From d4614f92d658c30b36835549776f8acc409eb7a3 Mon Sep 17 00:00:00 2001 From: NI0317 Date: Tue, 28 Jul 2026 11:59:52 +0800 Subject: [PATCH 01/24] feat(fs): add a model-facing directory listing tool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit `ctx.fs.listDir` has shipped since the filesystem seam gained it, with skill discovery as its only consumer; the model-facing tool was deferred to a separate decision. Nothing else could answer "what is in this directory": `rg --files` backs glob and grep and never emits a directory entry, so an empty directory is invisible, no output says which names are directories, and no output gives an entry count. `list` takes an optional `path`, defaulting to the session workspace so the common question needs no argument, and returns the direct children of one directory with their type. Two presentation rules carry it: directories sort first, then files, then non-regular children, each alphabetically — so truncation loses leaves rather than the tree — and the footer always states the complete listing's size and composition, so a capped view can never read as a whole directory. It emits no `fs/observed`: seeing a filename is not reading a file, and a listing must never satisfy the read-before-write gate. --- docs/config-catalog.md | 4 +- docs/tool-catalog.md | 22 ++- examples/acp-agent/tests/acp.snapshot.ts | 4 + .../system-prompt.expected.md | 14 ++ .../tool-schemas.expected.json | 13 ++ .../both-mode-turn/system-prompt.expected.md | 14 ++ .../both-mode-turn/tool-schemas.expected.json | 13 ++ .../code-mode-turn/system-prompt.expected.md | 14 ++ .../system-prompt.expected.md | 14 ++ .../system-prompt.expected.md | 2 + .../tool-schemas.expected.json | 13 ++ .../tests/snapshots/fs-list/input.json | 7 + .../tests/snapshots/fs-list/session.jsonl | 32 +++++ .../snapshots/fs-list/stdout.expected.jsonl | 4 + .../snapshots/fs-list/workspace/README.txt | 1 + .../fs-list/workspace/docs/guide.txt | 1 + .../snapshots/fs-list/workspace/package.json | 1 + .../snapshots/fs-list/workspace/src/index.txt | 1 + .../lsp-definition/system-prompt.expected.md | 2 + .../lsp-definition/tool-schemas.expected.json | 13 ++ .../pty-tools/system-prompt.expected.md | 2 + .../pty-tools/tool-schemas.expected.json | 13 ++ .../system-prompt.expected.md | 2 + .../tool-schemas.expected.json | 13 ++ .../skill-load/system-prompt.expected.md | 2 + .../skill-load/tool-schemas.expected.json | 13 ++ .../text-turn/system-prompt.expected.md | 2 + .../text-turn/tool-schemas.expected.json | 13 ++ .../web-fetch/system-prompt.expected.md | 2 + .../web-fetch/tool-schemas.expected.json | 13 ++ .../system-prompt.expected.md | 2 + .../tool-schemas.expected.json | 13 ++ .../advanced-toolchain/session.1.jsonl | 2 +- .../advanced-toolchain/session.2.jsonl | 2 +- .../advanced-toolchain/session.jsonl | 2 +- .../tests/snapshots/pty-tools/session.jsonl | 2 +- .../terminal.expected.txt | 2 +- .../core/tools/tests/gen-tool-catalog.spec.ts | 2 +- packages/fs/tool-fs/README.i18n.yaml | 6 +- packages/fs/tool-fs/README.md | 43 ++++-- packages/fs/tool-fs/README.zh.md | 43 ++++-- packages/fs/tool-fs/package.json | 2 +- packages/fs/tool-fs/src/index.ts | 18 ++- packages/fs/tool-fs/src/list-render.ts | 82 +++++++++++ packages/fs/tool-fs/src/list.ts | 120 ++++++++++++++++ packages/fs/tool-fs/tests/list-render.spec.ts | 69 +++++++++ packages/fs/tool-fs/tests/tools.spec.ts | 131 +++++++++++++++++- scripts/gen-tool-catalog.ts | 2 +- 48 files changed, 761 insertions(+), 46 deletions(-) create mode 100644 examples/acp-agent/tests/snapshots/fs-list/input.json create mode 100644 examples/acp-agent/tests/snapshots/fs-list/session.jsonl create mode 100644 examples/acp-agent/tests/snapshots/fs-list/stdout.expected.jsonl create mode 100644 examples/acp-agent/tests/snapshots/fs-list/workspace/README.txt create mode 100644 examples/acp-agent/tests/snapshots/fs-list/workspace/docs/guide.txt create mode 100644 examples/acp-agent/tests/snapshots/fs-list/workspace/package.json create mode 100644 examples/acp-agent/tests/snapshots/fs-list/workspace/src/index.txt create mode 100644 packages/fs/tool-fs/src/list-render.ts create mode 100644 packages/fs/tool-fs/src/list.ts create mode 100644 packages/fs/tool-fs/tests/list-render.spec.ts diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 47a8acfd30..0b0045b668 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1449,6 +1449,8 @@ Requires: `tools` · `fs` · `systemPrompt` ```ts config-catalog /** Plugin config (all optional — `Config` supplies the defaults). */ export interface Config { + /** Maximum entries one `list` call renders inline; the footer still reports the complete count. */ + listMaxEntries?: number /** Default and maximum number of lines returned by one `read` call. */ readLimit?: number /** Maximum characters returned for a single line before truncation. */ @@ -1460,7 +1462,7 @@ export interface Config { } ``` -Source: [`packages/fs/tool-fs/src/index.ts:24`](../packages/fs/tool-fs/src/index.ts) +Source: [`packages/fs/tool-fs/src/index.ts:27`](../packages/fs/tool-fs/src/index.ts) ## `@deepseek-ai/dsh-tool-fs-search` diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 311791e594..6edd5be644 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -20,7 +20,7 @@ This table connects model-visible tool names to the plugin package and service s | `@deepseek-ai/dsh-plan-mode` | `exit_plan_mode` | `ctx.tools`, `ctx.systemPrompt`, `ctx.userInteraction (execution time, opportunistic)` | `tool/call`, `plan/mode inactive on an approved review`, `tool/result` | - | exit_plan_mode stays in the model-facing schema while planning is inactive so transitions add no tool-catalog churn on top of the plan-policy change. Its execute path rejects calls outside plan mode; in plan mode it presents the plan over the user-interaction seam (approve / keep planning with feedback), and approval logs plan mode inactive at the step boundary. | | `@deepseek-ai/dsh-tool-bash` | `bash` | `ctx.tools`, `ctx.bash`, `ctx.tasks at call time for run_in_background` | `tool/call`, `tool/result` | - | The bash tool is the model-facing consumer of the bash executor seam. A `run_in_background` run registers with the generic `ctx.tasks` runtime and is collected/stopped through the `task_*` tools from `@deepseek-ai/dsh-tool-tasks`; the `enableRunInBackground` config (default true) removes the parameter entirely when disabled. | | `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `live plugin-tree mutations (mount/unmount)` | - | Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes. | -| `@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` | `edit`, `list`, `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. `list` enumerates one directory level through `ctx.fs.listDir` and records no observation, so seeing a filename never satisfies that read-before-write gate. | | `@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). 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. | @@ -316,6 +316,24 @@ Edit an existing UTF-8 text file by replacing literal text. Source: [`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts) +### `list` + +List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. + +```json +{ + "type": "object", + "properties": { + "path": { + "type": "string", + "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + } + } +} +``` + +Source: [`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts) + ### `read` Read a UTF-8 text file and return line-numbered content. @@ -371,7 +389,7 @@ Create or fully replace a UTF-8 text file. Source: [`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts) -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. +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. `list` enumerates one directory level through `ctx.fs.listDir` and records no observation, so seeing a filename never satisfies that read-before-write gate. ## `@deepseek-ai/dsh-tool-fs-search` diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 4fb6f9493b..6b04b0038e 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -121,6 +121,10 @@ const SCENARIOS: Scenario[] = [ hasModelTurn: true, recorded: true, }, + // A workspace whose subdirectories are what the answer depends on: `glob` + // could not produce them at all, so this scenario pins the listing envelope + // end to end (see the directory-listing Agent Note). + { name: 'fs-list', hasModelTurn: true, recorded: true }, { name: 'fs-read', hasModelTurn: true, recorded: true }, { name: 'fs-write', hasModelTurn: true, recorded: true }, { name: 'fs-edit', hasModelTurn: true, recorded: true }, diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md index 3a37f3da6a..c78b763fec 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md @@ -5,6 +5,8 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. + 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. @@ -97,6 +99,11 @@ interface ToolArgsMap { } & Record; /** 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. */ get_goal: Record; + /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */ + list: { + /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */ + path?: string; + } & Record; /** 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. */ ralph: { /** The immutable completion objective for every fresh Ralph round. */ @@ -298,6 +305,13 @@ interface ToolOutputMap { }; activation: "armed" | "disarmed"; }; + list: { + path: string; + entries: ({ + name: string; + type: "file" | "directory" | "other"; + })[]; + }; ralph: { runId: string; agentsStarted: number; diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json index 1abccfd566..f9aea468b5 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json @@ -172,6 +172,19 @@ "properties": {} } }, + { + "name": "list", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "parameters": { + "type": "object", + "properties": { + "path": { + "type": "string", + "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + } + } + } + }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md index 0cee2a6517..ede2684ae4 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md @@ -5,6 +5,8 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. + 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. @@ -80,6 +82,11 @@ interface ToolArgsMap { } & Record; /** 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. */ get_goal: Record; + /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */ + list: { + /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */ + path?: string; + } & Record; /** 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. */ ralph: { /** The immutable completion objective for every fresh Ralph round. */ @@ -269,6 +276,13 @@ interface ToolOutputMap { }; activation: "armed" | "disarmed"; }; + list: { + path: string; + entries: ({ + name: string; + type: "file" | "directory" | "other"; + })[]; + }; ralph: { runId: string; agentsStarted: number; diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json index b61d7bf623..1333345b48 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json @@ -115,6 +115,19 @@ "properties": {} } }, + { + "name": "list", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "parameters": { + "type": "object", + "properties": { + "path": { + "type": "string", + "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + } + } + } + }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md index 0cee2a6517..ede2684ae4 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md @@ -5,6 +5,8 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. + 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. @@ -80,6 +82,11 @@ interface ToolArgsMap { } & Record; /** 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. */ get_goal: Record; + /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */ + list: { + /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */ + path?: string; + } & Record; /** 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. */ ralph: { /** The immutable completion objective for every fresh Ralph round. */ @@ -269,6 +276,13 @@ interface ToolOutputMap { }; activation: "armed" | "disarmed"; }; + list: { + path: string; + entries: ({ + name: string; + type: "file" | "directory" | "other"; + })[]; + }; ralph: { runId: string; agentsStarted: number; diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md index 0cee2a6517..ede2684ae4 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md @@ -5,6 +5,8 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. + 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. @@ -80,6 +82,11 @@ interface ToolArgsMap { } & Record; /** 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. */ get_goal: Record; + /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */ + list: { + /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */ + path?: string; + } & Record; /** 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. */ ralph: { /** The immutable completion objective for every fresh Ralph round. */ @@ -269,6 +276,13 @@ interface ToolOutputMap { }; activation: "armed" | "disarmed"; }; + list: { + path: string; + entries: ({ + name: string; + type: "file" | "directory" | "other"; + })[]; + }; ralph: { runId: string; agentsStarted: number; diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/escalation-approved/system-prompt.expected.md index e3437ad61a..edca40eed4 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/escalation-approved/system-prompt.expected.md @@ -5,6 +5,8 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. + 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. diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json index 01ac777a42..ffb310c278 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json @@ -115,6 +115,19 @@ "properties": {} } }, + { + "name": "list", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "parameters": { + "type": "object", + "properties": { + "path": { + "type": "string", + "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + } + } + } + }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/fs-list/input.json b/examples/acp-agent/tests/snapshots/fs-list/input.json new file mode 100644 index 0000000000..67a0bc3f42 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-list/input.json @@ -0,0 +1,7 @@ +{ + "steps": [ + { "op": "initialize" }, + { "op": "newSession" }, + { "op": "prompt", "text": "Call the list tool exactly once, with no arguments at all (NOT bash, NOT glob, and do not pass a path). Then reply with exactly the names of the subdirectories it reported, alphabetically, separated by a single space, and nothing else." } + ] +} diff --git a/examples/acp-agent/tests/snapshots/fs-list/session.jsonl b/examples/acp-agent/tests/snapshots/fs-list/session.jsonl new file mode 100644 index 0000000000..0a05e2b1fe --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-list/session.jsonl @@ -0,0 +1,32 @@ +{"type":"session","version":0,"id":"ea640046-d959-4644-9a03-ff3d08133d4b","createdAt":1785159113359,"cwd":"/var/folders/8k/kj35k1fd6t90n0czg7k3hv140000gn/T/acp-snap-cwd-QJ2ZC6","delegationDepth":0} +{"type":"turn/start","seq":0,"time":1785159113361,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1785159113362,"data":{"content":[{"type":"text","text":"Call the list tool exactly once, with no arguments at all (NOT bash, NOT glob, and do not pass a path). Then reply with exactly the names of the subdirectories it reported, alphabetically, separated by a single space, and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"session/title","seq":2,"time":1785159113363,"data":{"title":"Call the list tool exactly","messageSeqs":[1],"source":{"kind":"fallback"}}} +{"type":"step/start","seq":3,"time":1785159113368,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":4,"time":1785159113369,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":5,"time":1785159115248,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"reasoning-chunks","seq0":6,"time0":1785159115249,"data":{"turn":1,"step":1,"index":0,"dt":[146,45,3,0,0,1,43,1,0,0,1,1,31,1,46,0,0,0,0,0,41,1,0,0,45,2,2,0,0,1,44,3,3,0],"texts":["The"," user"," wants"," me"," to"," call"," the"," list"," tool"," with"," no"," arguments"," and"," then"," reply"," with"," the"," names"," of"," the"," sub","direct","ories"," it"," reports",","," alphabet","ically",","," separated"," by"," a"," single"," space","."]}} +{"type":"assistant/chunk","seq":41,"time":1785159115836,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":42,"time":1785159115837,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_BSi06gcYvl6oad3I5qqG9244","name":"list","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":43,"time":1785159115837,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_BSi06gcYvl6oad3I5qqG9244","name":"list","argumentsDelta":"{}"}}} +{"type":"assistant/chunk","seq":44,"time":1785159115921,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to call the list tool with no arguments and then reply with the names of the subdirectories it reports, alphabetically, separated by a single space."}}}} +{"type":"assistant/chunk","seq":45,"time":1785159115921,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_BSi06gcYvl6oad3I5qqG9244","name":"list","arguments":"{}"}}}} +{"type":"assistant/chunk","seq":46,"time":1785159115921,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":5513,"outputTokens":62,"cacheReadTokens":0,"reasoningTokens":35}}}} +{"type":"assistant/chunk","seq":47,"time":1785159115922,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":48,"time":1785159115926,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to call the list tool with no arguments and then reply with the names of the subdirectories it reports, alphabetically, separated by a single space."},{"type":"tool-call","id":"call_00_BSi06gcYvl6oad3I5qqG9244","name":"list","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":5513,"outputTokens":62,"cacheReadTokens":0,"reasoningTokens":35}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"surfaceOp":"append"} +{"type":"tool/call","seq":49,"time":1785159115927,"data":{"turn":1,"step":1,"callId":"call_00_BSi06gcYvl6oad3I5qqG9244","name":"list","arguments":"{}"}} +{"type":"tool/result","seq":50,"time":1785159115944,"data":{"turn":1,"step":1,"callId":"call_00_BSi06gcYvl6oad3I5qqG9244","content":[{"type":"text","text":"/var/folders/8k/kj35k1fd6t90n0czg7k3hv140000gn/T/acp-snap-cwd-QJ2ZC6\ndirectory\n\ndocs/\nsrc/\npackage.json\nREADME.txt\n\n(4 entries: 2 directories, 2 files)\n"}],"isError":false},"sourceEventSeqs":[49],"surfaceOp":"append"} +{"type":"step/end","seq":51,"time":1785159115950,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":52,"time":1785159115951,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":53,"time":1785159116889,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"reasoning-chunks","seq0":54,"time0":1785159116890,"data":{"turn":1,"step":2,"index":0,"dt":[145,49,1,0,60,0,0,1,0,39,1,0,0,0,0,23,1,46,3,0,0],"texts":["The"," sub","direct","ories"," reported"," are"," `","docs","/","`"," and"," `","src","/","`."," Alphabet","ically",":"," docs",","," src","."]}} +{"type":"assistant/chunk","seq":76,"time":1785159117259,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":77,"time":1785159117259,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"docs"}}} +{"type":"assistant/chunk","seq":78,"time":1785159117297,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" src"}}} +{"type":"assistant/chunk","seq":79,"time":1785159117300,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The subdirectories reported are `docs/` and `src/`. Alphabetically: docs, src."}}}} +{"type":"assistant/chunk","seq":80,"time":1785159117300,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"docs src"}}}} +{"type":"assistant/chunk","seq":81,"time":1785159117300,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":161,"outputTokens":25,"cacheReadTokens":5504,"reasoningTokens":22}}}} +{"type":"assistant/chunk","seq":82,"time":1785159117300,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":83,"time":1785159117301,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The subdirectories reported are `docs/` and `src/`. Alphabetically: docs, src."},{"type":"text","text":"docs src"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":161,"outputTokens":25,"cacheReadTokens":5504,"reasoningTokens":22}},"sourceEventSeqs":[53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82],"surfaceOp":"append"} +{"type":"step/end","seq":84,"time":1785159117308,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":85,"time":1785159117309,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-list/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-list/stdout.expected.jsonl new file mode 100644 index 0000000000..22d36a3c79 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-list/stdout.expected.jsonl @@ -0,0 +1,4 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"docs src"}}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} diff --git a/examples/acp-agent/tests/snapshots/fs-list/workspace/README.txt b/examples/acp-agent/tests/snapshots/fs-list/workspace/README.txt new file mode 100644 index 0000000000..dab306f45e --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-list/workspace/README.txt @@ -0,0 +1 @@ +# Project diff --git a/examples/acp-agent/tests/snapshots/fs-list/workspace/docs/guide.txt b/examples/acp-agent/tests/snapshots/fs-list/workspace/docs/guide.txt new file mode 100644 index 0000000000..8c0d02fadc --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-list/workspace/docs/guide.txt @@ -0,0 +1 @@ +# Guide diff --git a/examples/acp-agent/tests/snapshots/fs-list/workspace/package.json b/examples/acp-agent/tests/snapshots/fs-list/workspace/package.json new file mode 100644 index 0000000000..e36fa754cf --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-list/workspace/package.json @@ -0,0 +1 @@ +{ "name": "demo" } diff --git a/examples/acp-agent/tests/snapshots/fs-list/workspace/src/index.txt b/examples/acp-agent/tests/snapshots/fs-list/workspace/src/index.txt new file mode 100644 index 0000000000..eab39ce89c --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-list/workspace/src/index.txt @@ -0,0 +1 @@ +export const answer = 42 diff --git a/examples/acp-agent/tests/snapshots/lsp-definition/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/lsp-definition/system-prompt.expected.md index 7bde8fe289..5a5df6233c 100644 --- a/examples/acp-agent/tests/snapshots/lsp-definition/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/lsp-definition/system-prompt.expected.md @@ -5,6 +5,8 @@ You are a coding assistant powered by the deepseek-v4-pro model. Your working di Verify your work by running the code or tests. Keep answers brief and factual. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. + 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. diff --git a/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json index 9b5925605c..3a0e7c1408 100644 --- a/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json @@ -115,6 +115,19 @@ "properties": {} } }, + { + "name": "list", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "parameters": { + "type": "object", + "properties": { + "path": { + "type": "string", + "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + } + } + } + }, { "name": "lsp", "description": "Query a language server for precise code navigation. operation is one of goToDefinition, findReferences, goToImplementation, hover. line and character are one-based UTF-16 cursor coordinates. findReferences includes the declaration.", diff --git a/examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md index df065a83cb..70dd754517 100644 --- a/examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md @@ -5,6 +5,8 @@ You are a coding assistant powered by the deepseek-v4-pro model. Your working di Verify your work by running the code or tests. Keep answers brief and factual. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. + 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. diff --git a/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json index 8e093db8bd..c529ad9077 100644 --- a/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json @@ -115,6 +115,19 @@ "properties": {} } }, + { + "name": "list", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "parameters": { + "type": "object", + "properties": { + "path": { + "type": "string", + "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + } + } + } + }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/session-query-spill/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/session-query-spill/system-prompt.expected.md index 68bdd841c7..658fa4e07c 100644 --- a/examples/acp-agent/tests/snapshots/session-query-spill/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/session-query-spill/system-prompt.expected.md @@ -5,6 +5,8 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. + 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. diff --git a/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json index beb93c6b53..4eff11591a 100644 --- a/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json @@ -115,6 +115,19 @@ "properties": {} } }, + { + "name": "list", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "parameters": { + "type": "object", + "properties": { + "path": { + "type": "string", + "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + } + } + } + }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md index 17e6773a03..6d926a90a8 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md @@ -5,6 +5,8 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. + 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. diff --git a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json index 01ac777a42..ffb310c278 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json @@ -115,6 +115,19 @@ "properties": {} } }, + { + "name": "list", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "parameters": { + "type": "object", + "properties": { + "path": { + "type": "string", + "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + } + } + } + }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md index 17e6773a03..6d926a90a8 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md @@ -5,6 +5,8 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. + 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. diff --git a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json index 01ac777a42..ffb310c278 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json @@ -115,6 +115,19 @@ "properties": {} } }, + { + "name": "list", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "parameters": { + "type": "object", + "properties": { + "path": { + "type": "string", + "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + } + } + } + }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md index 45705db0a5..4c20e18272 100644 --- a/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md @@ -5,6 +5,8 @@ You are a coding assistant powered by the deepseek-v4-pro model. Your working di Verify your work by running the code or tests. Keep answers brief and factual. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. + 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. diff --git a/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json index 70940f8907..59e3baf6b1 100644 --- a/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json @@ -115,6 +115,19 @@ "properties": {} } }, + { + "name": "list", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "parameters": { + "type": "object", + "properties": { + "path": { + "type": "string", + "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + } + } + } + }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md index 6cd8d5725f..6c5155f262 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md @@ -5,6 +5,8 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. + 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. diff --git a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json index 01ac777a42..ffb310c278 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json @@ -115,6 +115,19 @@ "properties": {} } }, + { + "name": "list", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "parameters": { + "type": "object", + "properties": { + "path": { + "type": "string", + "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + } + } + } + }, { "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.", diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 6cae860e36..c0f80e3cdf 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1783957884563,"data":{"title":"Reply with exactly DIRECT_CHILD_OK and","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** 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`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** 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. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** 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. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** 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`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** 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`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** 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. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** 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). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** 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. The 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. Script-body hooks: - `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. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"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":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for.\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** 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`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */\n list: {\n /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */\n path?: string;\n } & Record;\n /** 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. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** 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. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** 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`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** 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`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** 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. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** 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). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** 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. The 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. Script-body hooks: - `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. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n list: {\n path: string;\n entries: ({\n name: string;\n type: \"file\" | \"directory\" | \"other\";\n })[];\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"name":"list","description":"List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"Directory to list. Defaults to the session workspace; a relative path resolves against it."}}}},{"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":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":7,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index c00a4119c7..2bf8be7bfb 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1783957884700,"data":{"title":"Reply with exactly WORKFLOW_CHILD_OK and","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** 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`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** 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. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** 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. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** 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`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** 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`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** 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. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** 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). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** 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. The 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. Script-body hooks: - `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. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"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":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for.\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** 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`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */\n list: {\n /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */\n path?: string;\n } & Record;\n /** 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. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** 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. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** 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`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** 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`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** 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. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** 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). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** 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. The 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. Script-body hooks: - `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. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n list: {\n path: string;\n entries: ({\n name: string;\n type: \"file\" | \"directory\" | \"other\";\n })[];\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"name":"list","description":"List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"Directory to list. Defaults to the session workspace; a relative path resolves against it."}}}},{"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":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":7,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl index 9d2b188a45..8f531cf789 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1783957884479,"data":{"title":"Run this advanced flow exactly","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** 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`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** 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. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** 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. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** 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`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** 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`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** 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. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** 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). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n } & Record)[];\n } & Record;\n /** 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. The 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. Script-body hooks: - `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. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"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":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"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":true,"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for.\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** 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`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */\n list: {\n /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */\n path?: string;\n } & Record;\n /** 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. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** 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. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** 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`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** 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`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** 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. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** 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). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** 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. The 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. Script-body hooks: - `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. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n list: {\n path: string;\n entries: ({\n name: string;\n type: \"file\" | \"directory\" | \"other\";\n })[];\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"name":"list","description":"List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"Directory to list. Defaults to the session workspace; a relative path resolves against it."}}}},{"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":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":6,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":7,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl b/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl index 99eaf6e4ee..2cde7d9e42 100644 --- a/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl +++ b/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Exercise the six PTY tools in order, including one missing-session signal error, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":0,"data":{"title":"Exercise the six PTY tools","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse a terminal session only when work needs persistent terminal state or interactive stdin; prefer bash/read/write/edit for bounded one-shot operations. Track every terminal session id and close sessions that no longer matter. An inferred_idle or timeout result does not prove the foreground command exited.\n\nTrack 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.\n\nUse 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.\n\nUse 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.","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"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":"terminal_close","description":"Close one persistent terminal and wait until its captured owned process tree is gone.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."}},"required":["sessionId"]}},{"name":"terminal_list","description":"List persistent terminal sessions owned by the current agent.","parameters":{"type":"object","properties":{}}},{"name":"terminal_open","description":"Create a persistent, owner-isolated terminal session from a registered backend type. Use this for shell or REPL state that must survive across tool calls.","parameters":{"type":"object","properties":{"type":{"type":"string","description":"Registered terminal backend type, usually \"shell\"."},"name":{"type":"string","description":"Optional owner-local display name such as \"main\" or \"gdb\"."},"cwd":{"type":"string","description":"Initial working directory. Defaults to the deployment workspace root."}},"required":["type"]}},{"name":"terminal_read","description":"Read a bounded page of retained output from a persistent terminal without sending input.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"offset":{"type":"number","description":"Newest-relative line offset (default 0)."},"count":{"type":"number","description":"Requested line count (default 500; backend caps apply)."}},"required":["sessionId"]}},{"name":"terminal_send","description":"Send text to a persistent terminal. By default Enter is submitted and the call waits for a prompt, stdin wait, output silence, timeout, or session exit. Background mode returns a task id for task_output/task_kill.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id returned by terminal_open or terminal_list."},"text":{"type":"string","description":"UTF-8 text to write to the terminal."},"submit":{"type":"boolean","description":"Submit Enter after text (default true). Set false for control characters or incomplete REPL input."},"run_in_background":{"type":"boolean","description":"Return a task id immediately; collect with task_output or stop with task_kill."}},"required":["sessionId","text"]}},{"name":"terminal_signal","description":"Send an allowed signal to the current foreground process group of a persistent terminal.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"signal":{"type":"string","description":"Signal to deliver. Shell-targeted SIGKILL is rejected; use terminal_close.","enum":["SIGINT","SIGTERM","SIGKILL","SIGTSTP","SIGHUP"]}},"required":["sessionId","signal"]}},{"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":true,"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for.\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse a terminal session only when work needs persistent terminal state or interactive stdin; prefer bash/read/write/edit for bounded one-shot operations. Track every terminal session id and close sessions that no longer matter. An inferred_idle or timeout result does not prove the foreground command exited.\n\nTrack 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.\n\nUse 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.\n\nUse 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.","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"name":"list","description":"List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"Directory to list. Defaults to the session workspace; a relative path resolves against it."}}}},{"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":"terminal_close","description":"Close one persistent terminal and wait until its captured owned process tree is gone.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."}},"required":["sessionId"]}},{"name":"terminal_list","description":"List persistent terminal sessions owned by the current agent.","parameters":{"type":"object","properties":{}}},{"name":"terminal_open","description":"Create a persistent, owner-isolated terminal session from a registered backend type. Use this for shell or REPL state that must survive across tool calls.","parameters":{"type":"object","properties":{"type":{"type":"string","description":"Registered terminal backend type, usually \"shell\"."},"name":{"type":"string","description":"Optional owner-local display name such as \"main\" or \"gdb\"."},"cwd":{"type":"string","description":"Initial working directory. Defaults to the deployment workspace root."}},"required":["type"]}},{"name":"terminal_read","description":"Read a bounded page of retained output from a persistent terminal without sending input.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"offset":{"type":"number","description":"Newest-relative line offset (default 0)."},"count":{"type":"number","description":"Requested line count (default 500; backend caps apply)."}},"required":["sessionId"]}},{"name":"terminal_send","description":"Send text to a persistent terminal. By default Enter is submitted and the call waits for a prompt, stdin wait, output silence, timeout, or session exit. Background mode returns a task id for task_output/task_kill.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id returned by terminal_open or terminal_list."},"text":{"type":"string","description":"UTF-8 text to write to the terminal."},"submit":{"type":"boolean","description":"Submit Enter after text (default true). Set false for control characters or incomplete REPL input."},"run_in_background":{"type":"boolean","description":"Return a task id immediately; collect with task_output or stop with task_kill."}},"required":["sessionId","text"]}},{"name":"terminal_signal","description":"Send an allowed signal to the current foreground process group of a persistent terminal.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"signal":{"type":"string","description":"Signal to deliver. Shell-targeted SIGKILL is rejected; use terminal_close.","enum":["SIGINT","SIGTERM","SIGKILL","SIGTSTP","SIGHUP"]}},"required":["sessionId","signal"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"pty-spawn","name":"terminal_open","argumentsDelta":"{\"type\":\"shell\",\"name\":\"main\"}"}}} {"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-spawn","name":"terminal_open","arguments":"{\"type\":\"shell\",\"name\":\"main\"}"}}}} diff --git a/examples/tui-agent/tests/snapshots/code-mode-dispatch-spill/terminal.expected.txt b/examples/tui-agent/tests/snapshots/code-mode-dispatch-spill/terminal.expected.txt index aad4b2cd50..7a2024ac06 100644 --- a/examples/tui-agent/tests/snapshots/code-mode-dispatch-spill/terminal.expected.txt +++ b/examples/tui-agent/tests/snapshots/code-mode-dispatch-spill/terminal.expected.txt @@ -59,7 +59,7 @@ buffer style 1-1 inverse 27| "────────────────────────────────────────────────────────────────────────────────────────────────────" style 0-99 dim -28| "deepseek-v4-flash /workspace/project ↑123 ↓208 cache 99% 3% c" +28| "deepseek-v4-flash /workspace/project ↑123 ↓208 cache 99% 4% c" style 0-93 dim style 96-99 dim 29-35| diff --git a/packages/core/tools/tests/gen-tool-catalog.spec.ts b/packages/core/tools/tests/gen-tool-catalog.spec.ts index 3754595f56..974d88c18c 100644 --- a/packages/core/tools/tests/gen-tool-catalog.spec.ts +++ b/packages/core/tools/tests/gen-tool-catalog.spec.ts @@ -23,7 +23,7 @@ describe('gen-tool-catalog collectToolCatalog', () => { it('boots every shipped tool package and harvests its model-facing schemas', async () => { const catalog = await collectToolCatalog() const names = catalog.flatMap(entry => entry.schemas.map(s => s.name)).sort() - expect(names).toEqual(['ask_user_question', 'bash', 'cordis_inspect', 'cordis_mount', 'cordis_unmount', 'create_goal', 'edit', 'exit_plan_mode', 'get_goal', 'glob', 'grep', 'lsp', 'ralph', 'read', 'run_code', 'session_event_read', 'session_event_search', 'session_event_trace', 'session_search', 'session_trace', 'skill', 'subagent', 'task_kill', 'task_list', 'task_output', 'terminal_close', 'terminal_list', 'terminal_open', 'terminal_read', 'terminal_send', 'terminal_signal', 'todo_write', 'update_goal', 'web_fetch', 'web_search', 'workflow', 'write']) + expect(names).toEqual(['ask_user_question', 'bash', 'cordis_inspect', 'cordis_mount', 'cordis_unmount', 'create_goal', 'edit', 'exit_plan_mode', 'get_goal', 'glob', 'grep', 'list', 'lsp', 'ralph', 'read', 'run_code', 'session_event_read', 'session_event_search', 'session_event_trace', 'session_search', 'session_trace', 'skill', 'subagent', 'task_kill', 'task_list', 'task_output', 'terminal_close', 'terminal_list', 'terminal_open', 'terminal_read', 'terminal_send', 'terminal_signal', 'todo_write', 'update_goal', 'web_fetch', 'web_search', 'workflow', 'write']) // Every tool carries a JSON-Schema `parameters` object (what the model sees). for (const entry of catalog) { for (const schema of entry.schemas) { diff --git a/packages/fs/tool-fs/README.i18n.yaml b/packages/fs/tool-fs/README.i18n.yaml index 13f1ecd649..e6f4ccf9c0 100644 --- a/packages/fs/tool-fs/README.i18n.yaml +++ b/packages/fs/tool-fs/README.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 -README.md: 4ff9b043525e8e7a0b59e3d91410951d88bb9a69 -README.zh.md: f94a903c9c37f7d45b7f8cebabe21082388bd041 +# pnpm run verify-translation-pairing --write packages/fs/tool-fs/README.md +README.md: 08a4f74b928a38b92fdce5f6a03dd7c6c8f0af7c +README.zh.md: cdb45a12eb644e4882f7b92ac77b5bc7fc33f906 diff --git a/packages/fs/tool-fs/README.md b/packages/fs/tool-fs/README.md index 4ff9b04352..08a4f74b92 100644 --- a/packages/fs/tool-fs/README.md +++ b/packages/fs/tool-fs/README.md @@ -2,23 +2,24 @@ English | [中文](README.zh.md) -The **model-facing filesystem tools** — `read`, `write`, `edit` — and their **executor**. This is the consumer layer of the filesystem stack: it owns tool names, JSON schemas, argument validation, prompt sections, **read windowing**, and result formatting. It reads/writes/edits through the `ctx.fs` provider seam ([`@deepseek-ai/dsh-fs`](../fs)) **directly** — it injects `fs` (plus `tools`/`systemPrompt`), **not** a policy service. The freshness/observation policy is contributed by a separate plugin ([`@deepseek-ai/dsh-fs-policy`](../fs-policy)) through the `fs/*` event gate; the tool is not method-coupled to it. +The **model-facing filesystem tools** — `list`, `read`, `write`, `edit` — and their **executor**. This is the consumer layer of the filesystem stack: it owns tool names, JSON schemas, argument validation, prompt sections, **read windowing**, **listing order**, and result formatting. It reads/writes/edits through the `ctx.fs` provider seam ([`@deepseek-ai/dsh-fs`](../fs)) **directly** — it injects `fs` (plus `tools`/`systemPrompt`), **not** a policy service. The freshness/observation policy is contributed by a separate plugin ([`@deepseek-ai/dsh-fs-policy`](../fs-policy)) through the `fs/*` event gate; the tool is not method-coupled to it. ```ts ignore-check // Default deployment: a ctx.fs provider, the policy plugin, then the tools. await ctx.plugin(LocalFileSystem, { cwd: process.cwd() }) // @deepseek-ai/dsh-fs-local await ctx.plugin(FsPolicy) // @deepseek-ai/dsh-fs-policy (policy gate) -await ctx.plugin(ToolFs) // this package — registers read/write/edit +await ctx.plugin(ToolFs) // this package — registers list/read/write/edit ``` `@deepseek-ai/dsh-fs-policy` is **optional**: omit it and the tools run against the bare provider (unconditional write/overwrite/edit, no observed-state). A deployment that loads these tools is expected to also load it, so the behavior is read-before-write/edit. ## Config -All keys are optional; the defaults are the shipped read caps. +All keys are optional; the defaults are the shipped listing and read caps. | Key | Default | Meaning | |---|---|---| +| `listMaxEntries` | `200` | Entries one `list` call renders inline; the footer still reports the complete directory's size and composition. | | `readLimit` | `2000` | Default and maximum lines returned by one `read` call (the tool schema advertises it as the `limit` default). | | `readMaxLineLength` | `2000` | Characters kept per line before truncation (the suffix names the cap). | | `readMaxBytes` | `51200` | Byte cap on one `read` call's selected lines; overflow ends the window with a "capped" footer. | @@ -28,18 +29,20 @@ All keys are optional; the defaults are the shipped read caps. | Tool | Arguments | Behavior | |---|---|---| +| `list` | `path?` | Direct children of one directory with their type, defaulting to the session workspace. Ordered directories first, then files, then non-regular children, each alphabetical, and capped at the configured `listMaxEntries` (200). | | `read` | `file_path`, `offset?`, `limit?` | Line-numbered UTF-8 content with a pagination footer. `offset` is 1-based; `limit` defaults to and caps at the configured `readLimit` (2000). | | `write` | `file_path`, `content` | Create or fully replace a file. With the policy plugin: overwriting an existing file requires a prior `read` at the unchanged version; creating a new file does not. Without it: unconditional. | | `edit` | `file_path`, non-empty `old_string`, `new_string`, `replace_all?` | Literal replacement; unique match required unless `replace_all` is true. With the policy plugin: requires a prior `read` (any window) and the file unchanged since. Without it: unconditional. | Field names are snake_case to match Claude Code and existing harness tool schemas. -Canonical successes are `read` → `{ path, offset, lines: [{ number, text }], totalLines }`, `write` → `{ path, operation: 'create' | 'update', before: string | null, after }`, and `edit` → `{ path, before, after }`. Native renderers preserve the line-numbered read and mutation acknowledgements below. Write/edit derive replayable diff-card metadata from these values; the values themselves are execution-local and are not added to `tool/result`. +Canonical successes are `list` → `{ path, entries: [{ name, type: 'file' | 'directory' | 'other' }] }`, `read` → `{ path, offset, lines: [{ number, text }], totalLines }`, `write` → `{ path, operation: 'create' | 'update', before: string | null, after }`, and `edit` → `{ path, before, after }`. Native renderers preserve the line-numbered read and mutation acknowledgements below. Write/edit derive replayable diff-card metadata from these values; the values themselves are execution-local and are not added to `tool/result`. ## The tool is the executor; policy is an event gate The tools do **not** inject a policy service or inspect any cache. Each tool resolves the path via `ctx.fs.resolve(path, { cwd, signal })` — passing the calling agent's session cwd (`exec.agent.session.header.cwd`) so a relative path resolves against the session's workspace, matching `dsh-tool-bash`, and forwarding tool cancellation through resolution (see [the per-session cwd Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md)) — then: +- **list** — one `ctx.fs.listDir`; the seam already answers absence with `FS_NOT_FOUND` and a non-directory target with `FS_NOT_DIRECTORY`, so no probe precedes it. No `fs/observed`: a listing reads no file content and must not satisfy the read-before-write gate. (0 stat.) - **read** — one `ctx.fs.stat` (type + size routing + version), then `readText`/`streamText`, then builds the line window, then emits `fs/observed` with a plain `ctx.emit`. (1 stat.) - **write** — `ctx.waterfall('fs/write-intent', target, exec, () => undefined)` for the optional guard, then `ctx.fs.writeText(target, content, intent)`, then `fs/observed`. (0 stat.) - **edit** — `ctx.waterfall('fs/edit-intent', target, exec, () => undefined)` for the optional guard, then `ctx.fs.editText(target, edit, intent)`, then `fs/observed`. (0 stat.) @@ -50,9 +53,9 @@ The tool passes `exec` (the tool-execution context) as the opaque `actor` on eve `fs/observed` fires AFTER the read/write/edit already succeeded, via a plain `ctx.emit`. A listener is contractually a synchronous, side-effect-only recorder (`@deepseek-ai/dsh-fs-policy`'s is a `WeakMap.set`); the tool does not guard the emit, so a listener that throws would surface as the tool's `isError` result — async or fallible observation does not belong on this event. -`read` opts into concurrent scheduling because its only mutation is the synchronous version recorder. Recorder races fail closed when a later `write` or `edit` re-checks the version under its target lock; both mutation tools remain exclusive. See the [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md). +`list` and `read` opt into concurrent scheduling — `list` mutates nothing at all, and `read`'s only mutation is the synchronous version recorder. Recorder races fail closed when a later `write` or `edit` re-checks the version under its target lock; both mutation tools remain exclusive. See the [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md). -The package root exports only the Cordis plugin contract (`name`, `inject`, `Config`, and `apply`). Read rendering (line windowing + output formatting) lives in `src/read-render.ts` (Cordis-free, independently unit-tested); `src/read.ts`/`write.ts`/`edit.ts` are the tool executors and `src/index.ts` composes them. +The package root exports only the Cordis plugin contract (`name`, `inject`, `Config`, and `apply`). Pure presentation lives beside the executors and is independently unit-tested: read windowing and output formatting in `src/read-render.ts`, listing order and envelope in `src/list-render.ts` (both Cordis-free); `src/list.ts`/`read.ts`/`write.ts`/`edit.ts` are the tool executors and `src/index.ts` composes them. ## Model Experience @@ -60,7 +63,13 @@ The package root exports only the Cordis plugin contract (`name`, `inject`, `Con #### What the model sees -Every request in this plugin's registration scope receives the independently registered read, write, and edit guidance below. Scoped tool restrictions can hide schemas without removing these sections. +Every request in this plugin's registration scope receives the independently registered list, read, write, and edit guidance below. Scoped tool restrictions can hide schemas without removing these sections. + +##### List guidance + +```markdown +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +``` ##### Read guidance @@ -92,7 +101,7 @@ Prefix-stable while the plugin scope and guidance text are unchanged. Tool restr #### What the model sees -The model sees the generated [`read`, `write`, and `edit` schemas](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs), with snake_case arguments. Scoped tool restrictions can remove any definition for one agent. +The model sees the generated [`list`, `read`, `write`, and `edit` schemas](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs), with snake_case arguments. Scoped tool restrictions can remove any definition for one agent. #### Token effect @@ -102,6 +111,20 @@ Fixed schema cost on every request in that tool view. Prefix-stable while the visible tool definitions and order are unchanged. Registration lifecycle or scoped restrictions may invalidate reuse from the first changed schema token. +### List result + +#### What the model sees + +A successful listing is exactly ``, newline, `directory`, newline, ``, one line per entry, a blank line, one footer, and ``. A directory entry carries a trailing `/` and a non-regular child a trailing `@`; a regular file carries neither. The footer is exactly `(Empty directory)`, `( entries: directories, files)` — with `, other` appended only when such a child exists, and singulars where the count is one — or, when the view is capped, `(Showing of entries: directories, files. Entries are directories first, then files, each alphabetical; list a subdirectory to see the rest.)`. The complete count and composition are stated whether or not the view was capped, so a partial listing can never read as a whole directory. + +#### Token effect + +Listing output is capped by `listMaxEntries`; the retained call and result are resent until compaction. + +#### KV Cache effect + +Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Read result #### What the model sees @@ -134,7 +157,7 @@ Append-only; newly visible content follows the reusable request prefix and does #### What the model sees -Failures are normalized as `Error: `. This package's stable validation and read messages are `file_path must be a non-empty string`, `limit must be less than or equal to `, `old_string must be a non-empty string`, `old_string and new_string must differ`, `cannot read "": not found`, `cannot read "": not a regular file`, and `offset is out of range for "" ( lines)`; provider and policy templates are quoted in their package READMEs. +Failures are normalized as `Error: `. This package's stable validation and read messages are `file_path must be a non-empty string`, `path must be a non-empty string when given`, `limit must be less than or equal to `, `old_string must be a non-empty string`, `old_string and new_string must differ`, `cannot read "": not found`, `cannot read "": not a regular file`, and `offset is out of range for "" ( lines)`; provider and policy templates are quoted in their package READMEs. #### Token effect @@ -146,6 +169,6 @@ Append-only; newly visible content follows the reusable request prefix and does ## Known Limitations and Deferred Work -- **No model-facing directory listing ships** — `ctx.fs.listDir` serves provider code such as skill discovery, while the sibling [`dsh-tool-fs-search`](../tool-fs-search/) package supplies bash-backed `glob` and `grep` rather than extending the filesystem seam. +- **`list` reads one directory level and has no spill path** — recursion, pagination, and per-directory child counts are absent, and a listing past `listMaxEntries` is summarized by its footer rather than saved anywhere retrievable; the model lists a subdirectory instead. - **`read` handles UTF-8 text files only** — binary-safe reads and PDF/image/multimodal content are deferred; a directory target is `FS_NOT_REGULAR_FILE`. - **No timeout surface** — `read`/`write`/`edit` take no timeout argument and declare no `timeout-policy` budget; cancellation rides `exec.signal` only (the deliberate [fs-family stance](../README.md)). diff --git a/packages/fs/tool-fs/README.zh.md b/packages/fs/tool-fs/README.zh.md index f94a903c9c..cdb45a12eb 100644 --- a/packages/fs/tool-fs/README.zh.md +++ b/packages/fs/tool-fs/README.zh.md @@ -2,23 +2,24 @@ [English](README.md) | 中文 -**面向模型的文件系统工具**（`read`、`write`、`edit`）及其**执行器**。这是文件系统栈的消费方层：拥有工具名称、JSON schema、参数校验、提示词段、**读取窗口逻辑** 和结果格式化。它**直接** 通过 `ctx.fs` 提供方 seam（[`@deepseek-ai/dsh-fs`](../fs)）读取/写入/编辑：注入 `fs`（以及 `tools`/`systemPrompt`），**不** 注入政策服务。新鲜度/观察政策由独立插件（[`@deepseek-ai/dsh-fs-policy`](../fs-policy)）通过 `fs/*` 事件门禁贡献；工具不与其方法耦合。 +**面向模型的文件系统工具**（`list`、`read`、`write`、`edit`）及其**执行器**。这是文件系统栈的消费方层：拥有工具名称、JSON schema、参数校验、提示词段、**读取窗口逻辑**、**列出顺序** 和结果格式化。它**直接** 通过 `ctx.fs` 提供方 seam（[`@deepseek-ai/dsh-fs`](../fs)）读取/写入/编辑：注入 `fs`（以及 `tools`/`systemPrompt`），**不** 注入政策服务。新鲜度/观察政策由独立插件（[`@deepseek-ai/dsh-fs-policy`](../fs-policy)）通过 `fs/*` 事件门禁贡献；工具不与其方法耦合。 ```ts ignore-check // Default deployment: a ctx.fs provider, the policy plugin, then the tools. await ctx.plugin(LocalFileSystem, { cwd: process.cwd() }) // @deepseek-ai/dsh-fs-local await ctx.plugin(FsPolicy) // @deepseek-ai/dsh-fs-policy (policy gate) -await ctx.plugin(ToolFs) // this package — registers read/write/edit +await ctx.plugin(ToolFs) // this package — registers list/read/write/edit ``` `@deepseek-ai/dsh-fs-policy` 是**可选的**：省略时，工具直接使用裸提供方（无条件写入/覆盖/编辑，无已观察状态）。加载这些工具的部署也应加载该插件，从而提供编辑前读取行为。 ## 配置 -所有键均为可选；默认值是随产品交付的读取上限。 +所有键均为可选；默认值是随产品交付的列出与读取上限。 | 键 | 默认值 | 含义 | |---|---|---| +| `listMaxEntries` | `200` | 一次 `list` 调用内联渲染的条目数；footer 仍会报告整个目录的规模与构成。 | | `readLimit` | `2000` | 一次 `read` 调用返回的默认和最大行数（工具 schema 将其声明为 `limit` 默认值）。 | | `readMaxLineLength` | `2000` | 每行截断前保留的字符数（后缀会说明上限）。 | | `readMaxBytes` | `51200` | 一次 `read` 调用所选行的字节上限；溢出时以「已达上限」footer 结束窗口。 | @@ -28,18 +29,20 @@ await ctx.plugin(ToolFs) // this package — re | 工具 | 参数 | 行为 | |---|---|---| +| `list` | `path?` | 单个目录的直接子项及其类型，默认取会话工作区。顺序为先目录、再文件、最后非常规子项，各组内按字母序排列，并受配置的 `listMaxEntries`（200）限制。 | | `read` | `file_path`、`offset?`、`limit?` | 带行号的 UTF-8 内容和分页 footer。`offset` 从 1 开始；`limit` 默认为配置的 `readLimit`（2000），上限也为该值。 | | `write` | `file_path`、`content` | 创建文件或完整替换文件。有政策插件时：覆盖现有文件要求先在未变版本上执行 `read`；创建新文件不需要。没有插件时：无条件执行。 | | `edit` | `file_path`、非空 `old_string`、`new_string`、`replace_all?` | 字面量替换；除非 `replace_all` 为 true，否则要求唯一匹配。有政策插件时：要求先执行 `read`（任何窗口），且文件此后未变。没有插件时：无条件执行。 | 字段名使用 snake_case，与 Claude Code 和现有 harness 工具 schema 一致。 -规范成功值分别为：`read` → `{ path, offset, lines: [{ number, text }], totalLines }`，`write` → `{ path, operation: 'create' | 'update', before: string | null, after }`，`edit` → `{ path, before, after }`。Native 渲染器会保留下方带行号的读取结果和变更确认。写入/编辑从这些值派生可回放的 diff 卡片元数据；值本身仅用于执行，不会添加到 `tool/result`。 +规范成功值分别为：`list` → `{ path, entries: [{ name, type: 'file' | 'directory' | 'other' }] }`，`read` → `{ path, offset, lines: [{ number, text }], totalLines }`，`write` → `{ path, operation: 'create' | 'update', before: string | null, after }`，`edit` → `{ path, before, after }`。Native 渲染器会保留下方带行号的读取结果和变更确认。写入/编辑从这些值派生可回放的 diff 卡片元数据；值本身仅用于执行，不会添加到 `tool/result`。 ## 工具就是执行器；政策是事件门禁 工具**不** 注入政策服务，也不检查任何缓存。每个工具通过 `ctx.fs.resolve(path, { cwd, signal })` 解析路径；它会传入调用 agent（智能体）的会话 cwd（`exec.agent.session.header.cwd`），使相对路径以会话工作区为基准解析并与 `dsh-tool-bash` 一致，同时把工具取消转发到解析过程（见[每会话 cwd Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md)）。随后执行： +- **list**：一次 `ctx.fs.listDir`；seam 已经把不存在报告为 `FS_NOT_FOUND`、把非目录目标报告为 `FS_NOT_DIRECTORY`，因此前面不需要任何探测。不发出 `fs/observed`：列出不读取任何文件内容，也不得满足编辑前读取门禁。（0 次 stat。） - **read**：一次 `ctx.fs.stat`（用于类型、大小路由和版本），随后调用 `readText`/`streamText`，构建行窗口，再发出 `fs/observed`，使用普通 `ctx.emit`。（1 次 stat。） - **write**：调用 `ctx.waterfall('fs/write-intent', target, exec, () => undefined)` 取得可选防护，然后调用 `ctx.fs.writeText(target, content, intent)`，再发出 `fs/observed`。（0 次 stat。） - **edit**：调用 `ctx.waterfall('fs/edit-intent', target, exec, () => undefined)` 取得可选防护，然后调用 `ctx.fs.editText(target, edit, intent)`，再发出 `fs/observed`。（0 次 stat。） @@ -50,9 +53,9 @@ await ctx.plugin(ToolFs) // this package — re `fs/observed` 在读取/写入/编辑已经成功之后，通过普通 `ctx.emit` 发出。监听器的契约是同步且只有副作用的记录器（`@deepseek-ai/dsh-fs-policy` 使用 `WeakMap.set`）；工具不保护这次发出，因此监听器抛出会作为工具的 `isError` 结果出现。异步或可能失败的观察不属于该事件。 -`read` 允许并发调度，因为其唯一变更是同步版本记录器。稍后的 `write` 或 `edit` 会在目标锁内重新检查版本，因此记录器竞态会以拒绝方式关闭；两个变更工具仍保持互斥。见[并行工具调用 Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md)。 +`list` 与 `read` 都允许并发调度：`list` 完全不做任何变更，而 `read` 的唯一变更是同步版本记录器。稍后的 `write` 或 `edit` 会在目标锁内重新检查版本，因此记录器竞态会以拒绝方式关闭；两个变更工具仍保持互斥。见[并行工具调用 Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md)。 -包根目录只导出 Cordis 插件契约（`name`、`inject`、`Config` 和 `apply`）。读取渲染（行窗口与输出格式化）位于 `src/read-render.ts`（不依赖 Cordis，单独进行单元测试）；`src/read.ts`/`write.ts`/`edit.ts` 是工具执行器，`src/index.ts` 负责组合。 +包根目录只导出 Cordis 插件契约（`name`、`inject`、`Config` 和 `apply`）。纯展示逻辑与执行器并列存放并单独进行单元测试：读取窗口与输出格式化位于 `src/read-render.ts`，列出顺序与包络位于 `src/list-render.ts`（两者均不依赖 Cordis）；`src/list.ts`/`read.ts`/`write.ts`/`edit.ts` 是工具执行器，`src/index.ts` 负责组合。 ## 模型体验 @@ -60,7 +63,13 @@ await ctx.plugin(ToolFs) // this package — re #### 模型看到的内容 -该插件注册作用域内的每个请求都会收到下方独立注册的 read、write 与 edit 指导。作用域工具限制可以隐藏 schema，而不移除这些段。 +该插件注册作用域内的每个请求都会收到下方独立注册的 list、read、write 与 edit 指导。作用域工具限制可以隐藏 schema，而不移除这些段。 + +##### List 指导 + +```markdown +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +``` ##### Read 指导 @@ -92,7 +101,7 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces #### 模型看到的内容 -模型会看到已生成的 [`read`、`write` 和 `edit` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs)，参数使用 snake_case。作用域工具限制可以为某个 agent 移除任一定义。 +模型会看到已生成的 [`list`、`read`、`write` 和 `edit` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs)，参数使用 snake_case。作用域工具限制可以为某个 agent 移除任一定义。 #### Token 影响 @@ -102,6 +111,20 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces 只要可见工具定义和顺序不变，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。 +### 列出结果 + +#### 模型看到的内容 + +成功列出结果精确为 ``、换行、`directory`、换行、``、每个条目一行、一个空行、一条 footer 和 ``。目录条目带尾部 `/`，非常规子项带尾部 `@`，常规文件两者都不带。footer 精确为 `(Empty directory)`、`( entries: directories, files)`（仅当存在此类子项时才追加 `, other`，计数为一时使用单数形式），或在视图被截断时为 `(Showing of entries: directories, files. Entries are directories first, then files, each alphabetical; list a subdirectory to see the rest.)`。无论视图是否被截断，都会说明完整计数与构成，因此部分列出结果绝不会被读成整个目录。 + +#### Token 影响 + +列出输出受 `listMaxEntries` 限制；保留的调用与结果会反复发送，直到上下文压缩。 + +#### 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。 + ### 读取结果 #### 模型看到的内容 @@ -134,7 +157,7 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces #### 模型看到的内容 -失败会规范化为 `Error: `。本包稳定的校验和读取消息是 `file_path must be a non-empty string`、`limit must be less than or equal to `、`old_string must be a non-empty string`、`old_string and new_string must differ`、`cannot read "": not found`、`cannot read "": not a regular file` 和 `offset is out of range for "" ( lines)`；提供方和政策模板在各自包的 README 中逐字列出。 +失败会规范化为 `Error: `。本包稳定的校验和读取消息是 `file_path must be a non-empty string`、`path must be a non-empty string when given`、`limit must be less than or equal to `、`old_string must be a non-empty string`、`old_string and new_string must differ`、`cannot read "": not found`、`cannot read "": not a regular file` 和 `offset is out of range for "" ( lines)`；提供方和政策模板在各自包的 README 中逐字列出。 #### Token 影响 @@ -146,6 +169,6 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces ## 已知限制与延期工作 -- **未交付面向模型的目录列出工具**：`ctx.fs.listDir` 服务于 skill（技能）发现等提供方代码，同级 [`dsh-tool-fs-search`](../tool-fs-search/) 包则提供基于 bash 的 `glob` 与 `grep`，而不是扩展文件系统 seam。 +- **`list` 只读取一层目录，且没有溢出落盘路径**：不提供递归、分页和逐目录子项计数，超出 `listMaxEntries` 的部分只由 footer 概括，不会保存到任何可取回的位置；模型改为列出对应子目录。 - **`read` 只处理 UTF-8 文本文件**：二进制安全读取和 PDF/图像/多模态内容均延期处理；目录目标为 `FS_NOT_REGULAR_FILE`。 - **没有超时接口**：`read`/`write`/`edit` 不接受超时参数，也不声明 `timeout-policy` 预算；取消只通过 `exec.signal` 传递（见有意采用的 [fs 能力族立场](../README.md)）。 diff --git a/packages/fs/tool-fs/package.json b/packages/fs/tool-fs/package.json index 737f7ac26b..936d125013 100644 --- a/packages/fs/tool-fs/package.json +++ b/packages/fs/tool-fs/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-tool-fs", - "description": "Model-facing filesystem tools (read, write, edit) over the DeepSeek Harness filesystem seam (ctx.fs)", + "description": "Model-facing filesystem tools (list, read, write, edit) over the DeepSeek Harness filesystem seam (ctx.fs)", "version": "0.0.1", "private": true, "type": "module", diff --git a/packages/fs/tool-fs/src/index.ts b/packages/fs/tool-fs/src/index.ts index a4c96d606b..c8376ed123 100644 --- a/packages/fs/tool-fs/src/index.ts +++ b/packages/fs/tool-fs/src/index.ts @@ -1,16 +1,19 @@ /** - * Model-facing read, write, and edit tools over `ctx.fs`. This package owns schemas, validation, - * read windows, formatting, and observation events, never a concrete provider. An optional - * event policy supplies mutation guards; without one the tools use unconditional provider calls. + * Model-facing list, read, write, and edit tools over `ctx.fs`. This package owns schemas, + * validation, read windows, listing order, formatting, and observation events, never a concrete + * provider. An optional event policy supplies mutation guards; without one the tools use + * unconditional provider calls. * @module @deepseek-ai/dsh-tool-fs */ import type { Context } from 'cordis' import z from 'schemastery' import type {} from '@deepseek-ai/dsh-user-approval' +import { applyListTool } from './list.ts' import { applyReadTool, READ_LIMIT, STREAM_MIN_SIZE } from './read.ts' import { applyWriteTool } from './write.ts' import { applyEditTool } from './edit.ts' +import { LIST_MAX_ENTRIES } from './list-render.ts' import { READ_MAX_BYTES, READ_MAX_LINE_LENGTH } from './read-render.ts' import { FsSandboxSurface } from './sandbox.ts' @@ -22,6 +25,8 @@ export const inject = ['tools', 'fs', 'systemPrompt'] /** Plugin config (all optional — `Config` supplies the defaults). */ export interface Config { + /** Maximum entries one `list` call renders inline; the footer still reports the complete count. */ + listMaxEntries?: number /** Default and maximum number of lines returned by one `read` call. */ readLimit?: number /** Maximum characters returned for a single line before truncation. */ @@ -33,6 +38,7 @@ export interface Config { } export const Config: z = z.object({ + listMaxEntries: z.number().default(LIST_MAX_ENTRIES), readLimit: z.number().default(READ_LIMIT), readMaxLineLength: z.number().default(READ_MAX_LINE_LENGTH), readMaxBytes: z.number().default(READ_MAX_BYTES), @@ -42,21 +48,23 @@ export const Config: z = z.object({ /** The shape after schemastery applied the defaults. */ type ResolvedConfig = Required -/** Every read cap counts lines/chars/bytes — a positive integer, or windowing arithmetic misbehaves silently. */ +/** Every read or listing cap counts lines/chars/bytes/entries — a positive integer, or windowing arithmetic misbehaves silently. */ function assertPositiveInteger(name: string, value: number): void { if (!Number.isInteger(value) || value < 1) { throw new Error(`tool-fs: ${name} must be a positive integer`) } } -/** Register the full `read`/`write`/`edit` filesystem tool suite. */ +/** Register the full `list`/`read`/`write`/`edit` filesystem tool suite. */ export function apply(ctx: Context, config: Config): void { // schemastery (Config) has already filled every defaulted field. const resolved = config as ResolvedConfig + assertPositiveInteger('listMaxEntries', resolved.listMaxEntries) assertPositiveInteger('readLimit', resolved.readLimit) assertPositiveInteger('readMaxLineLength', resolved.readMaxLineLength) assertPositiveInteger('readMaxBytes', resolved.readMaxBytes) assertPositiveInteger('readStreamMinSize', resolved.readStreamMinSize) + applyListTool(ctx, { maxEntries: resolved.listMaxEntries }) applyReadTool(ctx, { limit: resolved.readLimit, maxLineLength: resolved.readMaxLineLength, diff --git a/packages/fs/tool-fs/src/list-render.ts b/packages/fs/tool-fs/src/list-render.ts new file mode 100644 index 0000000000..d7a65cbb27 --- /dev/null +++ b/packages/fs/tool-fs/src/list-render.ts @@ -0,0 +1,82 @@ +/** + * Pure listing presentation: order one directory's direct children so a capped + * view still shows the navigable structure, and render the model-facing + * envelope. Cordis-free and independently unit-tested, mirroring + * {@link module:@deepseek-ai/dsh-tool-fs/read-render}. + * @module @deepseek-ai/dsh-tool-fs/list-render + */ + +/** Default and maximum number of entries one `list` call renders inline (the `listMaxEntries` config). */ +export const LIST_MAX_ENTRIES = 200 + +/** One direct child in a rendered listing — the canonical entry shape the tool returns. */ +export interface ListedEntry { + /** Basename of the child inside the listed directory. */ + name: string + /** Whether the child is a regular file, a directory, or something else (symlink, socket, device). */ + type: 'file' | 'directory' | 'other' +} + +/** + * Order direct children so truncation cannot hide the directory tree: + * directories first, then files, then everything else, each group by name. + * + * The provider seam returns children in stable name order, which puts a + * subdirectory wherever the alphabet puts it; capping such a list can drop every + * subdirectory and leave the model believing a directory holds only files. This + * is the listing counterpart of the `glob` coverage footer. + * + * @param entries - the seam's direct children, in any order. + * @returns a new array in directory-first display order; the input is not mutated. + */ +export function orderEntries(entries: readonly T[]): T[] { + const rank = { directory: 0, file: 1, other: 2 } + return [...entries].sort((a, b) => rank[a.type] - rank[b.type] || a.name.localeCompare(b.name)) +} + +/** `1 directory` / `4 directories` — a count the model reads as prose, not as `1 directorie(s)`. */ +function count(n: number, singular: string, plural: string): string { + return `${n} ${n === 1 ? singular : plural}` +} + +/** The ` directories, files[, other]` breakdown; the `other` clause appears only when non-empty. */ +function breakdown(entries: readonly ListedEntry[]): string { + const directories = entries.filter(entry => entry.type === 'directory').length + const other = entries.filter(entry => entry.type === 'other').length + const files = entries.length - directories - other + const parts = [count(directories, 'directory', 'directories'), count(files, 'file', 'files')] + if (other > 0) parts.push(`${other} other`) + return parts.join(', ') +} + +/** + * Render the model-facing `list` result: the displayed entries, then a footer + * that always states the COMPLETE listing's size and composition, so a capped + * view can never read as the whole directory. + * + * Directories carry a trailing `/` and non-regular children a trailing `@`, so + * the model can tell what it may descend into without a second call. + * + * @param displayPath - the resolved directory as the backend displays it. + * @param entries - the complete listing, already in {@link orderEntries} order. + * @param maxEntries - how many entries to show inline; the rest are summarized by the footer. + * @returns the model-facing text. + */ +export function formatListOutput(displayPath: string, entries: readonly ListedEntry[], maxEntries: number): string { + const shown = entries.slice(0, maxEntries) + const suffix = { directory: '/', file: '', other: '@' } + const footer = shown.length < entries.length + ? `(Showing ${shown.length} of ${count(entries.length, 'entry', 'entries')}: ${breakdown(entries)}. ` + + 'Entries are directories first, then files, each alphabetical; list a subdirectory to see the rest.)' + : entries.length === 0 + ? '(Empty directory)' + : `(${count(entries.length, 'entry', 'entries')}: ${breakdown(entries)})` + const body = shown.length > 0 + ? `${shown.map(entry => `${entry.name}${suffix[entry.type]}`).join('\n')}\n\n${footer}` + : footer + return `${displayPath} +directory + +${body} +` +} diff --git a/packages/fs/tool-fs/src/list.ts b/packages/fs/tool-fs/src/list.ts new file mode 100644 index 0000000000..de6c6d1ddd --- /dev/null +++ b/packages/fs/tool-fs/src/list.ts @@ -0,0 +1,120 @@ +/** + * Model-facing directory listing. It enumerates ONE directory level through the + * provider seam's `listDir`, orders children so a capped view keeps the + * navigable structure, and renders the entries with their type. + * + * This is the orientation tool: `glob` and `grep` answer "where is the thing I + * can already name", while `list` answers "what is here at all". `rg --files` + * never emits directories, so no pattern makes `glob` describe a directory's + * shape — the gap this tool closes. + * @module @deepseek-ai/dsh-tool-fs/list + */ + +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' +import type { GenericCallView } from '@deepseek-ai/dsh-tools' +import type {} from '@deepseek-ai/dsh-fs' +import type {} from '@deepseek-ai/dsh-system-prompt' +import { formatListOutput, orderEntries } from './list-render.ts' +import { sessionResolveOptions } from './session-cwd.ts' + +/** Resolved list-tool caps — plugin config after defaulting (see `Config` in index.ts). */ +export interface ListToolCaps { + /** Maximum entries rendered inline; the footer still reports the complete listing's size. */ + maxEntries: number +} + +/** Validated `list` arguments after defaulting. */ +export interface ListInput { + /** Directory to list; `.` means the calling agent's session workspace. */ + path: string +} + +/** + * Validate value constraints the schema DSL can't express, and default an + * omitted `path` to `.` — the session workspace, so "what is in this project" + * needs no argument at all. + * + * @param args - the schema-validated `list` arguments. + * @returns the accepted input with `path` defaulted. + */ +export function parseListArgs(args: { path?: string }): ListInput { + if (args.path !