ```ts ignore-check // A deployment chooses how over-cap glob pages are selected. @@ -30,6 +30,8 @@ The binary ships with the package on every supported platform (macOS/Linux/Windo | `grepMaxLineBytes` | `2000` | Byte cap per matched-line preview; the cut preserves UTF-8 boundaries and is marked `(line truncated)`. | | `rawOutputMaxBytes` | `20000000` | Max complete raw `rg` stdout a search will parse (matches Claude Code's ripgrep raw buffer); larger raw output fails with `SEARCH_RAW_OUTPUT_OVERFLOW`. | | `timeoutMs` | `30000` | Cooperative tool-call budget attached to both tool definitions, enforced by `@deepseek-ai/dsh-timeout-policy` through `exec.signal`; the subprocess seam's terminate escalation is the hard kill. | +| `graceMs` | `3000` | Terminate-escalation grace period the subprocess seam grants past `timeoutMs` before the search fails as `SEARCH_ABORTED`. | +| `stderrMaxBytes` | `65536` | Diagnostic-tail budget for `rg` stderr, captured through the subprocess seam's collect disposition; a lossy read keeps only the tail (marked `[stderr truncated]`). | ## Tools @@ -42,7 +44,7 @@ Routine budgets stay out of the model-facing schema (no `head_limit`/`offset`/`c ## Two budgets, two artifacts -Raw `rg` stdout is an internal transport detail. Each search requests a collect-mode stdout budget of `rawOutputMaxBytes` from the subprocess seam and parses only complete retained stdout; if the seam still reports a lossy read, the search fails with `SEARCH_RAW_OUTPUT_OVERFLOW` and tells the model to narrow the query. A successful `glob` keeps the displayed search root and every acquired path in `{ root, paths }`; when sampling is enabled, `root` lets the Native renderer group an explicit relative or absolute search path by entries beneath that root rather than by its workdir prefix. `grep` keeps every acquired `{ path, lineNumber, line }` in `{ matches }`. Inline item and per-line preview caps apply only in the Native renderer. For a direct surface call with more logical results than the inline cap, post-policy best-effort saves the complete formatted preview through `ctx.spillStore.saveText()` and replaces only presentation with the configured page plus locator. Nested Code dispatches skip that spill because their full canonical value does not enter model context. Missing/failed spill keeps the inline page and reports that the complete result could not be saved—never an `isError`. +Raw `rg` stdout and stderr are internal transport details. Each search requests collect-mode budgets from the subprocess seam — complete stdout within `rawOutputMaxBytes` and a `stderrMaxBytes` diagnostic tail — with no spill files on either stream (the tool never reads a raw spill path). If the seam still reports a lossy stdout read, the search fails with `SEARCH_RAW_OUTPUT_OVERFLOW` and tells the model to narrow the query; a lossy stderr read only marks the diagnostic excerpt `[stderr truncated]`. A successful `glob` keeps the displayed search root and every acquired path in `{ root, paths }`; when sampling is enabled, `root` lets the Native renderer group an explicit relative or absolute search path by entries beneath that root rather than by its workdir prefix. `grep` keeps every acquired `{ path, lineNumber, line }` in `{ matches }`. Inline item and per-line preview caps apply only in the Native renderer. For a direct surface call with more logical results than the inline cap, post-policy best-effort saves the complete formatted preview through `ctx.spillStore.saveText()` and replaces only presentation with the configured page plus locator. Nested Code dispatches skip that spill because their full canonical value does not enter model context. Missing/failed spill keeps the inline page and reports that the complete result could not be saved—never an `isError`. ## Errors diff --git a/packages/fs/tool-fs-search/README.zh.md b/packages/fs/tool-fs-search/README.zh.md index 69ce49f3ad..42b123d5c4 100644 --- a/packages/fs/tool-fs-search/README.zh.md +++ b/packages/fs/tool-fs-search/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -**面向模型的文件系统发现工具**（`glob`、`grep`）由 **打包的 ripgrep 二进制**（`@vscode/ripgrep`）支持，而不是由 `ctx.fs` 提供方方法或系统 `rg` 安装支持。注册是无条件的：二进制随 npm 依赖一起交付，因此没有加载期可用性探针。每次调用都通过 `ctx.subprocess` seam 以固定 argv 向量 spawn 该二进制（模型控制的值是普通 argv 元素——不存在 shell 层，因此无需引号），解析原始 `rg` 输出，并返回相对于工作目录的规范值。本包注入 `tools`、`systemPrompt` 和 `subprocess`，有意**不**注入 `fs`；格式化结果 spill 为可选功能，因此机会性读取 `ctx.spillStore`，调用方式为 `ctx.get()`。 +**面向模型的文件系统发现工具**（`glob`、`grep`）由 **打包的 ripgrep 二进制**（`@vscode/ripgrep`）支持，而不是由 `ctx.fs` 提供方方法或系统 `rg` 安装支持。注册是无条件的：二进制随 npm 依赖一起交付，因此没有加载期可用性探针。每次调用都通过 `ctx.subprocess` seam 以固定 argv 向量 spawn 该二进制（前缀 `--no-config`，使宿主的 `RIPGREP_CONFIG_PATH` 无法向不受约束的 spawn 注入 `--pre` 预处理器；模型控制的值是普通 argv 元素——不存在 shell 层，因此无需引号），解析原始 `rg` 输出，并返回相对于工作目录的规范值。本包注入 `tools`、`systemPrompt` 和 `subprocess`，有意**不**注入 `fs`；格式化结果 spill 为可选功能，因此机会性读取 `ctx.spillStore`，调用方式为 `ctx.get()`。 ```ts ignore-check // A deployment chooses how over-cap glob pages are selected. @@ -30,6 +30,8 @@ await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh- | `grepMaxLineBytes` | `2000` | 每条匹配行预览的字节上限；截断会保留 UTF-8 边界，并标记为 `(line truncated)`。 | | `rawOutputMaxBytes` | `20000000` | 搜索将解析的完整原始 `rg` stdout 上限（与 Claude Code 的 ripgrep 原始 buffer 相同）；更大的原始输出以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败。 | | `timeoutMs` | `30000` | 附加到两个工具定义上的协作式工具调用预算，由 `@deepseek-ai/dsh-timeout-policy` 通过 `exec.signal` 强制执行；subprocess seam 的终止升级提供硬终止。 | +| `graceMs` | `3000` | subprocess seam 在 `timeoutMs` 之外授予的终止升级宽限期；超过后搜索以 `SEARCH_ABORTED` 失败。 | +| `stderrMaxBytes` | `65536` | `rg` stderr 的诊断尾部预算，经 subprocess seam 的 collect 形态捕获；lossy 读取只保留尾部（标记 `[stderr truncated]`）。 | ## 工具 @@ -42,7 +44,7 @@ await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh- ## 两类预算、两类产物 -原始 `rg` stdout 是内部传输细节。每次搜索从 subprocess seam 请求 `rawOutputMaxBytes` 的 collect 模式 stdout 预算，且只解析完整保留的 stdout；如果 seam 仍报告 lossy 读取，搜索会以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败，并要求模型缩小查询。成功的 `glob` 在 `{ root, paths }` 中保留所显示的搜索根及所有已取得路径；启用采样时，借助 `root`，原生渲染器能以显式的相对或绝对搜索路径为根，按该根下的条目分组，而不是按其工作目录前缀分组。`grep` 保留所有已取得的 `{ path, lineNumber, line }`，并将其存入 `{ matches }`。内联条目和每行预览上限只应用于原生渲染器。直接接口调用的逻辑结果超过内联上限时，后置策略会尽力通过 `ctx.spillStore.saveText()` 保存完整格式化预览，并只把呈现替换为配置指定的页面与 locator。嵌套 Code 分派会跳过 spill，因为其完整规范值不会进入模型上下文。spill 缺失/失败时保留内联页面，并报告完整结果无法保存，绝不会成为 `isError`。 +原始 `rg` stdout 与 stderr 是内部传输细节。每次搜索从 subprocess seam 请求 collect 模式预算——`rawOutputMaxBytes` 内的完整 stdout 与 `stderrMaxBytes` 的诊断尾部——两条流都不产生 spill 文件（工具从不读取原始 spill 路径）。如果 seam 仍报告 lossy stdout 读取，搜索会以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败，并要求模型缩小查询；lossy stderr 读取只把诊断摘录标记为 `[stderr truncated]`。成功的 `glob` 在 `{ root, paths }` 中保留所显示的搜索根及所有已取得路径；启用采样时，借助 `root`，原生渲染器能以显式的相对或绝对搜索路径为根，按该根下的条目分组，而不是按其工作目录前缀分组。`grep` 保留所有已取得的 `{ path, lineNumber, line }`，并将其存入 `{ matches }`。内联条目和每行预览上限只应用于原生渲染器。直接接口调用的逻辑结果超过内联上限时，后置策略会尽力通过 `ctx.spillStore.saveText()` 保存完整格式化预览，并只把呈现替换为配置指定的页面与 locator。嵌套 Code 分派会跳过 spill，因为其完整规范值不会进入模型上下文。spill 缺失/失败时保留内联页面，并报告完整结果无法保存，绝不会成为 `isError`。 ## 错误 diff --git a/packages/fs/tool-fs-search/src/glob.ts b/packages/fs/tool-fs-search/src/glob.ts index 6e7d411a01..3eeea9c75c 100644 --- a/packages/fs/tool-fs-search/src/glob.ts +++ b/packages/fs/tool-fs-search/src/glob.ts @@ -47,6 +47,10 @@ export interface GlobToolCaps { maxMetaBytes: number /** Cap on the complete raw `rg` stdout the tool will parse. */ rawOutputMaxBytes: number + /** Terminate-escalation grace period (ms) for the search process. */ + graceMs: number + /** Cap on the retained stderr diagnostic tail. */ + stderrMaxBytes: number /** Cooperative tool-call budget (ms) attached as `ToolDefinition.timeoutMs`. */ timeoutMs: number } @@ -337,7 +341,7 @@ export function applyGlobTool(ctx: Context, caps: GlobToolCaps): void { }, async execute(args, exec) { const input = parseGlobArgs(args) - const run = await runRipgrep(ctx, exec, 'glob', buildGlobCommand(input), caps.rawOutputMaxBytes) + const run = await runRipgrep(ctx, exec, 'glob', buildGlobCommand(input), caps.rawOutputMaxBytes, caps.graceMs, caps.stderrMaxBytes) const root = input.path === undefined ? '.' : toWorkdirRelative(input.path, run.workdir) if (run.noMatches) return { root, paths: [] } diff --git a/packages/fs/tool-fs-search/src/grep.ts b/packages/fs/tool-fs-search/src/grep.ts index 03b49f01e8..49548499ac 100644 --- a/packages/fs/tool-fs-search/src/grep.ts +++ b/packages/fs/tool-fs-search/src/grep.ts @@ -45,6 +45,10 @@ export interface GrepToolCaps { maxMetaBytes: number /** Cap on the complete raw `rg` stdout the tool will parse. */ rawOutputMaxBytes: number + /** Terminate-escalation grace period (ms) for the search process. */ + graceMs: number + /** Cap on the retained stderr diagnostic tail. */ + stderrMaxBytes: number /** Cooperative tool-call budget (ms) attached as `ToolDefinition.timeoutMs`. */ timeoutMs: number } @@ -265,7 +269,7 @@ export function presentGrepResult( * Register the `grep` tool and its system-prompt guidance. * * @param ctx - the plugin context; registrations are effects scoped to it, and - * execution uses its `bash` service. + * execution uses its `subprocess` service. * @param caps - the deployment's resolved grep caps (plugin config after defaulting). */ export function applyGrepTool(ctx: Context, caps: GrepToolCaps): void { @@ -315,7 +319,7 @@ export function applyGrepTool(ctx: Context, caps: GrepToolCaps): void { }, async execute(args, exec) { const input = parseGrepArgs(args) - const run = await runRipgrep(ctx, exec, 'grep', buildGrepCommand(input), caps.rawOutputMaxBytes) + const run = await runRipgrep(ctx, exec, 'grep', buildGrepCommand(input), caps.rawOutputMaxBytes, caps.graceMs, caps.stderrMaxBytes) if (run.noMatches) return { matches: [] } const all: GrepMatch[] = [] diff --git a/packages/fs/tool-fs-search/src/index.ts b/packages/fs/tool-fs-search/src/index.ts index e596ae3ca1..9a4042dde1 100644 --- a/packages/fs/tool-fs-search/src/index.ts +++ b/packages/fs/tool-fs-search/src/index.ts @@ -30,7 +30,7 @@ import type { Context } from 'cordis' import z from 'schemastery' import { GLOB_MAX_RESULTS, applyGlobTool } from './glob.ts' import { GREP_MAX_LINE_BYTES, GREP_MAX_MATCHES, applyGrepTool } from './grep.ts' -import { RAW_OUTPUT_MAX_BYTES, SEARCH_META_MAX_BYTES, SEARCH_TIMEOUT_MS } from './search-core.ts' +import { RAW_OUTPUT_MAX_BYTES, SEARCH_GRACE_MS, SEARCH_META_MAX_BYTES, SEARCH_STDERR_MAX_BYTES, SEARCH_TIMEOUT_MS } from './search-core.ts' export { GLOB_MAX_RESULTS, GLOB_VCS_EXCLUDES, applyGlobTool, buildGlobCommand, formatGlobOutput, parseGlobArgs, presentGlobCall, presentGlobResult, sampleAcrossTopLevel } from './glob.ts' export type { GlobInput, GlobSample, GlobToolCaps } from './glob.ts' @@ -49,7 +49,9 @@ export { export type { GrepInput, GrepToolCaps } from './grep.ts' export { RAW_OUTPUT_MAX_BYTES, + SEARCH_GRACE_MS, SEARCH_META_MAX_BYTES, + SEARCH_STDERR_MAX_BYTES, SEARCH_TIMEOUT_MS, SearchError, previewLine, @@ -58,7 +60,6 @@ export { trySaveFormattedResult, } from './search-core.ts' export type { GrepMatch, RipgrepRun, SearchErrorCode } from './search-core.ts' -export { singleQuote } from './shell-quote.ts' /** Cordis plugin name used by loader diagnostics. */ export const name = 'tool-fs-search' @@ -80,6 +81,10 @@ export interface Config { searchMetaMaxBytes?: number /** Max complete raw `rg` stdout bytes a search will parse; larger raw output fails with `SEARCH_RAW_OUTPUT_OVERFLOW`. */ rawOutputMaxBytes?: number + /** Terminate-escalation grace period (ms) for one search process, handed to the subprocess seam. */ + graceMs?: number + /** Max bytes retained for one search's stderr diagnostic tail (never surfaced to the model). */ + stderrMaxBytes?: number /** Cooperative tool-call timeout budget (ms) on both tools, enforced by `@deepseek-ai/dsh-timeout-policy` through `exec.signal`. */ timeoutMs?: number } @@ -91,6 +96,8 @@ export const Config: z = z.object({ grepMaxLineBytes: z.number().default(GREP_MAX_LINE_BYTES), searchMetaMaxBytes: z.number().default(SEARCH_META_MAX_BYTES), rawOutputMaxBytes: z.number().default(RAW_OUTPUT_MAX_BYTES), + graceMs: z.number().default(SEARCH_GRACE_MS), + stderrMaxBytes: z.number().default(SEARCH_STDERR_MAX_BYTES), timeoutMs: z.number().default(SEARCH_TIMEOUT_MS), }) @@ -121,12 +128,16 @@ export async function apply(ctx: Context, config: Config): Promise { assertPositiveInteger('grepMaxLineBytes', resolved.grepMaxLineBytes) assertPositiveInteger('searchMetaMaxBytes', resolved.searchMetaMaxBytes) assertPositiveInteger('rawOutputMaxBytes', resolved.rawOutputMaxBytes) + assertPositiveInteger('graceMs', resolved.graceMs) + assertPositiveInteger('stderrMaxBytes', resolved.stderrMaxBytes) assertPositiveInteger('timeoutMs', resolved.timeoutMs) applyGlobTool(ctx, { sampleOverCapGlobResults: resolved.sampleOverCapGlobResults, maxResults: resolved.globMaxResults, maxMetaBytes: resolved.searchMetaMaxBytes, rawOutputMaxBytes: resolved.rawOutputMaxBytes, + graceMs: resolved.graceMs, + stderrMaxBytes: resolved.stderrMaxBytes, timeoutMs: resolved.timeoutMs, }) applyGrepTool(ctx, { @@ -134,6 +145,8 @@ export async function apply(ctx: Context, config: Config): Promise { maxLineBytes: resolved.grepMaxLineBytes, maxMetaBytes: resolved.searchMetaMaxBytes, rawOutputMaxBytes: resolved.rawOutputMaxBytes, + graceMs: resolved.graceMs, + stderrMaxBytes: resolved.stderrMaxBytes, timeoutMs: resolved.timeoutMs, }) } diff --git a/packages/fs/tool-fs-search/src/search-core.ts b/packages/fs/tool-fs-search/src/search-core.ts index c9f5f80b5b..9444b029cc 100644 --- a/packages/fs/tool-fs-search/src/search-core.ts +++ b/packages/fs/tool-fs-search/src/search-core.ts @@ -44,15 +44,13 @@ export const SEARCH_TIMEOUT_MS = 30_000 /** * Default cap in bytes on the retained stderr tail of one search run — a - * diagnostic excerpt only (the tool never reads `stderr.spillPath`). + * diagnostic excerpt only (the tool never reads a stderr spill path, and the + * collect disposition requests none). */ -const SEARCH_STDERR_MAX_BYTES = 64 * 1024 - -/** Default whole-stream spill cap for search output (the subprocess seam requires an explicit budget). */ -const SEARCH_SPILL_MAX_BYTES = 64 * 1024 * 1024 +export const SEARCH_STDERR_MAX_BYTES = 64 * 1024 /** Default terminate grace period for a search process (ms). */ -const SEARCH_GRACE_MS = 3_000 +export const SEARCH_GRACE_MS = 3_000 /** * Default cap in bytes on one search's serialized `presentationMeta` (the @@ -110,7 +108,7 @@ export interface RipgrepRun { /** * The retained stderr tail as a diagnostic excerpt, with a truncation note when - * the subprocess seam dropped bytes (the tool never reads `stderr.spillPath`). + * the subprocess seam dropped bytes. */ function stderrExcerpt(stderrText: string, truncated: boolean): string { const text = stderrText.trim() @@ -118,15 +116,16 @@ function stderrExcerpt(stderrText: string, truncated: boolean): string { return truncated ? `${text} [stderr truncated]` : text } -/** Classify a nonzero-exit `rg` run into the search error vocabulary (invalid pattern vs missing `rg` vs everything else). */ +/** + * Classify a nonzero-exit `rg` run into the search error vocabulary. There is + * no shell layer, so an exit 127 or shell "command not found" text cannot + * occur — a launch failure rejects at spawn (see {@link runRipgrep}). + */ function classifyRunFailure(toolName: string, exitCode: number, stderrText: string, stderrTruncated: boolean): SearchError { const stderr = stderrExcerpt(stderrText, stderrTruncated) if (/regex parse error|error parsing glob/i.test(stderr)) { return new SearchError(`${toolName} pattern rejected by ripgrep: ${stderr}`, 'SEARCH_INVALID_PATTERN') } - if (exitCode === 127 || /command not found/i.test(stderr)) { - return new SearchError(`${toolName} requires ripgrep (rg) to launch${stderr.length > 0 ? `: ${stderr}` : ''}`, 'SEARCH_FAILED') - } return new SearchError(`${toolName} search failed (exit ${exitCode})${stderr.length > 0 ? `: ${stderr}` : ''}`, 'SEARCH_FAILED') } @@ -163,6 +162,13 @@ function completeStdout(toolName: string, stdout: SubprocessOutputRead, rawOutpu * (`@deepseek-ai/dsh-timeout-policy`) and caller cancellation terminate the * process tree. * + * The spawn is unconfined (a plain `ctx.subprocess` call), so `--no-config` + * is prepended: a host `RIPGREP_CONFIG_PATH` (or `rg.conf` next to the + * binary) can otherwise inject `--pre` and make ripgrep execute an arbitrary + * preprocessor for every matched file. The collect dispositions are the + * seam's diagnostic-tail shape (no spill files): the tools never read a raw + * spill path, and truncated stdout fails as `SEARCH_RAW_OUTPUT_OVERFLOW`. + * * Exit semantics are tool-owned: exit 0 is success with results, exit 1 is * success with zero results (`noMatches`), anything else throws a * {@link SearchError} (abort/timeout → `SEARCH_ABORTED`, invalid pattern → @@ -176,6 +182,8 @@ function completeStdout(toolName: string, stdout: SubprocessOutputRead, rawOutpu * @param toolName - `glob` or `grep`, used in error messages. * @param argv - the ripgrep arguments (every model value an unquoted argv element; no shell layer exists). * @param rawOutputMaxBytes - cap on the complete raw stdout the tool will parse. + * @param graceMs - the seam's terminate-escalation grace period. + * @param stderrMaxBytes - cap on the retained stderr diagnostic tail. * @returns the complete stdout, the zero-result flag, and the resolved workdir. */ export async function runRipgrep( @@ -184,6 +192,8 @@ export async function runRipgrep( toolName: string, argv: readonly string[], rawOutputMaxBytes: number, + graceMs: number, + stderrMaxBytes: number, ): Promise { if (exec.signal.aborted) { throw new SearchError(`${toolName} was aborted before completion (tool timeout or caller cancellation)`, 'SEARCH_ABORTED') @@ -191,16 +201,16 @@ export async function runRipgrep( const cwd = exec.agent?.session.header.cwd const workdir = cwd ?? process.cwd() const collect = (maxBytes: number): SubprocessCollect => - ({ maxBytes, spill: { maxBytes: SEARCH_SPILL_MAX_BYTES } }) + ({ maxBytes }) const handle = ctx.subprocess.spawn({ - argv: [rgPath, ...argv], + argv: [rgPath, '--no-config', ...argv], cwd: workdir, stdio: { stdin: 'ignore', stdout: collect(rawOutputMaxBytes), - stderr: collect(SEARCH_STDERR_MAX_BYTES), + stderr: collect(stderrMaxBytes), }, - graceMs: SEARCH_GRACE_MS, + graceMs, signal: exec.signal, } satisfies SubprocessSpawnSpec) let outcome: SubprocessOutcome diff --git a/packages/fs/tool-fs-search/src/shell-quote.ts b/packages/fs/tool-fs-search/src/shell-quote.ts deleted file mode 100644 index ea67abf449..0000000000 --- a/packages/fs/tool-fs-search/src/shell-quote.ts +++ /dev/null @@ -1,24 +0,0 @@ -/** - * POSIX single-quoting helper retained for compatibility with older - * deployments and tests. The current `glob`/`grep` command builders spawn the - * packaged ripgrep binary with a plain argv vector — no shell layer exists — - * so no quoting is involved; this module is kept because its export is part - * of the package surface. - * - * @module @deepseek-ai/dsh-tool-fs-search/shell-quote - */ - -/** - * POSIX single-quote a string for safe use as ONE shell word. Wraps the value - * in single quotes and rewrites every embedded single quote as `'\''` (close - * quote, an escaped literal quote, reopen quote). Inside single quotes the shell - * treats every other byte literally — spaces, newlines, `$`, backticks, `;`, - * `|`, `&`, glob metacharacters, and a leading `-` are all inert — so the result - * is a single, injection-safe argument regardless of the input. - * - * @param value - the raw, possibly model-controlled string to quote. - * @returns the value wrapped as one safe single-quoted shell word. - */ -export function singleQuote(value: string): string { - return `'${value.replaceAll("'", "'\\''")}'` -} diff --git a/packages/fs/tool-fs-search/tests/shell-quote.spec.ts b/packages/fs/tool-fs-search/tests/shell-quote.spec.ts deleted file mode 100644 index 84c8506be1..0000000000 --- a/packages/fs/tool-fs-search/tests/shell-quote.spec.ts +++ /dev/null @@ -1,59 +0,0 @@ -/** - * Unit tests for the shell-quoting safety boundary, plus a REAL round-trip: - * every adversarial value, quoted, must survive `bash -c "printf '%s' "` - * byte-for-byte — proving the quoting is inert in an actual shell, not just - * against a mental model of one. - */ - -import { describe, expect, it } from 'vitest' -import { spawnSync } from 'node:child_process' -import { singleQuote } from '@deepseek-ai/dsh-tool-fs-search' - -/** Adversarial values a model could pass as pattern / path / include. */ -const HOSTILE: readonly string[] = [ - 'plain', - 'with spaces', - "it's got 'quotes'", - '"double quoted"', - '$(rm -rf /tmp/nope)', - '`touch /tmp/nope`', - '$HOME and ${PATH}', - 'semi;colon && chain || pipe | bg &', - 'newline\nin the middle', - '-leading-dash', - '--leading-double-dash', - '*?[a-z]{x,y}', - '!bang', - '\\backslash\\', - '~tilde', - '# not a comment', - '>redirect &1', -] - -describe('singleQuote', () => { - it('wraps a plain value in single quotes', () => { - expect(singleQuote('abc')).toBe("'abc'") - }) - - it("rewrites embedded single quotes as '\\''", () => { - expect(singleQuote("a'b")).toBe("'a'\\''b'") - expect(singleQuote("''")).toBe("''\\'''\\'''") - }) - - it.each(HOSTILE.map(value => [JSON.stringify(value), value] as const))( - 'round-trips %s through a real bash -c unchanged', - (_label, value) => { - const result = spawnSync('bash', ['-c', `printf '%s' ${singleQuote(value)}`], { encoding: 'utf8' }) - expect(result.status).toBe(0) - expect(result.stdout).toBe(value) - }, - ) - - it('a quoted command substitution does not execute (the world stays untouched)', () => { - const canary = `/tmp/dsh-quote-canary-${process.pid}` - const result = spawnSync('bash', ['-c', `printf '%s' ${singleQuote(`$(touch ${canary})`)}`], { encoding: 'utf8' }) - expect(result.stdout).toBe(`$(touch ${canary})`) - // The canary file must NOT exist — the substitution stayed literal. - expect(spawnSync('test', ['-e', canary]).status).not.toBe(0) - }) -}) diff --git a/packages/fs/tool-fs-search/tests/tools.spec.ts b/packages/fs/tool-fs-search/tests/tools.spec.ts index d786fa3181..5c6713a7f0 100644 --- a/packages/fs/tool-fs-search/tests/tools.spec.ts +++ b/packages/fs/tool-fs-search/tests/tools.spec.ts @@ -291,6 +291,8 @@ describe('config validation', () => { ['grepMaxMatches', { grepMaxMatches: -1 }], ['grepMaxLineBytes', { grepMaxLineBytes: 1.5 }], ['rawOutputMaxBytes', { rawOutputMaxBytes: 0 }], + ['graceMs', { graceMs: 0 }], + ['stderrMaxBytes', { stderrMaxBytes: -1 }], ['timeoutMs', { timeoutMs: -100 }], ] as const)('rejects a non-positive or fractional %s at load', async (name, config) => { const ctx = new Context() @@ -372,16 +374,30 @@ describe('workdir derivation and signal forwarding', () => { expect(subprocess.spawns[1]?.cwd).toBe(process.cwd()) }) - it('spawns the packaged ripgrep binary with the fixed argv and budgeted collect streams', async () => { - const { ctx, subprocess } = await setup({ config: { rawOutputMaxBytes: 1234 } }) + it('spawns the packaged ripgrep binary with --no-config, the fixed argv, and budgeted collect streams', async () => { + const { ctx, subprocess } = await setup({ + config: { rawOutputMaxBytes: 1234, graceMs: 5000, stderrMaxBytes: 4096 }, + }) subprocess.handler = () => runResult('', { exitCode: 1 }) await call(ctx, 'grep', { pattern: 'needle' }) const spec = subprocess.spawns[0] - expect(spec?.argv[0]).toBe(rgPath) - expect(spec?.argv).toEqual([rgPath, '--json', '--regexp=needle']) + // --no-config keeps a host RIPGREP_CONFIG_PATH from injecting a + // preprocessor into this unconfined spawn. + expect(spec?.argv).toEqual([rgPath, '--no-config', '--json', '--regexp=needle']) expect(spec?.stdio.stdin).toBe('ignore') - // stdout gets the tool's parse budget; stderr is a diagnostic excerpt. + // stdout gets the tool's parse budget; stderr is a diagnostic excerpt; + // both are the seam's diagnostic-tail shape (no spill files requested). expect((spec?.stdio.stdout as { maxBytes: number }).maxBytes).toBe(1234) + expect((spec?.stdio.stderr as { maxBytes: number }).maxBytes).toBe(4096) + expect(spec?.graceMs).toBe(5_000) + }) + + it('defaults the stderr tail budget and grace period when the config omits them', async () => { + const { ctx, subprocess } = await setup() + subprocess.handler = () => runResult('', { exitCode: 1 }) + await call(ctx, 'grep', { pattern: 'needle' }) + const spec = subprocess.spawns[0] + expect((spec?.stdio.stderr as { maxBytes: number }).maxBytes).toBe(64 * 1024) expect(spec?.graceMs).toBe(3_000) }) @@ -430,7 +446,7 @@ describe('workdir derivation and signal forwarding', () => { const controller = new AbortController() controller.abort() const exec = { signal: controller.signal, name: 'glob', callId: CallId('direct-pre-abort') } as unknown as ToolExecution - await expect(runRipgrep(ctx, exec, 'glob', ['--files'], 1_000_000)).rejects + await expect(runRipgrep(ctx, exec, 'glob', ['--files'], 1_000_000, 3_000, 64 * 1024)).rejects .toMatchObject({ name: 'SearchError', code: 'SEARCH_ABORTED' }) }) @@ -489,20 +505,6 @@ describe('exit semantics and failure classification', () => { expect(result.error).toMatchObject({ info: { code: 'SEARCH_INVALID_PATTERN' } }) }) - it('a failed ripgrep launch classifies as SEARCH_FAILED naming ripgrep', async () => { - const { ctx, subprocess } = await setup() - subprocess.handler = () => runResult('', { exitCode: 127, stderr: { text: 'sh: rg: command not found' } }) - const result = await call(ctx, 'glob', { pattern: '*' }) - expect(result.error).toMatchObject({ info: { code: 'SEARCH_FAILED' } }) - expect(text(result)).toContain('requires ripgrep (rg)') - // The same classification holds from either evidence alone: the 127 exit - // with silent stderr, or a shell's command-not-found text on another exit. - subprocess.handler = () => runResult('', { exitCode: 127 }) - expect(text(await call(ctx, 'glob', { pattern: '*' }))).toContain('requires ripgrep (rg)') - subprocess.handler = () => runResult('', { exitCode: 2, stderr: { text: 'sh: rg: command not found' } }) - expect(text(await call(ctx, 'grep', { pattern: 'x' }))).toContain('requires ripgrep (rg)') - }) - it('other nonzero exits are SEARCH_FAILED carrying the stderr excerpt', async () => { const { ctx, subprocess } = await setup() subprocess.handler = () => runResult('', { exitCode: 2, stderr: { text: 'rg: missing.dir: IO error: no such file or directory' } }) @@ -682,7 +684,7 @@ describe('glob results', () => { subprocess.handler = () => runResult('sub/a.ts\n') const result = await call(ctx, 'glob', { pattern: '*.ts', path: 'sub' }) expect(result.isError).toBe(false) - expect(subprocess.spawns[0]?.argv).toEqual([rgPath, '--files', '--glob=*.ts', '--sort=modified', '--no-ignore', '--hidden', + expect(subprocess.spawns[0]?.argv).toEqual([rgPath, '--no-config', '--files', '--glob=*.ts', '--sort=modified', '--no-ignore', '--hidden', '--glob=!**/.git', '--glob=!**/.git/**', '--glob=!**/.svn', '--glob=!**/.svn/**', '--glob=!**/.hg', '--glob=!