From 6b79ce08c580c1921f545ac447b543cbc3970893 Mon Sep 17 00:00:00 2001 From: NI0317 Date: Tue, 28 Jul 2026 16:21:29 +0800 Subject: [PATCH] test(fs-search): minimize glob snapshot composition Boot the glob sampling scenario from a standalone ACP composition that exposes only bash, glob, and grep. Regenerate the smaller header fixtures and trim implementation narration already owned by the Agent Note. --- .../2026-07-27-glob-sampling.i18n.yaml | 4 +- .../bug-fix/2026-07-27-glob-sampling.md | 2 +- .../bug-fix/2026-07-27-glob-sampling.zh.md | 2 +- .../acp-agent/fs-search.cordis.snapshot.yml | 24 - examples/acp-agent/fs-search.cordis.yml | 13 - examples/acp-agent/tests/acp.snapshot.ts | 2 +- .../tests/fs-search.cordis.snapshot.yml | 34 ++ examples/acp-agent/tests/fs-search.cordis.yml | 32 ++ .../system-prompt.expected.md | 22 +- .../tool-schemas.expected.json | 437 +----------------- packages/fs/tool-fs-search/src/glob.ts | 35 +- 11 files changed, 78 insertions(+), 529 deletions(-) delete mode 100644 examples/acp-agent/fs-search.cordis.snapshot.yml delete mode 100644 examples/acp-agent/fs-search.cordis.yml create mode 100644 examples/acp-agent/tests/fs-search.cordis.snapshot.yml create mode 100644 examples/acp-agent/tests/fs-search.cordis.yml diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.i18n.yaml index 88e4ec9fc8..7c11db5207 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.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/2026-07-27-glob-sampling.md -2026-07-27-glob-sampling.md: c583f0cd8110684a94d0cd04f5cf2ae861ce7aa3 -2026-07-27-glob-sampling.zh.md: 97025a7714237fc716dee745a858140cd783ba2d +2026-07-27-glob-sampling.md: b9dfc7fc89ff61824094ccd5297f766c665f4edb +2026-07-27-glob-sampling.zh.md: 4f022467e461247c746e906b32f5ecffcb885d56 diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.md b/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.md index c583f0cd81..b9dfc7fc89 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.md +++ b/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.md @@ -42,4 +42,4 @@ The tool surface does not grow. The fix changes glob's prompt, schema descriptio ## Testing -Package tests pin concentrated and flat results, explicit roots, more groups than the JavaScript argument limit, exhausted groups, fewer slots than groups, and paths outside the workdir. The `fs-glob-sampling` ACP scenario boots the real Loader/app/sandbox-bash composition and executes the real search plugin against a deterministic `rg` process fixture; its result spans four top-level entries instead of returning one subtree's head. +Package tests pin concentrated and flat results, explicit roots, more groups than the JavaScript argument limit, exhausted groups, fewer slots than groups, and paths outside the workdir. The `fs-glob-sampling` ACP scenario boots a minimal real Loader/app/local-bash composition and executes the real search plugin against a deterministic `rg` process fixture; its result spans four top-level entries instead of returning one subtree's head. diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.zh.md b/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.zh.md index 97025a7714..4f022467e4 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.zh.md @@ -42,4 +42,4 @@ footer 会说明当前页面是跨条目的样本，而不是按修改时间排 ## 测试 -包测试锁定了结果集中与扁平两种情况、显式根目录、分组数超过 JavaScript 参数个数上限、分组耗尽、位置数少于分组数，以及工作目录以外的路径。`fs-glob-sampling` ACP（Agent Client Protocol）场景会启动真实的 Loader/app/sandbox-bash 组合，并让真实搜索插件对接确定性的 `rg` 进程 fixture（测试前置数据）；其结果覆盖 4 个顶层条目，而不是只返回某棵子树的前部。 +包测试锁定了结果集中与扁平两种情况、显式根目录、分组数超过 JavaScript 参数个数上限、分组耗尽、位置数少于分组数，以及工作目录以外的路径。`fs-glob-sampling` ACP（Agent Client Protocol）场景会启动最小化的真实 Loader/app/local-bash 组合，并让真实搜索插件对接确定性的 `rg` 进程 fixture（测试前置数据）；其结果覆盖 4 个顶层条目，而不是只返回某棵子树的前部。 diff --git a/examples/acp-agent/fs-search.cordis.snapshot.yml b/examples/acp-agent/fs-search.cordis.snapshot.yml deleted file mode 100644 index 1541cd96ce..0000000000 --- a/examples/acp-agent/fs-search.cordis.snapshot.yml +++ /dev/null @@ -1,24 +0,0 @@ -# Keyless counterpart to fs-search.cordis.yml: the search plugin and sandboxed -# bash execution remain real; only the model adapter is replaced by replay. -- id: base - name: '@cordisjs/plugin-include' - config: - path: ./cordis.yml - patches: - - id: llm-deepseek - name: '@deepseek-ai/dsh-llm-deepseek' - disabled: true - - insert: - - id: llm-replay - name: '@deepseek-ai/dsh-llm-replay' - config: - providers: - - id: deepseek - name: DeepSeek - models: - - id: deepseek-v4-flash - - id: deepseek-v4-pro - - id: tool-fs-search - name: '@deepseek-ai/dsh-tool-fs-search' - config: - globMaxResults: 4 diff --git a/examples/acp-agent/fs-search.cordis.yml b/examples/acp-agent/fs-search.cordis.yml deleted file mode 100644 index fd1eec2a38..0000000000 --- a/examples/acp-agent/fs-search.cordis.yml +++ /dev/null @@ -1,13 +0,0 @@ -# Search snapshot composition: mount the real model-facing search plugin over -# the shipped sandboxed bash stack. A four-path inline cap keeps the fixture -# small while forcing the over-cap sampling branch. -- id: base - name: '@cordisjs/plugin-include' - config: - path: ./cordis.yml - patches: - - insert: - - id: tool-fs-search - name: '@deepseek-ai/dsh-tool-fs-search' - config: - globMaxResults: 4 diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 9af14d850f..28e814a258 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -42,7 +42,7 @@ const RETRY_CONFIG = fileURLToPath(new URL('../retry.cordis.yml', import.meta.ur const SESSION_TITLE_CONFIG = fileURLToPath(new URL('../session-title.cordis.yml', import.meta.url)) 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_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' diff --git a/examples/acp-agent/tests/fs-search.cordis.snapshot.yml b/examples/acp-agent/tests/fs-search.cordis.snapshot.yml new file mode 100644 index 0000000000..e1755ec9d4 --- /dev/null +++ b/examples/acp-agent/tests/fs-search.cordis.snapshot.yml @@ -0,0 +1,34 @@ +# Minimal keyless composition: real app, bash, and search tool; replayed model. +- id: llm-replay + name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-pro + +- id: subprocess + name: '@deepseek-ai/dsh-subprocess-local' + +- id: bash + name: '@deepseek-ai/dsh-bash-local' + +- id: acp-agent + name: '@deepseek-ai/dsh-acp-demo' + config: + provider: deepseek + model: deepseek-v4-pro + persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' + persistenceCompression: none + workspaceContext: false + skills: + enabled: false + toolTasks: false + goals: false + persona: You are a concise snapshot agent working in {{cwd}}. + +- id: tool-fs-search + name: '@deepseek-ai/dsh-tool-fs-search' + config: + globMaxResults: 4 diff --git a/examples/acp-agent/tests/fs-search.cordis.yml b/examples/acp-agent/tests/fs-search.cordis.yml new file mode 100644 index 0000000000..171ab88980 --- /dev/null +++ b/examples/acp-agent/tests/fs-search.cordis.yml @@ -0,0 +1,32 @@ +# Minimal live counterpart for the glob-sampling snapshot composition. +- id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + config: + apiKey: !!js process.env.DEEPSEEK_API_KEY + baseURL: !!js process.env.DEEPSEEK_BASE_URL + models: + - id: deepseek-v4-pro + +- id: subprocess + name: '@deepseek-ai/dsh-subprocess-local' + +- id: bash + name: '@deepseek-ai/dsh-bash-local' + +- id: acp-agent + name: '@deepseek-ai/dsh-acp-demo' + config: + provider: deepseek + model: deepseek-v4-pro + persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' + workspaceContext: false + skills: + enabled: false + toolTasks: false + goals: false + persona: You are a concise snapshot agent working in {{cwd}}. + +- id: tool-fs-search + name: '@deepseek-ai/dsh-tool-fs-search' + config: + globMaxResults: 4 diff --git a/examples/acp-agent/tests/snapshots/fs-glob-sampling/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/fs-glob-sampling/system-prompt.expected.md index 467b05904b..eb22966cdb 100644 --- a/examples/acp-agent/tests/snapshots/fs-glob-sampling/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/fs-glob-sampling/system-prompt.expected.md @@ -1,29 +1,9 @@ You are an AI agent powered by the DeepSeek Harness SDK. -You are a coding assistant powered by the deepseek-v4-pro model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. - -Verify your work by running the code or tests. Keep answers brief and factual. - - -Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. - -Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. - -Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. +You are a concise snapshot agent working in {{cwd}}. Use the glob tool — not shell find — to discover files by path pattern. A pattern with no "/" matches basenames at any depth, so "*" matches every file in the tree rather than its top level. Results are files only, never directories, and include hidden and ignored files: a result that fits comes back in modification-time order, while a larger one is sampled across top-level entries, so it spans the tree instead of one subtree. Use the