== undefined && args.path.trim().length === 0) throw new Error('path must be a non-empty string when given') + return { path: args.path ?? '.' } +} + +/** + * Pending-call presentation: a generic card titled by the directory, with a + * follow-along location so a capable editor can reveal it. + * + * @param args - the raw tool arguments; only `path` is read. + * @returns the generic card view shown while the call runs. + */ +export function presentListCall(args: { path?: string }): GenericCallView { + const path = args.path ?? '.' + return { card: 'generic', title: `List ${path}`, kind: 'read', locations: [{ path }] } +} + +/** + * Register the `list` tool and its system-prompt guidance. + * + * @param ctx - the plugin context; registrations are effects scoped to it, and execution uses its `fs` service. + * @param caps - the deployment's resolved list caps (plugin config after defaulting). + */ +export function applyListTool(ctx: Context, caps: ListToolCaps): void { + ctx.systemPrompt.section({ + name: 'tool:list', + order: 99, + text: 'Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, ' + + 'and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. ' + + 'Reach for glob or grep once you know the path pattern or the text you are looking for.', + }) + + ctx.tools.register(defineTool({ + name: 'list', + description: 'List the direct children of one directory, with their type. ' + + `Entries are directories first, then files, each alphabetical; the first ${caps.maxEntries} are returned inline and the footer reports the complete count. ` + + 'Unlike glob, this shows subdirectories, so it is how to see what a directory contains.', + parameters: { + path: { type: 'string', description: 'Directory to list. Defaults to the session workspace; a relative path resolves against it.' }, + }, + output: { + schema: { + type: 'object', + additionalProperties: false, + properties: { + path: { type: 'string', required: true }, + entries: { + type: 'array', + required: true, + items: { + type: 'object', + additionalProperties: false, + properties: { + name: { type: 'string', required: true }, + type: { type: 'string', required: true, enum: ['file', 'directory', 'other'] }, + }, + }, + }, + }, + }, + render: (_args, value) => [{ type: 'text', text: formatListOutput(value.path, value.entries, caps.maxEntries) }], + }, + // Listing reads directory metadata only: no content, no version recorded, + // nothing a concurrent call could observe out of order. + isConcurrencySafe: () => true, + async execute(args, exec) { + const input = parseListArgs(args) + const target = await ctx.fs.resolve(input.path, sessionResolveOptions(exec, input.path)) + // No stat first: the seam already answers absence with FS_NOT_FOUND and a + // non-directory target with FS_NOT_DIRECTORY, so a probe would only add a + // round-trip and a second source of truth. (0 stat.) + const entries = await ctx.fs.listDir(target, exec.signal) + return { + path: target.displayPath, + entries: orderEntries(entries).map(({ name, type }) => ({ name, type })), + } + }, + presentCall: presentListCall, + })) +} diff --git a/packages/fs/tool-fs/tests/list-render.spec.ts b/packages/fs/tool-fs/tests/list-render.spec.ts new file mode 100644 index 0000000000..3d0a3ac5ce --- /dev/null +++ b/packages/fs/tool-fs/tests/list-render.spec.ts @@ -0,0 +1,69 @@ +/** + * Pure listing-presentation tests: display ordering and the model-facing + * envelope, exercised without a context or provider. + */ + +import { describe, expect, it } from 'vitest' +import { formatListOutput, orderEntries } from '../src/list-render.ts' +import type { ListedEntry } from '../src/list-render.ts' + +const entry = (name: string, type: ListedEntry['type'] = 'file'): ListedEntry => ({ name, type }) + +describe('orderEntries', () => { + it('groups directories, then files, then other, each by name', () => { + const ordered = orderEntries([ + entry('zeta.txt'), + entry('socket', 'other'), + entry('beta'), + entry('src', 'directory'), + entry('assets', 'directory'), + ]) + expect(ordered.map(e => e.name)).toEqual(['assets', 'src', 'beta', 'zeta.txt', 'socket']) + }) + + it('leaves the input array untouched and preserves extra entry fields', () => { + const input = [{ name: 'b', type: 'file' as const, size: 2 }, { name: 'a', type: 'file' as const, size: 1 }] + const ordered = orderEntries(input) + expect(input.map(e => e.name)).toEqual(['b', 'a']) + expect(ordered).toEqual([{ name: 'a', type: 'file', size: 1 }, { name: 'b', type: 'file', size: 2 }]) + }) +}) + +describe('formatListOutput', () => { + it('marks directories and non-regular children, and counts the whole listing', () => { + expect(formatListOutput('/w', [entry('src', 'directory'), entry('a.txt'), entry('sock', 'other')], 10)).toBe(`/w +directory + +src/ +a.txt +sock@ + +(3 entries: 1 directory, 1 file, 1 other) +`) + }) + + it('omits the "other" clause when every child is a file or a directory', () => { + expect(formatListOutput('/w', [entry('a.txt'), entry('b.txt')], 10)).toContain('(2 entries: 0 directories, 2 files)') + }) + + it('says a one-entry listing in the singular', () => { + expect(formatListOutput('/w', [entry('only', 'directory')], 10)).toContain('(1 entry: 1 directory, 0 files)') + }) + + it('states the complete size and composition when the view is capped', () => { + const entries = [entry('src', 'directory'), ...Array.from({ length: 5 }, (_, i) => entry(`f${i}.txt`))] + const rendered = formatListOutput('/w', entries, 2) + expect(rendered).toContain('src/\nf0.txt\n') + expect(rendered).not.toContain('f2.txt') + expect(rendered).toContain('(Showing 2 of 6 entries: 1 directory, 5 files. ' + + 'Entries are directories first, then files, each alphabetical; list a subdirectory to see the rest.)') + }) + + it('renders an empty directory as a footer alone', () => { + expect(formatListOutput('/w', [], 10)).toBe(`/w +directory + +(Empty directory) +`) + }) +}) diff --git a/packages/fs/tool-fs/tests/tools.spec.ts b/packages/fs/tool-fs/tests/tools.spec.ts index 8f93b524a9..66f88a6348 100644 --- a/packages/fs/tool-fs/tests/tools.spec.ts +++ b/packages/fs/tool-fs/tests/tools.spec.ts @@ -38,6 +38,7 @@ const testToolSignal = new AbortController().signal class FakeFs extends FileSystem { files = new Map() rejectWith?: FsError + dirs = new Map() writeIntents: (FsWriteIntent | undefined)[] = [] editIntents: ({ version: FsVersion } | undefined)[] = [] @@ -66,8 +67,9 @@ class FakeFs extends FileSystem { const content = this.files.get(target.targetKey) ?? '' return (async function* () { yield content })() } - override async listDir(_target: FsTarget): Promise { - return [] + override async listDir(target: FsTarget): Promise { + this.throwIfArmed() + return this.dirs.get(target.targetKey) ?? [] } override async writeText(target: FsTarget, content: string, expected?: FsWriteIntent): Promise { this.throwIfArmed() @@ -139,13 +141,15 @@ describe('session cwd resolution', () => { }) describe('registration', () => { - it('registers read, write, and edit', async () => { + it('registers list, read, write, and edit', async () => { const { ctx } = await setup() - expect(ctx.tools.schemas().map(s => s.name).sort()).toEqual(['edit', 'read', 'write']) + expect(ctx.tools.schemas().map(s => s.name).sort()).toEqual(['edit', 'list', 'read', 'write']) }) - it('declares read parallel-safe while write/edit remain exclusive', async () => { + it('declares list and read parallel-safe while write/edit remain exclusive', async () => { const { ctx } = await setup() + expect(ctx.tools.executionMode({ signal: testToolSignal, callId: CallId('list-safe'), name: 'list', arguments: {} })) + .toEqual({ kind: 'parallel' }) expect(ctx.tools.executionMode({ signal: testToolSignal, callId: CallId('read-safe'), name: 'read', arguments: { file_path: 'a.txt' } })) .toEqual({ kind: 'parallel' }) expect(ctx.tools.executionMode({ signal: testToolSignal, callId: CallId('write-exclusive'), name: 'write', arguments: { file_path: 'a.txt', content: 'x' } })) @@ -157,6 +161,7 @@ describe('registration', () => { it('registers prompt sections for each tool', async () => { const { ctx } = await setup() const prompt = renderPrompt(await ctx.systemPrompt.assemble()) + expect(prompt).toContain('Use the list tool') expect(prompt).toContain('Use the read tool') expect(prompt).toContain('Use the write tool') expect(prompt).toContain('Use the edit tool') @@ -179,9 +184,10 @@ describe('registration', () => { const fiber = await ctx.plugin(ToolFs) // Each tool contributes BOTH a schema and a prompt section; disposal must // withdraw both, not just the schemas. - expect(ctx.tools.schemas()).toHaveLength(3) + expect(ctx.tools.schemas()).toHaveLength(4) const sectionNames = (a: { sections: { name: string }[] }) => a.sections.map(s => s.name).sort() - expect(sectionNames(await ctx.systemPrompt.assemble())).toEqual(['deployment:persona', 'harness:identity', 'tool:edit', 'tool:read', 'tool:write']) + expect(sectionNames(await ctx.systemPrompt.assemble())) + .toEqual(['deployment:persona', 'harness:identity', 'tool:edit', 'tool:list', 'tool:read', 'tool:write']) await fiber.dispose() expect(ctx.tools.schemas()).toHaveLength(0) // Only the system-prompt plugin's own built-in sections remain. @@ -189,6 +195,107 @@ describe('registration', () => { }) }) +describe('list tool', () => { + /** Seed one directory's children; `listDir` order is deliberately NOT display order. */ + function seedDir(fs: FakeFs, path: string, children: readonly { name: string; type: 'file' | 'directory' | 'other' }[]): void { + fs.dirs.set(`key:${path}`, children.map(({ name, type }) => ({ + name, + type, + target: { targetKey: FsTargetKey(`key:${path}/${name}`), displayPath: `/abs/${path}/${name}` }, + }))) + } + + it('defaults to the session workspace and shows directories before files', async () => { + const { ctx, fs } = await setup() + seedDir(fs, '.', [ + { name: 'notes.md', type: 'file' }, + { name: 'zeroomega-3.3.23', type: 'directory' }, + { name: 'archive', type: 'directory' }, + { name: 'link-to-nowhere', type: 'other' }, + ]) + const result = await call(ctx, 'list', {}) + expect(result.isError).toBe(false) + if (result.isError) throw new Error('expected list success') + // The canonical value carries display order, so a Code Mode caller and the + // model see the same ordering contract. + expect(result.value).toEqual({ + path: '/abs/.', + entries: [ + { name: 'archive', type: 'directory' }, + { name: 'zeroomega-3.3.23', type: 'directory' }, + { name: 'notes.md', type: 'file' }, + { name: 'link-to-nowhere', type: 'other' }, + ], + }) + expect(text(result)).toBe(`/abs/. +directory + +archive/ +zeroomega-3.3.23/ +notes.md +link-to-nowhere@ + +(4 entries: 2 directories, 1 file, 1 other) +`) + }) + + it('lists an explicit path and reports an empty directory as such', async () => { + const { ctx, fs } = await setup() + seedDir(fs, 'empty', []) + const result = await call(ctx, 'list', { path: 'empty' }) + expect(text(result)).toContain('(Empty directory)') + expect(text(result)).toContain('/abs/empty') + }) + + it('caps the rendered entries but still reports the complete composition', async () => { + const ctx = new Context() + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(FakeFs) + await ctx.plugin(ToolFs, { listMaxEntries: 2 }) + const fs = ctx.fs as FakeFs + seedDir(fs, '.', [ + { name: 'a.txt', type: 'file' }, + { name: 'b.txt', type: 'file' }, + { name: 'c.txt', type: 'file' }, + { name: 'src', type: 'directory' }, + ]) + const result = await call(ctx, 'list', {}) + const rendered = text(result) + // The one directory survives the cap because directories sort first — the + // failure mode this ordering exists to prevent. + expect(rendered).toContain('src/\na.txt\n') + expect(rendered).not.toContain('c.txt') + expect(rendered).toContain('(Showing 2 of 4 entries: 1 directory, 3 files. ' + + 'Entries are directories first, then files, each alphabetical; list a subdirectory to see the rest.)') + }) + + it('rejects a blank path and surfaces provider failures', async () => { + const { ctx, fs } = await setup() + const blank = await call(ctx, 'list', { path: ' ' }) + expect(blank.isError).toBe(true) + expect(text(blank)).toContain('path must be a non-empty string when given') + + fs.rejectWith = new FsError('cannot list "/abs/a.txt": not a directory', 'FS_NOT_DIRECTORY') + const failed = await call(ctx, 'list', { path: 'a.txt' }) + expect(failed.isError).toBe(true) + expect(failed.error).toMatchObject({ info: { code: 'FS_NOT_DIRECTORY' } }) + }) + + it('records no observation, so a listing never authorizes a mutation', async () => { + const { ctx, fs } = await setup() + fs.files.set('key:a.txt', 'hello') + seedDir(fs, '.', [{ name: 'a.txt', type: 'file' }]) + const observed = vi.fn() + ctx.on('fs/observed', observed) + await call(ctx, 'list', {}) + expect(observed).not.toHaveBeenCalled() + // Seeing a name is not reading a file: the policy gate still demands a read. + const edit = await call(ctx, 'edit', { file_path: 'a.txt', old_string: 'h', new_string: 'j' }, { session: { header: {} } }) + expect(edit.error).toMatchObject({ info: { code: 'FS_NOT_OBSERVED' } }) + }) +}) + describe('read tool', () => { it('formats line-numbered content with a footer', async () => { const { ctx, fs } = await setup() @@ -439,6 +546,15 @@ describe('tool-owned presentation (pure presentCall)', () => { }) }) + it('list: titles by the directory, falling back to the workspace "." when unset', async () => { + expect(await presentCall('list', { path: 'src' })).toEqual({ + card: 'generic', title: 'List src', kind: 'read', locations: [{ path: 'src' }], + }) + expect(await presentCall('list', {})).toEqual({ + card: 'generic', title: 'List .', kind: 'read', locations: [{ path: '.' }], + }) + }) + it('read: bare title and line-1 location when offset/limit are unset', async () => { expect(await presentCall('read', { file_path: 'a.txt' })).toEqual({ card: 'generic', title: 'Read a.txt', kind: 'read', locations: [{ path: 'a.txt', line: 1 }], @@ -621,6 +737,7 @@ describe('read caps are plugin config', () => { }) it.each([ + ['listMaxEntries', { listMaxEntries: 0 }], ['readLimit', { readLimit: 0 }], ['readLimit', { readLimit: 2.5 }], ['readMaxLineLength', { readMaxLineLength: -1 }], diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index 3103b9878c..f25084917e 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -230,7 +230,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ await ctx.plugin(ToolFs) }, note: - '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.', + '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. `list` enumerates one directory level through `ctx.fs.listDir` and records no observation, so seeing a filename never satisfies that read-before-write gate.', }, { pkg: '@deepseek-ai/dsh-tool-fs-search', From 9b9b45e65efc383c84b92f2607aad4cc891601ec Mon Sep 17 00:00:00 2001 From: NI0317 Date: Tue, 28 Jul 2026 12:05:36 +0800 Subject: [PATCH 02/24] fix(fs-search): sample an over-cap glob result across the tree MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Asked what a workspace contained, an agent described one subfolder as the whole project. `glob {"pattern": "*"}` matched 10030 paths across 22 top-level entries and the inline page was the first 100 of them, all under a single unpacked archive. Three properties compose into that page: a pattern with no `/` matches basenames at any depth, so `*` means the whole tree rather than its top level; `--sort=modified` orders oldest first, and unpacking an archive restores timestamps that predate everything the user wrote; and the page was the head of that order. Each is defensible alone, and together they make the most ordinary request an agent receives produce a confident wrong answer. A result within `globMaxResults` is unchanged — shown whole, in modification-time order. Beyond it the page is filled round-robin across the complete result's top-level entries, so one subtree cannot own every slot, and the footer states that the page was sampled rather than taken in modification-time order. Measured on a 24-entry, 716-file reproduction, the head of 100 reaches 7 top-level names and the sampled page reaches 21. The spill artifact still holds the complete sorted list. The guidance and schema stop steering away from `ls`, state the any-depth pattern rule, say results are files and never directories, and point at `list` for a directory's contents. --- docs/tool-catalog.md | 8 +- packages/fs/tool-fs-search/README.i18n.yaml | 6 +- packages/fs/tool-fs-search/README.md | 9 +- packages/fs/tool-fs-search/README.zh.md | 9 +- packages/fs/tool-fs-search/src/glob.ts | 138 +++++++++++++++--- packages/fs/tool-fs-search/src/index.ts | 4 +- .../fs/tool-fs-search/tests/tools.spec.ts | 70 +++++++++ scripts/gen-tool-catalog.ts | 2 +- 8 files changed, 208 insertions(+), 38 deletions(-) diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 6edd5be644..0884910bde 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -21,7 +21,7 @@ This table connects model-visible tool names to the plugin package and service s | `@deepseek-ai/dsh-tool-bash` | `bash` | `ctx.tools`, `ctx.bash`, `ctx.tasks at call time for run_in_background` | `tool/call`, `tool/result` | - | The bash tool is the model-facing consumer of the bash executor seam. A `run_in_background` run registers with the generic `ctx.tasks` runtime and is collected/stopped through the `task_*` tools from `@deepseek-ai/dsh-tool-tasks`; the `enableRunInBackground` config (default true) removes the parameter entirely when disabled. | | `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `live plugin-tree mutations (mount/unmount)` | - | Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes. | | `@deepseek-ai/dsh-tool-fs` | `edit`, `list`, `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. `list` enumerates one directory level through `ctx.fs.listDir` and records no observation, so seeing a filename never satisfies that read-before-write gate. | -| `@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). 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.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). 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. An over-cap glob result does not return the head of the sorted list: its inline page is taken round-robin across the top-level entries of the complete result and the footer states that basis, because modification-time order is ascending and the restored timestamps of an unpacked archive put one subtree in front of every broad match. | | `@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. | @@ -395,7 +395,7 @@ The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an ` ### `glob` -Find files whose paths match a glob pattern. Returns matching paths sorted by modification time, including hidden and ignored files (VCS metadata directories are excluded). Returns the first 100 paths inline; a capped result reports where the complete list was saved. +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 100 paths come back in modification-time order; a larger result instead returns 100 paths sampled across top-level directories, says so, and reports where the complete sorted list was saved. To see what a directory contains, use the list tool instead. ```json { @@ -403,7 +403,7 @@ Find files whose paths match a glob pattern. Returns matching paths sorted by mo "properties": { "pattern": { "type": "string", - "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\")." + "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\"). A pattern with no \"/\" matches the basename at any depth, so \"*\" and \"*.ts\" both search the whole tree; include a separator to anchor the depth." }, "path": { "type": "string", @@ -447,7 +447,7 @@ 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). 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 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). 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. An over-cap glob result does not return the head of the sorted list: its inline page is taken round-robin across the top-level entries of the complete result and the footer states that basis, because modification-time order is ascending and the restored timestamps of an unpacked archive put one subtree in front of every broad match. ## `@deepseek-ai/dsh-tool-pty` diff --git a/packages/fs/tool-fs-search/README.i18n.yaml b/packages/fs/tool-fs-search/README.i18n.yaml index 07aaa3c9dc..ec8f6f8968 100644 --- a/packages/fs/tool-fs-search/README.i18n.yaml +++ b/packages/fs/tool-fs-search/README.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 -README.md: 88a80fb51d7161e6940a3460b7f506575592f9cb -README.zh.md: 87be92bb5a8e06dfc275aa6a1fcf97274a761025 +# pnpm run verify-translation-pairing --write packages/fs/tool-fs-search/README.md +README.md: 33792a6f4b72baa2626c6e8d37c672fb39681554 +README.zh.md: 5d13a7ff2cb3ddfda8168a34e4a4a897d3413e11 diff --git a/packages/fs/tool-fs-search/README.md b/packages/fs/tool-fs-search/README.md index 88a80fb51d..33792a6f4b 100644 --- a/packages/fs/tool-fs-search/README.md +++ b/packages/fs/tool-fs-search/README.md @@ -24,7 +24,7 @@ All keys are optional; the defaults are the shipped search caps. | Key | Default | Meaning | |---|---|---| -| `globMaxResults` | `100` | Max paths one `glob` call retains inline (matches Claude Code's `GlobTool` limit); later paths go to the formatted spill artifact. | +| `globMaxResults` | `100` | Max paths one `glob` call shows inline (matches Claude Code's `GlobTool` limit). Within it the result is shown whole in modification-time order; beyond it the inline page is sampled across top-level entries and the complete sorted list goes to the formatted spill artifact. | | `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`. | @@ -34,7 +34,7 @@ All keys are optional; the defaults are the shipped search caps. | 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 path per line, modification-time ordered. | +| `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, modification-time ordered — `rg --files` never emits a directory, so no pattern makes `glob` describe a directory's contents; that is [`dsh-tool-fs`](../tool-fs/)'s `list`. The pattern keeps ripgrep semantics: without a `/` it matches the basename at any depth, so `*` matches the whole tree. | | `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. @@ -58,7 +58,7 @@ After the load-time `rg` probe succeeds, every request in this plugin's registra ##### Glob guidance ```markdown -Use the glob tool — not shell find or ls — to discover files by path pattern. Results are sorted by modification time and include hidden and ignored files. +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 directories, so it spans the tree instead of one subtree. Use the list tool to see what a directory contains. ``` ##### Grep guidance @@ -93,7 +93,7 @@ Prefix-stable while tool visibility and definitions are unchanged. Registration #### What the model sees -`glob` returns one path per line; `grep` groups `Line : ` matches beneath each path. Empty searches return `No files found` or `No matches found`. A capped result ends with its omission count plus the spill locator and backend retrieval hint, or says the complete result could not be saved. +`glob` returns one path per line; `grep` groups `Line : ` matches beneath each path. Empty searches return `No files found` or `No matches found`. A capped result ends with its omission count plus the spill locator and backend retrieval hint, or says the complete result could not be saved. An over-cap `glob` result does not show the head of the sorted list: its inline page takes paths round-robin across the complete result's top-level entries, so one recently-written subtree cannot own every slot, and the footer says the page was sampled rather than taken in modification-time order, together with how many top-level entries it reached. When it could not reach them all, the footer also points at `list`. A result that fits inline is untouched, and a flat result — every path its own top-level entry — keeps the plain footer, because there the sample IS the recency-ordered head. The spill artifact always holds the complete list in modification-time order. #### Token effect @@ -122,3 +122,4 @@ Append-only; newly visible content follows the reusable request prefix and does - **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. - **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 groups by first path segment only** — an over-cap `glob` page balances across 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 87be92bb5a..5d13a7ff2c 100644 --- a/packages/fs/tool-fs-search/README.zh.md +++ b/packages/fs/tool-fs-search/README.zh.md @@ -24,7 +24,7 @@ await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh- | 键 | 默认值 | 含义 | |---|---|---| -| `globMaxResults` | `100` | 一次 `glob` 调用内联保留的最大路径数（与 Claude Code 的 `GlobTool` 上限相同）；后续路径写入格式化 spill 产物。 | +| `globMaxResults` | `100` | 一次 `glob` 调用内联展示的最大路径数（与 Claude Code 的 `GlobTool` 上限相同）。未超过时结果整体按修改时间展示；超过时内联页面改为跨顶层条目取样，完整的排序列表写入格式化 spill 产物。 | | `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。 | @@ -34,7 +34,7 @@ await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh- | 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。每行返回一个路径，按修改时间排序。 | +| `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，因此任何 pattern 都无法让 `glob` 描述一个目录的内容，那是 [`dsh-tool-fs`](../tool-fs/) 的 `list`。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。未超过 `globMaxResults` 的结果按修改时间排序；超过时内联页面改为跨顶层条目取样（见下）。 | | `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。 @@ -58,7 +58,7 @@ await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh- ##### Glob 指导 ```markdown -Use the glob tool — not shell find or ls — to discover files by path pattern. Results are sorted by modification time and include hidden and ignored files. +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 directories, so it spans the tree instead of one subtree. Use the list tool to see what a directory contains. ``` ##### Grep 指导 @@ -93,7 +93,7 @@ Use the grep tool — not shell grep or rg — to search file contents. Use read #### 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。 +`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。超过上限的 `glob` 结果不再展示排序列表的头部：其内联页面按轮转方式跨完整结果的顶层条目取样，因此单个新近写入的子树无法占满所有位置；footer 会说明该页面是取样得到而非按修改时间取用，并给出它触达了多少个顶层条目。未能触达全部时，footer 还会指向 `list`。未超过上限的结果原样不动；扁平结果（每个路径各自构成一个顶层条目）保留朴素 footer，因为此时取样结果就等于按新近度排序的头部。spill 产物始终保存按修改时间排序的完整列表。 #### Token 影响 @@ -122,3 +122,4 @@ Use the grep tool — not shell grep or rg — to search file contents. Use read - **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。 +- **取样只按路径首段分组**：超过上限的 `glob` 页面在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。 diff --git a/packages/fs/tool-fs-search/src/glob.ts b/packages/fs/tool-fs-search/src/glob.ts index 6d42acee66..d46b1d352d 100644 --- a/packages/fs/tool-fs-search/src/glob.ts +++ b/packages/fs/tool-fs-search/src/glob.ts @@ -3,17 +3,21 @@ * 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, retention, and formatting; process concerns (defaulting, + * 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 */ import type { Context } from 'cordis' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView } from '@deepseek-ai/dsh-tools' -import { ItemRetainer } from '@deepseek-ai/dsh-retention' -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' @@ -99,30 +103,116 @@ export function buildGlobCommand(input: GlobInput): string { } /** - * Format the model-facing `glob` result: the retained paths, then — when the - * result was capped — a footer carrying either the formatted-spill recovery - * locator or the could-not-save explanation. The omitted count is a budget fact: - * the search itself completed. + * The inline page of a capped `glob` result, plus how much of the complete + * result's top level it reaches. + */ +export interface GlobSample { + /** Paths to show inline: grouped by top-level entry, recency-ordered within each group. */ + items: string[] + /** Distinct top-level entries the shown paths reach. */ + shown: number + /** Distinct top-level entries across the complete result. */ + total: number +} + +/** + * The leading path segment of one display path — the top-level entry, relative + * to the search root, that the path sits under. A path with no separator is its + * own top-level entry. Leading separators are stripped first so an absolute path + * (one outside the workdir, which {@link toWorkdirRelative} leaves untouched) + * groups by its first real name instead of collapsing every such path into one + * empty group. + */ +function topLevelSegment(path: string): string { + const trimmed = path.replace(/^[\\/]+/, '') + const cut = trimmed.search(/[\\/]/) + return cut === -1 ? trimmed : trimmed.slice(0, cut) +} + +/** + * 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. * - * @param retained - the retention outcome over every discovered path. + * `--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. + * + * @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`. + * @returns the page grouped by top-level entry, with the shown/total top-level spread. + */ +export function sampleAcrossTopLevel(paths: readonly string[], maxItems: number): GlobSample { + const groups = new Map() + for (const path of paths) { + const group = groups.get(topLevelSegment(path)) + if (group === undefined) groups.set(topLevelSegment(path), [path]) + else group.push(path) + } + // Bounding the rounds by the largest group makes termination structural: the + // page can only fill or the groups run out, never spin on empty rounds. + const rounds = Math.max(0, ...[...groups.values()].map(group => group.length)) + const taken = new Map() + let count = 0 + for (let round = 0; round < rounds && count < maxItems; round += 1) { + for (const [key, group] of groups) { + if (count >= maxItems) break + const path = group[round] + if (path === undefined) continue + count += 1 + const bucket = taken.get(key) + if (bucket === undefined) taken.set(key, [path]) + else bucket.push(path) + } + } + return { items: [...taken.values()].flat(), shown: taken.size, total: groups.size } +} + +/** + * 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 recency-ordered head, and naming a spread would only + * restate the path counts already there. + * + * @param sample - the inline page and its top-level spread. + * @param seen - how many paths the complete result holds; always more than the page. * @param spillRef - the saved complete-result reference, or `undefined` when unsaved. * @returns the model-facing text. */ -export function formatGlobOutput(retained: RetainedItems, spillRef: SpillRef | undefined): string { - const body = retained.items.join('\n') - if (!retained.truncated) return body +export function formatGlobOutput(sample: GlobSample, seen: number, spillRef: SpillRef | undefined): string { + const body = sample.items.join('\n') const recovery = spillRef !== undefined ? `Full sorted result stored at: ${spillRef.locator}. ${spillRef.retrievalHint}` : 'The complete result could not be saved; narrow pattern or path to see more.' - return `${body}\n\n(Showing ${retained.kept} of ${retained.seen} paths. ${recovery})` + const basis = sample.total === seen + ? '.' + : `, sampled across ${sample.shown} of the ${sample.total} top-level entries this pattern matched instead of taken in modification-time order.` + + (sample.shown < sample.total ? ' Use the list tool to see what a directory contains.' : '') + return `${body}\n\n(Showing ${sample.items.length} of ${seen} paths${basis} ${recovery})` } -/** Retain and format one canonical path list for the Native surface. */ +/** Bound and format one canonical path list for the Native surface. */ function renderGlobPaths(paths: string[], maxResults: number, spillRef?: SpillRef): string { if (paths.length === 0) return 'No files found' - const retainer = new ItemRetainer({ kind: 'head', maxItems: maxResults }) - for (const path of paths) retainer.push(path) - return formatGlobOutput(retainer.finish(), spillRef) + // A result that fits is shown whole, untouched: modification-time order is the + // tool's contract, and over a complete result it is what answers age questions. + if (paths.length <= maxResults) return paths.join('\n') + return formatGlobOutput(sampleAcrossTopLevel(paths, maxResults), paths.length, spillRef) } /** @@ -147,16 +237,24 @@ export function applyGlobTool(ctx: Context, caps: GlobToolCaps): void { ctx.systemPrompt.section({ name: 'tool:glob', order: 103, - text: 'Use the glob tool — not shell find or ls — to discover files by path pattern. Results are sorted by modification time and include hidden and ignored files.', + text: '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 directories, ' + + 'so it spans the tree instead of one subtree. Use the list tool to see what a directory contains.', }) const tool = defineTool({ name: 'glob', - description: 'Find files whose paths match a glob pattern. Returns matching paths sorted by modification time, ' + 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). ' - + `Returns the first ${caps.maxResults} paths inline; a capped result reports where the complete list was saved.`, + + `Up to ${caps.maxResults} paths come back in modification-time order; a larger result instead returns ${caps.maxResults} paths sampled across top-level directories, ` + + 'says so, and reports where the complete sorted list was saved. To see what a directory contains, use the list tool instead.', parameters: { - pattern: { type: 'string', required: true, description: 'Glob pattern to match file paths against (e.g. "**/*.ts", "src/**/*.test.js").' }, + pattern: { + type: 'string', + required: true, + description: 'Glob pattern to match file paths against (e.g. "**/*.ts", "src/**/*.test.js"). ' + + 'A pattern with no "/" matches the basename at any depth, so "*" and "*.ts" both search the whole tree; include a separator to anchor the depth.', + }, path: { type: 'string', description: 'Directory to search in. Defaults to the session workspace; a relative path resolves against it.' }, }, timeoutMs: caps.timeoutMs, diff --git a/packages/fs/tool-fs-search/src/index.ts b/packages/fs/tool-fs-search/src/index.ts index 5930890b7a..b6ae6ebbad 100644 --- a/packages/fs/tool-fs-search/src/index.ts +++ b/packages/fs/tool-fs-search/src/index.ts @@ -33,8 +33,8 @@ 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_TIMEOUT_MS } from './search-core.ts' -export { GLOB_MAX_RESULTS, GLOB_VCS_EXCLUDES, applyGlobTool, buildGlobCommand, formatGlobOutput, parseGlobArgs, presentGlobCall } from './glob.ts' -export type { GlobInput, GlobToolCaps } from './glob.ts' +export { GLOB_MAX_RESULTS, GLOB_VCS_EXCLUDES, applyGlobTool, buildGlobCommand, formatGlobOutput, parseGlobArgs, presentGlobCall, sampleAcrossTopLevel } from './glob.ts' +export type { GlobInput, GlobSample, GlobToolCaps } from './glob.ts' export { GREP_MAX_LINE_BYTES, GREP_MAX_MATCHES, diff --git a/packages/fs/tool-fs-search/tests/tools.spec.ts b/packages/fs/tool-fs-search/tests/tools.spec.ts index 1951d97a8d..0bbe0e0bf5 100644 --- a/packages/fs/tool-fs-search/tests/tools.spec.ts +++ b/packages/fs/tool-fs-search/tests/tools.spec.ts @@ -29,6 +29,7 @@ import { presentGlobCall, presentGrepCall, previewLine, + sampleAcrossTopLevel, toWorkdirRelative, } from '@deepseek-ai/dsh-tool-fs-search' @@ -498,6 +499,38 @@ 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'] + // 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 }) + // 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 }) + }) + + 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 }) + }) + + 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 }) + }) + + 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 }) + }) + + it('reproduces the recency-ordered head for a flat result', () => { + expect(sampleAcrossTopLevel(['a.ts', 'b.ts', 'c.ts'], 2)).toEqual({ items: ['a.ts', 'b.ts'], shown: 2, total: 3 }) + }) +}) + describe('glob results', () => { it('lists workdir-relative paths (absolute output under the workdir is relativized)', async () => { const { ctx, bash } = await setup() @@ -545,6 +578,43 @@ describe('glob results', () => { expect(result.additionalContexts?.[0]?.content).toEqual([{ type: 'text', text: 'glob context' }]) }) + it('samples an over-cap result across top-level entries instead of taking its head', async () => { + // 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 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 ' + + 'instead of taken in modification-time order. Use the list tool to see what a directory contains. ' + + 'The complete result could not be saved; narrow pattern or path to see more.)') + }) + + it('drops the list hint when the sample does reach 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')) + 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 ' + + 'instead of taken in modification-time order. ' + + 'The complete result could not be saved; narrow pattern or path to see more.)') + }) + + 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') + 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 recency head', async () => { + const { ctx, bash } = await setup({ config: { globMaxResults: 2 } }) + bash.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') diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index f25084917e..8ac6dd247b 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -248,7 +248,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ await ctx.plugin(ToolFsSearch) }, 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). 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 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). 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. An over-cap glob result does not return the head of the sorted list: its inline page is taken round-robin across the top-level entries of the complete result and the footer states that basis, because modification-time order is ascending and the restored timestamps of an unpacked archive put one subtree in front of every broad match.', }, { pkg: '@deepseek-ai/dsh-tool-pty', From a9c0e006202d09307a76a5ecd6e47ddfc85aba34 Mon Sep 17 00:00:00 2001 From: NI0317 Date: Tue, 28 Jul 2026 12:06:25 +0800 Subject: [PATCH 03/24] docs: record the directory-listing and glob-sampling decision Agent Note for the two changes: what the session log showed, what ordering can and cannot fix (measured, correcting the first diagnosis), why the page is sampled only past the cap, why `list` is needed alongside it, and the alternatives each one beat. --- ...026-07-27-directory-listing-tool.i18n.yaml | 6 + .../2026-07-27-directory-listing-tool.md | 110 ++++++++++++++++++ .../2026-07-27-directory-listing-tool.zh.md | 110 ++++++++++++++++++ 3 files changed, 226 insertions(+) create mode 100644 .agents/notes/implemented/feature/2026-07-27-directory-listing-tool.i18n.yaml create mode 100644 .agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md create mode 100644 .agents/notes/implemented/feature/2026-07-27-directory-listing-tool.zh.md diff --git a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.i18n.yaml b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.i18n.yaml new file mode 100644 index 0000000000..27a498cb46 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.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/2026-07-27-directory-listing-tool.md +2026-07-27-directory-listing-tool.md: 4292c173f07064ff8825462e08096780c20ad9d6 +2026-07-27-directory-listing-tool.zh.md: 4033254b08a77ba7ed9b1f3e638213f019abb692 diff --git a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md new file mode 100644 index 0000000000..4292c173f0 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md @@ -0,0 +1,110 @@ +# Agent Note: Sample over-cap glob results across the tree, and give the model a directory-listing tool + +Status: implemented + +English | [中文](2026-07-27-directory-listing-tool.zh.md) + +## Problem + +Asked what a workspace contained, an agent described one subfolder as if it were the whole project. + +The session log shows exactly how. The workspace held 22 top-level entries and 11,485 files. The model called `glob {"pattern": "*"}`, which matched 10,030 paths; the tool showed the first 100, and all 100 sat under a single recently-unpacked subdirectory holding 355 of those files. The model never saw the other 21 top-level entries and answered from the one it did see. The session cwd was correct throughout — nothing was misconfigured, and every number the tool printed was true. + +Three properties of `glob` compose into that page: + +- **A pattern with no `/` matches at any depth.** The pattern goes to ripgrep as `--glob=`, where a glob without a separator matches the basename anywhere in the tree. `*` therefore means "every file in the workspace", not "the top level" — the opposite of what it means in a shell. The tool said nothing about this, and every example in its schema was `**/…`, so nothing suggested the plain form was recursive. +- **`--sort=modified` orders oldest first.** Unpacking an archive restores the timestamps stored inside it, which predate everything the user wrote, so a freshly unpacked subtree lands at the very front of any broad match. (Ripgrep sorts ascending; `--sortr` is the descending form and is not used here.) +- **The inline page was the head of that order.** `globMaxResults` (100) paths were kept from the front. Under the first two properties, one subtree takes every slot. + +Each property is defensible alone. Together they make the most ordinary request an agent receives — "what is in this directory" — reliably produce a confident wrong answer, because nothing in the result distinguishes "the 100 newest files in this workspace" from "this workspace". + +### What ordering can and cannot fix + +A directory's name reaches the model only as the prefix of one of its files' paths, since `rg --files` emits files and never directory entries. That is enough for ordering to matter a great deal, and not enough for `glob` to answer the question. + +Measured on a reproduction of the failure's shape — 24 top-level entries, 716 files, one recently-written subtree: + +| First 100 paths chosen by | Distinct top-level names visible | +| --- | --- | +| modification time, oldest first (the shipped behavior) | 7 | +| round-robin across top-level entries | 21 | + +So a differently chosen page does surface most of the missing names, and the original diagnosis that ordering could not have helped was wrong. What no ordering fixes: an entry with no files beneath it never appears at all (the reproduction's empty directory is absent from the complete 716-path output), and nothing in the output says which names are directories or how many entries a directory holds. `glob` can therefore convey a tree's rough shape; it cannot state a directory's contents. + +## Decision + +Two changes, in the two packages that own the two halves of the failure. + +### The inline page of an over-cap `glob` result is sampled, not taken from the head + +`@deepseek-ai/dsh-tool-fs-search`. A result within `globMaxResults` is unchanged: shown whole, in modification-time order. Only when the result is larger does the page change — and there, taking the head is what fails. + +`sampleAcrossTopLevel` groups the complete result by leading path segment and fills the page round-robin: every top-level entry gets a slot before any entry gets a second, and an entry that runs out of paths drops out so its remaining slots go to the rest. Sort order survives where it still carries meaning — groups are visited in the order ripgrep first emits them, and each group's own paths keep their relative order. The page is emitted grouped by entry rather than interleaved, so the breadth is legible at a glance. + +The footer states the basis, because a page that silently stopped being "the newest N" would be a second, quieter version of the same lie: + +``` +(Showing 100 of 10030 paths, sampled across 22 of the 22 top-level entries this pattern matched +instead of taken in modification-time order. Full sorted result stored at: …) +``` + +When the page cannot reach every top-level entry — more entries than slots — the footer says so with the shown/total spread and points at `list`. A flat result, where every path is its own top-level entry, keeps the plain `(Showing k of n paths. …)` footer: there the round-robin *is* the sorted head, and naming a spread would only restate the counts. The spill artifact always holds the complete list in modification-time order, so the sorted view is never lost. + +The guidance and schema stop misleading in the same change: "not shell find or ls" becomes "not shell find"; both now state that a pattern without `/` matches basenames at any depth, that results are files and never directories, that a fitting result is modification-time ordered while a larger one is sampled, and that `list` is the tool for a directory's contents. + +### `list`, in `@deepseek-ai/dsh-tool-fs` + +A fourth model-facing filesystem tool over the existing `ctx.fs.listDir` primitive, which until now shipped with skill discovery as its only consumer; [the seam Agent Note](../../archived/architecture/2026-07-03-filesystem-directory-listing-seam.md) deferred the model-facing consumer to a separate decision, which this is. + +It takes an optional `path` — defaulting to `.`, the calling agent's session workspace, so the common question needs no argument — and returns the direct children of one directory as `{ path, entries: [{ name, type }] }`, where `type` is `file`, `directory`, or `other`. It calls `listDir` and nothing else: the seam already reports absence as `FS_NOT_FOUND` and a non-directory target as `FS_NOT_DIRECTORY`, so a preceding `stat` would add a round-trip and a second source of truth. + +Two presentation rules carry the decision: + +- **Directories sort first, then files, then non-regular children, each alphabetically** — in the canonical value as well as the rendered text, so a Code Mode caller and the model see one ordering contract. The seam returns stable name order, which scatters subdirectories through the alphabet; capping such a list can drop every subdirectory and reproduce, inside `list`, the same blindness. Directory-first ordering makes truncation lose leaves, never structure. +- **The footer always states the complete listing's size and composition** — `(22 entries: 18 directories, 4 files)`, and when the view is capped at `listMaxEntries` (default 200, configurable), `(Showing 200 of 5000 entries: 12 directories, 4988 files. …)`. A partial listing therefore cannot read as a whole directory. + +Directory entries render with a trailing `/` and non-regular children with `@`, so the model can tell what it may descend into without a second call. + +`list` emits no `fs/observed`. Seeing a filename is not reading a file, and a listing must never satisfy the read-before-write gate that `@deepseek-ai/dsh-fs-policy` enforces. It declares `isConcurrencySafe`, because it mutates nothing at all. + +### Why both + +They answer different questions and neither substitutes for the other. `list` answers "what is here" exactly — entry names, their types, the complete count — which `glob` cannot do at any ordering. Sampling fixes the page a broad `glob` returns for every *other* question, which stays wrong even once a better tool exists, because the model has no reason to abandon a page that looks representative. + +## Alternatives considered + +**Leave `glob` ordering alone and only warn in the footer.** This is what the first implementation did: keep the recency head and add a clause saying the head covered 1 of 22 top-level entries. Rejected once measured. A warning asks the model to distrust the only data it has and go elsewhere; a better page just is not wrong. The warning also does nothing for a model that stops reading at the paths, which is the failure being fixed. + +**Sample always, replacing modification-time order outright.** Rejected. Over a complete result the order answers age questions — what is stale, what was touched last — a genuinely useful and separate purpose, and a complete result is the case where the order costs nothing and means everything. Sampling only past the cap is the point where the order has already stopped describing the result: the head of a 10,030-path list is not "the oldest files worth knowing about", it is an arbitrary 1% of them. + +**Sample by a skew threshold — head unless the head is badly concentrated.** Rejected. A threshold is a deployment-varying tunable with no evidence behind any value, and it makes the result's ordering contract conditional on data the model cannot see. "Over the cap" is a boundary the model already knows about from the footer. + +**Balance recursively, not just at the top level.** Deferred, and recorded as a Known Limitation. Top-level balance fixes the observed failure and is explainable in one sentence of tool description; per-level balancing needs a policy for how depth trades against breadth, which no current evidence settles. + +**Reject `*`, or silently rewrite it to a top-level-anchored pattern.** Rejected. The same basename-at-any-depth rule that makes `*` recursive is what makes `*.ts` mean "every TypeScript file", the overwhelmingly common and correct use; anchoring one and not the other is an arbitrary special case, and rejecting a pattern ripgrep accepts turns a working call into an error. Documenting the rule costs nothing and generalizes. + +**Add `list` without touching `glob`.** Rejected, for the reason stated under *Why both* above. The misleading page is reachable from any broad pattern, and a model that believes its sample is representative has no reason to reach for another tool. + +**Fix `glob` without adding `list`.** Rejected for the same reason in reverse. A sampled page shows most top-level *names*, but not which are directories, not the empty ones, and not the entry count; "what is in this directory" deserves a tool that answers it rather than a sample the model must infer from. + +**Report per-directory child counts in `list`.** Rejected. Counting each entry's children means one `listDir` per child — an N+1 fan-out across a seam that may be remote or sandboxed, paid on every listing, to sharpen a decision the model can settle by listing the one subdirectory it cares about. + +**Make `list` recursive with a depth argument.** Rejected for now. One level composes: the model lists what it needs to descend into. Recursion reintroduces the size and truncation problems this note exists to fix, and the provider primitive is deliberately one-level. + +**Spill a capped listing through `ctx.spillStore`, as `glob` does.** Rejected for v1. `glob` needs spill because a truncated path list has no cheap successor call; a truncated listing does, and the footer states the complete size and composition, so the model knows both that it is looking at part of a directory and what to do about it. + +## Consequences + +An over-cap `glob` result no longer returns the most recently modified paths. That is a real contract change on a hot path, and it is why the footer, the prompt section, and the schema all state the sampled basis rather than leaving the model to infer it. A result within the cap is byte-identical to before, so age-ordered reading keeps working wherever it was working. + +Balancing is by first path segment only, so a result concentrated deeper — one enormous directory inside an otherwise even tree — is still shown unevenly below the top level. Recorded in the package's Known Limitations. + +The shipped tool surface grows by one tool in every deployment that loads `@deepseek-ai/dsh-tool-fs`, which is all of them: a fixed schema and prompt cost on every request, and an invalidated pinned request header in the ACP snapshot scenario that pins full system-prompt and tool-schema content. The gain is that the harness's most common question has a correct answer; the previous state was not a missing convenience but a capability hole that produced confidently wrong answers. + +`ctx.fs.listDir` gains its first model-facing consumer, which makes its contract load-bearing for a product surface: a future remote or sandboxed backend must implement direct-child listing well enough for a model to navigate by, not merely well enough for skill discovery. The `other` type stays collapsed at the seam, so `list` cannot distinguish a symlink from a socket and marks both `@`. + +## Testing + +Package tests pin the model-visible text of both surfaces. For `glob`: `sampleAcrossTopLevel` over a concentrated result, an exhausted group handing its slots on, a page smaller than the top level, absolute paths outside the workdir, and a flat result that must reproduce the sorted head; plus end-to-end assertions that a fitting result is untouched, that an over-cap result returns the sampled page with the sampled-basis footer, that the list hint disappears once the page reaches every entry, and that a flat over-cap result keeps the plain footer. For `list`: the envelope, type markers, singular and plural footers, the empty-directory footer, and the capped footer that keeps the sole directory visible. A registry-level test asserts that a listing emits no `fs/observed` and that a following `edit` still fails `FS_NOT_OBSERVED`, so the tool cannot become an accidental read-before-write bypass. Prompt-section registration, schema registration, and HMR disposal cover the fourth tool alongside the existing three. + +The assembled transcript is the `fs-list` ACP scenario: a workspace whose answer is its subdirectories, where the model calls `list` with no arguments and the pinned tool result carries the directory-first envelope and its composition footer — an answer `glob` could not have produced at all. diff --git a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.zh.md b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.zh.md new file mode 100644 index 0000000000..4033254b08 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.zh.md @@ -0,0 +1,110 @@ +# Agent Note: Sample over-cap glob results across the tree, and give the model a directory-listing tool + +Status: implemented + +[English](2026-07-27-directory-listing-tool.md) | 中文 + +## Problem + +被问到工作区里有什么时，agent（智能体）把其中一个子目录当作整个项目描述了一遍。 + +会话日志把过程说得很清楚。该工作区有 22 个顶层条目、11485 个文件。模型调用了 `glob {"pattern": "*"}`，匹配到 10030 条路径；工具展示了前 100 条，而这 100 条全部位于同一个新近解包的子目录下，该子目录只占其中 355 个文件。模型从未看到另外 21 个顶层条目，只能依据它看到的那一个作答。整个过程中会话 cwd 都是正确的——没有任何配置错误，工具打印的每个数字也都是真的。 + +`glob` 的三项性质合成了那个页面： + +- **不含 `/` 的 pattern 匹配任意深度。** pattern 直接作为 `--glob=` 交给 ripgrep，而不含分隔符的 glob 匹配树中任何位置的基名。因此 `*` 的含义是「工作区里的每个文件」，而不是「顶层」——与它在 shell 里的含义正好相反。工具对此只字未提，schema 里的示例又全是 `**/…`，没有任何线索表明朴素写法是递归的。 +- **`--sort=modified` 按从旧到新排序。** 解包压缩档会还原档案内部保存的时间戳，它们早于用户自己写下的一切，因此新近解包的子树会落在任何宽泛匹配的最前面。（ripgrep 按升序排序；降序是 `--sortr`，此处未使用。） +- **内联页面取的是该顺序的头部。** 从最前面保留 `globMaxResults`（100）条路径。在前两项性质之下，一个子树吃掉全部位置。 + +单看每一项都站得住。合在一起，它们让 agent 收到的最普通的请求——「这个目录里有什么」——稳定地产出一个笃定的错误答案，因为结果里没有任何信息能区分「本工作区最新的 100 个文件」与「本工作区」。 + +### 排序能修什么，不能修什么 + +由于 `rg --files` 输出文件、从不输出目录条目，一个目录的名字只能作为其下某个文件路径的前缀抵达模型。这既足以让排序变得非常重要，也不足以让 `glob` 回答那个问题。 + +在一份复现该失败形态的目录上实测——24 个顶层条目、716 个文件、一个新近写入的子树： + +| 前 100 条路径的挑选方式 | 可见的顶层名个数 | +| --- | --- | +| 按修改时间、从旧到新（已交付的行为） | 7 | +| 跨顶层条目轮转 | 21 | + +也就是说，换一种页面挑选方式确实能呈现出大部分缺失的名字，最初那句「排序帮不上忙」的诊断是错的。排序修不了的是：没有任何文件的条目根本不会出现（复现目录里的空目录在完整的 716 条输出中一次都没出现），而且输出里没有任何信息说明哪些名字是目录、某个目录有多少条目。因此 `glob` 能传达一棵树的大致形状，却说不出一个目录的内容。 + +## Decision + +两项改动，分别落在承担这次失败两半责任的两个包中。 + +### 超过上限的 `glob` 结果，内联页面改为取样而非取头部 + +`@deepseek-ai/dsh-tool-fs-search`。未超过 `globMaxResults` 的结果完全不变：整体展示，按修改时间排序。只有结果更大时页面才改变——而恰恰在这种情况下，取头部是会失败的做法。 + +`sampleAcrossTopLevel` 按路径首段对完整结果分组，并以轮转方式填充页面：每个顶层条目都先拿到一个位置，任何条目才可能拿到第二个；某个条目的路径用尽后退出，其剩余份额交给其余条目。排序在仍有意义的地方被保留下来——分组按 ripgrep 首次输出它们的顺序访问，而每个分组内部的路径保持原有相对顺序。页面按条目分组输出而非交错输出，使覆盖广度一眼可辨。 + +footer 会说明取用依据，因为一个悄悄不再是「最新 N 条」的页面，只会成为同一个谎言更安静的版本： + +``` +(Showing 100 of 10030 paths, sampled across 22 of the 22 top-level entries this pattern matched +instead of taken in modification-time order. Full sorted result stored at: …) +``` + +当页面无法触达全部顶层条目时——条目数多于位置数——footer 会给出已触达/总计的分布并指向 `list`。扁平结果（每个路径各自构成一个顶层条目）保留朴素的 `(Showing k of n paths. …)` footer：此时轮转结果**就是**排序后的头部，说明分布只会重复计数。spill 产物始终保存按修改时间排序的完整列表，排序视图不会丢失。 + +同一次改动里，指导与 schema 也不再误导：「not shell find or ls」改为「not shell find」；两处现在都写明：不含 `/` 的 pattern 匹配任意深度的基名、结果只有文件从不包含目录、未超上限的结果按修改时间排序而更大的结果为取样所得、目录内容请用 `list`。 + +### `list`，位于 `@deepseek-ai/dsh-tool-fs` + +在既有的 `ctx.fs.listDir` 原语之上新增第四个面向模型的文件系统工具；该原语此前交付时唯一的消费方是 skill（技能）发现，[seam Agent Note](../../archived/architecture/2026-07-03-filesystem-directory-listing-seam.md) 把面向模型的消费方推迟为一项单独的决策，也就是本文。 + +它接受可选的 `path`，默认为 `.`，即调用 agent 的会话工作区，因此那个最常见的问题不需要任何参数；返回单个目录的直接子项，形如 `{ path, entries: [{ name, type }] }`，其中 `type` 为 `file`、`directory` 或 `other`。它只调用 `listDir`：seam 已经把不存在报告为 `FS_NOT_FOUND`、把非目录目标报告为 `FS_NOT_DIRECTORY`，前置 `stat` 只会多一次往返并制造第二个真源。 + +有两条展示规则承载了这个决策： + +- **先目录、再文件、最后非常规子项，各组内按字母序** —— 规范值与渲染文本采用同一顺序，使 Code Mode 调用方和模型看到同一份顺序契约。seam 返回的是稳定名称序，会把子目录散落在字母表各处；对这样的列表设上限可能丢掉全部子目录，在 `list` 内部重演同一种盲区。目录优先的顺序让截断只丢叶子，绝不丢结构。 +- **footer 始终说明完整列表的规模与构成** —— 例如 `(22 entries: 18 directories, 4 files)`；视图受 `listMaxEntries`（默认 200，可配置）截断时则为 `(Showing 200 of 5000 entries: 12 directories, 4988 files. …)`。因此部分列出结果不可能被读成整个目录。 + +目录条目渲染带尾部 `/`，非常规子项带 `@`，使模型无需第二次调用就能判断哪些可以继续进入。 + +`list` 不发出 `fs/observed`。看到文件名不等于读过文件，列出绝不能满足 `@deepseek-ai/dsh-fs-policy` 施加的编辑前读取门禁。它声明 `isConcurrencySafe`，因为它完全不做任何变更。 + +### 为什么两者都要 + +它们回答的是不同的问题，彼此无法替代。`list` 精确回答「这里有什么」——条目名、类型、完整计数——这是 `glob` 在任何排序下都做不到的。取样修的是宽泛 `glob` 为**其他**所有问题返回的那个页面；即便有了更好的工具，那个页面依然是错的，因为模型没有理由放弃一个看起来有代表性的页面。 + +## Alternatives considered + +**不动 `glob` 排序，只在 footer 里警告。** 这正是第一版实现的做法：保留新近序头部，加一句「该头部只覆盖 22 个顶层条目中的 1 个」。实测之后否决。一句警告是在要求模型不信任它手上唯一的数据并另寻他处；而一个更好的页面本身就不是错的。对于读到路径就停下的模型，警告也毫无作用——而那正是本次要修的失败。 + +**一律取样，彻底取消按修改时间排序。** 已否决。在完整结果上，该顺序回答的是与新旧有关的问题——哪些已经陈旧、哪些最后被动过——这是一个确实有用且独立的用途；而未超上限的完整结果恰恰是该顺序毫无代价、意义最大的场景。只在超过上限后取样，正好落在该顺序已经不再描述结果的那个点上：一份 10030 条列表的头部不是「最值得知道的最旧文件」，而是其中任意的 1%。 + +**按偏斜阈值决定是否取样——头部不太集中时仍取头部。** 已否决。阈值是随部署而变的可调参数，且其取值没有任何证据支撑；它还会让结果的顺序契约取决于模型看不到的数据。而「是否超过上限」是模型本来就能从 footer 得知的边界。 + +**递归均衡，而不只在顶层均衡。** 已延期，并记入已知限制。顶层均衡修好了已观察到的失败，且能用一句工具描述解释清楚；逐层均衡需要一套关于深度与广度如何权衡的策略，目前没有证据能定下来。 + +**拒绝 `*`，或悄悄将其改写为锚定顶层的 pattern。** 已否决。让 `*` 递归的那条「任意深度匹配基名」规则，同样让 `*.ts` 意为「每个 TypeScript 文件」，而后者是压倒性常见且正确的用法；只锚定其一是任意的特例，而拒绝一个 ripgrep 本可接受的 pattern 则把可用调用变成错误。把规则写进文档不花任何代价，而且可以推广。 + +**只加 `list`，不动 `glob`。** 已否决，理由见上文《为什么两者都要》。任何宽泛 pattern 都能触达那个误导性页面，而一个相信自己样本有代表性的模型，没有理由改用别的工具。 + +**只修 `glob`，不加 `list`。** 出于对称的理由否决。取样页面能展示大部分顶层**名字**，但说不出哪些是目录、看不到空目录、也给不出条目总数；「这个目录里有什么」值得一个直接回答它的工具，而不是一份需要模型去推断的样本。 + +**在 `list` 中报告每个目录的子项数。** 已否决。统计每个条目的子项意味着对每个子项各调用一次 `listDir`——在一个可能是远程或沙箱的 seam 上做 N+1 扇出，每次列出都要付费，只为了让模型少做一个它本可以通过列出所关心的那一个子目录就完成的判断。 + +**让 `list` 支持递归和深度参数。** 暂时否决。单层是可组合的：模型列出它需要进入的那一层即可。递归会重新引入本 Agent Note 要解决的规模与截断问题，而且提供方原语本身就有意只做一层。 + +**像 `glob` 那样，把达到上限的列出结果通过 `ctx.spillStore` 落盘。** v1 已否决。`glob` 需要 spill，是因为被截断的路径列表没有廉价的后继调用；被截断的列出结果有，而且 footer 已说明完整规模与构成，模型既知道自己只看到目录的一部分，也知道该怎么办。 + +## Consequences + +超过上限的 `glob` 结果不再返回修改时间最新的那些路径。这是热路径上一项真实的契约变更，也正因如此，footer、提示词段和 schema 都写明了取样这一依据，而不是留给模型去推断。未超上限的结果与此前逐字节相同，因此按新旧顺序阅读结果的用法在原本能用的地方继续能用。 + +均衡只按路径首段进行，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目录——在顶层以下仍然分布不均。已记入该包的已知限制。 + +随产品交付的工具接口在每个加载 `@deepseek-ai/dsh-tool-fs` 的部署中都多出一个工具，而这是全部部署：每个请求都要支付固定的 schema 与提示词成本，并且会使 ACP（Agent Client Protocol）快照场景中那份钉住完整系统提示词与工具 schema 内容的请求头失效。换来的是：harness 最常见的问题终于有了正确答案；此前的状态不是缺少一项便利，而是一个会产出笃定错误答案的能力空洞。 + +`ctx.fs.listDir` 拥有了第一个面向模型的消费方，其契约由此成为产品接口的承重部分：未来的远程或沙箱后端实现直接子项列出时，标准不再是「够 skill 发现用」，而是「够模型据以导航」。`other` 类型在 seam 处仍是合并的，因此 `list` 无法区分符号链接与套接字，两者都标记为 `@`。 + +## Testing + +包测试钉住两个接口面向模型的文本。`glob` 方面：`sampleAcrossTopLevel` 在集中结果、某分组用尽后交出份额、页面小于顶层条目数、工作目录之外的绝对路径，以及必须复现排序头部的扁平结果上的行为；另有端到端断言——未超上限的结果原样不动、超上限结果返回取样页面并带取样依据 footer、页面覆盖全部条目后 list 提示消失、扁平的超上限结果保留朴素 footer。`list` 方面：包络、类型标记、单复数 footer、空目录 footer，以及让唯一那个目录留在视野内的截断 footer。一项注册表层级的测试断言列出不会发出 `fs/observed`，且随后的 `edit` 仍以 `FS_NOT_OBSERVED` 失败，使该工具不会变成意外的编辑前读取绕过口。提示词段注册、schema 注册与 HMR（热模块替换）dispose（资源释放）覆盖了这第四个工具与既有三个工具。 + +组装后的 transcript（文本记录）由 `fs-list` ACP 场景承担：该工作区的答案就是它的子目录，模型不带任何参数调用 `list`，被钉住的工具结果携带目录优先的包络及其构成 footer —— 这个答案 `glob` 根本无法给出。 From 717852423fa4587134b2879378c5f5dbc4244ad4 Mon Sep 17 00:00:00 2001 From: NI0317 Date: Tue, 28 Jul 2026 13:01:26 +0800 Subject: [PATCH 04/24] fix(fs): harden directory listing and glob sampling --- ...026-07-27-directory-listing-tool.i18n.yaml | 4 +- .../2026-07-27-directory-listing-tool.md | 31 +++-- .../2026-07-27-directory-listing-tool.zh.md | 31 +++-- docs/config-catalog.md | 2 +- docs/tool-catalog.md | 16 ++- .../system-prompt.expected.md | 13 +- .../tool-schemas.expected.json | 6 +- .../both-mode-turn/system-prompt.expected.md | 13 +- .../both-mode-turn/tool-schemas.expected.json | 6 +- .../code-mode-turn/system-prompt.expected.md | 13 +- .../system-prompt.expected.md | 13 +- .../system-prompt.expected.md | 2 +- .../tool-schemas.expected.json | 6 +- .../tests/snapshots/fs-list/session.jsonl | 2 +- .../lsp-definition/system-prompt.expected.md | 2 +- .../lsp-definition/tool-schemas.expected.json | 6 +- .../pty-tools/system-prompt.expected.md | 2 +- .../pty-tools/tool-schemas.expected.json | 6 +- .../system-prompt.expected.md | 2 +- .../tool-schemas.expected.json | 6 +- .../skill-load/system-prompt.expected.md | 2 +- .../skill-load/tool-schemas.expected.json | 6 +- .../text-turn/system-prompt.expected.md | 2 +- .../text-turn/tool-schemas.expected.json | 6 +- .../web-fetch/system-prompt.expected.md | 2 +- .../web-fetch/tool-schemas.expected.json | 6 +- .../system-prompt.expected.md | 2 +- .../tool-schemas.expected.json | 6 +- .../advanced-toolchain/session.1.jsonl | 2 +- .../advanced-toolchain/session.2.jsonl | 2 +- .../advanced-toolchain/session.jsonl | 2 +- .../tests/snapshots/pty-tools/session.jsonl | 2 +- packages/fs/tool-fs-search/README.i18n.yaml | 4 +- packages/fs/tool-fs-search/README.md | 10 +- packages/fs/tool-fs-search/README.zh.md | 10 +- packages/fs/tool-fs-search/src/glob.ts | 57 +++++--- .../fs/tool-fs-search/tests/tools.spec.ts | 76 +++++++++-- packages/fs/tool-fs/README.i18n.yaml | 4 +- packages/fs/tool-fs/README.md | 18 +-- packages/fs/tool-fs/README.zh.md | 18 +-- packages/fs/tool-fs/src/index.ts | 2 +- packages/fs/tool-fs/src/list-render.ts | 123 +++++++++++------- packages/fs/tool-fs/src/list.ts | 58 +++++++-- packages/fs/tool-fs/tests/list-render.spec.ts | 36 +++-- packages/fs/tool-fs/tests/tools.spec.ts | 57 ++++++-- scripts/gen-tool-catalog.ts | 4 +- 46 files changed, 480 insertions(+), 219 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.i18n.yaml b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.i18n.yaml index 27a498cb46..79b30290b5 100644 --- a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md -2026-07-27-directory-listing-tool.md: 4292c173f07064ff8825462e08096780c20ad9d6 -2026-07-27-directory-listing-tool.zh.md: 4033254b08a77ba7ed9b1f3e638213f019abb692 +2026-07-27-directory-listing-tool.md: a23cdb0090f1a88b783d9717aa3f0434b6c2782e +2026-07-27-directory-listing-tool.zh.md: bab0138a79ae770ae7e841392b879940e8ac2dc4 diff --git a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md index 4292c173f0..a23cdb0090 100644 --- a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md +++ b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md @@ -16,13 +16,13 @@ Three properties of `glob` compose into that page: - **`--sort=modified` orders oldest first.** Unpacking an archive restores the timestamps stored inside it, which predate everything the user wrote, so a freshly unpacked subtree lands at the very front of any broad match. (Ripgrep sorts ascending; `--sortr` is the descending form and is not used here.) - **The inline page was the head of that order.** `globMaxResults` (100) paths were kept from the front. Under the first two properties, one subtree takes every slot. -Each property is defensible alone. Together they make the most ordinary request an agent receives — "what is in this directory" — reliably produce a confident wrong answer, because nothing in the result distinguishes "the 100 newest files in this workspace" from "this workspace". +Each property is defensible alone. Together they make the most ordinary request an agent receives — "what is in this directory" — reliably produce a confident wrong answer, because nothing in the result distinguishes "the 100 oldest files in this workspace" from "this workspace". ### What ordering can and cannot fix A directory's name reaches the model only as the prefix of one of its files' paths, since `rg --files` emits files and never directory entries. That is enough for ordering to matter a great deal, and not enough for `glob` to answer the question. -Measured on a reproduction of the failure's shape — 24 top-level entries, 716 files, one recently-written subtree: +Measured on a reproduction of the failure's shape — 24 top-level entries, 716 files, one old-timestamped subtree: | First 100 paths chosen by | Distinct top-level names visible | | --- | --- | @@ -39,31 +39,30 @@ Two changes, in the two packages that own the two halves of the failure. `@deepseek-ai/dsh-tool-fs-search`. A result within `globMaxResults` is unchanged: shown whole, in modification-time order. Only when the result is larger does the page change — and there, taking the head is what fails. -`sampleAcrossTopLevel` groups the complete result by leading path segment and fills the page round-robin: every top-level entry gets a slot before any entry gets a second, and an entry that runs out of paths drops out so its remaining slots go to the rest. Sort order survives where it still carries meaning — groups are visited in the order ripgrep first emits them, and each group's own paths keep their relative order. The page is emitted grouped by entry rather than interleaved, so the breadth is legible at a glance. +`sampleAcrossTopLevel` removes the displayed search-root prefix, groups the complete result by the next path segment, and fills the page round-robin: every entry immediately beneath the actual relative or absolute root gets a slot before any entry gets a second, and an entry that runs out of paths drops out so its remaining slots go to the rest. Sort order survives where it still carries meaning — groups are visited in the order ripgrep first emits them, and each group's own paths keep their relative order. The page is emitted grouped by entry rather than interleaved, so the breadth is legible at a glance. -The footer states the basis, because a page that silently stopped being "the newest N" would be a second, quieter version of the same lie: +The footer states the basis, because a page that silently stopped being "the first N in modification-time order" would be a second, quieter version of the same lie: ``` (Showing 100 of 10030 paths, sampled across 22 of the 22 top-level entries this pattern matched instead of taken in modification-time order. Full sorted result stored at: …) ``` -When the page cannot reach every top-level entry — more entries than slots — the footer says so with the shown/total spread and points at `list`. A flat result, where every path is its own top-level entry, keeps the plain `(Showing k of n paths. …)` footer: there the round-robin *is* the sorted head, and naming a spread would only restate the counts. The spill artifact always holds the complete list in modification-time order, so the sorted view is never lost. +When the page cannot reach every top-level entry — more entries than slots — the footer says so with the shown/total spread and tells the model to narrow `path`. A flat result, where every path is its own top-level entry, keeps the plain `(Showing k of n paths. …)` footer: there the round-robin *is* the sorted head, and naming a spread would only restate the counts. The spill artifact always holds the complete list in modification-time order, so the sorted view is never lost. -The guidance and schema stop misleading in the same change: "not shell find or ls" becomes "not shell find"; both now state that a pattern without `/` matches basenames at any depth, that results are files and never directories, that a fitting result is modification-time ordered while a larger one is sampled, and that `list` is the tool for a directory's contents. +The guidance and schema stop misleading in the same change: "not shell find or ls" becomes "not shell find"; both now state that a pattern without `/` matches basenames at any depth, that results are files and never directories, and that a fitting result is modification-time ordered while a larger one is sampled across top-level entries. They do not recommend sibling-package tools that may be absent from the current composition. ### `list`, in `@deepseek-ai/dsh-tool-fs` A fourth model-facing filesystem tool over the existing `ctx.fs.listDir` primitive, which until now shipped with skill discovery as its only consumer; [the seam Agent Note](../../archived/architecture/2026-07-03-filesystem-directory-listing-seam.md) deferred the model-facing consumer to a separate decision, which this is. -It takes an optional `path` — defaulting to `.`, the calling agent's session workspace, so the common question needs no argument — and returns the direct children of one directory as `{ path, entries: [{ name, type }] }`, where `type` is `file`, `directory`, or `other`. It calls `listDir` and nothing else: the seam already reports absence as `FS_NOT_FOUND` and a non-directory target as `FS_NOT_DIRECTORY`, so a preceding `stat` would add a round-trip and a second source of truth. +It takes optional `path` and 1-based `offset` arguments, defaulting to the calling agent's session workspace and entry 1, and returns one bounded page as `{ path, offset, entries: [{ name, type }], totalEntries, counts }`, where `type` is `file`, `directory`, or `other`. It calls `listDir` and nothing else: the seam already reports absence as `FS_NOT_FOUND` and a non-directory target as `FS_NOT_DIRECTORY`, so a preceding `stat` would add a round-trip and a second source of truth. -Two presentation rules carry the decision: +Three presentation rules carry the decision: -- **Directories sort first, then files, then non-regular children, each alphabetically** — in the canonical value as well as the rendered text, so a Code Mode caller and the model see one ordering contract. The seam returns stable name order, which scatters subdirectories through the alphabet; capping such a list can drop every subdirectory and reproduce, inside `list`, the same blindness. Directory-first ordering makes truncation lose leaves, never structure. -- **The footer always states the complete listing's size and composition** — `(22 entries: 18 directories, 4 files)`, and when the view is capped at `listMaxEntries` (default 200, configurable), `(Showing 200 of 5000 entries: 12 directories, 4988 files. …)`. A partial listing therefore cannot read as a whole directory. - -Directory entries render with a trailing `/` and non-regular children with `@`, so the model can tell what it may descend into without a second call. +- **Directories sort first, then files, then non-regular children, each alphabetically** before paging, so every offset traverses one stable order and the first page keeps navigable structure. +- **The canonical value and Native result carry one recoverable page** of at most `listMaxEntries` (default 200, configurable). The footer states the complete size and composition and gives `offset=` until the final page, so omitted sibling names remain reachable. +- **Filesystem text cannot forge presentation structure.** The path and entry names render as JSON strings with envelope-significant characters escaped; directory `/` and non-regular `@` markers sit outside the quoted name, so a regular filename ending in `@` remains distinguishable. `list` emits no `fs/observed`. Seeing a filename is not reading a file, and a listing must never satisfy the read-before-write gate that `@deepseek-ai/dsh-fs-policy` enforces. It declares `isConcurrencySafe`, because it mutates nothing at all. @@ -73,7 +72,7 @@ They answer different questions and neither substitutes for the other. `list` an ## Alternatives considered -**Leave `glob` ordering alone and only warn in the footer.** This is what the first implementation did: keep the recency head and add a clause saying the head covered 1 of 22 top-level entries. Rejected once measured. A warning asks the model to distrust the only data it has and go elsewhere; a better page just is not wrong. The warning also does nothing for a model that stops reading at the paths, which is the failure being fixed. +**Leave `glob` ordering alone and only warn in the footer.** This is what the first implementation did: keep the oldest-first head and add a clause saying the head covered 1 of 22 top-level entries. Rejected once measured. A warning asks the model to distrust the only data it has and go elsewhere; a better page just is not wrong. The warning also does nothing for a model that stops reading at the paths, which is the failure being fixed. **Sample always, replacing modification-time order outright.** Rejected. Over a complete result the order answers age questions — what is stale, what was touched last — a genuinely useful and separate purpose, and a complete result is the case where the order costs nothing and means everything. Sampling only past the cap is the point where the order has already stopped describing the result: the head of a 10,030-path list is not "the oldest files worth knowing about", it is an arbitrary 1% of them. @@ -91,11 +90,11 @@ They answer different questions and neither substitutes for the other. `list` an **Make `list` recursive with a depth argument.** Rejected for now. One level composes: the model lists what it needs to descend into. Recursion reintroduces the size and truncation problems this note exists to fix, and the provider primitive is deliberately one-level. -**Spill a capped listing through `ctx.spillStore`, as `glob` does.** Rejected for v1. `glob` needs spill because a truncated path list has no cheap successor call; a truncated listing does, and the footer states the complete size and composition, so the model knows both that it is looking at part of a directory and what to do about it. +**Spill a capped listing through `ctx.spillStore`, as `glob` does.** Rejected for v1. `glob` needs spill because its schema has no offset; `list` has a cheap successor call through the exact next offset in the footer, while every page repeats the complete size and composition. ## Consequences -An over-cap `glob` result no longer returns the most recently modified paths. That is a real contract change on a hot path, and it is why the footer, the prompt section, and the schema all state the sampled basis rather than leaving the model to infer it. A result within the cap is byte-identical to before, so age-ordered reading keeps working wherever it was working. +An over-cap `glob` result no longer returns the oldest paths at the head of modification-time order. That is a real contract change on a hot path, and it is why the footer, the prompt section, and the schema all state the sampled basis rather than leaving the model to infer it. A result within the cap is byte-identical to before, so age-ordered reading keeps working wherever it was working. Balancing is by first path segment only, so a result concentrated deeper — one enormous directory inside an otherwise even tree — is still shown unevenly below the top level. Recorded in the package's Known Limitations. @@ -105,6 +104,6 @@ The shipped tool surface grows by one tool in every deployment that loads `@deep ## Testing -Package tests pin the model-visible text of both surfaces. For `glob`: `sampleAcrossTopLevel` over a concentrated result, an exhausted group handing its slots on, a page smaller than the top level, absolute paths outside the workdir, and a flat result that must reproduce the sorted head; plus end-to-end assertions that a fitting result is untouched, that an over-cap result returns the sampled page with the sampled-basis footer, that the list hint disappears once the page reaches every entry, and that a flat over-cap result keeps the plain footer. For `list`: the envelope, type markers, singular and plural footers, the empty-directory footer, and the capped footer that keeps the sole directory visible. A registry-level test asserts that a listing emits no `fs/observed` and that a following `edit` still fails `FS_NOT_OBSERVED`, so the tool cannot become an accidental read-before-write bypass. Prompt-section registration, schema registration, and HMR disposal cover the fourth tool alongside the existing three. +Package tests pin the model-visible text of both surfaces. For `glob`: sampling over a concentrated result, an explicit relative root, more top-level groups than JavaScript's argument limit, an exhausted group handing its slots on, a page smaller than the top level, absolute paths outside the workdir, and a flat result that must reproduce the sorted head. For `list`: ordering, complete composition, offset continuation and rejection, empty directories, and filesystem names containing newlines, tag text, or marker suffixes. A registry-level test asserts that a listing emits no `fs/observed` and that a following `edit` still fails `FS_NOT_OBSERVED`, so the tool cannot become an accidental read-before-write bypass. Prompt-section registration, schema registration, and HMR disposal cover the fourth tool alongside the existing three. The assembled transcript is the `fs-list` ACP scenario: a workspace whose answer is its subdirectories, where the model calls `list` with no arguments and the pinned tool result carries the directory-first envelope and its composition footer — an answer `glob` could not have produced at all. diff --git a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.zh.md b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.zh.md index 4033254b08..bab0138a79 100644 --- a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.zh.md +++ b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.zh.md @@ -16,13 +16,13 @@ Status: implemented - **`--sort=modified` 按从旧到新排序。** 解包压缩档会还原档案内部保存的时间戳，它们早于用户自己写下的一切，因此新近解包的子树会落在任何宽泛匹配的最前面。（ripgrep 按升序排序；降序是 `--sortr`，此处未使用。） - **内联页面取的是该顺序的头部。** 从最前面保留 `globMaxResults`（100）条路径。在前两项性质之下，一个子树吃掉全部位置。 -单看每一项都站得住。合在一起，它们让 agent 收到的最普通的请求——「这个目录里有什么」——稳定地产出一个笃定的错误答案，因为结果里没有任何信息能区分「本工作区最新的 100 个文件」与「本工作区」。 +单看每一项都站得住。合在一起，它们让 agent 收到的最普通的请求——「这个目录里有什么」——稳定地产出一个笃定的错误答案，因为结果里没有任何信息能区分「本工作区按从旧到新顺序排在最前的 100 个文件」与「本工作区」。 ### 排序能修什么，不能修什么 由于 `rg --files` 输出文件、从不输出目录条目，一个目录的名字只能作为其下某个文件路径的前缀抵达模型。这既足以让排序变得非常重要，也不足以让 `glob` 回答那个问题。 -在一份复现该失败形态的目录上实测——24 个顶层条目、716 个文件、一个新近写入的子树： +在一份复现该失败形态的目录上实测——24 个顶层条目、716 个文件、一个时间戳较旧的子树： | 前 100 条路径的挑选方式 | 可见的顶层名个数 | | --- | --- | @@ -39,31 +39,30 @@ Status: implemented `@deepseek-ai/dsh-tool-fs-search`。未超过 `globMaxResults` 的结果完全不变：整体展示，按修改时间排序。只有结果更大时页面才改变——而恰恰在这种情况下，取头部是会失败的做法。 -`sampleAcrossTopLevel` 按路径首段对完整结果分组，并以轮转方式填充页面：每个顶层条目都先拿到一个位置，任何条目才可能拿到第二个；某个条目的路径用尽后退出，其剩余份额交给其余条目。排序在仍有意义的地方被保留下来——分组按 ripgrep 首次输出它们的顺序访问，而每个分组内部的路径保持原有相对顺序。页面按条目分组输出而非交错输出，使覆盖广度一眼可辨。 +`sampleAcrossTopLevel` 移除所显示的搜索根前缀，再按下一个路径段对完整结果分组，并以轮转方式填充页面：实际相对或绝对搜索根正下方的每个条目都先拿到一个位置，任何条目才可能拿到第二个；某个条目的路径用尽后退出，其剩余份额交给其余条目。排序在仍有意义的地方被保留下来——分组按 ripgrep 首次输出它们的顺序访问，而每个分组内部的路径保持原有相对顺序。页面按条目分组输出而非交错输出，使覆盖广度一眼可辨。 -footer 会说明取用依据，因为一个悄悄不再是「最新 N 条」的页面，只会成为同一个谎言更安静的版本： +footer 会说明取用依据，因为一个悄悄不再是「按修改时间排序的前 N 条」的页面，只会成为同一个谎言更安静的版本： ``` (Showing 100 of 10030 paths, sampled across 22 of the 22 top-level entries this pattern matched instead of taken in modification-time order. Full sorted result stored at: …) ``` -当页面无法触达全部顶层条目时——条目数多于位置数——footer 会给出已触达/总计的分布并指向 `list`。扁平结果（每个路径各自构成一个顶层条目）保留朴素的 `(Showing k of n paths. …)` footer：此时轮转结果**就是**排序后的头部，说明分布只会重复计数。spill 产物始终保存按修改时间排序的完整列表，排序视图不会丢失。 +当页面无法触达全部顶层条目时——条目数多于位置数——footer 会给出已触达/总计的分布，并要求模型缩小 `path`。扁平结果（每个路径各自构成一个顶层条目）保留朴素的 `(Showing k of n paths. …)` footer：此时轮转结果**就是**排序后的头部，说明分布只会重复计数。spill 产物始终保存按修改时间排序的完整列表，排序视图不会丢失。 -同一次改动里，指导与 schema 也不再误导：「not shell find or ls」改为「not shell find」；两处现在都写明：不含 `/` 的 pattern 匹配任意深度的基名、结果只有文件从不包含目录、未超上限的结果按修改时间排序而更大的结果为取样所得、目录内容请用 `list`。 +同一次改动里，指导与 schema 也不再误导：「not shell find or ls」改为「not shell find」；两处现在都写明：不含 `/` 的 pattern 匹配任意深度的基名、结果只有文件从不包含目录、未超上限的结果按修改时间排序，而更大的结果跨顶层条目取样。它们不会推荐当前组合中可能不存在的兄弟包工具。 ### `list`，位于 `@deepseek-ai/dsh-tool-fs` 在既有的 `ctx.fs.listDir` 原语之上新增第四个面向模型的文件系统工具；该原语此前交付时唯一的消费方是 skill（技能）发现，[seam Agent Note](../../archived/architecture/2026-07-03-filesystem-directory-listing-seam.md) 把面向模型的消费方推迟为一项单独的决策，也就是本文。 -它接受可选的 `path`，默认为 `.`，即调用 agent 的会话工作区，因此那个最常见的问题不需要任何参数；返回单个目录的直接子项，形如 `{ path, entries: [{ name, type }] }`，其中 `type` 为 `file`、`directory` 或 `other`。它只调用 `listDir`：seam 已经把不存在报告为 `FS_NOT_FOUND`、把非目录目标报告为 `FS_NOT_DIRECTORY`，前置 `stat` 只会多一次往返并制造第二个真源。 +它接受可选的 `path` 和从 1 开始的 `offset` 参数，默认取调用 agent 的会话工作区和第 1 个条目，并返回一个有界页面，形如 `{ path, offset, entries: [{ name, type }], totalEntries, counts }`，其中 `type` 为 `file`、`directory` 或 `other`。它只调用 `listDir`：seam 已经把不存在报告为 `FS_NOT_FOUND`、把非目录目标报告为 `FS_NOT_DIRECTORY`，前置 `stat` 只会多一次往返并制造第二个真源。 -有两条展示规则承载了这个决策： +有三条展示规则承载了这个决策： -- **先目录、再文件、最后非常规子项，各组内按字母序** —— 规范值与渲染文本采用同一顺序，使 Code Mode 调用方和模型看到同一份顺序契约。seam 返回的是稳定名称序，会把子目录散落在字母表各处；对这样的列表设上限可能丢掉全部子目录，在 `list` 内部重演同一种盲区。目录优先的顺序让截断只丢叶子，绝不丢结构。 -- **footer 始终说明完整列表的规模与构成** —— 例如 `(22 entries: 18 directories, 4 files)`；视图受 `listMaxEntries`（默认 200，可配置）截断时则为 `(Showing 200 of 5000 entries: 12 directories, 4988 files. …)`。因此部分列出结果不可能被读成整个目录。 - -目录条目渲染带尾部 `/`，非常规子项带 `@`，使模型无需第二次调用就能判断哪些可以继续进入。 +- **先目录、再文件、最后非常规子项，各组内按字母序**，然后再分页，使每个 offset 都遍历同一稳定顺序，且第一页保留可导航的结构。 +- **规范值和 Native 结果携带一个可继续取回的页面**，最多包含 `listMaxEntries` 个条目（默认 200，可配置）。footer 会说明完整规模与构成，并在最后一页之前给出 `offset=`，因此被省略的同级名称仍可取回。 +- **文件系统文本无法伪造展示结构。** 路径和条目名渲染为 JSON 字符串，并转义对包络有意义的字符；目录 `/` 与非常规子项 `@` 标记位于带引号名称之外，因此以 `@` 结尾的常规文件名仍可区分。 `list` 不发出 `fs/observed`。看到文件名不等于读过文件，列出绝不能满足 `@deepseek-ai/dsh-fs-policy` 施加的编辑前读取门禁。它声明 `isConcurrencySafe`，因为它完全不做任何变更。 @@ -73,7 +72,7 @@ instead of taken in modification-time order. Full sorted result stored at: …) ## Alternatives considered -**不动 `glob` 排序，只在 footer 里警告。** 这正是第一版实现的做法：保留新近序头部，加一句「该头部只覆盖 22 个顶层条目中的 1 个」。实测之后否决。一句警告是在要求模型不信任它手上唯一的数据并另寻他处；而一个更好的页面本身就不是错的。对于读到路径就停下的模型，警告也毫无作用——而那正是本次要修的失败。 +**不动 `glob` 排序，只在 footer 里警告。** 这正是第一版实现的做法：保留从旧到新的头部，加一句「该头部只覆盖 22 个顶层条目中的 1 个」。实测之后否决。一句警告是在要求模型不信任它手上唯一的数据并另寻他处；而一个更好的页面本身就不是错的。对于读到路径就停下的模型，警告也毫无作用——而那正是本次要修的失败。 **一律取样，彻底取消按修改时间排序。** 已否决。在完整结果上，该顺序回答的是与新旧有关的问题——哪些已经陈旧、哪些最后被动过——这是一个确实有用且独立的用途；而未超上限的完整结果恰恰是该顺序毫无代价、意义最大的场景。只在超过上限后取样，正好落在该顺序已经不再描述结果的那个点上：一份 10030 条列表的头部不是「最值得知道的最旧文件」，而是其中任意的 1%。 @@ -91,11 +90,11 @@ instead of taken in modification-time order. Full sorted result stored at: …) **让 `list` 支持递归和深度参数。** 暂时否决。单层是可组合的：模型列出它需要进入的那一层即可。递归会重新引入本 Agent Note 要解决的规模与截断问题，而且提供方原语本身就有意只做一层。 -**像 `glob` 那样，把达到上限的列出结果通过 `ctx.spillStore` 落盘。** v1 已否决。`glob` 需要 spill，是因为被截断的路径列表没有廉价的后继调用；被截断的列出结果有，而且 footer 已说明完整规模与构成，模型既知道自己只看到目录的一部分，也知道该怎么办。 +**像 `glob` 那样，把达到上限的列出结果通过 `ctx.spillStore` 落盘。** v1 已否决。`glob` 需要 spill，是因为其 schema 没有 offset；`list` 可以通过 footer 中精确的下一 offset 廉价地继续调用，而且每一页都会重复完整规模与构成。 ## Consequences -超过上限的 `glob` 结果不再返回修改时间最新的那些路径。这是热路径上一项真实的契约变更，也正因如此，footer、提示词段和 schema 都写明了取样这一依据，而不是留给模型去推断。未超上限的结果与此前逐字节相同，因此按新旧顺序阅读结果的用法在原本能用的地方继续能用。 +超过上限的 `glob` 结果不再返回按修改时间从旧到新排序时位于头部的那些路径。这是热路径上一项真实的契约变更，也正因如此，footer、提示词段和 schema 都写明了取样这一依据，而不是留给模型去推断。未超上限的结果与此前逐字节相同，因此按新旧顺序阅读结果的用法在原本能用的地方继续能用。 