**/.hg/**', From d22438e2b19ead2b14fae5bed5c788d2f9a5f036 Mon Sep 17 00:00:00 2001 From: Huanqi Cao Date: Sat, 1 Aug 2026 21:56:32 +0800 Subject: [PATCH 10/45] test(fs-search): re-record the glob-sampling snapshot against the real API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The scenario previously carried an authored fixture; W4 of #1119 review requires a live transcript. Recording surfaced two composition bugs that are fixed here alongside it: - provider ids: the app and the replay catalog both named the old 'deepseek' provider, which no adapter registers; both now use 'deepseek-official' - the live config lacked persistenceCompression: none, so record-mode sessions were written zstd-compressed and could not be harvested (the snapshot twin already forced plaintext) Recorded logs also need deterministic replay: - packChunks: false in both configs — the eager-drain batch boundaries that split packed delta runs are timing-dependent, so a packed log of a long reasoning stream cannot replay-match its live record - the fixture's request/header config and request/context are normalized to the replay-produced minimal shape (the live adapter logs model capabilities llm-replay has no data for), and tool-result path separators are canonicalized to '/' for the Linux golden posixOnly is restored now that the fixture is recorded. --- examples/acp-agent/tests/acp.snapshot.ts | 13 +- .../tests/fs-search.cordis.snapshot.yml | 8 +- examples/acp-agent/tests/fs-search.cordis.yml | 7 +- .../snapshots/fs-glob-sampling/session.jsonl | 145 +++++++++++++++--- 4 files changed, 142 insertions(+), 31 deletions(-) diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 277d0b20ca..abdf10e367 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -181,16 +181,23 @@ const SCENARIOS: Scenario[] = [ // `--sort=modified` order, pinning over-cap glob sampling without depending // on a host-installed ripgrep binary or a PATH stand-in. POSIX-only because // the displayed paths carry `/` separators the session-log comparison - // cannot normalize. + // cannot normalize. Recorded (not authored): the assistant turn is a real + // model transcript; re-record with `test:snapshot:record -t fs-glob-sampling`. + // The composition disables packed chunk rows (fs-search.cordis.yml), whose + // run boundaries depend on eager-drain timing, and the recorded fixture's + // `request/header` config and `request/context` are normalized to the + // replay-produced minimal shape (the live adapter logs model capabilities + // like maxTokens/reasoningEffort that llm-replay has no data for), and its + // tool-result paths are canonicalized to `/` separators. { name: 'fs-glob-sampling', hasModelTurn: true, - recorded: false, + recorded: true, + posixOnly: true, pinsHeader: true, headerClass: 'fs-search', configPath: FS_SEARCH_CONFIG, prepareWorkspace: prepareFsSearchWorkspace, - posixOnly: true, }, { name: 'fs-read', hasModelTurn: true, recorded: true }, { name: 'fs-write', hasModelTurn: true, recorded: true }, diff --git a/examples/acp-agent/tests/fs-search.cordis.snapshot.yml b/examples/acp-agent/tests/fs-search.cordis.snapshot.yml index 141691a087..5fcb2248f3 100644 --- a/examples/acp-agent/tests/fs-search.cordis.snapshot.yml +++ b/examples/acp-agent/tests/fs-search.cordis.snapshot.yml @@ -3,7 +3,7 @@ name: '@deepseek-ai/dsh-llm-replay' config: providers: - - id: deepseek + - id: deepseek-official name: DeepSeek models: - id: deepseek-v4-pro @@ -17,10 +17,14 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-demo' config: - provider: deepseek + provider: deepseek-official model: deepseek-v4-pro persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' persistenceCompression: none + # Unpacked rows: the eager-drain batch boundaries that split packed delta + # runs are timing-dependent, so packed logs cannot replay-match a live + # record of a long reasoning stream. + packChunks: false workspaceContext: false skills: enabled: false diff --git a/examples/acp-agent/tests/fs-search.cordis.yml b/examples/acp-agent/tests/fs-search.cordis.yml index 153128f914..0f6d5d9a63 100644 --- a/examples/acp-agent/tests/fs-search.cordis.yml +++ b/examples/acp-agent/tests/fs-search.cordis.yml @@ -16,9 +16,14 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-demo' config: - provider: deepseek + provider: deepseek-official model: deepseek-v4-pro persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' + persistenceCompression: !!js "process.env.DSH_SNAPSHOT === undefined ? 'zstd' : 'none'" + # Unpacked rows: the eager-drain batch boundaries that split packed delta + # runs are timing-dependent, so packed logs cannot replay-match a live + # record of a long reasoning stream. + packChunks: false workspaceContext: false skills: enabled: false diff --git a/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl b/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl index ca51259632..f1c26ca911 100644 --- a/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl @@ -1,25 +1,120 @@ -{"type":"session","version":0,"id":"f5a99d52-3eaa-4ce7-858d-61d4fd77df2a","createdAt":1785218400000,"cwd":"{{cwd}}","delegationDepth":0} -{"type":"turn/start","seq":0,"time":1785218400001,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1785218400002,"data":{"content":[{"type":"text","text":"Call glob exactly once with pattern * and path tree. Then reply with exactly GLOB_SAMPLED and nothing else."}],"source":{"kind":"user"},"role":"user","id":"6790985f-1de2-42f8-a7f1-24e46d6439c7"},"surfaceOp":"append"} -{"type":"session/title","seq":2,"time":1785218400003,"data":{"title":"Call glob exactly once with","messageSeqs":[1],"source":{"kind":"fallback"}}} -{"type":"step/start","seq":3,"time":1785218400004,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1785218400005,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"request/context","seq":5,"time":1785483397569,"data":{"provider":"deepseek","model":"deepseek-v4-pro"}} -{"type":"assistant/chunk","seq":6,"time":1785218400007,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":7,"time":1785218400008,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"glob-sampling-call","name":"glob","argumentsDelta":"{\"pattern\":\"*\",\"path\":\"tree\"}"}}} -{"type":"assistant/chunk","seq":8,"time":1785218400009,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\",\"path\":\"tree\"}"}}}} -{"type":"assistant/chunk","seq":9,"time":1785218400010,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1,"outputTokens":1}}}} -{"type":"assistant/chunk","seq":10,"time":1785483397579,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":11,"time":1785483397579,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\",\"path\":\"tree\"}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-pro"},"id":"a127cfe5-39fb-462c-8e5a-a8c79bd0e52b"},"usage":{"inputTokens":1,"outputTokens":1}},"sourceEventSeqs":[6,7,8,9,10],"surfaceOp":"append"} -{"type":"tool/call","seq":12,"time":1785483397579,"data":{"turn":1,"step":1,"callId":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\",\"path\":\"tree\"}"}} -{"type":"tool/result","seq":13,"time":1785483398062,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"glob-sampling-call"},"content":[{"type":"tool-result","toolCallId":"glob-sampling-call","content":[{"type":"text","text":"tree/archive/a.ts\ntree/docs/guide.md\ntree/src/index.ts\ntree/test/spec.ts\n\n(Showing 4 of 8 paths, sampled across 4 of the 6 top-level entries this pattern matched instead of taken in modification-time order. Narrow path to inspect a specific subtree. The complete result could not be saved; narrow pattern or path to see more.)"}],"isError":false}],"role":"user","id":"2beecb2e-627d-43dc-a936-03e1dc874093"},"meta":{"shape":"paths","paths":["tree/archive/a.ts","tree/docs/guide.md","tree/src/index.ts","tree/test/spec.ts"],"truncated":true,"total":8}},"sourceEventSeqs":[12],"surfaceOp":"append"} -{"type":"step/end","seq":14,"time":1785483398062,"data":{"turn":1,"step":1}} -{"type":"step/start","seq":15,"time":1785483398072,"data":{"turn":1,"step":2}} -{"type":"assistant/chunk","seq":16,"time":1785218400017,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} -{"type":"assistant/chunk","seq":17,"time":1785218400018,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"GLOB_SAMPLED"}}} -{"type":"assistant/chunk","seq":18,"time":1785218400019,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GLOB_SAMPLED"}}}} -{"type":"assistant/chunk","seq":19,"time":1785218400020,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":1,"outputTokens":1}}}} -{"type":"assistant/chunk","seq":20,"time":1785483398078,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":21,"time":1785483398078,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"GLOB_SAMPLED"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-pro"},"id":"ce2334a4-be71-490b-a502-29186a9ced5c"},"usage":{"inputTokens":1,"outputTokens":1}},"sourceEventSeqs":[16,17,18,19,20],"surfaceOp":"append"} -{"type":"step/end","seq":22,"time":1785483398078,"data":{"turn":1,"step":2}} -{"type":"turn/end","seq":23,"time":1785483398079,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"4428b809-66d5-4ea2-9a03-89de742fcda1","createdAt":1785591986068,"cwd":"{{cwd}}","delegationDepth":0} +{"type":"turn/start","seq":0,"time":1785591986072,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1785591986073,"data":{"content":[{"type":"text","text":"Call glob exactly once with pattern * and path tree. Then reply with exactly GLOB_SAMPLED and nothing else."}],"source":{"kind":"user"},"role":"user","id":"3d05fb76-4185-460b-9c6a-8c1b2495bc9f"},"surfaceOp":"append"} +{"type":"session/title","seq":2,"time":1785591986074,"data":{"title":"Call glob exactly once with","messageSeqs":[1],"source":{"kind":"fallback"}}} +{"type":"step/start","seq":3,"time":1785591986092,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":4,"time":1785591986093,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/context","seq":5,"time":1785591986094,"data":{"provider":"deepseek-official","model":"deepseek-v4-pro"}} +{"type":"assistant/chunk","seq":6,"time":1785591987500,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":7,"time":1785591987500,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":8,"time":1785591987529,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":9,"time":1785591987587,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":10,"time":1785591987588,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":11,"time":1785591987588,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":12,"time":1785591987588,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" call"}}} +{"type":"assistant/chunk","seq":13,"time":1785591987588,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" glob"}}} +{"type":"assistant/chunk","seq":14,"time":1785591987639,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":15,"time":1785591987639,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" once"}}} +{"type":"assistant/chunk","seq":16,"time":1785591987639,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":17,"time":1785591987685,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" pattern"}}} +{"type":"assistant/chunk","seq":18,"time":1785591987685,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" *"}}} +{"type":"assistant/chunk","seq":19,"time":1785591987876,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":20,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" path"}}} +{"type":"assistant/chunk","seq":21,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tree"}}} +{"type":"assistant/chunk","seq":22,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":23,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":24,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":25,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":26,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":27,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":28,"time":1785591987878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"G"}}} +{"type":"assistant/chunk","seq":29,"time":1785591987878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"LOB"}}} +{"type":"assistant/chunk","seq":30,"time":1785591987878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_S"}}} +{"type":"assistant/chunk","seq":31,"time":1785591987878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AM"}}} +{"type":"assistant/chunk","seq":32,"time":1785591987878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"PL"}}} +{"type":"assistant/chunk","seq":33,"time":1785591987878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ED"}}} +{"type":"assistant/chunk","seq":34,"time":1785591987977,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":35,"time":1785591988034,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":36,"time":1785591988035,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":37,"time":1785591988090,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":38,"time":1785591988090,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":39,"time":1785591988090,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"pattern"}}} +{"type":"assistant/chunk","seq":40,"time":1785591988091,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":41,"time":1785591988136,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":42,"time":1785591988136,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":43,"time":1785591988136,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"*"}}} +{"type":"assistant/chunk","seq":44,"time":1785591988193,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":45,"time":1785591988207,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":46,"time":1785591988207,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":47,"time":1785591988207,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"path"}}} +{"type":"assistant/chunk","seq":48,"time":1785591988207,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":49,"time":1785591988207,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":50,"time":1785591988284,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":51,"time":1785591988284,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"tree"}}} +{"type":"assistant/chunk","seq":52,"time":1785591988284,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":53,"time":1785591988338,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":54,"time":1785591988427,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to call glob exactly once with pattern * and path tree, then reply with exactly \"GLOB_SAMPLED\"."}}}} +{"type":"assistant/chunk","seq":55,"time":1785591988427,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","arguments":"{\"pattern\": \"*\", \"path\": \"tree\"}"}}}} +{"type":"assistant/chunk","seq":56,"time":1785591988427,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1286,"outputTokens":87,"cacheReadTokens":0,"reasoningTokens":28}}}} +{"type":"assistant/chunk","seq":57,"time":1785591988427,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":58,"time":1785591988430,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to call glob exactly once with pattern * and path tree, then reply with exactly \"GLOB_SAMPLED\"."