grep tool — not shell grep or rg — to search file contents. Use read on a matched file when you need surrounding context. Check the [exit code: N] marker on every bash result; investigate failures before moving on. - -Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. - -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. - -Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). - - -Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. - -Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out. diff --git a/examples/acp-agent/tests/snapshots/fs-glob-sampling/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/fs-glob-sampling/tool-schemas.expected.json index 1b25291c5c..4cb292798a 100644 --- a/examples/acp-agent/tests/snapshots/fs-glob-sampling/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/fs-glob-sampling/tool-schemas.expected.json @@ -2,7 +2,7 @@ "initial": [ { "name": "bash", - "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.", + "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.", "parameters": { "type": "object", "properties": { @@ -25,18 +25,6 @@ "run_in_background": { "type": "boolean", "description": "Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies." - }, - "sandbox_permissions": { - "type": "string", - "description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access." } }, "required": [ @@ -45,76 +33,6 @@ ] } }, - { - "name": "create_goal", - "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The concrete completion objective inferred from the direct human request." - }, - "max_goal_rounds": { - "type": "number", - "description": "Optional positive safe-integer limit on automatic continuation rounds." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "edit", - "description": "Edit an existing UTF-8 text file by replacing literal text.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to edit, resolved by the filesystem backend." - }, - "old_string": { - "type": "string", - "description": "Literal text to replace. Must match exactly." - }, - "new_string": { - "type": "string", - "description": "Literal replacement text. Use an empty string to delete the match." - }, - "replace_all": { - "type": "boolean", - "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once." - }, - "sandbox_permissions": { - "type": "string", - "description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access." - } - }, - "required": [ - "file_path", - "old_string", - "new_string" - ] - } - }, - { - "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", - "parameters": { - "type": "object", - "properties": {} - } - }, { "name": "glob", "description": "Find files whose paths match a glob pattern. Returns matching file paths — never directories — including hidden and ignored files (VCS metadata directories are excluded). Up to 4 paths come back in modification-time order; a larger result instead returns 4 paths sampled across top-level entries, says so, and reports where the complete sorted list was saved. This tool does not enumerate directory entries.", @@ -158,359 +76,6 @@ "pattern" ] } - }, - { - "name": "ralph", - "description": "Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The immutable completion objective for every fresh Ralph round." - }, - "maxRounds": { - "type": "number", - "description": "Optional positive safe-integer round cap, bounded by the deployment ceiling." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "read", - "description": "Read a UTF-8 text file and return line-numbered content.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to read, resolved by the filesystem backend." - }, - "offset": { - "type": "number", - "description": "1-based first line to return. Defaults to 1." - }, - "limit": { - "type": "number", - "description": "Maximum number of lines to return. Defaults to 2000." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "name": "skill", - "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.", - "parameters": { - "type": "object", - "properties": { - "name": { - "type": "string", - "description": "The exact skill name from the available skills list." - } - }, - "required": [ - "name" - ] - } - }, - { - "name": "subagent", - "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", - "parameters": { - "type": "object", - "properties": { - "description": { - "type": "string", - "description": "A short (3-5 word) description of the delegated task, for display." - }, - "prompt": { - "type": "string", - "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs." - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background task and return its id; collect with task_output or stop with task_kill." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "subagent_fork", - "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", - "parameters": { - "type": "object", - "properties": { - "description": { - "type": "string", - "description": "A short (3-5 word) description of the delegated task, for display." - }, - "prompt": { - "type": "string", - "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new." - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background task and return its id; collect with task_output or stop with task_kill." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "task_kill", - "description": "Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.", - "parameters": { - "type": "object", - "properties": { - "task_id": { - "type": "string", - "description": "Task id returned by the tool that started the background work." - }, - "reason": { - "type": "string", - "description": "Optional short reason, recorded in the log and forwarded to the task." - } - }, - "required": [ - "task_id" - ] - } - }, - { - "name": "task_list", - "description": "List your background tasks (running and finished) with their ids, kinds, and statuses.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "task_output", - "description": "Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.", - "parameters": { - "type": "object", - "properties": { - "task_id": { - "type": "string", - "description": "Task id returned by the tool that started the background work." - }, - "wait": { - "type": "boolean", - "description": "Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive." - }, - "timeout_ms": { - "type": "number", - "description": "Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum." - } - }, - "required": [ - "task_id" - ] - } - }, - { - "name": "todo_write", - "description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).", - "parameters": { - "type": "object", - "properties": { - "todos": { - "type": "array", - "description": "The COMPLETE task list, replacing any previous list.", - "items": { - "type": "object", - "additionalProperties": false, - "properties": { - "content": { - "type": "string", - "description": "What the task is — a short imperative line." - }, - "status": { - "type": "string", - "description": "pending (not started) | in_progress (now) | completed (done).", - "enum": [ - "pending", - "in_progress", - "completed" - ] - } - }, - "required": [ - "content", - "status" - ] - } - } - }, - "required": [ - "todos" - ] - } - }, - { - "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", - "parameters": { - "type": "object", - "properties": { - "goal_id": { - "type": "string", - "description": "Exact id returned by get_goal." - }, - "revision": { - "type": "number", - "description": "Exact positive revision returned by get_goal." - }, - "action": { - "type": "string", - "description": "edit | pause | resume | complete | blocked", - "enum": [ - "edit", - "pause", - "resume", - "complete", - "blocked" - ] - }, - "objective": { - "type": "string", - "description": "Replacement objective; valid only with action edit." - }, - "max_goal_rounds": { - "type": "number", - "description": "Replacement cap; valid only with action edit." - }, - "blocked_reason": { - "type": "string", - "description": "Concrete blocking condition; required only with action blocked." - } - }, - "required": [ - "goal_id", - "revision", - "action" - ] - } - }, - { - "name": "workflow", - "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", - "parameters": { - "type": "object", - "properties": { - "script": { - "type": "string", - "description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)." - }, - "meta": { - "type": "object", - "description": "The workflow identity block (plain JSON — never code).", - "additionalProperties": true, - "properties": { - "name": { - "type": "string", - "description": "Short kebab-case workflow name." - }, - "description": { - "type": "string", - "description": "One-line description of what the workflow does." - }, - "whenToUse": { - "type": "string", - "description": "Optional guidance on when this workflow applies." - }, - "phases": { - "type": "array", - "description": "Optional phase declarations matched by phase() calls.", - "items": { - "type": "object", - "additionalProperties": true, - "properties": { - "title": { - "type": "string", - "description": "The