均衡只按路径首段进行，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目录——在顶层以下仍然分布不均。已记入该包的已知限制。 @@ -105,6 +104,6 @@ instead of taken in modification-time order. Full sorted result stored at: …) ## Testing -包测试钉住两个接口面向模型的文本。`glob` 方面：`sampleAcrossTopLevel` 在集中结果、某分组用尽后交出份额、页面小于顶层条目数、工作目录之外的绝对路径，以及必须复现排序头部的扁平结果上的行为；另有端到端断言——未超上限的结果原样不动、超上限结果返回取样页面并带取样依据 footer、页面覆盖全部条目后 list 提示消失、扁平的超上限结果保留朴素 footer。`list` 方面：包络、类型标记、单复数 footer、空目录 footer，以及让唯一那个目录留在视野内的截断 footer。一项注册表层级的测试断言列出不会发出 `fs/observed`，且随后的 `edit` 仍以 `FS_NOT_OBSERVED` 失败，使该工具不会变成意外的编辑前读取绕过口。提示词段注册、schema 注册与 HMR（热模块替换）dispose（资源释放）覆盖了这第四个工具与既有三个工具。 +包测试钉住两个接口面向模型的文本。`glob` 方面：对集中结果取样、显式相对根、顶层分组数量超过 JavaScript 参数上限、某分组用尽后交出份额、页面小于顶层条目数、工作目录之外的绝对路径，以及必须复现排序头部的扁平结果。`list` 方面：顺序、完整构成、offset 续页与拒绝、空目录，以及包含换行、标签文本或标记后缀的文件系统名称。一项注册表层级的测试断言列出不会发出 `fs/observed`，且随后的 `edit` 仍以 `FS_NOT_OBSERVED` 失败，使该工具不会变成意外的编辑前读取绕过口。提示词段注册、schema 注册与 HMR（热模块替换）dispose（资源释放）覆盖了这第四个工具与既有三个工具。 组装后的 transcript（文本记录）由 `fs-list` ACP 场景承担：该工作区的答案就是它的子目录，模型不带任何参数调用 `list`，被钉住的工具结果携带目录优先的包络及其构成 footer —— 这个答案 `glob` 根本无法给出。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 0b0045b668..e87fc92c05 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1449,7 +1449,7 @@ Requires: `tools` · `fs` · `systemPrompt` ```ts config-catalog /** Plugin config (all optional — `Config` supplies the defaults). */ export interface Config { - /** Maximum entries one `list` call renders inline; the footer still reports the complete count. */ + /** Maximum entries one `list` page returns; the footer still reports the complete count. */ listMaxEntries?: number /** Default and maximum number of lines returned by one `read` call. */ readLimit?: number diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 0884910bde..97bf0cac1d 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -20,8 +20,8 @@ This table connects model-visible tool names to the plugin package and service s | `@deepseek-ai/dsh-plan-mode` | `exit_plan_mode` | `ctx.tools`, `ctx.systemPrompt`, `ctx.userInteraction (execution time, opportunistic)` | `tool/call`, `plan/mode inactive on an approved review`, `tool/result` | - | exit_plan_mode stays in the model-facing schema while planning is inactive so transitions add no tool-catalog churn on top of the plan-policy change. Its execute path rejects calls outside plan mode; in plan mode it presents the plan over the user-interaction seam (approve / keep planning with feedback), and approval logs plan mode inactive at the step boundary. | | `@deepseek-ai/dsh-tool-bash` | `bash` | `ctx.tools`, `ctx.bash`, `ctx.tasks at call time for run_in_background` | `tool/call`, `tool/result` | - | The bash tool is the model-facing consumer of the bash executor seam. A `run_in_background` run registers with the generic `ctx.tasks` runtime and is collected/stopped through the `task_*` tools from `@deepseek-ai/dsh-tool-tasks`; the `enableRunInBackground` config (default true) removes the parameter entirely when disabled. | | `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `live plugin-tree mutations (mount/unmount)` | - | Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes. | -| `@deepseek-ai/dsh-tool-fs` | `edit`, `list`, `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. `list` enumerates one directory level through `ctx.fs.listDir` and records no observation, so seeing a filename never satisfies that read-before-write gate. | -| `@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). 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. An over-cap glob result does not return the head of the sorted list: its inline page is taken round-robin across the top-level entries of the complete result and the footer states that basis, because modification-time order is ascending and the restored timestamps of an unpacked archive put one subtree in front of every broad match. | +| `@deepseek-ai/dsh-tool-fs` | `edit`, `list`, `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. `list` paginates one directory level through `ctx.fs.listDir` and records no observation, so seeing a filename never satisfies that read-before-write gate. | +| `@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). 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. An over-cap glob result does not return the head of the sorted list: its inline page is taken round-robin across entries immediately beneath the actual search root and the footer states that basis, because modification-time order is ascending and the restored timestamps of an unpacked archive put one subtree in front of every broad match. | | `@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. | @@ -318,7 +318,7 @@ Source: [`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts ### `list` -List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. +List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents. ```json { @@ -327,6 +327,10 @@ List the direct children of one directory, with their type. Entries are director "path": { "type": "string", "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + }, + "offset": { + "type": "number", + "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." } } } @@ -389,13 +393,13 @@ Create or fully replace a UTF-8 text file. Source: [`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts) -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. `list` enumerates one directory level through `ctx.fs.listDir` and records no observation, so seeing a filename never satisfies that read-before-write gate. +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. `list` paginates one directory level through `ctx.fs.listDir` and records no observation, so seeing a filename never satisfies that read-before-write gate. ## `@deepseek-ai/dsh-tool-fs-search` ### `glob` -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 100 paths come back in modification-time order; a larger result instead returns 100 paths sampled across top-level directories, says so, and reports where the complete sorted list was saved. To see what a directory contains, use the list tool instead. +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 100 paths come back in modification-time order; a larger result instead returns 100 paths sampled across top-level entries, says so, and reports where the complete sorted list was saved. This tool does not enumerate directory entries. ```json { @@ -447,7 +451,7 @@ 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). 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. An over-cap glob result does not return the head of the sorted list: its inline page is taken round-robin across the top-level entries of the complete result and the footer states that basis, because modification-time order is ascending and the restored timestamps of an unpacked archive put one subtree in front of every broad match. +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). 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. An over-cap glob result does not return the head of the sorted list: its inline page is taken round-robin across entries immediately beneath the actual search root and the footer states that basis, because modification-time order is ascending and the restored timestamps of an unpacked archive put one subtree in front of every broad match. ## `@deepseek-ai/dsh-tool-pty` diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md index c78b763fec..94bc0823bb 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md @@ -5,7 +5,7 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. 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. @@ -99,10 +99,12 @@ interface ToolArgsMap { } & Record; /** 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. */ get_goal: Record; - /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */ + /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents. */ list: { /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */ path?: string; + /** 1-based first entry to return. Defaults to 1; use the footer value to continue. */ + offset?: number; } & Record; /** 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. */ ralph: { @@ -307,10 +309,17 @@ interface ToolOutputMap { }; list: { path: string; + offset: number; entries: ({ name: string; type: "file" | "directory" | "other"; })[]; + totalEntries: number; + counts: { + directories: number; + files: number; + other: number; + }; }; ralph: { runId: string; diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json index f9aea468b5..dcacaad8ff 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json @@ -174,13 +174,17 @@ }, { "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", "parameters": { "type": "object", "properties": { "path": { "type": "string", "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + }, + "offset": { + "type": "number", + "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." } } } diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md index ede2684ae4..1a8589a47b 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md @@ -5,7 +5,7 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. 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. @@ -82,10 +82,12 @@ interface ToolArgsMap { } & Record; /** 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. */ get_goal: Record; - /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */ + /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents. */ list: { /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */ path?: string; + /** 1-based first entry to return. Defaults to 1; use the footer value to continue. */ + offset?: number; } & Record; /** 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. */ ralph: { @@ -278,10 +280,17 @@ interface ToolOutputMap { }; list: { path: string; + offset: number; entries: ({ name: string; type: "file" | "directory" | "other"; })[]; + totalEntries: number; + counts: { + directories: number; + files: number; + other: number; + }; }; ralph: { runId: string; diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json index 1333345b48..9f55d9291f 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json @@ -117,13 +117,17 @@ }, { "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", "parameters": { "type": "object", "properties": { "path": { "type": "string", "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + }, + "offset": { + "type": "number", + "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." } } } diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md index ede2684ae4..1a8589a47b 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md @@ -5,7 +5,7 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. 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. @@ -82,10 +82,12 @@ interface ToolArgsMap { } & Record; /** 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. */ get_goal: Record; - /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */ + /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents. */ list: { /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */ path?: string; + /** 1-based first entry to return. Defaults to 1; use the footer value to continue. */ + offset?: number; } & Record; /** 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. */ ralph: { @@ -278,10 +280,17 @@ interface ToolOutputMap { }; list: { path: string; + offset: number; entries: ({ name: string; type: "file" | "directory" | "other"; })[]; + totalEntries: number; + counts: { + directories: number; + files: number; + other: number; + }; }; ralph: { runId: string; diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md index ede2684ae4..1a8589a47b 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md @@ -5,7 +5,7 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. 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. @@ -82,10 +82,12 @@ interface ToolArgsMap { } & Record; /** 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. */ get_goal: Record; - /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */ + /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents. */ list: { /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */ path?: string; + /** 1-based first entry to return. Defaults to 1; use the footer value to continue. */ + offset?: number; } & Record; /** 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. */ ralph: { @@ -278,10 +280,17 @@ interface ToolOutputMap { }; list: { path: string; + offset: number; entries: ({ name: string; type: "file" | "directory" | "other"; })[]; + totalEntries: number; + counts: { + directories: number; + files: number; + other: number; + }; }; ralph: { runId: string; diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/escalation-approved/system-prompt.expected.md index edca40eed4..cd3c81f6f8 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/escalation-approved/system-prompt.expected.md @@ -5,7 +5,7 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. 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. diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json index ffb310c278..7094daf44e 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json @@ -117,13 +117,17 @@ }, { "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", "parameters": { "type": "object", "properties": { "path": { "type": "string", "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + }, + "offset": { + "type": "number", + "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." } } } diff --git a/examples/acp-agent/tests/snapshots/fs-list/session.jsonl b/examples/acp-agent/tests/snapshots/fs-list/session.jsonl index 0a05e2b1fe..533571ee3f 100644 --- a/examples/acp-agent/tests/snapshots/fs-list/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-list/session.jsonl @@ -15,7 +15,7 @@ {"type":"assistant/chunk","seq":47,"time":1785159115922,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":48,"time":1785159115926,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to call the list tool with no arguments and then reply with the names of the subdirectories it reports, alphabetically, separated by a single space."},{"type":"tool-call","id":"call_00_BSi06gcYvl6oad3I5qqG9244","name":"list","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":5513,"outputTokens":62,"cacheReadTokens":0,"reasoningTokens":35}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"surfaceOp":"append"} {"type":"tool/call","seq":49,"time":1785159115927,"data":{"turn":1,"step":1,"callId":"call_00_BSi06gcYvl6oad3I5qqG9244","name":"list","arguments":"{}"}} -{"type":"tool/result","seq":50,"time":1785159115944,"data":{"turn":1,"step":1,"callId":"call_00_BSi06gcYvl6oad3I5qqG9244","content":[{"type":"text","text":"/var/folders/8k/kj35k1fd6t90n0czg7k3hv140000gn/T/acp-snap-cwd-QJ2ZC6\ndirectory\n\ndocs/\nsrc/\npackage.json\nREADME.txt\n\n(4 entries: 2 directories, 2 files)\n"}],"isError":false},"sourceEventSeqs":[49],"surfaceOp":"append"} +{"type":"tool/result","seq":50,"time":1785159115944,"data":{"turn":1,"step":1,"callId":"call_00_BSi06gcYvl6oad3I5qqG9244","content":[{"type":"text","text":"\"/var/folders/8k/kj35k1fd6t90n0czg7k3hv140000gn/T/acp-snap-cwd-QJ2ZC6\"\ndirectory\n\n\"docs\"/\n\"src\"/\n\"package.json\"\n\"README.txt\"\n\n(4 entries: 2 directories, 2 files)\n"}],"isError":false},"sourceEventSeqs":[49],"surfaceOp":"append"} {"type":"step/end","seq":51,"time":1785159115950,"data":{"turn":1,"step":1}} {"type":"step/start","seq":52,"time":1785159115951,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":53,"time":1785159116889,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/lsp-definition/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/lsp-definition/system-prompt.expected.md index 5a5df6233c..d02b6d0859 100644 --- a/examples/acp-agent/tests/snapshots/lsp-definition/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/lsp-definition/system-prompt.expected.md @@ -5,7 +5,7 @@ You are a coding assistant powered by the deepseek-v4-pro model. Your working di Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. 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. diff --git a/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json index 3a0e7c1408..ab1bda91f3 100644 --- a/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json @@ -117,13 +117,17 @@ }, { "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", "parameters": { "type": "object", "properties": { "path": { "type": "string", "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + }, + "offset": { + "type": "number", + "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." } } } diff --git a/examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md index 70dd754517..c5496aeed5 100644 --- a/examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md @@ -5,7 +5,7 @@ You are a coding assistant powered by the deepseek-v4-pro model. Your working di Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. 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. diff --git a/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json index c529ad9077..0d20d22762 100644 --- a/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json @@ -117,13 +117,17 @@ }, { "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", "parameters": { "type": "object", "properties": { "path": { "type": "string", "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + }, + "offset": { + "type": "number", + "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." } } } diff --git a/examples/acp-agent/tests/snapshots/session-query-spill/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/session-query-spill/system-prompt.expected.md index 658fa4e07c..7d13160613 100644 --- a/examples/acp-agent/tests/snapshots/session-query-spill/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/session-query-spill/system-prompt.expected.md @@ -5,7 +5,7 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. 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. diff --git a/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json index 4eff11591a..caee8e049e 100644 --- a/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json @@ -117,13 +117,17 @@ }, { "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", "parameters": { "type": "object", "properties": { "path": { "type": "string", "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + }, + "offset": { + "type": "number", + "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." } } } diff --git a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md index 6d926a90a8..e6ab6361db 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md @@ -5,7 +5,7 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. 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. diff --git a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json index ffb310c278..7094daf44e 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json @@ -117,13 +117,17 @@ }, { "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", "parameters": { "type": "object", "properties": { "path": { "type": "string", "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + }, + "offset": { + "type": "number", + "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." } } } diff --git a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md index 6d926a90a8..e6ab6361db 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md @@ -5,7 +5,7 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. 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. diff --git a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json index ffb310c278..7094daf44e 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json @@ -117,13 +117,17 @@ }, { "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", "parameters": { "type": "object", "properties": { "path": { "type": "string", "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + }, + "offset": { + "type": "number", + "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." } } } diff --git a/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md index 4c20e18272..451746f412 100644 --- a/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md @@ -5,7 +5,7 @@ You are a coding assistant powered by the deepseek-v4-pro model. Your working di Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. 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. diff --git a/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json index 59e3baf6b1..6c389246e2 100644 --- a/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json @@ -117,13 +117,17 @@ }, { "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", "parameters": { "type": "object", "properties": { "path": { "type": "string", "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + }, + "offset": { + "type": "number", + "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." } } } diff --git a/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md index 6c5155f262..fdacca4b7f 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md @@ -5,7 +5,7 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. 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. diff --git a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json index ffb310c278..7094daf44e 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json @@ -117,13 +117,17 @@ }, { "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.", + "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", "parameters": { "type": "object", "properties": { "path": { "type": "string", "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." + }, + "offset": { + "type": "number", + "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." } } } diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index c0f80e3cdf..0471db78e0 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1783957884563,"data":{"title":"Reply with exactly DIRECT_CHILD_OK and","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for.\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** 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`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */\n list: {\n /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */\n path?: string;\n } & Record;\n /** 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. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** 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. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** 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`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** 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`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** 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. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** 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). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** 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. The 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. Script-body hooks: - `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. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n list: {\n path: string;\n entries: ({\n name: string;\n type: \"file\" | \"directory\" | \"other\";\n })[];\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"name":"list","description":"List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"Directory to list. Defaults to the session workspace; a relative path resolves against it."}}}},{"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":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer.\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** 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`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents. */\n list: {\n /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */\n path?: string;\n /** 1-based first entry to return. Defaults to 1; use the footer value to continue. */\n offset?: number;\n } & Record;\n /** 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. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** 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. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** 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`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** 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`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** 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. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** 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). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** 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. The 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. Script-body hooks: - `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. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n list: {\n path: string;\n offset: number;\n entries: ({\n name: string;\n type: \"file\" | \"directory\" | \"other\";\n })[];\n totalEntries: number;\n counts: {\n directories: number;\n files: number;\n other: number;\n };\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"name":"list","description":"List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"Directory to list. Defaults to the session workspace; a relative path resolves against it."},"offset":{"type":"number","description":"1-based first entry to return. Defaults to 1; use the footer value to continue."}}}},{"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":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":7,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 2bf8be7bfb..f0cad5bcd7 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1783957884700,"data":{"title":"Reply with exactly WORKFLOW_CHILD_OK and","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for.\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** 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`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */\n list: {\n /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */\n path?: string;\n } & Record;\n /** 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. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** 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. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** 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`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** 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`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** 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. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** 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). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** 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. The 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. Script-body hooks: - `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. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n list: {\n path: string;\n entries: ({\n name: string;\n type: \"file\" | \"directory\" | \"other\";\n })[];\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"name":"list","description":"List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"Directory to list. Defaults to the session workspace; a relative path resolves against it."}}}},{"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":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer.\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** 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`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents. */\n list: {\n /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */\n path?: string;\n /** 1-based first entry to return. Defaults to 1; use the footer value to continue. */\n offset?: number;\n } & Record;\n /** 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. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** 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. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** 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`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** 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`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** 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. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** 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). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** 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. The 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. Script-body hooks: - `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. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n list: {\n path: string;\n offset: number;\n entries: ({\n name: string;\n type: \"file\" | \"directory\" | \"other\";\n })[];\n totalEntries: number;\n counts: {\n directories: number;\n files: number;\n other: number;\n };\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"name":"list","description":"List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"Directory to list. Defaults to the session workspace; a relative path resolves against it."},"offset":{"type":"number","description":"1-based first entry to return. Defaults to 1; use the footer value to continue."}}}},{"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":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":7,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl index 8f531cf789..883feaf563 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1783957884479,"data":{"title":"Run this advanced flow exactly","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for.\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** 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`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains. */\n list: {\n /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */\n path?: string;\n } & Record;\n /** 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. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** 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. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** 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`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** 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`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** 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. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** 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). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** 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. The 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. Script-body hooks: - `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. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n list: {\n path: string;\n entries: ({\n name: string;\n type: \"file\" | \"directory\" | \"other\";\n })[];\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"name":"list","description":"List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"Directory to list. Defaults to the session workspace; a relative path resolves against it."}}}},{"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":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer.\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** 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`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents. */\n list: {\n /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */\n path?: string;\n /** 1-based first entry to return. Defaults to 1; use the footer value to continue. */\n offset?: number;\n } & Record;\n /** 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. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** 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. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** 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`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** 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`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** 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. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** 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). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** 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. The 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. Script-body hooks: - `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. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n list: {\n path: string;\n offset: number;\n entries: ({\n name: string;\n type: \"file\" | \"directory\" | \"other\";\n })[];\n totalEntries: number;\n counts: {\n directories: number;\n files: number;\n other: number;\n };\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"name":"list","description":"List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"Directory to list. Defaults to the session workspace; a relative path resolves against it."},"offset":{"type":"number","description":"1-based first entry to return. Defaults to 1; use the footer value to continue."}}}},{"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":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":6,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":7,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl b/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl index 2cde7d9e42..fd122fc594 100644 --- a/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl +++ b/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Exercise the six PTY tools in order, including one missing-session signal error, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":0,"data":{"title":"Exercise the six PTY tools","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for.\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse a terminal session only when work needs persistent terminal state or interactive stdin; prefer bash/read/write/edit for bounded one-shot operations. Track every terminal session id and close sessions that no longer matter. An inferred_idle or timeout result does not prove the foreground command exited.\n\nTrack 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.\n\nUse 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.\n\nUse 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.","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"name":"list","description":"List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; the first 200 are returned inline and the footer reports the complete count. Unlike glob, this shows subdirectories, so it is how to see what a directory contains.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"Directory to list. Defaults to the session workspace; a relative path resolves against it."}}}},{"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":"terminal_close","description":"Close one persistent terminal and wait until its captured owned process tree is gone.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."}},"required":["sessionId"]}},{"name":"terminal_list","description":"List persistent terminal sessions owned by the current agent.","parameters":{"type":"object","properties":{}}},{"name":"terminal_open","description":"Create a persistent, owner-isolated terminal session from a registered backend type. Use this for shell or REPL state that must survive across tool calls.","parameters":{"type":"object","properties":{"type":{"type":"string","description":"Registered terminal backend type, usually \"shell\"."},"name":{"type":"string","description":"Optional owner-local display name such as \"main\" or \"gdb\"."},"cwd":{"type":"string","description":"Initial working directory. Defaults to the deployment workspace root."}},"required":["type"]}},{"name":"terminal_read","description":"Read a bounded page of retained output from a persistent terminal without sending input.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"offset":{"type":"number","description":"Newest-relative line offset (default 0)."},"count":{"type":"number","description":"Requested line count (default 500; backend caps apply)."}},"required":["sessionId"]}},{"name":"terminal_send","description":"Send text to a persistent terminal. By default Enter is submitted and the call waits for a prompt, stdin wait, output silence, timeout, or session exit. Background mode returns a task id for task_output/task_kill.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id returned by terminal_open or terminal_list."},"text":{"type":"string","description":"UTF-8 text to write to the terminal."},"submit":{"type":"boolean","description":"Submit Enter after text (default true). Set false for control characters or incomplete REPL input."},"run_in_background":{"type":"boolean","description":"Return a task id immediately; collect with task_output or stop with task_kill."}},"required":["sessionId","text"]}},{"name":"terminal_signal","description":"Send an allowed signal to the current foreground process group of a persistent terminal.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"signal":{"type":"string","description":"Signal to deliver. Shell-targeted SIGKILL is rejected; use terminal_close.","enum":["SIGINT","SIGTERM","SIGKILL","SIGTSTP","SIGHUP"]}},"required":["sessionId","signal"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer.\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse a terminal session only when work needs persistent terminal state or interactive stdin; prefer bash/read/write/edit for bounded one-shot operations. Track every terminal session id and close sessions that no longer matter. An inferred_idle or timeout result does not prove the foreground command exited.\n\nTrack 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.\n\nUse 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.\n\nUse 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.","tools":[{"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"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."}},"required":["command","description"]}},{"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."}},"required":["file_path","old_string","new_string"]}},{"name":"list","description":"List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"Directory to list. Defaults to the session workspace; a relative path resolves against it."},"offset":{"type":"number","description":"1-based first entry to return. Defaults to 1; use the footer value to continue."}}}},{"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":"terminal_close","description":"Close one persistent terminal and wait until its captured owned process tree is gone.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."}},"required":["sessionId"]}},{"name":"terminal_list","description":"List persistent terminal sessions owned by the current agent.","parameters":{"type":"object","properties":{}}},{"name":"terminal_open","description":"Create a persistent, owner-isolated terminal session from a registered backend type. Use this for shell or REPL state that must survive across tool calls.","parameters":{"type":"object","properties":{"type":{"type":"string","description":"Registered terminal backend type, usually \"shell\"."},"name":{"type":"string","description":"Optional owner-local display name such as \"main\" or \"gdb\"."},"cwd":{"type":"string","description":"Initial working directory. Defaults to the deployment workspace root."}},"required":["type"]}},{"name":"terminal_read","description":"Read a bounded page of retained output from a persistent terminal without sending input.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"offset":{"type":"number","description":"Newest-relative line offset (default 0)."},"count":{"type":"number","description":"Requested line count (default 500; backend caps apply)."}},"required":["sessionId"]}},{"name":"terminal_send","description":"Send text to a persistent terminal. By default Enter is submitted and the call waits for a prompt, stdin wait, output silence, timeout, or session exit. Background mode returns a task id for task_output/task_kill.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id returned by terminal_open or terminal_list."},"text":{"type":"string","description":"UTF-8 text to write to the terminal."},"submit":{"type":"boolean","description":"Submit Enter after text (default true). Set false for control characters or incomplete REPL input."},"run_in_background":{"type":"boolean","description":"Return a task id immediately; collect with task_output or stop with task_kill."}},"required":["sessionId","text"]}},{"name":"terminal_signal","description":"Send an allowed signal to the current foreground process group of a persistent terminal.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"signal":{"type":"string","description":"Signal to deliver. Shell-targeted SIGKILL is rejected; use terminal_close.","enum":["SIGINT","SIGTERM","SIGKILL","SIGTSTP","SIGHUP"]}},"required":["sessionId","signal"]}},{"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":"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."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"pty-spawn","name":"terminal_open","argumentsDelta":"{\"type\":\"shell\",\"name\":\"main\"}"}}} {"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-spawn","name":"terminal_open","arguments":"{\"type\":\"shell\",\"name\":\"main\"}"}}}} diff --git a/packages/fs/tool-fs-search/README.i18n.yaml b/packages/fs/tool-fs-search/README.i18n.yaml index ec8f6f8968..68c621949d 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: 33792a6f4b72baa2626c6e8d37c672fb39681554 -README.zh.md: 5d13a7ff2cb3ddfda8168a34e4a4a897d3413e11 +README.md: 51b3fa5385330cdaba0b36dd71a6efe4fd3d0db5 +README.zh.md: 855db224652b818d5f3dadffd275581b5b760007 diff --git a/packages/fs/tool-fs-search/README.md b/packages/fs/tool-fs-search/README.md index 33792a6f4b..51b3fa5385 100644 --- a/packages/fs/tool-fs-search/README.md +++ b/packages/fs/tool-fs-search/README.md @@ -34,14 +34,14 @@ All keys are optional; the defaults are the shipped search caps. | 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, modification-time ordered — `rg --files` never emits a directory, so no pattern makes `glob` describe a directory's contents; that is [`dsh-tool-fs`](../tool-fs/)'s `list`. The pattern keeps ripgrep semantics: without a `/` it matches the basename at any depth, so `*` matches the whole tree. | +| `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, modification-time ordered; `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. | | `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 every acquired path in `{ paths }`; `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 a head 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 `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 }`; `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 a head 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 @@ -58,7 +58,7 @@ After the load-time `rg` probe succeeds, every request in this plugin's registra ##### Glob guidance ```markdown -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 directories, so it spans the tree instead of one subtree. Use the list tool to see what a directory contains. +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. ``` ##### Grep guidance @@ -93,7 +93,7 @@ Prefix-stable while tool visibility and definitions are unchanged. Registration #### What the model sees -`glob` returns one path per line; `grep` groups `Line : ` matches beneath each path. Empty searches return `No files found` or `No matches found`. A capped result ends with its omission count plus the spill locator and backend retrieval hint, or says the complete result could not be saved. An over-cap `glob` result does not show the head of the sorted list: its inline page takes paths round-robin across the complete result's top-level entries, so one recently-written subtree cannot own every slot, and the footer says the page was sampled rather than taken in modification-time order, together with how many top-level entries it reached. When it could not reach them all, the footer also points at `list`. A result that fits inline is untouched, and a flat result — every path its own top-level entry — keeps the plain footer, because there the sample IS the recency-ordered head. The spill artifact always holds the complete list in modification-time order. +`glob` returns one path per line; `grep` groups `Line : ` matches beneath each path. Empty searches return `No files found` or `No matches found`. A capped result ends with its omission count plus the spill locator and backend retrieval hint, or says the complete result could not be saved. An over-cap `glob` result does not show the head of the sorted list: its inline page takes paths round-robin across entries immediately beneath the actual search root, so one old-timestamped subtree cannot own every slot, and the footer states the sampled basis and how many top-level entries it reached. When it cannot reach them all, the footer tells the model to narrow `path`. A result that fits inline is untouched, and a flat result — every path its own top-level entry — keeps the plain footer, because there the sample is the modification-time-ordered head. The spill artifact always holds the complete list in modification-time order. #### Token effect @@ -122,4 +122,4 @@ Append-only; newly visible content follows the reusable request prefix and does - **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. - **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 groups by first path segment only** — an over-cap `glob` page balances across 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. +- **Sampling 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 5d13a7ff2c..855db22465 100644 --- a/packages/fs/tool-fs-search/README.zh.md +++ b/packages/fs/tool-fs-search/README.zh.md @@ -34,14 +34,14 @@ await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh- | 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，因此任何 pattern 都无法让 `glob` 描述一个目录的内容，那是 [`dsh-tool-fs`](../tool-fs/) 的 `list`。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。未超过 `globMaxResults` 的结果按修改时间排序；超过时内联页面改为跨顶层条目取样（见下）。 | +| `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。未超过 `globMaxResults` 的结果按修改时间排序；超过时内联页面改为跨顶层条目取样（见下）。 | | `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 `{ paths }` 中保留所有已取得路径；`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 Native 渲染器。直接接口调用的逻辑结果超过内联上限时，后置政策会尽力通过 `ctx.spillStore.saveText()` 保存完整格式化预览，并只把呈现替换为头部页面加 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 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；借助 `root`，Native 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 Native 渲染器。直接接口调用的逻辑结果超过内联上限时，后置政策会尽力通过 `ctx.spillStore.saveText()` 保存完整格式化预览，并只把呈现替换为头部页面加 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 @@ -58,7 +58,7 @@ await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh- ##### Glob 指导 ```markdown -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 directories, so it spans the tree instead of one subtree. Use the list tool to see what a directory contains. +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. ``` ##### Grep 指导 @@ -93,7 +93,7 @@ Use the grep tool — not shell grep or rg — to search file contents. Use read #### 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。超过上限的 `glob` 结果不再展示排序列表的头部：其内联页面按轮转方式跨完整结果的顶层条目取样，因此单个新近写入的子树无法占满所有位置；footer 会说明该页面是取样得到而非按修改时间取用，并给出它触达了多少个顶层条目。未能触达全部时，footer 还会指向 `list`。未超过上限的结果原样不动；扁平结果（每个路径各自构成一个顶层条目）保留朴素 footer，因为此时取样结果就等于按新近度排序的头部。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。超过上限的 `glob` 结果不再展示排序列表的头部：其内联页面按轮转方式跨实际搜索根正下方的条目取样，因此单个时间戳较旧的子树无法占满所有位置；footer 会说明取样依据及其触达的顶层条目数。无法触达全部时，footer 会要求模型缩小 `path`。未超过上限的结果原样不动；扁平结果（每个路径各自构成一个顶层条目）保留朴素 footer，因为此时取样结果就是按修改时间排序的头部。spill 产物始终保存按修改时间排序的完整列表。 #### Token 影响 @@ -122,4 +122,4 @@ Use the grep tool — not shell grep or rg — to search file contents. Use read - **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。 -- **取样只按路径首段分组**：超过上限的 `glob` 页面在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。 +- **取样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。 diff --git a/packages/fs/tool-fs-search/src/glob.ts b/packages/fs/tool-fs-search/src/glob.ts index d46b1d352d..94d9b0e627 100644 --- a/packages/fs/tool-fs-search/src/glob.ts +++ b/packages/fs/tool-fs-search/src/glob.ts @@ -107,7 +107,7 @@ export function buildGlobCommand(input: GlobInput): string { * result's top level it reaches. */ export interface GlobSample { - /** Paths to show inline: grouped by top-level entry, recency-ordered within each group. */ + /** Paths to show inline: grouped by top-level entry, modification-time ordered within each group. */ items: string[] /** Distinct top-level entries the shown paths reach. */ shown: number @@ -115,6 +115,18 @@ export interface GlobSample { total: number } +/** Remove the displayed search-root prefix before choosing a top-level group. */ +function relativeToSearchRoot(path: string, root: string): string { + if (root === '.') return path.replace(/^\.[\\/]/, '') + const trimmedRoot = root.replace(/[\\/]+$/, '') + if (trimmedRoot.length === 0) return path.replace(/^[\\/]+/, '') + if (path === trimmedRoot) return '' + if (path.startsWith(`${trimmedRoot}/`) || path.startsWith(`${trimmedRoot}\\`)) { + return path.slice(trimmedRoot.length + 1) + } + return path +} + /** * The leading path segment of one display path — the top-level entry, relative * to the search root, that the path sits under. A path with no separator is its @@ -149,18 +161,19 @@ function topLevelSegment(path: string): string { * * @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`. + * @param root - the search root in the same display-path space as `paths`. * @returns the page grouped by top-level entry, with the shown/total top-level spread. */ -export function sampleAcrossTopLevel(paths: readonly string[], maxItems: number): GlobSample { +export function sampleAcrossTopLevel(paths: readonly string[], maxItems: number, root = '.'): GlobSample { const groups = new Map() for (const path of paths) { - const group = groups.get(topLevelSegment(path)) - if (group === undefined) groups.set(topLevelSegment(path), [path]) + const key = topLevelSegment(relativeToSearchRoot(path, root)) + const group = groups.get(key) + if (group === undefined) groups.set(key, [path]) else group.push(path) } - // Bounding the rounds by the largest group makes termination structural: the - // page can only fill or the groups run out, never spin on empty rounds. - const rounds = Math.max(0, ...[...groups.values()].map(group => group.length)) + let rounds = 0 + for (const group of groups.values()) rounds = Math.max(rounds, group.length) const taken = new Map() let count = 0 for (let round = 0; round < rounds && count < maxItems; round += 1) { @@ -186,7 +199,7 @@ export function sampleAcrossTopLevel(paths: readonly string[], maxItems: number) * 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 recency-ordered head, and naming a spread would only + * the sample is the modification-time-ordered head, and naming a spread would only * restate the path counts already there. * * @param sample - the inline page and its top-level spread. @@ -202,17 +215,17 @@ export function formatGlobOutput(sample: GlobSample, seen: number, spillRef: Spi const basis = sample.total === seen ? '.' : `, sampled across ${sample.shown} of the ${sample.total} top-level entries this pattern matched instead of taken in modification-time order.` - + (sample.shown < sample.total ? ' Use the list tool to see what a directory contains.' : '') + + (sample.shown < sample.total ? ' Narrow path to inspect a specific subtree.' : '') return `${body}\n\n(Showing ${sample.items.length} of ${seen} paths${basis} ${recovery})` } -/** Bound and format one canonical path list for the Native surface. */ -function renderGlobPaths(paths: string[], maxResults: number, spillRef?: SpillRef): string { +/** Bound and format one canonical path list for the Native surface relative to its search root. */ +function renderGlobPaths(paths: string[], maxResults: number, root: string, spillRef?: SpillRef): string { if (paths.length === 0) return 'No files found' // A result that fits is shown whole, untouched: modification-time order is the // tool's contract, and over a complete result it is what answers age questions. if (paths.length <= maxResults) return paths.join('\n') - return formatGlobOutput(sampleAcrossTopLevel(paths, maxResults), paths.length, spillRef) + return formatGlobOutput(sampleAcrossTopLevel(paths, maxResults, root), paths.length, spillRef) } /** @@ -238,16 +251,16 @@ export function applyGlobTool(ctx: Context, caps: GlobToolCaps): void { name: 'tool:glob', order: 103, text: '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 directories, ' - + 'so it spans the tree instead of one subtree. Use the list tool to see what a directory contains.', + + '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.', }) const tool = defineTool({ 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 ${caps.maxResults} paths come back in modification-time order; a larger result instead returns ${caps.maxResults} paths sampled across top-level directories, ` - + 'says so, and reports where the complete sorted list was saved. To see what a directory contains, use the list tool instead.', + + `Up to ${caps.maxResults} paths come back in modification-time order; a larger result instead returns ${caps.maxResults} paths sampled across top-level entries, ` + + 'says so, and reports where the complete sorted list was saved. This tool does not enumerate directory entries.', parameters: { pattern: { type: 'string', @@ -263,15 +276,17 @@ export function applyGlobTool(ctx: Context, caps: GlobToolCaps): void { type: 'object', additionalProperties: false, properties: { + root: { type: 'string', required: true }, paths: { type: 'array', required: true, items: { type: 'string' } }, }, }, - render: (_args, value) => [{ type: 'text', text: renderGlobPaths(value.paths, caps.maxResults) }], + render: (_args, value) => [{ type: 'text', text: renderGlobPaths(value.paths, caps.maxResults, value.root) }], }, async execute(args, exec) { const input = parseGlobArgs(args) const run = await runRipgrep(ctx, exec, 'glob', buildGlobCommand(input), caps.rawOutputMaxBytes) - if (run.noMatches) return { paths: [] } + const root = input.path === undefined ? '.' : toWorkdirRelative(input.path, run.workdir) + if (run.noMatches) return { root, paths: [] } const all: string[] = [] for (const line of run.stdout.split('\n')) { @@ -279,7 +294,7 @@ export function applyGlobTool(ctx: Context, caps: GlobToolCaps): void { const displayPath = toWorkdirRelative(line, run.workdir) all.push(displayPath) } - return { paths: all } + return { root, paths: all } }, presentCall: presentGlobCall, }) @@ -287,14 +302,14 @@ export function applyGlobTool(ctx: Context, caps: GlobToolCaps): void { ctx.on('tools/post-execute', async (exec, result, next) => { const decision = await next() - const value = acceptedSurfaceValue(ctx, tool, exec, result, decision) as { paths: string[] } | undefined + const value = acceptedSurfaceValue(ctx, tool, exec, result, decision) as { root: string; paths: string[] } | undefined if (value === undefined) return decision const paths = value.paths if (paths.length <= caps.maxResults) return decision const spillRef = await trySaveFormattedResult(ctx, exec, 'glob-results.txt', paths.join('\n')) return { kind: 'accept', - content: [{ type: 'text', text: renderGlobPaths(paths, caps.maxResults, spillRef) }], + content: [{ type: 'text', text: renderGlobPaths(paths, caps.maxResults, value.root, spillRef) }], ...decision.additionalContexts !== undefined ? { additionalContexts: decision.additionalContexts } : {}, } }) diff --git a/packages/fs/tool-fs-search/tests/tools.spec.ts b/packages/fs/tool-fs-search/tests/tools.spec.ts index 0bbe0e0bf5..df49ce33aa 100644 --- a/packages/fs/tool-fs-search/tests/tools.spec.ts +++ b/packages/fs/tool-fs-search/tests/tools.spec.ts @@ -185,6 +185,10 @@ describe('registration', () => { const prompt = renderPrompt(await ctx.systemPrompt.assemble()) expect(prompt).toContain('Use the glob tool') expect(prompt).toContain('Use the grep tool') + expect(prompt).toContain('sampled across top-level entries') + expect(prompt).not.toContain('sampled across top-level directories') + const glob = ctx.tools.schemas().find(schema => schema.name === 'glob') + expect(glob?.description).toContain('sampled across top-level entries') }) it('does not register glob or grep when the bash executor cannot find rg', async () => { @@ -526,9 +530,37 @@ describe('cross-directory sampling', () => { .toEqual({ items: ['/out/a', '/away/c'], shown: 2, total: 2 }) }) - it('reproduces the recency-ordered head for a flat result', () => { + it('reproduces the modification-time-ordered head for a flat result', () => { expect(sampleAcrossTopLevel(['a.ts', 'b.ts', 'c.ts'], 2)).toEqual({ items: ['a.ts', 'b.ts'], shown: 2, total: 3 }) }) + + it('groups paths relative to an explicit search root', () => { + expect(sampleAcrossTopLevel([ + 'workspace/vendor/a.ts', + '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'], + 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(['C:\\root\\a\\one', 'C:\\root\\b\\two'], 2, 'C:\\root')) + .toEqual({ items: ['C:\\root\\a\\one', 'C:\\root\\b\\two'], shown: 2, total: 2 }) + expect(sampleAcrossTopLevel(['other/a.ts'], 1, 'src')) + .toEqual({ items: ['other/a.ts'], shown: 1, total: 1 }) + expect(sampleAcrossTopLevel(['src'], 1, 'src')) + .toEqual({ items: ['src'], shown: 1, total: 1 }) + }) + + it('handles more top-level groups than the JavaScript argument limit', () => { + const paths = Array.from({ length: 125_000 }, (_, index) => `dir-${index}/file.txt`) + expect(sampleAcrossTopLevel(paths, 100)).toMatchObject({ shown: 100, total: 125_000 }) + }) }) describe('glob results', () => { @@ -537,7 +569,7 @@ describe('glob results', () => { bash.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({ paths: [join('src', 'a.ts'), '/elsewhere/b.ts', 'rel/c.ts'] }) + expect(result.value).toEqual({ root: '.', paths: [join('src', 'a.ts'), '/elsewhere/b.ts', 'rel/c.ts'] }) expect(text(result)).toBe(`${join('src', 'a.ts')}\n/elsewhere/b.ts\nrel/c.ts`) }) @@ -565,7 +597,7 @@ describe('glob results', () => { 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') - expect(result.value).toEqual({ paths: ['a.ts', 'b.ts', 'c.ts', 'd.ts'] }) + expect(result.value).toEqual({ root: '.', paths: ['a.ts', 'b.ts', 'c.ts', 'd.ts'] }) expect(text(result)).toBe('a.ts\nb.ts\n\n(Showing 2 of 4 paths. Full sorted result stored at: /spill/glob-results.txt. Use the fake retrieval hint.)') expect(spill?.saves).toHaveLength(1) expect(spill?.saves[0]).toMatchObject({ @@ -587,11 +619,37 @@ describe('glob results', () => { 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 ' - + 'instead of taken in modification-time order. Use the list tool to see what a directory contains. ' + + '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.)') }) - it('drops the list hint when the sample does reach every top-level entry', async () => { + 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([ + 'workspace/vendor/a.ts', + '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') + expect(text(result)).toContain('sampled across 3 of the 3 top-level entries') + }) + + it('samples relative to an absolute search root after workdir display conversion', async () => { + const { ctx, bash } = await setup({ config: { globMaxResults: 3 } }) + bash.handler = () => runResult([ + '/w/workspace/vendor/a.ts', + '/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') + 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, bash } = await setup({ config: { globMaxResults: 3 } }) bash.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') }))) @@ -608,7 +666,7 @@ describe('glob results', () => { .toBe('vendor/a.ts\nvendor/b.ts\nsrc/c.ts') }) - it('keeps the plain footer for a flat result, where the sample IS the recency head', async () => { + 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') expect(text(await call(ctx, 'glob', { pattern: '*' }, { agent: agent('/w') }))) @@ -627,14 +685,14 @@ describe('glob results', () => { const { ctx, bash, spill } = await setup({ config: { globMaxResults: 1 }, spill: true }) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, - value: { paths: ['replacement-a.ts', 'replacement-b.ts'] }, + value: { root: '.', paths: ['replacement-a.ts', 'replacement-b.ts'] }, })) bash.handler = () => runResult('old-a.ts\nold-b.ts\n') const result = await call(ctx, 'glob', { pattern: '*.ts' }, { agent: agent('/w') }) if (result.isError) throw new Error('expected glob replacement success') - expect(result.value).toEqual({ paths: ['replacement-a.ts', 'replacement-b.ts'] }) + expect(result.value).toEqual({ root: '.', paths: ['replacement-a.ts', 'replacement-b.ts'] }) expect(text(result)).toContain('replacement-a.ts') expect(text(result)).not.toContain('old-a.ts') expect(spill?.saves).toHaveLength(0) @@ -648,7 +706,7 @@ describe('glob results', () => { parent: Symbol('run_code') as ToolExecutionToken, }) if (result.isError) throw new Error('expected glob success') - expect(result.value).toEqual({ paths: ['a.ts', 'b.ts', 'c.ts', 'd.ts'] }) + expect(result.value).toEqual({ root: '.', paths: ['a.ts', 'b.ts', 'c.ts', 'd.ts'] }) expect(text(result)).toBe('a.ts\nb.ts\n\n(Showing 2 of 4 paths. The complete result could not be saved; narrow pattern or path to see more.)') expect(spill?.saves).toHaveLength(0) }) diff --git a/packages/fs/tool-fs/README.i18n.yaml b/packages/fs/tool-fs/README.i18n.yaml index e6f4ccf9c0..687b72d93e 100644 --- a/packages/fs/tool-fs/README.i18n.yaml +++ b/packages/fs/tool-fs/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/README.md -README.md: 08a4f74b928a38b92fdce5f6a03dd7c6c8f0af7c -README.zh.md: cdb45a12eb644e4882f7b92ac77b5bc7fc33f906 +README.md: 3917356b0e4cf48708f2769a6387249f795115ca +README.zh.md: b1ea0b42ed146241ee35d628825e0152c1bc1669 diff --git a/packages/fs/tool-fs/README.md b/packages/fs/tool-fs/README.md index 08a4f74b92..3917356b0e 100644 --- a/packages/fs/tool-fs/README.md +++ b/packages/fs/tool-fs/README.md @@ -19,7 +19,7 @@ All keys are optional; the defaults are the shipped listing and read caps. | Key | Default | Meaning | |---|---|---| -| `listMaxEntries` | `200` | Entries one `list` call renders inline; the footer still reports the complete directory's size and composition. | +| `listMaxEntries` | `200` | Maximum entries one `list` page returns; the footer reports complete size and composition plus a next offset when more remain. | | `readLimit` | `2000` | Default and maximum lines returned by one `read` call (the tool schema advertises it as the `limit` default). | | `readMaxLineLength` | `2000` | Characters kept per line before truncation (the suffix names the cap). | | `readMaxBytes` | `51200` | Byte cap on one `read` call's selected lines; overflow ends the window with a "capped" footer. | @@ -29,14 +29,14 @@ All keys are optional; the defaults are the shipped listing and read caps. | Tool | Arguments | Behavior | |---|---|---| -| `list` | `path?` | Direct children of one directory with their type, defaulting to the session workspace. Ordered directories first, then files, then non-regular children, each alphabetical, and capped at the configured `listMaxEntries` (200). | +| `list` | `path?`, `offset?` | One page of direct children with their type, defaulting to the session workspace and entry 1. Ordered directories first, then files, then non-regular children, each alphabetical; when more remain, continue from the footer's next offset. | | `read` | `file_path`, `offset?`, `limit?` | Line-numbered UTF-8 content with a pagination footer. `offset` is 1-based; `limit` defaults to and caps at the configured `readLimit` (2000). | | `write` | `file_path`, `content` | Create or fully replace a file. With the policy plugin: overwriting an existing file requires a prior `read` at the unchanged version; creating a new file does not. Without it: unconditional. | | `edit` | `file_path`, non-empty `old_string`, `new_string`, `replace_all?` | Literal replacement; unique match required unless `replace_all` is true. With the policy plugin: requires a prior `read` (any window) and the file unchanged since. Without it: unconditional. | Field names are snake_case to match Claude Code and existing harness tool schemas. -Canonical successes are `list` → `{ path, entries: [{ name, type: 'file' | 'directory' | 'other' }] }`, `read` → `{ path, offset, lines: [{ number, text }], totalLines }`, `write` → `{ path, operation: 'create' | 'update', before: string | null, after }`, and `edit` → `{ path, before, after }`. Native renderers preserve the line-numbered read and mutation acknowledgements below. Write/edit derive replayable diff-card metadata from these values; the values themselves are execution-local and are not added to `tool/result`. +Canonical successes are `list` → `{ path, offset, entries: [{ name, type }], totalEntries, counts: { directories, files, other } }`, `read` → `{ path, offset, lines: [{ number, text }], totalLines }`, `write` → `{ path, operation: 'create' | 'update', before: string | null, after }`, and `edit` → `{ path, before, after }`. `list.entries` is one bounded page; `type` is `file`, `directory`, or `other`, while its totals describe the complete directory. Native renderers preserve the listing/read envelopes and mutation acknowledgements below. Write/edit derive replayable diff-card metadata from these values; the values themselves are execution-local and are not added to `tool/result`. ## The tool is the executor; policy is an event gate @@ -68,7 +68,7 @@ Every request in this plugin's registration scope receives the independently reg ##### List guidance ```markdown -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. ``` ##### Read guidance @@ -115,11 +115,11 @@ Prefix-stable while the visible tool definitions and order are unchanged. Regist #### What the model sees -A successful listing is exactly ``, newline, `directory`, newline, ``, one line per entry, a blank line, one footer, and ``. A directory entry carries a trailing `/` and a non-regular child a trailing `@`; a regular file carries neither. The footer is exactly `(Empty directory)`, `( entries: directories, files)` — with `, other` appended only when such a child exists, and singulars where the count is one — or, when the view is capped, `(Showing of entries: directories, files. Entries are directories first, then files, each alphabetical; list a subdirectory to see the rest.)`. The complete count and composition are stated whether or not the view was capped, so a partial listing can never read as a whole directory. +A successful listing is ``, newline, `directory`, newline, ``, one line per page entry, a blank line, one footer, and ``. Each entry name is a JSON string with `<`, `>`, and `&` additionally Unicode-escaped so filesystem text cannot forge the envelope; a directory carries a trailing `/`, a non-regular child a trailing `@`, and a regular file neither. The footer is `(Empty directory)`, `( entries: directories, files)` with optional `, other`, or `(Showing entries - of : . Use offset= to continue.)`; the final page omits the continuation sentence. Every page states the complete count and composition. #### Token effect -Listing output is capped by `listMaxEntries`; the retained call and result are resent until compaction. +Listing output and its canonical `entries` page are capped by `listMaxEntries`; the retained call and result are resent until compaction. #### KV Cache effect @@ -157,7 +157,7 @@ Append-only; newly visible content follows the reusable request prefix and does #### What the model sees -Failures are normalized as `Error: `. This package's stable validation and read messages are `file_path must be a non-empty string`, `path must be a non-empty string when given`, `limit must be less than or equal to `, `old_string must be a non-empty string`, `old_string and new_string must differ`, `cannot read "": not found`, `cannot read "": not a regular file`, and `offset is out of range for "" ( lines)`; provider and policy templates are quoted in their package READMEs. +Failures are normalized as `Error: `. This package's stable validation and read messages are `file_path must be a non-empty string`, `path must be a non-empty string when given`, `offset must be a positive integer`, `limit must be less than or equal to `, `old_string must be a non-empty string`, `old_string and new_string must differ`, `cannot read "": not found`, `cannot read "": not a regular file`, `offset is out of range for "" ( entries)`, and the corresponding ` lines` read error; provider and policy templates are quoted in their package READMEs. #### Token effect @@ -169,6 +169,6 @@ Append-only; newly visible content follows the reusable request prefix and does ## Known Limitations and Deferred Work -- **`list` reads one directory level and has no spill path** — recursion, pagination, and per-directory child counts are absent, and a listing past `listMaxEntries` is summarized by its footer rather than saved anywhere retrievable; the model lists a subdirectory instead. +- **`list` reads one directory level** — recursion and per-directory child counts are absent; offset pagination traverses only the current directory's ordered direct children. - **`read` handles UTF-8 text files only** — binary-safe reads and PDF/image/multimodal content are deferred; a directory target is `FS_NOT_REGULAR_FILE`. -- **No timeout surface** — `read`/`write`/`edit` take no timeout argument and declare no `timeout-policy` budget; cancellation rides `exec.signal` only (the deliberate [fs-family stance](../README.md)). +- **No timeout surface** — `list`/`read`/`write`/`edit` take no timeout argument and declare no `timeout-policy` budget; cancellation rides `exec.signal` only (the deliberate [fs-family stance](../README.md)). diff --git a/packages/fs/tool-fs/README.zh.md b/packages/fs/tool-fs/README.zh.md index cdb45a12eb..b1ea0b42ed 100644 --- a/packages/fs/tool-fs/README.zh.md +++ b/packages/fs/tool-fs/README.zh.md @@ -19,7 +19,7 @@ await ctx.plugin(ToolFs) // this package — re | 键 | 默认值 | 含义 | |---|---|---| -| `listMaxEntries` | `200` | 一次 `list` 调用内联渲染的条目数；footer 仍会报告整个目录的规模与构成。 | +| `listMaxEntries` | `200` | 单个 `list` 页面返回的最大条目数；footer 会报告完整规模与构成，并在仍有条目时给出下一 offset。 | | `readLimit` | `2000` | 一次 `read` 调用返回的默认和最大行数（工具 schema 将其声明为 `limit` 默认值）。 | | `readMaxLineLength` | `2000` | 每行截断前保留的字符数（后缀会说明上限）。 | | `readMaxBytes` | `51200` | 一次 `read` 调用所选行的字节上限；溢出时以「已达上限」footer 结束窗口。 | @@ -29,14 +29,14 @@ await ctx.plugin(ToolFs) // this package — re | 工具 | 参数 | 行为 | |---|---|---| -| `list` | `path?` | 单个目录的直接子项及其类型，默认取会话工作区。顺序为先目录、再文件、最后非常规子项，各组内按字母序排列，并受配置的 `listMaxEntries`（200）限制。 | +| `list` | `path?`、`offset?` | 单个目录的一页直接子项及其类型，默认取会话工作区并从第 1 个条目开始。顺序为先目录、再文件、最后非常规子项，各组内按字母序排列；仍有条目时按 footer 给出的下一 offset 继续。 | | `read` | `file_path`、`offset?`、`limit?` | 带行号的 UTF-8 内容和分页 footer。`offset` 从 1 开始；`limit` 默认为配置的 `readLimit`（2000），上限也为该值。 | | `write` | `file_path`、`content` | 创建文件或完整替换文件。有政策插件时：覆盖现有文件要求先在未变版本上执行 `read`；创建新文件不需要。没有插件时：无条件执行。 | | `edit` | `file_path`、非空 `old_string`、`new_string`、`replace_all?` | 字面量替换；除非 `replace_all` 为 true，否则要求唯一匹配。有政策插件时：要求先执行 `read`（任何窗口），且文件此后未变。没有插件时：无条件执行。 | 字段名使用 snake_case，与 Claude Code 和现有 harness 工具 schema 一致。 -规范成功值分别为：`list` → `{ path, entries: [{ name, type: 'file' | 'directory' | 'other' }] }`，`read` → `{ path, offset, lines: [{ number, text }], totalLines }`，`write` → `{ path, operation: 'create' | 'update', before: string | null, after }`，`edit` → `{ path, before, after }`。Native 渲染器会保留下方带行号的读取结果和变更确认。写入/编辑从这些值派生可回放的 diff 卡片元数据；值本身仅用于执行，不会添加到 `tool/result`。 +规范成功值分别为：`list` → `{ path, offset, entries: [{ name, type }], totalEntries, counts: { directories, files, other } }`，`read` → `{ path, offset, lines: [{ number, text }], totalLines }`，`write` → `{ path, operation: 'create' | 'update', before: string | null, after }`，`edit` → `{ path, before, after }`。`list.entries` 是一个有界页面；`type` 为 `file`、`directory` 或 `other`，而总计信息描述的是完整目录。Native 渲染器会保留下方的列出/读取包络和变更确认。写入/编辑从这些值派生可回放的 diff 卡片元数据；值本身仅用于执行，不会添加到 `tool/result`。 ## 工具就是执行器；政策是事件门禁 @@ -68,7 +68,7 @@ await ctx.plugin(ToolFs) // this package — re ##### List 指导 ```markdown -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. Reach for glob or grep once you know the path pattern or the text you are looking for. +Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. ``` ##### Read 指导 @@ -115,11 +115,11 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces #### 模型看到的内容 -成功列出结果精确为 ``、换行、`directory`、换行、``、每个条目一行、一个空行、一条 footer 和 ``。目录条目带尾部 `/`，非常规子项带尾部 `@`，常规文件两者都不带。footer 精确为 `(Empty directory)`、`( entries: directories, files)`（仅当存在此类子项时才追加 `, other`，计数为一时使用单数形式），或在视图被截断时为 `(Showing of entries: directories, files. Entries are directories first, then files, each alphabetical; list a subdirectory to see the rest.)`。无论视图是否被截断，都会说明完整计数与构成，因此部分列出结果绝不会被读成整个目录。 +成功列出结果为 ``、换行、`directory`、换行、``、页面中的每个条目一行、一个空行、一条 footer 和 ``。每个条目名都是 JSON 字符串，并额外对 `<`、`>` 和 `&` 做 Unicode 转义，使文件系统文本无法伪造包络；目录带尾部 `/`，非常规子项带尾部 `@`，常规文件两者都不带。footer 为 `(Empty directory)`、`( entries: directories, files)`（可选追加 `, other`），或 `(Showing entries - of : . Use offset= to continue.)`；最后一页省略继续提示。每一页都会说明完整计数与构成。 #### Token 影响 -列出输出受 `listMaxEntries` 限制；保留的调用与结果会反复发送，直到上下文压缩。 +列出输出及其规范 `entries` 页面受 `listMaxEntries` 限制；保留的调用与结果会反复发送，直到上下文压缩。 #### KV Cache 影响 @@ -157,7 +157,7 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces #### 模型看到的内容 -失败会规范化为 `Error: `。本包稳定的校验和读取消息是 `file_path must be a non-empty string`、`path must be a non-empty string when given`、`limit must be less than or equal to `、`old_string must be a non-empty string`、`old_string and new_string must differ`、`cannot read "": not found`、`cannot read "": not a regular file` 和 `offset is out of range for "" ( lines)`；提供方和政策模板在各自包的 README 中逐字列出。 +失败会规范化为 `Error: `。本包稳定的校验和读取消息是 `file_path must be a non-empty string`、`path must be a non-empty string when given`、`offset must be a positive integer`、`limit must be less than or equal to `、`old_string must be a non-empty string`、`old_string and new_string must differ`、`cannot read "": not found`、`cannot read "": not a regular file`、`offset is out of range for "" ( entries)`，以及对应的 ` lines` 读取错误；提供方和政策模板在各自包的 README 中逐字列出。 #### Token 影响 @@ -169,6 +169,6 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces ## 已知限制与延期工作 -- **`list` 只读取一层目录，且没有溢出落盘路径**：不提供递归、分页和逐目录子项计数，超出 `listMaxEntries` 的部分只由 footer 概括，不会保存到任何可取回的位置；模型改为列出对应子目录。 +- **`list` 只读取一层目录**：不提供递归和逐目录子项计数；offset 分页只遍历当前目录中按顺序排列的直接子项。 - **`read` 只处理 UTF-8 文本文件**：二进制安全读取和 PDF/图像/多模态内容均延期处理；目录目标为 `FS_NOT_REGULAR_FILE`。 -- **没有超时接口**：`read`/`write`/`edit` 不接受超时参数，也不声明 `timeout-policy` 预算；取消只通过 `exec.signal` 传递（见有意采用的 [fs 能力族立场](../README.md)）。 +- **没有超时接口**：`list`/`read`/`write`/`edit` 不接受超时参数，也不声明 `timeout-policy` 预算；取消只通过 `exec.signal` 传递（见有意采用的 [fs 能力族立场](../README.md)）。 diff --git a/packages/fs/tool-fs/src/index.ts b/packages/fs/tool-fs/src/index.ts index c8376ed123..7890d5084d 100644 --- a/packages/fs/tool-fs/src/index.ts +++ b/packages/fs/tool-fs/src/index.ts @@ -25,7 +25,7 @@ export const inject = ['tools', 'fs', 'systemPrompt'] /** Plugin config (all optional — `Config` supplies the defaults). */ export interface Config { - /** Maximum entries one `list` call renders inline; the footer still reports the complete count. */ + /** Maximum entries one `list` page returns; the footer still reports the complete count. */ listMaxEntries?: number /** Default and maximum number of lines returned by one `read` call. */ readLimit?: number diff --git a/packages/fs/tool-fs/src/list-render.ts b/packages/fs/tool-fs/src/list-render.ts index d7a65cbb27..eef3392ec0 100644 --- a/packages/fs/tool-fs/src/list-render.ts +++ b/packages/fs/tool-fs/src/list-render.ts @@ -1,80 +1,111 @@ /** - * Pure listing presentation: order one directory's direct children so a capped - * view still shows the navigable structure, and render the model-facing - * envelope. Cordis-free and independently unit-tested, mirroring - * {@link module:@deepseek-ai/dsh-tool-fs/read-render}. + * Pure directory-listing presentation: order direct children, count complete + * composition, and render a bounded page without allowing filesystem text to + * forge the result envelope. * @module @deepseek-ai/dsh-tool-fs/list-render */ -/** Default and maximum number of entries one `list` call renders inline (the `listMaxEntries` config). */ +/** Default and maximum number of entries one `list` call returns (the `listMaxEntries` config). */ export const LIST_MAX_ENTRIES = 200 -/** One direct child in a rendered listing — the canonical entry shape the tool returns. */ +/** One direct child in a directory listing. */ export interface ListedEntry { /** Basename of the child inside the listed directory. */ name: string - /** Whether the child is a regular file, a directory, or something else (symlink, socket, device). */ + /** Whether the child is a regular file, a directory, or something else. */ type: 'file' | 'directory' | 'other' } +/** Complete-listing composition retained on every page. */ +export interface ListCounts { + directories: number + files: number + other: number +} + +/** Canonical bounded result returned by one `list` call. */ +export interface ListPage { + /** Backend display path of the listed directory. */ + path: string + /** 1-based index of the first returned entry. */ + offset: number + /** Current page in directory-first, name-sorted order. */ + entries: ListedEntry[] + /** Number of direct children in the complete listing. */ + totalEntries: number + /** Composition of the complete listing, not only this page. */ + counts: ListCounts +} + /** - * Order direct children so truncation cannot hide the directory tree: - * directories first, then files, then everything else, each group by name. - * - * The provider seam returns children in stable name order, which puts a - * subdirectory wherever the alphabet puts it; capping such a list can drop every - * subdirectory and leave the model believing a directory holds only files. This - * is the listing counterpart of the `glob` coverage footer. - * - * @param entries - the seam's direct children, in any order. - * @returns a new array in directory-first display order; the input is not mutated. + * Sort directories before files before other entries, each group by name. + * @param entries - direct children in provider order. + * @returns a new directory-first array without mutating `entries`. */ export function orderEntries(entries: readonly T[]): T[] { const rank = { directory: 0, file: 1, other: 2 } return [...entries].sort((a, b) => rank[a.type] - rank[b.type] || a.name.localeCompare(b.name)) } -/** `1 directory` / `4 directories` — a count the model reads as prose, not as `1 directorie(s)`. */ +/** + * Count every entry type in a complete listing. + * @param entries - every direct child in the listed directory. + * @returns the complete directory/file/other composition. + */ +export function countEntries(entries: readonly ListedEntry[]): ListCounts { + const counts: ListCounts = { directories: 0, files: 0, other: 0 } + for (const entry of entries) { + if (entry.type === 'directory') counts.directories += 1 + else if (entry.type === 'file') counts.files += 1 + else counts.other += 1 + } + return counts +} + +/** `1 directory` / `4 directories`. */ function count(n: number, singular: string, plural: string): string { return `${n} ${n === 1 ? singular : plural}` } -/** The ` directories, files[, other]` breakdown; the `other` clause appears only when non-empty. */ -function breakdown(entries: readonly ListedEntry[]): string { - const directories = entries.filter(entry => entry.type === 'directory').length - const other = entries.filter(entry => entry.type === 'other').length - const files = entries.length - directories - other - const parts = [count(directories, 'directory', 'directories'), count(files, 'file', 'files')] - if (other > 0) parts.push(`${other} other`) +/** Complete-listing composition as model-facing prose. */ +function breakdown(counts: ListCounts): string { + const parts = [ + count(counts.directories, 'directory', 'directories'), + count(counts.files, 'file', 'files'), + ] + if (counts.other > 0) parts.push(`${counts.other} other`) return parts.join(', ') } +/** JSON-string encode untrusted filesystem text and neutralize envelope tags. */ +function encodeFilesystemText(value: string): string { + return JSON.stringify(value) + .replaceAll('<', '\\u003c') + .replaceAll('>', '\\u003e') + .replaceAll('&', '\\u0026') +} + /** - * Render the model-facing `list` result: the displayed entries, then a footer - * that always states the COMPLETE listing's size and composition, so a capped - * view can never read as the whole directory. + * Render one bounded listing page. Entry names are JSON strings followed by `/` + * for directories or `@` for non-regular children; regular files have no suffix. + * The footer carries complete composition and an exact continuation offset. * - * Directories carry a trailing `/` and non-regular children a trailing `@`, so - * the model can tell what it may descend into without a second call. - * - * @param displayPath - the resolved directory as the backend displays it. - * @param entries - the complete listing, already in {@link orderEntries} order. - * @param maxEntries - how many entries to show inline; the rest are summarized by the footer. - * @returns the model-facing text. + * @param page - the canonical listing page. + * @returns the model-facing directory envelope. */ -export function formatListOutput(displayPath: string, entries: readonly ListedEntry[], maxEntries: number): string { - const shown = entries.slice(0, maxEntries) +export function formatListOutput(page: ListPage): string { const suffix = { directory: '/', file: '', other: '@' } - const footer = shown.length < entries.length - ? `(Showing ${shown.length} of ${count(entries.length, 'entry', 'entries')}: ${breakdown(entries)}. ` - + 'Entries are directories first, then files, each alphabetical; list a subdirectory to see the rest.)' - : entries.length === 0 - ? '(Empty directory)' - : `(${count(entries.length, 'entry', 'entries')}: ${breakdown(entries)})` - const body = shown.length > 0 - ? `${shown.map(entry => `${entry.name}${suffix[entry.type]}`).join('\n')}\n\n${footer}` + const end = page.entries.length === 0 ? 