},{"type":"tool-call","id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","arguments":"{\"pattern\": \"*\", \"path\": \"tree\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"b74cbab2-c017-4e44-8c09-a7745d8b274a"},"usage":{"inputTokens":1286,"outputTokens":87,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} +{"type":"tool/call","seq":59,"time":1785591988431,"data":{"turn":1,"step":1,"callId":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","arguments":"{\"pattern\": \"*\", \"path\": \"tree\"}"}} +{"type":"tool/result","seq":60,"time":1785591988476,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_00_1cLZjkCW0vxVw0e3xVfh3430"},"content":[{"type":"tool-result","toolCallId":"call_00_1cLZjkCW0vxVw0e3xVfh3430","content":[{"type":"text","text":"tree/archive/a.ts\ntree/docs/guide.md\ntree/src/index.ts\ntree/test/spec.ts\n\n(Showing 4 of 8 paths, sampled across 4 of the 6 top-level entries this pattern matched instead of taken in modification-time order. Narrow path to inspect a specific subtree. The complete result could not be saved; narrow pattern or path to see more.)"}],"isError":false}],"role":"user","id":"10284f88-4890-49ed-9a17-56edbd6bfaa7"},"meta":{"shape":"paths","paths":["tree/archive/a.ts","tree/docs/guide.md","tree/src/index.ts","tree/test/spec.ts"],"truncated":true,"total":8}},"sourceEventSeqs":[59],"surfaceOp":"append"} +{"type":"step/end","seq":61,"time":1785591988476,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":62,"time":1785591988482,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":63,"time":1785591989939,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":64,"time":1785591989939,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":65,"time":1785591989939,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" glob"}}} +{"type":"assistant/chunk","seq":66,"time":1785591989939,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} +{"type":"assistant/chunk","seq":67,"time":1785591989939,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" shows"}}} +{"type":"assistant/chunk","seq":68,"time":1785591989988,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":69,"time":1785591990024,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} +{"type":"assistant/chunk","seq":70,"time":1785591990127,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sampled"}}} +{"type":"assistant/chunk","seq":71,"time":1785591990128,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" -"}}} +{"type":"assistant/chunk","seq":72,"time":1785591990128,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" "}}} +{"type":"assistant/chunk","seq":73,"time":1785591990128,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"4"}}} +{"type":"assistant/chunk","seq":74,"time":1785591990454,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" of"}}} +{"type":"assistant/chunk","seq":75,"time":1785591990454,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" "}}} +{"type":"assistant/chunk","seq":76,"time":1785591990454,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"8"}}} +{"type":"assistant/chunk","seq":77,"time":1785591990454,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" paths"}}} +{"type":"assistant/chunk","seq":78,"time":1785591990454,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" across"}}} +{"type":"assistant/chunk","seq":79,"time":1785591990454,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" "}}} +{"type":"assistant/chunk","seq":80,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"4"}}} +{"type":"assistant/chunk","seq":81,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" of"}}} +{"type":"assistant/chunk","seq":82,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" "}}} +{"type":"assistant/chunk","seq":83,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"6"}}} +{"type":"assistant/chunk","seq":84,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" top"}}} +{"type":"assistant/chunk","seq":85,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"-level"}}} +{"type":"assistant/chunk","seq":86,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" entries"}}} +{"type":"assistant/chunk","seq":87,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":88,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":89,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} +{"type":"assistant/chunk","seq":90,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":91,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":92,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":93,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":94,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":95,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"G"}}} +{"type":"assistant/chunk","seq":96,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"LOB"}}} +{"type":"assistant/chunk","seq":97,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_S"}}} +{"type":"assistant/chunk","seq":98,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"AM"}}} +{"type":"assistant/chunk","seq":99,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"PL"}}} +{"type":"assistant/chunk","seq":100,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ED"}}} +{"type":"assistant/chunk","seq":101,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":102,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} +{"type":"assistant/chunk","seq":103,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instructed"}}} +{"type":"assistant/chunk","seq":104,"time":1785591990470,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":105,"time":1785591990470,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":106,"time":1785591990470,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"G"}}} +{"type":"assistant/chunk","seq":107,"time":1785591990470,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"LOB"}}} +{"type":"assistant/chunk","seq":108,"time":1785591990470,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_S"}}} +{"type":"assistant/chunk","seq":109,"time":1785591990470,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"AM"}}} +{"type":"assistant/chunk","seq":110,"time":1785591990518,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"PL"}}} +{"type":"assistant/chunk","seq":111,"time":1785591990518,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ED"}}} +{"type":"assistant/chunk","seq":112,"time":1785591990526,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The glob result shows it was sampled - 4 of 8 paths across 4 of 6 top-level entries. I need to reply with exactly \"GLOB_SAMPLED\" as instructed."}}}} +{"type":"assistant/chunk","seq":113,"time":1785591990527,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"GLOB_SAMPLED"}}}} +{"type":"assistant/chunk","seq":114,"time":1785591990527,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":188,"outputTokens":48,"cacheReadTokens":1280,"reasoningTokens":41}}}} +{"type":"assistant/chunk","seq":115,"time":1785591990527,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":116,"time":1785591990527,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The glob result shows it was sampled - 4 of 8 paths across 4 of 6 top-level entries. I need to reply with exactly \"GLOB_SAMPLED\" as instructed."},{"type":"text","text":"GLOB_SAMPLED"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"dd3a9c28-43b2-4fdc-8089-1547309a71c0"},"usage":{"inputTokens":188,"outputTokens":48,"cacheReadTokens":1280,"reasoningTokens":41}},"sourceEventSeqs":[63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115],"surfaceOp":"append"} +{"type":"step/end","seq":117,"time":1785591990527,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":118,"time":1785591990528,"data":{"turn":1,"reason":{"kind":"completed"}}} From a27ca7b88f46d461a4549dba1d9d0272b785bd21 Mon Sep 17 00:00:00 2001 From: Huanqi Cao Date: Sat, 1 Aug 2026 22:34:16 +0800 Subject: [PATCH 11/45] test(fs-search): keep the glob-sampling fixture in canonical packed layout The session-fixture-layout gate requires every session JSONL fixture in the canonical packed layout (maximal delta runs per kind/block, as migrate:packed-session-fixtures rewrites); the packChunks: false knob violated that invariant and failed the snapshot job. Revert the knob and canonicalize the recorded fixture instead: the live log's eager-drain-packed rows migrate to the maximal-run layout a burst replay reproduces, so the fixture stays replay-deterministic and canonical. --- examples/acp-agent/tests/acp.snapshot.ts | 14 +-- .../tests/fs-search.cordis.snapshot.yml | 4 - examples/acp-agent/tests/fs-search.cordis.yml | 4 - .../snapshots/fs-glob-sampling/session.jsonl | 97 +------------------ 4 files changed, 11 insertions(+), 108 deletions(-) diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index abdf10e367..326a7ee0c0 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -182,13 +182,13 @@ const SCENARIOS: Scenario[] = [ // on a host-installed ripgrep binary or a PATH stand-in. POSIX-only because // the displayed paths carry `/` separators the session-log comparison // cannot normalize. Recorded (not authored): the assistant turn is a real - // model transcript; re-record with `test:snapshot:record -t fs-glob-sampling`. - // The composition disables packed chunk rows (fs-search.cordis.yml), whose - // run boundaries depend on eager-drain timing, and the recorded fixture's - // `request/header` config and `request/context` are normalized to the - // replay-produced minimal shape (the live adapter logs model capabilities - // like maxTokens/reasoningEffort that llm-replay has no data for), and its - // tool-result paths are canonicalized to `/` separators. + // model transcript; re-record with `test:snapshot:record -t fs-glob-sampling` + // and then `migrate:packed-session-fixtures`, which canonicalizes the live + // log's eager-drain-packed rows into the maximal-run layout replay produces. + // The recorded fixture's `request/header` config and `request/context` are + // normalized to the replay-produced minimal shape (the live adapter logs + // model capabilities like maxTokens/reasoningEffort that llm-replay has no + // data for), and its tool-result paths are canonicalized to `/` separators. { name: 'fs-glob-sampling', hasModelTurn: true, diff --git a/examples/acp-agent/tests/fs-search.cordis.snapshot.yml b/examples/acp-agent/tests/fs-search.cordis.snapshot.yml index 5fcb2248f3..0db692f5bd 100644 --- a/examples/acp-agent/tests/fs-search.cordis.snapshot.yml +++ b/examples/acp-agent/tests/fs-search.cordis.snapshot.yml @@ -21,10 +21,6 @@ model: deepseek-v4-pro persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' persistenceCompression: none - # Unpacked rows: the eager-drain batch boundaries that split packed delta - # runs are timing-dependent, so packed logs cannot replay-match a live - # record of a long reasoning stream. - packChunks: false workspaceContext: false skills: enabled: false diff --git a/examples/acp-agent/tests/fs-search.cordis.yml b/examples/acp-agent/tests/fs-search.cordis.yml index 0f6d5d9a63..c86b34b8aa 100644 --- a/examples/acp-agent/tests/fs-search.cordis.yml +++ b/examples/acp-agent/tests/fs-search.cordis.yml @@ -20,10 +20,6 @@ model: deepseek-v4-pro persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' persistenceCompression: !!js "process.env.DSH_SNAPSHOT === undefined ? 'zstd' : 'none'" - # Unpacked rows: the eager-drain batch boundaries that split packed delta - # runs are timing-dependent, so packed logs cannot replay-match a live - # record of a long reasoning stream. - packChunks: false workspaceContext: false skills: enabled: false diff --git a/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl b/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl index f1c26ca911..d85c0ea447 100644 --- a/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl @@ -6,53 +6,9 @@ {"type":"request/header","seq":4,"time":1785591986093,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":5,"time":1785591986094,"data":{"provider":"deepseek-official","model":"deepseek-v4-pro"}} {"type":"assistant/chunk","seq":6,"time":1785591987500,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":7,"time":1785591987500,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":8,"time":1785591987529,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":9,"time":1785591987587,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":10,"time":1785591987588,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":11,"time":1785591987588,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":12,"time":1785591987588,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" call"}}} -{"type":"assistant/chunk","seq":13,"time":1785591987588,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" glob"}}} -{"type":"assistant/chunk","seq":14,"time":1785591987639,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":15,"time":1785591987639,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" once"}}} -{"type":"assistant/chunk","seq":16,"time":1785591987639,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":17,"time":1785591987685,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" pattern"}}} -{"type":"assistant/chunk","seq":18,"time":1785591987685,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" *"}}} -{"type":"assistant/chunk","seq":19,"time":1785591987876,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":20,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" path"}}} -{"type":"assistant/chunk","seq":21,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tree"}}} -{"type":"assistant/chunk","seq":22,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":23,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} -{"type":"assistant/chunk","seq":24,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":25,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":26,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":27,"time":1785591987877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":28,"time":1785591987878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"G"}}} -{"type":"assistant/chunk","seq":29,"time":1785591987878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"LOB"}}} -{"type":"assistant/chunk","seq":30,"time":1785591987878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_S"}}} -{"type":"assistant/chunk","seq":31,"time":1785591987878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AM"}}} -{"type":"assistant/chunk","seq":32,"time":1785591987878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"PL"}}} -{"type":"assistant/chunk","seq":33,"time":1785591987878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ED"}}} -{"type":"assistant/chunk","seq":34,"time":1785591987977,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"reasoning-chunks","seq0":7,"time0":1785591987500,"data":{"turn":1,"step":1,"index":0,"dt":[29,58,1,0,0,0,51,0,0,46,0,191,1,0,0,0,0,0,0,0,1,0,0,0,0,0,99],"texts":["The"," user"," wants"," me"," to"," call"," glob"," exactly"," once"," with"," pattern"," *"," and"," path"," tree",","," then"," reply"," with"," exactly"," \"","G","LOB","_S","AM","PL","ED","\"."]