phase title phase() calls match by exact string." - }, - "detail": { - "type": "string", - "description": "Optional one-line description of the phase." - }, - "provider": { - "type": "string", - "description": "Optional provider override this phase is expected to use." - }, - "model": { - "type": "string", - "description": "Optional model override this phase is expected to use." - } - }, - "required": [ - "title" - ] - } - } - }, - "required": [ - "name", - "description" - ] - }, - "args": { - "type": "object", - "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).", - "additionalProperties": true - } - }, - "required": [ - "script", - "meta" - ] - } - }, - { - "name": "write", - "description": "Create or fully replace a UTF-8 text file.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to write, resolved by the filesystem backend." - }, - "content": { - "type": "string", - "description": "Full UTF-8 text content to write." - }, - "sandbox_permissions": { - "type": "string", - "description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access." - } - }, - "required": [ - "file_path", - "content" - ] - } } ], "changes": [] diff --git a/packages/fs/tool-fs-search/src/glob.ts b/packages/fs/tool-fs-search/src/glob.ts index 94d9b0e627..12af97a24b 100644 --- a/packages/fs/tool-fs-search/src/glob.ts +++ b/packages/fs/tool-fs-search/src/glob.ts @@ -5,13 +5,6 @@ * 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`. - * - * A complete result keeps ripgrep's modification-time order. A result too large - * to show inline does NOT: its inline page is sampled across the complete - * result's top-level entries ({@link sampleAcrossTopLevel}), because the sorted - * head of a broad match is routinely one subtree's worth of files and reads as - * if the workspace held nothing else. - * * @module @deepseek-ai/dsh-tool-fs-search/glob */ @@ -145,19 +138,9 @@ function topLevelSegment(path: string): string { * Choose the inline page of an over-cap result by round-robin across the * complete result's top-level entries, instead of taking its head. * - * `--sort=modified` (oldest first) is the right order for a complete result and - * the wrong basis for a sample of one: a broad pattern in a workspace holding one - * unpacked archive — whose restored timestamps predate everything the user - * wrote — gives a head that is entirely that subtree, and the model reads the - * page as the workspace. Round-robin gives every top-level entry a slot before - * any entry gets a second, so the page spans the tree; an entry that runs out of - * paths drops out and its remaining slots go to the rest. - * - * Modification-time order survives where it still means something: groups are - * visited in the order ripgrep first emits them, and each group's own paths keep - * their relative order. With one path per group — a flat result — this - * reproduces the sorted head exactly, so nothing changes for a result that has - * no subtree to hide. + * Every top-level entry receives a slot before any receives a second; exhausted + * groups drop out. Group order and order within each group follow `paths`, so a + * flat result reproduces the modification-time head. * * @param paths - the complete result, in ripgrep's modification-time order. * @param maxItems - how many paths the page may hold; the caller has already established it is smaller than `paths`. @@ -191,16 +174,8 @@ export function sampleAcrossTopLevel(paths: readonly string[], maxItems: number, } /** - * Format a CAPPED `glob` result: the inline page, then a footer stating that - * the page is a cross-directory sample rather than the most recent paths, how - * much of the top level it reaches, and either the formatted-spill recovery - * locator or the could-not-save explanation. The omitted count is a budget - * fact: the search itself completed. A result that fits inline never reaches - * here — it is emitted verbatim, in ripgrep's order. - * - * A result whose every path is its own top-level entry keeps the plain footer: - * the sample is the modification-time-ordered head, and naming a spread would only - * restate the path counts already there. + * Format a capped sampled page and its complete-result recovery path. A flat + * result keeps the plain footer because its sample is the modification-time head. * * @param sample - the inline page and its top-level spread. * @param seen - how many paths the complete result holds; always more than the page.