0 : page.offset + page.entries.length - 1 + const footer = page.totalEntries === 0 + ? '(Empty directory)' + : page.offset > 1 || page.entries.length < page.totalEntries + ? `(Showing entries ${page.offset}-${end} of ${page.totalEntries}: ${breakdown(page.counts)}.` + + (end < page.totalEntries ? ` Use offset=${end + 1} to continue.)` : ')') + : `(${count(page.totalEntries, 'entry', 'entries')}: ${breakdown(page.counts)})` + const body = page.entries.length > 0 + ? `${page.entries.map(entry => `${encodeFilesystemText(entry.name)}${suffix[entry.type]}`).join('\n')}\n\n${footer}` : footer - return `${displayPath} + return `${encodeFilesystemText(page.path)} directory ${body} diff --git a/packages/fs/tool-fs/src/list.ts b/packages/fs/tool-fs/src/list.ts index de6c6d1ddd..270e2803b8 100644 --- a/packages/fs/tool-fs/src/list.ts +++ b/packages/fs/tool-fs/src/list.ts @@ -13,14 +13,15 @@ import type { Context } from 'cordis' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView } from '@deepseek-ai/dsh-tools' +import { FsError } from '@deepseek-ai/dsh-fs' import type {} from '@deepseek-ai/dsh-fs' import type {} from '@deepseek-ai/dsh-system-prompt' -import { formatListOutput, orderEntries } from './list-render.ts' +import { countEntries, formatListOutput, orderEntries } from './list-render.ts' import { sessionResolveOptions } from './session-cwd.ts' /** Resolved list-tool caps — plugin config after defaulting (see `Config` in index.ts). */ export interface ListToolCaps { - /** Maximum entries rendered inline; the footer still reports the complete listing's size. */ + /** Maximum entries returned on one page; the footer still reports complete size and composition. */ maxEntries: number } @@ -28,6 +29,8 @@ export interface ListToolCaps { export interface ListInput { /** Directory to list; `.` means the calling agent's session workspace. */ path: string + /** 1-based first entry to return from the directory-first ordering. */ + offset: number } /** @@ -36,23 +39,26 @@ export interface ListInput { * needs no argument at all. * * @param args - the schema-validated `list` arguments. - * @returns the accepted input with `path` defaulted. + * @returns the accepted input with `path` and `offset` defaulted. */ -export function parseListArgs(args: { path?: string }): ListInput { +export function parseListArgs(args: { path?: string; offset?: number }): ListInput { if (args.path !== undefined && args.path.trim().length === 0) throw new Error('path must be a non-empty string when given') - return { path: args.path ?? '.' } + const offset = args.offset ?? 1 + if (!Number.isInteger(offset) || offset < 1) throw new Error('offset must be a positive integer') + return { path: args.path ?? '.', offset } } /** * Pending-call presentation: a generic card titled by the directory, with a * follow-along location so a capable editor can reveal it. * - * @param args - the raw tool arguments; only `path` is read. + * @param args - the raw tool arguments; `path` and `offset` feed the title. * @returns the generic card view shown while the call runs. */ -export function presentListCall(args: { path?: string }): GenericCallView { +export function presentListCall(args: { path?: string; offset?: number }): GenericCallView { const path = args.path ?? '.' - return { card: 'generic', title: `List ${path}`, kind: 'read', locations: [{ path }] } + const window = args.offset !== undefined ? ` (from entry ${args.offset})` : '' + return { card: 'generic', title: `List ${path}${window}`, kind: 'read', locations: [{ path }] } } /** @@ -67,16 +73,17 @@ export function applyListTool(ctx: Context, caps: ListToolCaps): void { order: 99, text: 'Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, ' + 'and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. ' - + 'Reach for glob or grep once you know the path pattern or the text you are looking for.', + + 'When a result is capped, continue with the offset named in its footer.', }) ctx.tools.register(defineTool({ name: 'list', description: 'List the direct children of one directory, with their type. ' - + `Entries are directories first, then files, each alphabetical; the first ${caps.maxEntries} are returned inline and the footer reports the complete count. ` - + 'Unlike glob, this shows subdirectories, so it is how to see what a directory contains.', + + `Entries are directories first, then files, each alphabetical; up to ${caps.maxEntries} are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. ` + + 'It includes subdirectories and is the tool for seeing one directory\'s contents.', parameters: { path: { type: 'string', description: 'Directory to list. Defaults to the session workspace; a relative path resolves against it.' }, + offset: { type: 'number', description: '1-based first entry to return. Defaults to 1; use the footer value to continue.' }, }, output: { schema: { @@ -84,6 +91,7 @@ export function applyListTool(ctx: Context, caps: ListToolCaps): void { additionalProperties: false, properties: { path: { type: 'string', required: true }, + offset: { type: 'integer', required: true }, entries: { type: 'array', required: true, @@ -96,9 +104,20 @@ export function applyListTool(ctx: Context, caps: ListToolCaps): void { }, }, }, + totalEntries: { type: 'integer', required: true }, + counts: { + type: 'object', + required: true, + additionalProperties: false, + properties: { + directories: { type: 'integer', required: true }, + files: { type: 'integer', required: true }, + other: { type: 'integer', required: true }, + }, + }, }, }, - render: (_args, value) => [{ type: 'text', text: formatListOutput(value.path, value.entries, caps.maxEntries) }], + render: (_args, value) => [{ type: 'text', text: formatListOutput(value) }], }, // Listing reads directory metadata only: no content, no version recorded, // nothing a concurrent call could observe out of order. @@ -109,10 +128,21 @@ export function applyListTool(ctx: Context, caps: ListToolCaps): void { // No stat first: the seam already answers absence with FS_NOT_FOUND and a // non-directory target with FS_NOT_DIRECTORY, so a probe would only add a // round-trip and a second source of truth. (0 stat.) - const entries = await ctx.fs.listDir(target, exec.signal) + const entries = orderEntries(await ctx.fs.listDir(target, exec.signal)) + if (input.offset > entries.length && !(entries.length === 0 && input.offset === 1)) { + throw new FsError( + `offset ${input.offset} is out of range for "${target.displayPath}" (${entries.length} entries)`, + 'FS_NOT_FOUND', + ) + } return { path: target.displayPath, - entries: orderEntries(entries).map(({ name, type }) => ({ name, type })), + offset: input.offset, + entries: entries + .slice(input.offset - 1, input.offset - 1 + caps.maxEntries) + .map(({ name, type }) => ({ name, type })), + totalEntries: entries.length, + counts: countEntries(entries), } }, presentCall: presentListCall, diff --git a/packages/fs/tool-fs/tests/list-render.spec.ts b/packages/fs/tool-fs/tests/list-render.spec.ts index 3d0a3ac5ce..2c26c1be2c 100644 --- a/packages/fs/tool-fs/tests/list-render.spec.ts +++ b/packages/fs/tool-fs/tests/list-render.spec.ts @@ -4,11 +4,22 @@ */ import { describe, expect, it } from 'vitest' -import { formatListOutput, orderEntries } from '../src/list-render.ts' -import type { ListedEntry } from '../src/list-render.ts' +import { countEntries, formatListOutput, orderEntries } from '../src/list-render.ts' +import type { ListedEntry, ListPage } from '../src/list-render.ts' const entry = (name: string, type: ListedEntry['type'] = 'file'): ListedEntry => ({ name, type }) +function page(entries: ListedEntry[], options: { offset?: number; totalEntries?: number; all?: ListedEntry[] } = {}): ListPage { + const all = options.all ?? entries + return { + path: '/w', + offset: options.offset ?? 1, + entries, + totalEntries: options.totalEntries ?? all.length, + counts: countEntries(all), + } +} + describe('orderEntries', () => { it('groups directories, then files, then other, each by name', () => { const ordered = orderEntries([ @@ -31,36 +42,35 @@ describe('orderEntries', () => { describe('formatListOutput', () => { it('marks directories and non-regular children, and counts the whole listing', () => { - expect(formatListOutput('/w', [entry('src', 'directory'), entry('a.txt'), entry('sock', 'other')], 10)).toBe(`/w + expect(formatListOutput(page([entry('src', 'directory'), entry('a.txt'), entry('sock', 'other')]))).toBe(`"/w" directory -src/ -a.txt -sock@ +"src"/ +"a.txt" +"sock"@ (3 entries: 1 directory, 1 file, 1 other) `) }) it('omits the "other" clause when every child is a file or a directory', () => { - expect(formatListOutput('/w', [entry('a.txt'), entry('b.txt')], 10)).toContain('(2 entries: 0 directories, 2 files)') + expect(formatListOutput(page([entry('a.txt'), entry('b.txt')]))).toContain('(2 entries: 0 directories, 2 files)') }) it('says a one-entry listing in the singular', () => { - expect(formatListOutput('/w', [entry('only', 'directory')], 10)).toContain('(1 entry: 1 directory, 0 files)') + expect(formatListOutput(page([entry('only', 'directory')]))).toContain('(1 entry: 1 directory, 0 files)') }) it('states the complete size and composition when the view is capped', () => { const entries = [entry('src', 'directory'), ...Array.from({ length: 5 }, (_, i) => entry(`f${i}.txt`))] - const rendered = formatListOutput('/w', entries, 2) - expect(rendered).toContain('src/\nf0.txt\n') + const rendered = formatListOutput(page(entries.slice(0, 2), { totalEntries: entries.length, all: entries })) + expect(rendered).toContain('"src"/\n"f0.txt"\n') expect(rendered).not.toContain('f2.txt') - expect(rendered).toContain('(Showing 2 of 6 entries: 1 directory, 5 files. ' - + 'Entries are directories first, then files, each alphabetical; list a subdirectory to see the rest.)') + expect(rendered).toContain('(Showing entries 1-2 of 6: 1 directory, 5 files. Use offset=3 to continue.)') }) it('renders an empty directory as a footer alone', () => { - expect(formatListOutput('/w', [], 10)).toBe(`/w + expect(formatListOutput(page([]))).toBe(`"/w" directory (Empty directory) diff --git a/packages/fs/tool-fs/tests/tools.spec.ts b/packages/fs/tool-fs/tests/tools.spec.ts index 66f88a6348..74268b72ca 100644 --- a/packages/fs/tool-fs/tests/tools.spec.ts +++ b/packages/fs/tool-fs/tests/tools.spec.ts @@ -162,6 +162,7 @@ describe('registration', () => { const { ctx } = await setup() const prompt = renderPrompt(await ctx.systemPrompt.assemble()) expect(prompt).toContain('Use the list tool') + expect(prompt).not.toContain('glob or grep') expect(prompt).toContain('Use the read tool') expect(prompt).toContain('Use the write tool') expect(prompt).toContain('Use the edit tool') @@ -220,20 +221,23 @@ describe('list tool', () => { // model see the same ordering contract. expect(result.value).toEqual({ path: '/abs/.', + offset: 1, entries: [ { name: 'archive', type: 'directory' }, { name: 'zeroomega-3.3.23', type: 'directory' }, { name: 'notes.md', type: 'file' }, { name: 'link-to-nowhere', type: 'other' }, ], + totalEntries: 4, + counts: { directories: 2, files: 1, other: 1 }, }) - expect(text(result)).toBe(`/abs/. + expect(text(result)).toBe(`"/abs/." directory -archive/ -zeroomega-3.3.23/ -notes.md -link-to-nowhere@ +"archive"/ +"zeroomega-3.3.23"/ +"notes.md" +"link-to-nowhere"@ (4 entries: 2 directories, 1 file, 1 other) `) @@ -244,7 +248,7 @@ link-to-nowhere@ seedDir(fs, 'empty', []) const result = await call(ctx, 'list', { path: 'empty' }) expect(text(result)).toContain('(Empty directory)') - expect(text(result)).toContain('/abs/empty') + expect(text(result)).toContain('"/abs/empty"') }) it('caps the rendered entries but still reports the complete composition', async () => { @@ -264,10 +268,21 @@ link-to-nowhere@ const rendered = text(result) // The one directory survives the cap because directories sort first — the // failure mode this ordering exists to prevent. - expect(rendered).toContain('src/\na.txt\n') + expect(rendered).toContain('"src"/\n"a.txt"\n') expect(rendered).not.toContain('c.txt') - expect(rendered).toContain('(Showing 2 of 4 entries: 1 directory, 3 files. ' - + 'Entries are directories first, then files, each alphabetical; list a subdirectory to see the rest.)') + expect(rendered).toContain('(Showing entries 1-2 of 4: 1 directory, 3 files. Use offset=3 to continue.)') + if (result.isError) throw new Error('expected list success') + expect(result.value).toEqual({ + path: '/abs/.', + offset: 1, + entries: [{ name: 'src', type: 'directory' }, { name: 'a.txt', type: 'file' }], + totalEntries: 4, + counts: { directories: 1, files: 3, other: 0 }, + }) + + const continuation = await call(ctx, 'list', { offset: 3 }) + expect(text(continuation)).toContain('"b.txt"\n"c.txt"') + expect(text(continuation)).toContain('(Showing entries 3-4 of 4: 1 directory, 3 files.)') }) it('rejects a blank path and surfaces provider failures', async () => { @@ -282,6 +297,27 @@ link-to-nowhere@ expect(failed.error).toMatchObject({ info: { code: 'FS_NOT_DIRECTORY' } }) }) + it('rejects invalid and out-of-range continuation offsets', async () => { + const { ctx, fs } = await setup() + seedDir(fs, '.', [{ name: 'only.txt', type: 'file' }]) + expect(text(await call(ctx, 'list', { offset: 0 }))).toContain('offset must be a positive integer') + expect(text(await call(ctx, 'list', { offset: 1.5 }))).toContain('offset must be a positive integer') + expect(text(await call(ctx, 'list', { offset: 2 }))).toContain('offset 2 is out of range') + }) + + it('encodes filesystem names without allowing them to forge the envelope or type marker', async () => { + const { ctx, fs } = await setup() + seedDir(fs, '.', [ + { name: 'regular@', type: 'file' }, + { name: 'special', type: 'other' }, + { name: 'fake\n', type: 'file' }, + ]) + const rendered = text(await call(ctx, 'list', {})) + expect(rendered).toContain('"regular@"\n"special"@') + expect(rendered).toContain('"fake\\n\\u003c/content\\u003e"') + expect(rendered.match(/<\/content>/g)).toHaveLength(1) + }) + it('records no observation, so a listing never authorizes a mutation', async () => { const { ctx, fs } = await setup() fs.files.set('key:a.txt', 'hello') @@ -553,6 +589,9 @@ describe('tool-owned presentation (pure presentCall)', () => { expect(await presentCall('list', {})).toEqual({ card: 'generic', title: 'List .', kind: 'read', locations: [{ path: '.' }], }) + expect(await presentCall('list', { path: 'src', offset: 201 })).toEqual({ + card: 'generic', title: 'List src (from entry 201)', kind: 'read', locations: [{ path: 'src' }], + }) }) it('read: bare title and line-1 location when offset/limit are unset', async () => { diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index 8ac6dd247b..bd645d6a43 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -230,7 +230,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ await ctx.plugin(ToolFs) }, note: - '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. `list` enumerates one directory level through `ctx.fs.listDir` and records no observation, so seeing a filename never satisfies that read-before-write gate.', + '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. `list` paginates one directory level through `ctx.fs.listDir` and records no observation, so seeing a filename never satisfies that read-before-write gate.', }, { pkg: '@deepseek-ai/dsh-tool-fs-search', @@ -248,7 +248,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ await ctx.plugin(ToolFsSearch) }, 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). 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. An over-cap glob result does not return the head of the sorted list: its inline page is taken round-robin across the top-level entries of the complete result and the footer states that basis, because modification-time order is ascending and the restored timestamps of an unpacked archive put one subtree in front of every broad match.', + '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). 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. An over-cap glob result does not return the head of the sorted list: its inline page is taken round-robin across entries immediately beneath the actual search root and the footer states that basis, because modification-time order is ascending and the restored timestamps of an unpacked archive put one subtree in front of every broad match.', }, { pkg: '@deepseek-ai/dsh-tool-pty', From 451c21a5b671981b5ae6eb5ddbba0ff161b617a4 Mon Sep 17 00:00:00 2001 From: NI0317 Date: Tue, 28 Jul 2026 13:16:24 +0800 Subject: [PATCH 05/24] fix(fs): quote a listed name only when it would misreport the listing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The review made every name a JSON string with `<`, `>`, and `&` escaped. The hazards behind that are real and each is now covered: a control character splits one entry across lines, `` until the final page, so omitted sibling names remain reachable. -- **Filesystem text cannot forge presentation structure.** The path and entry names render as JSON strings with envelope-significant characters escaped; directory `/` and non-regular `@` markers sit outside the quoted name, so a regular filename ending in `@` remains distinguishable. +- **Filesystem text cannot forge presentation structure.** A name is emitted verbatim unless it would make the listing lie — a control character splitting one entry across lines, ``，因此被省略的同级名称仍可取回。 -- **文件系统文本无法伪造展示结构。** 路径和条目名渲染为 JSON 字符串，并转义对包络有意义的字符；目录 `/` 与非常规子项 `@` 标记位于带引号名称之外，因此以 `@` 结尾的常规文件名仍可区分。 +- **文件系统文本无法伪造展示结构。** 条目名默认原样输出；只有当它会让列出结果失真时才转为 JSON 字符串并中和 `\"/var/folders/8k/kj35k1fd6t90n0czg7k3hv140000gn/T/acp-snap-cwd-QJ2ZC6\"\ndirectory\n\n\"docs\"/\n\"src\"/\n\"package.json\"\n\"README.txt\"\n\n(4 entries: 2 directories, 2 files)\n"}],"isError":false},"sourceEventSeqs":[49],"surfaceOp":"append"} +{"type":"tool/result","seq":50,"time":1785159115944,"data":{"turn":1,"step":1,"callId":"call_00_BSi06gcYvl6oad3I5qqG9244","content":[{"type":"text","text":"/var/folders/8k/kj35k1fd6t90n0czg7k3hv140000gn/T/acp-snap-cwd-QJ2ZC6\ndirectory\n\ndocs/\nsrc/\npackage.json\nREADME.txt\n\n(4 entries: 2 directories, 2 files)\n"}],"isError":false},"sourceEventSeqs":[49],"surfaceOp":"append"} {"type":"step/end","seq":51,"time":1785159115950,"data":{"turn":1,"step":1}} {"type":"step/start","seq":52,"time":1785159115951,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":53,"time":1785159116889,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/packages/fs/tool-fs/README.i18n.yaml b/packages/fs/tool-fs/README.i18n.yaml index 687b72d93e..3e7c989373 100644 --- a/packages/fs/tool-fs/README.i18n.yaml +++ b/packages/fs/tool-fs/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/README.md -README.md: 3917356b0e4cf48708f2769a6387249f795115ca -README.zh.md: b1ea0b42ed146241ee35d628825e0152c1bc1669 +README.md: 8fdd54fb36353ca6c1dbcf71cdad38c4bcf26b7d +README.zh.md: 567c8e0df58950369c59785859948e32cbccdef4 diff --git a/packages/fs/tool-fs/README.md b/packages/fs/tool-fs/README.md index 3917356b0e..8fdd54fb36 100644 --- a/packages/fs/tool-fs/README.md +++ b/packages/fs/tool-fs/README.md @@ -115,7 +115,7 @@ Prefix-stable while the visible tool definitions and order are unchanged. Regist #### What the model sees -A successful listing is ``, newline, `directory`, newline, ``, one line per page entry, a blank line, one footer, and ``. Each entry name is a JSON string with `<`, `>`, and `&` additionally Unicode-escaped so filesystem text cannot forge the envelope; a directory carries a trailing `/`, a non-regular child a trailing `@`, and a regular file neither. The footer is `(Empty directory)`, `( entries: directories, files)` with optional `, other`, or `(Showing entries - of : . Use offset= to continue.)`; the final page omits the continuation sentence. Every page states the complete count and composition. +A successful listing is ``, newline, `directory`, newline, ``, one line per page entry, a blank line, one footer, and ``. A directory carries a trailing `/`, a non-regular child a trailing `@`, and a regular file neither. A name is emitted verbatim unless it could make the listing say something untrue — a control character, a leading `"`, a backslash, ` entries: directories, files)` with optional `, other`, or `(Showing entries - of : . Use offset= to continue.)`; the final page omits the continuation sentence. Every page states the complete count and composition. #### Token effect diff --git a/packages/fs/tool-fs/README.zh.md b/packages/fs/tool-fs/README.zh.md index b1ea0b42ed..567c8e0df5 100644 --- a/packages/fs/tool-fs/README.zh.md +++ b/packages/fs/tool-fs/README.zh.md @@ -115,7 +115,7 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces #### 模型看到的内容 -成功列出结果为 ``、换行、`directory`、换行、``、页面中的每个条目一行、一个空行、一条 footer 和 ``。每个条目名都是 JSON 字符串，并额外对 `<`、`>` 和 `&` 做 Unicode 转义，使文件系统文本无法伪造包络；目录带尾部 `/`，非常规子项带尾部 `@`，常规文件两者都不带。footer 为 `(Empty directory)`、`( entries: directories, files)`（可选追加 `, other`），或 `(Showing entries - of : . Use offset= to continue.)`；最后一页省略继续提示。每一页都会说明完整计数与构成。 +成功列出结果为 ``、换行、`directory`、换行、``、页面中的每个条目一行、一个空行、一条 footer 和 ``。目录带尾部 `/`，非常规子项带尾部 `@`，常规文件两者都不带。条目名默认原样输出，只有当它可能让列出结果失真时才转为 JSON 字符串并中和 ` entries: directories, files)`（可选追加 `, other`），或 `(Showing entries - of : . Use offset= to continue.)`；最后一页省略继续提示。每一页都会说明完整计数与构成。 #### Token 影响 diff --git a/packages/fs/tool-fs/src/list-render.ts b/packages/fs/tool-fs/src/list-render.ts index eef3392ec0..86b57d02b3 100644 --- a/packages/fs/tool-fs/src/list-render.ts +++ b/packages/fs/tool-fs/src/list-render.ts @@ -77,17 +77,41 @@ function breakdown(counts: ListCounts): string { return parts.join(', ') } -/** JSON-string encode untrusted filesystem text and neutralize envelope tags. */ -function encodeFilesystemText(value: string): string { - return JSON.stringify(value) - .replaceAll('<', '\\u003c') - .replaceAll('>', '\\u003e') - .replaceAll('&', '\\u0026') +/** + * Names this renderer cannot emit verbatim, because POSIX allows every byte but + * `/` and NUL in a name and each of these would make the listing say something + * untrue: + * + * - a control character (a newline above all) splits one entry across lines; + * - ` 0 - ? `${page.entries.map(entry => `${encodeFilesystemText(entry.name)}${suffix[entry.type]}`).join('\n')}\n\n${footer}` + ? `${page.entries.map(entry => `${renderName(entry.name)}${suffix[entry.type]}`).join('\n')}\n\n${footer}` : footer - return `${encodeFilesystemText(page.path)} + return `${renderName(page.path)} directory ${body} diff --git a/packages/fs/tool-fs/tests/list-render.spec.ts b/packages/fs/tool-fs/tests/list-render.spec.ts index 2c26c1be2c..792c91bd18 100644 --- a/packages/fs/tool-fs/tests/list-render.spec.ts +++ b/packages/fs/tool-fs/tests/list-render.spec.ts @@ -42,12 +42,12 @@ describe('orderEntries', () => { describe('formatListOutput', () => { it('marks directories and non-regular children, and counts the whole listing', () => { - expect(formatListOutput(page([entry('src', 'directory'), entry('a.txt'), entry('sock', 'other')]))).toBe(`"/w" + expect(formatListOutput(page([entry('src', 'directory'), entry('a.txt'), entry('sock', 'other')]))).toBe(`/w directory -"src"/ -"a.txt" -"sock"@ +src/ +a.txt +sock@ (3 entries: 1 directory, 1 file, 1 other) `) @@ -64,13 +64,13 @@ describe('formatListOutput', () => { it('states the complete size and composition when the view is capped', () => { const entries = [entry('src', 'directory'), ...Array.from({ length: 5 }, (_, i) => entry(`f${i}.txt`))] const rendered = formatListOutput(page(entries.slice(0, 2), { totalEntries: entries.length, all: entries })) - expect(rendered).toContain('"src"/\n"f0.txt"\n') + expect(rendered).toContain('src/\nf0.txt\n') expect(rendered).not.toContain('f2.txt') expect(rendered).toContain('(Showing entries 1-2 of 6: 1 directory, 5 files. Use offset=3 to continue.)') }) it('renders an empty directory as a footer alone', () => { - expect(formatListOutput(page([]))).toBe(`"/w" + expect(formatListOutput(page([]))).toBe(`/w directory (Empty directory) diff --git a/packages/fs/tool-fs/tests/tools.spec.ts b/packages/fs/tool-fs/tests/tools.spec.ts index 74268b72ca..1ab91fb665 100644 --- a/packages/fs/tool-fs/tests/tools.spec.ts +++ b/packages/fs/tool-fs/tests/tools.spec.ts @@ -231,13 +231,13 @@ describe('list tool', () => { totalEntries: 4, counts: { directories: 2, files: 1, other: 1 }, }) - expect(text(result)).toBe(`"/abs/." + expect(text(result)).toBe(`/abs/. directory -"archive"/ -"zeroomega-3.3.23"/ -"notes.md" -"link-to-nowhere"@ +archive/ +zeroomega-3.3.23/ +notes.md +link-to-nowhere@ (4 entries: 2 directories, 1 file, 1 other) `) @@ -248,7 +248,7 @@ describe('list tool', () => { seedDir(fs, 'empty', []) const result = await call(ctx, 'list', { path: 'empty' }) expect(text(result)).toContain('(Empty directory)') - expect(text(result)).toContain('"/abs/empty"') + expect(text(result)).toContain('/abs/empty') }) it('caps the rendered entries but still reports the complete composition', async () => { @@ -268,7 +268,7 @@ describe('list tool', () => { const rendered = text(result) // The one directory survives the cap because directories sort first — the // failure mode this ordering exists to prevent. - expect(rendered).toContain('"src"/\n"a.txt"\n') + expect(rendered).toContain('src/\na.txt\n') expect(rendered).not.toContain('c.txt') expect(rendered).toContain('(Showing entries 1-2 of 4: 1 directory, 3 files. Use offset=3 to continue.)') if (result.isError) throw new Error('expected list success') @@ -281,7 +281,7 @@ describe('list tool', () => { }) const continuation = await call(ctx, 'list', { offset: 3 }) - expect(text(continuation)).toContain('"b.txt"\n"c.txt"') + expect(text(continuation)).toContain('b.txt\nc.txt') expect(text(continuation)).toContain('(Showing entries 3-4 of 4: 1 directory, 3 files.)') }) @@ -313,8 +313,10 @@ describe('list tool', () => { { name: 'fake\n', type: 'file' }, ]) const rendered = text(await call(ctx, 'list', {})) - expect(rendered).toContain('"regular@"\n"special"@') - expect(rendered).toContain('"fake\\n\\u003c/content\\u003e"') + // A regular file really named `regular@` must not read as a socket named + // `regular`, and a newline in a name must not become a second entry. + expect(rendered).toContain('"regular@"\nspecial@') + expect(rendered).toContain('"fake\\n<\\/content>"') expect(rendered.match(/<\/content>/g)).toHaveLength(1) }) From 57cf1379186ef04c56c2688dbb48ebed8bc2d0c8 Mon Sep 17 00:00:00 2001 From: NI0317 Date: Tue, 28 Jul 2026 14:42:59 +0800 Subject: [PATCH 06/24] fix(fs-search): keep broad glob samples representative Remove the duplicate model-facing list tool from this branch; directory orientation remains available through bash ls. Keep the glob sampling fix, add a real ACP composition snapshot, and narrow the decision record to the shipped bug fix. --- .../2026-07-27-glob-sampling.i18n.yaml} | 6 +- .../bug-fix/2026-07-27-glob-sampling.md | 45 ++ .../bug-fix/2026-07-27-glob-sampling.zh.md | 45 ++ .../2026-07-27-directory-listing-tool.md | 109 ---- .../2026-07-27-directory-listing-tool.zh.md | 109 ---- docs/config-catalog.md | 4 +- docs/tool-catalog.md | 4 +- .../acp-agent/fs-search.cordis.snapshot.yml | 24 + examples/acp-agent/fs-search.cordis.yml | 13 + examples/acp-agent/tests/acp.snapshot.ts | 19 +- .../acp-agent/tests/fixtures/fs-search-bin/rg | 8 + .../system-prompt.expected.md | 23 - .../tool-schemas.expected.json | 17 - .../both-mode-turn/system-prompt.expected.md | 23 - .../both-mode-turn/tool-schemas.expected.json | 17 - .../code-mode-turn/system-prompt.expected.md | 23 - .../system-prompt.expected.md | 23 - .../system-prompt.expected.md | 2 - .../tool-schemas.expected.json | 17 - .../snapshots/fs-glob-sampling/input.json | 7 + .../snapshots/fs-glob-sampling/session.jsonl | 24 + .../stdout.expected.jsonl | 2 +- .../system-prompt.expected.md | 29 + .../tool-schemas.expected.json | 517 ++++++++++++++++++ .../tests/snapshots/fs-list/input.json | 7 - .../tests/snapshots/fs-list/session.jsonl | 32 -- .../snapshots/fs-list/workspace/README.txt | 1 - .../fs-list/workspace/docs/guide.txt | 1 - .../snapshots/fs-list/workspace/package.json | 1 - .../snapshots/fs-list/workspace/src/index.txt | 1 - .../lsp-definition/system-prompt.expected.md | 2 - .../lsp-definition/tool-schemas.expected.json | 17 - .../pty-tools/system-prompt.expected.md | 2 - .../pty-tools/tool-schemas.expected.json | 17 - .../system-prompt.expected.md | 2 - .../tool-schemas.expected.json | 17 - .../skill-load/system-prompt.expected.md | 2 - .../skill-load/tool-schemas.expected.json | 17 - .../text-turn/system-prompt.expected.md | 2 - .../text-turn/tool-schemas.expected.json | 17 - .../web-fetch/system-prompt.expected.md | 2 - .../web-fetch/tool-schemas.expected.json | 17 - .../system-prompt.expected.md | 2 - .../tool-schemas.expected.json | 17 - .../core/tools/tests/gen-tool-catalog.spec.ts | 2 +- packages/fs/tool-fs/README.i18n.yaml | 6 +- packages/fs/tool-fs/README.md | 45 +- packages/fs/tool-fs/README.zh.md | 45 +- packages/fs/tool-fs/package.json | 2 +- packages/fs/tool-fs/src/index.ts | 18 +- packages/fs/tool-fs/src/list-render.ts | 137 ----- packages/fs/tool-fs/src/list.ts | 150 ----- packages/fs/tool-fs/tests/list-render.spec.ts | 79 --- packages/fs/tool-fs/tests/tools.spec.ts | 172 +----- scripts/gen-tool-catalog.ts | 4 +- 55 files changed, 775 insertions(+), 1171 deletions(-) rename .agents/notes/implemented/{feature/2026-07-27-directory-listing-tool.i18n.yaml => bug-fix/2026-07-27-glob-sampling.i18n.yaml} (58%) create mode 100644 .agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.md create mode 100644 .agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.zh.md delete mode 100644 .agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md delete mode 100644 .agents/notes/implemented/feature/2026-07-27-directory-listing-tool.zh.md create mode 100644 examples/acp-agent/fs-search.cordis.snapshot.yml create mode 100644 examples/acp-agent/fs-search.cordis.yml create mode 100755 examples/acp-agent/tests/fixtures/fs-search-bin/rg create mode 100644 examples/acp-agent/tests/snapshots/fs-glob-sampling/input.json create mode 100644 examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl rename examples/acp-agent/tests/snapshots/{fs-list => fs-glob-sampling}/stdout.expected.jsonl (90%) create mode 100644 examples/acp-agent/tests/snapshots/fs-glob-sampling/system-prompt.expected.md create mode 100644 examples/acp-agent/tests/snapshots/fs-glob-sampling/tool-schemas.expected.json delete mode 100644 examples/acp-agent/tests/snapshots/fs-list/input.json delete mode 100644 examples/acp-agent/tests/snapshots/fs-list/session.jsonl delete mode 100644 examples/acp-agent/tests/snapshots/fs-list/workspace/README.txt delete mode 100644 examples/acp-agent/tests/snapshots/fs-list/workspace/docs/guide.txt delete mode 100644 examples/acp-agent/tests/snapshots/fs-list/workspace/package.json delete mode 100644 examples/acp-agent/tests/snapshots/fs-list/workspace/src/index.txt delete mode 100644 packages/fs/tool-fs/src/list-render.ts delete mode 100644 packages/fs/tool-fs/src/list.ts delete mode 100644 packages/fs/tool-fs/tests/list-render.spec.ts diff --git a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.i18n.yaml similarity index 58% rename from .agents/notes/implemented/feature/2026-07-27-directory-listing-tool.i18n.yaml rename to .agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.i18n.yaml index 9bf1c8cb73..88e4ec9fc8 100644 --- a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.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 .agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md -2026-07-27-directory-listing-tool.md: fd8e8fb22d0b75a4d457e800296fa3ce2c2b5bd5 -2026-07-27-directory-listing-tool.zh.md: 7d4e797878858ea1ca09f1eea6c6a3953c9abae6 +# 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 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 new file mode 100644 index 0000000000..c583f0cd81 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.md @@ -0,0 +1,45 @@ +# Agent Note: Sample over-cap glob results across the tree + +Status: implemented + +English | [中文](2026-07-27-glob-sampling.zh.md) + +## Problem + +Asked what a workspace contained, an agent described one subfolder as if it were the whole project. The workspace held 22 top-level entries and 11,485 files. `glob {"pattern":"*"}` matched 10,030 paths, but all 100 inline paths sat under one recently unpacked subtree, so the model never saw the other 21 entries. + +Three individually valid behaviors composed into the false impression. A glob without `/` matches basenames at any depth, so `*` means every file in the tree rather than the shell's current-directory expansion. Ripgrep's `--sort=modified` is ascending, so an archive's restored old timestamps put that subtree first. The inline page then took the head of that order without saying that it represented only one concentrated slice. + +## Decision + +A result that fits within `globMaxResults` remains complete and byte-for-byte modification-time ordered. An over-cap result is sampled round-robin across the complete result's top-level entries: every entry receives one slot before any receives a second, exhausted groups drop out, and relative order remains stable within each group. Grouping is relative to the actual search root, including an explicit `path`. + +The footer states that the page is a cross-entry sample rather than the modification-time head, reports how many top-level entries it reaches when that fact adds information, and preserves the complete sorted list in the spill artifact. When more top-level entries exist than inline slots, it tells the model to narrow `path`. + +The prompt and schema also state that a pattern without `/` matches at any depth and that glob returns files, never directory entries. Directory orientation remains ordinary shell work in deployments that expose the model-facing bash tool: use `ls` for one directory, and glob for a named file-path pattern across the tree. `ctx.fs.listDir` remains an internal provider primitive used by skill discovery; this decision adds no model-facing `list` tool. + +## Alternatives considered + +**Keep the modification-time head and only warn about concentration.** Rejected after measuring the failure shape. A warning asks the model to distrust the only paths it received; representative data fixes the answer directly. + +**Sample every result.** Rejected. A complete result loses nothing to truncation, so modification-time order remains useful for age-oriented questions. Sampling begins only when the head stops describing the whole. + +**Switch to newest-first order.** Rejected. It merely changes which concentrated subtree can dominate and removes the existing oldest-first contract without making a capped page representative. + +**Sample only past a skew threshold.** Rejected. No current evidence supports a deployment-wide threshold, and the model could not know which ordering contract applied. The existing cap is the explainable transition. + +**Balance recursively below the top level.** Deferred. First-segment balance fixes the observed failure; deeper balancing needs an unsupported depth-versus-breadth policy. + +**Add a model-facing `list` tool.** Rejected after implementation review. The default coding composition already exposes general bash and the model understands `ls`; a duplicate tool would add permanent schema/prompt tokens plus ordering, pagination, symlink, escaping, UI, and snapshot contracts without a distinct security or policy benefit. Thin deployments without a model-facing bash tool do not gain directory orientation from this change. + +**Reject `*` or silently anchor separator-free patterns.** Rejected. The same basename-at-any-depth behavior makes `*.ts` useful across a tree. Documenting the rule preserves working ripgrep semantics. + +## Consequences + +An over-cap glob page no longer answers age-order questions from its inline paths; its footer says so, and the spill artifact retains the complete sorted view. Sampling balances only the first segment beneath the search root, so a deeper hot subtree can still dominate within one top-level entry. + +The tool surface does not grow. The fix changes glob's prompt, schema description, canonical output (`root` records the sampling basis), and over-cap Native rendering while leaving fitting results unchanged. + +## 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. 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 new file mode 100644 index 0000000000..97025a7714 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.zh.md @@ -0,0 +1,45 @@ +# Agent Note: 跨目录树采样超出上限的 glob 结果 + +Status: implemented + +[English](2026-07-27-glob-sampling.md) | 中文 + +## 问题 + +用户询问工作区包含什么内容时，一个 agent（智能体）把某个子文件夹描述成了整个项目。该工作区有 22 个顶层条目和 11,485 个文件。`glob {"pattern":"*"}` 匹配到 10,030 条路径，但内联显示的 100 条路径全部位于一棵近期解压的子树中，因此模型完全没有看到其余 21 个条目。 + +三个单独看都合理的行为叠加后造成了错误印象。不含 `/` 的 glob 会匹配任意深度的文件名，因此 `*` 表示目录树中的每个文件，而不是 shell 对当前目录执行的展开。Ripgrep 的 `--sort=modified` 按升序排列，因此归档包还原出的旧时间戳会让该子树排在最前。随后，内联页面直接截取这一顺序的前部，却没有说明它只代表集中于一处的切片。 + +## 决策 + +未超过 `globMaxResults` 的结果仍保持完整，且按修改时间排序的内容逐字节不变。超过上限时，系统会在完整结果的顶层条目之间按轮转方式采样：每个条目都先获得一个位置，之后才有条目获得第二个位置；已经用尽的分组会退出轮转；各组内部的相对顺序保持稳定。分组始终以实际搜索根为基准，显式指定 `path` 时也如此。 + +footer 会说明当前页面是跨条目的样本，而不是按修改时间排序的前部；当顶层条目覆盖数能提供额外信息时，还会报告该数量；完整排序列表仍保存在 spill 产物中。若顶层条目数量超过内联位置数，footer 会要求模型缩小 `path`。 + +提示词与 schema 还会说明：不含 `/` 的模式会匹配任意深度，glob 只返回文件，绝不返回目录条目。在向模型暴露 bash 工具的部署中，目录定位仍由普通 shell 操作完成：查看一个目录使用 `ls`，跨目录树按指定文件路径模式查找则使用 glob。skill（技能）发现流程仍将 `ctx.fs.listDir` 作为内部提供方原语使用；本决策不会新增面向模型的 `list` 工具。 + +## 考虑过的替代方案 + +**保留按修改时间排序的前部，只警告结果过于集中。** 测量实际故障形态后否决。警告只会要求模型怀疑自己拿到的唯一一批路径；具有代表性的数据能直接修正答案。 + +**对所有结果采样。** 否决。完整结果没有因截断损失任何信息，因此按修改时间排序仍有助于回答关注新旧时间的问题。只有当截取前部已经无法描述整体时，才开始采样。 + +**改为最新优先排序。** 否决。这只会改变哪一棵结果集中的子树可能占据主导；既取消了现有的最旧优先契约，也没有让受限页面更具代表性。 + +**仅在偏斜超过阈值时采样。** 否决。目前没有证据支持适用于所有部署的统一阈值，模型也无法判断当前采用的是哪一种排序契约。现有上限是可以清楚解释的切换点。 + +**在顶层以下递归平衡。** 暂缓。按第一路径段做平衡已经修复观测到的故障；更深层的平衡需要一套尚无依据的深度与广度取舍策略。 + +**新增面向模型的 `list` 工具。** 实现评审后否决。默认编程组合已经提供通用 bash，模型也理解 `ls`；重复工具会永久增加 schema 与提示词所占的 token，并引入排序、分页、符号链接、转义、UI 与快照契约，却没有独立的安全或策略收益。不向模型提供 bash 工具的精简部署也不会因本次改动获得目录定位能力。 + +**拒绝 `*`，或在不含分隔符的模式前静默加上根目录锚点。** 否决。同样的「在任意深度匹配文件名」行为使 `*.ts` 可以有效地跨目录树搜索。记录这条规则能够保留正常工作的 Ripgrep 语义。 + +## 影响 + +超过上限的 glob 页面无法再根据内联路径回答按时间判断新旧的问题；footer 会明确说明这一点，spill 产物仍保留完整的排序视图。采样只平衡搜索根下的第一路径段，因此某个顶层条目内部较深处、结果密集的子树仍可能占据主导。 + +工具接口不会扩大。此修复会更改 glob 的提示词、schema 描述、规范输出（`root` 记录采样基准）以及超过上限时的 Native 渲染，未超过上限的结果保持不变。 + +## 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。 diff --git a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md b/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md deleted file mode 100644 index fd8e8fb22d..0000000000 --- a/.agents/notes/implemented/feature/2026-07-27-directory-listing-tool.md +++ /dev/null @@ -1,109 +0,0 @@ -# Agent Note: Sample over-cap glob results across the tree, and give the model a directory-listing tool - -Status: implemented - -English | [中文](2026-07-27-directory-listing-tool.zh.md) - -## Problem - -Asked what a workspace contained, an agent described one subfolder as if it were the whole project. - -The session log shows exactly how. The workspace held 22 top-level entries and 11,485 files. The model called `glob {"pattern": "*"}`, which matched 10,030 paths; the tool showed the first 100, and all 100 sat under a single recently-unpacked subdirectory holding 355 of those files. The model never saw the other 21 top-level entries and answered from the one it did see. The session cwd was correct throughout — nothing was misconfigured, and every number the tool printed was true. - -Three properties of `glob` compose into that page: - -- **A pattern with no `/` matches at any depth.** The pattern goes to ripgrep as `--glob=`, where a glob without a separator matches the basename anywhere in the tree. `*` therefore means "every file in the workspace", not "the top level" — the opposite of what it means in a shell. The tool said nothing about this, and every example in its schema was `**/…`, so nothing suggested the plain form was recursive. -- **`--sort=modified` orders oldest first.** Unpacking an archive restores the timestamps stored inside it, which predate everything the user wrote, so a freshly unpacked subtree lands at the very front of any broad match. (Ripgrep sorts ascending; `--sortr` is the descending form and is not used here.) -- **The inline page was the head of that order.** `globMaxResults` (100) paths were kept from the front. Under the first two properties, one subtree takes every slot. - -Each property is defensible alone. Together they make the most ordinary request an agent receives — "what is in this directory" — reliably produce a confident wrong answer, because nothing in the result distinguishes "the 100 oldest files in this workspace" from "this workspace". - -### What ordering can and cannot fix - -A directory's name reaches the model only as the prefix of one of its files' paths, since `rg --files` emits files and never directory entries. That is enough for ordering to matter a great deal, and not enough for `glob` to answer the question. - -Measured on a reproduction of the failure's shape — 24 top-level entries, 716 files, one old-timestamped subtree: - -| First 100 paths chosen by | Distinct top-level names visible | -| --- | --- | -| modification time, oldest first (the shipped behavior) | 7 | -| round-robin across top-level entries | 21 | - -So a differently chosen page does surface most of the missing names, and the original diagnosis that ordering could not have helped was wrong. What no ordering fixes: an entry with no files beneath it never appears at all (the reproduction's empty directory is absent from the complete 716-path output), and nothing in the output says which names are directories or how many entries a directory holds. `glob` can therefore convey a tree's rough shape; it cannot state a directory's contents. - -## Decision - -Two changes, in the two packages that own the two halves of the failure. - -### The inline page of an over-cap `glob` result is sampled, not taken from the head - -`@deepseek-ai/dsh-tool-fs-search`. A result within `globMaxResults` is unchanged: shown whole, in modification-time order. Only when the result is larger does the page change — and there, taking the head is what fails. - -`sampleAcrossTopLevel` removes the displayed search-root prefix, groups the complete result by the next path segment, and fills the page round-robin: every entry immediately beneath the actual relative or absolute root gets a slot before any entry gets a second, and an entry that runs out of paths drops out so its remaining slots go to the rest. Sort order survives where it still carries meaning — groups are visited in the order ripgrep first emits them, and each group's own paths keep their relative order. The page is emitted grouped by entry rather than interleaved, so the breadth is legible at a glance. - -The footer states the basis, because a page that silently stopped being "the first N in modification-time order" would be a second, quieter version of the same lie: - -``` -(Showing 100 of 10030 paths, sampled across 22 of the 22 top-level entries this pattern matched -instead of taken in modification-time order. Full sorted result stored at: …) -``` - -When the page cannot reach every top-level entry — more entries than slots — the footer says so with the shown/total spread and tells the model to narrow `path`. A flat result, where every path is its own top-level entry, keeps the plain `(Showing k of n paths. …)` footer: there the round-robin *is* the sorted head, and naming a spread would only restate the counts. The spill artifact always holds the complete list in modification-time order, so the sorted view is never lost. - -The guidance and schema stop misleading in the same change: "not shell find or ls" becomes "not shell find"; both now state that a pattern without `/` matches basenames at any depth, that results are files and never directories, and that a fitting result is modification-time ordered while a larger one is sampled across top-level entries. They do not recommend sibling-package tools that may be absent from the current composition. - -### `list`, in `@deepseek-ai/dsh-tool-fs` - -A fourth model-facing filesystem tool over the existing `ctx.fs.listDir` primitive, which until now shipped with skill discovery as its only consumer; [the seam Agent Note](../../archived/architecture/2026-07-03-filesystem-directory-listing-seam.md) deferred the model-facing consumer to a separate decision, which this is. - -It takes optional `path` and 1-based `offset` arguments, defaulting to the calling agent's session workspace and entry 1, and returns one bounded page as `{ path, offset, entries: [{ name, type }], totalEntries, counts }`, where `type` is `file`, `directory`, or `other`. It calls `listDir` and nothing else: the seam already reports absence as `FS_NOT_FOUND` and a non-directory target as `FS_NOT_DIRECTORY`, so a preceding `stat` would add a round-trip and a second source of truth. - -Three presentation rules carry the decision: - -- **Directories sort first, then files, then non-regular children, each alphabetically** before paging, so every offset traverses one stable order and the first page keeps navigable structure. -- **The canonical value and Native result carry one recoverable page** of at most `listMaxEntries` (default 200, configurable). The footer states the complete size and composition and gives `offset=` until the final page, so omitted sibling names remain reachable. -- **Filesystem text cannot forge presentation structure.** A name is emitted verbatim unless it would make the listing lie — a control character splitting one entry across lines, `` 交给 ripgrep，而不含分隔符的 glob 匹配树中任何位置的基名。因此 `*` 的含义是「工作区里的每个文件」，而不是「顶层」——与它在 shell 里的含义正好相反。工具对此只字未提，schema 里的示例又全是 `**/…`，没有任何线索表明朴素写法是递归的。 -- **`--sort=modified` 按从旧到新排序。** 解包压缩档会还原档案内部保存的时间戳，它们早于用户自己写下的一切，因此新近解包的子树会落在任何宽泛匹配的最前面。（ripgrep 按升序排序；降序是 `--sortr`，此处未使用。） -- **内联页面取的是该顺序的头部。** 从最前面保留 `globMaxResults`（100）条路径。在前两项性质之下，一个子树吃掉全部位置。 - -单看每一项都站得住。合在一起，它们让 agent 收到的最普通的请求——「这个目录里有什么」——稳定地产出一个笃定的错误答案，因为结果里没有任何信息能区分「本工作区按从旧到新顺序排在最前的 100 个文件」与「本工作区」。 - -### 排序能修什么，不能修什么 - -由于 `rg --files` 输出文件、从不输出目录条目，一个目录的名字只能作为其下某个文件路径的前缀抵达模型。这既足以让排序变得非常重要，也不足以让 `glob` 回答那个问题。 - -在一份复现该失败形态的目录上实测——24 个顶层条目、716 个文件、一个时间戳较旧的子树： - -| 前 100 条路径的挑选方式 | 可见的顶层名个数 | -| --- | --- | -| 按修改时间、从旧到新（已交付的行为） | 7 | -| 跨顶层条目轮转 | 21 | - -也就是说，换一种页面挑选方式确实能呈现出大部分缺失的名字，最初那句「排序帮不上忙」的诊断是错的。排序修不了的是：没有任何文件的条目根本不会出现（复现目录里的空目录在完整的 716 条输出中一次都没出现），而且输出里没有任何信息说明哪些名字是目录、某个目录有多少条目。因此 `glob` 能传达一棵树的大致形状，却说不出一个目录的内容。 - -## Decision - -两项改动，分别落在承担这次失败两半责任的两个包中。 - -### 超过上限的 `glob` 结果，内联页面改为取样而非取头部 - -`@deepseek-ai/dsh-tool-fs-search`。未超过 `globMaxResults` 的结果完全不变：整体展示，按修改时间排序。只有结果更大时页面才改变——而恰恰在这种情况下，取头部是会失败的做法。 - -`sampleAcrossTopLevel` 移除所显示的搜索根前缀，再按下一个路径段对完整结果分组，并以轮转方式填充页面：实际相对或绝对搜索根正下方的每个条目都先拿到一个位置，任何条目才可能拿到第二个；某个条目的路径用尽后退出，其剩余份额交给其余条目。排序在仍有意义的地方被保留下来——分组按 ripgrep 首次输出它们的顺序访问，而每个分组内部的路径保持原有相对顺序。页面按条目分组输出而非交错输出，使覆盖广度一眼可辨。 - -footer 会说明取用依据，因为一个悄悄不再是「按修改时间排序的前 N 条」的页面，只会成为同一个谎言更安静的版本： - -``` -(Showing 100 of 10030 paths, sampled across 22 of the 22 top-level entries this pattern matched -instead of taken in modification-time order. Full sorted result stored at: …) -``` - -当页面无法触达全部顶层条目时——条目数多于位置数——footer 会给出已触达/总计的分布，并要求模型缩小 `path`。扁平结果（每个路径各自构成一个顶层条目）保留朴素的 `(Showing k of n paths. …)` footer：此时轮转结果**就是**排序后的头部，说明分布只会重复计数。spill 产物始终保存按修改时间排序的完整列表，排序视图不会丢失。 - -同一次改动里，指导与 schema 也不再误导：「not shell find or ls」改为「not shell find」；两处现在都写明：不含 `/` 的 pattern 匹配任意深度的基名、结果只有文件从不包含目录、未超上限的结果按修改时间排序，而更大的结果跨顶层条目取样。它们不会推荐当前组合中可能不存在的兄弟包工具。 - -### `list`，位于 `@deepseek-ai/dsh-tool-fs` - -在既有的 `ctx.fs.listDir` 原语之上新增第四个面向模型的文件系统工具；该原语此前交付时唯一的消费方是 skill（技能）发现，[seam Agent Note](../../archived/architecture/2026-07-03-filesystem-directory-listing-seam.md) 把面向模型的消费方推迟为一项单独的决策，也就是本文。 - -它接受可选的 `path` 和从 1 开始的 `offset` 参数，默认取调用 agent 的会话工作区和第 1 个条目，并返回一个有界页面，形如 `{ path, offset, entries: [{ name, type }], totalEntries, counts }`，其中 `type` 为 `file`、`directory` 或 `other`。它只调用 `listDir`：seam 已经把不存在报告为 `FS_NOT_FOUND`、把非目录目标报告为 `FS_NOT_DIRECTORY`，前置 `stat` 只会多一次往返并制造第二个真源。 - -有三条展示规则承载了这个决策： - -- **先目录、再文件、最后非常规子项，各组内按字母序**，然后再分页，使每个 offset 都遍历同一稳定顺序，且第一页保留可导航的结构。 -- **规范值和 Native 结果携带一个可继续取回的页面**，最多包含 `listMaxEntries` 个条目（默认 200，可配置）。footer 会说明完整规模与构成，并在最后一页之前给出 `offset=`，因此被省略的同级名称仍可取回。 -- **文件系统文本无法伪造展示结构。** 条目名默认原样输出；只有当它会让列出结果失真时才转为 JSON 字符串并中和 `; /** 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. */ get_goal: Record; - /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents. */ - list: { - /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */ - path?: string; - /** 1-based first entry to return. Defaults to 1; use the footer value to continue. */ - offset?: number; - } & Record; /** 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. */ ralph: { /** The immutable completion objective for every fresh Ralph round. */ @@ -307,20 +298,6 @@ interface ToolOutputMap { }; activation: "armed" | "disarmed"; }; - list: { - path: string; - offset: number; - entries: ({ - name: string; - type: "file" | "directory" | "other"; - })[]; - totalEntries: number; - counts: { - directories: number; - files: number; - other: number; - }; - }; ralph: { runId: string; agentsStarted: number; diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json index 93457f0e37..314b24e2be 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json @@ -172,23 +172,6 @@ "properties": {} } }, - { - "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", - "parameters": { - "type": "object", - "properties": { - "path": { - "type": "string", - "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." - }, - "offset": { - "type": "number", - "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." - } - } - } - }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md index 1a8589a47b..0cee2a6517 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md @@ -5,8 +5,6 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. - 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. @@ -82,13 +80,6 @@ interface ToolArgsMap { } & Record; /** 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. */ get_goal: Record; - /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents. */ - list: { - /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */ - path?: string; - /** 1-based first entry to return. Defaults to 1; use the footer value to continue. */ - offset?: number; - } & Record; /** 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. */ ralph: { /** The immutable completion objective for every fresh Ralph round. */ @@ -278,20 +269,6 @@ interface ToolOutputMap { }; activation: "armed" | "disarmed"; }; - list: { - path: string; - offset: number; - entries: ({ - name: string; - type: "file" | "directory" | "other"; - })[]; - totalEntries: number; - counts: { - directories: number; - files: number; - other: number; - }; - }; ralph: { runId: string; agentsStarted: number; diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json index 9f55d9291f..b61d7bf623 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json @@ -115,23 +115,6 @@ "properties": {} } }, - { - "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", - "parameters": { - "type": "object", - "properties": { - "path": { - "type": "string", - "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." - }, - "offset": { - "type": "number", - "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." - } - } - } - }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md index 1a8589a47b..0cee2a6517 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md @@ -5,8 +5,6 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. - 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. @@ -82,13 +80,6 @@ interface ToolArgsMap { } & Record; /** 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. */ get_goal: Record; - /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents. */ - list: { - /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */ - path?: string; - /** 1-based first entry to return. Defaults to 1; use the footer value to continue. */ - offset?: number; - } & Record; /** 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. */ ralph: { /** The immutable completion objective for every fresh Ralph round. */ @@ -278,20 +269,6 @@ interface ToolOutputMap { }; activation: "armed" | "disarmed"; }; - list: { - path: string; - offset: number; - entries: ({ - name: string; - type: "file" | "directory" | "other"; - })[]; - totalEntries: number; - counts: { - directories: number; - files: number; - other: number; - }; - }; ralph: { runId: string; agentsStarted: number; diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md index 1a8589a47b..0cee2a6517 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md @@ -5,8 +5,6 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. - 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. @@ -82,13 +80,6 @@ interface ToolArgsMap { } & Record; /** 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. */ get_goal: Record; - /** List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents. */ - list: { - /** Directory to list. Defaults to the session workspace; a relative path resolves against it. */ - path?: string; - /** 1-based first entry to return. Defaults to 1; use the footer value to continue. */ - offset?: number; - } & Record; /** 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. */ ralph: { /** The immutable completion objective for every fresh Ralph round. */ @@ -278,20 +269,6 @@ interface ToolOutputMap { }; activation: "armed" | "disarmed"; }; - list: { - path: string; - offset: number; - entries: ({ - name: string; - type: "file" | "directory" | "other"; - })[]; - totalEntries: number; - counts: { - directories: number; - files: number; - other: number; - }; - }; ralph: { runId: string; agentsStarted: number; diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/escalation-approved/system-prompt.expected.md index cd3c81f6f8..e3437ad61a 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/escalation-approved/system-prompt.expected.md @@ -5,8 +5,6 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. - 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. diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json index 7094daf44e..01ac777a42 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json @@ -115,23 +115,6 @@ "properties": {} } }, - { - "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", - "parameters": { - "type": "object", - "properties": { - "path": { - "type": "string", - "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." - }, - "offset": { - "type": "number", - "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." - } - } - } - }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/fs-glob-sampling/input.json b/examples/acp-agent/tests/snapshots/fs-glob-sampling/input.json new file mode 100644 index 0000000000..cc5fc95e59 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-glob-sampling/input.json @@ -0,0 +1,7 @@ +{ + "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." } + ] +} diff --git a/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl b/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl new file mode 100644 index 0000000000..16a7d9b631 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl @@ -0,0 +1,24 @@ +{"type":"session","version":0,"id":"f5a99d52-3eaa-4ce7-858d-61d4fd77df2a","createdAt":1785218400000,"cwd":"/tmp/acp-fs-glob-sampling","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"}},"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":"assistant/chunk","seq":5,"time":1785218400006,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":6,"time":1785218400007,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"glob-sampling-call","name":"glob","argumentsDelta":"{\"pattern\":\"*\"}"}}} +{"type":"assistant/chunk","seq":7,"time":1785218400008,"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":8,"time":1785218400009,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1,"outputTokens":1}}}} +{"type":"assistant/chunk","seq":9,"time":1785218400010,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":10,"time":1785218400011,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-pro"},"usage":{"inputTokens":1,"outputTokens":1}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"} +{"type":"tool/call","seq":11,"time":1785218400012,"data":{"turn":1,"step":1,"callId":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\"}"}} +{"type":"tool/result","seq":12,"time":1785218400013,"data":{"turn":1,"step":1,"callId":"glob-sampling-call","content":[{"type":"text","text":"archive/a.ts\nsrc/index.ts\ndocs/guide.md\ntest/spec.ts\n\n(Showing 4 of 6 paths, sampled across 4 of the 4 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.)"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"} +{"type":"step/end","seq":13,"time":1785218400014,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":14,"time":1785218400015,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":15,"time":1785218400016,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":16,"time":1785218400017,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"GLOB_SAMPLED"}}} +{"type":"assistant/chunk","seq":17,"time":1785218400018,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GLOB_SAMPLED"}}}} +{"type":"assistant/chunk","seq":18,"time":1785218400019,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":1,"outputTokens":1}}}} +{"type":"assistant/chunk","seq":19,"time":1785218400020,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":20,"time":1785218400021,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"GLOB_SAMPLED"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-pro"},"usage":{"inputTokens":1,"outputTokens":1}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"} +{"type":"step/end","seq":21,"time":1785218400022,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":22,"time":1785218400023,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-list/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-glob-sampling/stdout.expected.jsonl similarity index 90% rename from examples/acp-agent/tests/snapshots/fs-list/stdout.expected.jsonl rename to examples/acp-agent/tests/snapshots/fs-glob-sampling/stdout.expected.jsonl index 22d36a3c79..691b11cef0 100644 --- a/examples/acp-agent/tests/snapshots/fs-list/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-glob-sampling/stdout.expected.jsonl @@ -1,4 +1,4 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"docs src"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"GLOB_SAMPLED"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} 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 new file mode 100644 index 0000000000..467b05904b --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-glob-sampling/system-prompt.expected.md @@ -0,0 +1,29 @@ +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. + +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 new file mode 100644 index 0000000000..1b25291c5c --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-glob-sampling/tool-schemas.expected.json @@ -0,0 +1,517 @@ +{ + "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.", + "parameters": { + "type": "object", + "properties": { + "command": { + "type": "string", + "description": "The bash command to execute." + }, + "description": { + "type": "string", + "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"." + }, + "timeoutMs": { + "type": "number", + "description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry." + }, + "workdir": { + "type": "string", + "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it." + }, + "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": [ + "command", + "description" + ] + } + }, + { + "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.", + "parameters": { + "type": "object", + "properties": { + "pattern": { + "type": "string", + "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\"). A pattern with no \"/\" matches the basename at any depth, so \"*\" and \"*.ts\" both search the whole tree; include a separator to anchor the depth." + }, + "path": { + "type": "string", + "description": "Directory to search in. Defaults to the session workspace; a relative path resolves against it." + } + }, + "required": [ + "pattern" + ] + } + }, + { + "name": "grep", + "description": "Search file contents with a ripgrep regular expression. Returns matching lines with line numbers, grouped by file. Returns the first 250 matches inline; a capped result reports where the complete match list was saved. Use read on a matched file for surrounding context.", + "parameters": { + "type": "object", + "properties": { + "pattern": { + "type": "string", + "description": "Regular expression to search for (ripgrep syntax)." + }, + "path": { + "type": "string", + "description": "File or directory to search. Defaults to the session workspace; a relative path resolves against it." + }, + "include": { + "type": "string", + "description": "One glob filter for which files to search (e.g. \"*.ts\", \"*.{js,jsx}\"). Not a list; negation is not supported." + } + }, + "required": [ + "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/examples/acp-agent/tests/snapshots/fs-list/input.json b/examples/acp-agent/tests/snapshots/fs-list/input.json deleted file mode 100644 index 67a0bc3f42..0000000000 --- a/examples/acp-agent/tests/snapshots/fs-list/input.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "steps": [ - { "op": "initialize" }, - { "op": "newSession" }, - { "op": "prompt", "text": "Call the list tool exactly once, with no arguments at all (NOT bash, NOT glob, and do not pass a path). Then reply with exactly the names of the subdirectories it reported, alphabetically, separated by a single space, and nothing else." } - ] -} diff --git a/examples/acp-agent/tests/snapshots/fs-list/session.jsonl b/examples/acp-agent/tests/snapshots/fs-list/session.jsonl deleted file mode 100644 index 0a05e2b1fe..0000000000 --- a/examples/acp-agent/tests/snapshots/fs-list/session.jsonl +++ /dev/null @@ -1,32 +0,0 @@ -{"type":"session","version":0,"id":"ea640046-d959-4644-9a03-ff3d08133d4b","createdAt":1785159113359,"cwd":"/var/folders/8k/kj35k1fd6t90n0czg7k3hv140000gn/T/acp-snap-cwd-QJ2ZC6","delegationDepth":0} -{"type":"turn/start","seq":0,"time":1785159113361,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1785159113362,"data":{"content":[{"type":"text","text":"Call the list tool exactly once, with no arguments at all (NOT bash, NOT glob, and do not pass a path). Then reply with exactly the names of the subdirectories it reported, alphabetically, separated by a single space, and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"session/title","seq":2,"time":1785159113363,"data":{"title":"Call the list tool exactly","messageSeqs":[1],"source":{"kind":"fallback"}}} -{"type":"step/start","seq":3,"time":1785159113368,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1785159113369,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":5,"time":1785159115248,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"reasoning-chunks","seq0":6,"time0":1785159115249,"data":{"turn":1,"step":1,"index":0,"dt":[146,45,3,0,0,1,43,1,0,0,1,1,31,1,46,0,0,0,0,0,41,1,0,0,45,2,2,0,0,1,44,3,3,0],"texts":["The"," user"," wants"," me"," to"," call"," the"," list"," tool"," with"," no"," arguments"," and"," then"," reply"," with"," the"," names"," of"," the"," sub","direct","ories"," it"," reports",","," alphabet","ically",","," separated"," by"," a"," single"," space","."]}} -{"type":"assistant/chunk","seq":41,"time":1785159115836,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":42,"time":1785159115837,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_BSi06gcYvl6oad3I5qqG9244","name":"list","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":43,"time":1785159115837,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_BSi06gcYvl6oad3I5qqG9244","name":"list","argumentsDelta":"{}"}}} -{"type":"assistant/chunk","seq":44,"time":1785159115921,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to call the list tool with no arguments and then reply with the names of the subdirectories it reports, alphabetically, separated by a single space."}}}} -{"type":"assistant/chunk","seq":45,"time":1785159115921,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_BSi06gcYvl6oad3I5qqG9244","name":"list","arguments":"{}"}}}} -{"type":"assistant/chunk","seq":46,"time":1785159115921,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":5513,"outputTokens":62,"cacheReadTokens":0,"reasoningTokens":35}}}} -{"type":"assistant/chunk","seq":47,"time":1785159115922,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":48,"time":1785159115926,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to call the list tool with no arguments and then reply with the names of the subdirectories it reports, alphabetically, separated by a single space."},{"type":"tool-call","id":"call_00_BSi06gcYvl6oad3I5qqG9244","name":"list","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":5513,"outputTokens":62,"cacheReadTokens":0,"reasoningTokens":35}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"surfaceOp":"append"} -{"type":"tool/call","seq":49,"time":1785159115927,"data":{"turn":1,"step":1,"callId":"call_00_BSi06gcYvl6oad3I5qqG9244","name":"list","arguments":"{}"}} -{"type":"tool/result","seq":50,"time":1785159115944,"data":{"turn":1,"step":1,"callId":"call_00_BSi06gcYvl6oad3I5qqG9244","content":[{"type":"text","text":"/var/folders/8k/kj35k1fd6t90n0czg7k3hv140000gn/T/acp-snap-cwd-QJ2ZC6\ndirectory\n\ndocs/\nsrc/\npackage.json\nREADME.txt\n\n(4 entries: 2 directories, 2 files)\n"}],"isError":false},"sourceEventSeqs":[49],"surfaceOp":"append"} -{"type":"step/end","seq":51,"time":1785159115950,"data":{"turn":1,"step":1}} -{"type":"step/start","seq":52,"time":1785159115951,"data":{"turn":1,"step":2}} -{"type":"assistant/chunk","seq":53,"time":1785159116889,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"reasoning-chunks","seq0":54,"time0":1785159116890,"data":{"turn":1,"step":2,"index":0,"dt":[145,49,1,0,60,0,0,1,0,39,1,0,0,0,0,23,1,46,3,0,0],"texts":["The"," sub","direct","ories"," reported"," are"," `","docs","/","`"," and"," `","src","/","`."," Alphabet","ically",":"," docs",","," src","."]}} -{"type":"assistant/chunk","seq":76,"time":1785159117259,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":77,"time":1785159117259,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"docs"}}} -{"type":"assistant/chunk","seq":78,"time":1785159117297,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" src"}}} -{"type":"assistant/chunk","seq":79,"time":1785159117300,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The subdirectories reported are `docs/` and `src/`. Alphabetically: docs, src."}}}} -{"type":"assistant/chunk","seq":80,"time":1785159117300,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"docs src"}}}} -{"type":"assistant/chunk","seq":81,"time":1785159117300,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":161,"outputTokens":25,"cacheReadTokens":5504,"reasoningTokens":22}}}} -{"type":"assistant/chunk","seq":82,"time":1785159117300,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":83,"time":1785159117301,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The subdirectories reported are `docs/` and `src/`. Alphabetically: docs, src."},{"type":"text","text":"docs src"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":161,"outputTokens":25,"cacheReadTokens":5504,"reasoningTokens":22}},"sourceEventSeqs":[53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82],"surfaceOp":"append"} -{"type":"step/end","seq":84,"time":1785159117308,"data":{"turn":1,"step":2}} -{"type":"turn/end","seq":85,"time":1785159117309,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-list/workspace/README.txt b/examples/acp-agent/tests/snapshots/fs-list/workspace/README.txt deleted file mode 100644 index dab306f45e..0000000000 --- a/examples/acp-agent/tests/snapshots/fs-list/workspace/README.txt +++ /dev/null @@ -1 +0,0 @@ -# Project diff --git a/examples/acp-agent/tests/snapshots/fs-list/workspace/docs/guide.txt b/examples/acp-agent/tests/snapshots/fs-list/workspace/docs/guide.txt deleted file mode 100644 index 8c0d02fadc..0000000000 --- a/examples/acp-agent/tests/snapshots/fs-list/workspace/docs/guide.txt +++ /dev/null @@ -1 +0,0 @@ -# Guide diff --git a/examples/acp-agent/tests/snapshots/fs-list/workspace/package.json b/examples/acp-agent/tests/snapshots/fs-list/workspace/package.json deleted file mode 100644 index e36fa754cf..0000000000 --- a/examples/acp-agent/tests/snapshots/fs-list/workspace/package.json +++ /dev/null @@ -1 +0,0 @@ -{ "name": "demo" } diff --git a/examples/acp-agent/tests/snapshots/fs-list/workspace/src/index.txt b/examples/acp-agent/tests/snapshots/fs-list/workspace/src/index.txt deleted file mode 100644 index eab39ce89c..0000000000 --- a/examples/acp-agent/tests/snapshots/fs-list/workspace/src/index.txt +++ /dev/null @@ -1 +0,0 @@ -export const answer = 42 diff --git a/examples/acp-agent/tests/snapshots/lsp-definition/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/lsp-definition/system-prompt.expected.md index d02b6d0859..7bde8fe289 100644 --- a/examples/acp-agent/tests/snapshots/lsp-definition/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/lsp-definition/system-prompt.expected.md @@ -5,8 +5,6 @@ You are a coding assistant powered by the deepseek-v4-pro model. Your working di Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. - 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. diff --git a/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json index ab1bda91f3..9b5925605c 100644 --- a/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json @@ -115,23 +115,6 @@ "properties": {} } }, - { - "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", - "parameters": { - "type": "object", - "properties": { - "path": { - "type": "string", - "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." - }, - "offset": { - "type": "number", - "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." - } - } - } - }, { "name": "lsp", "description": "Query a language server for precise code navigation. operation is one of goToDefinition, findReferences, goToImplementation, hover. line and character are one-based UTF-16 cursor coordinates. findReferences includes the declaration.", diff --git a/examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md index c5496aeed5..df065a83cb 100644 --- a/examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md @@ -5,8 +5,6 @@ You are a coding assistant powered by the deepseek-v4-pro model. Your working di Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. - 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. diff --git a/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json index 0d20d22762..8e093db8bd 100644 --- a/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json @@ -115,23 +115,6 @@ "properties": {} } }, - { - "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", - "parameters": { - "type": "object", - "properties": { - "path": { - "type": "string", - "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." - }, - "offset": { - "type": "number", - "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." - } - } - } - }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/session-query-spill/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/session-query-spill/system-prompt.expected.md index 7d13160613..68bdd841c7 100644 --- a/examples/acp-agent/tests/snapshots/session-query-spill/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/session-query-spill/system-prompt.expected.md @@ -5,8 +5,6 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. - 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. diff --git a/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json index caee8e049e..beb93c6b53 100644 --- a/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json @@ -115,23 +115,6 @@ "properties": {} } }, - { - "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", - "parameters": { - "type": "object", - "properties": { - "path": { - "type": "string", - "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." - }, - "offset": { - "type": "number", - "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." - } - } - } - }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md index e6ab6361db..17e6773a03 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md @@ -5,8 +5,6 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. - 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. diff --git a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json index 7094daf44e..01ac777a42 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json @@ -115,23 +115,6 @@ "properties": {} } }, - { - "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", - "parameters": { - "type": "object", - "properties": { - "path": { - "type": "string", - "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." - }, - "offset": { - "type": "number", - "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." - } - } - } - }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md index e6ab6361db..17e6773a03 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md @@ -5,8 +5,6 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. - 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. diff --git a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json index 7094daf44e..01ac777a42 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json @@ -115,23 +115,6 @@ "properties": {} } }, - { - "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", - "parameters": { - "type": "object", - "properties": { - "path": { - "type": "string", - "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." - }, - "offset": { - "type": "number", - "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." - } - } - } - }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md index 451746f412..45705db0a5 100644 --- a/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md @@ -5,8 +5,6 @@ You are a coding assistant powered by the deepseek-v4-pro model. Your working di Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. - 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. diff --git a/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json index 6c389246e2..70940f8907 100644 --- a/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json @@ -115,23 +115,6 @@ "properties": {} } }, - { - "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", - "parameters": { - "type": "object", - "properties": { - "path": { - "type": "string", - "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." - }, - "offset": { - "type": "number", - "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." - } - } - } - }, { "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.", diff --git a/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md index fdacca4b7f..6cd8d5725f 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md @@ -5,8 +5,6 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. - 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. diff --git a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json index 7094daf44e..01ac777a42 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json @@ -115,23 +115,6 @@ "properties": {} } }, - { - "name": "list", - "description": "List the direct children of one directory, with their type. Entries are directories first, then files, each alphabetical; up to 200 are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. It includes subdirectories and is the tool for seeing one directory's contents.", - "parameters": { - "type": "object", - "properties": { - "path": { - "type": "string", - "description": "Directory to list. Defaults to the session workspace; a relative path resolves against it." - }, - "offset": { - "type": "number", - "description": "1-based first entry to return. Defaults to 1; use the footer value to continue." - } - } - } - }, { "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.", diff --git a/packages/core/tools/tests/gen-tool-catalog.spec.ts b/packages/core/tools/tests/gen-tool-catalog.spec.ts index 974d88c18c..3754595f56 100644 --- a/packages/core/tools/tests/gen-tool-catalog.spec.ts +++ b/packages/core/tools/tests/gen-tool-catalog.spec.ts @@ -23,7 +23,7 @@ describe('gen-tool-catalog collectToolCatalog', () => { it('boots every shipped tool package and harvests its model-facing schemas', async () => { const catalog = await collectToolCatalog() const names = catalog.flatMap(entry => entry.schemas.map(s => s.name)).sort() - expect(names).toEqual(['ask_user_question', 'bash', 'cordis_inspect', 'cordis_mount', 'cordis_unmount', 'create_goal', 'edit', 'exit_plan_mode', 'get_goal', 'glob', 'grep', 'list', 'lsp', 'ralph', 'read', 'run_code', 'session_event_read', 'session_event_search', 'session_event_trace', 'session_search', 'session_trace', 'skill', 'subagent', 'task_kill', 'task_list', 'task_output', 'terminal_close', 'terminal_list', 'terminal_open', 'terminal_read', 'terminal_send', 'terminal_signal', 'todo_write', 'update_goal', 'web_fetch', 'web_search', 'workflow', 'write']) + expect(names).toEqual(['ask_user_question', 'bash', 'cordis_inspect', 'cordis_mount', 'cordis_unmount', 'create_goal', 'edit', 'exit_plan_mode', 'get_goal', 'glob', 'grep', 'lsp', 'ralph', 'read', 'run_code', 'session_event_read', 'session_event_search', 'session_event_trace', 'session_search', 'session_trace', 'skill', 'subagent', 'task_kill', 'task_list', 'task_output', 'terminal_close', 'terminal_list', 'terminal_open', 'terminal_read', 'terminal_send', 'terminal_signal', 'todo_write', 'update_goal', 'web_fetch', 'web_search', 'workflow', 'write']) // Every tool carries a JSON-Schema `parameters` object (what the model sees). for (const entry of catalog) { for (const schema of entry.schemas) { diff --git a/packages/fs/tool-fs/README.i18n.yaml b/packages/fs/tool-fs/README.i18n.yaml index 3e7c989373..13f1ecd649 100644 --- a/packages/fs/tool-fs/README.i18n.yaml +++ b/packages/fs/tool-fs/README.