}} {"type":"assistant/chunk","seq":35,"time":1785591988034,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":36,"time":1785591988035,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":37,"time":1785591988090,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":38,"time":1785591988090,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":39,"time":1785591988090,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"pattern"}}} -{"type":"assistant/chunk","seq":40,"time":1785591988091,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":41,"time":1785591988136,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":42,"time":1785591988136,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":43,"time":1785591988136,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"*"}}} -{"type":"assistant/chunk","seq":44,"time":1785591988193,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":45,"time":1785591988207,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":46,"time":1785591988207,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":47,"time":1785591988207,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"path"}}} -{"type":"assistant/chunk","seq":48,"time":1785591988207,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":49,"time":1785591988207,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":50,"time":1785591988284,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":51,"time":1785591988284,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"tree"}}} -{"type":"assistant/chunk","seq":52,"time":1785591988284,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":53,"time":1785591988338,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","argumentsDelta":"}"}}} +{"type":"tool-call-chunks","seq0":36,"time0":1785591988035,"data":{"turn":1,"step":1,"index":1,"dt":[55,0,0,1,45,0,0,57,14,0,0,0,0,77,0,0,54],"id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","args":["","{","\"","pattern","\"",": ","\"","*","\"",", ","\"","path","\"",": ","\"","tree","\"","}"]}} {"type":"assistant/chunk","seq":54,"time":1785591988427,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to call glob exactly once with pattern * and path tree, then reply with exactly \"GLOB_SAMPLED\"."}}}} {"type":"assistant/chunk","seq":55,"time":1785591988427,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_1cLZjkCW0vxVw0e3xVfh3430","name":"glob","arguments":"{\"pattern\": \"*\", \"path\": \"tree\"}"}}}} {"type":"assistant/chunk","seq":56,"time":1785591988427,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1286,"outputTokens":87,"cacheReadTokens":0,"reasoningTokens":28}}}} @@ -63,54 +19,9 @@ {"type":"step/end","seq":61,"time":1785591988476,"data":{"turn":1,"step":1}} {"type":"step/start","seq":62,"time":1785591988482,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":63,"time":1785591989939,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":64,"time":1785591989939,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":65,"time":1785591989939,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" glob"}}} -{"type":"assistant/chunk","seq":66,"time":1785591989939,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} -{"type":"assistant/chunk","seq":67,"time":1785591989939,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" shows"}}} -{"type":"assistant/chunk","seq":68,"time":1785591989988,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} -{"type":"assistant/chunk","seq":69,"time":1785591990024,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} -{"type":"assistant/chunk","seq":70,"time":1785591990127,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sampled"}}} -{"type":"assistant/chunk","seq":71,"time":1785591990128,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" -"}}} -{"type":"assistant/chunk","seq":72,"time":1785591990128,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" "}}} -{"type":"assistant/chunk","seq":73,"time":1785591990128,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"4"}}} -{"type":"assistant/chunk","seq":74,"time":1785591990454,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" of"}}} -{"type":"assistant/chunk","seq":75,"time":1785591990454,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" "}}} -{"type":"assistant/chunk","seq":76,"time":1785591990454,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"8"}}} -{"type":"assistant/chunk","seq":77,"time":1785591990454,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" paths"}}} -{"type":"assistant/chunk","seq":78,"time":1785591990454,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" across"}}} -{"type":"assistant/chunk","seq":79,"time":1785591990454,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" "}}} -{"type":"assistant/chunk","seq":80,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"4"}}} -{"type":"assistant/chunk","seq":81,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" of"}}} -{"type":"assistant/chunk","seq":82,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" "}}} -{"type":"assistant/chunk","seq":83,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"6"}}} -{"type":"assistant/chunk","seq":84,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" top"}}} -{"type":"assistant/chunk","seq":85,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"-level"}}} -{"type":"assistant/chunk","seq":86,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" entries"}}} -{"type":"assistant/chunk","seq":87,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":88,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":89,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} -{"type":"assistant/chunk","seq":90,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":91,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":92,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":93,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":94,"time":1785591990455,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":95,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"G"}}} -{"type":"assistant/chunk","seq":96,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"LOB"}}} -{"type":"assistant/chunk","seq":97,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_S"}}} -{"type":"assistant/chunk","seq":98,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"AM"}}} -{"type":"assistant/chunk","seq":99,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"PL"}}} -{"type":"assistant/chunk","seq":100,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ED"}}} -{"type":"assistant/chunk","seq":101,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":102,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} -{"type":"assistant/chunk","seq":103,"time":1785591990456,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instructed"}}} -{"type":"assistant/chunk","seq":104,"time":1785591990470,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"reasoning-chunks","seq0":64,"time0":1785591989939,"data":{"turn":1,"step":2,"index":0,"dt":[0,0,0,49,36,103,1,0,0,326,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,14],"texts":["The"," glob"," result"," shows"," it"," was"," sampled"," -"," ","4"," of"," ","8"," paths"," across"," ","4"," of"," ","6"," top","-level"," entries","."," I"," need"," to"," reply"," with"," exactly"," \"","G","LOB","_S","AM","PL","ED","\""," as"," instructed","."]}} {"type":"assistant/chunk","seq":105,"time":1785591990470,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":106,"time":1785591990470,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"G"}}} -{"type":"assistant/chunk","seq":107,"time":1785591990470,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"LOB"}}} -{"type":"assistant/chunk","seq":108,"time":1785591990470,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_S"}}} -{"type":"assistant/chunk","seq":109,"time":1785591990470,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"AM"}}} -{"type":"assistant/chunk","seq":110,"time":1785591990518,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"PL"}}} -{"type":"assistant/chunk","seq":111,"time":1785591990518,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ED"}}} +{"type":"text-chunks","seq0":106,"time0":1785591990470,"data":{"turn":1,"step":2,"index":1,"dt":[0,0,0,48,0],"texts":["G","LOB","_S","AM","PL","ED"]}} {"type":"assistant/chunk","seq":112,"time":1785591990526,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The glob result shows it was sampled - 4 of 8 paths across 4 of 6 top-level entries. I need to reply with exactly \"GLOB_SAMPLED\" as instructed."}}}} {"type":"assistant/chunk","seq":113,"time":1785591990527,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"GLOB_SAMPLED"}}}} {"type":"assistant/chunk","seq":114,"time":1785591990527,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":188,"outputTokens":48,"cacheReadTokens":1280,"reasoningTokens":41}}}} From 601fb9d1952ea07a6bba070ad1887c2b0890136e Mon Sep 17 00:00:00 2001 From: Huanqi Cao Date: Sun, 2 Aug 2026 01:11:08 +0800 Subject: [PATCH 12/45] fix(fs-search): address the second-round #1119 review - inline the collect() identity wrapper now that both streams use the seam's diagnostic-tail shape - resolve the packaged rg path lazily at the first call (memoized): @vscode/ripgrep resolves its platform package at module evaluation, so a static import turned a missing/corrupt platform package into a Loader composition failure instead of the documented per-call SEARCH_FAILED - classify synchronous spawn-creation throws (a NUL in argv, an abort racing the pre-check, a rejected resolution) into SEARCH_FAILED / SEARCH_ABORTED instead of leaking raw errors - correct the stderrMaxBytes contract: the stderr excerpt is embedded in SEARCH_* error messages, not hidden from the model - export virtualManifest and pin its three acceptance paths (prefix hit, pnpm-11 truncated-name content-scan fallback, both miss) with fixture unit tests Tests: rg-path.spec.ts (resolution failure + memoized rejection), tools.spec.ts spawn-creation classification, notices spec virtualManifest. --- ...26-08-01-packaged-ripgrep-search.i18n.yaml | 4 +- .../2026-08-01-packaged-ripgrep-search.md | 2 +- .../2026-08-01-packaged-ripgrep-search.zh.md | 2 +- docs/config-catalog.md | 4 +- packages/fs/tool-fs-search/src/index.ts | 3 +- packages/fs/tool-fs-search/src/search-core.ts | 70 ++++++++++++++----- .../fs/tool-fs-search/tests/rg-path.spec.ts | 37 ++++++++++ .../fs/tool-fs-search/tests/tools.spec.ts | 43 ++++++++++++ scripts/gen-third-party-notices.spec.ts | 57 ++++++++++++++- scripts/gen-third-party-notices.ts | 7 +- 10 files changed, 200 insertions(+), 29 deletions(-) create mode 100644 packages/fs/tool-fs-search/tests/rg-path.spec.ts diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml index 3647587fa5..f63372c8b4 100644 --- a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-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/architecture/2026-08-01-packaged-ripgrep-search.md -2026-08-01-packaged-ripgrep-search.md: 849cc0804a2081492297649ac8f13236e2ac60fe -2026-08-01-packaged-ripgrep-search.zh.md: 4381c3a8bca8e6bb9ab375ad352fec5a5ddb9f99 +2026-08-01-packaged-ripgrep-search.md: 7c515618a18b61bd90177a6fdf19bbd52e564209 +2026-08-01-packaged-ripgrep-search.zh.md: f2b1a12c737f772bff6a6c91c17f7453dbc89748 diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md index 849cc0804a..7c515618a1 100644 --- a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md @@ -12,7 +12,7 @@ The `glob`/`grep` tools ran through the bash executor seam, which made a system ## Decision -`@deepseek-ai/dsh-tool-fs-search` now runs the PACKAGED ripgrep binary (`@vscode/ripgrep`, an npm dependency whose optional platform packages ship the binary) through the `ctx.subprocess` seam: `runRipgrep()` spawns `rgPath` with a plain argv vector prefixed by `--no-config`, collect-mode stdout/stderr, `graceMs`, and `exec.signal` forwarded. There is no shell layer, so the shell-quoting boundary is gone from execution; the `singleQuote` helper and its shell-spawning tests are deleted with it. The raw streams request the seam's diagnostic-tail collect shape (no spill files — the tool never reads a raw spill path; a lossy stdout read fails as `SEARCH_RAW_OUTPUT_OVERFLOW`). The terminate grace and the stderr tail budget are validated `Config` fields (`graceMs` default 3000, `stderrMaxBytes` default 64 KiB), no longer inherited from bash-local's config. Registration is unconditional — the load-time `command -v rg` probe and the conditional registration decision are deleted, and with them the "rg not found" warning. The package injects `tools`, `systemPrompt`, and `subprocess`. +`@deepseek-ai/dsh-tool-fs-search` now