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 packages/fs/tool-fs/README.md -README.md: 8fdd54fb36353ca6c1dbcf71cdad38c4bcf26b7d -README.zh.md: 567c8e0df58950369c59785859948e32cbccdef4 +# pnpm run verify-translation-pairing --write +README.md: 4ff9b043525e8e7a0b59e3d91410951d88bb9a69 +README.zh.md: f94a903c9c37f7d45b7f8cebabe21082388bd041 diff --git a/packages/fs/tool-fs/README.md b/packages/fs/tool-fs/README.md index 8fdd54fb36..4ff9b04352 100644 --- a/packages/fs/tool-fs/README.md +++ b/packages/fs/tool-fs/README.md @@ -2,24 +2,23 @@ English | [中文](README.zh.md) -The **model-facing filesystem tools** — `list`, `read`, `write`, `edit` — and their **executor**. This is the consumer layer of the filesystem stack: it owns tool names, JSON schemas, argument validation, prompt sections, **read windowing**, **listing order**, and result formatting. It reads/writes/edits through the `ctx.fs` provider seam ([`@deepseek-ai/dsh-fs`](../fs)) **directly** — it injects `fs` (plus `tools`/`systemPrompt`), **not** a policy service. The freshness/observation policy is contributed by a separate plugin ([`@deepseek-ai/dsh-fs-policy`](../fs-policy)) through the `fs/*` event gate; the tool is not method-coupled to it. +The **model-facing filesystem tools** — `read`, `write`, `edit` — and their **executor**. This is the consumer layer of the filesystem stack: it owns tool names, JSON schemas, argument validation, prompt sections, **read windowing**, and result formatting. It reads/writes/edits through the `ctx.fs` provider seam ([`@deepseek-ai/dsh-fs`](../fs)) **directly** — it injects `fs` (plus `tools`/`systemPrompt`), **not** a policy service. The freshness/observation policy is contributed by a separate plugin ([`@deepseek-ai/dsh-fs-policy`](../fs-policy)) through the `fs/*` event gate; the tool is not method-coupled to it. ```ts ignore-check // Default deployment: a ctx.fs provider, the policy plugin, then the tools. await ctx.plugin(LocalFileSystem, { cwd: process.cwd() }) // @deepseek-ai/dsh-fs-local await ctx.plugin(FsPolicy) // @deepseek-ai/dsh-fs-policy (policy gate) -await ctx.plugin(ToolFs) // this package — registers list/read/write/edit +await ctx.plugin(ToolFs) // this package — registers read/write/edit ``` `@deepseek-ai/dsh-fs-policy` is **optional**: omit it and the tools run against the bare provider (unconditional write/overwrite/edit, no observed-state). A deployment that loads these tools is expected to also load it, so the behavior is read-before-write/edit. ## Config -All keys are optional; the defaults are the shipped listing and read caps. +All keys are optional; the defaults are the shipped read caps. | Key | Default | Meaning | |---|---|---| -| `listMaxEntries` | `200` | Maximum entries one `list` page returns; the footer reports complete size and composition plus a next offset when more remain. | | `readLimit` | `2000` | Default and maximum lines returned by one `read` call (the tool schema advertises it as the `limit` default). | | `readMaxLineLength` | `2000` | Characters kept per line before truncation (the suffix names the cap). | | `readMaxBytes` | `51200` | Byte cap on one `read` call's selected lines; overflow ends the window with a "capped" footer. | @@ -29,20 +28,18 @@ All keys are optional; the defaults are the shipped listing and read caps. | Tool | Arguments | Behavior | |---|---|---| -| `list` | `path?`, `offset?` | One page of direct children with their type, defaulting to the session workspace and entry 1. Ordered directories first, then files, then non-regular children, each alphabetical; when more remain, continue from the footer's next offset. | | `read` | `file_path`, `offset?`, `limit?` | Line-numbered UTF-8 content with a pagination footer. `offset` is 1-based; `limit` defaults to and caps at the configured `readLimit` (2000). | | `write` | `file_path`, `content` | Create or fully replace a file. With the policy plugin: overwriting an existing file requires a prior `read` at the unchanged version; creating a new file does not. Without it: unconditional. | | `edit` | `file_path`, non-empty `old_string`, `new_string`, `replace_all?` | Literal replacement; unique match required unless `replace_all` is true. With the policy plugin: requires a prior `read` (any window) and the file unchanged since. Without it: unconditional. | Field names are snake_case to match Claude Code and existing harness tool schemas. -Canonical successes are `list` → `{ path, offset, entries: [{ name, type }], totalEntries, counts: { directories, files, other } }`, `read` → `{ path, offset, lines: [{ number, text }], totalLines }`, `write` → `{ path, operation: 'create' | 'update', before: string | null, after }`, and `edit` → `{ path, before, after }`. `list.entries` is one bounded page; `type` is `file`, `directory`, or `other`, while its totals describe the complete directory. Native renderers preserve the listing/read envelopes and mutation acknowledgements below. Write/edit derive replayable diff-card metadata from these values; the values themselves are execution-local and are not added to `tool/result`. +Canonical successes are `read` → `{ path, offset, lines: [{ number, text }], totalLines }`, `write` → `{ path, operation: 'create' | 'update', before: string | null, after }`, and `edit` → `{ path, before, after }`. Native renderers preserve the line-numbered read and mutation acknowledgements below. Write/edit derive replayable diff-card metadata from these values; the values themselves are execution-local and are not added to `tool/result`. ## The tool is the executor; policy is an event gate The tools do **not** inject a policy service or inspect any cache. Each tool resolves the path via `ctx.fs.resolve(path, { cwd, signal })` — passing the calling agent's session cwd (`exec.agent.session.header.cwd`) so a relative path resolves against the session's workspace, matching `dsh-tool-bash`, and forwarding tool cancellation through resolution (see [the per-session cwd Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md)) — then: -- **list** — one `ctx.fs.listDir`; the seam already answers absence with `FS_NOT_FOUND` and a non-directory target with `FS_NOT_DIRECTORY`, so no probe precedes it. No `fs/observed`: a listing reads no file content and must not satisfy the read-before-write gate. (0 stat.) - **read** — one `ctx.fs.stat` (type + size routing + version), then `readText`/`streamText`, then builds the line window, then emits `fs/observed` with a plain `ctx.emit`. (1 stat.) - **write** — `ctx.waterfall('fs/write-intent', target, exec, () => undefined)` for the optional guard, then `ctx.fs.writeText(target, content, intent)`, then `fs/observed`. (0 stat.) - **edit** — `ctx.waterfall('fs/edit-intent', target, exec, () => undefined)` for the optional guard, then `ctx.fs.editText(target, edit, intent)`, then `fs/observed`. (0 stat.) @@ -53,9 +50,9 @@ The tool passes `exec` (the tool-execution context) as the opaque `actor` on eve `fs/observed` fires AFTER the read/write/edit already succeeded, via a plain `ctx.emit`. A listener is contractually a synchronous, side-effect-only recorder (`@deepseek-ai/dsh-fs-policy`'s is a `WeakMap.set`); the tool does not guard the emit, so a listener that throws would surface as the tool's `isError` result — async or fallible observation does not belong on this event. -`list` and `read` opt into concurrent scheduling — `list` mutates nothing at all, and `read`'s only mutation is the synchronous version recorder. Recorder races fail closed when a later `write` or `edit` re-checks the version under its target lock; both mutation tools remain exclusive. See the [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md). +`read` opts into concurrent scheduling because its only mutation is the synchronous version recorder. Recorder races fail closed when a later `write` or `edit` re-checks the version under its target lock; both mutation tools remain exclusive. See the [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md). -The package root exports only the Cordis plugin contract (`name`, `inject`, `Config`, and `apply`). Pure presentation lives beside the executors and is independently unit-tested: read windowing and output formatting in `src/read-render.ts`, listing order and envelope in `src/list-render.ts` (both Cordis-free); `src/list.ts`/`read.ts`/`write.ts`/`edit.ts` are the tool executors and `src/index.ts` composes them. +The package root exports only the Cordis plugin contract (`name`, `inject`, `Config`, and `apply`). Read rendering (line windowing + output formatting) lives in `src/read-render.ts` (Cordis-free, independently unit-tested); `src/read.ts`/`write.ts`/`edit.ts` are the tool executors and `src/index.ts` composes them. ## Model Experience @@ -63,13 +60,7 @@ The package root exports only the Cordis plugin contract (`name`, `inject`, `Con #### What the model sees -Every request in this plugin's registration scope receives the independently registered list, read, write, and edit guidance below. Scoped tool restrictions can hide schemas without removing these sections. - -##### List guidance - -```markdown -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. -``` +Every request in this plugin's registration scope receives the independently registered read, write, and edit guidance below. Scoped tool restrictions can hide schemas without removing these sections. ##### Read guidance @@ -101,7 +92,7 @@ Prefix-stable while the plugin scope and guidance text are unchanged. Tool restr #### What the model sees -The model sees the generated [`list`, `read`, `write`, and `edit` schemas](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs), with snake_case arguments. Scoped tool restrictions can remove any definition for one agent. +The model sees the generated [`read`, `write`, and `edit` schemas](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs), with snake_case arguments. Scoped tool restrictions can remove any definition for one agent. #### Token effect @@ -111,20 +102,6 @@ Fixed schema cost on every request in that tool view. Prefix-stable while the visible tool definitions and order are unchanged. Registration lifecycle or scoped restrictions may invalidate reuse from the first changed schema token. -### List result - -#### What the model sees - -A successful listing is ``, newline, `directory`, newline, ``, one line per page entry, a blank line, one footer, and ``. A directory carries a trailing `/`, a non-regular child a trailing `@`, and a regular file neither. A name is emitted verbatim unless it could make the listing say something untrue — a control character, a leading `"`, a backslash, ` entries: directories, files)` with optional `, other`, or `(Showing entries - of : . Use offset= to continue.)`; the final page omits the continuation sentence. Every page states the complete count and composition. - -#### Token effect - -Listing output and its canonical `entries` page are capped by `listMaxEntries`; the retained call and result are resent until compaction. - -#### KV Cache effect - -Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. - ### Read result #### What the model sees @@ -157,7 +134,7 @@ Append-only; newly visible content follows the reusable request prefix and does #### What the model sees -Failures are normalized as `Error: `. This package's stable validation and read messages are `file_path must be a non-empty string`, `path must be a non-empty string when given`, `offset must be a positive integer`, `limit must be less than or equal to `, `old_string must be a non-empty string`, `old_string and new_string must differ`, `cannot read "": not found`, `cannot read "": not a regular file`, `offset is out of range for "" ( entries)`, and the corresponding ` lines` read error; provider and policy templates are quoted in their package READMEs. +Failures are normalized as `Error: `. This package's stable validation and read messages are `file_path must be a non-empty string`, `limit must be less than or equal to `, `old_string must be a non-empty string`, `old_string and new_string must differ`, `cannot read "": not found`, `cannot read "": not a regular file`, and `offset is out of range for "" ( lines)`; provider and policy templates are quoted in their package READMEs. #### Token effect @@ -169,6 +146,6 @@ Append-only; newly visible content follows the reusable request prefix and does ## Known Limitations and Deferred Work -- **`list` reads one directory level** — recursion and per-directory child counts are absent; offset pagination traverses only the current directory's ordered direct children. +- **No model-facing directory listing ships** — `ctx.fs.listDir` serves provider code such as skill discovery, while the sibling [`dsh-tool-fs-search`](../tool-fs-search/) package supplies bash-backed `glob` and `grep` rather than extending the filesystem seam. - **`read` handles UTF-8 text files only** — binary-safe reads and PDF/image/multimodal content are deferred; a directory target is `FS_NOT_REGULAR_FILE`. -- **No timeout surface** — `list`/`read`/`write`/`edit` take no timeout argument and declare no `timeout-policy` budget; cancellation rides `exec.signal` only (the deliberate [fs-family stance](../README.md)). +- **No timeout surface** — `read`/`write`/`edit` take no timeout argument and declare no `timeout-policy` budget; cancellation rides `exec.signal` only (the deliberate [fs-family stance](../README.md)). diff --git a/packages/fs/tool-fs/README.zh.md b/packages/fs/tool-fs/README.zh.md index 567c8e0df5..f94a903c9c 100644 --- a/packages/fs/tool-fs/README.zh.md +++ b/packages/fs/tool-fs/README.zh.md @@ -2,24 +2,23 @@ [English](README.md) | 中文 -**面向模型的文件系统工具**（`list`、`read`、`write`、`edit`）及其**执行器**。这是文件系统栈的消费方层：拥有工具名称、JSON schema、参数校验、提示词段、**读取窗口逻辑**、**列出顺序** 和结果格式化。它**直接** 通过 `ctx.fs` 提供方 seam（[`@deepseek-ai/dsh-fs`](../fs)）读取/写入/编辑：注入 `fs`（以及 `tools`/`systemPrompt`），**不** 注入政策服务。新鲜度/观察政策由独立插件（[`@deepseek-ai/dsh-fs-policy`](../fs-policy)）通过 `fs/*` 事件门禁贡献；工具不与其方法耦合。 +**面向模型的文件系统工具**（`read`、`write`、`edit`）及其**执行器**。这是文件系统栈的消费方层：拥有工具名称、JSON schema、参数校验、提示词段、**读取窗口逻辑** 和结果格式化。它**直接** 通过 `ctx.fs` 提供方 seam（[`@deepseek-ai/dsh-fs`](../fs)）读取/写入/编辑：注入 `fs`（以及 `tools`/`systemPrompt`），**不** 注入政策服务。新鲜度/观察政策由独立插件（[`@deepseek-ai/dsh-fs-policy`](../fs-policy)）通过 `fs/*` 事件门禁贡献；工具不与其方法耦合。 ```ts ignore-check // Default deployment: a ctx.fs provider, the policy plugin, then the tools. await ctx.plugin(LocalFileSystem, { cwd: process.cwd() }) // @deepseek-ai/dsh-fs-local await ctx.plugin(FsPolicy) // @deepseek-ai/dsh-fs-policy (policy gate) -await ctx.plugin(ToolFs) // this package — registers list/read/write/edit +await ctx.plugin(ToolFs) // this package — registers read/write/edit ``` `@deepseek-ai/dsh-fs-policy` 是**可选的**：省略时，工具直接使用裸提供方（无条件写入/覆盖/编辑，无已观察状态）。加载这些工具的部署也应加载该插件，从而提供编辑前读取行为。 ## 配置 -所有键均为可选；默认值是随产品交付的列出与读取上限。 +所有键均为可选；默认值是随产品交付的读取上限。 | 键 | 默认值 | 含义 | |---|---|---| -| `listMaxEntries` | `200` | 单个 `list` 页面返回的最大条目数；footer 会报告完整规模与构成，并在仍有条目时给出下一 offset。 | | `readLimit` | `2000` | 一次 `read` 调用返回的默认和最大行数（工具 schema 将其声明为 `limit` 默认值）。 | | `readMaxLineLength` | `2000` | 每行截断前保留的字符数（后缀会说明上限）。 | | `readMaxBytes` | `51200` | 一次 `read` 调用所选行的字节上限；溢出时以「已达上限」footer 结束窗口。 | @@ -29,20 +28,18 @@ await ctx.plugin(ToolFs) // this package — re | 工具 | 参数 | 行为 | |---|---|---| -| `list` | `path?`、`offset?` | 单个目录的一页直接子项及其类型，默认取会话工作区并从第 1 个条目开始。顺序为先目录、再文件、最后非常规子项，各组内按字母序排列；仍有条目时按 footer 给出的下一 offset 继续。 | | `read` | `file_path`、`offset?`、`limit?` | 带行号的 UTF-8 内容和分页 footer。`offset` 从 1 开始；`limit` 默认为配置的 `readLimit`（2000），上限也为该值。 | | `write` | `file_path`、`content` | 创建文件或完整替换文件。有政策插件时：覆盖现有文件要求先在未变版本上执行 `read`；创建新文件不需要。没有插件时：无条件执行。 | | `edit` | `file_path`、非空 `old_string`、`new_string`、`replace_all?` | 字面量替换；除非 `replace_all` 为 true，否则要求唯一匹配。有政策插件时：要求先执行 `read`（任何窗口），且文件此后未变。没有插件时：无条件执行。 | 字段名使用 snake_case，与 Claude Code 和现有 harness 工具 schema 一致。 -规范成功值分别为：`list` → `{ path, offset, entries: [{ name, type }], totalEntries, counts: { directories, files, other } }`，`read` → `{ path, offset, lines: [{ number, text }], totalLines }`，`write` → `{ path, operation: 'create' | 'update', before: string | null, after }`，`edit` → `{ path, before, after }`。`list.entries` 是一个有界页面；`type` 为 `file`、`directory` 或 `other`，而总计信息描述的是完整目录。Native 渲染器会保留下方的列出/读取包络和变更确认。写入/编辑从这些值派生可回放的 diff 卡片元数据；值本身仅用于执行，不会添加到 `tool/result`。 +规范成功值分别为：`read` → `{ path, offset, lines: [{ number, text }], totalLines }`，`write` → `{ path, operation: 'create' | 'update', before: string | null, after }`，`edit` → `{ path, before, after }`。Native 渲染器会保留下方带行号的读取结果和变更确认。写入/编辑从这些值派生可回放的 diff 卡片元数据；值本身仅用于执行，不会添加到 `tool/result`。 ## 工具就是执行器；政策是事件门禁 工具**不** 注入政策服务，也不检查任何缓存。每个工具通过 `ctx.fs.resolve(path, { cwd, signal })` 解析路径；它会传入调用 agent（智能体）的会话 cwd（`exec.agent.session.header.cwd`），使相对路径以会话工作区为基准解析并与 `dsh-tool-bash` 一致，同时把工具取消转发到解析过程（见[每会话 cwd Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md)）。随后执行： -- **list**：一次 `ctx.fs.listDir`；seam 已经把不存在报告为 `FS_NOT_FOUND`、把非目录目标报告为 `FS_NOT_DIRECTORY`，因此前面不需要任何探测。不发出 `fs/observed`：列出不读取任何文件内容，也不得满足编辑前读取门禁。（0 次 stat。） - **read**：一次 `ctx.fs.stat`（用于类型、大小路由和版本），随后调用 `readText`/`streamText`，构建行窗口，再发出 `fs/observed`，使用普通 `ctx.emit`。（1 次 stat。） - **write**：调用 `ctx.waterfall('fs/write-intent', target, exec, () => undefined)` 取得可选防护，然后调用 `ctx.fs.writeText(target, content, intent)`，再发出 `fs/observed`。（0 次 stat。） - **edit**：调用 `ctx.waterfall('fs/edit-intent', target, exec, () => undefined)` 取得可选防护，然后调用 `ctx.fs.editText(target, edit, intent)`，再发出 `fs/observed`。（0 次 stat。） @@ -53,9 +50,9 @@ await ctx.plugin(ToolFs) // this package — re `fs/observed` 在读取/写入/编辑已经成功之后，通过普通 `ctx.emit` 发出。监听器的契约是同步且只有副作用的记录器（`@deepseek-ai/dsh-fs-policy` 使用 `WeakMap.set`）；工具不保护这次发出，因此监听器抛出会作为工具的 `isError` 结果出现。异步或可能失败的观察不属于该事件。 -`list` 与 `read` 都允许并发调度：`list` 完全不做任何变更，而 `read` 的唯一变更是同步版本记录器。稍后的 `write` 或 `edit` 会在目标锁内重新检查版本，因此记录器竞态会以拒绝方式关闭；两个变更工具仍保持互斥。见[并行工具调用 Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md)。 +`read` 允许并发调度，因为其唯一变更是同步版本记录器。稍后的 `write` 或 `edit` 会在目标锁内重新检查版本，因此记录器竞态会以拒绝方式关闭；两个变更工具仍保持互斥。见[并行工具调用 Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md)。 -包根目录只导出 Cordis 插件契约（`name`、`inject`、`Config` 和 `apply`）。纯展示逻辑与执行器并列存放并单独进行单元测试：读取窗口与输出格式化位于 `src/read-render.ts`，列出顺序与包络位于 `src/list-render.ts`（两者均不依赖 Cordis）；`src/list.ts`/`read.ts`/`write.ts`/`edit.ts` 是工具执行器，`src/index.ts` 负责组合。 +包根目录只导出 Cordis 插件契约（`name`、`inject`、`Config` 和 `apply`）。读取渲染（行窗口与输出格式化）位于 `src/read-render.ts`（不依赖 Cordis，单独进行单元测试）；`src/read.ts`/`write.ts`/`edit.ts` 是工具执行器，`src/index.ts` 负责组合。 ## 模型体验 @@ -63,13 +60,7 @@ await ctx.plugin(ToolFs) // this package — re #### 模型看到的内容 -该插件注册作用域内的每个请求都会收到下方独立注册的 list、read、write 与 edit 指导。作用域工具限制可以隐藏 schema，而不移除这些段。 - -##### List 指导 - -```markdown -Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. When a result is capped, continue with the offset named in its footer. -``` +该插件注册作用域内的每个请求都会收到下方独立注册的 read、write 与 edit 指导。作用域工具限制可以隐藏 schema，而不移除这些段。 ##### Read 指导 @@ -101,7 +92,7 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces #### 模型看到的内容 -模型会看到已生成的 [`list`、`read`、`write` 和 `edit` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs)，参数使用 snake_case。作用域工具限制可以为某个 agent 移除任一定义。 +模型会看到已生成的 [`read`、`write` 和 `edit` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs)，参数使用 snake_case。作用域工具限制可以为某个 agent 移除任一定义。 #### Token 影响 @@ -111,20 +102,6 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces 只要可见工具定义和顺序不变，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。 -### 列出结果 - -#### 模型看到的内容 - -成功列出结果为 ``、换行、`directory`、换行、``、页面中的每个条目一行、一个空行、一条 footer 和 ``。目录带尾部 `/`，非常规子项带尾部 `@`，常规文件两者都不带。条目名默认原样输出，只有当它可能让列出结果失真时才转为 JSON 字符串并中和 ` entries: directories, files)`（可选追加 `, other`），或 `(Showing entries - of : . Use offset= to continue.)`；最后一页省略继续提示。每一页都会说明完整计数与构成。 - -#### Token 影响 - -列出输出及其规范 `entries` 页面受 `listMaxEntries` 限制；保留的调用与结果会反复发送，直到上下文压缩。 - -#### 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。 - ### 读取结果 #### 模型看到的内容 @@ -157,7 +134,7 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces #### 模型看到的内容 -失败会规范化为 `Error: `。本包稳定的校验和读取消息是 `file_path must be a non-empty string`、`path must be a non-empty string when given`、`offset must be a positive integer`、`limit must be less than or equal to `、`old_string must be a non-empty string`、`old_string and new_string must differ`、`cannot read "": not found`、`cannot read "": not a regular file`、`offset is out of range for "" ( entries)`，以及对应的 ` lines` 读取错误；提供方和政策模板在各自包的 README 中逐字列出。 +失败会规范化为 `Error: `。本包稳定的校验和读取消息是 `file_path must be a non-empty string`、`limit must be less than or equal to `、`old_string must be a non-empty string`、`old_string and new_string must differ`、`cannot read "": not found`、`cannot read "": not a regular file` 和 `offset is out of range for "" ( lines)`；提供方和政策模板在各自包的 README 中逐字列出。 #### Token 影响 @@ -169,6 +146,6 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces ## 已知限制与延期工作 -- **`list` 只读取一层目录**：不提供递归和逐目录子项计数；offset 分页只遍历当前目录中按顺序排列的直接子项。 +- **未交付面向模型的目录列出工具**：`ctx.fs.listDir` 服务于 skill（技能）发现等提供方代码，同级 [`dsh-tool-fs-search`](../tool-fs-search/) 包则提供基于 bash 的 `glob` 与 `grep`，而不是扩展文件系统 seam。 - **`read` 只处理 UTF-8 文本文件**：二进制安全读取和 PDF/图像/多模态内容均延期处理；目录目标为 `FS_NOT_REGULAR_FILE`。 -- **没有超时接口**：`list`/`read`/`write`/`edit` 不接受超时参数，也不声明 `timeout-policy` 预算；取消只通过 `exec.signal` 传递（见有意采用的 [fs 能力族立场](../README.md)）。 +- **没有超时接口**：`read`/`write`/`edit` 不接受超时参数，也不声明 `timeout-policy` 预算；取消只通过 `exec.signal` 传递（见有意采用的 [fs 能力族立场](../README.md)）。 diff --git a/packages/fs/tool-fs/package.json b/packages/fs/tool-fs/package.json index 936d125013..737f7ac26b 100644 --- a/packages/fs/tool-fs/package.json +++ b/packages/fs/tool-fs/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-tool-fs", - "description": "Model-facing filesystem tools (list, read, write, edit) over the DeepSeek Harness filesystem seam (ctx.fs)", + "description": "Model-facing filesystem tools (read, write, edit) over the DeepSeek Harness filesystem seam (ctx.fs)", "version": "0.0.1", "private": true, "type": "module", diff --git a/packages/fs/tool-fs/src/index.ts b/packages/fs/tool-fs/src/index.ts index 7890d5084d..a4c96d606b 100644 --- a/packages/fs/tool-fs/src/index.ts +++ b/packages/fs/tool-fs/src/index.ts @@ -1,19 +1,16 @@ /** - * Model-facing list, read, write, and edit tools over `ctx.fs`. This package owns schemas, - * validation, read windows, listing order, formatting, and observation events, never a concrete - * provider. An optional event policy supplies mutation guards; without one the tools use - * unconditional provider calls. + * Model-facing read, write, and edit tools over `ctx.fs`. This package owns schemas, validation, + * read windows, formatting, and observation events, never a concrete provider. An optional + * event policy supplies mutation guards; without one the tools use unconditional provider calls. * @module @deepseek-ai/dsh-tool-fs */ import type { Context } from 'cordis' import z from 'schemastery' import type {} from '@deepseek-ai/dsh-user-approval' -import { applyListTool } from './list.ts' import { applyReadTool, READ_LIMIT, STREAM_MIN_SIZE } from './read.ts' import { applyWriteTool } from './write.ts' import { applyEditTool } from './edit.ts' -import { LIST_MAX_ENTRIES } from './list-render.ts' import { READ_MAX_BYTES, READ_MAX_LINE_LENGTH } from './read-render.ts' import { FsSandboxSurface } from './sandbox.ts' @@ -25,8 +22,6 @@ export const inject = ['tools', 'fs', 'systemPrompt'] /** Plugin config (all optional — `Config` supplies the defaults). */ export interface Config { - /** Maximum entries one `list` page returns; the footer still reports the complete count. */ - listMaxEntries?: number /** Default and maximum number of lines returned by one `read` call. */ readLimit?: number /** Maximum characters returned for a single line before truncation. */ @@ -38,7 +33,6 @@ export interface Config { } export const Config: z = z.object({ - listMaxEntries: z.number().default(LIST_MAX_ENTRIES), readLimit: z.number().default(READ_LIMIT), readMaxLineLength: z.number().default(READ_MAX_LINE_LENGTH), readMaxBytes: z.number().default(READ_MAX_BYTES), @@ -48,23 +42,21 @@ export const Config: z = z.object({ /** The shape after schemastery applied the defaults. */ type ResolvedConfig = Required -/** Every read or listing cap counts lines/chars/bytes/entries — a positive integer, or windowing arithmetic misbehaves silently. */ +/** Every read cap counts lines/chars/bytes — a positive integer, or windowing arithmetic misbehaves silently. */ function assertPositiveInteger(name: string, value: number): void { if (!Number.isInteger(value) || value < 1) { throw new Error(`tool-fs: ${name} must be a positive integer`) } } -/** Register the full `list`/`read`/`write`/`edit` filesystem tool suite. */ +/** Register the full `read`/`write`/`edit` filesystem tool suite. */ export function apply(ctx: Context, config: Config): void { // schemastery (Config) has already filled every defaulted field. const resolved = config as ResolvedConfig - assertPositiveInteger('listMaxEntries', resolved.listMaxEntries) assertPositiveInteger('readLimit', resolved.readLimit) assertPositiveInteger('readMaxLineLength', resolved.readMaxLineLength) assertPositiveInteger('readMaxBytes', resolved.readMaxBytes) assertPositiveInteger('readStreamMinSize', resolved.readStreamMinSize) - applyListTool(ctx, { maxEntries: resolved.listMaxEntries }) applyReadTool(ctx, { limit: resolved.readLimit, maxLineLength: resolved.readMaxLineLength, diff --git a/packages/fs/tool-fs/src/list-render.ts b/packages/fs/tool-fs/src/list-render.ts deleted file mode 100644 index 86b57d02b3..0000000000 --- a/packages/fs/tool-fs/src/list-render.ts +++ /dev/null @@ -1,137 +0,0 @@ -/** - * Pure directory-listing presentation: order direct children, count complete - * composition, and render a bounded page without allowing filesystem text to - * forge the result envelope. - * @module @deepseek-ai/dsh-tool-fs/list-render - */ - -/** Default and maximum number of entries one `list` call returns (the `listMaxEntries` config). */ -export const LIST_MAX_ENTRIES = 200 - -/** One direct child in a directory listing. */ -export interface ListedEntry { - /** Basename of the child inside the listed directory. */ - name: string - /** Whether the child is a regular file, a directory, or something else. */ - type: 'file' | 'directory' | 'other' -} - -/** Complete-listing composition retained on every page. */ -export interface ListCounts { - directories: number - files: number - other: number -} - -/** Canonical bounded result returned by one `list` call. */ -export interface ListPage { - /** Backend display path of the listed directory. */ - path: string - /** 1-based index of the first returned entry. */ - offset: number - /** Current page in directory-first, name-sorted order. */ - entries: ListedEntry[] - /** Number of direct children in the complete listing. */ - totalEntries: number - /** Composition of the complete listing, not only this page. */ - counts: ListCounts -} - -/** - * Sort directories before files before other entries, each group by name. - * @param entries - direct children in provider order. - * @returns a new directory-first array without mutating `entries`. - */ -export function orderEntries(entries: readonly T[]): T[] { - const rank = { directory: 0, file: 1, other: 2 } - return [...entries].sort((a, b) => rank[a.type] - rank[b.type] || a.name.localeCompare(b.name)) -} - -/** - * Count every entry type in a complete listing. - * @param entries - every direct child in the listed directory. - * @returns the complete directory/file/other composition. - */ -export function countEntries(entries: readonly ListedEntry[]): ListCounts { - const counts: ListCounts = { directories: 0, files: 0, other: 0 } - for (const entry of entries) { - if (entry.type === 'directory') counts.directories += 1 - else if (entry.type === 'file') counts.files += 1 - else counts.other += 1 - } - return counts -} - -/** `1 directory` / `4 directories`. */ -function count(n: number, singular: string, plural: string): string { - return `${n} ${n === 1 ? singular : plural}` -} - -/** Complete-listing composition as model-facing prose. */ -function breakdown(counts: ListCounts): string { - const parts = [ - count(counts.directories, 'directory', 'directories'), - count(counts.files, 'file', 'files'), - ] - if (counts.other > 0) parts.push(`${counts.other} other`) - return parts.join(', ') -} - -/** - * Names this renderer cannot emit verbatim, because POSIX allows every byte but - * `/` and NUL in a name and each of these would make the listing say something - * untrue: - * - * - a control character (a newline above all) splits one entry across lines; - * - ` 1 || page.entries.length < page.totalEntries - ? `(Showing entries ${page.offset}-${end} of ${page.totalEntries}: ${breakdown(page.counts)}.` - + (end < page.totalEntries ? ` Use offset=${end + 1} to continue.)` : ')') - : `(${count(page.totalEntries, 'entry', 'entries')}: ${breakdown(page.counts)})` - const body = page.entries.length > 0 - ? `${page.entries.map(entry => `${renderName(entry.name)}${suffix[entry.type]}`).join('\n')}\n\n${footer}` - : footer - return `${renderName(page.path)} -directory - -${body} -` -} diff --git a/packages/fs/tool-fs/src/list.ts b/packages/fs/tool-fs/src/list.ts deleted file mode 100644 index 270e2803b8..0000000000 --- a/packages/fs/tool-fs/src/list.ts +++ /dev/null @@ -1,150 +0,0 @@ -/** - * Model-facing directory listing. It enumerates ONE directory level through the - * provider seam's `listDir`, orders children so a capped view keeps the - * navigable structure, and renders the entries with their type. - * - * This is the orientation tool: `glob` and `grep` answer "where is the thing I - * can already name", while `list` answers "what is here at all". `rg --files` - * never emits directories, so no pattern makes `glob` describe a directory's - * shape — the gap this tool closes. - * @module @deepseek-ai/dsh-tool-fs/list - */ - -import type { Context } from 'cordis' -import { defineTool } from '@deepseek-ai/dsh-tools' -import type { GenericCallView } from '@deepseek-ai/dsh-tools' -import { FsError } from '@deepseek-ai/dsh-fs' -import type {} from '@deepseek-ai/dsh-fs' -import type {} from '@deepseek-ai/dsh-system-prompt' -import { countEntries, formatListOutput, orderEntries } from './list-render.ts' -import { sessionResolveOptions } from './session-cwd.ts' - -/** Resolved list-tool caps — plugin config after defaulting (see `Config` in index.ts). */ -export interface ListToolCaps { - /** Maximum entries returned on one page; the footer still reports complete size and composition. */ - maxEntries: number -} - -/** Validated `list` arguments after defaulting. */ -export interface ListInput { - /** Directory to list; `.` means the calling agent's session workspace. */ - path: string - /** 1-based first entry to return from the directory-first ordering. */ - offset: number -} - -/** - * Validate value constraints the schema DSL can't express, and default an - * omitted `path` to `.` — the session workspace, so "what is in this project" - * needs no argument at all. - * - * @param args - the schema-validated `list` arguments. - * @returns the accepted input with `path` and `offset` defaulted. - */ -export function parseListArgs(args: { path?: string; offset?: number }): ListInput { - if (args.path !== undefined && args.path.trim().length === 0) throw new Error('path must be a non-empty string when given') - const offset = args.offset ?? 1 - if (!Number.isInteger(offset) || offset < 1) throw new Error('offset must be a positive integer') - return { path: args.path ?? '.', offset } -} - -/** - * Pending-call presentation: a generic card titled by the directory, with a - * follow-along location so a capable editor can reveal it. - * - * @param args - the raw tool arguments; `path` and `offset` feed the title. - * @returns the generic card view shown while the call runs. - */ -export function presentListCall(args: { path?: string; offset?: number }): GenericCallView { - const path = args.path ?? '.' - const window = args.offset !== undefined ? ` (from entry ${args.offset})` : '' - return { card: 'generic', title: `List ${path}${window}`, kind: 'read', locations: [{ path }] } -} - -/** - * Register the `list` tool and its system-prompt guidance. - * - * @param ctx - the plugin context; registrations are effects scoped to it, and execution uses its `fs` service. - * @param caps - the deployment's resolved list caps (plugin config after defaulting). - */ -export function applyListTool(ctx: Context, caps: ListToolCaps): void { - ctx.systemPrompt.section({ - name: 'tool:list', - order: 99, - text: 'Use the list tool — not shell ls — to see what a directory contains. It returns the direct children of one directory, files and subdirectories alike, ' - + 'and defaults to the session workspace, so it is the first step for orienting in an unfamiliar project. ' - + 'When a result is capped, continue with the offset named in its footer.', - }) - - ctx.tools.register(defineTool({ - name: 'list', - description: 'List the direct children of one directory, with their type. ' - + `Entries are directories first, then files, each alphabetical; up to ${caps.maxEntries} are returned from the requested offset, and the footer gives the complete count plus a next offset when more remain. ` - + 'It includes subdirectories and is the tool for seeing one directory\'s contents.', - parameters: { - path: { type: 'string', description: 'Directory to list. Defaults to the session workspace; a relative path resolves against it.' }, - offset: { type: 'number', description: '1-based first entry to return. Defaults to 1; use the footer value to continue.' }, - }, - output: { - schema: { - type: 'object', - additionalProperties: false, - properties: { - path: { type: 'string', required: true }, - offset: { type: 'integer', required: true }, - entries: { - type: 'array', - required: true, - items: { - type: 'object', - additionalProperties: false, - properties: { - name: { type: 'string', required: true }, - type: { type: 'string', required: true, enum: ['file', 'directory', 'other'] }, - }, - }, - }, - totalEntries: { type: 'integer', required: true }, - counts: { - type: 'object', - required: true, - additionalProperties: false, - properties: { - directories: { type: 'integer', required: true }, - files: { type: 'integer', required: true }, - other: { type: 'integer', required: true }, - }, - }, - }, - }, - render: (_args, value) => [{ type: 'text', text: formatListOutput(value) }], - }, - // Listing reads directory metadata only: no content, no version recorded, - // nothing a concurrent call could observe out of order. - isConcurrencySafe: () => true, - async execute(args, exec) { - const input = parseListArgs(args) - const target = await ctx.fs.resolve(input.path, sessionResolveOptions(exec, input.path)) - // No stat first: the seam already answers absence with FS_NOT_FOUND and a - // non-directory target with FS_NOT_DIRECTORY, so a probe would only add a - // round-trip and a second source of truth. (0 stat.) - const entries = orderEntries(await ctx.fs.listDir(target, exec.signal)) - if (input.offset > entries.length && !(entries.length === 0 && input.offset === 1)) { - throw new FsError( - `offset ${input.offset} is out of range for "${target.displayPath}" (${entries.length} entries)`, - 'FS_NOT_FOUND', - ) - } - return { - path: target.displayPath, - offset: input.offset, - entries: entries - .slice(input.offset - 1, input.offset - 1 + caps.maxEntries) - .map(({ name, type }) => ({ name, type })), - totalEntries: entries.length, - counts: countEntries(entries), - } - }, - presentCall: presentListCall, - })) -} diff --git a/packages/fs/tool-fs/tests/list-render.spec.ts b/packages/fs/tool-fs/tests/list-render.spec.ts deleted file mode 100644 index 792c91bd18..0000000000 --- a/packages/fs/tool-fs/tests/list-render.spec.ts +++ /dev/null @@ -1,79 +0,0 @@ -/** - * Pure listing-presentation tests: display ordering and the model-facing - * envelope, exercised without a context or provider. - */ - -import { describe, expect, it } from 'vitest' -import { countEntries, formatListOutput, orderEntries } from '../src/list-render.ts' -import type { ListedEntry, ListPage } from '../src/list-render.ts' - -const entry = (name: string, type: ListedEntry['type'] = 'file'): ListedEntry => ({ name, type }) - -function page(entries: ListedEntry[], options: { offset?: number; totalEntries?: number; all?: ListedEntry[] } = {}): ListPage { - const all = options.all ?? entries - return { - path: '/w', - offset: options.offset ?? 1, - entries, - totalEntries: options.totalEntries ?? all.length, - counts: countEntries(all), - } -} - -describe('orderEntries', () => { - it('groups directories, then files, then other, each by name', () => { - const ordered = orderEntries([ - entry('zeta.txt'), - entry('socket', 'other'), - entry('beta'), - entry('src', 'directory'), - entry('assets', 'directory'), - ]) - expect(ordered.map(e => e.name)).toEqual(['assets', 'src', 'beta', 'zeta.txt', 'socket']) - }) - - it('leaves the input array untouched and preserves extra entry fields', () => { - const input = [{ name: 'b', type: 'file' as const, size: 2 }, { name: 'a', type: 'file' as const, size: 1 }] - const ordered = orderEntries(input) - expect(input.map(e => e.name)).toEqual(['b', 'a']) - expect(ordered).toEqual([{ name: 'a', type: 'file', size: 1 }, { name: 'b', type: 'file', size: 2 }]) - }) -}) - -describe('formatListOutput', () => { - it('marks directories and non-regular children, and counts the whole listing', () => { - expect(formatListOutput(page([entry('src', 'directory'), entry('a.txt'), entry('sock', 'other')]))).toBe(`/w -directory - -src/ -a.txt -sock@ - -(3 entries: 1 directory, 1 file, 1 other) -`) - }) - - it('omits the "other" clause when every child is a file or a directory', () => { - expect(formatListOutput(page([entry('a.txt'), entry('b.txt')]))).toContain('(2 entries: 0 directories, 2 files)') - }) - - it('says a one-entry listing in the singular', () => { - expect(formatListOutput(page([entry('only', 'directory')]))).toContain('(1 entry: 1 directory, 0 files)') - }) - - it('states the complete size and composition when the view is capped', () => { - const entries = [entry('src', 'directory'), ...Array.from({ length: 5 }, (_, i) => entry(`f${i}.txt`))] - const rendered = formatListOutput(page(entries.slice(0, 2), { totalEntries: entries.length, all: entries })) - expect(rendered).toContain('src/\nf0.txt\n') - expect(rendered).not.toContain('f2.txt') - expect(rendered).toContain('(Showing entries 1-2 of 6: 1 directory, 5 files. Use offset=3 to continue.)') - }) - - it('renders an empty directory as a footer alone', () => { - expect(formatListOutput(page([]))).toBe(`/w -directory - -(Empty directory) -`) - }) -}) diff --git a/packages/fs/tool-fs/tests/tools.spec.ts b/packages/fs/tool-fs/tests/tools.spec.ts index 53b58d2dcf..de844dcaf4 100644 --- a/packages/fs/tool-fs/tests/tools.spec.ts +++ b/packages/fs/tool-fs/tests/tools.spec.ts @@ -38,7 +38,6 @@ const testToolSignal = new AbortController().signal class FakeFs extends FileSystem { files = new Map() rejectWith?: FsError - dirs = new Map() writeIntents: (FsWriteIntent | undefined)[] = [] editIntents: ({ version: FsVersion } | undefined)[] = [] @@ -67,9 +66,8 @@ class FakeFs extends FileSystem { const content = this.files.get(target.targetKey) ?? '' return (async function* () { yield content })() } - override async listDir(target: FsTarget): Promise { - this.throwIfArmed() - return this.dirs.get(target.targetKey) ?? [] + override async listDir(_target: FsTarget): Promise { + return [] } override async writeText(target: FsTarget, content: string, expected?: FsWriteIntent): Promise { this.throwIfArmed() @@ -141,15 +139,13 @@ describe('session cwd resolution', () => { }) describe('registration', () => { - it('registers list, read, write, and edit', async () => { + it('registers read, write, and edit', async () => { const { ctx } = await setup() - expect(ctx.tools.schemas().map(s => s.name).sort()).toEqual(['edit', 'list', 'read', 'write']) + expect(ctx.tools.schemas().map(s => s.name).sort()).toEqual(['edit', 'read', 'write']) }) - it('declares list and read parallel-safe while write/edit remain exclusive', async () => { + it('declares read parallel-safe while write/edit remain exclusive', async () => { const { ctx } = await setup() - expect(ctx.tools.executionMode({ signal: testToolSignal, callId: CallId('list-safe'), name: 'list', arguments: {} })) - .toEqual({ kind: 'parallel' }) expect(ctx.tools.executionMode({ signal: testToolSignal, callId: CallId('read-safe'), name: 'read', arguments: { file_path: 'a.txt' } })) .toEqual({ kind: 'parallel' }) expect(ctx.tools.executionMode({ signal: testToolSignal, callId: CallId('write-exclusive'), name: 'write', arguments: { file_path: 'a.txt', content: 'x' } })) @@ -161,8 +157,6 @@ describe('registration', () => { it('registers prompt sections for each tool', async () => { const { ctx } = await setup() const prompt = renderPrompt(await ctx.systemPrompt.assemble()) - expect(prompt).toContain('Use the list tool') - expect(prompt).not.toContain('glob or grep') expect(prompt).toContain('Use the read tool') expect(prompt).toContain('Use the write tool') expect(prompt).toContain('Use the edit tool') @@ -185,10 +179,9 @@ describe('registration', () => { const fiber = await ctx.plugin(ToolFs) // Each tool contributes BOTH a schema and a prompt section; disposal must // withdraw both, not just the schemas. - expect(ctx.tools.schemas()).toHaveLength(4) + expect(ctx.tools.schemas()).toHaveLength(3) const sectionNames = (a: { sections: { name: string }[] }) => a.sections.map(s => s.name).sort() - expect(sectionNames(await ctx.systemPrompt.assemble())) - .toEqual(['deployment:persona', 'harness:identity', 'tool:edit', 'tool:list', 'tool:read', 'tool:write']) + expect(sectionNames(await ctx.systemPrompt.assemble())).toEqual(['deployment:persona', 'harness:identity', 'tool:edit', 'tool:read', 'tool:write']) await fiber.dispose() expect(ctx.tools.schemas()).toHaveLength(0) // Only the system-prompt plugin's own built-in sections remain. @@ -196,144 +189,6 @@ describe('registration', () => { }) }) -describe('list tool', () => { - /** Seed one directory's children; `listDir` order is deliberately NOT display order. */ - function seedDir(fs: FakeFs, path: string, children: readonly { name: string; type: 'file' | 'directory' | 'other' }[]): void { - fs.dirs.set(`key:${path}`, children.map(({ name, type }) => ({ - name, - type, - target: { targetKey: FsTargetKey(`key:${path}/${name}`), displayPath: `/abs/${path}/${name}` }, - }))) - } - - it('defaults to the session workspace and shows directories before files', async () => { - const { ctx, fs } = await setup() - seedDir(fs, '.', [ - { name: 'notes.md', type: 'file' }, - { name: 'zeroomega-3.3.23', type: 'directory' }, - { name: 'archive', type: 'directory' }, - { name: 'link-to-nowhere', type: 'other' }, - ]) - const result = await call(ctx, 'list', {}) - expect(result.isError).toBe(false) - if (result.isError) throw new Error('expected list success') - // The canonical value carries display order, so a Code Mode caller and the - // model see the same ordering contract. - expect(result.value).toEqual({ - path: '/abs/.', - offset: 1, - entries: [ - { name: 'archive', type: 'directory' }, - { name: 'zeroomega-3.3.23', type: 'directory' }, - { name: 'notes.md', type: 'file' }, - { name: 'link-to-nowhere', type: 'other' }, - ], - totalEntries: 4, - counts: { directories: 2, files: 1, other: 1 }, - }) - expect(text(result)).toBe(`/abs/. -directory - -archive/ -zeroomega-3.3.23/ -notes.md -link-to-nowhere@ - -(4 entries: 2 directories, 1 file, 1 other) -`) - }) - - it('lists an explicit path and reports an empty directory as such', async () => { - const { ctx, fs } = await setup() - seedDir(fs, 'empty', []) - const result = await call(ctx, 'list', { path: 'empty' }) - expect(text(result)).toContain('(Empty directory)') - expect(text(result)).toContain('/abs/empty') - }) - - it('caps the rendered entries but still reports the complete composition', async () => { - const ctx = new Context() - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(FakeFs) - await ctx.plugin(ToolFs, { listMaxEntries: 2 }) - const fs = ctx.fs as FakeFs - seedDir(fs, '.', [ - { name: 'a.txt', type: 'file' }, - { name: 'b.txt', type: 'file' }, - { name: 'c.txt', type: 'file' }, - { name: 'src', type: 'directory' }, - ]) - const result = await call(ctx, 'list', {}) - const rendered = text(result) - // The one directory survives the cap because directories sort first — the - // failure mode this ordering exists to prevent. - expect(rendered).toContain('src/\na.txt\n') - expect(rendered).not.toContain('c.txt') - expect(rendered).toContain('(Showing entries 1-2 of 4: 1 directory, 3 files. Use offset=3 to continue.)') - if (result.isError) throw new Error('expected list success') - expect(result.value).toEqual({ - path: '/abs/.', - offset: 1, - entries: [{ name: 'src', type: 'directory' }, { name: 'a.txt', type: 'file' }], - totalEntries: 4, - counts: { directories: 1, files: 3, other: 0 }, - }) - - const continuation = await call(ctx, 'list', { offset: 3 }) - expect(text(continuation)).toContain('b.txt\nc.txt') - expect(text(continuation)).toContain('(Showing entries 3-4 of 4: 1 directory, 3 files.)') - }) - - it('rejects a blank path and surfaces provider failures', async () => { - const { ctx, fs } = await setup() - const blank = await call(ctx, 'list', { path: ' ' }) - expect(blank.isError).toBe(true) - expect(text(blank)).toContain('path must be a non-empty string when given') - - fs.rejectWith = new FsError('cannot list "/abs/a.txt": not a directory', 'FS_NOT_DIRECTORY') - const failed = await call(ctx, 'list', { path: 'a.txt' }) - expect(failed.isError).toBe(true) - expect(failed.error).toMatchObject({ info: { code: 'FS_NOT_DIRECTORY' } }) - }) - - it('rejects invalid and out-of-range continuation offsets', async () => { - const { ctx, fs } = await setup() - seedDir(fs, '.', [{ name: 'only.txt', type: 'file' }]) - expect(text(await call(ctx, 'list', { offset: 0 }))).toContain('offset must be a positive integer') - expect(text(await call(ctx, 'list', { offset: 1.5 }))).toContain('offset must be a positive integer') - expect(text(await call(ctx, 'list', { offset: 2 }))).toContain('offset 2 is out of range') - }) - - it('encodes filesystem names without allowing them to forge the envelope or type marker', async () => { - const { ctx, fs } = await setup() - seedDir(fs, '.', [ - { name: 'regular@', type: 'file' }, - { name: 'special', type: 'other' }, - { name: 'fake\n', type: 'file' }, - ]) - const rendered = text(await call(ctx, 'list', {})) - // A regular file really named `regular@` must not read as a socket named - // `regular`, and a newline in a name must not become a second entry. - expect(rendered).toContain('"regular@"\nspecial@') - expect(rendered).toContain('"fake\\n<\\/content>"') - expect(rendered.match(/<\/content>/g)).toHaveLength(1) - }) - - it('records no observation, so a listing never authorizes a mutation', async () => { - const { ctx, fs } = await setup() - fs.files.set('key:a.txt', 'hello') - seedDir(fs, '.', [{ name: 'a.txt', type: 'file' }]) - const observed = vi.fn() - ctx.on('fs/observed', observed) - await call(ctx, 'list', {}) - expect(observed).not.toHaveBeenCalled() - // Seeing a name is not reading a file: the policy gate still demands a read. - const edit = await call(ctx, 'edit', { file_path: 'a.txt', old_string: 'h', new_string: 'j' }, { session: { header: {} } }) - expect(edit.error).toMatchObject({ info: { code: 'FS_NOT_OBSERVED' } }) - }) -}) - describe('read tool', () => { it('formats line-numbered content with a footer', async () => { const { ctx, fs } = await setup() @@ -589,18 +444,6 @@ describe('tool-owned presentation (pure presentCall)', () => { }) }) - it('list: titles by the directory, falling back to the workspace "." when unset', async () => { - expect(await presentCall('list', { path: 'src' })).toEqual({ - card: 'generic', title: 'List src', kind: 'read', locations: [{ path: 'src' }], - }) - expect(await presentCall('list', {})).toEqual({ - card: 'generic', title: 'List .', kind: 'read', locations: [{ path: '.' }], - }) - expect(await presentCall('list', { path: 'src', offset: 201 })).toEqual({ - card: 'generic', title: 'List src (from entry 201)', kind: 'read', locations: [{ path: 'src' }], - }) - }) - it('read: bare title and line-1 location when offset/limit are unset', async () => { expect(await presentCall('read', { file_path: 'a.txt' })).toEqual({ card: 'generic', title: 'Read a.txt', kind: 'read', locations: [{ path: 'a.txt', line: 1 }], @@ -813,7 +656,6 @@ describe('read caps are plugin config', () => { }) it.each([ - ['listMaxEntries', { listMaxEntries: 0 }], ['readLimit', { readLimit: 0 }], ['readLimit', { readLimit: 2.5 }], ['readMaxLineLength', { readMaxLineLength: -1 }], diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index c507ae0e0d..7bdc8b68a8 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -230,7 +230,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ await ctx.plugin(ToolFs) }, note: - '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. `list` paginates one directory level through `ctx.fs.listDir` and records no observation, so seeing a filename never satisfies that read-before-write gate.', + '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.', }, { pkg: '@deepseek-ai/dsh-tool-fs-search', @@ -248,7 +248,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ await ctx.plugin(ToolFsSearch) }, 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). 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. An over-cap glob result does not return the head of the sorted list: its inline page is taken round-robin across entries immediately beneath the actual search root and the footer states that basis, because modification-time order is ascending and the restored timestamps of an unpacked archive put one subtree in front of every broad match.', + '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). 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 6b79ce08c580c1921f545ac447b543cbc3970893 Mon Sep 17 00:00:00 2001 From: NI0317 Date: Tue, 28 Jul 2026 16:21:29 +0800 Subject: [PATCH 07/24] 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. From 89d30b0ef71320a562ab41f99c68548be41d2d50 Mon Sep 17 00:00:00 2001 From: creatixchu Date: Thu, 30 Jul 2026 19:09:19 +0800 Subject: [PATCH 08/24] feat(user-interaction): declare a plan-review presentation intent on questions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A question may now carry `intent`, a tagged declaration that it IS a decision of a known shape, so a UI that recognises the tag can present it as such instead of as a generic option list. The one member is `{ kind: 'plan-review', approve }`, which plan-mode sets on the exit_plan_mode review. An intent shapes presentation only: a UI honouring it answers with the same option labels a generic UI would send, so the tool reads one answer shape either way, and a UI that does not know the tag renders the generic flow. `approve` names the affirmative option rather than relying on option order; since no type can tie that label to the question's own option list, `ask()` rejects a mismatch as BAD_INTENT, and the wire schema rejects an unknown tag outright rather than silently rendering generic. plan-mode also stops reporting a dismissed review as "the user cancelled ask_user_question" — a tool it never called. A dismissal now tells the model the user took the turn back to speak, and to stay in plan mode and wait; every other ask failure keeps its own message. --- docs/cordis-catalog/services.md | 4 +- .../user-interaction.i18n.yaml | 6 +-- docs/core-data-structures/user-interaction.md | 26 ++++++++++++ .../user-interaction.zh.md | 26 ++++++++++++ .../cordis/tool-cordis/src/api-catalog.ts | 6 ++- .../host/apiproxy/src/api/events.schema.ts | 5 +++ .../host/apiproxy/tests/rpc-schemas.spec.ts | 11 +++++ packages/plan/plan-mode/README.i18n.yaml | 4 +- packages/plan/plan-mode/README.md | 7 +++- packages/plan/plan-mode/README.zh.md | 7 +++- packages/plan/plan-mode/src/index.ts | 24 +++++++++-- .../plan/plan-mode/tests/plan-mode.spec.ts | 38 ++++++++++++++++- packages/ui/user-interaction/README.i18n.yaml | 4 +- packages/ui/user-interaction/README.md | 9 +++- packages/ui/user-interaction/README.zh.md | 9 +++- packages/ui/user-interaction/src/index.ts | 17 +++++++- packages/ui/user-interaction/src/types.ts | 20 +++++++++ .../tests/user-interaction.spec.ts | 41 +++++++++++++++++++ scripts/type-equiv.manifest.json | 5 +++ 19 files changed, 246 insertions(+), 23 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 8e4030c2fe..6ab505b3fb 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -908,7 +908,7 @@ set(agent: Agent, active: boolean): 'committed' | 'queued' | 'cancelled' | 'noop Types: [Agent](../core-data-structures/core.md) -Source: [`packages/plan/plan-mode/src/index.ts:179`](../../packages/plan/plan-mode/src/index.ts) +Source: [`packages/plan/plan-mode/src/index.ts:182`](../../packages/plan/plan-mode/src/index.ts) ## `ctx.pty` — `PtyService` @@ -2284,7 +2284,7 @@ async ask(request: AskUserQuestionRequest): Promise Types: [AskUserQuestionAnswer](../core-data-structures/user-interaction.md) · [AskUserQuestionRequest](../core-data-structures/user-interaction.md) · [UserInteractionProvider](../core-data-structures/user-interaction.md) -Source: [`packages/ui/user-interaction/src/index.ts:50`](../../packages/ui/user-interaction/src/index.ts) +Source: [`packages/ui/user-interaction/src/index.ts:51`](../../packages/ui/user-interaction/src/index.ts) ## `ctx.web` — `WebService` diff --git a/docs/core-data-structures/user-interaction.i18n.yaml b/docs/core-data-structures/user-interaction.i18n.yaml index 66cb12815e..ee739a59d3 100644 --- a/docs/core-data-structures/user-interaction.i18n.yaml +++ b/docs/core-data-structures/user-interaction.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 -user-interaction.md: 798a9790f424683775284a98421be08e6e1399e3 -user-interaction.zh.md: 12bfcffe4fe4caaacb54e90126eac55e333d64a5 +# pnpm run verify-translation-pairing --write docs/core-data-structures/user-interaction.md +user-interaction.md: 4ebaf66131b3ab7a7c205bef1ba533e9321d4f0b +user-interaction.zh.md: 8e5542b995bbf061b097d650ab79505e93151fa8 diff --git a/docs/core-data-structures/user-interaction.md b/docs/core-data-structures/user-interaction.md index 798a9790f4..4ebaf66131 100644 --- a/docs/core-data-structures/user-interaction.md +++ b/docs/core-data-structures/user-interaction.md @@ -20,6 +20,30 @@ interface AskUserQuestionOption { } ``` +## Presentation intent + +`AskUserQuestionIntent` is the optional declaration that a question IS a decision of a known shape. It is tagged on `kind` so intents can be added; a UI that does not recognise a tag renders the generic option list. An intent shapes presentation only — a UI honouring it answers with the same option labels a generic UI would send, so the caller reads one answer shape either way. `approve` names the affirmative option instead of relying on option order, and `ask()` rejects an `approve` naming none of its own question's options. + +```ts type-equiv +/** + * A caller-declared presentation intent: the question IS a decision of this + * shape, so a UI that recognises the tag may present it as such instead of as a + * generic option list. Tagged so further intents can be added; a UI that does + * not know a tag renders the generic flow, and the answer encoding is identical + * either way — an intent shapes presentation only, never the protocol. + */ +type AskUserQuestionIntent = { + /** A plan submitted for review: `detail` is the plan markdown, and the decision approves or declines it. */ + kind: 'plan-review' + /** + * The option label that approves the plan; every other option declines it. + * Named rather than positional so no UI infers the verdict from option order. + * An `approve` naming no option of its own question is rejected at `ask()`. + */ + approve: string +} +``` + ## Question item `AskUserQuestionItem` is one question in a request. The caller supplies a stable `id`, which is echoed back with the answer so batched questions remain routable. Optional `detail` carries supporting text that providers render with the question but keep out of selectable option labels. @@ -39,6 +63,8 @@ interface AskUserQuestionItem { options?: AskUserQuestionOption[] /** Whether more than one option may be selected. Defaults to single-select. */ multiSelect?: boolean + /** Optional presentation intent for capable UIs; absent asks for the generic option list. */ + intent?: AskUserQuestionIntent } ``` diff --git a/docs/core-data-structures/user-interaction.zh.md b/docs/core-data-structures/user-interaction.zh.md index 12bfcffe4f..8e5542b995 100644 --- a/docs/core-data-structures/user-interaction.zh.md +++ b/docs/core-data-structures/user-interaction.zh.md @@ -20,6 +20,30 @@ interface AskUserQuestionOption { } ``` +## 呈现意图 + +`AskUserQuestionIntent` 是一项可选声明：某个问题本身就是一次已知形状的决定。它按 `kind` 打标签，因此意图可以扩充；不认识某个标签的 UI 渲染通用选项列表。意图只塑造呈现 —— 遵循它的 UI 回答的仍是通用 UI 会发送的那些 option label，因此调用方两种情况下读到的都是同一种回答形态。`approve` 指名肯定选项，而不依赖选项顺序；`ask()` 会拒绝未命中该问题自身任一选项的 `approve`。 + +```ts type-equiv +/** + * A caller-declared presentation intent: the question IS a decision of this + * shape, so a UI that recognises the tag may present it as such instead of as a + * generic option list. Tagged so further intents can be added; a UI that does + * not know a tag renders the generic flow, and the answer encoding is identical + * either way — an intent shapes presentation only, never the protocol. + */ +type AskUserQuestionIntent = { + /** A plan submitted for review: `detail` is the plan markdown, and the decision approves or declines it. */ + kind: 'plan-review' + /** + * The option label that approves the plan; every other option declines it. + * Named rather than positional so no UI infers the verdict from option order. + * An `approve` naming no option of its own question is rejected at `ask()`. + */ + approve: string +} +``` + ## 问题条目 `AskUserQuestionItem` 是请求中的一个问题。调用方提供稳定的 `id`，它会随答案原样返回，使批量问题仍可路由。可选的 `detail` 携带辅助文本；提供方会将其随问题渲染，但不会放入可选 option label。 @@ -39,6 +63,8 @@ interface AskUserQuestionItem { options?: AskUserQuestionOption[] /** Whether more than one option may be selected. Defaults to single-select. */ multiSelect?: boolean + /** Optional presentation intent for capable UIs; absent asks for the generic option list. */ + intent?: AskUserQuestionIntent } ``` diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index d7cdc4e253..74d66a5631 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -1503,9 +1503,13 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'AskUserQuestionAnswerItem', declaration: 'export interface AskUserQuestionAnswerItem {\n id: string;\n selected: string[];\n custom?: string;\n}', }, + { + name: 'AskUserQuestionIntent', + declaration: 'export type AskUserQuestionIntent = {\n kind: \'plan-review\';\n approve: string;\n};', + }, { name: 'AskUserQuestionItem', - declaration: 'export interface AskUserQuestionItem {\n id: string;\n question: string;\n detail?: string;\n header?: string;\n options?: AskUserQuestionOption[];\n multiSelect?: boolean;\n}', + declaration: 'export interface AskUserQuestionItem {\n id: string;\n question: string;\n detail?: string;\n header?: string;\n options?: AskUserQuestionOption[];\n multiSelect?: boolean;\n intent?: AskUserQuestionIntent;\n}', }, { name: 'AskUserQuestionOption', diff --git a/packages/host/apiproxy/src/api/events.schema.ts b/packages/host/apiproxy/src/api/events.schema.ts index 4e17b1f403..43b7a147e4 100644 --- a/packages/host/apiproxy/src/api/events.schema.ts +++ b/packages/host/apiproxy/src/api/events.schema.ts @@ -23,6 +23,11 @@ export const askUserQuestionItemSchema = z.object({ detail: z.string().optional(), options: z.array(z.object({ label: z.string(), description: z.string().optional() })).optional(), multiSelect: z.boolean().optional(), + // Presentation intent: a tagged union on the wire, so an unknown tag is a + // rejected frame rather than a silently generic render. + intent: z.discriminatedUnion('kind', [ + z.object({ kind: z.literal('plan-review'), approve: z.string() }), + ]).optional(), }) satisfies z.ZodType> /** Unified message envelope carried by transient queue frames. */ diff --git a/packages/host/apiproxy/tests/rpc-schemas.spec.ts b/packages/host/apiproxy/tests/rpc-schemas.spec.ts index 80cd0baf4c..0b4d0b78ee 100644 --- a/packages/host/apiproxy/tests/rpc-schemas.spec.ts +++ b/packages/host/apiproxy/tests/rpc-schemas.spec.ts @@ -399,6 +399,17 @@ describe('events frame schemas', () => { expect(() => muxFrameSchema.parse({ type: 'question/requested', sessionId: 's', questions: [] })).toThrow() }) + it('carries a question presentation intent through, and rejects an unknown one', () => { + const intent = { kind: 'plan-review', approve: 'Approve' } + expect(askUserQuestionItemSchema.parse({ + id: 'plan-review', question: 'Approve?', detail: '# Plan', options: [{ label: 'Approve' }], intent, + }).intent).toEqual(intent) + // An unrecognised tag is a rejected frame, not a silently generic render. + for (const invalid of [{ kind: 'plan-review' }, { kind: 'poll', approve: 'Approve' }, { approve: 'Approve' }]) { + expect(() => askUserQuestionItemSchema.parse({ id: 'q', question: 'Q?', intent: invalid })).toThrow() + } + }) + it('rejects a queue snapshot with malformed items', () => { expect(() => muxFrameSchema.parse({ type: 'session/queue', sessionId: 's', items: 'x' })).toThrow() expect(() => muxFrameSchema.parse({ type: 'session/queue', sessionId: 's', items: [{ id: '', message: {} }] })).toThrow() diff --git a/packages/plan/plan-mode/README.i18n.yaml b/packages/plan/plan-mode/README.i18n.yaml index c5a13bee7e..a4b6723b98 100644 --- a/packages/plan/plan-mode/README.i18n.yaml +++ b/packages/plan/plan-mode/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/plan/plan-mode/README.md -README.md: d3c2c14fe616e1c9b4e33b716570b084db6474cf -README.zh.md: 6d6878c4b0300a716ad16be60fd86bc79f1514ba +README.md: 6f0a9ac477b49b96ddfc2ce667e3556dec727569 +README.zh.md: 922b153aa1b08e1a6003f63736ea402787bff1dd diff --git a/packages/plan/plan-mode/README.md b/packages/plan/plan-mode/README.md index d3c2c14fe6..6f0a9ac477 100644 --- a/packages/plan/plan-mode/README.md +++ b/packages/plan/plan-mode/README.md @@ -14,6 +14,8 @@ Logged, per-agent plan collaboration state with deployment-owned guidance, direc While active, `plan:policy` renders the configured `section`. The plugin always registers `exit_plan_mode`, keeping tool schemas stable across the transition; its execute path accepts only active plan mode and leaves it only after an exact user approval through `ctx.userInteraction`. +The review question declares the `plan-review` presentation intent, naming `Approve` as the label that approves it, so a capable UI presents the plan as a decision instead of a generic question; the answer the tool reads is the same either way. A dismissed review — the user closing the request to speak instead — is reported to the model as such, telling it to stay in plan mode and wait for the message; every other review failure keeps the seam's own message. + When `ctx.commands` is composed, the package registers `/plan [message]` and reserves the exact argument `off` for direct exit. Bare `/plan` selects plan mode; any other non-empty argument selects it first and is then submitted through `agent.steer()`, so it becomes the next step's ordinary logged user message under plan guidance. `/plan off` selects inactive without sending model input; it also cancels a pending entry before plan mode reaches a request. The TUI consumes the plugin-owned `/plan` command; other front doors may drive the same service directly without defining a second mode vocabulary. @@ -77,7 +79,7 @@ The user block is append-only conversation growth. Entering or leaving plan mode #### What the model sees -The [`exit_plan_mode` schema](../../../docs/tool-catalog.md#deepseek-aidsh-plan-mode) remains available in both states; execution outside plan mode fails, while an approved in-mode review returns the canonical `{ approved: true }` value and renders the existing confirmation text. Rejection remains a failed call carrying review feedback. +The [`exit_plan_mode` schema](../../../docs/tool-catalog.md#deepseek-aidsh-plan-mode) remains available in both states; execution outside plan mode fails, while an approved in-mode review returns the canonical `{ approved: true }` value and renders the existing confirmation text. Rejection remains a failed call carrying review feedback, and a dismissed review a failed call naming the user's takeover. #### Token effect @@ -92,4 +94,5 @@ Mode transitions do not change the tool catalog; plan arguments and review resul - Plan mode guides rather than enforces; deployments needing a hard boundary must combine independent sandbox and approval controls. - A pending selection made while idle is lost if the process exits before the next boundary, so the UI must reapply it. - Forked agents inherit logged plan state, while newly spawned agents begin inactive; there is no creation-time plan option. -- The `exit_plan_mode` review arc (submit → human review → approved flip or rejected feedback) is covered by package tests only; its assembled-application snapshot left with the retired ACP UI scenarios ([automation-only ACP](../../../.agents/notes/implemented/simplification/2026-07-23-acp-automation-only-protocol.md)) and the TUI keyless scenarios exercise only `/plan` entry and `/plan off` exit. +- The `exit_plan_mode` review arc has one assembled-application snapshot, the Web `plan-review` e2e lane (submit → decision card → approved flip). The rejected-feedback and dismissed branches are covered by package tests only, and the TUI keyless scenarios exercise only `/plan` entry and `/plan off` exit. +- Only the Web UI renders the `plan-review` intent; the TUI presents the review through its generic question flow, which is answerable but does not read as a plan gate. diff --git a/packages/plan/plan-mode/README.zh.md b/packages/plan/plan-mode/README.zh.md index 6d6878c4b0..922b153aa1 100644 --- a/packages/plan/plan-mode/README.zh.md +++ b/packages/plan/plan-mode/README.zh.md @@ -14,6 +14,8 @@ 激活时，`plan:policy` 会渲染已配置的 `section`。插件始终注册 `exit_plan_mode`，使工具 schema 在转换期间保持稳定；其 execute 路径只接受已激活的 plan mode，且只有通过 `ctx.userInteraction` 获得精确用户批准后才退出。 +评审问题声明 `plan-review` 呈现意图，并指名 `Approve` 为表示批准的标签，因此有能力的 UI 会把计划呈现为一次决定而非通用问题；两种情况下该工具读到的回答完全相同。放弃审阅 —— 用户关掉请求改用说话 —— 会如实报告给模型，要求它留在 plan mode 中等待那条消息；其余每一种评审失败都保留 seam 自身的消息。 + 组合 `ctx.commands` 时，该包（package）会注册 `/plan [message]`，并保留精确参数 `off` 用于直接退出。不带参数的 `/plan` 选择 plan mode；任何其他非空参数都会先选择 plan mode，再通过 `agent.steer()` 提交，因此它会在 plan 引导下成为下一步骤的常规已记录用户消息。`/plan off` 选择未激活状态，不发送模型输入；它还可以在 plan mode 进入选择到达请求之前取消该待生效选择。 TUI 消费插件拥有的 `/plan` 命令；其他入口可以直接驱动同一服务，无需定义第二套 mode 词汇。 @@ -77,7 +79,7 @@ You are in plan mode. Explore and design before presenting the complete plan thr #### 模型所见内容 -[`exit_plan_mode` schema](../../../docs/tool-catalog.md#deepseek-aidsh-plan-mode) 在两种状态下均可用；在 plan mode 外执行会失败，而 plan mode 内经批准的评审会返回规范 `{ approved: true }` 值，并渲染现有确认文本。拒绝仍是携带评审反馈的失败调用。 +[`exit_plan_mode` schema](../../../docs/tool-catalog.md#deepseek-aidsh-plan-mode) 在两种状态下均可用；在 plan mode 外执行会失败，而 plan mode 内经批准的评审会返回规范 `{ approved: true }` 值，并渲染现有确认文本。拒绝仍是携带评审反馈的失败调用，放弃审阅则是一次指明用户接手的失败调用。 #### Token 影响 @@ -92,4 +94,5 @@ Mode 转换不改变工具目录；plan 参数与评审结果按常规方式扩 - Plan mode 只进行引导，而不强制执行；需要硬边界的部署必须组合独立的沙箱与批准控制。 - 如果进程在下一个边界之前退出，空闲时作出的待生效选择会丢失，因此 UI 必须重新应用它。 - Fork 的 agent 会继承已记录的 plan 状态，新 spawn 的 agent 则从未激活状态开始；不存在创建时 plan 选项。 -- `exit_plan_mode` 评审弧（提交 → 人类评审 → 已批准切换或已拒绝反馈）仅由包测试覆盖；其组装应用快照随已退役 ACP UI 场景一起离开（[仅面向自动化的 ACP](../../../.agents/notes/implemented/simplification/2026-07-23-acp-automation-only-protocol.md)），TUI 无密钥场景只演练 `/plan` 进入和 `/plan off` 退出。 +- `exit_plan_mode` 评审弧有一个组装应用快照，即 Web `plan-review` e2e 通道（提交 → 决定卡片 → 已批准切换）。已拒绝反馈与放弃审阅两个分支仅由包测试覆盖，TUI 无密钥场景只演练 `/plan` 进入和 `/plan off` 退出。 +- 只有 Web UI 渲染 `plan-review` 意图；TUI 通过其通用问题流程呈现该评审，可以回答，但读起来不像一个计划关口。 diff --git a/packages/plan/plan-mode/src/index.ts b/packages/plan/plan-mode/src/index.ts index dc6b788825..b2a5f6076d 100644 --- a/packages/plan/plan-mode/src/index.ts +++ b/packages/plan/plan-mode/src/index.ts @@ -29,7 +29,7 @@ import { createUserMessage } from '@deepseek-ai/dsh-llm' import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' import { defineTool } from '@deepseek-ai/dsh-tools' import type {} from '@deepseek-ai/dsh-system-prompt' -import type {} from '@deepseek-ai/dsh-user-interaction' +import { UserInteractionError } from '@deepseek-ai/dsh-user-interaction' // Type-only edge: resolves `ctx.commands` for the optional command child. import type {} from '@deepseek-ai/dsh-commands' // Type-only: resolves ctx.sessionProjections for the optional unit child. @@ -70,6 +70,9 @@ export interface PlanModeConfig { section: string } +/** The review question's id, echoed in the answer this tool reads. */ +const REVIEW_ID = 'plan-review' + /** The review question's approve option label. */ const APPROVE_LABEL = 'Approve' @@ -317,7 +320,7 @@ export class PlanModeService extends Service { } const answer = await interaction.ask({ questions: [{ - id: 'plan-review', + id: REVIEW_ID, header: 'Plan review', question: 'Approve this plan and leave plan mode?', detail: args.plan, @@ -325,16 +328,31 @@ export class PlanModeService extends Service { { label: APPROVE_LABEL, description: 'Leave plan mode; the plan is carried out from the next step.' }, { label: KEEP_PLANNING_LABEL, description: 'Stay in plan mode; feedback goes back to the model.' }, ], + // Presentation only: a capable UI renders the plan as a review + // decision instead of a generic question, and answers with one of + // the labels above either way. + intent: { kind: 'plan-review', approve: APPROVE_LABEL }, }], agent, signal: exec.signal, + }).catch((cause: unknown) => { + // A dismissed review is not a failed one: the user took the turn back + // to say something the two options do not cover. Say so, because the + // generic channel message names ask_user_question, which the model + // never called. An abort (turn cancel, provider teardown) keeps its + // own message — there is no user to wait for. + if (cause instanceof UserInteractionError && cause.code === 'ASK_CANCELLED') { + throw new Error('The user dismissed the plan review to speak instead; ' + + 'stay in plan mode, stop here, and wait for their message.') + } + throw cause }) // A review may outlive this plugin fiber. Without boundary listeners, // an approved result could never land, so fail and keep planning. if (disposed) { throw new Error('the plan-mode service was reloaded while the plan was under review; present the plan again') } - const reviewItems = answer.answers.filter(entry => entry.id === 'plan-review') + const reviewItems = answer.answers.filter(entry => entry.id === REVIEW_ID) const item = reviewItems.length === 1 ? reviewItems[0] : undefined if (item?.selected.length !== 1 || item.selected[0] !== APPROVE_LABEL || item.custom !== undefined) { const feedback = item?.custom ?? '' diff --git a/packages/plan/plan-mode/tests/plan-mode.spec.ts b/packages/plan/plan-mode/tests/plan-mode.spec.ts index 72d273d20f..6fa165cbb0 100644 --- a/packages/plan/plan-mode/tests/plan-mode.spec.ts +++ b/packages/plan/plan-mode/tests/plan-mode.spec.ts @@ -6,7 +6,9 @@ import ToolRegistry, { RUN_CODE_NAME, defineContentToolFixture } from '@deepseek import { Session, SessionId } from '@deepseek-ai/dsh-session' import { agentEvents, type Agent } from '@deepseek-ai/dsh-agent' import { createScope } from '@deepseek-ai/dsh-scope' -import UserInteractionService, { type AskUserQuestionRequest } from '@deepseek-ai/dsh-user-interaction' +import UserInteractionService, { + UserInteractionError, type AskUserQuestionRequest, +} from '@deepseek-ai/dsh-user-interaction' import CommandService from '@deepseek-ai/dsh-commands' import { CodeRuntime, type CodeRunRequest, type CodeRunResult } from '@deepseek-ai/dsh-code-runtime' import PlanModeService, { EXIT_PLAN_MODE, foldPlanMode, resolveConfig } from '../src/index.ts' @@ -894,6 +896,40 @@ describe('exit_plan_mode', () => { expect(result.content).toEqual([{ type: 'text', text: 'Error: The user chose to keep planning; revise the plan and present it again.' }]) }) + it('declares the plan-review presentation intent naming its approve option', async () => { + const { ctx, agent, asked } = await setupWithReview({ selected: ['Approve'] }) + await callExit(ctx, agent) + const question = asked[0]?.questions[0] + expect(question?.intent).toEqual({ kind: 'plan-review', approve: 'Approve' }) + // The named label is one this same question offers, so a UI honouring the + // intent answers a choice this tool accepts. + expect(question?.options?.map(option => option.label)).toContain(question?.intent?.approve) + }) + + it('reads a dismissed review as the user taking the turn back, not as a failure', async () => { + const { ctx, agent } = await setupWithReview() + ctx.userInteraction.registerProvider({ + ask: () => Promise.reject(new UserInteractionError( + 'the user cancelled ask_user_question', 'ASK_CANCELLED')), + }) + const result = await callExit(ctx, agent) + expect(result.isError).toBe(true) + expect(result.content).toEqual([{ type: 'text', text: 'Error: The user dismissed the plan review to speak instead; stay in plan mode, stop here, and wait for their message.' }]) + expect(foldPlanMode(agent.session.events)).toBe(true) + }) + + it('leaves every other review failure its own message', async () => { + const { ctx, agent } = await setupWithReview() + ctx.userInteraction.registerProvider({ + ask: () => Promise.reject(new UserInteractionError( + 'ask_user_question was aborted before the user answered', 'ASK_ABORTED')), + }) + const result = await callExit(ctx, agent) + expect(result.isError).toBe(true) + expect(result.content).toEqual([{ type: 'text', text: 'Error: ask_user_question was aborted before the user answered' }]) + expect(foldPlanMode(agent.session.events)).toBe(true) + }) + it('forwards the execution abort signal to the review question', async () => { const { ctx, agent, asked } = await setupWithReview({ selected: ['Approve'] }) const controller = new AbortController() diff --git a/packages/ui/user-interaction/README.i18n.yaml b/packages/ui/user-interaction/README.i18n.yaml index 98e40aa0d3..96973400df 100644 --- a/packages/ui/user-interaction/README.i18n.yaml +++ b/packages/ui/user-interaction/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/user-interaction/README.md -README.md: d234d6677bdd772f1bbd2c979c0d41f90aef5c32 -README.zh.md: c89210b6955a661313ca9e0e82e43da5a4d1db79 +README.md: f134e912149190efb81ea9f64c5d63632ce8c626 +README.zh.md: ab6432dcbddc36d3ef9ca957b3901cb76257539a diff --git a/packages/ui/user-interaction/README.md b/packages/ui/user-interaction/README.md index d234d6677b..f134e91214 100644 --- a/packages/ui/user-interaction/README.md +++ b/packages/ui/user-interaction/README.md @@ -13,14 +13,19 @@ Abstract user-interaction seam. It owns `ctx.userInteraction`, the service a mod ### Key Types -- `AskUserQuestionRequest` — `{ questions: [{ id, question, detail?, header?, options?, multiSelect? }], agent?, signal? }`; `detail` supplies supporting text that providers render with the question without turning it into an option label. +- `AskUserQuestionRequest` — `{ questions: [{ id, question, detail?, header?, options?, multiSelect?, intent? }], agent?, signal? }`; `detail` supplies supporting text that providers render with the question without turning it into an option label. - `AskUserQuestionOption` — `{ label, description? }`. +- `AskUserQuestionIntent` — `{ kind: 'plan-review', approve }`; the tagged presentation intent below. - `AskUserQuestionAnswer` — `{ answers: [{ id, selected, custom? }] }`. - `UserInteractionProvider` — UI implementation with `ask(request)`. -- `UserInteractionError` — `HarnessError` subclass with codes such as `EMPTY_QUESTIONS`, `NO_PROVIDER`, `DUPLICATE_PROVIDER`, and `ASK_ABORTED`. +- `UserInteractionError` — `HarnessError` subclass with codes such as `EMPTY_QUESTIONS`, `BAD_INTENT`, `NO_PROVIDER`, `DUPLICATE_PROVIDER`, and `ASK_ABORTED`. When an answer includes `custom`, `selected` is empty; custom text is an override rather than a supplement to selected choices. A UI may preserve a skipped item as `{ id, selected: [] }`, keeping the existing answer shape while retaining other answers in the batch. +### Presentation intent + +`intent` declares that a question IS a decision of a known shape, so a UI that recognises the tag may present it as such — `plan-review` says `detail` is a plan under review, and `dsh-plan-mode` sets it on the `exit_plan_mode` question. An intent shapes presentation only: a UI honouring it answers with the same option labels a generic UI would send, and a UI that does not know the tag renders the generic option list, so callers read one answer shape either way. `approve` names the label that approves rather than relying on option order; `ask()` rejects an intent whose `approve` names none of that question's own options with `BAD_INTENT`, since no type can tie the two together. + ## Role This is the interface package. Model-facing consumers such as `@deepseek-ai/dsh-tool-ask-user` depend on this seam; `dsh-tui` and the host runtime provide interactive implementations. The loop stays unchanged: a tool call awaits a promise, and the tool result resumes the normal agent loop. diff --git a/packages/ui/user-interaction/README.zh.md b/packages/ui/user-interaction/README.zh.md index c89210b695..ab6432dcbd 100644 --- a/packages/ui/user-interaction/README.zh.md +++ b/packages/ui/user-interaction/README.zh.md @@ -13,14 +13,19 @@ ### 关键类型 -- `AskUserQuestionRequest`：`{ questions: [{ id, question, detail?, header?, options?, multiSelect? }], agent?, signal? }`；`detail` 提供辅助文本，提供方会将其随问题一起渲染，而不会将其变成选项标签。 +- `AskUserQuestionRequest`：`{ questions: [{ id, question, detail?, header?, options?, multiSelect?, intent? }], agent?, signal? }`；`detail` 提供辅助文本，提供方会将其随问题一起渲染，而不会将其变成选项标签。 - `AskUserQuestionOption`：`{ label, description? }`。 +- `AskUserQuestionIntent`：`{ kind: 'plan-review', approve }`；即下文的带标签呈现意图。 - `AskUserQuestionAnswer`：`{ answers: [{ id, selected, custom? }] }`。 - `UserInteractionProvider`：包含 `ask(request)` 的 UI 实现。 -- `UserInteractionError`：`HarnessError` 的子类，包含 `EMPTY_QUESTIONS`、`NO_PROVIDER`、`DUPLICATE_PROVIDER` 和 `ASK_ABORTED` 等代码。 +- `UserInteractionError`：`HarnessError` 的子类，包含 `EMPTY_QUESTIONS`、`BAD_INTENT`、`NO_PROVIDER`、`DUPLICATE_PROVIDER` 和 `ASK_ABORTED` 等代码。 当回答包含 `custom` 时，`selected` 为空；自定义文本是所选选项的替代，而不是补充。UI 可以把跳过的条目保留为 `{ id, selected: [] }`，既维持现有回答形态，也保留该批次中的其他回答。 +### 呈现意图 + +`intent` 声明某个问题本身就是一次已知形状的决定，因此认识该标签的 UI 可以照此呈现 —— `plan-review` 表示 `detail` 是一份待审阅的计划，`dsh-plan-mode` 会在 `exit_plan_mode` 的问题上设置它。意图只塑造呈现：遵循它的 UI 回答的仍是通用 UI 会发送的那些选项标签，不认识该标签的 UI 渲染通用选项列表，因此调用方两种情况下读到的都是同一种回答形态。`approve` 指名表示批准的标签，而不依赖选项顺序；由于没有类型能把两者绑定起来，`ask()` 会以 `BAD_INTENT` 拒绝 `approve` 未命中该问题自身任一选项的意图。 + ## 职责 这是接口包（package）。`@deepseek-ai/dsh-tool-ask-user` 等面向模型的消费方依赖此 seam；`dsh-tui` 和宿主运行时提供交互式实现。循环保持不变：工具调用等待 Promise，工具结果随后恢复正常的 agent loop（智能体循环）。 diff --git a/packages/ui/user-interaction/src/index.ts b/packages/ui/user-interaction/src/index.ts index 4b5caf6a55..af0aa40e7b 100644 --- a/packages/ui/user-interaction/src/index.ts +++ b/packages/ui/user-interaction/src/index.ts @@ -20,7 +20,8 @@ declare module 'cordis' { import type { AskUserQuestionAnswer, AskUserQuestionItem } from './types.ts' export type { - AskUserQuestionAnswer, AskUserQuestionAnswerItem, AskUserQuestionItem, AskUserQuestionOption, + AskUserQuestionAnswer, AskUserQuestionAnswerItem, AskUserQuestionIntent, AskUserQuestionItem, + AskUserQuestionOption, } from './types.ts' /** Request for a human answer. */ @@ -86,6 +87,20 @@ export class UserInteractionService extends Service { if (request.questions.length === 0) { throw new UserInteractionError('ask_user_question requires at least one question', 'EMPTY_QUESTIONS') } + // A presentation intent names an option label the types cannot pin to its + // own question's option list. A UI honouring the intent answers with that + // label, so a name matching nothing would answer a choice the asker never + // offered — caught here, at the asker, rather than in a UI. + for (const question of request.questions) { + const intent = question.intent + if (intent === undefined) continue + if (!(question.options ?? []).some(option => option.label === intent.approve)) { + throw new UserInteractionError( + `question ${question.id} declares intent ${intent.kind} whose approve label ` + + `${JSON.stringify(intent.approve)} names none of its options`, + 'BAD_INTENT') + } + } if (this.provider === undefined) { throw new UserInteractionError('no user-interaction provider is registered', 'NO_PROVIDER') } diff --git a/packages/ui/user-interaction/src/types.ts b/packages/ui/user-interaction/src/types.ts index ddf3e43489..15747e371c 100644 --- a/packages/ui/user-interaction/src/types.ts +++ b/packages/ui/user-interaction/src/types.ts @@ -13,6 +13,24 @@ export interface AskUserQuestionOption { description?: string } +/** + * A caller-declared presentation intent: the question IS a decision of this + * shape, so a UI that recognises the tag may present it as such instead of as a + * generic option list. Tagged so further intents can be added; a UI that does + * not know a tag renders the generic flow, and the answer encoding is identical + * either way — an intent shapes presentation only, never the protocol. + */ +export type AskUserQuestionIntent = { + /** A plan submitted for review: `detail` is the plan markdown, and the decision approves or declines it. */ + kind: 'plan-review' + /** + * The option label that approves the plan; every other option declines it. + * Named rather than positional so no UI infers the verdict from option order. + * An `approve` naming no option of its own question is rejected at `ask()`. + */ + approve: string +} + /** One question in a user-interaction request. */ export interface AskUserQuestionItem { /** Stable caller-provided question id, echoed in the answer. */ @@ -27,6 +45,8 @@ export interface AskUserQuestionItem { options?: AskUserQuestionOption[] /** Whether more than one option may be selected. Defaults to single-select. */ multiSelect?: boolean + /** Optional presentation intent for capable UIs; absent asks for the generic option list. */ + intent?: AskUserQuestionIntent } /** Answer to one question. */ diff --git a/packages/ui/user-interaction/tests/user-interaction.spec.ts b/packages/ui/user-interaction/tests/user-interaction.spec.ts index adfbc9d4bb..e9fca39761 100644 --- a/packages/ui/user-interaction/tests/user-interaction.spec.ts +++ b/packages/ui/user-interaction/tests/user-interaction.spec.ts @@ -83,4 +83,45 @@ describe('UserInteractionService', () => { .rejects.toMatchObject({ name: 'UserInteractionError', code: 'EMPTY_QUESTIONS' }) expect(p.ask).not.toHaveBeenCalled() }) + + it('rejects an intent whose approve label names none of its own options', async () => { + const ctx = new Context() + await ctx.plugin(UserInteractionService) + const p = { ask: vi.fn(async () => ({ answers: [] })) } + ctx.userInteraction.registerProvider(p) + const question = { id: 'plan-review', question: 'Approve?', detail: '# Plan' } + + // A wrong label among offered options, and no options offered at all. + for (const options of [[{ label: 'Approve' }], undefined]) { + await expect(ctx.userInteraction.ask({ + questions: [{ + ...question, + ...(options === undefined ? {} : { options }), + intent: { kind: 'plan-review', approve: 'Ship it' }, + }], + })).rejects.toMatchObject({ name: 'UserInteractionError', code: 'BAD_INTENT' }) + } + expect(p.ask).not.toHaveBeenCalled() + }) + + it('passes an intent through once its approve label names an offered option', async () => { + const ctx = new Context() + await ctx.plugin(UserInteractionService) + const p = provider('Approve') + ctx.userInteraction.registerProvider(p) + const intent = { kind: 'plan-review', approve: 'Approve' } as const + + const result = await ctx.userInteraction.ask({ + questions: [ + { id: 'plain', question: 'Proceed?' }, + { + id: 'plan-review', question: 'Approve?', detail: '# Plan', + options: [{ label: 'Approve' }, { label: 'Keep planning' }], intent, + }, + ], + }) + + expect(result.answers).toEqual([{ id: 'plain', selected: ['Approve'] }]) + expect(p.seen[0]?.questions[1]?.intent).toEqual(intent) + }) }) diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index d886b33df2..8a5eebdd7d 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -694,6 +694,11 @@ "symbol": "AskUserQuestionOption", "source": "packages/ui/user-interaction/src/types.ts" }, + { + "doc": "docs/core-data-structures/user-interaction.md", + "symbol": "AskUserQuestionIntent", + "source": "packages/ui/user-interaction/src/types.ts" + }, { "doc": "docs/core-data-structures/user-interaction.md", "symbol": "AskUserQuestionItem", From 2363ef01eb14560ecce3cdede09b48a3280122e5 Mon Sep 17 00:00:00 2001 From: creatixchu Date: Thu, 30 Jul 2026 19:09:35 +0800 Subject: [PATCH 09/24] feat(web): render a plan review as a decision card, not a quiz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Web composer now renders a request that declares the `plan-review` intent as its own surface: the waiting-approval card language — amber "Plan review" strip, the plan as the scrolling markdown body, the question as the card's accessible name — over one decision row of Chat about it / Refuse / Approve. Gone from that surface are the 1/1 pager, the numbered radio rows, the custom answer row, and Skip/Submit, which made approving a plan read as sitting an exam. Approve and Refuse answer with the asker's own option labels and keep its descriptions as tooltips; Chat about it cancels the request so the composer returns and the user can simply say what they want. Copy is bilingual under the existing `question` namespace. The shape choice lives inside the single composer entry rather than a second chain registration, so the two surfaces cannot race the same carrier, and `planReviewOf` falls back to the generic flow for any request it cannot render as a card — the client sits downstream of a wire boundary and every request must stay answerable. --- ...-plan-review-presentation-intent.i18n.yaml | 6 + ...6-07-30-plan-review-presentation-intent.md | 55 +++++ ...7-30-plan-review-presentation-intent.zh.md | 55 +++++ apps/web/tests/plan-review.e2e.ts | 113 +++++++++ .../plan-review/approved.expected.md | 51 ++++ .../snapshots/plan-review/review.expected.md | 44 ++++ .../tests/snapshots/plan-review/session.jsonl | 39 ++++ packages/client/ui-question/README.i18n.yaml | 4 +- packages/client/ui-question/README.md | 2 + packages/client/ui-question/README.zh.md | 2 + .../src/client/PlanReviewPanel.module.css | 113 +++++++++ .../src/client/PlanReviewPanel.tsx | 100 ++++++++ .../src/client/QuestionComposer.tsx | 17 +- .../ui-question/src/client/contract/slots.ts | 59 +++++ .../client/ui-question/src/client/index.ts | 12 +- .../client/ui-question/src/client/locales.ts | 8 + .../tests/plan-review-panel.spec.tsx | 221 ++++++++++++++++++ 17 files changed, 894 insertions(+), 7 deletions(-) create mode 100644 .agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.i18n.yaml create mode 100644 .agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.md create mode 100644 .agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.zh.md create mode 100644 apps/web/tests/plan-review.e2e.ts create mode 100644 apps/web/tests/snapshots/plan-review/approved.expected.md create mode 100644 apps/web/tests/snapshots/plan-review/review.expected.md create mode 100644 apps/web/tests/snapshots/plan-review/session.jsonl create mode 100644 packages/client/ui-question/src/client/PlanReviewPanel.module.css create mode 100644 packages/client/ui-question/src/client/PlanReviewPanel.tsx create mode 100644 packages/client/ui-question/tests/plan-review-panel.spec.tsx diff --git a/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.i18n.yaml b/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.i18n.yaml new file mode 100644 index 0000000000..3de0b88f5c --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.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/2026-07-30-plan-review-presentation-intent.md +2026-07-30-plan-review-presentation-intent.md: aa85156d87a35d049f3cfab465fc668a63781a73 +2026-07-30-plan-review-presentation-intent.zh.md: fffee3de6341d45b26b88e1cc67a3895e747afac diff --git a/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.md b/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.md new file mode 100644 index 0000000000..aa85156d87 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.md @@ -0,0 +1,55 @@ +# Agent Note: Plan review as a decision, not a question + +Status: implemented + +English | [中文](2026-07-30-plan-review-presentation-intent.zh.md) + +## Problem + +`exit_plan_mode` presents a finished plan for review through `ctx.userInteraction.ask()`, the same seam `ask_user_question` uses. On the Web GUI that made a plan review render as the generic question flow of [the ask-question Web presentation](2026-07-29-ask-question-web-presentation.md): a `1 / 1` pager, the plan as a question's supporting detail, the two verdicts as numbered radio rows with descriptions, an "Other — enter a custom answer" row, and `Skip this question` / `Submit` in the footer. + +Every one of those affordances is wrong for the surface. Reviewing a plan is one decision over one document, and the quiz chrome told the user they were being examined rather than asked to approve work — reported as "让人很困惑以为在做题". The paging controls page a set of one. Skipping is not an outcome the tool accepts (it folds into keep-planning). Worst, the surface gave no hint that this was the plan gate at all, while the adjacent waiting-approval takeover already had exactly the right shape for a decision: a tinted strip naming what is being decided, the subject as the body, and a right-aligned action row. + +## Decision + +A question may declare a **presentation intent**, and the Web composer renders a declared intent as its own surface. `AskUserQuestionItem` gains `intent?: AskUserQuestionIntent`, a tagged shape whose one member is `{ kind: 'plan-review', approve: string }`; `plan-mode` sets it on the review question, naming `Approve` as the label that approves. + +An intent shapes presentation only. The answer protocol is untouched: a UI honouring the intent answers with the same option labels a generic UI would send, so `exit_plan_mode` reads one answer shape regardless of which surface collected it, and a UI that does not know a tag renders the generic flow with nothing lost but the layout. + +`approve` names the affirmative option instead of relying on option order, so no UI infers a verdict from a position. Because the types cannot tie that label to the question's own option list, `UserInteractionService.ask()` rejects an intent whose `approve` names none of its options (`BAD_INTENT`) — at the asker, before any UI can answer a choice that was never offered. On the wire the intent is a discriminated union, so an unrecognised tag is a rejected frame rather than a silently generic render. + +`ui-question` renders the intent as `PlanReviewPanel`, in the waiting-approval card language: the amber strip carries `Plan review`, the plan is the scrolling markdown body, and the decision row holds three actions — `Chat about it`, `Refuse`, `Approve`. The question text becomes the card's accessible name rather than a headline, because the buttons already say what the decision is. Approve and Refuse answer with the asker's own option labels and keep the asker's descriptions as tooltips; `Chat about it` cancels the request, which returns the composer so the user can simply say what they want. All copy is bilingual under the existing `question` namespace. + +Routing lives inside the single composer entry (`QuestionComposer` chooses the shape) rather than in a second chain registration, and `planReviewOf` claims a request only when the batch is one question that declares the intent, carries the plan as its `detail`, and offers the named approve label. Anything else stays a generic question — the client is downstream of a wire boundary, so a request it cannot render as a card must still be answerable. + +Dismissal became its own model-facing outcome. `ASK_CANCELLED` previously reached the model as "the user cancelled ask_user_question", naming a tool it never called; `exit_plan_mode` now reports that the user dismissed the review to speak instead and to stay in plan mode and wait. Every other ask failure — an abort from turn cancel or provider teardown, where no user is coming — keeps its own message. + +## Alternatives considered + +**Make plan review its own pending kind (`plan-review/requested`).** Rejected as the wrong size for a presentation problem. It buys an honest response shape (approve / decline / discuss instead of an answer batch) at the cost of a third `PendingKind`, new requested/resolved frames and schemas, an api-proxy registry and respond branch, client session and baseline-replay handling, and a new three-package capability seam for a decision the question protocol already expresses. Worth revisiting only if plan review grows outcomes the answer shape cannot carry. + +**Route the card on the question's `id` or `header` (`plan-review` / `Plan review`).** Rejected: string-sniffing a foreign package's copy across a wire boundary, which any wording change silently breaks. The intent is the declaration that makes the routing legible. + +**Order the options and let the card read position 0 as approve.** Rejected: a positional contract at a package seam, invisible in both the type and the wire frame, and unenforceable — a producer that reorders its options would invert a user's verdict. Naming the label costs one string. + +**Register a second composer-chain entry for the plan card.** Rejected: two entries would select over the same pending question carrier, making the surface depend on chain priority and on whether the plan package's client half is composed at all. One entry that picks its own shape cannot race itself, and the generic flow is the built-in fallback. + +**Put the panel in `ui-plan` beside the plan chip.** Rejected: the panel's whole behavior is the question carrier's answer encoding (`PendingQuestion`), which `ui-question` owns; the intent is a question-protocol field, not plan-mode's private channel. Rendering declared intents belongs to the package that owns question rendering, as tool render intents belong to the tool renderer. + +**Extract a shared takeover card with `ui-conversation`'s `ApprovalPanel`.** Not done: the two takeovers agree on tokens and geometry but not on content — this body is scrolling markdown, that one a headline plus a command line — and the shared shell would be two elements wide. They are kept in step by token, not by component. + +**Give `Chat about it` its own protocol outcome.** Rejected: dismissing a request is a verb the generic flow already has (the `×` that cancels the batch). Promoting it to a labelled button is presentation; inventing a fourth wire outcome for it is not. + +## Consequences + +The question protocol now carries a presentation axis. Adding a second intent is a tag on the union, a producer that sets it, a schema member, and a panel — no new frame, service, or answer shape. The cost is that the question seam knows presentation exists at all, and that `ui-question` knows the word "plan"; both are the price of one entry owning every question surface. + +The plan gate reads as a plan gate: the plan is the card's content, the verdict is two labelled buttons, and taking the turn back is a third. The generic flow is untouched for every other question, and its committed goldens did not move. + +A deployment whose client half predates this change still shows the quiz layout — correct, answerable, and merely unstyled — because the intent is additive and the fallback is the generic flow. + +## Testing + +`ui-question` tests pin the narrowing (single-question batch, intent present, plan as detail, named approve label offered, decline absent when only approve is offered) and the panel (strip, markdown plan, accessible name, absence of pager/radio/skip/custom, approve and decline answering with the asker's labels, dismissal cancelling, one-shot latch with re-arm and message on a rejected receipt, tooltips present and absent, both locales). `user-interaction` tests pin `BAD_INTENT` and intent pass-through; `plan-mode` tests pin the declared intent against its own option list and both failure messages; the apiproxy schema test pins wire acceptance and an unknown tag's rejection. + +The `plan-review` Web e2e lane records `/plan` entering plan mode for real, the model calling `exit_plan_mode`, the decision card taking the composer (asserting the generic flow did **not** claim the request), and the card's own Approve completing the turn — two keyless goldens, the waiting card and the approved transcript. diff --git a/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.zh.md b/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.zh.md new file mode 100644 index 0000000000..fffee3de63 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.zh.md @@ -0,0 +1,55 @@ +# Agent Note：计划审阅是一次决定，不是一道题 + +Status: implemented + +[English](2026-07-30-plan-review-presentation-intent.md) | 中文 + +## 问题 + +`exit_plan_mode` 通过 `ctx.userInteraction.ask()` 把写好的计划交给用户审阅，而这正是 `ask_user_question` 使用的同一个 seam。在 Web GUI 上，这导致计划审阅渲染为[ask-question Web 呈现](2026-07-29-ask-question-web-presentation.md)里的通用问题流程：一个 `1 / 1` 分页器、计划作为问题的补充说明、两个裁决作为带描述的编号单选行、一行"其他，请填写自定义答案"，以及底部的 `跳过本题` / `提交`。 + +这些可交互元素对这个界面而言无一正确。审阅一份计划是对一份文档做一次决定，而做题式的界面告诉用户他正在被考试，而不是被请求批准一份工作 —— 实际反馈是"让人很困惑以为在做题"。分页控件在给只有一项的集合分页。跳过并不是该工具接受的结果（它会折叠成继续规划）。最糟的是，这个界面完全没有暗示这就是计划关口，而旁边的等待审批接管早就具备了一次决定该有的形状：一条带色条带说明正在决定什么、主体是决定的对象、右对齐的操作行。 + +## 决定 + +一个问题可以声明**呈现意图（presentation intent）**，Web 输入区把已声明的意图渲染为它自己的界面。`AskUserQuestionItem` 新增 `intent?: AskUserQuestionIntent`，一个带标签的形状，目前唯一成员是 `{ kind: 'plan-review', approve: string }`；`plan-mode` 在审阅问题上设置它，并指明 `Approve` 是表示批准的标签。 + +意图只塑造呈现。回答协议不变：遵循意图的 UI 回答的仍是通用 UI 会发送的那些选项标签，因此无论由哪个界面收集，`exit_plan_mode` 读到的都是同一种回答形状；而不认识某个标签的 UI 渲染通用流程，除布局之外一无所失。 + +`approve` 指名肯定选项，而不依赖选项顺序，因此没有任何 UI 会从位置推断裁决。由于类型无法把该标签绑定到问题自身的选项列表，`UserInteractionService.ask()` 会拒绝 `approve` 未命中任一选项的意图（`BAD_INTENT`）—— 拦在提问方一侧，早于任何 UI 回答一个从未被提供过的选择。在协议格式（wire format）上意图是可辨识联合，因此无法识别的标签是被拒绝的帧，而不是静默退回通用渲染。 + +`ui-question` 把该意图渲染为 `PlanReviewPanel`，沿用等待审批卡片的语言：琥珀色条带写着 `Plan review`，计划是可滚动的 markdown 主体，决定行放三个操作 —— `Chat about it`、`Refuse`、`Approve`。问题文本成为卡片的无障碍名称而非标题，因为按钮已经说明了这次决定是什么。Approve 与 Refuse 用提问方自己的选项标签回答，并把提问方的描述保留为 tooltip；`Chat about it` 取消该请求，从而让输入区归位，用户直接说他想说的话即可。所有文案在既有 `question` 命名空间下双语。 + +路由住在单一输入区条目内部（由 `QuestionComposer` 选择形状），而不是第二个链式注册；`planReviewOf` 仅在这一批只有一个问题、该问题声明了意图、以 `detail` 承载计划、并提供了被指名的批准标签时才接管请求。其他情形一律保持通用问题 —— 客户端位于协议边界的下游，它无法渲染成卡片的请求仍必须可回答。 + +放弃审阅成为面向模型的独立结果。`ASK_CANCELLED` 以前传到模型的是"the user cancelled ask_user_question"，指名了一个它从未调用的工具；现在 `exit_plan_mode` 报告用户放弃审阅是为了改用说话，并要求留在 plan mode 中等待。其余每一种 ask 失败 —— 轮次取消或提供方拆卸导致的中止，那里并没有用户会来 —— 保留它们自己的消息。 + +## 备选方案 + +**让计划审阅成为自己的待处理种类（`plan-review/requested`）。** 否决：对一个呈现问题来说尺寸不对。它换来的是诚实的响应形状（approve / decline / discuss 而非一批回答），代价是第三个 `PendingKind`、新的 requested/resolved 帧与 schema、一个 api-proxy 注册表与响应分支、客户端会话与基线重放处理，以及为一个问题协议已能表达的决定新增一个三包能力 seam。只有当计划审阅长出回答形状承载不了的结果时才值得重新考虑。 + +**按问题的 `id` 或 `header`（`plan-review` / `Plan review`）路由卡片。** 否决：这是跨协议边界嗅探另一个包的文案字符串，任何措辞改动都会静默破坏它。意图才是让路由可读的那个声明。 + +**约定选项顺序，让卡片把第 0 个位置读作批准。** 否决：这是包边界上的位置约定，在类型和协议帧里都看不见，也无法强制 —— 生产方一旦重排选项，就会颠倒用户的裁决。指名标签只花一个字符串。 + +**为计划卡片注册第二个输入区链条目。** 否决：两个条目会对同一个待回答问题载体做选择，使界面取决于链优先级、以及计划包的客户端半边是否被组合。一个自己挑形状的条目不会和自己抢，而通用流程正是内建的回退。 + +**把面板放在 `ui-plan` 里、紧挨计划状态标签。** 否决：面板的全部行为就是问题载体的回答编码（`PendingQuestion`），那是 `ui-question` 拥有的；意图是问题协议的字段，不是 plan-mode 的私有通道。渲染已声明的意图属于拥有问题渲染的那个包，正如工具渲染意图属于工具渲染方。 + +**与 `ui-conversation` 的 `ApprovalPanel` 抽出共享的接管卡片。** 未做：两个接管在 token 和几何上一致，但内容不一致 —— 这边的主体是可滚动 markdown，那边是一行标题加一行命令 —— 共享外壳只会剩两个元素宽。它们靠 token 保持一致，而不是靠组件。 + +**给 `Chat about it` 自己的协议结果。** 否决：放弃一个请求是通用流程已有的动词（取消整批的 `×`）。把它提升为带标签的按钮属于呈现；为它发明第四种协议结果不属于。 + +## 结果 + +问题协议从此带有一个呈现轴。新增第二个意图 = 联合上的一个标签、一个设置它的生产方、一个 schema 成员、一个面板 —— 不需要新的帧、服务或回答形状。代价是问题 seam 从此知道"呈现"这件事存在，且 `ui-question` 知道"plan"这个词；两者都是由单一条目拥有全部问题界面所要付的价钱。 + +计划关口读起来就像计划关口：计划是卡片的内容，裁决是两个带标签的按钮，把轮次拿回来是第三个。通用流程对其他每个问题都未受影响，其已提交的 golden 也没有变动。 + +客户端半边早于本次改动的部署仍然显示做题式布局 —— 正确、可回答、只是没有专门样式 —— 因为意图是增量的，而回退就是通用流程。 + +## 测试 + +`ui-question` 测试钉住收窄（单问题批、意图存在、计划作为 detail、被指名的批准标签确实被提供、只提供批准时 decline 缺席）与面板（条带、markdown 计划、无障碍名称、无分页/单选/跳过/自定义、批准与拒绝用提问方的标签回答、放弃触发取消、一次性闭锁在回执被拒时重新武装并给出消息、tooltip 有与无、两种语言）。`user-interaction` 测试钉住 `BAD_INTENT` 与意图透传；`plan-mode` 测试钉住已声明的意图与其自身选项列表的一致、以及两条失败消息；apiproxy schema 测试钉住协议接受与未知标签的拒绝。 + +`plan-review` Web e2e 通道录制了 `/plan` 真实进入 plan mode、模型调用 `exit_plan_mode`、决定卡片接管输入区（并断言通用流程**没有**接管该请求）、以及卡片自身的 Approve 完成该轮 —— 两份无密钥 golden：等待中的卡片与批准后的会话记录。 diff --git a/apps/web/tests/plan-review.e2e.ts b/apps/web/tests/plan-review.e2e.ts new file mode 100644 index 0000000000..28272777fb --- /dev/null +++ b/apps/web/tests/plan-review.e2e.ts @@ -0,0 +1,113 @@ +// Web e2e scenario: the plan-review takeover. The shipped composition mounts +// plan mode and its client seat, so `/plan ` enters plan mode for real +// and the recorded turn ends on exit_plan_mode blocking against the live +// userInteraction seam. The composer is then occupied by the plan decision +// card — not the generic question flow — and approving it through the card +// completes the turn with the approval in the log. +// Replay is deterministic: the plan content arrives from replayed chunks, the +// review wait is real, and the approve click is the test's own gesture (the +// turn cannot complete without it, in record and replay alike). +import { readFile } from 'node:fs/promises' +import { fileURLToPath } from 'node:url' +import { join } from 'node:path' +import type { Browser, Page } from 'playwright' +import { chromium } from 'playwright' +import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest' +import type { SessionEvent } from '@deepseek-ai/dsh-session' +import { + assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts, + launchWebScaffold, recordFixture, watchConsole, webSnapshotMode, type WebScaffold, +} from './scaffold.ts' +import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts' + +const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/plan-review', import.meta.url)) +const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl') +// The waiting golden owns the decision card; the approved golden owns the +// transcript the approval leaves behind — the state the card cannot see. +const REVIEW_EXPECTED = join(SNAPSHOT_DIR, 'review.expected.md') +const APPROVED_EXPECTED = join(SNAPSHOT_DIR, 'approved.expected.md') +const MODE = webSnapshotMode() + +// One command line: /plan enters plan mode and submits the rest as the turn's +// message. The task is deliberately self-contained (nothing to explore in a +// fresh workspace) so the recorded turn is a plan and its review, and the +// approved continuation is one word. +const TASK = 'Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. ' + + 'Call exit_plan_mode with a short plan of at most five bullet points. ' + + 'Once the plan is approved, reply with the single word DONE and stop.' +const LINE = `/plan ${TASK}` + +describe('web e2e: plan review takeover round trip', () => { + let scaffold: WebScaffold + let browser: Browser + let page: Page + let tripwire: ReturnType + const sessionEvents: SessionEvent[] = [] + + beforeAll(async () => { + scaffold = await launchWebScaffold(MODE === 'record' ? {} : { replayFixture: FIXTURE, paceMs: 15 }) + scaffold.ctx.on('session/event', (_session, event: SessionEvent) => { sessionEvents.push(event) }) + browser = await chromium.launch() + // English page: the decision copy is the surface under test, and the + // golden pins one language. + page = await newEnglishPage(browser) + tripwire = watchConsole(page) + await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) + await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) + await connectFreshWorkspace(page) + }, 120_000) + + afterAll(async () => { + await browser?.close() + await scaffold?.close() + }) + + it('reviews the plan on a decision card and approves through it', async () => { + onTestFailed(() => saveFailureShot(page, 'web-e2e-plan-review')) + if (MODE !== 'record') { + expect(fixtureUserPrompts(await readFile(FIXTURE, 'utf8'))).toEqual([TASK]) + } + const input = page.locator('textarea').first() + await input.waitFor({ timeout: 10_000 }) + const settled = scaffold.whenTurnSettled(MODE === 'record' ? 180_000 : 30_000) + await input.fill(LINE) + await input.press('Enter') + + // The card takes over the input area while exit_plan_mode blocks. Its + // presence is a STABLE waiting state (it stays until answered), so a plain + // waitFor is race-free. + const card = page.locator('[data-plan-review-key]') + await card.waitFor({ timeout: MODE === 'record' ? 120_000 : 30_000 }) + // The plan-review request must NOT land on the generic question flow. + expect(await page.locator('[data-question-key]').count()).toBe(0) + await expect.poll(() => card.getByText('Plan review').count(), { timeout: 10_000 }).toBeGreaterThan(0) + + if (MODE !== 'record') { + const snapshot = await captureStableAria(page, '[data-plan-review-key]', scaffold.workspaceCwd) + await compareOrRefreshGolden(REVIEW_EXPECTED, snapshot, MODE) + } + + await card.getByRole('button', { name: 'Approve' }).click() + + const sessionId = await settled + if (MODE === 'record') { + await recordFixture(scaffold, sessionId, FIXTURE) + return + } + // World state: the approval reached the tool, and plan mode is left behind. + const results = sessionEvents.filter(e => e.type === 'tool/result') + expect(JSON.stringify(results.at(-1))).toContain('Plan approved') + await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1) + // Card gone; regular input restored. + expect(await page.locator('[data-plan-review-key]').count()).toBe(0) + await expect.poll(() => page.locator('textarea').first().isEnabled(), { timeout: 10_000 }).toBe(true) + const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd) + await compareOrRefreshGolden(APPROVED_EXPECTED, snapshot, MODE) + expect(tripwire.pageErrors).toEqual([]) + expect(tripwire.warnings).toEqual([]) + }, 200_000) + + it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => { + await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'review.expected.md', 'approved.expected.md']) + }) +}) diff --git a/apps/web/tests/snapshots/plan-review/approved.expected.md b/apps/web/tests/snapshots/plan-review/approved.expected.md new file mode 100644 index 0000000000..aca0bc31bb --- /dev/null +++ b/apps/web/tests/snapshots/plan-review/approved.expected.md @@ -0,0 +1,51 @@ +- banner: + - navigation "Session hierarchy": + - 'button "Plan a small change: add" [disabled]' + - tablist: + - tab "Chat" [selected] + - tab "Trajectory" +- img +- text: "/plan Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop. Plan mode on. Use /plan off to leave. Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop. {{clock}}" +- button "复制": + - img +- button "在新对话中分支": + - img +- button "编辑": + - img +- 'button "Think The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."': + - img + - img + - text: "Think The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly." +- paragraph: + - text: Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with + - code: exit_plan_mode + - text: . +- button "复制": + - img +- button "在新对话中分支": + - img +- text: {{clock}} +- button: + - img + - img +- text: "Tool call exit_plan_mode · # Add `--greeting` flag to CLI" +- 'button "Think The plan was approved. The user''s last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."': + - img + - img + - text: "Think The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop." +- paragraph: DONE +- button "复制": + - img +- button "在新对话中分支": + - img +- text: {{clock}} +- textbox "Message the agent" +- button "Add attachment": + - img +- 'button "Access mode, current: Danger Full Access"': Danger Full Access +- button "Plan mode off, press to turn on": Plan off +- button "Select model, current DeepSeek-V4-Flash": + - text: DeepSeek-V4-Flash + - img +- button "Send message" [disabled] +- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 51% Input 10.2K tok · Output 346 tok diff --git a/apps/web/tests/snapshots/plan-review/review.expected.md b/apps/web/tests/snapshots/plan-review/review.expected.md new file mode 100644 index 0000000000..81d3af911c --- /dev/null +++ b/apps/web/tests/snapshots/plan-review/review.expected.md @@ -0,0 +1,44 @@ +- region "Approve this plan and leave plan mode?": + - text: Plan review + - heading "Add --greeting flag to CLI" [level=1]: + - text: Add + - code: "--greeting" + - text: flag to CLI + - list: + - listitem: + - strong: Locate the CLI entry point + - text: (e.g., + - code: cli.py + - text: "," + - code: main.go + - text: "," + - code: index.js + - text: etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar). + - listitem: + - strong: Register a new optional string argument + - text: named + - code: "--greeting" + - text: with a short alias ( + - code: "-g" + - text: if available) and a sensible default value (e.g., + - code: "\"Hello\"" + - text: ). + - listitem: + - strong: Thread the parsed value + - text: through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message). + - listitem: + - strong: Update the help text + - text: so + - code: "--help" + - text: or + - code: "-h" + - text: shows the new flag with its description. + - listitem: + - strong: No tests or config changes + - text: unless they already exist and directly validate the flag's presence. + - status + - button "Chat about it": + - img + - text: Chat about it + - button "Refuse" + - button "Approve" diff --git a/apps/web/tests/snapshots/plan-review/session.jsonl b/apps/web/tests/snapshots/plan-review/session.jsonl new file mode 100644 index 0000000000..960c05393f --- /dev/null +++ b/apps/web/tests/snapshots/plan-review/session.jsonl @@ -0,0 +1,39 @@ +{"type":"session","version":0,"id":"{{sessionId}}","createdAt":1785406804293,"cwd":"{{cwd}}/workspace"} +{"type":"command/run","seq":0,"time":1785406804350,"data":{"commandId":"cmd-228a60ef-1","name":"plan","args":" Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop.","source":{"kind":"user"}}} +{"type":"plan/mode","seq":1,"time":1785406804350,"data":{"active":true}} +{"type":"command/done","seq":2,"time":1785406804352,"data":{"commandId":"cmd-228a60ef-1","kind":"success","text":"Plan mode on. Use /plan off to leave."}} +{"type":"turn/start","seq":3,"time":1785406804353,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":4,"time":1785406804353,"data":{"content":[{"type":"text","text":"Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"a22bd0d2-15dc-4bfb-b978-0d5961459e57"},"surfaceOp":"append"} +{"type":"session/title","seq":5,"time":1785406804354,"data":{"title":"Plan a small change: add","messageSeqs":[4],"source":{"kind":"fallback"}}} +{"type":"step/start","seq":6,"time":1785406804355,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":7,"time":1785406804356,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash","reasoningEffort":"high"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":8,"time":1785406805697,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"reasoning-chunks","seq0":9,"time0":1785406805698,"data":{"turn":1,"step":1,"index":0,"dt":[151,31,0,0,0,0,18,1,0,0,0,31,1,0,0,0,1,23,0,0,0,19,0,0,37,1,0,0,0,0,12,1,0,0,28,0,1,0,24,1,0,0,0,0,26,1,0,0,26,1,22],"texts":["The"," user"," wants"," me"," to"," plan"," a"," small"," change"," to"," add"," a"," `","--","gre","eting","`"," flag"," to"," a"," CLI","."," They"," explicitly"," told"," me"," not"," to"," read"," or"," write"," any"," files",","," and"," to"," call"," exit","_","plan","_mode"," with"," a"," short"," plan","."," Let"," me"," do"," that"," directly","."]}} +{"type":"assistant/chunk","seq":61,"time":1785406806155,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"text-chunks","seq0":62,"time0":1785406806156,"data":{"turn":1,"step":1,"index":1,"dt":[0,20,0,34,23,26,0,1,0,0,28,0,0,0,32,0,15,1,0,30,1,0,0,23,1,0,24,0,0,0],"texts":["Since"," the"," user"," has"," explicitly"," asked"," me"," not"," to"," read"," or"," write"," any"," files"," and"," to"," go"," straight"," to"," planning",","," I","'ll"," proceed"," with"," `","exit","_","plan","_mode","`."]}} +{"type":"assistant/chunk","seq":93,"time":1785406806493,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":2,"blockType":"tool-call"}}} +{"type":"tool-call-chunks","seq0":94,"time0":1785406806493,"data":{"turn":1,"step":1,"index":2,"dt":[27,1,0,0,0,24,0,0,29,1,0,0,0,1,20,0,27,1,0,21,28,0,0,31,1,23,0,0,1,23,0,0,0,23,1,0,28,20,26,28,1,0,29,1,0,0,21,28,0,0,25,1,26,1,0,0,24,1,0,26,0,0,0,1,23,1,0,0,22,29,0,31,1,1,0,21,1,0,0,0,0,20,0,32,25,0,0,22,0,0,27,0,1,0,31,0,1,0,0,20,1,0,0,0,0,24,0,1,0,26,1,29,1,26,1,0,25,30,1,18,0,30,0,0,30,21,1,28,0,21,1,0,0,23,1,23,36,0,0,1,0,13,1,28,27,0,0,25,1,45,1,11,0,21,0,0,0,0,23,0,0,32,1,0,0,0,16,28,0,27,1,0,22,31,1,24,1,21,32,1,0,24,1,0,24],"id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","args":["","{","\"","plan","\"",": ","\"","#"," Add"," `","--","gre","eting","`"," flag"," to"," CLI","\\n\\n","-"," **","Loc","ate"," the"," CLI"," entry"," point","**"," (","e",".g",".,"," `","cli",".py","`,"," `","main",".go","`,"," `","index",".js","`"," etc",".)"," and"," find"," the"," argument"," parser"," definition"," (","arg","parse",","," click",","," cob","ra",","," y","args",","," or"," similar",").\\n","-"," **","Register"," a"," new"," optional"," string"," argument","**"," named"," `","--","gre","eting","`"," with"," a"," short"," alias"," (`","-","g","`"," if"," available",")"," and"," a"," sensible"," default"," value"," (","e",".g",".,"," `","\\\"","Hello","\\\"","`",").\\n","-"," **","Thread"," the"," parsed"," value","**"," through"," the"," main"," handler"," function"," so"," it"," is"," passed"," where"," the"," greeting"," string"," is"," used"," (","e",".g",".,"," the"," welcome","/","response"," message",").\\n","-"," **","Update"," the"," help"," text","**"," so"," `","--","help","`"," or"," `","-","h","`"," shows"," the"," new"," flag"," with"," its"," description",".\\n","-"," **","No"," tests"," or"," config"," changes","**"," unless"," they"," already"," exist"," and"," directly"," validate"," the"," flag","'s"," presence",".","\"","}"]}} +{"type":"assistant/chunk","seq":280,"time":1785406808318,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."}}}} +{"type":"assistant/chunk","seq":281,"time":1785406808318,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with `exit_plan_mode`."}}}} +{"type":"assistant/chunk","seq":282,"time":1785406808318,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":2,"block":{"type":"tool-call","id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}}}} +{"type":"assistant/chunk","seq":283,"time":1785406808319,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":4529,"outputTokens":303,"cacheReadTokens":640,"reasoningTokens":52}}}} +{"type":"assistant/chunk","seq":284,"time":1785406808319,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":285,"time":1785406808324,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."},{"type":"text","text":"Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with `exit_plan_mode`."},{"type":"tool-call","id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"b9e18116-68f6-4442-b5a5-a33277ef526c"},"usage":{"inputTokens":4529,"outputTokens":303,"cacheReadTokens":640,"reasoningTokens":52}},"sourceEventSeqs":[8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283,284],"surfaceOp":"append"} +{"type":"tool/call","seq":286,"time":1785406808325,"data":{"turn":1,"step":1,"callId":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}} +{"type":"tool/result","seq":287,"time":1785406808720,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_00_TPh5fH8x5kRezK115kgx8155"},"content":[{"type":"tool-result","toolCallId":"call_00_TPh5fH8x5kRezK115kgx8155","content":[{"type":"text","text":"Plan approved — plan mode exited; carry out the plan starting with your next step."}],"isError":false}],"role":"user","id":"e7cf1f9f-e143-48df-b975-440a9d61a538"}},"sourceEventSeqs":[286],"surfaceOp":"append"} +{"type":"step/end","seq":288,"time":1785406808721,"data":{"turn":1,"step":1}} +{"type":"plan/mode","seq":289,"time":1785406808721,"data":{"active":false}} +{"type":"step/start","seq":290,"time":1785406808723,"data":{"turn":1,"step":2}} +{"type":"request/header","seq":291,"time":1785406808723,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash","reasoningEffort":"high"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}} +{"type":"assistant/chunk","seq":292,"time":1785406809855,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"reasoning-chunks","seq0":293,"time0":1785406809855,"data":{"turn":1,"step":2,"index":0,"dt":[133,28,1,0,0,17,0,28,1,0,0,29,0,0,0,0,0,21,0,0,0,35,0,0,0,0,0,14,1,37,1,0,1,17,0,0,0,0,1],"texts":["The"," plan"," was"," approved","."," The"," user","'s"," last"," instruction"," says",":"," \"","Once"," the"," plan"," is"," approved",","," reply"," with"," the"," single"," word"," D","ONE"," and"," stop",".\""," So"," I"," should"," just"," reply"," with"," D","ONE"," and"," stop","."]}} +{"type":"assistant/chunk","seq":333,"time":1785406810252,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":334,"time":1785406810253,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}} +{"type":"assistant/chunk","seq":335,"time":1785406810253,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":336,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."}}}} +{"type":"assistant/chunk","seq":337,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":338,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":441,"outputTokens":43,"cacheReadTokens":4608,"reasoningTokens":40}}}} +{"type":"assistant/chunk","seq":339,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":340,"time":1785406810257,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."},{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"2d9da552-d236-4166-9d06-dffa9bace4cd"},"usage":{"inputTokens":441,"outputTokens":43,"cacheReadTokens":4608,"reasoningTokens":40}},"sourceEventSeqs":[292,293,294,295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,326,327,328,329,330,331,332,333,334,335,336,337,338,339],"surfaceOp":"append"} +{"type":"step/end","seq":341,"time":1785406810258,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":342,"time":1785406810258,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/packages/client/ui-question/README.i18n.yaml b/packages/client/ui-question/README.i18n.yaml index 26f790b296..cd2f0556a4 100644 --- a/packages/client/ui-question/README.i18n.yaml +++ b/packages/client/ui-question/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-question/README.md -README.md: 0700375758774610fcd897b9a3e16484206a871d -README.zh.md: d9e5eb22cef13e16ab1ce2cebba9e563bd9d08d9 +README.md: 6b40c503be61c2458cefceabbb35e16a3befbe66 +README.zh.md: 7c0c4ee67d1ef8b4507f3899bdb1ae2f76408032 diff --git a/packages/client/ui-question/README.md b/packages/client/ui-question/README.md index 0700375758..6b40c503be 100644 --- a/packages/client/ui-question/README.md +++ b/packages/client/ui-question/README.md @@ -6,6 +6,8 @@ Web `ask_user_question` feature plugin. Its host half mounts `dsh-tool-ask-user` The component renders one question at a time with progress navigation, single- and multi-select choices, recommendation badges derived from label suffixes, and custom answers. Question detail reuses the assistant-output `MarkdownText` primitive, including its GFM rendering and untrusted-content policy. The capped card keeps its title, navigation, and submission actions fixed while long detail and choices share an internal scroll region. Single-select choices advance immediately, and Enter submits once every question is answered or skipped; Enter during IME composition confirms the input candidate without advancing. It submits one structured answer batch for the whole request: “Skip this question” retains other drafts and emits the existing blank `{ selected: [] }` shape for that item, while close rejects the whole wait as `ASK_CANCELLED`. +A request whose single question declares a presentation intent renders as that intent's own surface instead. `plan-review` — set by `dsh-plan-mode` on the `exit_plan_mode` review — takes the waiting-approval card shape: a `Plan review` strip, the plan as the scrolling markdown body, the question text as the card's accessible name, and one decision row of `Chat about it` / `Refuse` / `Approve`. Approve and Refuse answer with the asker's own option labels (the intent names which label approves, so the verdict never rides option order) and keep the asker's descriptions as tooltips; `Chat about it` rejects the wait as `ASK_CANCELLED`, returning the composer so the user can say what they want instead. A request that declares no intent, batches more than one question, or fails to offer the named approve label stays on the generic flow — the layout is all an intent changes, never the answer. + Selection state is local to a component keyed by the request rpcId. A replay with the same id preserves a still-mounted draft, while `question/resolved` from the host removes the composer. The host remains authoritative: successful HTTP delivery does not remove pending state locally. Composer chrome copy (pager, buttons, placeholders, validation feedback) is bilingual: the plugin registers zh/en dictionaries under the `question` namespace of `dsh-client-locale` and hands the entry its bound translator plus the locale snapshot source through the inject face, so a locale switch re-renders a mounted composer. Question and option text arrives from the model and renders verbatim; carrier failure messages also display untranslated. diff --git a/packages/client/ui-question/README.zh.md b/packages/client/ui-question/README.zh.md index d9e5eb22ce..7c0c4ee67d 100644 --- a/packages/client/ui-question/README.zh.md +++ b/packages/client/ui-question/README.zh.md @@ -6,6 +6,8 @@ Web `ask_user_question` 功能插件。只有选择 Web 功能时，其主机侧 组件每次渲染一个问题，提供进度导航、单选和多选选项、由标签后缀派生的推荐徽标，以及自定义答案。问题详情复用助手输出的 `MarkdownText` 原语，包括其 GFM 渲染与不受信内容策略。封顶卡片保持标题、导航与提交动作固定，超长的详情与选项共享内部滚动区。单选选项会立即前进；所有问题均已回答或跳过后，Enter 会提交；IME 输入法组合期间按 Enter 只会确认输入候选，不会前进。组件为整个请求提交一批结构化答案：「跳过此问题」会保留其他草稿，并为该项发出既有的空 `{ selected: [] }` 形状；关闭则以 `ASK_CANCELLED` 拒绝整个等待。 +若某个请求的唯一问题声明了呈现意图，则改为渲染该意图自己的界面。`plan-review` —— 由 `dsh-plan-mode` 在 `exit_plan_mode` 审阅上设置 —— 采用等待审批卡片的形状：一条 `Plan review` 条带、计划作为可滚动的 markdown 主体、问题文本作为卡片的无障碍名称，以及一行 `Chat about it` / `Refuse` / `Approve` 的决定操作。Approve 与 Refuse 用提问方自己的选项标签回答（意图指名哪个标签表示批准，因此裁决绝不依赖选项顺序），并把提问方的描述保留为 tooltip；`Chat about it` 以 `ASK_CANCELLED` 拒绝该等待，让编辑器归位，用户可以直接说出他想说的话。未声明意图、一批含多个问题、或未提供被指名的批准标签的请求，一律留在通用流程上 —— 意图改变的只是布局，从不改变答案。 + 选择状态只存在于以请求 rpcId 为 key 的组件本地。使用相同 id 回放时，只要组件仍挂载，就会保留草稿；主机发出的 `question/resolved` 则会移除编辑器。主机仍具有最终决定权：HTTP 交付成功不会在本地移除待处理状态。 编辑器外框文案（翻页器、按钮、占位符、校验提示）是双语的：插件在 `dsh-client-locale` 的 `question` 命名空间下注册 zh/en 词典，并通过 inject face 把绑定的翻译函数和 locale 快照源交给该配置项，因此切换语言会重新渲染已挂载的编辑器。问题与选项文本来自模型并原样渲染；载体失败消息也不经翻译直接显示。 diff --git a/packages/client/ui-question/src/client/PlanReviewPanel.module.css b/packages/client/ui-question/src/client/PlanReviewPanel.module.css new file mode 100644 index 0000000000..428effab2b --- /dev/null +++ b/packages/client/ui-question/src/client/PlanReviewPanel.module.css @@ -0,0 +1,113 @@ +/* Plan-review takeover: the waiting-approval card language (amber strip on a + floating capsule, right-aligned actions) applied to a reviewed plan. Kept as + its own module rather than shared with ui-conversation's ApprovalPanel: the + two takeovers agree on tokens and geometry, not on content — this one's body + is scrollable markdown, that one's is a headline plus a command line. Warn + semantics ride the alias state tokens; no hardcoded colors. */ + +/* Mirrors the question card's frame so the takeover is a content swap. */ +.frame { + display: flex; + justify-content: center; + padding: 6px 24px 10px; +} + +.card { + display: flex; + overflow: hidden; + flex-direction: column; + width: 100%; + max-width: 776px; + /* Composer seat sits in a fixed-height conversation column (overflow + hidden): cap the card against the viewport and scroll the plan, so the + strip and the decision row stay reachable on a long plan. */ + max-height: min(60vh, 520px); + border: 1px solid var(--dsw-alias-state-warn-secondary); + border-radius: 20px; + background: var(--dsw-specific-input-major); + box-shadow: var(--dsw-shadow-lv2); + color: var(--dsw-alias-label-primary); + /* Elevated surface in dark: the plan body inside scrolls once the card hits + the cap above, so the thumb takes the l2 pair (see ui-theme + styles/scrollbar.css for the rebinding contract). */ + --dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2); + --dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2); +} + +.card, +.card * { + box-sizing: border-box; +} + +/* Tinted full-width header band, as on the approval takeover. */ +.strip { + display: flex; + align-items: center; + flex-shrink: 0; + gap: 8px; + padding: 10px 16px; + background: var(--dsw-alias-state-warn-tertiary); + color: var(--dsw-alias-state-warn-primary); + font-size: 13px; + line-height: 18px; +} + +.dot { + width: 8px; + height: 8px; + border-radius: 50%; + background: var(--dsw-alias-state-warn-primary); +} + +/* The plan is the panel's message: it takes the whole body and the scroll. */ +.body { + flex: 1 1 auto; + min-height: 0; + overflow-y: auto; + overscroll-behavior: contain; + padding: 12px 16px 4px; + font-size: 14px; + line-height: 22px; +} + +.footer { + display: flex; + align-items: center; + justify-content: space-between; + flex-shrink: 0; + gap: 12px; + padding: 8px 16px 12px; +} + +.feedback { + min-height: 16px; + color: var(--dsw-alias-state-error-primary); + font-size: 11px; + line-height: 16px; +} + +.actions { + display: flex; + align-items: center; + flex-shrink: 0; + gap: 8px; +} + +@media (max-width: 720px) { + .frame { + padding: 6px 10px 10px; + } + + .card { + border-radius: 16px; + } + + .body { + padding: 10px 12px 4px; + } + + .footer { + align-items: flex-end; + padding: 8px 12px 10px; + } +} diff --git a/packages/client/ui-question/src/client/PlanReviewPanel.tsx b/packages/client/ui-question/src/client/PlanReviewPanel.tsx new file mode 100644 index 0000000000..020df9c82c --- /dev/null +++ b/packages/client/ui-question/src/client/PlanReviewPanel.tsx @@ -0,0 +1,100 @@ +// PlanReviewPanel: the composer takeover for a question carrying the +// `plan-review` presentation intent. A plan under review is one decision over +// one body of markdown, so it takes the waiting-approval card shape — tinted +// strip, content, right-aligned action row — instead of the generic question +// flow's pager, numbered options, skip and custom-answer affordances, which +// read as a quiz the user is being graded on. +// +// The three actions are the whole decision surface: approve and decline answer +// the question with the option labels the asker offered (localised copy on the +// buttons, the asker's descriptions as their tooltips), while "discuss" +// dismisses the request so the composer returns and the user can simply say +// what they want. Dismissal is the generic flow's own cancel verb, promoted to +// a labelled button because in a two-outcome decision it is the third real +// answer, not an escape hatch. + +import { useState } from 'react' +import { Button, IconEditOutline16, MarkdownText } from '@deepseek-ai/dsh-client-ui-primitives' +import type { PendingQuestion, PlanReview, QuestionComposerProps } from './contract/slots.ts' +import css from './PlanReviewPanel.module.css' + +/** The panel's own props: the question domain face, the narrowed review, and the locale seat. */ +export type PlanReviewPanelProps = + { pending: PendingQuestion; review: PlanReview } & Pick + +/** + * Optional-prop spread for a decision button's tooltip: `title` is optional on + * the DOM props, and exactOptionalPropertyTypes rejects an explicit undefined. + * + * @param description - the asker's option description, when it carries one. + * @returns The `title` prop to spread, or nothing. + */ +function tooltip(description: string | undefined): { title?: string } { + return description === undefined ? {} : { title: description } +} + +/** + * Render a plan review as a decision card. + * + * @param props - the question domain face, the narrowed plan review, and `t`. + * @returns The plan-review takeover for this request. + */ +export function PlanReviewPanel({ pending, review, t }: PlanReviewPanelProps) { + // One-shot latch shaped like the approval takeover's: the panel leaves only + // when the host's resolved frame lands, so until then a second click must + // not re-fire. A failed send (rejected receipt / transport) re-arms it and + // shows why, since nothing else would tell the user the click was lost. + const [busy, setBusy] = useState(false) + const [error, setError] = useState(null) + const settle = (send: () => Promise): void => { + setBusy(true) + setError(null) + void send().catch((cause: unknown) => { + setBusy(false) + setError(cause instanceof Error ? cause.message : String(cause)) + }) + } + const decide = (label: string): void => { + settle(() => pending.answer({ answers: [{ id: review.id, selected: [label] }] })) + } + const decline = review.decline + + return ( +
+
+
+ + {t('plan.header')} +
+
+ +
+
+
{error}
+
+ + {decline !== undefined && ( + + )} + +
+
+
+
+ ) +} diff --git a/packages/client/ui-question/src/client/QuestionComposer.tsx b/packages/client/ui-question/src/client/QuestionComposer.tsx index 30caf7f98e..abe87f567e 100644 --- a/packages/client/ui-question/src/client/QuestionComposer.tsx +++ b/packages/client/ui-question/src/client/QuestionComposer.tsx @@ -5,9 +5,10 @@ import { IconCloseOutline16, IconEditOutline16, MarkdownText, } from '@deepseek-ai/dsh-client-ui-primitives' import { - PendingQuestion, + PendingQuestion, planReviewOf, type QuestionAnswer, type QuestionComposerProps, } from './contract/slots.ts' +import { PlanReviewPanel } from './PlanReviewPanel.tsx' import css from './QuestionComposer.module.css' interface DraftAnswer { @@ -46,14 +47,24 @@ function isComposing(event: KeyboardEvent new PendingQuestion(props.matched), [props.matched]) - return + const review = useMemo(() => planReviewOf(question.questions), [question]) + return review === undefined + ? + : } function QuestionFlow({ pending, t }: { pending: PendingQuestion } & Pick) { diff --git a/packages/client/ui-question/src/client/contract/slots.ts b/packages/client/ui-question/src/client/contract/slots.ts index 54e87c016d..f92eb33f52 100644 --- a/packages/client/ui-question/src/client/contract/slots.ts +++ b/packages/client/ui-question/src/client/contract/slots.ts @@ -19,6 +19,65 @@ export type QuestionWait = PendingWait<'question'> /** One structured answer batch covering every question of the request. */ export type QuestionAnswer = QuestionResponsePayload['answer'] +/** One question of the request, as the carrier payload carries it. */ +type QuestionItem = QuestionWait['payload']['questions'][number] + +/** One option the asker offered on a question. */ +type QuestionOption = NonNullable[number] + +/** + * A request narrowed to the `plan-review` presentation intent: everything the + * decision card renders and answers with, so the panel never re-reads the + * request shape. `approve` and `decline` are the asker's own options — an + * answer must carry one of those labels verbatim — and `plan` is the markdown + * body under review. + */ +export interface PlanReview { + /** The reviewed question's id, echoed in the answer. */ + id: string + /** The question text, kept as the card's accessible name. */ + question: string + /** The plan markdown under review. */ + plan: string + /** The option that approves the plan. */ + approve: QuestionOption + /** The option that declines it; absent when the asker offered no other option. */ + decline?: QuestionOption +} + +/** + * Narrow a request to a renderable plan review, or return undefined to leave it + * to the generic question flow. + * + * The card is one decision over one plan, so it claims a request only when the + * batch is a single question that declares the intent, carries the plan as its + * detail, and offers the approve label the intent names. The asker's own + * service validates that label, but this is a wire boundary: a request failing + * any part of it still renders and stays answerable as a generic question + * rather than reaching a card that cannot express it. + * + * @param questions - the request's whole question batch. + * @returns The narrowed review, or undefined when the generic flow owns it. + */ +export function planReviewOf(questions: readonly QuestionItem[]): PlanReview | undefined { + if (questions.length !== 1) return undefined + // Length-checked above; the index read is the narrowing tax, not a guess. + const question = questions[0] as QuestionItem + const intent = question.intent + if (intent?.kind !== 'plan-review' || question.detail === undefined) return undefined + const options = question.options ?? [] + const approve = options.find(option => option.label === intent.approve) + if (approve === undefined) return undefined + const decline = options.find(option => option.label !== intent.approve) + return { + id: question.id, + question: question.question, + plan: question.detail, + approve, + ...(decline === undefined ? {} : { decline }), + } +} + /** * Question domain face over the carrier: render identity and questions * transparently forwarded; answer/cancel own the wire encoding (the ok value diff --git a/packages/client/ui-question/src/client/index.ts b/packages/client/ui-question/src/client/index.ts index 63f7517c3a..9c6893fd18 100644 --- a/packages/client/ui-question/src/client/index.ts +++ b/packages/client/ui-question/src/client/index.ts @@ -5,6 +5,12 @@ * question carrier (matched prop), and the whole behavior surface rides the * carrier (domain encoding in contract/slots.ts PendingQuestion); copy rides * the standard locale seat. Export discipline: packages/client/AGENTS.md. + * + * One entry, two shapes: the composer renders a request that declares a + * presentation intent as that intent's own surface (`plan-review` → the plan + * decision card) and every other request as the generic question flow. A + * separate chain entry per shape would race the same carrier, so the shape + * choice lives inside this entry — see QuestionComposer. */ import type { ClientContext } from '@deepseek-ai/dsh-client-runtime/client' import type { ComposerChainProps } from '@deepseek-ai/dsh-client-ui-conversation/client' @@ -14,8 +20,10 @@ import type { QuestionWait } from './contract/slots.ts' import { QuestionComposer } from './QuestionComposer.tsx' import { en, zh, type QuestionKey } from './locales.ts' -export { PendingQuestion } from './contract/slots.ts' -export type { QuestionAnswer, QuestionComposerProps, QuestionWait } from './contract/slots.ts' +export { PendingQuestion, planReviewOf } from './contract/slots.ts' +export type { + PlanReview, QuestionAnswer, QuestionComposerProps, QuestionWait, +} from './contract/slots.ts' export type { QuestionKey } from './locales.ts' declare module '@deepseek-ai/dsh-client-ui-slots' { diff --git a/packages/client/ui-question/src/client/locales.ts b/packages/client/ui-question/src/client/locales.ts index f124b34da2..bd5ee515ae 100644 --- a/packages/client/ui-question/src/client/locales.ts +++ b/packages/client/ui-question/src/client/locales.ts @@ -11,6 +11,10 @@ export const zh = { 'custom.placeholder': '输入你的答案', 'action.skip': '跳过本题', 'action.next': '下一题', + 'plan.header': '计划待审', + 'plan.approve': '确认执行', + 'plan.decline': '拒绝', + 'plan.discuss': '去聊天里说', } satisfies Record /** The question namespace key union. */ @@ -27,4 +31,8 @@ export const en = { 'custom.placeholder': 'Type your answer', 'action.skip': 'Skip this question', 'action.next': 'Next', + 'plan.header': 'Plan review', + 'plan.approve': 'Approve', + 'plan.decline': 'Refuse', + 'plan.discuss': 'Chat about it', } satisfies Record diff --git a/packages/client/ui-question/tests/plan-review-panel.spec.tsx b/packages/client/ui-question/tests/plan-review-panel.spec.tsx new file mode 100644 index 0000000000..3c2c456c57 --- /dev/null +++ b/packages/client/ui-question/tests/plan-review-panel.spec.tsx @@ -0,0 +1,221 @@ +// @vitest-environment jsdom +// The plan-review takeover, driven through the composer entry that routes to +// it: a request carrying the intent must reach the decision card and answer +// with the asker's own option labels, and a request that does not (or cannot) +// must keep the generic question flow. +import { afterEach, describe, expect, it, vi } from 'vitest' +import { cleanup, fireEvent, render, screen } from '@testing-library/react' +import type { + ConversationSnapshot, SessionId, SessionListState, WorkspaceListState, +} from '@deepseek-ai/dsh-client-runtime/client' +import { PendingWait } from '@deepseek-ai/dsh-client-runtime/client' +import type { RpcReceipt } from '@deepseek-ai/dsh-client-connection/client' +import { RpcId } from '@deepseek-ai/dsh-client-connection/client' +import type { SnapshotSelectorHook } from '@deepseek-ai/dsh-client-ui-slots' +import { planReviewOf, type QuestionComposerProps, type QuestionWait } from '../src/client/contract/slots.ts' +import { QuestionComposer } from '../src/client/QuestionComposer.tsx' +import { en, zh } from '../src/client/locales.ts' +import { en as commonEn } from '@deepseek-ai/dsh-client-locale/src/locales/en.ts' +import { zh as commonZh } from '@deepseek-ai/dsh-client-locale/src/locales/zh.ts' + +afterEach(cleanup) + +const SID = 's1' as SessionId + +/** Seat stub over a dictionary pair mirroring the real lookup chain: package dictionary, then common vocabulary, then the key. */ +const seatOver = (dict: Record, common: Record): QuestionComposerProps['t'] => + (key => dict[key] ?? common[key] ?? key) + +/** Framework standard-kit stubs: the panel consumes only the locale seat. */ +const kit = { + sessionId: SID, + useSession: (() => { throw new Error('unused') }) as unknown as SnapshotSelectorHook, + useSessions: (() => { throw new Error('unused') }) as unknown as SnapshotSelectorHook, + useWorkspaces: (() => { throw new Error('unused') }) as unknown as SnapshotSelectorHook, + useProjection: (() => undefined) as never, + useInput: (() => { throw new Error('unused') }) as never, + inputActions: { setDraft: () => { throw new Error('unused') }, submit: () => { throw new Error('unused') } } as never, + t: seatOver(zh, commonZh), +} + +const PLAN = '# Ship the picker\n\n- read the store\n- render the rows\n' + +/** The plan-mode request shape: one question, the plan as detail, approve named. */ +const questions = (): QuestionWait['payload']['questions'] => [{ + id: 'plan-review', + header: 'Plan review', + question: 'Approve this plan and leave plan mode?', + detail: PLAN, + options: [ + { label: 'Approve', description: 'Leave plan mode; the plan is carried out from the next step.' }, + { label: 'Keep planning', description: 'Stay in plan mode; feedback goes back to the model.' }, + ], + intent: { kind: 'plan-review', approve: 'Approve' }, +}] + +/** Carrier fixture over a scripted respond carrier. */ +function wait( + payload: QuestionWait['payload'] = { questions: questions() }, + respond = vi.fn(() => Promise.resolve({ accepted: true })), +) { + return { carrier: new PendingWait('question', RpcId('q-1'), SID, payload, respond), respond } +} + +/** The client-response envelope respond must have received for a decision. */ +function decidedEnvelope(label: string) { + return { + type: 'client-response', rpcId: RpcId('q-1'), + result: { ok: true, value: { sessionId: SID, answer: { answers: [{ id: 'plan-review', selected: [label] }] } } }, + } +} + +describe('planReviewOf', () => { + it('narrows a plan-review request to its decision, options included', () => { + expect(planReviewOf(questions())).toEqual({ + id: 'plan-review', + question: 'Approve this plan and leave plan mode?', + plan: PLAN, + approve: { label: 'Approve', description: 'Leave plan mode; the plan is carried out from the next step.' }, + decline: { label: 'Keep planning', description: 'Stay in plan mode; feedback goes back to the model.' }, + }) + }) + + it('leaves the decline absent when the asker offered approve alone', () => { + const [question] = questions() + const review = planReviewOf([{ ...question as object, options: [{ label: 'Approve' }] } as never]) + expect(review?.approve).toEqual({ label: 'Approve' }) + expect(review === undefined ? true : 'decline' in review).toBe(false) + }) + + it.each([ + ['a batch of more than one question', () => [...questions(), ...questions()]], + ['no intent at all', () => [{ ...questions()[0] as object, intent: undefined }]], + ['an intent without the plan as detail', () => [{ ...questions()[0] as object, detail: undefined }]], + ['an intent whose approve names no option', () => [{ + ...questions()[0] as object, intent: { kind: 'plan-review', approve: 'Ship it' }, + }]], + ['an intent with no options at all', () => [{ ...questions()[0] as object, options: undefined }]], + ])('declines %s, leaving the request to the generic flow', (_case, build) => { + expect(planReviewOf(build() as never)).toBeUndefined() + }) + + it('declines an empty batch, which the generic flow reports as such', () => { + expect(planReviewOf([])).toBeUndefined() + }) +}) + +describe('PlanReviewPanel', () => { + it('renders the plan under a review strip, with none of the quiz affordances', () => { + const { carrier } = wait() + render() + + expect(document.querySelector('[data-plan-review-key="q:q-1"]')).toBeTruthy() + expect(screen.getByText(zh['plan.header'])).toBeTruthy() + // The plan renders as markdown, so its heading is a heading. + expect(screen.getByRole('heading', { name: 'Ship the picker' })).toBeTruthy() + expect(screen.getByText('render the rows')).toBeTruthy() + // The question text stays as the card's accessible name rather than a title + // that reads like a test item. + expect(screen.getByLabelText('Approve this plan and leave plan mode?')).toBeTruthy() + // No pager, no numbered options, no skip, no custom answer. + expect(screen.queryByText('1 / 1')).toBeNull() + expect(screen.queryByRole('radio')).toBeNull() + expect(screen.queryByText(zh['action.skip'])).toBeNull() + expect(screen.queryByRole('textbox')).toBeNull() + }) + + it('answers with the asker\'s approve label and keeps its description as the tooltip', () => { + const { carrier, respond } = wait() + render() + + const approve = screen.getByRole('button', { name: zh['plan.approve'] }) + expect(approve.getAttribute('title')).toBe('Leave plan mode; the plan is carried out from the next step.') + fireEvent.click(approve) + expect(respond).toHaveBeenCalledWith(decidedEnvelope('Approve')) + // One-shot: every action locks until the host's resolved frame lands. + expect(approve.hasAttribute('disabled')).toBe(true) + expect(screen.getByRole('button', { name: zh['plan.decline'] }).hasAttribute('disabled')).toBe(true) + fireEvent.click(approve) + expect(respond).toHaveBeenCalledTimes(1) + }) + + it('answers with the asker\'s decline label', () => { + const { carrier, respond } = wait() + render() + + fireEvent.click(screen.getByRole('button', { name: zh['plan.decline'] })) + expect(respond).toHaveBeenCalledWith(decidedEnvelope('Keep planning')) + }) + + it('dismisses the request so the composer returns for a plain message', () => { + const { carrier, respond } = wait() + render() + + fireEvent.click(screen.getByRole('button', { name: zh['plan.discuss'] })) + expect(respond).toHaveBeenCalledWith({ + type: 'client-response', rpcId: RpcId('q-1'), + result: { + ok: false, + error: { code: 'cancelled', message: 'the user closed this question request', details: {} }, + }, + }) + }) + + it('omits the tooltip for an option carrying no description', () => { + const { carrier } = wait({ questions: [{ + ...questions()[0] as object, + options: [{ label: 'Approve' }, { label: 'Keep planning' }], + }] as never }) + render() + + expect(screen.getByRole('button', { name: zh['plan.approve'] }).hasAttribute('title')).toBe(false) + expect(screen.getByRole('button', { name: zh['plan.decline'] }).hasAttribute('title')).toBe(false) + }) + + it('hides the decline action when the asker offered approve alone', () => { + const { carrier } = wait({ questions: [{ + ...questions()[0] as object, options: [{ label: 'Approve' }], + }] as never }) + render() + + expect(screen.queryByRole('button', { name: zh['plan.decline'] })).toBeNull() + expect(screen.getByRole('button', { name: zh['plan.approve'] })).toBeTruthy() + }) + + it('re-arms the actions and says why when the decision does not land', async () => { + const { carrier, respond } = wait( + { questions: questions() }, + vi.fn(() => Promise.resolve({ accepted: false, reason: 'not-pending' })), + ) + render() + + fireEvent.click(screen.getByRole('button', { name: zh['plan.approve'] })) + const failure = await screen.findByText('question response rejected: not-pending') + expect(failure.getAttribute('role')).toBe('status') + // Re-armed for the retry: a lost click must not leave a dead card. + expect(screen.getByRole('button', { name: zh['plan.approve'] }).hasAttribute('disabled')).toBe(false) + fireEvent.click(screen.getByRole('button', { name: zh['plan.approve'] })) + expect(respond).toHaveBeenCalledTimes(2) + }) + + it('reports a non-Error transport failure as its stringified value', async () => { + // A non-Error rejection is the case under test: a carrier can reject with + // anything, and the panel must still show the user something. + // oxlint-disable-next-line typescript/prefer-promise-reject-errors + const { carrier } = wait({ questions: questions() }, vi.fn(() => Promise.reject('socket gone'))) + render() + + fireEvent.click(screen.getByRole('button', { name: zh['plan.discuss'] })) + expect(await screen.findByText('socket gone')).toBeTruthy() + }) + + it('carries the same decision surface in English', () => { + const { carrier } = wait() + render() + + expect(screen.getByText('Plan review')).toBeTruthy() + expect(screen.getByRole('button', { name: 'Approve' })).toBeTruthy() + expect(screen.getByRole('button', { name: 'Refuse' })).toBeTruthy() + expect(screen.getByRole('button', { name: 'Chat about it' })).toBeTruthy() + }) +}) From 132294fe8d5b61cc9aac174cb4ff2ad57a94bed2 Mon Sep 17 00:00:00 2001 From: creatixchu Date: Thu, 30 Jul 2026 19:12:02 +0800 Subject: [PATCH 10/24] fix(web): register the plan-review e2e lane in the host-plane program MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The lane boots the host spine through the shared scaffold, so it belongs to tsconfig.host.json and must stay out of the client-registered apps/web project — one program cannot hold both sides of the cordis Context merges. --- apps/web/tsconfig.json | 1 + tsconfig.host.json | 1 + 2 files changed, 2 insertions(+) diff --git a/apps/web/tsconfig.json b/apps/web/tsconfig.json index 7a7f228fb0..5f903b79b5 100644 --- a/apps/web/tsconfig.json +++ b/apps/web/tsconfig.json @@ -25,6 +25,7 @@ "tests/scaffold.ts", "tests/live-interactions.e2e.ts", "tests/question-composer.e2e.ts", + "tests/plan-review.e2e.ts", "tests/steering.e2e.ts", "tests/navigation-panes.e2e.ts", "tests/lifecycle-chrome.e2e.ts", diff --git a/tsconfig.host.json b/tsconfig.host.json index f55010712e..80579d7943 100644 --- a/tsconfig.host.json +++ b/tsconfig.host.json @@ -12,6 +12,7 @@ "apps/web/tests/support.ts", "apps/web/tests/live-interactions.e2e.ts", "apps/web/tests/question-composer.e2e.ts", + "apps/web/tests/plan-review.e2e.ts", "apps/web/tests/steering.e2e.ts", "apps/web/tests/navigation-panes.e2e.ts", "apps/web/tests/lifecycle-chrome.e2e.ts", From fb3018716176955531c521a00626feee63b7be32 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 30 Jul 2026 19:27:44 +0800 Subject: [PATCH 11/24] fix(web): isolate replay skill discovery --- ...6-07-24-web-gui-browser-e2e-lane.i18n.yaml | 4 +- .../2026-07-24-web-gui-browser-e2e-lane.md | 4 +- .../2026-07-24-web-gui-browser-e2e-lane.zh.md | 4 +- apps/web/tests/scaffold-hermetic.e2e.ts | 57 +++++++++++++++++++ apps/web/tests/scaffold.ts | 26 +++++++-- apps/web/tsconfig.json | 1 + tsconfig.host.json | 1 + 7 files changed, 85 insertions(+), 12 deletions(-) create mode 100644 apps/web/tests/scaffold-hermetic.e2e.ts diff --git a/.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.i18n.yaml b/.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.i18n.yaml index 14990e32c8..7b59000f1e 100644 --- a/.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.i18n.yaml +++ b/.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.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/testing/2026-07-24-web-gui-browser-e2e-lane.md -2026-07-24-web-gui-browser-e2e-lane.md: fb28b7013550a853b92e50810f5bc34f2c02d2e4 -2026-07-24-web-gui-browser-e2e-lane.zh.md: b9a7d050031c3d08269a3b971cd1a84f082efba7 +2026-07-24-web-gui-browser-e2e-lane.md: e47509378a8df25e5adac89a0f70c7ac1a8314c4 +2026-07-24-web-gui-browser-e2e-lane.zh.md: 1b2ea038b9a2c5ffd20442dcdf6986ce4e55af5f diff --git a/.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md b/.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md index fb28b70135..e47509378a 100644 --- a/.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md +++ b/.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md @@ -16,7 +16,7 @@ The web GUI ships as a real assembled chain — chromium page → client plugin A plain shared-fixture module (the [testing-policy sanctioned shape](../../../../docs/testing.md)), not a package: the gate-worthy logic — replay derivation, session parsing, log scrubbing, persistence — lives in the gated packages `dsh-llm-replay`, `dsh-acp-snapshot`, and `dsh-session-persistence-jsonl`; what remains is boot wiring and browser glue, and chromium-driving code cannot hold per-file 100% coverage on the browserless coverage runners. -`launchWebScaffold()` boots the real web composition from the shipped `apps/cli/config/base.cordis.yml` plus `apps/cli/config/web.cordis.yml` through the vendored Loader's include mechanism — the same tree and mechanism `AppCLIEntry` drives for `dsh web`. Divergences ride include patches over that tree, the ACP `cordis.snapshot.yml` pattern expressed in-process: temp `persistenceRoot`, `workspace-context` disabled (recorded fixtures must not embed this repo's AGENTS.md), `session-title-llm` disabled (its fire-and-forget title call would race the loop for the session's replay cursor), the webserver row pinned to port 0 with the built dist, and in keyless modes `llm-deepseek` disabled. A patch id that stops matching a row fails the boot sweep loudly instead of drifting. The boot runs `chdir`'d to the temp workspace so the api-gateway's `process.cwd()` session default, tool cwds, and fixtures agree; the `dsh web` bin's own glue (argv, profile json, AppCLIEntry) stays held by the keyless CLI smokes in `smoke-real.e2e.ts`. Setup rollback and ordinary close both dispose the Cordis tree before removing the two owned temp roots, attempt every cleanup independently, and report cleanup failures without masking the setup failure. +`launchWebScaffold()` boots the real web composition from the shipped `apps/cli/config/base.cordis.yml` plus `apps/cli/config/web.cordis.yml` through the vendored Loader's include mechanism — the same tree and mechanism `AppCLIEntry` drives for `dsh web`. Divergences ride include patches over that tree, the ACP `cordis.snapshot.yml` pattern expressed in-process: temp `persistenceRoot`; every host-level `skill-local` root (`dshHome`, `agentsHome`, and `bundledSkillDir`) pinned beneath the temp workspace with watching disabled, because ambient skill catalogs are model-visible input; `workspace-context` disabled (recorded fixtures must not embed this repo's AGENTS.md); `session-title-llm` disabled (its fire-and-forget title call would race the loop for the session's replay cursor); the webserver row pinned to port 0 with the built dist; and in keyless modes `llm-deepseek` disabled. A patch id that stops matching a row fails the boot sweep loudly instead of drifting. The boot runs `chdir`'d to the temp workspace so the api-gateway's `process.cwd()` session default, tool cwds, and fixtures agree; the `dsh web` bin's own glue (argv, profile json, AppCLIEntry) stays held by the keyless CLI smokes in `smoke-real.e2e.ts`. Setup rollback and ordinary close both dispose the Cordis tree before removing the two owned temp roots, attempt every cleanup independently, and report cleanup failures without masking the setup failure. Keyless model displacement is the disabled adapter row plus `installLlmReplay` filling the open seam on the settled root ctx in providers-catalog mode — never catch-all: with the adapter row disabled no adapter exists, so catch-all would leave `resolveModelInfo` unroutable and `compact-basic`'s post-step pressure check would warn every step instead of being provably inert (the published 128k `contextWindow` keeps it inert for small fixtures). The direct install rather than an inserted replay plugin row is deliberate: it returns the `ReplayHandle` the teardown consumption check needs. A scenario with no fixture leaves the seam empty, so a stray stream fails loud with NO_ADAPTER. @@ -76,7 +76,7 @@ Surveyed AI-chat/agent web UIs and mocking layers (LibreChat, vercel/ai-chatbot ## Testing -`pnpm run test:web` builds and runs the lane keylessly; `test:web:built` runs it against existing build artifacts. `DSH_SNAPSHOT=record pnpm exec vitest run --config vitest.web.config.ts apps/web/tests/` records a prompting scenario against the live model, and `DSH_SNAPSHOT=refresh pnpm run test:web` rewrites aria goldens keylessly. CI explicitly selects replay mode. `dsh-llm-replay` unit coverage pins pacing, cancellation, consumption diagnostics, sidecar validation, indexed replacement, and the single append position. +`pnpm run test:web` builds and runs the lane keylessly; `test:web:built` runs it against existing build artifacts. `DSH_SNAPSHOT=record pnpm exec vitest run --config vitest.web.config.ts apps/web/tests/` records a prompting scenario against the live model, and `DSH_SNAPSHOT=refresh pnpm run test:web` rewrites aria goldens keylessly. CI explicitly selects replay mode. The scaffold hermeticity scenario populates distinct entries in all three ambient skill roots and requires none to enter the assembled catalog. `dsh-llm-replay` unit coverage pins pacing, cancellation, consumption diagnostics, sidecar validation, indexed replacement, and the single append position. ## Deferred diff --git a/.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.zh.md b/.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.zh.md index b9a7d05003..1b2ea038b9 100644 --- a/.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.zh.md +++ b/.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.zh.md @@ -16,7 +16,7 @@ Web GUI 以一条真实组装链交付——chromium 页面 → client 插件 bu 一个普通的共享 fixture 模块（[测试政策认可的形态](../../../../docs/testing.md)），不是包：值得门禁把守的逻辑——回放推导、会话解析、日志脱敏、持久化——都在已受门禁的包 `dsh-llm-replay`、`dsh-acp-snapshot`、`dsh-session-persistence-jsonl` 中；剩下的只是启动接线和浏览器胶水，而驱动 chromium 的源码在无浏览器的覆盖率 runner 上无法诚实保持逐文件 100% 覆盖率。 -`launchWebScaffold()` 通过 vendored Loader 的 include 机制，从交付的 `apps/cli/config/base.cordis.yml` 与 `apps/cli/config/web.cordis.yml` 启动真实 web 组合——与 `AppCLIEntry` 为 `dsh web` 驱动的是同一棵树、同一套机制。差异全部经 include patch 覆盖在这棵树上，即 ACP `cordis.snapshot.yml` 模式的进程内表达：临时 `persistenceRoot`；禁用 `workspace-context`（录制的 fixture 不得嵌入本仓库的 AGENTS.md）；禁用 `session-title-llm`（其发后不管的标题调用会与循环争抢会话的回放游标）；webserver 行钉到端口 0 加已构建 dist；无密钥模式下禁用 `llm-deepseek`。patch 的 id 一旦不再匹配任何行，boot 扫描会大声失败而不是漂移。boot 在临时工作区 `chdir` 下运行，使 api-gateway 的 `process.cwd()` 会话默认值、工具 cwd 与 fixture 一致；`dsh web` bin 自身的胶水（argv、profile json、AppCLIEntry）仍由 `smoke-real.e2e.ts` 中的无密钥 CLI 冒烟把守。初始化回滚和正常关闭都会先对 Cordis 树执行 dispose（资源释放），再删除 scaffold 持有的两个临时根目录；每项清理都会独立尝试，并会报告清理失败而不掩盖初始化失败。 +`launchWebScaffold()` 通过 vendored Loader 的 include 机制，从交付的 `apps/cli/config/base.cordis.yml` 与 `apps/cli/config/web.cordis.yml` 启动真实 web 组合——与 `AppCLIEntry` 为 `dsh web` 驱动的是同一棵树、同一套机制。差异全部经 include patch 覆盖在这棵树上，即 ACP `cordis.snapshot.yml` 模式的进程内表达：临时 `persistenceRoot`；每个主机级 `skill-local` 根目录（`dshHome`、`agentsHome` 和 `bundledSkillDir`）都钉在临时工作区下并禁用监听，因为环境 skill（技能）目录是模型可见输入；禁用 `workspace-context`（录制的 fixture 不得嵌入本仓库的 AGENTS.md）；禁用 `session-title-llm`（其发后不管的标题调用会与循环争抢会话的回放游标）；webserver 行钉到端口 0 加已构建 dist；无密钥模式下禁用 `llm-deepseek`。patch 的 id 一旦不再匹配任何行，boot 扫描会大声失败而不是漂移。boot 在临时工作区 `chdir` 下运行，使 api-gateway 的 `process.cwd()` 会话默认值、工具 cwd 与 fixture 一致；`dsh web` bin 自身的胶水（argv、profile json、AppCLIEntry）仍由 `smoke-real.e2e.ts` 中的无密钥 CLI 冒烟把守。初始化回滚和正常关闭都会先对 Cordis 树执行 dispose（资源释放），再删除 scaffold 持有的两个临时根目录；每项清理都会独立尝试，并会报告清理失败而不掩盖初始化失败。 无密钥的模型替换 = 禁用适配器行的 patch 加 `installLlmReplay` 在停稳的根 ctx 上以提供方目录（providers-catalog）模式填充开放的 seam——绝不用 catch-all：适配器行被禁用后不存在任何适配器，catch-all 会让 `resolveModelInfo` 无路由可走，`compact-basic` 的步后压力检查将步步告警，而不是被可证明地闲置（发布的 128k `contextWindow` 使该路径对小 fixture 保持闲置）。选择直接安装而非插入回放插件行是刻意的：直接安装返回收尾消费检查所需的 `ReplayHandle`。没有 fixture 的场景让 seam 保持空置，任何离群的流式调用都会以 NO_ADAPTER 大声失败。 @@ -76,7 +76,7 @@ Web GUI 以一条真实组装链交付——chromium 页面 → client 插件 bu ## Testing -`pnpm run test:web` 构建并无密钥运行该车道；`test:web:built` 基于现有构建产物运行。`DSH_SNAPSHOT=record pnpm exec vitest run --config vitest.web.config.ts apps/web/tests/` 对真实模型录制一个发起提示的场景，`DSH_SNAPSHOT=refresh pnpm run test:web` 则无密钥重写 aria 预期输出。CI 显式选择回放模式。`dsh-llm-replay` 单元覆盖率钉住节奏控制、取消、消费诊断、sidecar 校验、按索引替换与唯一的追加位置。 +`pnpm run test:web` 构建并无密钥运行该车道；`test:web:built` 基于现有构建产物运行。`DSH_SNAPSHOT=record pnpm exec vitest run --config vitest.web.config.ts apps/web/tests/` 对真实模型录制一个发起提示的场景，`DSH_SNAPSHOT=refresh pnpm run test:web` 则无密钥重写 aria 预期输出。CI 显式选择回放模式。scaffold 环境隔离场景会在全部 3 个环境 skill 根目录中分别填入不同条目，并要求这些条目都不得进入组装后的目录。`dsh-llm-replay` 单元覆盖率钉住节奏控制、取消、消费诊断、sidecar 校验、按索引替换与唯一的追加位置。 ## 暂缓 diff --git a/apps/web/tests/scaffold-hermetic.e2e.ts b/apps/web/tests/scaffold-hermetic.e2e.ts new file mode 100644 index 0000000000..6e14eebfa5 --- /dev/null +++ b/apps/web/tests/scaffold-hermetic.e2e.ts @@ -0,0 +1,57 @@ +import { mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { expect, it } from 'vitest' +import type {} from '@deepseek-ai/dsh-skill' +import { launchWebScaffold, type WebScaffold } from './scaffold.ts' + +async function writeSkill(root: string, name: string): Promise { + const bundle = join(root, name) + await mkdir(bundle, { recursive: true }) + await writeFile(join(bundle, 'SKILL.md'), `--- +name: ${name} +description: Must not enter the Web replay scaffold +--- + +Ambient host state. +`) +} + +it('isolates replay skill discovery from every ambient host root', async () => { + const ambient = await mkdtemp(join(tmpdir(), 'dsh-web-ambient-skills-')) + const dshHome = join(ambient, 'dsh-home') + const agentsHome = join(ambient, 'agents-home') + const bundled = join(ambient, 'bundled') + await Promise.all([ + writeSkill(join(dshHome, 'skills'), 'ambient-dsh'), + writeSkill(join(agentsHome, 'skills'), 'ambient-agents'), + writeSkill(bundled, 'ambient-bundled'), + ]) + + const originalDshHome = process.env.DSH_HOME + const originalAgentsHome = process.env.DSH_AGENTS_HOME + const originalBundled = process.env.DSH_BUNDLED_SKILL_DIR + process.env.DSH_HOME = dshHome + process.env.DSH_AGENTS_HOME = agentsHome + process.env.DSH_BUNDLED_SKILL_DIR = bundled + let scaffold: WebScaffold | undefined + try { + scaffold = await launchWebScaffold() + const names = (await scaffold.ctx.skills.list({ cwd: scaffold.workspaceCwd })).map(skill => skill.name) + expect(names).not.toContain('ambient-dsh') + expect(names).not.toContain('ambient-agents') + expect(names).not.toContain('ambient-bundled') + } finally { + try { + await scaffold?.close() + } finally { + if (originalDshHome === undefined) delete process.env.DSH_HOME + else process.env.DSH_HOME = originalDshHome + if (originalAgentsHome === undefined) delete process.env.DSH_AGENTS_HOME + else process.env.DSH_AGENTS_HOME = originalAgentsHome + if (originalBundled === undefined) delete process.env.DSH_BUNDLED_SKILL_DIR + else process.env.DSH_BUNDLED_SKILL_DIR = originalBundled + await rm(ambient, { recursive: true, force: true }) + } + } +}) diff --git a/apps/web/tests/scaffold.ts b/apps/web/tests/scaffold.ts index 1c030b4097..cfa0374c77 100644 --- a/apps/web/tests/scaffold.ts +++ b/apps/web/tests/scaffold.ts @@ -9,12 +9,13 @@ // from live session memory), refresh (keyless replay that rewrites goldens). // // Composition divergences from `dsh web`, all deliberate, all via include -// patches after the shipped surface overlay: temp persistenceRoot; -// workspace-context disabled (recorded fixtures must not embed this repo's -// AGENTS.md); session-title-llm disabled (its fire-and-forget title call -// would race the loop for the session's replay cursor); webserver pinned to -// port 0 with the built dist; keyless modes disable llm-deepseek and fill -// the open llm seam post-boot with installLlmReplay on the settled root ctx +// patches after the shipped surface overlay: temp persistenceRoot; local skill +// roots confined to the temp workspace; workspace-context disabled (recorded +// fixtures must not embed this repo's AGENTS.md); session-title-llm disabled +// (its fire-and-forget title call would race the loop for the session's replay +// cursor); webserver pinned to port 0 with the built dist; keyless modes +// disable llm-deepseek and fill the open llm seam post-boot with +// installLlmReplay on the settled root ctx // (the plugin-row path discards the ReplayHandle; the direct install keeps // assertConsumed for the teardown fixture-consumption check). import { existsSync } from 'node:fs' @@ -172,6 +173,19 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise Date: Thu, 30 Jul 2026 19:38:18 +0800 Subject: [PATCH 12/24] fix(web): keep the plan card to decisions it can actually answer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Review follow-ups on the presentation intent. The card claimed any single-question request declaring the intent, then sent one of two labels — so a producer offering a third option, or a multi-select batch, lost answers the generic flow would have shown. That contradicts the intent's own contract, so `planReviewOf` now claims only a binary single choice and leaves everything else to the flow that can express it. `ask()` also rejects a plan-review intent on a question with no `detail`: the intent declares detail IS the plan, and without one a honouring UI asks the user to approve something invisible. The client keeps its own fallback — it sits downstream of a wire boundary — but the misconfiguration now fails at the asker. `planReviewOf` stops being a value export of the client contract face (client export discipline: pure helpers stay internal; the tests already import it relatively), and the ui-question README fallback list, both languages, now states every condition the code enforces. --- ...0-plan-review-presentation-intent.i18n.yaml | 4 ++-- ...26-07-30-plan-review-presentation-intent.md | 6 +++--- ...07-30-plan-review-presentation-intent.zh.md | 6 +++--- .../user-interaction.i18n.yaml | 4 ++-- docs/core-data-structures/user-interaction.md | 4 ++-- .../user-interaction.zh.md | 4 ++-- packages/client/ui-question/README.i18n.yaml | 4 ++-- packages/client/ui-question/README.md | 2 +- packages/client/ui-question/README.zh.md | 2 +- .../ui-question/src/client/contract/slots.ts | 18 ++++++++++++------ .../client/ui-question/src/client/index.ts | 2 +- .../tests/plan-review-panel.spec.tsx | 7 +++++++ packages/ui/user-interaction/README.i18n.yaml | 4 ++-- packages/ui/user-interaction/README.md | 2 +- packages/ui/user-interaction/README.zh.md | 2 +- packages/ui/user-interaction/src/index.ts | 16 ++++++++++++---- packages/ui/user-interaction/src/types.ts | 2 +- .../tests/user-interaction.spec.ts | 18 ++++++++++++++++++ 18 files changed, 73 insertions(+), 34 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.i18n.yaml b/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.i18n.yaml index 3de0b88f5c..d6f77e3e14 100644 --- a/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.