runs the PACKAGED ripgrep binary (`@vscode/ripgrep`, an npm dependency whose optional platform packages ship the binary) through the `ctx.subprocess` seam: `runRipgrep()` spawns `rgPath` with a plain argv vector prefixed by `--no-config`, collect-mode stdout/stderr, `graceMs`, and `exec.signal` forwarded. `rgPath` resolves lazily at the first call (memoized per process): `@vscode/ripgrep` resolves its platform package at module evaluation, so a static import would turn a missing or corrupt platform package (`--omit=optional`, partial install) into a Loader-composition failure — the load-time failure mode this change exists to remove. There is no shell layer, so the shell-quoting boundary is gone from execution; the `singleQuote` helper and its shell-spawning tests are deleted with it. The raw streams request the seam's diagnostic-tail collect shape (no spill files — the tool never reads a raw spill path; a lossy stdout read fails as `SEARCH_RAW_OUTPUT_OVERFLOW`). The terminate grace and the stderr tail budget are validated `Config` fields (`graceMs` default 3000, `stderrMaxBytes` default 64 KiB), no longer inherited from bash-local's config. Registration is unconditional — the load-time `command -v rg` probe and the conditional registration decision are deleted, and with them the "rg not found" warning. The package injects `tools`, `systemPrompt`, and `subprocess`. Exit semantics stay tool-owned: exit 0 is success with results, exit 1 is a successful empty search, anything else classifies into the existing `SEARCH_*` vocabulary (invalid pattern, launch failure, signal kill, raw-output overflow). Timeout is the cooperative tool-call budget attached to the tool definitions: `@deepseek-ai/dsh-timeout-policy` aborts `exec.signal`, the subprocess seam's terminate escalation provides the hard kill, and the tool reports `SEARCH_ABORTED`. The working directory is the session header cwd when present, else `process.cwd()` — there is no executor config to default through anymore, so the tool owns the fallback. diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md index 4381c3a8bc..f2b1a12c73 100644 --- a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -`@deepseek-ai/dsh-tool-fs-search` 现在运行 PACKAGED（打包的）ripgrep 二进制（`@vscode/ripgrep`，一个 npm 依赖，其可选平台包随附二进制），经由 `ctx.subprocess` seam：`runRipgrep()` 以纯 argv 向量 spawn `rgPath`，向量前缀 `--no-config`，配以 collect 模式 stdout/stderr、`graceMs` 与转发的 `exec.signal`。不再有 shell 层，执行路径上的 shell 引号边界随之消失；`singleQuote` 工具与其 shell spawn 测试一并删除。原始流使用 seam 的诊断尾部 collect 形态（无 spill 文件——工具从不读取原始 spill 路径；lossy stdout 读取以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败）。终止宽限与 stderr 尾部预算成为经校验的 `Config` 字段（`graceMs` 默认 3000，`stderrMaxBytes` 默认 64 KiB），不再继承自 bash-local 的配置。注册变为无条件——加载期 `command -v rg` 探针与条件注册决策被删除，连同那条 "rg not found" 警告。本包注入 `tools`、`systemPrompt` 与 `subprocess`。 +`@deepseek-ai/dsh-tool-fs-search` 现在运行 PACKAGED（打包的）ripgrep 二进制（`@vscode/ripgrep`，一个 npm 依赖，其可选平台包随附二进制），经由 `ctx.subprocess` seam：`runRipgrep()` 以纯 argv 向量 spawn `rgPath`，向量前缀 `--no-config`，配以 collect 模式 stdout/stderr、`graceMs` 与转发的 `exec.signal`。`rgPath` 在首次调用时懒解析（进程内 memoize）：`@vscode/ripgrep` 在模块求值阶段解析其平台包，静态导入会把平台包缺失/损坏（`--omit=optional`、安装不全）变成 Loader 组合加载失败——这正是本次改动要消除的加载期失败模式。不再有 shell 层，执行路径上的 shell 引号边界随之消失；`singleQuote` 工具与其 shell spawn 测试一并删除。原始流使用 seam 的诊断尾部 collect 形态（无 spill 文件——工具从不读取原始 spill 路径；lossy stdout 读取以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败）。终止宽限与 stderr 尾部预算成为经校验的 `Config` 字段（`graceMs` 默认 3000，`stderrMaxBytes` 默认 64 KiB），不再继承自 bash-local 的配置。注册变为无条件——加载期 `command -v rg` 探针与条件注册决策被删除，连同那条 "rg not found" 警告。本包注入 `tools`、`systemPrompt` 与 `subprocess`。 退出语义仍由工具拥有：退出码 0 为有结果的成功，1 为成功的空搜索，其余归入既有 `SEARCH_*` 词汇（无效模式、启动失败、信号杀死、原始输出溢出）。超时是挂在工具定义上的协作式工具调用预算：`@deepseek-ai/dsh-timeout-policy` 中止 `exec.signal`，subprocess seam 的终止升级提供硬终止，工具报告 `SEARCH_ABORTED`。工作目录为会话 header cwd（存在时），否则为 `process.cwd()`——不再有执行器配置可供默认化，因此回退由工具自己拥有。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index a37e8da1c9..c568634985 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1735,14 +1735,14 @@ export interface Config { rawOutputMaxBytes?: number /** Terminate-escalation grace period (ms) for one search process, handed to the subprocess seam. */ graceMs?: number - /** Max bytes retained for one search's stderr diagnostic tail (never surfaced to the model). */ + /** Max bytes retained for one search's stderr tail; the excerpt is embedded in `SEARCH_*` error messages, never shown on success. */ stderrMaxBytes?: number /** Cooperative tool-call timeout budget (ms) on both tools, enforced by `@deepseek-ai/dsh-timeout-policy` through `exec.signal`. */ timeoutMs?: number } ``` -Source: [`packages/fs/tool-fs-search/src/index.ts:71`](../packages/fs/tool-fs-search/src/index.ts) +Source: [`packages/fs/tool-fs-search/src/index.ts:72`](../packages/fs/tool-fs-search/src/index.ts) ## `@deepseek-ai/dsh-tool-goal` diff --git a/packages/fs/tool-fs-search/src/index.ts b/packages/fs/tool-fs-search/src/index.ts index 9a4042dde1..7f8e43cb73 100644 --- a/packages/fs/tool-fs-search/src/index.ts +++ b/packages/fs/tool-fs-search/src/index.ts @@ -55,6 +55,7 @@ export { SEARCH_TIMEOUT_MS, SearchError, previewLine, + resolveRgPath, runRipgrep, toWorkdirRelative, trySaveFormattedResult, @@ -83,7 +84,7 @@ export interface Config { rawOutputMaxBytes?: number /** Terminate-escalation grace period (ms) for one search process, handed to the subprocess seam. */ graceMs?: number - /** Max bytes retained for one search's stderr diagnostic tail (never surfaced to the model). */ + /** Max bytes retained for one search's stderr tail; the excerpt is embedded in `SEARCH_*` error messages, never shown on success. */ stderrMaxBytes?: number /** Cooperative tool-call timeout budget (ms) on both tools, enforced by `@deepseek-ai/dsh-timeout-policy` through `exec.signal`. */ timeoutMs?: number diff --git a/packages/fs/tool-fs-search/src/search-core.ts b/packages/fs/tool-fs-search/src/search-core.ts index 9444b029cc..854c593190 100644 --- a/packages/fs/tool-fs-search/src/search-core.ts +++ b/packages/fs/tool-fs-search/src/search-core.ts @@ -21,11 +21,10 @@ import { isAbsolute, relative, sep } from 'node:path' import type { Context } from 'cordis' -import { rgPath } from '@vscode/ripgrep' import { HarnessError } from '@deepseek-ai/dsh-llm' import { ItemRetainer, TextRetainer } from '@deepseek-ai/dsh-retention' import type { RetainedItems } from '@deepseek-ai/dsh-retention' -import type { SubprocessCollect, SubprocessOutcome, SubprocessOutputRead, SubprocessSpawnSpec } from '@deepseek-ai/dsh-subprocess' +import type { SubprocessHandle, SubprocessOutcome, SubprocessOutputRead, SubprocessSpawnSpec } from '@deepseek-ai/dsh-subprocess' import type { SaveTextSpill, SpillRef } from '@deepseek-ai/dsh-spill' import type { ToolExecution } from '@deepseek-ai/dsh-tools' @@ -154,6 +153,26 @@ function completeStdout(toolName: string, stdout: SubprocessOutputRead, rawOutpu ) } +let rgPathPromise: Promise | undefined + +/** + * The packaged ripgrep binary path, resolved lazily once per process. + * + * `@vscode/ripgrep` resolves its platform package (`@vscode/ripgrep- + * -`) at module evaluation, so a static import would turn a missing or + * corrupt platform package (`pnpm install --omit=optional`, partial install) + * into a failure of the whole Loader composition. Resolving at the call + * boundary keeps that failure at the first search call as `SEARCH_FAILED` — + * the package's documented no-load-time-probe contract. + * + * @returns the packaged binary's absolute path; the memoized promise rejects + * when the platform package cannot be resolved. + */ +export function resolveRgPath(): Promise { + rgPathPromise ??= import('@vscode/ripgrep').then(module => module.rgPath) + return rgPathPromise +} + /** * Run the packaged ripgrep binary with a plain argv vector and return its * complete raw stdout. The working directory is the calling agent's session @@ -173,9 +192,12 @@ function completeStdout(toolName: string, stdout: SubprocessOutputRead, rawOutpu * success with zero results (`noMatches`), anything else throws a * {@link SearchError} (abort/timeout → `SEARCH_ABORTED`, invalid pattern → * `SEARCH_INVALID_PATTERN`, the rest → `SEARCH_FAILED` / - * `SEARCH_RAW_OUTPUT_OVERFLOW`). A spawn REJECTION — the seam's - * infrastructure failures — is translated into `SEARCH_FAILED` with the - * original as `cause`; a pre-aborted signal becomes `SEARCH_ABORTED`. + * `SEARCH_RAW_OUTPUT_OVERFLOW`). Both launch-time failure domains are + * classified: a synchronous throw at spawn CREATION (a NUL in argv, an abort + * racing the pre-check, a rejected `@vscode/ripgrep` resolution) and a + * rejection of `handle.done` (the seam's infrastructure failures) both become + * `SEARCH_FAILED` with the original as `cause` — an abort already observed by + * creation time becomes `SEARCH_ABORTED` instead. * * @param ctx - the plugin context; execution uses its `subprocess` service. * @param exec - the tool-execution context; supplies the session cwd and the abort signal. @@ -200,19 +222,31 @@ export async function runRipgrep( } const cwd = exec.agent?.session.header.cwd const workdir = cwd ?? process.cwd() - const collect = (maxBytes: number): SubprocessCollect => - ({ maxBytes }) - const handle = ctx.subprocess.spawn({ - argv: [rgPath, '--no-config', ...argv], - cwd: workdir, - stdio: { - stdin: 'ignore', - stdout: collect(rawOutputMaxBytes), - stderr: collect(stderrMaxBytes), - }, - graceMs, - signal: exec.signal, - } satisfies SubprocessSpawnSpec) + let handle: SubprocessHandle + try { + handle = ctx.subprocess.spawn({ + argv: [await resolveRgPath(), '--no-config', ...argv], + cwd: workdir, + stdio: { + stdin: 'ignore', + stdout: { maxBytes: rawOutputMaxBytes }, + stderr: { maxBytes: stderrMaxBytes }, + }, + graceMs, + signal: exec.signal, + } satisfies SubprocessSpawnSpec) + } catch (error: unknown) { + // Node's spawn() throws synchronously for a NUL in argv, and the local + // impl can throw synchronously when the signal aborts between the check + // above and this call (or when the platform-package resolution rejects). + // The static narrowing that proves this re-check "always false" cannot + // see AbortSignal state changes. + // oxlint-disable-next-line typescript/no-unnecessary-condition + if (exec.signal.aborted) { + throw new SearchError(`${toolName} was aborted before completion (tool timeout or caller cancellation)`, 'SEARCH_ABORTED') + } + throw new SearchError(`${toolName} could not start its search command (ripgrep launch failed)`, 'SEARCH_FAILED', { cause: error }) + } let outcome: SubprocessOutcome try { outcome = await handle.done diff --git a/packages/fs/tool-fs-search/tests/rg-path.spec.ts b/packages/fs/tool-fs-search/tests/rg-path.spec.ts new file mode 100644 index 0000000000..52888a3453 --- /dev/null +++ b/packages/fs/tool-fs-search/tests/rg-path.spec.ts @@ -0,0 +1,37 @@ +/** + * Failure-path tests for the lazy packaged-ripgrep resolution. The success + * path (the real `@vscode/ripgrep` module) is exercised throughout + * tools.spec.ts; here the module is mocked to throw at evaluation, proving a + * missing or corrupt platform package (`--omit=optional`, partial install) + * surfaces as a per-call `SEARCH_FAILED` — not a composition-load failure. + */ + +import { describe, expect, it, vi } from 'vitest' +import { Context } from 'cordis' +import { CallId } from '@deepseek-ai/dsh-llm' +import type { ToolExecution } from '@deepseek-ai/dsh-tools' +import { resolveRgPath, runRipgrep } from '@deepseek-ai/dsh-tool-fs-search' + +// Any access to the mocked module's surface throws — the shape a missing +// platform package produces at module evaluation. +vi.mock('@vscode/ripgrep', () => new Proxy({}, { + get() { + throw new Error('platform package @vscode/ripgrep-win32-x64 is not installed') + }, +})) + +describe('lazy packaged-ripgrep resolution', () => { + it('fails the first search call with SEARCH_FAILED instead of failing module load', async () => { + // The resolution rejects before any spawn, so no subprocess service is needed. + const controller = new AbortController() + const exec = { signal: controller.signal, name: 'glob', callId: CallId('missing-platform-package') } as unknown as ToolExecution + + await expect(runRipgrep(new Context(), exec, 'glob', ['--files'], 1_000_000, 3_000, 64 * 1024)) + .rejects.toMatchObject({ name: 'SearchError', code: 'SEARCH_FAILED' }) + }) + + it('keeps failing every subsequent call (the resolution is memoized)', async () => { + await expect(resolveRgPath()).rejects.toThrow(/platform package/) + await expect(resolveRgPath()).rejects.toThrow(/platform package/) + }) +}) diff --git a/packages/fs/tool-fs-search/tests/tools.spec.ts b/packages/fs/tool-fs-search/tests/tools.spec.ts index 5c6713a7f0..a8a2498c60 100644 --- a/packages/fs/tool-fs-search/tests/tools.spec.ts +++ b/packages/fs/tool-fs-search/tests/tools.spec.ts @@ -32,6 +32,7 @@ import { presentGrepCall, presentGrepResult, previewLine, + resolveRgPath, runRipgrep, sampleAcrossTopLevel, toWorkdirRelative, @@ -468,6 +469,48 @@ describe('workdir derivation and signal forwarding', () => { expect(text(result)).toContain('could not start') }) + it('classifies a synchronous spawn-creation throw as SEARCH_FAILED', async () => { + // Node's spawn() throws synchronously for a NUL in argv, and the local + // impl can throw synchronously for other invalid specs. Creation-time + // failures must join the error vocabulary instead of escaping raw. + const { ctx, subprocess } = await setup() + subprocess.handler = () => { throw new Error('spawn ERR_INVALID_ARG_VALUE') } + + const result = await call(ctx, 'grep', { pattern: 'x' }) + + expect(result.isError).toBe(true) + expect(result.error).toMatchObject({ info: { name: 'SearchError', code: 'SEARCH_FAILED' } }) + expect(text(result)).toContain('could not start') + }) + + it('classifies a synchronous spawn-creation throw after an abort as SEARCH_ABORTED', async () => { + // The local