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/2026-07-30-plan-review-presentation-intent.md -2026-07-30-plan-review-presentation-intent.md: aa85156d87a35d049f3cfab465fc668a63781a73 -2026-07-30-plan-review-presentation-intent.zh.md: fffee3de6341d45b26b88e1cc67a3895e747afac +2026-07-30-plan-review-presentation-intent.md: aeab12aac308c24aa5c4b5953a60ae0f2cf6c5b5 +2026-07-30-plan-review-presentation-intent.zh.md: 4096018e374212c821675ce6ed3a2355df20edc9 diff --git a/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.md b/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.md index aa85156d87..aeab12aac3 100644 --- a/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.md +++ b/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.md @@ -16,11 +16,11 @@ A question may declare a **presentation intent**, and the Web composer renders a An intent shapes presentation only. The answer protocol is untouched: a UI honouring the intent answers with the same option labels a generic UI would send, so `exit_plan_mode` reads one answer shape regardless of which surface collected it, and a UI that does not know a tag renders the generic flow with nothing lost but the layout. -`approve` names the affirmative option instead of relying on option order, so no UI infers a verdict from a position. Because the types cannot tie that label to the question's own option list, `UserInteractionService.ask()` rejects an intent whose `approve` names none of its options (`BAD_INTENT`) — at the asker, before any UI can answer a choice that was never offered. On the wire the intent is a discriminated union, so an unrecognised tag is a rejected frame rather than a silently generic render. +`approve` names the affirmative option instead of relying on option order, so no UI infers a verdict from a position. Two assertions an intent makes are beyond the types, and `UserInteractionService.ask()` rejects both as `BAD_INTENT` at the asker: an `approve` naming none of that question's own options — before any UI can answer a choice never offered — and an intent on a question with no `detail`, the thing it declares itself a review of, which would ask the user to approve something invisible. On the wire the intent is a discriminated union, so an unrecognised tag is a rejected frame rather than a silently generic render. `ui-question` renders the intent as `PlanReviewPanel`, in the waiting-approval card language: the amber strip carries `Plan review`, the plan is the scrolling markdown body, and the decision row holds three actions — `Chat about it`, `Refuse`, `Approve`. The question text becomes the card's accessible name rather than a headline, because the buttons already say what the decision is. Approve and Refuse answer with the asker's own option labels and keep the asker's descriptions as tooltips; `Chat about it` cancels the request, which returns the composer so the user can simply say what they want. All copy is bilingual under the existing `question` namespace. -Routing lives inside the single composer entry (`QuestionComposer` chooses the shape) rather than in a second chain registration, and `planReviewOf` claims a request only when the batch is one question that declares the intent, carries the plan as its `detail`, and offers the named approve label. Anything else stays a generic question — the client is downstream of a wire boundary, so a request it cannot render as a card must still be answerable. +Routing lives inside the single composer entry (`QuestionComposer` chooses the shape) rather than in a second chain registration, and `planReviewOf` claims a request only when the card can send every answer that request allows: one question declaring the intent, the plan as its `detail`, the named approve label offered, and a binary single choice — at most one option besides approve, and not multi-select. A third option or a multi-select batch has answers two buttons cannot express, so the generic flow keeps it, and keeps anything else the card cannot render. "Presentation only" is therefore literal: an intent never costs the user a reachable answer, and the client — downstream of a wire boundary — leaves every request answerable. Dismissal became its own model-facing outcome. `ASK_CANCELLED` previously reached the model as "the user cancelled ask_user_question", naming a tool it never called; `exit_plan_mode` now reports that the user dismissed the review to speak instead and to stay in plan mode and wait. Every other ask failure — an abort from turn cancel or provider teardown, where no user is coming — keeps its own message. @@ -50,6 +50,6 @@ A deployment whose client half predates this change still shows the quiz layout ## Testing -`ui-question` tests pin the narrowing (single-question batch, intent present, plan as detail, named approve label offered, decline absent when only approve is offered) and the panel (strip, markdown plan, accessible name, absence of pager/radio/skip/custom, approve and decline answering with the asker's labels, dismissal cancelling, one-shot latch with re-arm and message on a rejected receipt, tooltips present and absent, both locales). `user-interaction` tests pin `BAD_INTENT` and intent pass-through; `plan-mode` tests pin the declared intent against its own option list and both failure messages; the apiproxy schema test pins wire acceptance and an unknown tag's rejection. +`ui-question` tests pin the narrowing (single-question batch, intent present, plan as detail, named approve label offered, binary single choice, decline absent when only approve is offered) and the panel (strip, markdown plan, accessible name, absence of pager/radio/skip/custom, approve and decline answering with the asker's labels, dismissal cancelling, one-shot latch with re-arm and message on a rejected receipt, tooltips present and absent, both locales). `user-interaction` tests pin both `BAD_INTENT` rejections and intent pass-through; `plan-mode` tests pin the declared intent against its own option list and both failure messages; the apiproxy schema test pins wire acceptance and an unknown tag's rejection. The `plan-review` Web e2e lane records `/plan` entering plan mode for real, the model calling `exit_plan_mode`, the decision card taking the composer (asserting the generic flow did **not** claim the request), and the card's own Approve completing the turn — two keyless goldens, the waiting card and the approved transcript. diff --git a/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.zh.md b/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.zh.md index fffee3de63..4096018e37 100644 --- a/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.zh.md +++ b/.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.zh.md @@ -16,11 +16,11 @@ Status: implemented 意图只塑造呈现。回答协议不变：遵循意图的 UI 回答的仍是通用 UI 会发送的那些选项标签，因此无论由哪个界面收集，`exit_plan_mode` 读到的都是同一种回答形状；而不认识某个标签的 UI 渲染通用流程，除布局之外一无所失。 -`approve` 指名肯定选项，而不依赖选项顺序，因此没有任何 UI 会从位置推断裁决。由于类型无法把该标签绑定到问题自身的选项列表，`UserInteractionService.ask()` 会拒绝 `approve` 未命中任一选项的意图（`BAD_INTENT`）—— 拦在提问方一侧，早于任何 UI 回答一个从未被提供过的选择。在协议格式（wire format）上意图是可辨识联合，因此无法识别的标签是被拒绝的帧，而不是静默退回通用渲染。 +`approve` 指名肯定选项，而不依赖选项顺序，因此没有任何 UI 会从位置推断裁决。意图作出的两项断言超出类型的表达能力，`UserInteractionService.ask()` 都以 `BAD_INTENT` 在提问方一侧拒绝：`approve` 未命中该问题自身的任一选项 —— 早于任何 UI 回答一个从未被提供过的选择；以及意图落在没有 `detail` 的问题上，而 `detail` 正是它自称在审阅的东西，那会让用户去批准一件看不见的事。在协议格式（wire format）上意图是可辨识联合，因此无法识别的标签是被拒绝的帧，而不是静默退回通用渲染。 `ui-question` 把该意图渲染为 `PlanReviewPanel`，沿用等待审批卡片的语言：琥珀色条带写着 `Plan review`，计划是可滚动的 markdown 主体，决定行放三个操作 —— `Chat about it`、`Refuse`、`Approve`。问题文本成为卡片的无障碍名称而非标题，因为按钮已经说明了这次决定是什么。Approve 与 Refuse 用提问方自己的选项标签回答，并把提问方的描述保留为 tooltip；`Chat about it` 取消该请求，从而让输入区归位，用户直接说他想说的话即可。所有文案在既有 `question` 命名空间下双语。 -路由住在单一输入区条目内部（由 `QuestionComposer` 选择形状），而不是第二个链式注册；`planReviewOf` 仅在这一批只有一个问题、该问题声明了意图、以 `detail` 承载计划、并提供了被指名的批准标签时才接管请求。其他情形一律保持通用问题 —— 客户端位于协议边界的下游，它无法渲染成卡片的请求仍必须可回答。 +路由住在单一输入区条目内部（由 `QuestionComposer` 选择形状），而不是第二个链式注册；`planReviewOf` 仅在卡片能够发出该请求允许的每一个答案时才接管：只有一个问题且声明了意图、以 `detail` 承载计划、提供了被指名的批准标签，且是二元单选 —— 除批准外最多一个选项，且非多选。出现第三个选项或多选批次时，其答案是两个按钮无法表达的，通用流程保留它，也保留其他任何卡片渲染不了的请求。因此"只塑造呈现"是字面意义上的：意图绝不让用户失去一个可达的答案，而位于协议边界下游的客户端让每个请求都保持可回答。 放弃审阅成为面向模型的独立结果。`ASK_CANCELLED` 以前传到模型的是"the user cancelled ask_user_question"，指名了一个它从未调用的工具；现在 `exit_plan_mode` 报告用户放弃审阅是为了改用说话，并要求留在 plan mode 中等待。其余每一种 ask 失败 —— 轮次取消或提供方拆卸导致的中止，那里并没有用户会来 —— 保留它们自己的消息。 @@ -50,6 +50,6 @@ Status: implemented ## 测试 -`ui-question` 测试钉住收窄（单问题批、意图存在、计划作为 detail、被指名的批准标签确实被提供、只提供批准时 decline 缺席）与面板（条带、markdown 计划、无障碍名称、无分页/单选/跳过/自定义、批准与拒绝用提问方的标签回答、放弃触发取消、一次性闭锁在回执被拒时重新武装并给出消息、tooltip 有与无、两种语言）。`user-interaction` 测试钉住 `BAD_INTENT` 与意图透传；`plan-mode` 测试钉住已声明的意图与其自身选项列表的一致、以及两条失败消息；apiproxy schema 测试钉住协议接受与未知标签的拒绝。 +`ui-question` 测试钉住收窄（单问题批、意图存在、计划作为 detail、被指名的批准标签确实被提供、二元单选、只提供批准时 decline 缺席）与面板（条带、markdown 计划、无障碍名称、无分页/单选/跳过/自定义、批准与拒绝用提问方的标签回答、放弃触发取消、一次性闭锁在回执被拒时重新武装并给出消息、tooltip 有与无、两种语言）。`user-interaction` 测试钉住两种 `BAD_INTENT` 拒绝与意图透传；`plan-mode` 测试钉住已声明的意图与其自身选项列表的一致、以及两条失败消息；apiproxy schema 测试钉住协议接受与未知标签的拒绝。 `plan-review` Web e2e 通道录制了 `/plan` 真实进入 plan mode、模型调用 `exit_plan_mode`、决定卡片接管输入区（并断言通用流程**没有**接管该请求）、以及卡片自身的 Approve 完成该轮 —— 两份无密钥 golden：等待中的卡片与批准后的会话记录。 diff --git a/docs/core-data-structures/user-interaction.i18n.yaml b/docs/core-data-structures/user-interaction.i18n.yaml index ee739a59d3..bc281d9bb7 100644 --- a/docs/core-data-structures/user-interaction.i18n.yaml +++ b/docs/core-data-structures/user-interaction.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 docs/core-data-structures/user-interaction.md -user-interaction.md: 4ebaf66131b3ab7a7c205bef1ba533e9321d4f0b -user-interaction.zh.md: 8e5542b995bbf061b097d650ab79505e93151fa8 +user-interaction.md: 2483382eee07d379b13d456149096c8afab70e4b +user-interaction.zh.md: 57f57277975597fff712705cc741ae8e78643642 diff --git a/docs/core-data-structures/user-interaction.md b/docs/core-data-structures/user-interaction.md index 4ebaf66131..2483382eee 100644 --- a/docs/core-data-structures/user-interaction.md +++ b/docs/core-data-structures/user-interaction.md @@ -22,7 +22,7 @@ interface AskUserQuestionOption { ## Presentation intent -`AskUserQuestionIntent` is the optional declaration that a question IS a decision of a known shape. It is tagged on `kind` so intents can be added; a UI that does not recognise a tag renders the generic option list. An intent shapes presentation only — a UI honouring it answers with the same option labels a generic UI would send, so the caller reads one answer shape either way. `approve` names the affirmative option instead of relying on option order, and `ask()` rejects an `approve` naming none of its own question's options. +`AskUserQuestionIntent` is the optional declaration that a question IS a decision of a known shape. It is tagged on `kind` so intents can be added; a UI that does not recognise a tag renders the generic option list. An intent shapes presentation only — a UI honouring it answers with the same option labels a generic UI would send, so the caller reads one answer shape either way. `approve` names the affirmative option instead of relying on option order. `ask()` rejects the two assertions no type can carry: an `approve` naming none of its own question's options, and an intent on a question with no `detail`. ```ts type-equiv /** @@ -33,7 +33,7 @@ interface AskUserQuestionOption { * either way — an intent shapes presentation only, never the protocol. */ type AskUserQuestionIntent = { - /** A plan submitted for review: `detail` is the plan markdown, and the decision approves or declines it. */ + /** A plan submitted for review: `detail` is the plan markdown `ask()` requires, and the decision approves or declines it. */ kind: 'plan-review' /** * The option label that approves the plan; every other option declines it. diff --git a/docs/core-data-structures/user-interaction.zh.md b/docs/core-data-structures/user-interaction.zh.md index 8e5542b995..57f5727797 100644 --- a/docs/core-data-structures/user-interaction.zh.md +++ b/docs/core-data-structures/user-interaction.zh.md @@ -22,7 +22,7 @@ interface AskUserQuestionOption { ## 呈现意图 -`AskUserQuestionIntent` 是一项可选声明：某个问题本身就是一次已知形状的决定。它按 `kind` 打标签，因此意图可以扩充；不认识某个标签的 UI 渲染通用选项列表。意图只塑造呈现 —— 遵循它的 UI 回答的仍是通用 UI 会发送的那些 option label，因此调用方两种情况下读到的都是同一种回答形态。`approve` 指名肯定选项，而不依赖选项顺序；`ask()` 会拒绝未命中该问题自身任一选项的 `approve`。 +`AskUserQuestionIntent` 是一项可选声明：某个问题本身就是一次已知形状的决定。它按 `kind` 打标签，因此意图可以扩充；不认识某个标签的 UI 渲染通用选项列表。意图只塑造呈现 —— 遵循它的 UI 回答的仍是通用 UI 会发送的那些 option label，因此调用方两种情况下读到的都是同一种回答形态。`approve` 指名肯定选项，而不依赖选项顺序。有两项断言是任何类型都承载不了的，`ask()` 会拒绝它们：`approve` 未命中该问题自身的任一选项，以及意图落在没有 `detail` 的问题上。 ```ts type-equiv /** @@ -33,7 +33,7 @@ interface AskUserQuestionOption { * either way — an intent shapes presentation only, never the protocol. */ type AskUserQuestionIntent = { - /** A plan submitted for review: `detail` is the plan markdown, and the decision approves or declines it. */ + /** A plan submitted for review: `detail` is the plan markdown `ask()` requires, and the decision approves or declines it. */ kind: 'plan-review' /** * The option label that approves the plan; every other option declines it. diff --git a/packages/client/ui-question/README.i18n.yaml b/packages/client/ui-question/README.i18n.yaml index cd2f0556a4..914485fbbb 100644 --- a/packages/client/ui-question/README.i18n.yaml +++ b/packages/client/ui-question/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-question/README.md -README.md: 6b40c503be61c2458cefceabbb35e16a3befbe66 -README.zh.md: 7c0c4ee67d1ef8b4507f3899bdb1ae2f76408032 +README.md: 5ebba2a1da6e6108b82e9deb235b84f987600345 +README.zh.md: 0aa6428a9b6472fc5b525c11b4716ebc50c378c3 diff --git a/packages/client/ui-question/README.md b/packages/client/ui-question/README.md index 6b40c503be..5ebba2a1da 100644 --- a/packages/client/ui-question/README.md +++ b/packages/client/ui-question/README.md @@ -6,7 +6,7 @@ Web `ask_user_question` feature plugin. Its host half mounts `dsh-tool-ask-user` The component renders one question at a time with progress navigation, single- and multi-select choices, recommendation badges derived from label suffixes, and custom answers. Question detail reuses the assistant-output `MarkdownText` primitive, including its GFM rendering and untrusted-content policy. The capped card keeps its title, navigation, and submission actions fixed while long detail and choices share an internal scroll region. Single-select choices advance immediately, and Enter submits once every question is answered or skipped; Enter during IME composition confirms the input candidate without advancing. It submits one structured answer batch for the whole request: “Skip this question” retains other drafts and emits the existing blank `{ selected: [] }` shape for that item, while close rejects the whole wait as `ASK_CANCELLED`. -A request whose single question declares a presentation intent renders as that intent's own surface instead. `plan-review` — set by `dsh-plan-mode` on the `exit_plan_mode` review — takes the waiting-approval card shape: a `Plan review` strip, the plan as the scrolling markdown body, the question text as the card's accessible name, and one decision row of `Chat about it` / `Refuse` / `Approve`. Approve and Refuse answer with the asker's own option labels (the intent names which label approves, so the verdict never rides option order) and keep the asker's descriptions as tooltips; `Chat about it` rejects the wait as `ASK_CANCELLED`, returning the composer so the user can say what they want instead. A request that declares no intent, batches more than one question, or fails to offer the named approve label stays on the generic flow — the layout is all an intent changes, never the answer. +A request whose single question declares a presentation intent renders as that intent's own surface instead. `plan-review` — set by `dsh-plan-mode` on the `exit_plan_mode` review — takes the waiting-approval card shape: a `Plan review` strip, the plan as the scrolling markdown body, the question text as the card's accessible name, and one decision row of `Chat about it` / `Refuse` / `Approve`. Approve and Refuse answer with the asker's own option labels (the intent names which label approves, so the verdict never rides option order) and keep the asker's descriptions as tooltips; `Chat about it` rejects the wait as `ASK_CANCELLED`, returning the composer so the user can say what they want instead. The card claims a request only when it can send every answer that request allows: one question, the intent declared, the plan present as `detail`, the named approve label offered, and a binary single choice (at most one option besides approve, not multi-select). Anything else — no intent, a batch of several questions, a missing plan, an approve label naming no option, a third option, a multi-select decision — stays on the generic flow, which can express it. An intent changes the layout, never which answers are reachable. Selection state is local to a component keyed by the request rpcId. A replay with the same id preserves a still-mounted draft, while `question/resolved` from the host removes the composer. The host remains authoritative: successful HTTP delivery does not remove pending state locally. diff --git a/packages/client/ui-question/README.zh.md b/packages/client/ui-question/README.zh.md index 7c0c4ee67d..0aa6428a9b 100644 --- a/packages/client/ui-question/README.zh.md +++ b/packages/client/ui-question/README.zh.md @@ -6,7 +6,7 @@ Web `ask_user_question` 功能插件。只有选择 Web 功能时，其主机侧 组件每次渲染一个问题，提供进度导航、单选和多选选项、由标签后缀派生的推荐徽标，以及自定义答案。问题详情复用助手输出的 `MarkdownText` 原语，包括其 GFM 渲染与不受信内容策略。封顶卡片保持标题、导航与提交动作固定，超长的详情与选项共享内部滚动区。单选选项会立即前进；所有问题均已回答或跳过后，Enter 会提交；IME 输入法组合期间按 Enter 只会确认输入候选，不会前进。组件为整个请求提交一批结构化答案：「跳过此问题」会保留其他草稿，并为该项发出既有的空 `{ selected: [] }` 形状；关闭则以 `ASK_CANCELLED` 拒绝整个等待。 -若某个请求的唯一问题声明了呈现意图，则改为渲染该意图自己的界面。`plan-review` —— 由 `dsh-plan-mode` 在 `exit_plan_mode` 审阅上设置 —— 采用等待审批卡片的形状：一条 `Plan review` 条带、计划作为可滚动的 markdown 主体、问题文本作为卡片的无障碍名称，以及一行 `Chat about it` / `Refuse` / `Approve` 的决定操作。Approve 与 Refuse 用提问方自己的选项标签回答（意图指名哪个标签表示批准，因此裁决绝不依赖选项顺序），并把提问方的描述保留为 tooltip；`Chat about it` 以 `ASK_CANCELLED` 拒绝该等待，让编辑器归位，用户可以直接说出他想说的话。未声明意图、一批含多个问题、或未提供被指名的批准标签的请求，一律留在通用流程上 —— 意图改变的只是布局，从不改变答案。 +若某个请求的唯一问题声明了呈现意图，则改为渲染该意图自己的界面。`plan-review` —— 由 `dsh-plan-mode` 在 `exit_plan_mode` 审阅上设置 —— 采用等待审批卡片的形状：一条 `Plan review` 条带、计划作为可滚动的 markdown 主体、问题文本作为卡片的无障碍名称，以及一行 `Chat about it` / `Refuse` / `Approve` 的决定操作。Approve 与 Refuse 用提问方自己的选项标签回答（意图指名哪个标签表示批准，因此裁决绝不依赖选项顺序），并把提问方的描述保留为 tooltip；`Chat about it` 以 `ASK_CANCELLED` 拒绝该等待，让编辑器归位，用户可以直接说出他想说的话。卡片只在能够发出该请求允许的每一个答案时才接管：只有一个问题、声明了意图、计划以 `detail` 存在、提供了被指名的批准标签，且是二元单选（除批准外最多一个选项，且非多选）。其他任何情形 —— 没有意图、一批含多个问题、缺少计划、批准标签未命中任何选项、出现第三个选项、多选决定 —— 都留在能够表达它的通用流程上。意图改变的只是布局，从不改变可达的答案。 选择状态只存在于以请求 rpcId 为 key 的组件本地。使用相同 id 回放时，只要组件仍挂载，就会保留草稿；主机发出的 `question/resolved` 则会移除编辑器。主机仍具有最终决定权：HTTP 交付成功不会在本地移除待处理状态。 diff --git a/packages/client/ui-question/src/client/contract/slots.ts b/packages/client/ui-question/src/client/contract/slots.ts index f92eb33f52..8f9d9f8c75 100644 --- a/packages/client/ui-question/src/client/contract/slots.ts +++ b/packages/client/ui-question/src/client/contract/slots.ts @@ -49,12 +49,16 @@ export interface PlanReview { * Narrow a request to a renderable plan review, or return undefined to leave it * to the generic question flow. * - * The card is one decision over one plan, so it claims a request only when the - * batch is a single question that declares the intent, carries the plan as its - * detail, and offers the approve label the intent names. The asker's own - * service validates that label, but this is a wire boundary: a request failing - * any part of it still renders and stays answerable as a generic question - * rather than reaching a card that cannot express it. + * The card is one decision over one plan, and it claims a request only when it + * can send every answer that request allows — an intent changes the layout, + * never which answers are reachable. So the batch must be a single question + * that declares the intent, carries the plan as its detail, offers the approve + * label the intent names, and is a binary single choice: at most one option + * besides approve, and not multi-select. A third option or a multi-select batch + * has answers two buttons cannot express, so the generic flow keeps it — as it + * keeps any request whose intent the asker's own service would have rejected, + * because the client sits downstream of a wire boundary and every request must + * stay answerable. * * @param questions - the request's whole question batch. * @returns The narrowed review, or undefined when the generic flow owns it. @@ -65,7 +69,9 @@ export function planReviewOf(questions: readonly QuestionItem[]): PlanReview | u const question = questions[0] as QuestionItem const intent = question.intent if (intent?.kind !== 'plan-review' || question.detail === undefined) return undefined + if (question.multiSelect === true) return undefined const options = question.options ?? [] + if (options.length > 2) return undefined const approve = options.find(option => option.label === intent.approve) if (approve === undefined) return undefined const decline = options.find(option => option.label !== intent.approve) diff --git a/packages/client/ui-question/src/client/index.ts b/packages/client/ui-question/src/client/index.ts index 9c6893fd18..8cc25aeb88 100644 --- a/packages/client/ui-question/src/client/index.ts +++ b/packages/client/ui-question/src/client/index.ts @@ -20,7 +20,7 @@ import type { QuestionWait } from './contract/slots.ts' import { QuestionComposer } from './QuestionComposer.tsx' import { en, zh, type QuestionKey } from './locales.ts' -export { PendingQuestion, planReviewOf } from './contract/slots.ts' +export { PendingQuestion } from './contract/slots.ts' export type { PlanReview, QuestionAnswer, QuestionComposerProps, QuestionWait, } from './contract/slots.ts' diff --git a/packages/client/ui-question/tests/plan-review-panel.spec.tsx b/packages/client/ui-question/tests/plan-review-panel.spec.tsx index 3c2c456c57..069445415f 100644 --- a/packages/client/ui-question/tests/plan-review-panel.spec.tsx +++ b/packages/client/ui-question/tests/plan-review-panel.spec.tsx @@ -95,6 +95,13 @@ describe('planReviewOf', () => { ...questions()[0] as object, intent: { kind: 'plan-review', approve: 'Ship it' }, }]], ['an intent with no options at all', () => [{ ...questions()[0] as object, options: undefined }]], + // Two buttons cannot send a third label or a combination, and the generic + // flow can: an intent never costs the user a reachable answer. + ['a third option the card could not offer', () => [{ + ...questions()[0] as object, + options: [{ label: 'Approve' }, { label: 'Keep planning' }, { label: 'Start over' }], + }]], + ['a multi-select decision', () => [{ ...questions()[0] as object, multiSelect: true }]], ])('declines %s, leaving the request to the generic flow', (_case, build) => { expect(planReviewOf(build() as never)).toBeUndefined() }) diff --git a/packages/ui/user-interaction/README.i18n.yaml b/packages/ui/user-interaction/README.i18n.yaml index 96973400df..a74e6ec71b 100644 --- a/packages/ui/user-interaction/README.i18n.yaml +++ b/packages/ui/user-interaction/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/user-interaction/README.md -README.md: f134e912149190efb81ea9f64c5d63632ce8c626 -README.zh.md: ab6432dcbddc36d3ef9ca957b3901cb76257539a +README.md: d62e75d110b8be339c5f9449b0834320f695ac99 +README.zh.md: 55258e85e56df2375ed8f195fa0b3b731a9cb816 diff --git a/packages/ui/user-interaction/README.md b/packages/ui/user-interaction/README.md index f134e91214..d62e75d110 100644 --- a/packages/ui/user-interaction/README.md +++ b/packages/ui/user-interaction/README.md @@ -24,7 +24,7 @@ When an answer includes `custom`, `selected` is empty; custom text is an overrid ### Presentation intent -`intent` declares that a question IS a decision of a known shape, so a UI that recognises the tag may present it as such — `plan-review` says `detail` is a plan under review, and `dsh-plan-mode` sets it on the `exit_plan_mode` question. An intent shapes presentation only: a UI honouring it answers with the same option labels a generic UI would send, and a UI that does not know the tag renders the generic option list, so callers read one answer shape either way. `approve` names the label that approves rather than relying on option order; `ask()` rejects an intent whose `approve` names none of that question's own options with `BAD_INTENT`, since no type can tie the two together. +`intent` declares that a question IS a decision of a known shape, so a UI that recognises the tag may present it as such — `plan-review` says `detail` is a plan under review, and `dsh-plan-mode` sets it on the `exit_plan_mode` question. An intent shapes presentation only: a UI honouring it answers with the same option labels a generic UI would send, and a UI that does not know the tag renders the generic option list, so callers read one answer shape either way. `approve` names the label that approves rather than relying on option order. `ask()` rejects with `BAD_INTENT` the two assertions no type can carry: an `approve` naming none of that question's own options, and an intent on a question with no `detail` — the thing it declares itself a review of. ## Role diff --git a/packages/ui/user-interaction/README.zh.md b/packages/ui/user-interaction/README.zh.md index ab6432dcbd..55258e85e5 100644 --- a/packages/ui/user-interaction/README.zh.md +++ b/packages/ui/user-interaction/README.zh.md @@ -24,7 +24,7 @@ ### 呈现意图 -`intent` 声明某个问题本身就是一次已知形状的决定，因此认识该标签的 UI 可以照此呈现 —— `plan-review` 表示 `detail` 是一份待审阅的计划，`dsh-plan-mode` 会在 `exit_plan_mode` 的问题上设置它。意图只塑造呈现：遵循它的 UI 回答的仍是通用 UI 会发送的那些选项标签，不认识该标签的 UI 渲染通用选项列表，因此调用方两种情况下读到的都是同一种回答形态。`approve` 指名表示批准的标签，而不依赖选项顺序；由于没有类型能把两者绑定起来，`ask()` 会以 `BAD_INTENT` 拒绝 `approve` 未命中该问题自身任一选项的意图。 +`intent` 声明某个问题本身就是一次已知形状的决定，因此认识该标签的 UI 可以照此呈现 —— `plan-review` 表示 `detail` 是一份待审阅的计划，`dsh-plan-mode` 会在 `exit_plan_mode` 的问题上设置它。意图只塑造呈现：遵循它的 UI 回答的仍是通用 UI 会发送的那些选项标签，不认识该标签的 UI 渲染通用选项列表，因此调用方两种情况下读到的都是同一种回答形态。`approve` 指名表示批准的标签，而不依赖选项顺序。有两项断言是任何类型都承载不了的，`ask()` 会以 `BAD_INTENT` 拒绝它们：`approve` 未命中该问题自身的任一选项，以及意图落在没有 `detail` 的问题上 —— 而 `detail` 正是它自称在审阅的东西。 ## 职责 diff --git a/packages/ui/user-interaction/src/index.ts b/packages/ui/user-interaction/src/index.ts index af0aa40e7b..506b3c6bfe 100644 --- a/packages/ui/user-interaction/src/index.ts +++ b/packages/ui/user-interaction/src/index.ts @@ -87,10 +87,13 @@ export class UserInteractionService extends Service { if (request.questions.length === 0) { throw new UserInteractionError('ask_user_question requires at least one question', 'EMPTY_QUESTIONS') } - // A presentation intent names an option label the types cannot pin to its - // own question's option list. A UI honouring the intent answers with that - // label, so a name matching nothing would answer a choice the asker never - // offered — caught here, at the asker, rather than in a UI. + // A presentation intent asserts two things the types cannot: that the + // named approve label is one of this question's own options, and that a + // plan-review carries the plan it is a review of. A UI honouring the + // intent answers with that label, and shows that detail as the plan, so + // either gap would put a choice the asker never offered — or an approval of + // something invisible — in front of the user. Caught at the asker, where + // the mistake is, rather than in each UI. for (const question of request.questions) { const intent = question.intent if (intent === undefined) continue @@ -100,6 +103,11 @@ export class UserInteractionService extends Service { + `${JSON.stringify(intent.approve)} names none of its options`, 'BAD_INTENT') } + if (question.detail === undefined) { + throw new UserInteractionError( + `question ${question.id} declares intent ${intent.kind} without the detail it reviews`, + 'BAD_INTENT') + } } if (this.provider === undefined) { throw new UserInteractionError('no user-interaction provider is registered', 'NO_PROVIDER') diff --git a/packages/ui/user-interaction/src/types.ts b/packages/ui/user-interaction/src/types.ts index 15747e371c..63949e81a1 100644 --- a/packages/ui/user-interaction/src/types.ts +++ b/packages/ui/user-interaction/src/types.ts @@ -21,7 +21,7 @@ export interface AskUserQuestionOption { * either way — an intent shapes presentation only, never the protocol. */ export type AskUserQuestionIntent = { - /** A plan submitted for review: `detail` is the plan markdown, and the decision approves or declines it. */ + /** A plan submitted for review: `detail` is the plan markdown `ask()` requires, and the decision approves or declines it. */ kind: 'plan-review' /** * The option label that approves the plan; every other option declines it. diff --git a/packages/ui/user-interaction/tests/user-interaction.spec.ts b/packages/ui/user-interaction/tests/user-interaction.spec.ts index e9fca39761..df6b878cbd 100644 --- a/packages/ui/user-interaction/tests/user-interaction.spec.ts +++ b/packages/ui/user-interaction/tests/user-interaction.spec.ts @@ -104,6 +104,24 @@ describe('UserInteractionService', () => { expect(p.ask).not.toHaveBeenCalled() }) + it('rejects a plan-review intent on a question carrying no plan to review', async () => { + const ctx = new Context() + await ctx.plugin(UserInteractionService) + const p = { ask: vi.fn(async () => ({ answers: [] })) } + ctx.userInteraction.registerProvider(p) + + // Detail IS the plan for this intent, so a UI honouring it would ask the + // user to approve something they cannot see. + await expect(ctx.userInteraction.ask({ + questions: [{ + id: 'plan-review', question: 'Approve?', + options: [{ label: 'Approve' }, { label: 'Keep planning' }], + intent: { kind: 'plan-review', approve: 'Approve' }, + }], + })).rejects.toMatchObject({ name: 'UserInteractionError', code: 'BAD_INTENT' }) + expect(p.ask).not.toHaveBeenCalled() + }) + it('passes an intent through once its approve label names an offered option', async () => { const ctx = new Context() await ctx.plugin(UserInteractionService) From 6777e4fab97315c398f676eb37b9416c933c435d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 30 Jul 2026 21:14:03 +0800 Subject: [PATCH 13/24] fix(fs-search): make glob sampling an explicit choice --- .../2026-07-27-glob-sampling.i18n.yaml | 4 +- .../bug-fix/2026-07-27-glob-sampling.md | 16 ++++---- .../bug-fix/2026-07-27-glob-sampling.zh.md | 16 ++++---- apps/cli/config/base.cordis.yml | 2 + docs/config-catalog.md | 4 +- docs/tool-catalog.md | 4 +- .../tests/fs-search.cordis.snapshot.yml | 1 + examples/acp-agent/tests/fs-search.cordis.yml | 1 + packages/fs/tool-fs-search/README.i18n.yaml | 4 +- packages/fs/tool-fs-search/README.md | 31 ++++++++------ packages/fs/tool-fs-search/README.zh.md | 31 ++++++++------ packages/fs/tool-fs-search/src/glob.ts | 41 +++++++++++++------ packages/fs/tool-fs-search/src/index.ts | 6 ++- .../tool-fs-search/tests/integration.spec.ts | 2 +- .../fs/tool-fs-search/tests/load-path.spec.ts | 2 +- .../fs/tool-fs-search/tests/tools.spec.ts | 38 +++++++++++++++-- scripts/gen-tool-catalog.ts | 4 +- 17 files changed, 140 insertions(+), 67 deletions(-) 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 7c11db5207..6a898fa0a4 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: b9dfc7fc89ff61824094ccd5297f766c665f4edb -2026-07-27-glob-sampling.zh.md: 4f022467e461247c746e906b32f5ecffcb885d56 +2026-07-27-glob-sampling.md: 67912cf290b127a96819d57f30387197af68323d +2026-07-27-glob-sampling.zh.md: e339a5f87b483849df60feb726b061fe85074300 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 b9dfc7fc89..67912cf290 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 @@ -12,15 +12,17 @@ Three individually valid behaviors composed into the false impression. A glob wi ## Decision -A result that fits within `globMaxResults` remains complete and byte-for-byte modification-time ordered. An over-cap result is sampled round-robin across the complete result's top-level entries: every entry receives one slot before any receives a second, exhausted groups drop out, and relative order remains stable within each group. Grouping is relative to the actual search root, including an explicit `path`. +A result that fits within `globMaxResults` remains complete and byte-for-byte modification-time ordered. The required `sampleOverCapGlobResults` config has no fallback: `false` retains the modification-time head for an over-cap result, while `true` samples round-robin across the complete result's top-level entries. In sampling mode, every entry receives one slot before any receives a second, exhausted groups drop out, relative order remains stable within each group, and grouping is relative to the actual search root, including an explicit `path`. -The footer states that the page is a cross-entry sample rather than the modification-time head, reports how many top-level entries it reaches when that fact adds information, and preserves the complete sorted list in the spill artifact. When more top-level entries exist than inline slots, it tells the model to narrow `path`. +In sampling mode, the footer states that the page is a cross-entry sample rather than the modification-time head and reports how many top-level entries it reaches when that fact adds information. When more top-level entries exist than inline slots, it tells the model to narrow `path`. Head mode keeps the ordinary capped-result footer. When spill succeeds, both modes preserve the complete sorted list in the artifact. -The prompt and schema also state that a pattern without `/` matches at any depth and that glob returns files, never directory entries. Directory orientation remains ordinary shell work in deployments that expose the model-facing bash tool: use `ls` for one directory, and glob for a named file-path pattern across the tree. `ctx.fs.listDir` remains an internal provider primitive used by skill discovery; this decision adds no model-facing `list` tool. +The prompt and schema state the configured over-cap ordering, that a pattern without `/` matches at any depth, and that glob returns files, never directory entries. The shipped CLI composition explicitly selects head mode; deployments that want representative capped pages select sampling mode. Directory orientation remains ordinary shell work in deployments that expose the model-facing bash tool: use `ls` for one directory, and glob for a named file-path pattern across the tree. `ctx.fs.listDir` remains an internal provider primitive used by skill discovery; this decision adds no model-facing `list` tool. ## Alternatives considered -**Keep the modification-time head and only warn about concentration.** Rejected after measuring the failure shape. A warning asks the model to distrust the only paths it received; representative data fixes the answer directly. +**Keep the modification-time head as the only behavior.** Rejected after measuring the failure shape. Some deployments need the stable ordering, but a deployment that values workspace orientation can explicitly select representative data instead of asking the model to distrust the only paths it received. + +**Give the sampling choice a default.** Rejected. No product-wide evidence establishes either ordering as the implicit contract, so every composition selects one and misconfiguration fails at load. **Sample every result.** Rejected. A complete result loses nothing to truncation, so modification-time order remains useful for age-oriented questions. Sampling begins only when the head stops describing the whole. @@ -36,10 +38,10 @@ The prompt and schema also state that a pattern without `/` matches at any depth ## Consequences -An over-cap glob page no longer answers age-order questions from its inline paths; its footer says so, and the spill artifact retains the complete sorted view. Sampling balances only the first segment beneath the search root, so a deeper hot subtree can still dominate within one top-level entry. +A sampling-mode over-cap page no longer answers age-order questions from its inline paths; its footer says so, and the spill artifact retains the complete sorted view. Sampling balances only the first segment beneath the search root, so a deeper hot subtree can still dominate within one top-level entry. Head mode retains the concentration risk as an explicit deployment trade-off. -The tool surface does not grow. The fix changes glob's prompt, schema description, canonical output (`root` records the sampling basis), and over-cap Native rendering while leaving fitting results unchanged. +The tool surface does not grow. Every composition must set `sampleOverCapGlobResults`; changing it alters glob's prompt, schema description, and over-cap Native rendering. The canonical output keeps `root` so sampling mode can recover its grouping basis, while fitting results remain unchanged. ## 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 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. +Package tests pin the required config, both over-cap modes, their prompt and schema descriptions, 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 explicitly enables sampling, 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 4f022467e4..e339a5f87b 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 @@ -12,15 +12,17 @@ Status: implemented ## 决策 -未超过 `globMaxResults` 的结果仍保持完整，且按修改时间排序的内容逐字节不变。超过上限时，系统会在完整结果的顶层条目之间按轮转方式采样：每个条目都先获得一个位置，之后才有条目获得第二个位置；已经用尽的分组会退出轮转；各组内部的相对顺序保持稳定。分组始终以实际搜索根为基准，显式指定 `path` 时也如此。 +未超过 `globMaxResults` 的结果仍保持完整，且按修改时间排序的内容逐字节不变。必填的 `sampleOverCapGlobResults` 配置没有回退值：`false` 会为超过上限的结果保留按修改时间排序的前部，`true` 则会在完整结果的顶层条目之间按轮转方式采样。采样模式下，每个条目都先获得一个位置，之后才有条目获得第二个位置；已经用尽的分组会退出轮转；各组内部的相对顺序保持稳定；分组以实际搜索根为基准，显式指定 `path` 时也如此。 -footer 会说明当前页面是跨条目的样本，而不是按修改时间排序的前部；当顶层条目覆盖数能提供额外信息时，还会报告该数量；完整排序列表仍保存在 spill 产物中。若顶层条目数量超过内联位置数，footer 会要求模型缩小 `path`。 +采样模式下，footer 会说明当前页面是跨条目的样本，而不是按修改时间排序的前部；当触达的顶层条目数能提供额外信息时，还会报告该数量。若顶层条目数量超过内联位置数，footer 会要求模型缩小 `path`。保留前部的模式沿用达到上限时的普通 footer。spill 成功时，两种模式都会在该产物中保留完整排序列表。 -提示词与 schema 还会说明：不含 `/` 的模式会匹配任意深度，glob 只返回文件，绝不返回目录条目。在向模型暴露 bash 工具的部署中，目录定位仍由普通 shell 操作完成：查看一个目录使用 `ls`，跨目录树按指定文件路径模式查找则使用 glob。skill（技能）发现流程仍将 `ctx.fs.listDir` 作为内部提供方原语使用；本决策不会新增面向模型的 `list` 工具。 +提示词与 schema 会说明配置所指定的超限结果排序方式、不含 `/` 的模式会匹配任意深度，以及 glob 只返回文件而绝不返回目录条目。随产品交付的 CLI（命令行界面）组合显式选择保留前部的模式；希望达到上限的页面具有代表性的部署则选择采样模式。在向模型暴露 bash 工具的部署中，目录定位仍由普通 shell 操作完成：查看一个目录使用 `ls`，跨目录树按指定文件路径模式查找则使用 glob。skill（技能）发现流程仍将 `ctx.fs.listDir` 作为内部提供方原语使用；本决策不会新增面向模型的 `list` 工具。 ## 考虑过的替代方案 -**保留按修改时间排序的前部，只警告结果过于集中。** 测量实际故障形态后否决。警告只会要求模型怀疑自己拿到的唯一一批路径；具有代表性的数据能直接修正答案。 +**只保留按修改时间排序的前部。** 测量实际故障形态后否决。某些部署需要这种稳定排序；但重视工作区定位的部署可以显式选择具有代表性的数据，而不必要求模型怀疑自己拿到的唯一一批路径。 + +**为采样选项提供默认值。** 否决。没有全产品范围的证据支持把任一排序作为隐式契约，因此每个组合都必须选择一种，配置错误则在加载时失败。 **对所有结果采样。** 否决。完整结果没有因截断损失任何信息，因此按修改时间排序仍有助于回答关注新旧时间的问题。只有当截取前部已经无法描述整体时，才开始采样。 @@ -36,10 +38,10 @@ footer 会说明当前页面是跨条目的样本，而不是按修改时间排 ## 影响 -超过上限的 glob 页面无法再根据内联路径回答按时间判断新旧的问题；footer 会明确说明这一点，spill 产物仍保留完整的排序视图。采样只平衡搜索根下的第一路径段，因此某个顶层条目内部较深处、结果密集的子树仍可能占据主导。 +采样模式下，超过上限的 glob 页面无法再根据内联路径回答按时间判断新旧的问题；footer 会明确说明这一点，spill 产物仍保留完整的排序视图。采样只平衡搜索根下的第一路径段，因此某个顶层条目内部较深处、结果密集的子树仍可能占据主导。保留前部的模式则把集中风险作为显式部署取舍保留下来。 -工具接口不会扩大。此修复会更改 glob 的提示词、schema 描述、规范输出（`root` 记录采样基准）以及超过上限时的 Native 渲染，未超过上限的结果保持不变。 +工具接口不会扩大。每个组合都必须设置 `sampleOverCapGlobResults`；更改该值会改变 glob 的提示词、schema 描述以及超过上限时的 Native 渲染。规范输出保留 `root`，以便采样模式恢复其分组基准；未超过上限的结果保持不变。 ## 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。 +包测试锁定了必填配置、两种超过上限模式及其提示词和 schema 描述、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）场景会显式启用采样，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/apps/cli/config/base.cordis.yml b/apps/cli/config/base.cordis.yml index 67c2b3b551..bc8c3434de 100644 --- a/apps/cli/config/base.cordis.yml +++ b/apps/cli/config/base.cordis.yml @@ -102,6 +102,8 @@ - id: tool-fs-search name: '@deepseek-ai/dsh-tool-fs-search' + config: + sampleOverCapGlobResults: false - id: workspace-context name: '@deepseek-ai/dsh-workspace-context' diff --git a/docs/config-catalog.md b/docs/config-catalog.md index dde2d6f65b..98b798b9b7 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1664,8 +1664,10 @@ Source: [`packages/fs/tool-fs/src/index.ts:24`](../packages/fs/tool-fs/src/index Requires: `tools` · `systemPrompt` · `bash` ```ts config-catalog -/** Plugin config (all optional — `Config` supplies the defaults). */ +/** Plugin config; over-cap glob sampling is an explicit deployment choice and the remaining fields have defaults. */ export interface Config { + /** Whether an over-cap `glob` page is sampled across top-level entries instead of taking the modification-time head. */ + sampleOverCapGlobResults: boolean /** Max paths one `glob` call retains inline; later paths go to the formatted spill file. */ globMaxResults?: number /** Max flat matches one `grep` call retains inline; later matches go to the formatted spill file. */ diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index bac13da635..7d6fa79dea 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). 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.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-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). 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 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-pty` diff --git a/examples/acp-agent/tests/fs-search.cordis.snapshot.yml b/examples/acp-agent/tests/fs-search.cordis.snapshot.yml index e1755ec9d4..141691a087 100644 --- a/examples/acp-agent/tests/fs-search.cordis.snapshot.yml +++ b/examples/acp-agent/tests/fs-search.cordis.snapshot.yml @@ -31,4 +31,5 @@ - id: tool-fs-search name: '@deepseek-ai/dsh-tool-fs-search' config: + sampleOverCapGlobResults: true globMaxResults: 4 diff --git a/examples/acp-agent/tests/fs-search.cordis.yml b/examples/acp-agent/tests/fs-search.cordis.yml index 171ab88980..153128f914 100644 --- a/examples/acp-agent/tests/fs-search.cordis.yml +++ b/examples/acp-agent/tests/fs-search.cordis.yml @@ -29,4 +29,5 @@ - id: tool-fs-search name: '@deepseek-ai/dsh-tool-fs-search' config: + sampleOverCapGlobResults: true globMaxResults: 4 diff --git a/packages/fs/tool-fs-search/README.i18n.yaml b/packages/fs/tool-fs-search/README.i18n.yaml index 2d11c1356a..bedb8289c1 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: 51b3fa5385330cdaba0b36dd71a6efe4fd3d0db5 -README.zh.md: de9e50c90724cbc40f6de5880e7000ae0552b52d +README.md: b12ffda9869c7d6bef5ea5b54594781ecf555ff4 +README.zh.md: 7dd6cdf9a209f2fe357b4ffe48d20d574266ce60 diff --git a/packages/fs/tool-fs-search/README.md b/packages/fs/tool-fs-search/README.md index 51b3fa5385..b12ffda986 100644 --- a/packages/fs/tool-fs-search/README.md +++ b/packages/fs/tool-fs-search/README.md @@ -5,9 +5,9 @@ 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. ```ts ignore-check -// Default deployment: a bash executor whose PATH includes rg, then the discovery tools. +// 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(ToolFsSearch) // this package — conditionally registers glob/grep +await ctx.plugin(ToolFsSearch, { sampleOverCapGlobResults: false }) // Optional: a spill backend makes capped results fully recoverable. await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh-spill-local ``` @@ -20,11 +20,12 @@ The mounted bash executor must be able to resolve `rg` from its `PATH` at plugin ## Config -All keys are optional; the defaults are the shipped search caps. +`sampleOverCapGlobResults` is required and has no fallback; deployments choose the over-cap ordering contract explicitly. The remaining keys are optional search caps with the defaults below. | Key | Default | Meaning | |---|---|---| -| `globMaxResults` | `100` | Max paths one `glob` call shows inline (matches Claude Code's `GlobTool` limit). Within it the result is shown whole in modification-time order; beyond it the inline page is sampled across top-level entries and the complete sorted list goes to the formatted spill artifact. | +| `sampleOverCapGlobResults` | none (required) | `true` samples an over-cap `glob` page across top-level entries; `false` keeps the modification-time-ordered head. When formatted spill succeeds, both modes preserve the complete sorted list in that artifact. | +| `globMaxResults` | `100` | Max paths one `glob` call shows inline (matches Claude Code's `GlobTool` limit). A result within the cap remains complete and modification-time ordered. | | `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`. | @@ -34,14 +35,14 @@ All keys are optional; the defaults are the shipped search caps. | 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, modification-time ordered; `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. | +| `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`. | | `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 }`; `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 a head 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 `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`. ## Errors @@ -55,12 +56,18 @@ Search failures carry the package-owned `SearchError` (a `HarnessError` subclass 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. -##### Glob guidance +##### Glob guidance with `sampleOverCapGlobResults: true` ```markdown 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. ``` +##### Glob guidance with `sampleOverCapGlobResults: false` + +```markdown +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 keeps the modification-time-ordered head. +``` + ##### Grep guidance ```markdown @@ -69,17 +76,17 @@ Use the grep tool — not shell grep or rg — to search file contents. Use read #### Token effect -Fixed guidance cost per request while the tools are registered. +Fixed guidance cost per request while the tools are registered; the required sampling choice selects one glob variant. #### KV Cache effect -Prefix-stable while the plugin scope and guidance text are unchanged. Activation or disposal may invalidate reuse from this prompt section. +Prefix-stable while the plugin scope, sampling choice, and guidance text are unchanged. Activation, disposal, or changing the choice may invalidate reuse from this prompt section. ### Tool schemas #### What the model sees -The generated [`glob` and `grep` schemas](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs-search) after the load-time `rg` probe succeeds and while this surface is visible. +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. #### Token effect @@ -93,7 +100,7 @@ Prefix-stable while tool visibility and definitions are unchanged. Registration #### What the model sees -`glob` returns one path per line; `grep` groups `Line : ` matches beneath each path. Empty searches return `No files found` or `No matches found`. A capped result ends with its omission count plus the spill locator and backend retrieval hint, or says the complete result could not be saved. An over-cap `glob` result does not show the head of the sorted list: its inline page takes paths round-robin across entries immediately beneath the actual search root, so one old-timestamped subtree cannot own every slot, and the footer states the sampled basis and how many top-level entries it reached. When it cannot reach them all, the footer tells the model to narrow `path`. A result that fits inline is untouched, and a flat result — every path its own top-level entry — keeps the plain footer, because there the sample is the modification-time-ordered head. The spill artifact always holds the complete list in modification-time order. +`glob` returns one path per line; `grep` groups `Line : ` matches beneath each path. Empty searches return `No files found` or `No matches found`. A capped result ends with its omission count plus the spill locator and backend retrieval hint, or says the complete result could not be saved. With `sampleOverCapGlobResults: true`, an over-cap `glob` page takes paths round-robin across entries immediately beneath the actual search root, and the footer states the sampled basis and how many top-level entries it reached; when it cannot reach them all, the footer tells the model to narrow `path`. With `false`, the page is the modification-time-ordered head and keeps the plain capped-result footer. A result that fits inline is untouched, and a flat sampled result also keeps the plain footer because its sample equals the modification-time head. The spill artifact always holds the complete list in modification-time order. #### Token effect @@ -122,4 +129,4 @@ Append-only; newly visible content follows the reusable request prefix and does - **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. - **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 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. +- **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 de9e50c907..7dd6cdf9a2 100644 --- a/packages/fs/tool-fs-search/README.zh.md +++ b/packages/fs/tool-fs-search/README.zh.md @@ -5,9 +5,9 @@ **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()`。 ```ts ignore-check -// Default deployment: a bash executor whose PATH includes rg, then the discovery tools. +// 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(ToolFsSearch) // this package — conditionally registers glob/grep +await ctx.plugin(ToolFsSearch, { sampleOverCapGlobResults: false }) // Optional: a spill backend makes capped results fully recoverable. await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh-spill-local ``` @@ -20,11 +20,12 @@ await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh- ## 配置 -所有键均为可选；默认值是随产品交付的搜索上限。 +`sampleOverCapGlobResults` 是必填项且没有回退值；部署必须显式选择超过上限时的排序契约。其余键是可选的搜索上限，默认值如下。 | 键 | 默认值 | 含义 | |---|---|---| -| `globMaxResults` | `100` | 一次 `glob` 调用内联展示的最大路径数（与 Claude Code 的 `GlobTool` 上限相同）。未超过时结果整体按修改时间展示；超过时内联页面改为跨顶层条目取样，完整的排序列表写入格式化 spill 产物。 | +| `sampleOverCapGlobResults` | 无（必填） | `true` 会在顶层条目之间对超过上限的 `glob` 页面采样；`false` 保留按修改时间排序的前部。格式化 spill 成功时，两种模式都会在该产物中保留完整排序列表。 | +| `globMaxResults` | `100` | 一次 `glob` 调用内联展示的最大路径数（与 Claude Code 的 `GlobTool` 上限相同）。未超过上限的结果保持完整，并按修改时间排序。 | | `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。 | @@ -34,14 +35,14 @@ await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh- | 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。未超过 `globMaxResults` 的结果按修改时间排序；超过时内联页面改为跨顶层条目取样（见下）。 | +| `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`。 | | `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；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，并只把呈现替换为头部页面加 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 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`。 ## 错误 @@ -55,12 +56,18 @@ await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh- 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。 -##### Glob 指导 +##### 启用 `sampleOverCapGlobResults: true` 时的 Glob 指导 ```markdown 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. ``` +##### 启用 `sampleOverCapGlobResults: false` 时的 Glob 指导 + +```markdown +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 keeps the modification-time-ordered head. +``` + ##### Grep 指导 ```markdown @@ -69,17 +76,17 @@ 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。 +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。 #### KV Cache 影响 -只要插件作用域和指导文本不变，前缀就保持稳定。启用或 dispose（资源释放）可能从该提示词段开始使复用失效。 +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。 ### 工具 schema #### 模型看到的内容 -当前接口可见时，公开已生成的 [`glob` 和 `grep` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs-search)；前提是加载时 `rg` 探测成功。 +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。 #### Token 影响 @@ -93,7 +100,7 @@ Use the grep tool — not shell grep or rg — to search file contents. Use read #### 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。超过上限的 `glob` 结果不再展示排序列表的头部：其内联页面按轮转方式跨实际搜索根正下方的条目取样，因此单个时间戳较旧的子树无法占满所有位置；footer 会说明取样依据及其触达的顶层条目数。无法触达全部时，footer 会要求模型缩小 `path`。未超过上限的结果原样不动；扁平结果（每个路径各自构成一个顶层条目）保留朴素 footer，因为此时取样结果就是按修改时间排序的头部。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。 #### Token 影响 @@ -122,4 +129,4 @@ Use the grep tool — not shell grep or rg — to search file contents. Use read - **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。 -- **取样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。 +- **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。 diff --git a/packages/fs/tool-fs-search/src/glob.ts b/packages/fs/tool-fs-search/src/glob.ts index 12af97a24b..c9806b7bd8 100644 --- a/packages/fs/tool-fs-search/src/glob.ts +++ b/packages/fs/tool-fs-search/src/glob.ts @@ -38,6 +38,8 @@ export const GLOB_VCS_EXCLUDES: readonly string[] = ['.git', '.svn', '.hg', '.bz /** Resolved glob-tool caps — plugin config after defaulting (see `Config` in index.ts). */ export interface GlobToolCaps { + /** Whether over-cap pages are sampled across top-level entries instead of taking the modification-time head. */ + sampleOverCapGlobResults: boolean /** Max paths retained inline; later paths go to the formatted spill file. */ maxResults: number /** Cap on the complete raw `rg` stdout the tool will parse. */ @@ -183,24 +185,32 @@ export function sampleAcrossTopLevel(paths: readonly string[], maxItems: number, * @returns the model-facing text. */ export function formatGlobOutput(sample: GlobSample, seen: number, spillRef: SpillRef | undefined): string { - const body = sample.items.join('\n') - const recovery = spillRef !== undefined - ? `Full sorted result stored at: ${spillRef.locator}. ${spillRef.retrievalHint}` - : 'The complete result could not be saved; narrow pattern or path to see more.' const basis = sample.total === seen ? '.' : `, sampled across ${sample.shown} of the ${sample.total} top-level entries this pattern matched instead of taken in modification-time order.` + (sample.shown < sample.total ? ' Narrow path to inspect a specific subtree.' : '') - return `${body}\n\n(Showing ${sample.items.length} of ${seen} paths${basis} ${recovery})` + return formatGlobPage(sample.items, seen, spillRef, basis) +} + +/** Format one bounded page and the recovery path for its complete sorted result. */ +function formatGlobPage(items: readonly string[], seen: number, spillRef: SpillRef | undefined, basis: string): string { + const body = items.join('\n') + const recovery = spillRef !== undefined + ? `Full sorted result stored at: ${spillRef.locator}. ${spillRef.retrievalHint}` + : 'The complete result could not be saved; narrow pattern or path to see more.' + return `${body}\n\n(Showing ${items.length} of ${seen} paths${basis} ${recovery})` } /** Bound and format one canonical path list for the Native surface relative to its search root. */ -function renderGlobPaths(paths: string[], maxResults: number, root: string, spillRef?: SpillRef): string { +function renderGlobPaths(paths: string[], caps: GlobToolCaps, root: string, spillRef?: SpillRef): string { if (paths.length === 0) return 'No files found' // A result that fits is shown whole, untouched: modification-time order is the // tool's contract, and over a complete result it is what answers age questions. - if (paths.length <= maxResults) return paths.join('\n') - return formatGlobOutput(sampleAcrossTopLevel(paths, maxResults, root), paths.length, spillRef) + if (paths.length <= caps.maxResults) return paths.join('\n') + if (!caps.sampleOverCapGlobResults) { + return formatGlobPage(paths.slice(0, caps.maxResults), paths.length, spillRef, '.') + } + return formatGlobOutput(sampleAcrossTopLevel(paths, caps.maxResults, root), paths.length, spillRef) } /** @@ -222,19 +232,24 @@ export function presentGlobCall(args: { pattern: string; path?: string }): Gener * @param caps - the deployment's resolved glob caps (plugin config after defaulting). */ export function applyGlobTool(ctx: Context, caps: GlobToolCaps): void { + const overCapGuidance = caps.sampleOverCapGlobResults + ? 'while a larger one is sampled across top-level entries, so it spans the tree instead of one subtree.' + : 'while a larger one keeps the modification-time-ordered head.' ctx.systemPrompt.section({ name: 'tool:glob', order: 103, text: '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.', + + `Results are files only, never directories, and include hidden and ignored files: a result that fits comes back in modification-time order, ${overCapGuidance}`, }) + const overCapDescription = caps.sampleOverCapGlobResults + ? `a larger result instead returns ${caps.maxResults} paths sampled across top-level entries` + : `a larger result returns the first ${caps.maxResults} paths in modification-time order` const tool = defineTool({ 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 ${caps.maxResults} paths come back in modification-time order; a larger result instead returns ${caps.maxResults} paths sampled across top-level entries, ` + + `Up to ${caps.maxResults} paths come back in modification-time order; ${overCapDescription}, ` + 'says so, and reports where the complete sorted list was saved. This tool does not enumerate directory entries.', parameters: { pattern: { @@ -255,7 +270,7 @@ export function applyGlobTool(ctx: Context, caps: GlobToolCaps): void { paths: { type: 'array', required: true, items: { type: 'string' } }, }, }, - render: (_args, value) => [{ type: 'text', text: renderGlobPaths(value.paths, caps.maxResults, value.root) }], + render: (_args, value) => [{ type: 'text', text: renderGlobPaths(value.paths, caps, value.root) }], }, async execute(args, exec) { const input = parseGlobArgs(args) @@ -284,7 +299,7 @@ export function applyGlobTool(ctx: Context, caps: GlobToolCaps): void { const spillRef = await trySaveFormattedResult(ctx, exec, 'glob-results.txt', paths.join('\n')) return { kind: 'accept', - content: [{ type: 'text', text: renderGlobPaths(paths, caps.maxResults, value.root, spillRef) }], + content: [{ type: 'text', text: renderGlobPaths(paths, caps, value.root, spillRef) }], ...decision.additionalContexts !== undefined ? { additionalContexts: decision.additionalContexts } : {}, } }) diff --git a/packages/fs/tool-fs-search/src/index.ts b/packages/fs/tool-fs-search/src/index.ts index b6ae6ebbad..eea213a938 100644 --- a/packages/fs/tool-fs-search/src/index.ts +++ b/packages/fs/tool-fs-search/src/index.ts @@ -58,8 +58,10 @@ 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'] -/** Plugin config (all optional — `Config` supplies the defaults). */ +/** Plugin config; over-cap glob sampling is an explicit deployment choice and the remaining fields have defaults. */ export interface Config { + /** Whether an over-cap `glob` page is sampled across top-level entries instead of taking the modification-time head. */ + sampleOverCapGlobResults: boolean /** Max paths one `glob` call retains inline; later paths go to the formatted spill file. */ globMaxResults?: number /** Max flat matches one `grep` call retains inline; later matches go to the formatted spill file. */ @@ -73,6 +75,7 @@ export interface Config { } export const Config: z = z.object({ + sampleOverCapGlobResults: z.boolean().required(), globMaxResults: z.number().default(GLOB_MAX_RESULTS), grepMaxMatches: z.number().default(GREP_MAX_MATCHES), grepMaxLineBytes: z.number().default(GREP_MAX_LINE_BYTES), @@ -137,6 +140,7 @@ export async function apply(ctx: Context, config: Config): Promise { return } applyGlobTool(ctx, { + sampleOverCapGlobResults: resolved.sampleOverCapGlobResults, maxResults: resolved.globMaxResults, rawOutputMaxBytes: resolved.rawOutputMaxBytes, timeoutMs: resolved.timeoutMs, diff --git a/packages/fs/tool-fs-search/tests/integration.spec.ts b/packages/fs/tool-fs-search/tests/integration.spec.ts index 6be9629460..8cb96e7e66 100644 --- a/packages/fs/tool-fs-search/tests/integration.spec.ts +++ b/packages/fs/tool-fs-search/tests/integration.spec.ts @@ -64,7 +64,7 @@ describe.skipIf(!hasRg)('search tools over the real bash executor + real rg', () await ctx.plugin(ToolRegistry) await ctx.plugin(LocalSubprocessService) await ctx.plugin(LocalBashExecutor, { cwd: dir, timeoutMs: 20_000 }) - await ctx.plugin(ToolFsSearch) + await ctx.plugin(ToolFsSearch, { sampleOverCapGlobResults: true }) }) afterEach(async () => { 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 0f72529567..71022720fc 100644 --- a/packages/fs/tool-fs-search/tests/load-path.spec.ts +++ b/packages/fs/tool-fs-search/tests/load-path.spec.ts @@ -82,7 +82,7 @@ describe('dsh-tool-fs-search real-load-path guard', () => { const loader = Object.create(Loader.prototype) as Loader const unwrapped = loader.unwrapExports(toolFsSearch) as Parameters[0] // A collapsed export shape (dropped inject) would throw "without inject" here. - const fiber = await ctx.plugin(unwrapped) + const fiber = await ctx.plugin(unwrapped, { sampleOverCapGlobResults: true }) expect(ctx.tools.schemas().map(s => s.name)).toEqual(expect.arrayContaining(['glob', 'grep'])) await fiber.dispose() }) diff --git a/packages/fs/tool-fs-search/tests/tools.spec.ts b/packages/fs/tool-fs-search/tests/tools.spec.ts index ccb3af5b80..da273ec2a2 100644 --- a/packages/fs/tool-fs-search/tests/tools.spec.ts +++ b/packages/fs/tool-fs-search/tests/tools.spec.ts @@ -111,12 +111,14 @@ class FakeSpill extends SpillStore { } interface SetupOptions { - config?: ToolFsSearch.Config + config?: Partial spill?: boolean probeError?: Error probeResult?: BashRunResult } +const DEFAULT_CONFIG = { sampleOverCapGlobResults: true } satisfies ToolFsSearch.Config + async function setup(options: SetupOptions = {}) { const ctx = new Context() const warnings: string[] = [] @@ -128,7 +130,7 @@ async function setup(options: SetupOptions = {}) { if (options.probeResult) bash.probeResult = options.probeResult if (options.probeError) bash.probeError = options.probeError if (options.spill === true) await ctx.plugin(FakeSpill) - const fiber = await ctx.plugin(ToolFsSearch, options.config) + 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 } } @@ -216,7 +218,7 @@ describe('registration', () => { const ctx = new Context() await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) - await ctx.plugin(ToolFsSearch) // no bash executor + await ctx.plugin(ToolFsSearch, DEFAULT_CONFIG) // no bash executor expect(ctx.tools.schemas()).toHaveLength(0) }) @@ -241,9 +243,27 @@ describe('registration', () => { expect(ctx.tools.get('glob')?.timeoutMs).toBe(30_000) expect(ctx.tools.get('grep')?.timeoutMs).toBe(30_000) }) + + it('describes the modification-time head when over-cap sampling is disabled', async () => { + const { ctx } = await setup({ config: { sampleOverCapGlobResults: false } }) + const prompt = renderPrompt(await ctx.systemPrompt.assemble()) + expect(prompt).toContain('a larger one keeps the modification-time-ordered head') + expect(prompt).not.toContain('sampled across top-level entries') + const glob = ctx.tools.schemas().find(schema => schema.name === 'glob') + expect(glob?.description).toContain('a larger result returns the first 100 paths in modification-time order') + expect(glob?.description).not.toContain('sampled across top-level entries') + }) }) describe('config validation', () => { + it('requires an explicit over-cap glob sampling choice', () => { + expect(() => new ToolFsSearch.Config()).toThrow(/sampleOverCapGlobResults/) + expect(new ToolFsSearch.Config({ sampleOverCapGlobResults: false })).toMatchObject({ + sampleOverCapGlobResults: false, + globMaxResults: 100, + }) + }) + it.each([ ['globMaxResults', { globMaxResults: 0 }], ['grepMaxMatches', { grepMaxMatches: -1 }], @@ -255,7 +275,7 @@ describe('config validation', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(FakeBash) - await expect(ctx.plugin(ToolFsSearch, config)).rejects.toThrow(new RegExp(`tool-fs-search: ${name} must be a positive integer`)) + await expect(ctx.plugin(ToolFsSearch, { ...DEFAULT_CONFIG, ...config })).rejects.toThrow(new RegExp(`tool-fs-search: ${name} must be a positive integer`)) }) }) @@ -625,6 +645,16 @@ describe('glob results', () => { + 'The complete result could not be saved; narrow pattern or path to see more.)') }) + it('keeps the modification-time head when over-cap sampling is disabled', async () => { + const { ctx, bash } = 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')) + 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([ diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index b092154b21..a77bdb6d95 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -273,10 +273,10 @@ const TOOL_PACKAGES: ToolPackage[] = [ // 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) - await ctx.plugin(ToolFsSearch) + 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). 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 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.', }, { pkg: '@deepseek-ai/dsh-tool-pty', From 57fb5b488e4bd5cbf4f543330ce8894bdbd82de8 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Wed, 29 Jul 2026 03:03:43 +0800 Subject: [PATCH 14/24] feat: fork --- .../client/connection/src/client/fixture.ts | 45 ++++++++++++++ packages/client/connection/tests/fake-api.ts | 2 + .../runtime/src/client/contract/sessions.ts | 8 +++ .../runtime/src/client/sessions/manager.ts | 30 ++++++++++ .../runtime/src/client/sessions/service.ts | 32 ++++++++++ packages/client/runtime/tests/fake-api.ts | 2 + packages/client/test-runtime/src/sessions.ts | 13 +++- .../ui-conversation/src/client/apply.ts | 7 +++ .../src/client/chat/ChatView.tsx | 4 +- .../src/client/chat/MessageIconActions.tsx | 13 ++-- .../src/client/chat/MessageItem.tsx | 5 +- .../src/client/contract/slots.ts | 2 + .../ui-conversation/tests/chat-view.spec.tsx | 4 +- .../src/client/WorkspaceBrowser.tsx | 34 +++++++++-- .../ui-workspace/src/client/contract/slots.ts | 2 + .../client/ui-workspace/src/client/index.ts | 7 +++ .../ui-workspace/src/client/rows/Rows.tsx | 16 +++-- .../client/ui-workspace/tests/rows.spec.tsx | 54 ++++++++--------- .../tests/workspace-browser.spec.tsx | 1 + packages/host/apiproxy/src/api-proxy.ts | 60 +++++++++++++++++++ packages/host/apiproxy/src/api/rpc-map.ts | 1 + packages/host/apiproxy/src/api/rpc.schema.ts | 1 + packages/host/apiproxy/src/api/rpc.ts | 1 + .../host/apiproxy/src/api/sessions.schema.ts | 11 ++++ packages/host/apiproxy/src/api/sessions.ts | 14 +++++ packages/host/apiproxy/src/fetch/client.ts | 4 ++ packages/host/apiproxy/src/fetch/handler.ts | 2 + .../apiproxy/tests/client-handler.spec.ts | 1 + .../host/apiproxy/tests/fetch-carrier.spec.ts | 3 + 29 files changed, 330 insertions(+), 49 deletions(-) diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index cb79a6b9a2..282dfbee56 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -1042,6 +1042,50 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy { const appended = logOf(sessionId).at(-1) as SessionEvent return ok(request, { title: normalized, seq: appended.seq }) }, + fork: (request) => { + const { sessionId, atSeq } = request.payload + const source = summaryOf(sessionId) + if (source === undefined) { + return err(request, { + code: 'session-not-found', + message: `no session ${sessionId}`, + details: { sessionId }, + }) + } + const log = logs.get(sessionId) ?? [] + // Host-parallel boundary: first turn/end at or after atSeq, falling + // back to the last completed turn; no completed turn = fork-unavailable. + const boundary = (atSeq === undefined ? undefined : log.find(e => e.type === 'turn/end' && e.seq >= atSeq)) + ?? log.findLast(e => e.type === 'turn/end') + if (boundary === undefined) { + return err(request, { + code: 'fork-unavailable', + message: `session ${sessionId} has no completed turn`, + details: { sessionId }, + }) + } + let cut = boundary.seq + 1 + while (cut < log.length && log[cut]?.type !== 'turn/start') cut++ + const child: SessionSummary = { + sessionId: sid(`fx-${nextSession++}`), updatedAt: Date.now(), running: false, blank: false, + parentSessionId: sessionId, + ...source.cwd === undefined ? {} : { cwd: source.cwd }, + } + logs.set(child.sessionId, log.slice(0, cut)) + sessions.push(child) + emitHost({ + type: 'host/session-added', sessionId: child.sessionId, blank: false, + parentSessionId: sessionId, + ...source.cwd === undefined ? {} : { cwd: source.cwd }, + }) + const workspace = workspaces.find(w => w.sessionIds.includes(sessionId)) + if (workspace !== undefined) { + workspace.sessionIds = [child.sessionId, ...workspace.sessionIds] + workspace.updatedAt = new Date().toISOString() + emitHost({ type: 'host/workspace-changed', workspace: { ...workspace } }) + } + return ok(request, { sessionId: child.sessionId }) + }, history: async (request) => { const log = logs.get(request.payload.sessionId) ?? [] // Snapshot at request time, deliver after the transit delay (mirrors a real host under latency). @@ -1591,6 +1635,7 @@ export class FixtureApiClient extends AbstractApiClient { case 'session.models': return this.api.sessions.models(request) case 'session.selectModel': return this.api.sessions.selectModel(request) case 'session.rename': return this.api.sessions.rename(request) + case 'session.fork': return this.api.sessions.fork(request) case 'session.prompt': return this.api.sessions.prompt(request) case 'session.updateQueue': return this.api.sessions.updateQueue(request) case 'session.cancel': return this.api.sessions.cancel(request) diff --git a/packages/client/connection/tests/fake-api.ts b/packages/client/connection/tests/fake-api.ts index 89bcb9301d..8e99d9f9bb 100644 --- a/packages/client/connection/tests/fake-api.ts +++ b/packages/client/connection/tests/fake-api.ts @@ -46,6 +46,7 @@ export class FakeApiClient implements IApiClient { onList: (payload: unknown) => Promise> = () => Promise.resolve(ok({ items: [] })) onCreate: (payload: unknown) => Promise> = () => Promise.resolve(ok({ sessionId: 'fk-new' as SessionId })) onRename: (payload: unknown) => Promise> = () => Promise.resolve(ok({ title: 'fk-renamed', seq: 0 })) + onFork: (payload: unknown) => Promise> = () => Promise.resolve(ok({ sessionId: 'fk-fork' as SessionId })) onHistory: (payload: { sessionId: SessionId; beforeSeq?: number; maxMessages?: number }) => Promise> = () => Promise.resolve(ok({ @@ -99,6 +100,7 @@ export class FakeApiClient implements IApiClient { selectModel: (payload: ModelTarget & { sessionId: SessionId }) => this.record('session.selectModel', payload, this.onSelectModel(payload)), rename: (payload: unknown) => this.record('session.rename', payload, this.onRename(payload)), + fork: (payload: unknown) => this.record('session.fork', payload, this.onFork(payload)), prompt: (payload: unknown) => this.record('session.prompt', payload, this.onPrompt(payload)), updateQueue: (payload: unknown) => this.record('session.updateQueue', payload, this.onUpdateQueue(payload)), cancel: (payload: unknown) => this.record('session.cancel', payload, this.onCancel(payload)), diff --git a/packages/client/runtime/src/client/contract/sessions.ts b/packages/client/runtime/src/client/contract/sessions.ts index d26b392072..7c147df80c 100644 --- a/packages/client/runtime/src/client/contract/sessions.ts +++ b/packages/client/runtime/src/client/contract/sessions.ts @@ -29,6 +29,14 @@ export interface ISessions { open(id: SessionId): void /** Clear the current selection into the no-session view state. */ clear(): void + /** + * Fork a session from a completed-turn prefix of the source; on resolution + * the child is in the list store and `open()` can target it. + * @param opts - source session id and the optional event seq anchoring the + * cut (the boundary is the first turn/end at or after it). + * @returns the child session id. + */ + fork(opts: { sessionId: SessionId; atSeq?: number }): Promise /** * Register a per-session standard-props provider (hooks become `use` * selector hooks on the render side; props spread verbatim). diff --git a/packages/client/runtime/src/client/sessions/manager.ts b/packages/client/runtime/src/client/sessions/manager.ts index ff68e21921..f60d7b51e8 100644 --- a/packages/client/runtime/src/client/sessions/manager.ts +++ b/packages/client/runtime/src/client/sessions/manager.ts @@ -289,6 +289,36 @@ export class SessionManager { } } + /** + * Contract session.fork; on success merge the child into summaries + * immediately (same synchronous-addressability guarantee as create). The + * child carries the source's history, so it is never blank; lineage rides + * parentSessionId so the list nests it under its source. + * @param opts - source session and the optional seq anchoring the cut. + * @returns the fork result (the child session id). + */ + async fork( + opts: { sessionId: SessionId; atSeq?: number }, + ): Promise> { + try { + const source = this.summaries.find(s => s.sessionId === opts.sessionId) + const { result } = await this.api.sessions.fork({ + sessionId: opts.sessionId, + ...opts.atSeq === undefined ? {} : { atSeq: opts.atSeq }, + }) + if (result.ok) { + this.recordMutation({ kind: 'upsert', summary: { + sessionId: result.value.sessionId, updatedAt: Date.now(), running: false, blank: false, + parentSessionId: opts.sessionId, + ...(source?.cwd !== undefined ? { cwd: source.cwd } : {}), + } }) + } + return result + } catch (error) { + return transportError(error) + } + } + /** * Insert-or-enrich a locally synthesized summary: a new id prepends; an * existing entry only gains fields it lacks (the session-added frame and the diff --git a/packages/client/runtime/src/client/sessions/service.ts b/packages/client/runtime/src/client/sessions/service.ts index 71067d6330..b5bf951605 100644 --- a/packages/client/runtime/src/client/sessions/service.ts +++ b/packages/client/runtime/src/client/sessions/service.ts @@ -81,6 +81,22 @@ export class SessionCreateError extends Error { } } +/** Structured session-fork failure. */ +export class SessionForkError extends Error { + override readonly name = 'SessionForkError' + + /** + * @param rpcError - Host business or folded transport error. + * @param sourceSessionId - the session the fork was cut from. + */ + constructor( + readonly rpcError: RpcError, + readonly sourceSessionId: SessionId, + ) { + super(`session fork failed: ${rpcError.code}: ${rpcError.message}`) + } +} + /** Session assembly handle for SessionProvider/inject factories (identity-stable per session). */ export interface SessionBinding { readonly sessionId: SessionId @@ -317,6 +333,22 @@ export class SessionsService implements ISessions { return result.value.sessionId } + /** + * Fork a session from a completed-turn prefix of the source (same + * synchronous-addressability guarantee as {@link SessionsService.create}: + * on resolution the child is in the list store and open() can target it). + * @param opts - source session id and the optional event seq anchoring the + * cut (the boundary is the first turn/end at or after it). + * @returns the child session id. + * @throws {SessionForkError} with the source id. + */ + async fork(opts: { sessionId: SessionId; atSeq?: number }): Promise { + const result = await this.manager.fork(opts) + if (!result.ok) throw new SessionForkError(result.error, opts.sessionId) + this.projectList() + return result.value.sessionId + } + /** * Resolve an Agent-scoped context view (use-and-discard). * @param id - session id (the agent identity — 1:1 same axis). diff --git a/packages/client/runtime/tests/fake-api.ts b/packages/client/runtime/tests/fake-api.ts index eb2a06294e..85dd4c5a55 100644 --- a/packages/client/runtime/tests/fake-api.ts +++ b/packages/client/runtime/tests/fake-api.ts @@ -64,6 +64,7 @@ export class FakeApiClient implements IApiClient { onCreate: (payload: unknown) => Promise> = () => Promise.resolve(ok({ sessionId: 'fk-new' as SessionId })) readonly defaultModel: ModelTarget = { provider: 'deepseek', model: 'deepseek-v4-flash' } onRename: (payload: unknown) => Promise> = () => Promise.resolve(ok({ title: 'fk-renamed', seq: 0 })) + onFork: (payload: unknown) => Promise> = () => Promise.resolve(ok({ sessionId: 'fk-fork' as SessionId })) onHistory: (payload: { sessionId: SessionId; beforeSeq?: number; maxMessages?: number }) => Promise> = () => Promise.resolve(ok({ events: [], hasMore: false })) @@ -118,6 +119,7 @@ export class FakeApiClient implements IApiClient { selectModel: (payload: { provider: string; model: string }) => this.record('session.selectModel', payload, this.onSelectModel(payload)), rename: (payload: unknown) => this.record('session.rename', payload, this.onRename(payload)), + fork: (payload: unknown) => this.record('session.fork', payload, this.onFork(payload)), prompt: (payload: unknown) => this.record('session.prompt', payload, this.onPrompt(payload)), updateQueue: (payload: unknown) => this.record('session.updateQueue', payload, this.onUpdateQueue(payload)), cancel: (payload: unknown) => this.record('session.cancel', payload, this.onCancel(payload)), diff --git a/packages/client/test-runtime/src/sessions.ts b/packages/client/test-runtime/src/sessions.ts index 4fdfb32cc0..f585772b38 100644 --- a/packages/client/test-runtime/src/sessions.ts +++ b/packages/client/test-runtime/src/sessions.ts @@ -169,7 +169,7 @@ export class TestSessions implements ISessions { private readonly channel: SessionProvideChannel /** Calls observed on the service-level face (open/clear), newest last. */ - readonly calls: { method: 'open' | 'clear'; args: unknown[] }[] = [] + readonly calls: { method: 'open' | 'clear' | 'fork'; args: unknown[] }[] = [] /** * @param stabilize - the owning runtime's act wrapper. @@ -392,6 +392,17 @@ export class TestSessions implements ISessions { this.list.update((draft) => { draft.current = undefined }) } + /** + * Recorded fork stub: no child materializes (benches asserting the full + * fork flow drive the production service; this face only proves the call). + * @param opts - source session id and optional cut anchor. + * @returns the source id (no child record is created). + */ + fork(opts: { sessionId: SessionId; atSeq?: number }): Promise { + this.calls.push({ method: 'fork', args: [opts] }) + return Promise.resolve(opts.sessionId) + } + /** * The session face of a fixture (typed view for assertions; fixture * behavior methods are grafted onto it). diff --git a/packages/client/ui-conversation/src/client/apply.ts b/packages/client/ui-conversation/src/client/apply.ts index c6b597ae79..ca0159ce3d 100644 --- a/packages/client/ui-conversation/src/client/apply.ts +++ b/packages/client/ui-conversation/src/client/apply.ts @@ -262,6 +262,13 @@ export function apply(ctx: Context): void { }) }, loadOlder: () => { void scoped.loadOlder() }, + forkAt: (seq) => { + sessions.fork({ sessionId, atSeq: seq }) + .then((childId) => { sessions.open(childId) }) + .catch(() => { + // Fork failure keeps the source view untouched (composer-stop posture). + }) + }, } }, }, ChatView) diff --git a/packages/client/ui-conversation/src/client/chat/ChatView.tsx b/packages/client/ui-conversation/src/client/chat/ChatView.tsx index b9e1e3351f..68b9b71cb8 100644 --- a/packages/client/ui-conversation/src/client/chat/ChatView.tsx +++ b/packages/client/ui-conversation/src/client/chat/ChatView.tsx @@ -230,7 +230,7 @@ function StreamingTail({ useSession, onGrow }: { * The chat view slot entry: pure component over the composed props (tool rows * render through the declared keyed hole's renderSlot share). */ -export function ChatView({ useSession, useSessions, useStore, renderSlot, sessionId, openFile, loadOlder }: ChatViewSlotProps) { +export function ChatView({ useSession, useSessions, useStore, renderSlot, sessionId, openFile, loadOlder, forkAt }: ChatViewSlotProps) { const nodes = useSession(s => s.nodes) // Workspace root off the session list row: path summaries display relative to it. const cwd = useSessions(s => s.byId[sessionId]?.cwd) @@ -385,7 +385,7 @@ export function ChatView({ useSession, useSessions, useStore, renderSlot, sessio } /* v8 ignore next -- tool-result never reaches here: deriveChatFlow folds them into groups. */ if (node.kind === 'tool-result') return null - return + return } return ( diff --git a/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx b/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx index fc76cfb753..124371f2da 100644 --- a/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx +++ b/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx @@ -1,5 +1,6 @@ -// Shared IconActions chrome for user and assistant messages: copy / branch -// live (branch still a stub), date-aware clock, optional edit stub. +// Shared IconActions chrome for user and assistant messages: copy live, +// branch wired through onBranch (stub without it), date-aware clock, +// optional edit stub. import { useCallback } from 'react' import { @@ -18,17 +19,19 @@ export interface MessageIconActionsProps { clock: 'start' | 'end' /** When true, append the stub edit control (user bubble). */ edit?: boolean | undefined + /** Fork the session at this message; absent leaves the branch control a stub. */ + onBranch?: (() => void) | undefined /** Parent layout class composed onto the actions row. */ className?: string | undefined } /** * Copy / branch (/ clock) IconActions row shared by user and assistant chrome. - * @param props - Copy text, event time, clock side, optional edit, className. + * @param props - Copy text, event time, clock side, optional edit, branch callback, className. * @returns The actions row element. */ export function MessageIconActions({ - text, time, clock, edit, className, + text, time, clock, edit, onBranch, className, }: MessageIconActionsProps) { const day = useCalendarDay() const onCopy = useCallback(() => { @@ -48,7 +51,7 @@ export function MessageIconActions({ - diff --git a/packages/client/ui-conversation/src/client/chat/MessageItem.tsx b/packages/client/ui-conversation/src/client/chat/MessageItem.tsx index aa56d35270..2eb8e313ae 100644 --- a/packages/client/ui-conversation/src/client/chat/MessageItem.tsx +++ b/packages/client/ui-conversation/src/client/chat/MessageItem.tsx @@ -16,6 +16,8 @@ import css from './MessageItem.module.css' export interface MessageItemProps { node: UserMessageNode | SteeringMessageNode | ContextMessageNode | UnknownSurfaceNode + /** Fork the session through the turn containing this message (user-bubble branch action). */ + onFork?: (seq: number) => void } function contentText(content: readonly unknown[]): { text: string; rest: unknown[] } { @@ -61,7 +63,7 @@ function projectUserText(text: string): ReactNode { return <>{parts} } -export const MessageItem = memo(function MessageItem({ node }: MessageItemProps) { +export const MessageItem = memo(function MessageItem({ node, onFork }: MessageItemProps) { switch (node.kind) { case 'user': { const { text, rest } = contentText(node.content) @@ -76,6 +78,7 @@ export const MessageItem = memo(function MessageItem({ node }: MessageItemProps) time={node.time} clock="start" edit + onBranch={onFork === undefined ? undefined : () => { onFork(node.seq) }} className={css.actions} /> diff --git a/packages/client/ui-conversation/src/client/contract/slots.ts b/packages/client/ui-conversation/src/client/contract/slots.ts index 1684e616b2..dca8cbc567 100644 --- a/packages/client/ui-conversation/src/client/contract/slots.ts +++ b/packages/client/ui-conversation/src/client/contract/slots.ts @@ -419,6 +419,8 @@ export interface ChatViewInjected { */ openFile: (path: string) => void loadOlder: () => void + /** Fork the session through the turn containing the message at `seq`, then open the child. */ + forkAt: (seq: number) => void } /** Full chat-view component props: runtime share & the declared toolview/commandview holes' render share & store share & injected share. */ diff --git a/packages/client/ui-conversation/tests/chat-view.spec.tsx b/packages/client/ui-conversation/tests/chat-view.spec.tsx index c0cb4dcb78..960f954d61 100644 --- a/packages/client/ui-conversation/tests/chat-view.spec.tsx +++ b/packages/client/ui-conversation/tests/chat-view.spec.tsx @@ -94,6 +94,7 @@ function makeHarness(init?: Partial) { const openDetails = vi.fn<(t: SelectionTarget) => void>() const openFile = vi.fn<(path: string) => void>() const loadOlder = vi.fn() + const forkAt = vi.fn() // Selection rides the REAL chat store (same construction path as // production; the view reads it through the PropsStore useStore share). // renderSlot stub renders the render-site fallback (an empty keyed ledger: @@ -120,9 +121,10 @@ function makeHarness(init?: Partial) { openDetails, openFile, loadOlder, + forkAt, } const setSelection = (next: SelectionTarget | null): void => { chat.actions.select(next) } - return { set, ChatView, props, openDetails, openFile, loadOlder, setSelection } + return { set, ChatView, props, openDetails, openFile, loadOlder, forkAt, setSelection } } describe('chat-flow derivation', () => { diff --git a/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx b/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx index a1fa0683ac..035bfe06a7 100644 --- a/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx +++ b/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx @@ -83,7 +83,7 @@ interface DragState { type SessionTreeProps = Pick< WorkspaceBrowserProps, - 'useSessions' | 'startSession' | 'open' | 'insertSessionBefore' + 'useSessions' | 'startSession' | 'open' | 'forkSession' | 'insertSessionBefore' > & { workspaces: readonly WorkspaceView[] /** Live search filter owned by the browser root (the query outlives the tree). */ @@ -98,7 +98,7 @@ type SessionTreeProps = Pick< /** The scrolling session tree; unmounting at collapse settle drops the sessions subscription and expansion state. */ function SessionTree({ - useSessions, startSession, open, workspaces, query, + useSessions, startSession, open, forkSession, workspaces, query, onRenameRequest, onDeleteRequest, onSessionRename, insertSessionBefore, }: SessionTreeProps) { const list = useSessions(s => s) @@ -115,6 +115,24 @@ function SessionTree({ if (current === undefined || currentGroup === undefined) return setExpandedProjects(l => (l.includes(currentGroup) ? l : [...l, currentGroup])) }, [current, currentGroup]) + // The selected session must be visible: unfold its ancestor chain (fork + // lands the child under a possibly folded parent row). + const currentAncestors = useMemo(() => { + const chain: string[] = [] + let cursor = current === undefined ? undefined : list.byId[current]?.parentId + while (cursor !== undefined && !chain.includes(cursor)) { + chain.push(cursor) + cursor = list.byId[cursor]?.parentId + } + return chain + }, [current, list]) + useEffect(() => { + if (currentAncestors.length === 0) return + setExpandedSessions((l) => { + const missing = currentAncestors.filter(id => !l.includes(id)) + return missing.length === 0 ? l : [...l, ...missing] + }) + }, [currentAncestors]) const groups = useMemo( () => deriveGroups(list, workspaces, { expandedProjects, expandedSessions, query }), [list, workspaces, expandedProjects, expandedSessions, query], @@ -195,6 +213,7 @@ function SessionTree({ now={now} onOpen={open} onRename={onSessionRename} + onFork={forkSession} onToggle={(id) => { setExpandedSessions(l => toggled(l, id)) }} drag={dragProps} /> @@ -209,7 +228,7 @@ function SessionTree({ } /** The flat "In one list" body: every session a top-level row, newest-first. */ -function FlatList({ useSessions, open, onSessionRename, query }: Pick) { +function FlatList({ useSessions, open, forkSession, onSessionRename, query }: Pick) { const list = useSessions(s => s) const rows = useMemo(() => deriveFlat(list, { query }), [list, query]) const now = Date.now() @@ -228,6 +247,7 @@ function FlatList({ useSessions, open, onSessionRename, query }: Pick {}} flat @@ -254,6 +274,7 @@ export function WorkspaceBrowser({ startSession, open, renameSession, + forkSession, renameWorkspace, deleteWorkspace, insertSessionBefore, @@ -460,13 +481,14 @@ export function WorkspaceBrowser({ {/* Always-mounted seat keeps the region's flex slot while the list itself is wide-only. */} -