impl can throw synchronously when the signal aborts between + // the pre-spawn check and the spawn call; no process was launched, so the + // abort is the reportable cause. + const { ctx, subprocess } = await setup() + const controller = new AbortController() + subprocess.handler = () => { + controller.abort('timeout') + throw new Error('aborted during spawn') + } + + const result = await call(ctx, 'glob', { pattern: '*' }, { signal: controller.signal }) + + expect(result.isError).toBe(true) + expect(result.error).toMatchObject({ info: { name: 'SearchError', code: 'SEARCH_ABORTED' } }) + expect(text(result)).toContain('aborted before completion') + }) + + it('resolves the packaged ripgrep path lazily, once per process', async () => { + // The module must not touch @vscode/ripgrep at load (a missing platform + // package would otherwise fail the whole composition), and repeated + // resolution reuses the first result. The resolution-failure path is + // pinned separately in rg-path.spec.ts. + await setup() + expect(await resolveRgPath()).toBe(rgPath) + expect(resolveRgPath()).toBe(resolveRgPath()) + }) + it('rejects when the subprocess implementation drops a requested collect stream', async () => { const { ctx, subprocess } = await setup() subprocess.dropReaders = true diff --git a/scripts/gen-third-party-notices.spec.ts b/scripts/gen-third-party-notices.spec.ts index 707c30ff70..f31cca6879 100644 --- a/scripts/gen-third-party-notices.spec.ts +++ b/scripts/gen-third-party-notices.spec.ts @@ -1,7 +1,8 @@ -import { readdirSync, readFileSync } from 'node:fs' -import { resolve } from 'node:path' +import { mkdirSync, mkdtempSync, readdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs' +import { join, resolve } from 'node:path' +import { tmpdir } from 'node:os' import { describe, expect, it } from 'vitest' -import { collectPythonDependencies, isPermissive, type Manifest, manifestPatterns, parsePyprojectRequirements, parseVendoredRows, render, tierExternalDeps } from './gen-third-party-notices.ts' +import { collectPythonDependencies, isPermissive, type Manifest, manifestPatterns, parsePyprojectRequirements, parseVendoredRows, render, tierExternalDeps, virtualManifest } from './gen-third-party-notices.ts' const root = resolve(import.meta.dirname, '..') @@ -63,6 +64,56 @@ describe('tierExternalDeps', () => { }) }) +describe('virtualManifest', () => { + it('resolves a manifest from an ordinary prefix-matching store directory', () => { + const root = mkdtempSync(join(tmpdir(), 'dsh-notices-prefix-')) + try { + const name = '@scope/pkg' + const version = '1.0.0' + const store = join(root, 'store') + const manifestDir = join(store, `${name.replace('/', '+')}@${version}`, 'node_modules', name) + mkdirSync(manifestDir, { recursive: true }) + writeFileSync(join(manifestDir, 'package.json'), JSON.stringify({ name, version, license: 'MIT' })) + + expect(virtualManifest(store, name)).toMatchObject({ name, version, license: 'MIT' }) + } finally { + rmSync(root, { recursive: true, force: true }) + } + }) + + it('falls back to a content scan when pnpm 11 truncates the store directory name', () => { + const root = mkdtempSync(join(tmpdir(), 'dsh-notices-truncated-')) + try { + const name = '@scope/pkg' + const version = '2.0.0' + const store = join(root, 'store') + // The truncated name no longer starts with `@scope+pkg@`, so only the + // whole-store content scan can find the package. + const manifestDir = join(store, '@scope+pkg_9f1c2d3e4a5b6c7d8e9f0a1b2c3d4e5f', 'node_modules', name) + mkdirSync(manifestDir, { recursive: true }) + writeFileSync(join(manifestDir, 'package.json'), JSON.stringify({ name, version, license: 'Apache-2.0' })) + + expect(virtualManifest(store, name)).toMatchObject({ name, version, license: 'Apache-2.0' }) + } finally { + rmSync(root, { recursive: true, force: true }) + } + }) + + it('returns undefined when neither the prefix nor the content scan finds the package', () => { + const root = mkdtempSync(join(tmpdir(), 'dsh-notices-miss-')) + try { + const store = join(root, 'store') + const other = join(store, 'other-pkg@1.0.0', 'node_modules', 'other-pkg') + mkdirSync(other, { recursive: true }) + writeFileSync(join(other, 'package.json'), JSON.stringify({ name: 'other-pkg', version: '1.0.0' })) + + expect(virtualManifest(store, '@scope/missing')).toBeUndefined() + } finally { + rmSync(root, { recursive: true, force: true }) + } + }) +}) + describe('parseVendoredRows', () => { it('reads the committed vendor manifest table', () => { const rows = parseVendoredRows(readFileSync(resolve(root, 'vendor/README.md'), 'utf8')) diff --git a/scripts/gen-third-party-notices.ts b/scripts/gen-third-party-notices.ts index a4a1f4c343..6b790829d5 100644 --- a/scripts/gen-third-party-notices.ts +++ b/scripts/gen-third-party-notices.ts @@ -172,8 +172,13 @@ type VirtualManifest = Manifest & { license?: string; repository?: string | { ur * long names (a peer-suffixed name past the length limit becomes * `_`), so a content scan falls back over the whole store when * the prefix misses. + * + * @param virtual - the `.pnpm` virtual store directory to scan. + * @param name - the external package name, exactly as `node_modules` spells it. + * @returns the parsed manifest, or `undefined` when neither the prefix match + * nor the content scan finds the package's `package.json`. */ -function virtualManifest(virtual: string, name: string): VirtualManifest | undefined { +export function virtualManifest(virtual: string, name: string): VirtualManifest | undefined { const prefix = `${name.replace('/', '+')}@` const entry = readdirSync(virtual).find(dir => dir.startsWith(prefix)) if (entry !== undefined) { From 3c6583370f994f9e5454a2f71c40d0b09d72fd4b Mon Sep 17 00:00:00 2001 From: Huanqi Cao Date: Sun, 2 Aug 2026 11:25:51 +0800 Subject: [PATCH 13/45] fix(fs-search): platform-normalize sampling test paths The sampler and the workdir-relative display conversion group by node:path.sep, so the POSIX-style '/' literals in the cross-directory sampling cases collapse into per-path groups on Windows (every path its own top-level entry), turning the round-robin sample into a head. The same gap exists on master (its platform-separator fix predates these tests); normalize the literals through a platform helper instead, and keep the POSIX-backslash-as-filename case Windows-skipped as before. --- .../fs/tool-fs-search/tests/tools.spec.ts | 65 ++++++++++--------- 1 file changed, 36 insertions(+), 29 deletions(-) diff --git a/packages/fs/tool-fs-search/tests/tools.spec.ts b/packages/fs/tool-fs-search/tests/tools.spec.ts index a8a2498c60..9a8fa991ff 100644 --- a/packages/fs/tool-fs-search/tests/tools.spec.ts +++ b/packages/fs/tool-fs-search/tests/tools.spec.ts @@ -40,6 +40,13 @@ import { const testToolSignal = new AbortController().signal +/** + * Normalize a POSIX-style test path to the platform separator: the sampler and + * the workdir-relative display conversion group by `node:path.sep`, so + * `/`-literal paths would collapse into per-path groups on Windows. + */ +const w = (path: string): string => path.replaceAll('/', sep) + /** One scripted collect-mode stream, returned by `readFrom(0)` after settlement. */ interface ScriptedStream { text: string @@ -621,24 +628,24 @@ describe('raw output acquisition', () => { describe('cross-directory sampling', () => { it('gives every top-level entry a slot before any entry gets a second', () => { - const paths = ['v/a', 'v/b', 'v/c', 'v/d', 'src/e', 'guide/f'] + const paths = ['v/a', 'v/b', 'v/c', 'v/d', 'src/e', 'guide/f'].map(w) // The head of 3 would be all `v/`; the sample reaches all three entries. - expect(sampleAcrossTopLevel(paths, 3)).toEqual({ items: ['v/a', 'src/e', 'guide/f'], shown: 3, total: 3 }) + expect(sampleAcrossTopLevel(paths, 3)).toEqual({ items: ['v/a', 'src/e', 'guide/f'].map(w), shown: 3, total: 3 }) // Extra slots go round again — to the only entry with paths left — and the // page stays grouped by entry rather than interleaved. - expect(sampleAcrossTopLevel(paths, 5)).toEqual({ items: ['v/a', 'v/b', 'v/c', 'src/e', 'guide/f'], shown: 3, total: 3 }) + expect(sampleAcrossTopLevel(paths, 5)).toEqual({ items: ['v/a', 'v/b', 'v/c', 'src/e', 'guide/f'].map(w), shown: 3, total: 3 }) }) it('hands an exhausted entry the remaining slots go to entries that still have paths', () => { - const paths = ['solo/a', 'many/b', 'many/c', 'many/d'] - expect(sampleAcrossTopLevel(paths, 3)).toEqual({ items: ['solo/a', 'many/b', 'many/c'], shown: 2, total: 2 }) + const paths = ['solo/a', 'many/b', 'many/c', 'many/d'].map(w) + expect(sampleAcrossTopLevel(paths, 3)).toEqual({ items: ['solo/a', 'many/b', 'many/c'].map(w), shown: 2, total: 2 }) }) it('does not rescan exhausted entries while filling a skewed page', () => { const singletonCount = 12_500 const paths = [ - ...Array.from({ length: singletonCount }, (_, index) => `group-${index}/only`), - ...Array.from({ length: singletonCount }, (_, index) => `late/${index}`), + ...Array.from({ length: singletonCount }, (_, index) => `group-${index}${sep}only`), + ...Array.from({ length: singletonCount }, (_, index) => `late${sep}${index}`), ] expect(sampleAcrossTopLevel(paths, paths.length - 1)).toMatchObject({ shown: singletonCount + 1, @@ -648,15 +655,15 @@ describe('cross-directory sampling', () => { }, 500) it('reports the entries it could not reach when the page is smaller than the top level', () => { - const paths = ['a/1', 'b/1', 'c/1', 'd/1'] - expect(sampleAcrossTopLevel(paths, 2)).toEqual({ items: ['a/1', 'b/1'], shown: 2, total: 4 }) + const paths = ['a/1', 'b/1', 'c/1', 'd/1'].map(w) + expect(sampleAcrossTopLevel(paths, 2)).toEqual({ items: ['a/1', 'b/1'].map(w), shown: 2, total: 4 }) }) it('groups an absolute path by its first real name, not by its empty root segment', () => { // Paths outside the workdir stay absolute; without stripping the leading // separator every one of them would collapse into a single empty group. - expect(sampleAcrossTopLevel(['/out/a', '/out/b', '/away/c', '/away/d'], 2)) - .toEqual({ items: ['/out/a', '/away/c'], shown: 2, total: 2 }) + expect(sampleAcrossTopLevel(['/out/a', '/out/b', '/away/c', '/away/d'].map(w), 2)) + .toEqual({ items: ['/out/a', '/away/c'].map(w), shown: 2, total: 2 }) }) it('reproduces the modification-time-ordered head for a flat result', () => { @@ -669,15 +676,15 @@ describe('cross-directory sampling', () => { 'workspace/vendor/b.ts', 'workspace/source/c.ts', 'workspace/guides/d.md', - ], 3, 'workspace')).toEqual({ - items: ['workspace/vendor/a.ts', 'workspace/source/c.ts', 'workspace/guides/d.md'], + ].map(w), 3, 'workspace')).toEqual({ + items: ['workspace/vendor/a.ts', 'workspace/source/c.ts', 'workspace/guides/d.md'].map(w), shown: 3, total: 3, }) - expect(sampleAcrossTopLevel(['./vendor/a.ts', './src/b.ts'], 2, '.')) - .toEqual({ items: ['./vendor/a.ts', './src/b.ts'], shown: 2, total: 2 }) - expect(sampleAcrossTopLevel(['/vendor/a.ts', '/src/b.ts'], 2, '/')) - .toEqual({ items: ['/vendor/a.ts', '/src/b.ts'], shown: 2, total: 2 }) + expect(sampleAcrossTopLevel(['./vendor/a.ts', './src/b.ts'].map(w), 2, '.')) + .toEqual({ items: ['./vendor/a.ts', './src/b.ts'].map(w), shown: 2, total: 2 }) + expect(sampleAcrossTopLevel(['/vendor/a.ts', '/src/b.ts'].map(w), 2, w('/'))) + .toEqual({ items: ['/vendor/a.ts', '/src/b.ts'].map(w), shown: 2, total: 2 }) const rooted = [ ['root', 'a', 'one'].join(sep), ['root', 'a', 'two'].join(sep), @@ -685,8 +692,8 @@ describe('cross-directory sampling', () => { ] expect(sampleAcrossTopLevel(rooted, 2, 'root')) .toEqual({ items: [rooted[0], rooted[2]], shown: 2, total: 2 }) - expect(sampleAcrossTopLevel(['other/a.ts'], 1, 'src')) - .toEqual({ items: ['other/a.ts'], shown: 1, total: 1 }) + expect(sampleAcrossTopLevel(['other/a.ts'].map(w), 1, 'src')) + .toEqual({ items: ['other/a.ts'].map(w), shown: 1, total: 1 }) expect(sampleAcrossTopLevel(['src'], 1, 'src')) .toEqual({ items: ['src'], shown: 1, total: 1 }) }) @@ -767,9 +774,9 @@ describe('glob results', () => { // freshly-unpacked subtree first, and a head-of-3 reads like the entire // workspace. The sample reaches every top-level entry instead. const { ctx, subprocess } = await setup({ config: { globMaxResults: 3 } }) - subprocess.handler = () => runResult(['vendor/a.ts', 'vendor/b.ts', 'vendor/c.ts', 'src/d.ts', 'guide/e.md', 'top.txt'].join('\n')) + subprocess.handler = () => runResult(['vendor/a.ts', 'vendor/b.ts', 'vendor/c.ts', 'src/d.ts', 'guide/e.md', 'top.txt'].map(w).join('\n')) const result = await call(ctx, 'glob', { pattern: '*' }, { agent: agent('/w') }) - expect(text(result)).toBe('vendor/a.ts\nsrc/d.ts\nguide/e.md\n\n' + expect(text(result)).toBe(['vendor/a.ts', 'src/d.ts', 'guide/e.md'].map(w).join('\n') + '\n\n' + '(Showing 3 of 6 paths, sampled across 3 of the 4 top-level entries this pattern matched ' + 'instead of taken in modification-time order. Narrow path to inspect a specific subtree. ' + 'The complete result could not be saved; narrow pattern or path to see more.)') @@ -792,9 +799,9 @@ describe('glob results', () => { 'workspace/vendor/b.ts', 'workspace/source/c.ts', 'workspace/guides/d.md', - ].join('\n')) - const result = await call(ctx, 'glob', { pattern: '*', path: 'workspace' }, { agent: agent('/w') }) - expect(text(result)).toContain('workspace/vendor/a.ts\nworkspace/source/c.ts\nworkspace/guides/d.md') + ].map(w).join('\n')) + const result = await call(ctx, 'glob', { pattern: '*', path: w('workspace') }, { agent: agent('/w') }) + expect(text(result)).toContain(['workspace/vendor/a.ts', 'workspace/source/c.ts', 'workspace/guides/d.md'].map(w).join('\n')) expect(text(result)).toContain('sampled across 3 of the 3 top-level entries') }) @@ -805,17 +812,17 @@ describe('glob results', () => { '/w/workspace/vendor/b.ts', '/w/workspace/source/c.ts', '/w/workspace/guides/d.md', - ].join('\n')) - const result = await call(ctx, 'glob', { pattern: '*', path: '/w/workspace' }, { agent: agent('/w') }) - expect(text(result)).toContain('workspace/vendor/a.ts\nworkspace/source/c.ts\nworkspace/guides/d.md') + ].map(w).join('\n')) + const result = await call(ctx, 'glob', { pattern: '*', path: w('/w/workspace') }, { agent: agent(w('/w')) }) + expect(text(result)).toContain(['workspace/vendor/a.ts', 'workspace/source/c.ts', 'workspace/guides/d.md'].map(w).join('\n')) expect(text(result)).toContain('sampled across 3 of the 3 top-level entries') }) it('drops the narrowing hint when the sample reaches every top-level entry', async () => { const { ctx, subprocess } = await setup({ config: { globMaxResults: 3 } }) - subprocess.handler = () => runResult(['vendor/a.ts', 'vendor/b.ts', 'vendor/c.ts', 'src/d.ts'].join('\n')) + subprocess.handler = () => runResult(['vendor/a.ts', 'vendor/b.ts', 'vendor/c.ts', 'src/d.ts'].map(w).join('\n')) expect(text(await call(ctx, 'glob', { pattern: '*' }, { agent: agent('/w') }))) - .toBe('vendor/a.ts\nvendor/b.ts\nsrc/d.ts\n\n' + .toBe(['vendor/a.ts', 'vendor/b.ts', 'src/d.ts'].map(w).join('\n') + '\n\n' + '(Showing 3 of 4 paths, sampled across 2 of the 2 top-level entries this pattern matched ' + 'instead of taken in modification-time order. ' + 'The complete result could not be saved; narrow pattern or path to see more.)') From 998b80886b94504cc53f8230713c35d274f83ccd Mon Sep 17 00:00:00 2001 From: Huanqi Cao Date: Sun, 2 Aug 2026 11:26:06 +0800 Subject: [PATCH 14/45] fix(tool-str-replace-editor): platform-normalize listing assertion paths The view listing carries absolute display paths, so the POSIX-style 'node_modules_old/kept.js' substring assertions only match on Linux (Windows display paths use backslashes). Assert with platform separators to keep the same check meaningful on Windows; the pre-existing gap is identical on master. --- packages/fs/tool-str-replace-editor/tests/tools.spec.ts | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/packages/fs/tool-str-replace-editor/tests/tools.spec.ts b/packages/fs/tool-str-replace-editor/tests/tools.spec.ts index 797263897f..4fda9a2d3f 100644 --- a/packages/fs/tool-str-replace-editor/tests/tools.spec.ts +++ b/packages/fs/tool-str-replace-editor/tests/tools.spec.ts @@ -244,8 +244,10 @@ describe('tool-str-replace-editor', () => { expect(listing).not.toContain('too-deep.txt') expect(listing).not.toContain('index.js') expect(listing).not.toContain('module.pyc') - expect(listing).toContain('node_modules_old/kept.js') - expect(listing).toContain('__pycache__backup/kept.py') + // The listing carries absolute display paths; the POSIX-style substrings + // only match on Linux, so assert with platform separators. + expect(listing).toContain(join('node_modules_old', 'kept.js')) + expect(listing).toContain(join('__pycache__backup', 'kept.py')) const clipped = await setup({ maxOutputChars: 10 }) await writeFile(join(clipped.root, 'large.txt'), 'x'.repeat(100)) From a2ec6cefc2c5d9d194f6d4b94a7d986d2f79c10e Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Mon, 3 Aug 2026 15:38:26 +0800 Subject: [PATCH 15/45] fix(client-web): scroll the web_search source card instead of collapsing Replace the WebBlock search card's head/tail collapse and expand button with a fixed-height scroll container that lists every source the tool returned. The model-facing side is unchanged: the seam still caps sources at searchMaxResults and the truncated indicator stays, so model-visible and frontend-visible sources remain identical. Remove CHAT_WEB_MAX_SOURCES and DEFAULT_WEB_MAX_SOURCES: with scroll, the chat row and details panel show the same full list. --- ...6-08-03-web-search-source-scroll.i18n.yaml | 6 ++ .../2026-08-03-web-search-source-scroll.md | 35 +++++++++ .../2026-08-03-web-search-source-scroll.zh.md | 35 +++++++++ .../src/client/chat/ToolRow.tsx | 3 +- .../src/client/contract/web-card-model.ts | 10 --- .../src/client/skeleton/DetailsPanel.tsx | 13 ++-- .../ui-conversation/tests/web-card.spec.tsx | 5 +- .../ui-primitives/src/WebBlock.module.css | 34 +++------ .../client/ui-primitives/src/WebBlock.tsx | 67 +++-------------- packages/client/ui-primitives/src/index.ts | 2 +- .../ui-primitives/tests/web-block.spec.tsx | 73 +++++-------------- 11 files changed, 127 insertions(+), 156 deletions(-) create mode 100644 .agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.i18n.yaml create mode 100644 .agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.md create mode 100644 .agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.zh.md diff --git a/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.i18n.yaml b/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.i18n.yaml new file mode 100644 index 0000000000..801d72dd39 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# 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/2026-08-03-web-search-source-scroll.md +2026-08-03-web-search-source-scroll.md: 9c1cb772fe768af833477f5f87c2804cbcaf068c +2026-08-03-web-search-source-scroll.zh.md: 0b3ef09c9f204ccbc034c509918053af4cf30821 diff --git a/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.md b/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.md new file mode 100644 index 0000000000..9c1cb772fe --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.md @@ -0,0 +1,35 @@ +# Agent Note: Web search source card scrolls instead of collapsing + +Status: implemented + +English | [中文](2026-08-03-web-search-source-scroll.zh.md) + +## Problem + +The `web_search` result card (`WebBlock`, `packages/client/ui-primitives/src/WebBlock.tsx`) rendered its source list with a head/tail collapse: past a `maxSources` count (16 in the details panel, 8 in the chat row via `CHAT_WEB_MAX_SOURCES`) it drew the first `ceil(max/2)` sources, an `… 其余 N 条来源` expand button, then the last `max - ceil(max/2)`, mirroring `TerminalBlock`'s output cap. A user reading the card saw `来源列表已截断` and assumed the frontend had dropped sources it was holding. + +It had not. The seam (`capSources`, `packages/web/web/src/index.ts`) cuts the provider's sources to the tool's `searchMaxResults` bound (default 8) and sets `truncated`, and that one capped list feeds both the model-facing render text and the card's `presentationMeta`. The card never holds more sources than the model saw. So the collapse was hiding sources the user was entitled to see in full — and, with the default bound at 8 and the panel cap at 16, it almost never even triggered, leaving only the `truncated` note with no way to reveal anything. + +## Decision + +`WebBlock`'s search arm renders every source it receives in one `
    `, with no head/tail slicing, no expand button, and no `maxSources` prop. `.sources` (`WebBlock.module.css`) gets a fixed `max-height` and `overflow-y: auto`, so a list longer than the card height scrolls in place rather than growing the card or hiding rows. The height is a design constant of the card geometry, so it lives in CSS, not a plugin config field. + +The model side is unchanged: the seam still caps sources at `searchMaxResults`, the model-facing render text is untouched, and the `truncated` flag and its `来源列表已截断` indicator stay. What the model sees and what the card shows remain the same list — the card just shows all of it, scrollable, instead of collapsing the middle. + +`CHAT_WEB_MAX_SOURCES` and the primitive's `DEFAULT_WEB_MAX_SOURCES` are removed: with scroll, the chat row and the details panel show the same full list, differentiated only by their container height. `
  1. ` still pins each source's 1-based citation index; without the collapse gap the ordinals are now simply contiguous. + +## Alternatives considered + +**Raise `searchMaxResults` (or make it unbounded) so more sources reach both the model and the card.** Rejected by the user: it changes model-side behavior (more sources into every request's context, more tokens) and breaks the invariant that model-visible and frontend-visible sources are identical. The instruction was explicit — keep the cap and the truncation, add a scrollbar. + +**Keep the head/tail collapse and add scroll only to the expanded region.** Rejected: two overlapping mechanisms for one concern. Once the whole list is always rendered, the collapse arithmetic, the expand/collapse state, and the button are dead weight; scroll alone bounds the height. + +**Make the scroll height a plugin config field.** Rejected: the height bounds the card's on-screen geometry, not a deployment policy, so per [web-card-model](2026-07-30-web-result-card.md)'s precedent for `CHAT_WEB_MAX_SOURCES` it belongs in CSS as a design constant. + +## Testing + +`packages/client/ui-primitives/tests/web-block.spec.tsx` drops the collapse cases (head/tail slice, expand-on-click, collapsed-tail numbering, expander-out-of-numbering, head-alone, default cap) and adds: a 30-source card renders all 30 `
  2. ` with no `[aria-expanded]` and no ` -
    3. - )} - {tail.map((source, index) => ( - - ))} + {sources.map((source, index) => )}
)} {truncated &&
来源列表已截断
} diff --git a/packages/client/ui-primitives/src/index.ts b/packages/client/ui-primitives/src/index.ts index b19147a1cc..79bae60c36 100644 --- a/packages/client/ui-primitives/src/index.ts +++ b/packages/client/ui-primitives/src/index.ts @@ -32,7 +32,7 @@ export { SearchBlock, DEFAULT_SEARCH_MAX_LINES } from './SearchBlock.tsx' export type { SearchBlockProps, SearchMatchesBlockProps, SearchPathsBlockProps, SearchFileGroup, SearchBlockLineMatch, } from './SearchBlock.tsx' -export { WebBlock, DEFAULT_WEB_MAX_SOURCES } from './WebBlock.tsx' +export { WebBlock } from './WebBlock.tsx' export type { WebBlockProps, WebSearchBlockProps, WebFetchBlockProps, WebSourceView } from './WebBlock.tsx' export { CodeBlock } from './markdown/CodeBlock.tsx' export type { CodeBlockProps } from './markdown/CodeBlock.tsx' diff --git a/packages/client/ui-primitives/tests/web-block.spec.tsx b/packages/client/ui-primitives/tests/web-block.spec.tsx index d681ce753b..c26d0a6916 100644 --- a/packages/client/ui-primitives/tests/web-block.spec.tsx +++ b/packages/client/ui-primitives/tests/web-block.spec.tsx @@ -1,19 +1,19 @@ // @vitest-environment jsdom // WebBlock: both kinds of the web card. The search card's answer, its citation // list with the title-or-hostname label fallback and optional snippet/date, the -// source-list height cap and its expand control, and the truncated indicator; -// the fetch card's linked URL, status, and truncation. Safe-link attributes on -// both kinds: an http(s) URL becomes an external anchor (target/rel), any other -// URL renders as plain text with no href. +// full source list rendered inside a scroll container, and the truncated +// indicator; the fetch card's linked URL, status, and truncation. Safe-link +// attributes on both kinds: an http(s) URL becomes an external anchor +// (target/rel), any other URL renders as plain text with no href. import { afterEach, describe, expect, it } from 'vitest' -import { cleanup, fireEvent, render } from '@testing-library/react' -import { DEFAULT_WEB_MAX_SOURCES, WebBlock } from '../src/index.ts' +import { cleanup, render } from '@testing-library/react' +import { WebBlock } from '../src/index.ts' import type { WebSourceView } from '../src/index.ts' afterEach(cleanup) -/** `count` sources with sequential hostnames, so the cap slices read distinctly. */ +/** `count` sources with sequential hostnames, so each row reads distinctly. */ function sources(count: number): WebSourceView[] { return Array.from({ length: count }, (_value, index) => ({ url: `https://site-${index}.example.com/page`, @@ -123,58 +123,23 @@ describe('WebBlock search card', () => { expect(off.queryByText('来源列表已截断')).toBeNull() }) - it('renders every source and no expand control under the cap', () => { - const view = render() - expect(view.container.querySelectorAll('[class^="_source_"]')).toHaveLength(4) + it('renders every source with no expand control, in one scroll container', () => { + // The card shows the whole list the tool returned — the same sources the + // model saw — with no head/tail collapse and no expand button; a long list + // scrolls within the .sources container instead. + const view = render() + expect(view.container.querySelectorAll('li[class^="_source_"]')).toHaveLength(30) expect(view.container.querySelector('[aria-expanded]')).toBeNull() - }) - - it('slices head and tail over the cap and expands on click', () => { - const view = render() - // maxSources 4: head = ceil(4/2) = 2, tail = 4 - 2 = 2, 6 hidden. - expect([...view.container.querySelectorAll('[class^="_sourceLink_"]')].map(n => n.textContent)) - .toEqual(['Source 0', 'Source 1', 'Source 8', 'Source 9']) - const toggle = view.getByRole('button', { name: '展开其余 6 条来源' }) - expect(toggle.getAttribute('aria-expanded')).toBe('false') - expect(toggle.textContent).toBe('… 其余 6 条来源') - - fireEvent.click(toggle) - expect(view.container.querySelectorAll('[class^="_source_"]')).toHaveLength(10) - const collapse = view.getByRole('button', { name: '收起来源' }) - expect(collapse.getAttribute('aria-expanded')).toBe('true') - expect(collapse.textContent).toBe('收起') - - fireEvent.click(collapse) - expect(view.container.querySelectorAll('[class^="_source_"]')).toHaveLength(4) - }) - - it('numbers a collapsed tail by each source original position, not its visible slot', () => { - // maxSources 4 over 10 sources: the tail is sources 8 and 9, which must read - // as citations 9 and 10 (via
  • ), not renumbered 3 and 4. - const view = render() - const items = [...view.container.querySelectorAll('li[class^="_source_"]')] - expect(items.map(li => li.getAttribute('value'))).toEqual(['1', '2', '9', '10']) - }) - - it('keeps the expander out of the ordered-list numbering', () => { - // The expander is a marker-less
  • , so it is valid inside
      and does not - // consume a citation number between the head and tail sources. - const view = render() + expect(view.container.querySelector('button')).toBeNull() + // Every direct child of the
        is a source
      1. (no marker-less expander). const ol = view.container.querySelector('ol')! - // Every direct child is an
      2. (no bare