- {wide && (groupBy === 'flat' - ? +
+ {wide && (groupBy === 'flat' + ? : ( void /** Rename a Session (explicit user title; resolves on host acceptance). */ renameSession: (sessionId: SessionId, title: string) => Promise + /** Fork a Session at its last completed turn and open the child. */ + forkSession: (sessionId: SessionId) => void /** Rename a Host Workspace (rejects on name conflict; resolves on durability). */ renameWorkspace: (workspaceId: WorkspaceId, title: string) => Promise /** Delete only a Host Workspace registration; directory and Session logs remain. */ diff --git a/packages/client/ui-workspace/src/client/index.ts b/packages/client/ui-workspace/src/client/index.ts index c1f5e61ba4..f7ced8016a 100644 --- a/packages/client/ui-workspace/src/client/index.ts +++ b/packages/client/ui-workspace/src/client/index.ts @@ -59,6 +59,13 @@ export function apply(ctx: ClientContext): void { const result = await session.rename(title) if (!result.ok) throw new Error(result.error.message) }, + forkSession: (sessionId) => { + ctx.sessions.fork({ sessionId }) + .then((childId) => { ctx.sessions.open(childId) }) + .catch(() => { + // Fork failure keeps the list untouched (composer-stop posture). + }) + }, renameWorkspace: async (workspaceId, title) => { await ctx.workspaces.rename(workspaceId, title) }, deleteWorkspace: async (workspaceId) => { await ctx.workspaces.delete(workspaceId) }, insertSessionBefore: async (workspaceId, sessionId, beforeSessionId) => { diff --git a/packages/client/ui-workspace/src/client/rows/Rows.tsx b/packages/client/ui-workspace/src/client/rows/Rows.tsx index a507ac2991..c4b9752690 100644 --- a/packages/client/ui-workspace/src/client/rows/Rows.tsx +++ b/packages/client/ui-workspace/src/client/rows/Rows.tsx @@ -2,8 +2,8 @@ * Workspace browser tree row components (figma Cell set 14:3080): pure presentational — * all data and callbacks arrive via props. Hover swaps (folder->chevron, * time->ellipsis, action buttons) are CSS-only. Row ... menus are visual-only - * except workspace Rename/Delete and session Rename; the session and workspace - * hover cards are suppressed while a menu is open. + * except workspace Rename/Delete and session Rename/Fork; the session and + * workspace hover cards are suppressed while a menu is open. */ import { useState } from 'react' import clsx from 'clsx' @@ -184,7 +184,7 @@ function rowHalf(e: { clientY: number; currentTarget: HTMLElement }): 'before' | return e.clientY < rect.top + rect.height / 2 ? 'before' : 'after' } -export function SessionNodeItem({ node, depth, currentId, now, onOpen, onRename, onToggle, drag, flat = false }: { +export function SessionNodeItem({ node, depth, currentId, now, onOpen, onRename, onFork, onToggle, drag, flat = false }: { node: SessionNode depth: number currentId: string | undefined @@ -192,6 +192,8 @@ export function SessionNodeItem({ node, depth, currentId, now, onOpen, onRename, onOpen: (id: SessionNode['id']) => void /** Open the browser-owned session rename dialog (row menu action). */ onRename: (id: SessionNode['id'], currentTitle: string) => void + /** Fork a session at its last completed turn (row menu action). */ + onFork: (id: SessionNode['id']) => void onToggle: (id: SessionNode['id']) => void /** Present only on draggable rows (workspace-group roots outside search). */ drag?: RowDragProps | undefined @@ -259,9 +261,10 @@ export function SessionNodeItem({ node, depth, currentId, now, onOpen, onRename, open={menuOpen} onClose={() => { setMenuOpen(false) }} items={SESSION_MENU_ITEMS} - onSelect={(id) => { - setMenuOpen(false) - if (id === 'rename') onRename(node.id, row.title) // fork/delete stay visual-only. + onSelect={(id) => { + setMenuOpen(false) + if (id === 'rename') onRename(node.id, row.title) + if (id === 'fork') onFork(node.id) // delete stays visual-only. }} portal closeOnPointerLeave @@ -295,6 +298,7 @@ export function SessionNodeItem({ node, depth, currentId, now, onOpen, onRename, now={now} onOpen={onOpen} onRename={onRename} + onFork={onFork} onToggle={onToggle} /> ))} diff --git a/packages/client/ui-workspace/tests/rows.spec.tsx b/packages/client/ui-workspace/tests/rows.spec.tsx index c4b440578a..dc8e9379dc 100644 --- a/packages/client/ui-workspace/tests/rows.spec.tsx +++ b/packages/client/ui-workspace/tests/rows.spec.tsx @@ -67,9 +67,9 @@ describe('workspace browser rows', () => { } const onOpen = vi.fn() const onToggle = vi.fn() - const view = render( - , + const view = render( + , ) const parentRow = screen.getByText('Parent').closest('[role="treeitem"]')! @@ -88,9 +88,9 @@ describe('workspace browser rows', () => { view.rerender( , ) expect(screen.getByRole('button', { name: 'Expand' })).toBeTruthy() @@ -162,9 +162,9 @@ describe('workspace browser rows', () => { const node: SessionNode = { id: sid('s1'), title: 'One', children: [], hasChildren: false, expanded: false, running: false, updatedAt: 0, - } - render() + } + render() fireEvent.click(screen.getByRole('button', { name: 'Session actions for One' })) expect(onOpen).not.toHaveBeenCalled() expect(screen.getByRole('menuitem', { name: 'Delete session' }).className).toMatch(/danger/) @@ -189,9 +189,9 @@ describe('workspace browser rows', () => { const node: SessionNode = { id: sid('p'), title: 'Parent', children: [], hasChildren: true, expanded: false, running: false, updatedAt: 0, - } - render() + } + render() expect(screen.queryByRole('button', { name: 'Expand' })).toBeNull() }) @@ -201,9 +201,9 @@ describe('workspace browser rows', () => { const node: SessionNode = { id: sid('s1'), title: 'Hovered', children: [], hasChildren: false, expanded: false, running: true, updatedAt: 0, - } - render() + } + render() const wrapper = screen.getByRole('treeitem').parentElement as HTMLElement fireEvent.pointerEnter(wrapper) act(() => { vi.advanceTimersByTime(500) }) @@ -228,9 +228,9 @@ describe('workspace browser rows', () => { const node: SessionNode = { id: sid('s1'), title: 'Quiet', children: [], hasChildren: false, expanded: false, running: false, updatedAt: 0, - } - render() + } + render() fireEvent.pointerEnter(screen.getByRole('treeitem').parentElement as HTMLElement) act(() => { vi.advanceTimersByTime(500) }) expect(screen.getByText('Idle')).toBeTruthy() @@ -246,9 +246,9 @@ describe('workspace browser rows', () => { expanded: false, running: false, updatedAt: 0, } const inactive = dragProps() - const { rerender } = render( - , + const { rerender } = render( + , ) const row = screen.getByRole('treeitem') stubRect(row) @@ -264,9 +264,9 @@ describe('workspace browser rows', () => { expect(inactive.end).toHaveBeenCalledOnce() const active = dragProps({ active: true, marker: 'before' }) - rerender( - , + rerender( + , ) stubRect(screen.getByRole('treeitem')) // Top half hovers/drops 'before'; bottom half 'after' (row mid = 117). @@ -278,9 +278,9 @@ describe('workspace browser rows', () => { expect(active.drop).toHaveBeenCalledWith('after') const after = dragProps({ active: true, marker: 'after' }) - rerender( - , + rerender( + , ) expect(screen.getByRole('treeitem').className).toMatch(/dropAfter/) }) diff --git a/packages/client/ui-workspace/tests/workspace-browser.spec.tsx b/packages/client/ui-workspace/tests/workspace-browser.spec.tsx index abe896dffe..d0535ecdfa 100644 --- a/packages/client/ui-workspace/tests/workspace-browser.spec.tsx +++ b/packages/client/ui-workspace/tests/workspace-browser.spec.tsx @@ -56,6 +56,7 @@ function mount(overrides: Partial = {}) { startSession: vi.fn(), open: vi.fn(), renameSession: vi.fn(async () => {}), + forkSession: vi.fn(), renameWorkspace: vi.fn(async () => {}), deleteWorkspace: vi.fn(async () => {}), insertSessionBefore: vi.fn(async () => {}), diff --git a/packages/host/apiproxy/src/api-proxy.ts b/packages/host/apiproxy/src/api-proxy.ts index cab5747963..e3c73746a9 100644 --- a/packages/host/apiproxy/src/api-proxy.ts +++ b/packages/host/apiproxy/src/api-proxy.ts @@ -1148,6 +1148,66 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro } }, + async fork(request) { + const { sessionId, atSeq } = request.payload + const found = await agentFor(sessionId) + if ('error' in found) return err(request, found.error) + const source = found.agent.session + const events = source.events + // Boundary: the first turn/end at or after atSeq (fork includes that + // whole turn); an overshooting atSeq or an omitted one falls back to + // the last completed turn. + const boundary = (atSeq === undefined ? undefined : events.find(e => e.type === 'turn/end' && e.seq >= atSeq)) + ?? events.findLast(e => e.type === 'turn/end') + if (boundary === undefined) { + return err(request, { + code: 'fork-unavailable', + message: `session "${sessionId}" has no completed turn to fork from`, + details: { sessionId }, + }) + } + // Extend the cut through trailing out-of-band appends (session/title, + // injections) up to the next turn/start: they are standalone events, so + // the seed stays balanced, and the child inherits a title generated + // right after the boundary turn. + let cut = boundary.seq + 1 + while (cut < events.length && events[cut]?.type !== 'turn/start') cut++ + const childId = `session-${randomUUID()}` as SessionId + try { + await ctx.agents.create({ + sessionId: childId, + seed: events.slice(0, cut), + meta: { + ...source.header.cwd === undefined ? {} : { cwd: source.header.cwd }, + parentSession: source.id, + seedLength: cut, + }, + agentOptions, + }) + } catch (error: unknown) { + return err(request, { + code: 'internal', + message: `failed to fork session "${sessionId}": ${String(error)}`, + details: {}, + }) + } + // Keep the child in the source's Workspace so the list nests it under + // its parent; the child is already published if the attach fails. + const workspace = ctx.workspace.list().find(w => w.sessionIds.includes(source.id)) + if (workspace !== undefined) { + try { + await workspace.attachSession(childId) + } catch (error: unknown) { + return err(request, { + code: 'workspace-attach-failed', + message: `session "${childId}" was forked but could not attach to workspace "${workspace.id}": ${String(error)}`, + details: { sessionId: childId, workspaceId: workspace.id }, + }) + } + } + return ok(request, { sessionId: childId }) + }, + async prompt(request) { const { sessionId, mode, content } = request.payload const found = await agentFor(sessionId) diff --git a/packages/host/apiproxy/src/api/rpc-map.ts b/packages/host/apiproxy/src/api/rpc-map.ts index bc197be3c5..54c68e9c1c 100644 --- a/packages/host/apiproxy/src/api/rpc-map.ts +++ b/packages/host/apiproxy/src/api/rpc-map.ts @@ -24,6 +24,7 @@ export interface RpcMethodMap { 'session.models': SessionsApi['models'] 'session.selectModel': SessionsApi['selectModel'] 'session.rename': SessionsApi['rename'] + 'session.fork': SessionsApi['fork'] 'session.prompt': SessionsApi['prompt'] 'session.updateQueue': SessionsApi['updateQueue'] 'session.cancel': SessionsApi['cancel'] diff --git a/packages/host/apiproxy/src/api/rpc.schema.ts b/packages/host/apiproxy/src/api/rpc.schema.ts index cbd793ebd0..95701f6deb 100644 --- a/packages/host/apiproxy/src/api/rpc.schema.ts +++ b/packages/host/apiproxy/src/api/rpc.schema.ts @@ -51,6 +51,7 @@ export const rpcErrorSchema: z.ZodType = z.discriminatedUnion('code', z.object({ code: z.literal('command-error'), message: z.string(), details: z.object({}) }), z.object({ code: z.literal('unknown-command'), message: z.string(), details: z.object({}) }), z.object({ code: z.literal('title-invalid'), message: z.string(), details: z.object({ sessionId: z.string() }) }), + z.object({ code: z.literal('fork-unavailable'), message: z.string(), details: z.object({ sessionId: z.string() }) }), z.object({ code: z.literal('internal'), message: z.string(), details: z.object({}) }), ]) as unknown as z.ZodType diff --git a/packages/host/apiproxy/src/api/rpc.ts b/packages/host/apiproxy/src/api/rpc.ts index c1fa4e1611..720db149c1 100644 --- a/packages/host/apiproxy/src/api/rpc.ts +++ b/packages/host/apiproxy/src/api/rpc.ts @@ -51,6 +51,7 @@ export interface RpcErrorDetailsMap { /** A leading-/ prompt named no registered command; the message names the token. */ 'unknown-command': {} 'title-invalid': { sessionId: SessionId } + 'fork-unavailable': { sessionId: SessionId } 'internal': {} } diff --git a/packages/host/apiproxy/src/api/sessions.schema.ts b/packages/host/apiproxy/src/api/sessions.schema.ts index e3744ec37a..12bc273d98 100644 --- a/packages/host/apiproxy/src/api/sessions.schema.ts +++ b/packages/host/apiproxy/src/api/sessions.schema.ts @@ -89,6 +89,17 @@ export const sessionRenameValueSchema = z.object({ seq: z.number().int().nonnegative(), }) satisfies z.ZodType>> +/** session.fork request payload (atSeq anchors the completed-turn cut). */ +export const sessionForkRequestSchema = z.object({ + sessionId: sessionIdSchema, + atSeq: z.number().int().nonnegative().optional(), +}) satisfies z.ZodType>> + +/** session.fork response value (the child session id). */ +export const sessionForkValueSchema = z.object({ + sessionId: sessionIdSchema, +}) satisfies z.ZodType>> + /** session.history request payload (beforeSeq/maxMessages page backwards from the window tail). */ export const sessionHistoryRequestSchema = z.object({ sessionId: sessionIdSchema, diff --git a/packages/host/apiproxy/src/api/sessions.ts b/packages/host/apiproxy/src/api/sessions.ts index 077087a0de..70a4003a1a 100644 --- a/packages/host/apiproxy/src/api/sessions.ts +++ b/packages/host/apiproxy/src/api/sessions.ts @@ -238,6 +238,20 @@ export interface SessionsApi { * one — carried for future rendering; the state change is the feedback). A usage/state error is an * RPC error with code command-error; an unrecognized name is an RPC error with code unknown-command. */ + /** + * Forks a new session from a completed-turn prefix of the source. `atSeq` + * anchors the cut: the boundary is the first `turn/end` at or after it + * (a message's fork button passes the message seq, so the fork includes + * that whole turn); a boundary past the log end, or an omitted `atSeq`, + * falls back to the source's last completed turn. A source with no + * completed turn fails with `fork-unavailable`. The child inherits the + * source cwd (and its workspace attachment) and records + * `parentSessionId` lineage; the seed prefix carries the source title. + */ + fork(request: RpcRequest<{ sessionId: SessionId; atSeq?: number }>): + Promise> + + /** Sends a message. content is core's ContentBlock[] verbatim; mode maps 1:1 — queue→send, steer→steer. */ prompt(request: RpcRequest<{ sessionId: SessionId; mode: 'queue' | 'steer'; content: ContentBlock[] }>): Promise> diff --git a/packages/host/apiproxy/src/fetch/client.ts b/packages/host/apiproxy/src/fetch/client.ts index 38e684fa20..b1dc1e4a1e 100644 --- a/packages/host/apiproxy/src/fetch/client.ts +++ b/packages/host/apiproxy/src/fetch/client.ts @@ -20,6 +20,7 @@ import { import { sessionCancelValueSchema, sessionCreateValueSchema, + sessionForkValueSchema, sessionHistoryValueSchema, sessionListValueSchema, sessionModelsValueSchema, @@ -69,6 +70,7 @@ export interface IApiClient { models(payload: RequestPayload<'session.models'>, signal?: AbortSignal): Promise>> selectModel(payload: RequestPayload<'session.selectModel'>, signal?: AbortSignal): Promise>> rename(payload: RequestPayload<'session.rename'>, signal?: AbortSignal): Promise>> + fork(payload: RequestPayload<'session.fork'>, signal?: AbortSignal): Promise>> prompt(payload: RequestPayload<'session.prompt'>, signal?: AbortSignal): Promise>> updateQueue(payload: RequestPayload<'session.updateQueue'>, signal?: AbortSignal): Promise>> cancel(payload: RequestPayload<'session.cancel'>, signal?: AbortSignal): Promise>> @@ -121,6 +123,7 @@ const UNARY_VALUE_SCHEMAS: { [K in keyof RpcMethodMap]: z.ZodType this.callUnary('session.models', payload, signal), selectModel: (payload, signal) => this.callUnary('session.selectModel', payload, signal), rename: (payload, signal) => this.callUnary('session.rename', payload, signal), + fork: (payload, signal) => this.callUnary('session.fork', payload, signal), prompt: (payload, signal) => this.callUnary('session.prompt', payload, signal), updateQueue: (payload, signal) => this.callUnary('session.updateQueue', payload, signal), cancel: (payload, signal) => this.callUnary('session.cancel', payload, signal), diff --git a/packages/host/apiproxy/src/fetch/handler.ts b/packages/host/apiproxy/src/fetch/handler.ts index 98dac06b9f..785ce7431b 100644 --- a/packages/host/apiproxy/src/fetch/handler.ts +++ b/packages/host/apiproxy/src/fetch/handler.ts @@ -17,6 +17,7 @@ import { clientRequestSchema, clientResponseSchema } from '../api/rpc.schema.ts' import { sessionCancelRequestSchema, sessionCreateRequestSchema, + sessionForkRequestSchema, sessionHistoryRequestSchema, sessionListRequestSchema, sessionModelsRequestSchema, @@ -71,6 +72,7 @@ const UNARY_ROUTES: UnaryRoutes = { 'session.models': { schema: sessionModelsRequestSchema, invoke: (api, r) => api.sessions.models(r) }, 'session.selectModel': { schema: sessionSelectModelRequestSchema, invoke: (api, r) => api.sessions.selectModel(r) }, 'session.rename': { schema: sessionRenameRequestSchema, invoke: (api, r) => api.sessions.rename(r) }, + 'session.fork': { schema: sessionForkRequestSchema, invoke: (api, r) => api.sessions.fork(r) }, 'session.prompt': { schema: sessionPromptRequestSchema, invoke: (api, r) => api.sessions.prompt(r) }, 'session.updateQueue': { schema: sessionUpdateQueueRequestSchema, invoke: (api, r) => api.sessions.updateQueue(r) }, 'session.cancel': { schema: sessionCancelRequestSchema, invoke: (api, r) => api.sessions.cancel(r) }, diff --git a/packages/host/apiproxy/tests/client-handler.spec.ts b/packages/host/apiproxy/tests/client-handler.spec.ts index 4751e3357b..2981c9ddea 100644 --- a/packages/host/apiproxy/tests/client-handler.spec.ts +++ b/packages/host/apiproxy/tests/client-handler.spec.ts @@ -47,6 +47,7 @@ function scriptedApi(overrides: { selected: { provider: r.payload.provider, model: r.payload.model }, }), rename: r => ok(r, { title: 'renamed', seq: 0 }), + fork: r => ok(r, { sessionId: sid('s-fork') }), prompt: r => ok(r, { accepted: true as const }), updateQueue: r => ok(r, { accepted: true as const }), cancel: r => ok(r, { accepted: true as const }), diff --git a/packages/host/apiproxy/tests/fetch-carrier.spec.ts b/packages/host/apiproxy/tests/fetch-carrier.spec.ts index f356beac0d..bc76b7242f 100644 --- a/packages/host/apiproxy/tests/fetch-carrier.spec.ts +++ b/packages/host/apiproxy/tests/fetch-carrier.spec.ts @@ -70,6 +70,9 @@ function fakeApi(overrides: Partial<{ muxFrames: MuxFrame[]; hostFrames: HostFra async rename(request) { return { rpcId: request.rpcId, result: { ok: true, value: { title: request.payload.title, seq: 0 } } } }, + async fork(request) { + return { rpcId: request.rpcId, result: { ok: true, value: { sessionId: 's-fork' as never } } } + }, async prompt(request) { return { rpcId: request.rpcId, result: { ok: true, value: { accepted: true as const } } } }, From 36f148939894b019803f7230066ea951cf7668d9 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Thu, 30 Jul 2026 12:55:10 +0800 Subject: [PATCH 15/24] fix(web): address session fork review findings --- ...026-06-30-session-store-fork-api.i18n.yaml | 4 +- .../2026-06-30-session-store-fork-api.md | 8 +- .../2026-06-30-session-store-fork-api.zh.md | 8 +- apps/web/tests/message-actions.e2e.ts | 23 ++- .../message-actions/fork.expected.md | 9 ++ .../snapshots/message-actions/ui.expected.md | 3 +- .../client/connection/src/client/fixture.ts | 16 +- packages/client/runtime/README.i18n.yaml | 4 +- packages/client/runtime/README.md | 4 + packages/client/runtime/README.zh.md | 4 + .../runtime/src/client/contract/sessions.ts | 3 +- .../runtime/src/client/sessions/manager.ts | 10 +- .../runtime/src/client/sessions/service.ts | 3 +- packages/client/runtime/tests/manager.spec.ts | 17 ++ .../test-runtime/tests/runtime.spec.tsx | 4 +- .../client/ui-conversation/README.i18n.yaml | 4 +- packages/client/ui-conversation/README.md | 2 +- packages/client/ui-conversation/README.zh.md | 4 +- packages/client/ui-workspace/README.i18n.yaml | 4 +- packages/client/ui-workspace/README.md | 4 +- packages/client/ui-workspace/README.zh.md | 4 +- .../src/client/WorkspaceBrowser.tsx | 4 +- .../ui-workspace/src/client/rows/Rows.tsx | 8 +- .../client/ui-workspace/tests/rows.spec.tsx | 60 +++---- packages/host/apiproxy/README.i18n.yaml | 4 +- packages/host/apiproxy/README.md | 4 +- packages/host/apiproxy/README.zh.md | 8 +- packages/host/apiproxy/src/api-proxy.ts | 21 ++- packages/host/apiproxy/src/api/sessions.ts | 9 +- .../apiproxy/tests/api-proxy-fork.spec.ts | 151 ++++++++++++++++++ .../apiproxy/tests/client-handler.spec.ts | 15 ++ 31 files changed, 346 insertions(+), 80 deletions(-) create mode 100644 apps/web/tests/snapshots/message-actions/fork.expected.md create mode 100644 packages/host/apiproxy/tests/api-proxy-fork.spec.ts diff --git a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.i18n.yaml b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.i18n.yaml index 437bd200dc..5669911951 100644 --- a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.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/2026-06-30-session-store-fork-api.md -2026-06-30-session-store-fork-api.md: 5342deba8ca879026d32ee1420cb3c0fdf67c500 -2026-06-30-session-store-fork-api.zh.md: 51a3e0ce50aff10a9812c91d24dc6e78a56c43ba +2026-06-30-session-store-fork-api.md: 69ff85e1f137f4f263bf951af0a3f655411c606a +2026-06-30-session-store-fork-api.zh.md: 3304a6f384c9004b3572c95881f832a4aa21b77c diff --git a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md index 5342deba8c..69ff85e1f1 100644 --- a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md +++ b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md @@ -28,6 +28,12 @@ class SessionStore extends Service { An empty prefix is forkable; any non-empty boundary must be a safe existing sequence outside an open turn. Typed errors distinguish missing sources, stale objects, duplicate child ids, invalid boundaries, and prefixes ending during execution. Broader log validation and crash repair remain with their existing owners. +### Host and browser adaptation + +The Host `session.fork` RPC accepts `atSeq` as an anchor within the desired turn rather than as the store's inclusive safe boundary. It selects the first `turn/end` at or after that anchor; an omitted or past-end anchor selects the last completed turn. An anchor already in the log but not followed by a matching `turn/end` returns `fork-unavailable` and never falls back to an earlier turn, so a message action cannot silently omit the clicked message. + +The Host creates the child through the agent registry with the selected seed and lineage, and pre-publication setup installs the latest logged provider, model, and reasoning target before the child can run. It then attaches the child to the source Workspace. An attachment failure returns `workspace-attach-failed` with the already-published child id; the client reconciles that child into its summary list before surfacing the error. The Session-row action uses the last completed turn, while a message action supplies its event seq; both open the child after success, and lineage expansion makes it visible beneath the source. + ## Alternatives considered **Separate `ctx.sessionFork` service.** This was the first implementation, but review showed it overfit the capability-seam pattern. The code had no swappable backend, no extra event surface, no independent ownership lifecycle, and no durable behavior beyond `ctx.sessions.create({ seed, meta })`. Keeping a separate package would make callers discover and install a second service just to perform policy around a session-store primitive. @@ -40,4 +46,4 @@ An empty prefix is forkable; any non-empty boundary must be a safe existing sequ The public surface stays small and discoverable: live session branching is part of `ctx.sessions`, next to `create({ seed })`, rather than a standalone service or a two-step helper pair. Persistence continues to work through existing `session/created` and `session/flush` behavior: a forked child starts life with seeded events, so existing backends persist that seed once and preserve `parentSession` / `seedLength` in the header. -The v1 scope still excludes ACP `session/fork`, unloaded persisted-session forking, model-facing tools, and subagent refactors. If a future ACP method is added, it should advertise the capability only after it has protocol and snapshot coverage; this Agent Note adds no ACP wire behavior, so no ACP snapshot is required. Fork-child replay remains covered by the existing [seed-boundary testing Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md), while this API gets focused `dsh-session` unit tests plus JSONL persistence coverage. +The v1 scope still excludes ACP `session/fork`, unloaded persisted-session forking, model-facing tools, and subagent refactors. If a future ACP method is added, it should advertise the capability only after it has protocol and snapshot coverage; this Agent Note adds no ACP wire behavior, so no ACP snapshot is required. Fork-child replay remains covered by the existing [seed-boundary testing Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md); focused store, Host, carrier, and client tests pin the boundary and reconciliation contracts, while the real Chromium scenario pins the assembled message action and lineage tree. diff --git a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.zh.md b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.zh.md index 51a3e0ce50..3304a6f384 100644 --- a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.zh.md +++ b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.zh.md @@ -28,6 +28,12 @@ class SessionStore extends Service { 空前缀可以被 fork；任何非空边界都必须是位于开放轮次之外且安全、已存在的序号。类型化的错误区分源缺失、对象陈旧、子 id 重复、边界无效和前缀结束于执行过程中等情况。更广泛的日志校验与崩溃恢复仍由其现有的负责方处理。 +### Host 与浏览器适配 + +Host 的 `session.fork` RPC 接受 `atSeq`，并将其视为所需轮次内的锚点，而非 store 中包含该序号的安全边界。它选择该锚点处或其后的首个 `turn/end`；锚点省略或超过末尾时，选择最后一个已完成轮次。若锚点已在日志中，但从该锚点起找不到匹配的 `turn/end`，则返回 `fork-unavailable`，绝不回退到更早的轮次，因此消息操作不会静默遗漏所点击的消息。 + +Host 通过 agent（智能体）注册表，以选定的种子和谱系创建子会话；发布前 setup 会先安装日志中最新的提供方、模型和推理（reasoning）目标，子会话才能运行。随后，Host 将子会话附加到源 Workspace。若附加失败，则返回 `workspace-attach-failed` 及已发布的子会话 id；客户端先将该子会话对账到摘要列表，再向调用方报告错误。Session 行操作使用最后一个已完成轮次，消息操作则提供其事件 seq；两者都会在成功后打开子会话，展开谱系后可在源会话下看到它。 + ## 曾考虑的替代方案 **独立的 `ctx.sessionFork` 服务。** 这是最初的实现，但评审表明它过度套用了 capability-seam 模式。代码没有可替换的后端、没有额外的事件面、没有独立的所有权生命周期，也没有超出 `ctx.sessions.create({ seed, meta })` 的持久化行为。保留独立包会迫使调用方为了在会话存储原语之上执行一层策略而去发现并安装第二个服务。 @@ -40,4 +46,4 @@ class SessionStore extends Service { 公开接口保持精简且易于发现：活跃会话分支是 `ctx.sessions` 的一部分，紧邻 `create({ seed })`，而非一个独立服务或一对两步辅助函数。持久化继续通过现有的 `session/created` 和 `session/flush` 行为运作：fork 出的子会话以种子事件开始生命，因此现有后端只需持久化该种子一次，并在 header 中保存 `parentSession`／`seedLength`。 -v1 范围仍然排除 ACP（Agent Client Protocol） `session/fork`、对未加载的已持久化会话的 fork、面向模型的工具，以及 subagent 重构。如果未来添加 ACP 方法，应在具备协议与快照覆盖后才广播该能力；本 Agent Note 不添加任何 ACP 协议行为，因此不需要 ACP 快照。fork 子会话的回放仍由现有的[种子边界测试 Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md) 覆盖，而本 API 则获得专门的 `dsh-session` 单元测试加 JSONL 持久化覆盖。 +v1 范围仍然排除 ACP（Agent Client Protocol） `session/fork`、对未加载的已持久化会话的 fork、面向模型的工具，以及 subagent 重构。如果未来添加 ACP 方法，应在具备协议与快照覆盖后才广播该能力；本 Agent Note 不添加任何 ACP 协议行为，因此不需要 ACP 快照。fork 子会话的回放仍由现有的[种子边界测试 Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md) 覆盖；store、Host、载体与客户端的专项测试固定边界和对账契约，真实 Chromium 场景则固定组装后的消息操作与谱系树。 diff --git a/apps/web/tests/message-actions.e2e.ts b/apps/web/tests/message-actions.e2e.ts index aa14308d43..d3c4f45fd7 100644 --- a/apps/web/tests/message-actions.e2e.ts +++ b/apps/web/tests/message-actions.e2e.ts @@ -8,6 +8,7 @@ import { fileURLToPath } from 'node:url' import type { Browser, Page } from 'playwright' import { chromium } from 'playwright' import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest' +import { SessionId } from '@deepseek-ai/dsh-session' import { assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts, launchWebScaffold, seedSession, watchConsole, webSnapshotMode, type WebScaffold, @@ -19,6 +20,7 @@ const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/message-actions', import // a new recording (workspace-management / sidebar-scrollbar pattern). const SEED = fileURLToPath(new URL('./snapshots/seeded-history/seed.jsonl', import.meta.url)) const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md') +const FORK_EXPECTED = join(SNAPSHOT_DIR, 'fork.expected.md') const MODE = webSnapshotMode() const SEED_ID = 'message-actions-web-e2e' @@ -85,9 +87,28 @@ describe('web e2e: message IconActions and clocks on settled history', () => { await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE) }) + it.skipIf(MODE === 'record')('forks the session through the settled user-message action', async () => { + onTestFailed(() => saveFailureShot(page, 'web-e2e-message-fork')) + await page.getByRole('button', { name: '在新对话中分支' }).first().click() + await expect.poll( + () => scaffold.ctx.agents.list().find(agent => agent.session.header.parentSession === SessionId(SEED_ID)), + { timeout: 15_000 }, + ).toBeDefined() + await expect.poll( + () => page.locator('[role="treeitem"][aria-selected="true"]').count(), + { timeout: 10_000 }, + ).toBe(1) + const tree = await captureStableAria( + page, + '[role="tree"][aria-label="Sessions"]', + scaffold.workspaceCwd, + ) + await compareOrRefreshGolden(FORK_EXPECTED, tree, MODE) + }) + it.skipIf(MODE === 'record')('issued zero model calls and kept a closed inventory', async () => { expect(tripwire.pageErrors).toEqual([]) expect(tripwire.warnings).toEqual([]) - await assertFixtureInventory(SNAPSHOT_DIR, ['ui.expected.md']) + await assertFixtureInventory(SNAPSHOT_DIR, ['fork.expected.md', 'ui.expected.md']) }) }) diff --git a/apps/web/tests/snapshots/message-actions/fork.expected.md b/apps/web/tests/snapshots/message-actions/fork.expected.md new file mode 100644 index 0000000000..2afb7d4d23 --- /dev/null +++ b/apps/web/tests/snapshots/message-actions/fork.expected.md @@ -0,0 +1,9 @@ +- tree "Sessions": + - treeitem "Ungrouped 2 sessions" [expanded]: + - img + - text: Ungrouped 2 sessions + - treeitem "Collapse Use the read tool twice 1min" [expanded]: + - button "Collapse": + - img + - text: Use the read tool twice 1min + - treeitem "Use the read tool twice now" [selected] diff --git a/apps/web/tests/snapshots/message-actions/ui.expected.md b/apps/web/tests/snapshots/message-actions/ui.expected.md index 19ba02d99d..e21b3782a8 100644 --- a/apps/web/tests/snapshots/message-actions/ui.expected.md +++ b/apps/web/tests/snapshots/message-actions/ui.expected.md @@ -31,7 +31,7 @@ - img - button "在新对话中分支": - img -- text: {{clock}} +- text: {{clock}} cache hit 98% · 15,962 tokens · 1 turns · 2 steps - textbox "Message the agent" - button "Add attachment": - img @@ -41,4 +41,3 @@ - text: deepseek-v4-flash - img - button "Send message" [disabled] -- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index 282dfbee56..916125ff6f 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -1053,14 +1053,20 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy { }) } const log = logs.get(sessionId) ?? [] - // Host-parallel boundary: first turn/end at or after atSeq, falling - // back to the last completed turn; no completed turn = fork-unavailable. - const boundary = (atSeq === undefined ? undefined : log.find(e => e.type === 'turn/end' && e.seq >= atSeq)) - ?? log.findLast(e => e.type === 'turn/end') + const lastSeq = log.at(-1)?.seq ?? -1 + const anchoredBoundary = atSeq === undefined + ? undefined + : log.find(e => e.type === 'turn/end' && e.seq >= atSeq) + const boundary = anchoredBoundary + ?? (atSeq === undefined || atSeq > lastSeq + ? log.findLast(e => e.type === 'turn/end') + : undefined) if (boundary === undefined) { return err(request, { code: 'fork-unavailable', - message: `session ${sessionId} has no completed turn`, + message: atSeq !== undefined && atSeq <= lastSeq + ? `session ${sessionId} has not completed the turn containing event ${String(atSeq)}` + : `session ${sessionId} has no completed turn`, details: { sessionId }, }) } diff --git a/packages/client/runtime/README.i18n.yaml b/packages/client/runtime/README.i18n.yaml index fa4c87adb2..4ef6fd488c 100644 --- a/packages/client/runtime/README.i18n.yaml +++ b/packages/client/runtime/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/runtime/README.md -README.md: 766d8516225cd46cb1a3a80c832d1cf55e816140 -README.zh.md: 9b514afca91f604b3e895187de3b5532bf22a692 +README.md: db6388dccee6e065066cc70e141073d99822ce0f +README.zh.md: e1b6902d0d30972bd613553081e0f0e8d5da2a05 diff --git a/packages/client/runtime/README.md b/packages/client/runtime/README.md index 766d851622..db6388dcce 100644 --- a/packages/client/runtime/README.md +++ b/packages/client/runtime/README.md @@ -28,6 +28,10 @@ SlotsService gives the renderer separate bare observables for `useSessions` and `SessionManager` retains the latest validated `session/title` control snapshot independently of list and session-instance arrival. Newer event seqs replace older snapshots, title timestamps contribute to list recency, and a subscription baseline discards any retained title beyond its `lastSeq` before the optional folded title arrives. Explicit session removal also clears the retained title. The client-facing `SessionSummary.title` is therefore only the actual durable title; `displayTitle` is always present and falls back through the cwd basename and session id. A cold persisted session keeps that fallback until opening or resuming it causes the host to fold and project its log-backed title. `ISession.rename` settles the `title` projection cell directly from the unary response's `{title, seq}` under the same higher-seq-wins rule — the list row and every `useProjection('title')` reader update ahead of the push frame, whose later replay of the same seq is a no-op. +## Session forking + +`ISessions.fork({sessionId, atSeq?})` resolves only after the child summary is locally addressable, carrying source lineage and cwd with `blank: false`; callers choose whether to open it. A `workspace-attach-failed` response still identifies a child already published by the Host, so `SessionManager` reconciles that partial success before `SessionForkError` reaches the caller instead of making a retry create a duplicate child. + ## Session model selection Each resident `Session` owns a `modelSelection` snapshot containing the current provider/model target, provider-grouped directory, provider-local failures, and the `idle`/`loading`/`ready`/`selecting`/`error` state. History establishes or refreshes the current target, opening a selector refreshes the directory, and selection failures preserve the last target and usable groups. Directory and selection operations share a monotonically increasing generation so an older response cannot overwrite a newer selection. A reconnect rebuild restores the target reported by the Host without replacing unchanged selection substructure. diff --git a/packages/client/runtime/README.zh.md b/packages/client/runtime/README.zh.md index 9b514afca9..e1b6902d0d 100644 --- a/packages/client/runtime/README.zh.md +++ b/packages/client/runtime/README.zh.md @@ -28,6 +28,10 @@ SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸 `SessionManager` 独立于列表和 Session 实例到达情况，保留最近一次通过验证的 `session/title` 控制快照。seq 更高的事件会替换旧快照，标题时间戳计入列表新近程度；订阅基线会先丢弃 seq 超过其 `lastSeq` 的任何已保留标题，再接收可选的折叠标题。显式移除 Session 也会清除已保留标题。因此，面向客户端的 `SessionSummary.title` 只包含实际的持久化标题；`displayTitle` 始终存在，并依次回退到 cwd basename 和 Session id。冷态持久化会话会保持该回退值，直到打开或恢复会话，促使主机折叠并投影由日志支撑的标题。`ISession.rename` 用 unary 响应中的 `{title, seq}` 直接结算 `title` 投影格，遵循同一 seq 高者胜规则——列表行和所有 `useProjection('title')` 读者在推送帧到达前即更新；推送帧随后重放同一 seq 时为无操作。 +## 会话 fork + +`ISessions.fork({sessionId, atSeq?})` 只在子会话摘要已能在本地寻址后才完成；该摘要携带源会话的谱系和 cwd，且 `blank: false`，由调用方决定是否打开。即使响应为 `workspace-attach-failed`，其中仍会标识 Host 已发布的子会话，因此 `SessionManager` 会先将这一部分成功对账，再让 `SessionForkError` 到达调用方，避免重试创建重复的子会话。 + ## 会话模型选择 每个常驻 `Session` 都拥有一个 `modelSelection` 快照，其中包含当前提供方/模型目标、按提供方分组的目录、逐提供方失败记录，以及 `idle`／`loading`／`ready`／`selecting`／`error` 状态。历史记录会建立或刷新当前目标，打开选择器会刷新目录；选择失败会保留上一个目标和可用分组。目录与选择操作共用单调递增的代次，因此较旧响应无法覆盖较新的选择。重连重建会恢复 Host 报告的目标，同时不替换未变化的选择子结构。 diff --git a/packages/client/runtime/src/client/contract/sessions.ts b/packages/client/runtime/src/client/contract/sessions.ts index 7c147df80c..1b59c3c27c 100644 --- a/packages/client/runtime/src/client/contract/sessions.ts +++ b/packages/client/runtime/src/client/contract/sessions.ts @@ -33,7 +33,8 @@ export interface ISessions { * Fork a session from a completed-turn prefix of the source; on resolution * the child is in the list store and `open()` can target it. * @param opts - source session id and the optional event seq anchoring the - * cut (the boundary is the first turn/end at or after it). + * cut (the boundary is the first turn/end at or after it; an in-log + * anchor in an open turn is unavailable rather than clipped backward). * @returns the child session id. */ fork(opts: { sessionId: SessionId; atSeq?: number }): Promise diff --git a/packages/client/runtime/src/client/sessions/manager.ts b/packages/client/runtime/src/client/sessions/manager.ts index f60d7b51e8..4ba134b321 100644 --- a/packages/client/runtime/src/client/sessions/manager.ts +++ b/packages/client/runtime/src/client/sessions/manager.ts @@ -293,7 +293,8 @@ export class SessionManager { * Contract session.fork; on success merge the child into summaries * immediately (same synchronous-addressability guarantee as create). The * child carries the source's history, so it is never blank; lineage rides - * parentSessionId so the list nests it under its source. + * parentSessionId so the list nests it under its source. A child published + * before Workspace attachment fails is also reconciled into the list. * @param opts - source session and the optional seq anchoring the cut. * @returns the fork result (the child session id). */ @@ -306,9 +307,12 @@ export class SessionManager { sessionId: opts.sessionId, ...opts.atSeq === undefined ? {} : { atSeq: opts.atSeq }, }) - if (result.ok) { + const childId = result.ok + ? result.value.sessionId + : workspaceAttachSessionId(result.error) + if (childId !== undefined) { this.recordMutation({ kind: 'upsert', summary: { - sessionId: result.value.sessionId, updatedAt: Date.now(), running: false, blank: false, + sessionId: childId, updatedAt: Date.now(), running: false, blank: false, parentSessionId: opts.sessionId, ...(source?.cwd !== undefined ? { cwd: source.cwd } : {}), } }) diff --git a/packages/client/runtime/src/client/sessions/service.ts b/packages/client/runtime/src/client/sessions/service.ts index b5bf951605..741aba4c24 100644 --- a/packages/client/runtime/src/client/sessions/service.ts +++ b/packages/client/runtime/src/client/sessions/service.ts @@ -338,7 +338,8 @@ export class SessionsService implements ISessions { * synchronous-addressability guarantee as {@link SessionsService.create}: * on resolution the child is in the list store and open() can target it). * @param opts - source session id and the optional event seq anchoring the - * cut (the boundary is the first turn/end at or after it). + * cut (the boundary is the first turn/end at or after it; an in-log + * anchor in an open turn is unavailable rather than clipped backward). * @returns the child session id. * @throws {SessionForkError} with the source id. */ diff --git a/packages/client/runtime/tests/manager.spec.ts b/packages/client/runtime/tests/manager.spec.ts index 33b46538d9..afe6308249 100644 --- a/packages/client/runtime/tests/manager.spec.ts +++ b/packages/client/runtime/tests/manager.spec.ts @@ -277,6 +277,23 @@ describe('remaining branches', () => { expect(manager.getListSnapshot().items[0]).not.toHaveProperty('cwd') }) + it('reconciles a fork child published before workspace attachment fails', async () => { + const api = new FakeApiClient() + api.onFork = () => Promise.resolve(err({ + code: 'workspace-attach-failed', + message: 'forked but unattached', + details: { sessionId: S2, workspaceId: 'w1' }, + } as never)) + const manager = new SessionManager(api) + const result = await manager.fork({ sessionId: S1 }) + expect(result).toMatchObject({ ok: false, error: { code: 'workspace-attach-failed' } }) + expect(manager.getListSnapshot().items).toEqual([expect.objectContaining({ + sessionId: S2, + parentSessionId: S1, + blank: false, + })]) + }) + it('reconciles a preallocated id after an ordinary transport failure', async () => { const api = new FakeApiClient() api.onCreate = () => Promise.reject(new Error('response lost')) diff --git a/packages/client/test-runtime/tests/runtime.spec.tsx b/packages/client/test-runtime/tests/runtime.spec.tsx index c5084112eb..eddc6efe76 100644 --- a/packages/client/test-runtime/tests/runtime.spec.tsx +++ b/packages/client/test-runtime/tests/runtime.spec.tsx @@ -201,7 +201,7 @@ describe('sessions', () => { await runtime.dispose() }) - it('records service-face calls; open() moves the selection and clear() empties it', async () => { + it('records service-face calls; open() moves selection, clear() empties it, and fork() echoes the source', async () => { const runtime = await runtimeWithFrame() await runtime.sessions.add({ id: 's1' }) await runtime.sessions.add({ id: 's2' }) @@ -211,9 +211,11 @@ describe('sessions', () => { runtime.sessions.clear() await runtime.flush() expect(runtime.sessions.list.getSnapshot().current).toBeUndefined() + await expect(runtime.sessions.fork({ sessionId: 's1' as SessionId, atSeq: 7 })).resolves.toBe('s1') expect(runtime.sessions.calls).toEqual([ { method: 'open', args: ['s1'] }, { method: 'clear', args: [] }, + { method: 'fork', args: [{ sessionId: 's1', atSeq: 7 }] }, ]) await runtime.dispose() }) diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml index 1588367646..d5d1dcfbfb 100644 --- a/packages/client/ui-conversation/README.i18n.yaml +++ b/packages/client/ui-conversation/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-conversation/README.md -README.md: fc466190a744a1c13094ca6ebf62755d5bf49c98 -README.zh.md: f6fbff9c1e5d005b64e928680bbf401d94e4ce79 +README.md: 02834be207e45bb1ff65b75a0c75a884db3be315 +README.zh.md: 84f9d79660207a68305d75ac0e7deaecdedf00d6 diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md index fc466190a7..02834be207 100644 --- a/packages/client/ui-conversation/README.md +++ b/packages/client/ui-conversation/README.md @@ -38,7 +38,7 @@ None; this package neither assembles nor sends a provider request. - **Stats-line durations cover the in-window flow only** — LLM and tool wall times fold the snapshot's assistant `timing` and tool call/result pairs, so nodes outside the loaded event window (older history) are not counted. - **Details panel is the minimal form and currently has no entry point** — selected call args/result raw display; the Input/Output/Metadata switch, Prev/Next stepping, and See-in-trajectory deep link are deferred. Tool rows stopped being details-panel click targets and nothing replaced that gesture, so `ChatViewInjected.openDetails` is implemented but uncalled and the panel (including its terminal card) is unreachable in the assembled application; its rendering stays covered by mounting it with a selection directly. -- **Assistant per-message paging is a reserved slot** — drawn in the design, not implemented. The finalized content IconActions row (copy / branch / clock) ships under text output only; branch remains a chrome stub. +- **Assistant per-message paging is a reserved slot** — drawn in the design, not implemented. The finalized content IconActions row (copy / branch / clock) ships under text output only; branch forks through the turn containing that message and opens the child, while a fork failure leaves the source selected. - **The sparkle icon for the others tool row is a hand-drawn approximation** — the design glyph's vector geometry is not exportable locally; promotion into ui-primitives waits on an exact export. - **The approval panel's "Always allow this type" is deferred** — durable grants need a grant-storage design; only allow-once/reject answer today. - **TodoPanel truncates long item text to one ellipsized line** — the figma strip has no wrap or expand affordance; full text is not readable inline. diff --git a/packages/client/ui-conversation/README.zh.md b/packages/client/ui-conversation/README.zh.md index f6fbff9c1e..84f9d79660 100644 --- a/packages/client/ui-conversation/README.zh.md +++ b/packages/client/ui-conversation/README.zh.md @@ -36,9 +36,9 @@ todo 两个面就是在该形状上的两个注册项，都是普通注册方插 ## 已知限制与暂缓事项 -- **统计行的耗时只覆盖窗口内消息流**：LLM 与工具墙钟时间由快照的 assistant `timing` 与工具 call/result 配对折算，落在已加载事件窗口之外的节点（更早的历史）不计入。 +- **统计行的耗时只覆盖窗口内消息流**：LLM（大语言模型）与工具墙钟时间由快照的 assistant `timing` 与工具 call/result 配对折算，落在已加载事件窗口之外的节点（更早的历史）不计入。 - **详情面板是最小形态，且当前没有入口**：以原始形式显示已选择调用的参数／结果；Input/Output/Metadata 切换、Prev/Next 步进与 See-in-trajectory 深链接暂缓实现。工具行已不再是详情面板的点击目标，且没有任何手势接替它，因此 `ChatViewInjected.openDetails` 虽已实现却无人调用，该面板（含其终端卡片）在组装后的应用中不可达；其渲染仍由直接以选中态挂载它来覆盖。 -- **assistant 逐消息分页是预留 slot**：设计中已有图稿，尚未实现。已定稿的内容 IconActions 行（复制／分支／时钟）只挂在 text 输出下；分支仍是 chrome stub。 +- **assistant 逐消息分页是预留 slot**：设计中已有图稿，尚未实现。已定稿的内容 IconActions 行（复制／分支／时钟）只挂在 text 输出下；分支会 fork 到包含该消息的轮次末尾并打开子会话，而 fork 失败时源会话保持选中。 - **others 工具行的闪光图标是手绘近似版本**：无法在本地导出设计字形的矢量几何；等到存在精确导出后再将其提升到 ui-primitives。 - **审批面板的「始终允许此类」暂缓**：持久授权需要授权存储设计；今天只能回答允许一次／拒绝。 - **TodoPanel 将过长条目截成单行省略号**：figma 条没有换行或展开入口，完整文本无法在行内读完。 diff --git a/packages/client/ui-workspace/README.i18n.yaml b/packages/client/ui-workspace/README.i18n.yaml index 536911a16a..a8f5d98981 100644 --- a/packages/client/ui-workspace/README.i18n.yaml +++ b/packages/client/ui-workspace/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-workspace/README.md -README.md: a1b58f4abe0925be3b426d10344777e46caa9ba0 -README.zh.md: a472507bc45549c8feb55a75d294cbd7b3138cc5 +README.md: f0dbd3de4ac5b7934b4077b2986f5def5be329c8 +README.zh.md: b9f068c6d1709f0a01d22c3fb1cdc391764d666b diff --git a/packages/client/ui-workspace/README.md b/packages/client/ui-workspace/README.md index a1b58f4abe..f0dbd3de4a 100644 --- a/packages/client/ui-workspace/README.md +++ b/packages/client/ui-workspace/README.md @@ -6,6 +6,8 @@ Shared Workspace picker plugin. `WorkspaceBrowser` is registered into the sideba The picker lists real Host Workspace entities through the global `useWorkspaces` hook. Selecting a Workspace invokes the slot owner's `onPick` callback to retarget the frontend Session object. Each registration declares a **directory-flow child hole** (`single` kind: `conversation.hero.workspace.directoryFlow` / `sidebar.workspaces.directoryFlow`) that the composed picker package's client half fills with its picking interaction — the [`-native`](../../host/directory-picker-native/README.md) backend's renderless OS-chooser driver today, an in-app browsing dialog under a `-browse` composition. The flat **Open local folder...** action renders only while the surface's hole is occupied (occupancy read per menu render; an empty hole means the composition has no picking affordance — the seam's documented no-flow default). This package owns the trigger and the adoption: the occupant reports one picked path per open through the hole's owner conversation (`open`/`busy`/`onPicked`/`onCancel`/`onError`), and the owner adopts it through the object layer, selecting the committed Workspace only after its list projection has refreshed; cancellation is silent, and errors land in the retryable folder dialog whose **Choose again** reopens the flow. **Create a new workspace** retains the name dialog and disables names already present in that list, while the Host remains authoritative for concurrent or non-UI callers. The runtime Session and Workspace services own materialization. The Workspace row's Delete action opens a confirmation that states the retention boundary, blocks duplicate submission, and keeps failures open; success removes the group while its Sessions remain under Ungrouped. The Session row's Rename action opens the same browser-owned dialog pattern prefilled with the row's display title: no client-side conflict rule exists (the host normalizes and may reject with `title-invalid`, rendered in the dialog alert), and confirming an unchanged title is deliberately allowed — it pins the current automatic title against regeneration. +The Session row's Fork action forks at the source's last completed turn and opens the child; the lineage-aware tree nests it beneath the source. A failure leaves the current selection unchanged. + Both target slots are declared by other plugins, so `apply` registers through declaration-aware deferral and re-registers after a declaring slot is restored. ## Model Experience @@ -18,5 +20,5 @@ None; this package neither assembles nor sends a provider request. ## Known Limitations and Deferred Work -- **No Session deletion or fork control** — the Session menu's Fork and Delete rows remain visual-only (Rename is wired); Workspace registration deletion does not delete Sessions. +- **No Session deletion control** — the Session menu's Delete row remains visual-only; Workspace registration deletion does not delete Sessions. - **Native folder selection depends on the local Host carrier** — under the `-native` composition, fixture-only or remote browser deployments cannot open a local operating-system dialog; platform failures are shown in a retryable modal. Remote-capable picking is the `-browse` composition's in-app flow. diff --git a/packages/client/ui-workspace/README.zh.md b/packages/client/ui-workspace/README.zh.md index a472507bc4..b9f068c6d1 100644 --- a/packages/client/ui-workspace/README.zh.md +++ b/packages/client/ui-workspace/README.zh.md @@ -6,6 +6,8 @@ 该选择器通过全局 `useWorkspaces` hook 列出真实的 Host Workspace 实体。选择 Workspace 会调用 slot owner 的 `onPick` 回调，重新定位前端 Session 对象。每个注册各自声明一个**目录流子洞**（`single` kind：`conversation.hero.workspace.directoryFlow`／`sidebar.workspaces.directoryFlow`），由组合的选择器包 client half 填入其选取交互——今天是 [`-native`](../../host/directory-picker-native/README.md) 后端的无渲染 OS 选择器驱动，`-browse` 组合下则是应用内浏览对话框。平铺显示的 **打开本地文件夹…** 操作仅在本表层的洞被占用时渲染（每次菜单渲染读取占用状态；洞为空意味着该组合没有选目录能力——seam 文档化的无流程默认行为）。本包持有触发与接纳：占用者经洞的 owner 会话（`open`/`busy`/`onPicked`/`onCancel`/`onError`）每次打开上报一个所选路径，owner 通过对象层接纳它，并等待 Workspace 列表投影刷新后才选中已提交的 Workspace；取消操作不会显示提示，错误落入可重试的文件夹对话框，其 **重新选择** 会重新打开流程。**创建新工作区** 操作保留名称对话框，并禁用列表中已有的名称，而 Host 对并发或非 UI 调用方仍具有最终决定权。运行时 Session 与 Workspace 服务负责物化。Workspace 行内的 Delete 操作会打开确认框，说明保留边界、阻止重复提交，并在失败时保持打开；成功后，该分组会被移除，其 Session 则留在 Ungrouped 下。Session 行内的 Rename 操作打开同款浏览器持有的对话框，并以该行的显示标题预填：客户端不设名称冲突规则（host 负责规范化，可能以 `title-invalid` 拒绝，错误渲染在对话框告警区）；确认未修改的标题是有意允许的——这正是把当前自动标题钉住、不再被重新生成覆盖的手势。 +Session 行内的 Fork 操作在源会话最后一个已完成轮次处 fork 并打开子会话；感知谱系的树会将子会话嵌套在源会话下。失败不会改变当前选中项。 + 两个目标 slot 都由其他插件声明，因此 `apply` 通过声明感知的延迟机制完成注册，并在声明该 slot 的插件恢复后重新注册。 ## 模型体验 @@ -18,5 +20,5 @@ ## 已知限制与暂缓事项 -- **没有 Session 删除与 fork 控件**：Session 菜单的 Fork 与 Delete 行仍仅提供视觉效果（Rename 已接线）；删除 Workspace 注册记录不会删除 Session。 +- **没有 Session 删除控件**：Session 菜单的 Delete 行仍仅提供视觉效果；删除 Workspace 注册记录不会删除 Session。 - **原生文件夹选择依赖本地 Host 载体**：在 `-native` 组合下，仅使用 fixture（测试前置数据）的部署或远程浏览器部署无法打开本地操作系统对话框；模态框会显示平台故障，并允许重试。可远程的选取是 `-browse` 组合的应用内流程。 diff --git a/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx b/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx index 035bfe06a7..933b49bdf0 100644 --- a/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx +++ b/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx @@ -481,8 +481,8 @@ export function WorkspaceBrowser({ {/* Always-mounted seat keeps the region's flex slot while the list itself is wide-only. */} -
- {wide && (groupBy === 'flat' +
+ {wide && (groupBy === 'flat' ? : ( { setMenuOpen(false) }} items={SESSION_MENU_ITEMS} - onSelect={(id) => { - setMenuOpen(false) - if (id === 'rename') onRename(node.id, row.title) - if (id === 'fork') onFork(node.id) // delete stays visual-only. + onSelect={(id) => { + setMenuOpen(false) + if (id === 'rename') onRename(node.id, row.title) + if (id === 'fork') onFork(node.id) // delete stays visual-only. }} portal closeOnPointerLeave diff --git a/packages/client/ui-workspace/tests/rows.spec.tsx b/packages/client/ui-workspace/tests/rows.spec.tsx index dc8e9379dc..44a311d6d3 100644 --- a/packages/client/ui-workspace/tests/rows.spec.tsx +++ b/packages/client/ui-workspace/tests/rows.spec.tsx @@ -67,9 +67,9 @@ describe('workspace browser rows', () => { } const onOpen = vi.fn() const onToggle = vi.fn() - const view = render( - , + const view = render( + , ) const parentRow = screen.getByText('Parent').closest('[role="treeitem"]')! @@ -88,9 +88,9 @@ describe('workspace browser rows', () => { view.rerender( , ) expect(screen.getByRole('button', { name: 'Expand' })).toBeTruthy() @@ -156,15 +156,16 @@ describe('workspace browser rows', () => { expect(screen.queryByRole('button', { name: /Workspace actions/ })).toBeNull() }) - it('session row menu opens without opening the session and dispatches rename', () => { + it('session row menu opens without opening the session and dispatches rename and fork', () => { const onOpen = vi.fn() const onRename = vi.fn() + const onFork = vi.fn() const node: SessionNode = { id: sid('s1'), title: 'One', children: [], hasChildren: false, expanded: false, running: false, updatedAt: 0, - } - render() + } + render() fireEvent.click(screen.getByRole('button', { name: 'Session actions for One' })) expect(onOpen).not.toHaveBeenCalled() expect(screen.getByRole('menuitem', { name: 'Delete session' }).className).toMatch(/danger/) @@ -173,9 +174,10 @@ describe('workspace browser rows', () => { expect(screen.queryByRole('menu')).toBeNull() expect(onRename).toHaveBeenCalledWith(node.id, 'One') expect(onOpen).not.toHaveBeenCalled() - // Fork and Delete stay visual-only. fireEvent.click(screen.getByRole('button', { name: 'Session actions for One' })) fireEvent.click(screen.getByRole('menuitem', { name: 'Fork session' })) + expect(onFork).toHaveBeenCalledWith(node.id) + // Delete stays visual-only. fireEvent.click(screen.getByRole('button', { name: 'Session actions for One' })) fireEvent.click(screen.getByRole('menuitem', { name: 'Delete session' })) expect(onRename).toHaveBeenCalledOnce() @@ -189,9 +191,9 @@ describe('workspace browser rows', () => { const node: SessionNode = { id: sid('p'), title: 'Parent', children: [], hasChildren: true, expanded: false, running: false, updatedAt: 0, - } - render() + } + render() expect(screen.queryByRole('button', { name: 'Expand' })).toBeNull() }) @@ -201,9 +203,9 @@ describe('workspace browser rows', () => { const node: SessionNode = { id: sid('s1'), title: 'Hovered', children: [], hasChildren: false, expanded: false, running: true, updatedAt: 0, - } - render() + } + render() const wrapper = screen.getByRole('treeitem').parentElement as HTMLElement fireEvent.pointerEnter(wrapper) act(() => { vi.advanceTimersByTime(500) }) @@ -228,9 +230,9 @@ describe('workspace browser rows', () => { const node: SessionNode = { id: sid('s1'), title: 'Quiet', children: [], hasChildren: false, expanded: false, running: false, updatedAt: 0, - } - render() + } + render() fireEvent.pointerEnter(screen.getByRole('treeitem').parentElement as HTMLElement) act(() => { vi.advanceTimersByTime(500) }) expect(screen.getByText('Idle')).toBeTruthy() @@ -246,9 +248,9 @@ describe('workspace browser rows', () => { expanded: false, running: false, updatedAt: 0, } const inactive = dragProps() - const { rerender } = render( - , + const { rerender } = render( + , ) const row = screen.getByRole('treeitem') stubRect(row) @@ -264,9 +266,9 @@ describe('workspace browser rows', () => { expect(inactive.end).toHaveBeenCalledOnce() const active = dragProps({ active: true, marker: 'before' }) - rerender( - , + rerender( + , ) stubRect(screen.getByRole('treeitem')) // Top half hovers/drops 'before'; bottom half 'after' (row mid = 117). @@ -278,9 +280,9 @@ describe('workspace browser rows', () => { expect(active.drop).toHaveBeenCalledWith('after') const after = dragProps({ active: true, marker: 'after' }) - rerender( - , + rerender( + , ) expect(screen.getByRole('treeitem').className).toMatch(/dropAfter/) }) diff --git a/packages/host/apiproxy/README.i18n.yaml b/packages/host/apiproxy/README.i18n.yaml index 236cc5968f..95c3643886 100644 --- a/packages/host/apiproxy/README.i18n.yaml +++ b/packages/host/apiproxy/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/host/apiproxy/README.md -README.md: 8f9deb6add7d30bf1609cc7febcb1febafe392c1 -README.zh.md: 399d45208b6d3f4152c27556523b6944432bec66 +README.md: 3ec21f90a495fe42e40c4407e0a81faa34a1e427 +README.zh.md: 5bcd310c23c35b851216176d69b13965dd2e1c3e diff --git a/packages/host/apiproxy/README.md b/packages/host/apiproxy/README.md index 8f9deb6add..3ec21f90a4 100644 --- a/packages/host/apiproxy/README.md +++ b/packages/host/apiproxy/README.md @@ -16,6 +16,8 @@ The layering/protocol decisions are recorded in the [GUI layering and RPC protoc Session titles ride the generic projection pair like every other domain — the history-tail `projections` block plus `session/projection` frames under the `title` key (the bespoke `session/title` frame is retired). Titles do not join `session.list`; cold sessions remain metadata-only there until opening or resuming attaches their logs. `session.rename` accepts an explicit user title (resuming a cold session first), delegating to `ctx.sessionTitle.rename` — the accepted `session/title` event pins the title against automatic regeneration — and returns the normalized title plus its event seq so a client settles its `title` projection cell ahead of the push frame; a title that normalizes to empty returns `title-invalid`. +`session.fork` maps an optional event anchor to the first `turn/end` at or after it, letting a message action include that message's whole turn. An omitted or past-end anchor selects the last completed turn; an in-log anchor whose turn remains open returns `fork-unavailable` rather than clipping backward. The published child inherits the source's seeded history, cwd, latest logged provider/model/reasoning target, and lineage before joining the source Workspace. If Workspace attachment fails, `workspace-attach-failed` carries the already-published child id so clients can reconcile it. The [SessionStore fork decision](../../../.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md) owns the boundary rationale. + Session model routing is a session-domain contract. `session.models` returns the selected provider/model/reasoning target with provider-grouped advisory models, exact-route reasoning metadata, and provider-local lookup failures. `session.selectModel` validates the optional adapter-owned reasoning effort and replaces the complete target selected for the next prompt-assembly boundary. Catalog membership is not validation: an adapter may resolve an unlisted model, while an unavailable route or unsupported effort returns `model-unavailable`. Pending queued input is a live control-plane contract, not session history. The gateway mirrors queued `InboxItem` occurrences from `agent/inbox/*` and broadcasts authoritative `session/queue` snapshots on every queued change and reconnect; pending steering stays outside this Web projection. `session.updateQueue` addresses one `InboxItemId`: edit replaces pending content and remove discards it. A driver claim wins races by retiring the address before admission; a later operation returns `queue-item-not-found`. The operation queries only an attached Agent and never resumes a cold session because process-local inbox identities do not survive restart or disposal. The client never infers retirement from turn or status events. @@ -43,7 +45,7 @@ None; this package neither assembles nor sends a provider request. ## Known Limitations and Deferred Work - **`respond` routing is shipped, but pending-interaction state is host-side work** — the wire shape (POST `/api/respond`, `RpcReceipt`) is final; the pending table that makes late/duplicate answers meaningful lives in `src/api-proxy.ts` and is still minimal (questions only, no approvals). -- **Reserved seams stay out of `RpcMethodMap`** — `session.fork`, `prompt.mode: 'inject'`, `task.list`, `host.listModels`, and a describe `hostInstanceId` are documented reservations; an unknown method fails loud at envelope parse rather than getting a not-implemented code. +- **Reserved seams stay out of `RpcMethodMap`** — `prompt.mode: 'inject'`, `task.list`, `host.listModels`, and a describe `hostInstanceId` are documented reservations; an unknown method fails loud at envelope parse rather than getting a not-implemented code. - **No protocol version field** — client and host ship together; `host.describe` gains a version negotiation field only when an independently released client exists. - **Linux native picker requires desktop tooling** — under the `native` capability, `host.pickDirectory` reports an actionable error when neither Zenity nor KDialog is installed; the browse backend is the composition-level fallback (see the [native backend README](../directory-picker-native/README.md)). - **A cold session's `updatedAt` counts a mere pickup as a write (per-file backends only)** — the attached projection excludes the `session/end-seed` boundary, because picking a session up is not activity, but a cold session's `updatedAt` is its log file's mtime and every durable write refreshes that, the boundary included. `agentFor()` resumes a cold session on first touch, so merely opening one in a client writes it. This applies only where `locate()` resolves a per-session artifact, i.e. JSONL; SQLite returns `undefined`, so its cold sessions fall back to `createdAt` and are skewed the other way — too old rather than too new — independently of this boundary. A session touched without being worked in therefore sorts newer than its last real activity until it attaches. Separating the two needs a log read, which is exactly what the mtime path exists to avoid; a stored last-activity field in the index would fix it at the source, scoped in the [last-activity-index Agent Note](../../../.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.md). diff --git a/packages/host/apiproxy/README.zh.md b/packages/host/apiproxy/README.zh.md index 399d45208b..5bcd310c23 100644 --- a/packages/host/apiproxy/README.zh.md +++ b/packages/host/apiproxy/README.zh.md @@ -16,7 +16,9 @@ 会话标题与其他所有领域一样搭乘这对通用投影机制——历史尾页的 `projections` 块外加 `title` 键下的 `session/projection` 帧（专设的 `session/title` 帧已下线）。标题不会加入 `session.list`；冷会话在其中仍只有元数据，直到打开或恢复操作附加其日志。`session.rename` 接受用户显式标题（冷会话先恢复），委托给 `ctx.sessionTitle.rename`——被接受的 `session/title` 事件将标题钉住、不再被自动生成覆盖——并返回规范化后的标题及其事件 seq，让 client 在推送帧到达前就结算自己的 `title` 投影格；规范化后为空的标题返回 `title-invalid`。 -会话模型路由属于会话领域契约。`session.models` 返回选中的提供方／模型／推理（reasoning）目标，以及按提供方分组的建议性模型、精确路由推理元数据和逐提供方查询失败记录。`session.selectModel` 校验由适配器持有的可选推理强度，并替换将在下一提示词组装边界使用的完整目标。目录成员关系不构成校验：适配器可以解析未列出的模型，而不可用路由或不受支持的推理强度会返回 `model-unavailable`。 +`session.fork` 将可选事件锚点映射到该锚点处或其后的首个 `turn/end`，使消息操作可包含该消息所在的完整轮次。锚点省略或超过末尾时，选择最后一个已完成轮次；若锚点已在日志中，而其所在轮次仍开放，则返回 `fork-unavailable`，不会向较早位置裁剪。发布后的子会话会先继承源会话的种子历史、cwd、日志中最新的提供方／模型／推理（reasoning）目标及谱系，再加入源 Workspace。如果附加到 Workspace 失败，`workspace-attach-failed` 会携带已发布的子会话 id，供客户端对账。[SessionStore fork 决策](../../../.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md)给出边界设计的理由。 + +会话模型路由属于会话领域契约。`session.models` 返回选中的提供方／模型／推理目标，以及按提供方分组的建议性模型、精确路由推理元数据和逐提供方查询失败记录。`session.selectModel` 校验由适配器持有的可选推理强度，并替换将在下一提示词组装边界使用的完整目标。目录成员关系不构成校验：适配器可以解析未列出的模型，而不可用路由或不受支持的推理强度会返回 `model-unavailable`。 待处理的 queued 输入属于实时控制平面契约，而非会话历史。网关镜像来自 `agent/inbox/*` 的 queued `InboxItem` 入队项，并在每次 queued 变更和重连时广播权威的 `session/queue` 快照；待处理 steering（中途引导）不进入此 Web 投影。`session.updateQueue` 通过 `InboxItemId` 寻址单个项：编辑会替换待处理内容，移除会将其丢弃。驱动器在接纳前退役寻址标识，因此认领会赢得竞态；之后的操作返回 `queue-item-not-found`。该操作只查询当前已挂载的 Agent，绝不恢复冷会话，因为进程本地 inbox 标识无法在重启或资源释放后存活。客户端绝不根据轮次或状态事件推断项已退役。 @@ -43,7 +45,7 @@ Workspace 列表与 Session 列表是相互独立的重连基线。`workspace.cr ## 已知限制与延期工作 - **`respond` 路由已经发布，但待处理交互状态仍属宿主侧工作**：协议形状（POST `/api/respond`、`RpcReceipt`）已经定型；使延迟或重复回答具有明确语义的待处理表位于 `src/api-proxy.ts`，目前仍很精简（只支持问题，不支持审批）。 -- **预留 seam 不进入 `RpcMethodMap`**：`session.fork`、`prompt.mode: 'inject'`、`task.list`、`host.listModels` 和描述字段 `hostInstanceId` 都是已记录的预留项；未知方法会在信封解析时直接失败，而不会返回「尚未实现」错误码。 +- **预留 seam 不进入 `RpcMethodMap`**：`prompt.mode: 'inject'`、`task.list`、`host.listModels` 和描述字段 `hostInstanceId` 都是已记录的预留项；未知方法会在信封解析时直接失败，而不会返回「尚未实现」错误码。 - **没有协议版本字段**：客户端与宿主一同发布；只有出现独立发布的客户端后，`host.describe` 才会增加版本协商字段。 - **Linux 原生选择器依赖桌面工具**：在 `native` 能力下，Zenity 和 KDialog 均未安装时，`host.pickDirectory` 会给出包含解决建议的错误提示；组合层面的回退是 browse 后端（见 [native 后端 README](../directory-picker-native/README.md)）。 -- **冷会话的 `updatedAt` 会把一次单纯的拾起算作写入（仅逐文件后端）**：已附加投影排除了 `session/end-seed` 边界，因为接手一个会话不算活动；但冷会话的 `updatedAt` 取自其日志文件的 mtime，而每一次持久写入都会刷新它，包括这条边界。`agentFor()` 会在首次触碰时恢复一个冷会话，因此在客户端里仅仅打开一个会话就会写入它。这只适用于 `locate()` 能解析出逐会话产物的场景，即 JSONL；SQLite 返回 `undefined`，因此它的冷会话回退到 `createdAt`，偏差方向相反——偏旧而不是偏新——且与这条边界无关。于是一个被触碰过却没有在里面工作过的会话，在重新附加之前会排在它最后一次真实活动之后。要把两者区分开需要读取日志，而这恰恰是 mtime 路径存在的目的；在索引中存储一个最后活动字段可以从源头修好它，范围见[最后活动索引 Agent Note](../../../.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.md)。 +- **冷会话的 `updatedAt` 会把一次单纯的拾起算作写入（仅逐文件后端）**：已附加投影排除了 `session/end-seed` 边界，因为接手一个会话不算活动；但冷会话的 `updatedAt` 取自其日志文件的 mtime，而每一次持久写入都会刷新它，包括这条边界。`agentFor()` 会在首次触碰时恢复一个冷会话，因此在客户端里仅仅打开一个会话就会写入它。这只适用于 `locate()` 能解析出逐会话产物的场景，即 JSONL；SQLite 返回 `undefined`，因此它的冷会话回退到 `createdAt`，偏差方向相反——偏旧而不是偏新——且与这条边界无关。于是一个被触碰过却没有在里面工作过的会话，在重新附加之前会按晚于其最后一次真实活动的时间排序。要把两者区分开需要读取日志，而这恰恰是 mtime 路径存在的目的；在索引中存储一个最后活动字段可以从源头修好它，范围见[最后活动索引 Agent Note（agent 决策记录）](../../../.agents/notes/proposed/architecture/2026-07-29-durable-last-activity-index.md)。 diff --git a/packages/host/apiproxy/src/api-proxy.ts b/packages/host/apiproxy/src/api-proxy.ts index e3c73746a9..bcd9873263 100644 --- a/packages/host/apiproxy/src/api-proxy.ts +++ b/packages/host/apiproxy/src/api-proxy.ts @@ -1154,15 +1154,23 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro if ('error' in found) return err(request, found.error) const source = found.agent.session const events = source.events - // Boundary: the first turn/end at or after atSeq (fork includes that - // whole turn); an overshooting atSeq or an omitted one falls back to - // the last completed turn. - const boundary = (atSeq === undefined ? undefined : events.find(e => e.type === 'turn/end' && e.seq >= atSeq)) - ?? events.findLast(e => e.type === 'turn/end') + // An in-log anchor belongs to the turn containing it and must never + // clip backward to an earlier completed turn. Omitted and past-end + // anchors retain the last-completed-turn shortcut. + const lastSeq = events.at(-1)?.seq ?? -1 + const anchoredBoundary = atSeq === undefined + ? undefined + : events.find(e => e.type === 'turn/end' && e.seq >= atSeq) + const boundary = anchoredBoundary + ?? (atSeq === undefined || atSeq > lastSeq + ? events.findLast(e => e.type === 'turn/end') + : undefined) if (boundary === undefined) { return err(request, { code: 'fork-unavailable', - message: `session "${sessionId}" has no completed turn to fork from`, + message: atSeq !== undefined && atSeq <= lastSeq + ? `session "${sessionId}" has not completed the turn containing event ${String(atSeq)}` + : `session "${sessionId}" has no completed turn to fork from`, details: { sessionId }, }) } @@ -1183,6 +1191,7 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro seedLength: cut, }, agentOptions, + setup: installTarget, }) } catch (error: unknown) { return err(request, { diff --git a/packages/host/apiproxy/src/api/sessions.ts b/packages/host/apiproxy/src/api/sessions.ts index 70a4003a1a..d386241bf1 100644 --- a/packages/host/apiproxy/src/api/sessions.ts +++ b/packages/host/apiproxy/src/api/sessions.ts @@ -243,10 +243,11 @@ export interface SessionsApi { * anchors the cut: the boundary is the first `turn/end` at or after it * (a message's fork button passes the message seq, so the fork includes * that whole turn); a boundary past the log end, or an omitted `atSeq`, - * falls back to the source's last completed turn. A source with no - * completed turn fails with `fork-unavailable`. The child inherits the - * source cwd (and its workspace attachment) and records - * `parentSessionId` lineage; the seed prefix carries the source title. + * falls back to the source's last completed turn. An in-log anchor whose + * turn is still open fails with `fork-unavailable` instead of clipping to + * an earlier turn. The child inherits the source cwd, latest logged model + * target, workspace attachment, and `parentSessionId` lineage; the seed + * prefix carries the source title. */ fork(request: RpcRequest<{ sessionId: SessionId; atSeq?: number }>): Promise> diff --git a/packages/host/apiproxy/tests/api-proxy-fork.spec.ts b/packages/host/apiproxy/tests/api-proxy-fork.spec.ts new file mode 100644 index 0000000000..64cb1188f5 --- /dev/null +++ b/packages/host/apiproxy/tests/api-proxy-fork.spec.ts @@ -0,0 +1,151 @@ +/** Session-fork boundaries, lineage, and inherited model routing. */ + +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentHandle, CreateAgentOptions } from '@deepseek-ai/dsh-agent' +import { createUserMessage, ReasoningEffortId } from '@deepseek-ai/dsh-llm' +import type { LlmCallConfig } from '@deepseek-ai/dsh-llm' +import SessionStore from '@deepseek-ai/dsh-session' +import type { Session, SessionId } from '@deepseek-ai/dsh-session' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import UserInteractionService from '@deepseek-ai/dsh-user-interaction' +import type { RpcRequest } from '@deepseek-ai/dsh-host-apiproxy/api/rpc' +import { RpcId } from '@deepseek-ai/dsh-host-apiproxy/api/rpc' +import { createApiProxy } from '@deepseek-ai/dsh-host-apiproxy' + +const sid = (id: string): SessionId => id as SessionId + +let nextRpc = 1 +function request

(payload: P): RpcRequest

{ + return { rpcId: RpcId(`fork-${String(nextRpc++)}`), payload } +} + +async function composed(): Promise { + const ctx = new Context() + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt, { persona: '' }) + await ctx.plugin(AgentRegistry) + await ctx.plugin(UserInteractionService) + ctx.provide('workspace', { list: () => [] } as never) + ctx.agents.setFactory({ + createAgent: async (ownerCtx: Context, options: CreateAgentOptions): Promise => { + const session = ctx.sessions.create(options.sessionId, { + ...options.seed === undefined ? {} : { seed: [...options.seed] }, + ...options.meta === undefined ? {} : { meta: options.meta }, + }) + const agent = {} as Agent + const agentCtx = ownerCtx.extend({ agent }) + Object.assign(agent, { id: session.id, session, status: 'idle', ctx: agentCtx }) + await options.setup?.(agentCtx) + ctx.agents.register(agent) + return { agent, dispose: () => Promise.resolve() } + }, + resume: () => Promise.reject(new Error('fork test sources are live')), + }) + return ctx +} + +function liveAgent(ctx: Context, id: string, turns: number, openTail = false): Session { + const session = ctx.sessions.create(sid(id), { meta: { cwd: '/proj' } }) + for (let turn = 1; turn <= turns; turn++) { + session.append('turn/start', { turn, trigger: { kind: 'message', source: { kind: 'user' } } }) + session.append('user/message', createUserMessage({ + content: [{ type: 'text', text: `prompt ${String(turn)}` }], + source: { kind: 'user' }, + }), { surfaceOp: 'append' }) + session.append('turn/end', { turn, reason: { kind: 'completed' } }) + } + if (openTail) { + session.append('turn/start', { turn: turns + 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + session.append('user/message', createUserMessage({ + content: [{ type: 'text', text: 'open prompt' }], + source: { kind: 'user' }, + }), { surfaceOp: 'append' }) + } + ctx.agents.register({ id: session.id, session, status: 'idle', ctx } as Agent) + return session +} + +const api = (ctx: Context) => createApiProxy(ctx, { + provider: 'default-provider', + model: 'default-model', + cwd: '/tmp', + workspaceRoot: '/tmp', +}) + +describe('sessions.fork', () => { + it('cuts at the anchored completed turn and records lineage and cwd', async () => { + const ctx = await composed() + const source = liveAgent(ctx, 'session-source', 2) + const response = await api(ctx).sessions.fork(request({ sessionId: source.id, atSeq: 1 })) + expect(response.result.ok).toBe(true) + if (!response.result.ok) return + const child = ctx.sessions.get(response.result.value.sessionId) + expect(child?.events.length).toBe(3) + expect(child?.header.parentSession).toBe(source.id) + expect(child?.header.cwd).toBe('/proj') + await ctx.fiber.dispose() + }) + + it('uses the last completed turn only for omitted and past-end anchors', async () => { + const ctx = await composed() + const source = liveAgent(ctx, 'session-tail', 2, true) + const proxy = api(ctx) + const omitted = await proxy.sessions.fork(request({ sessionId: source.id })) + expect(omitted.result.ok).toBe(true) + if (omitted.result.ok) { + expect(ctx.sessions.get(omitted.result.value.sessionId)?.events.length).toBe(6) + } + const pastEnd = await proxy.sessions.fork(request({ sessionId: source.id, atSeq: 999 })) + expect(pastEnd.result.ok).toBe(true) + await ctx.fiber.dispose() + }) + + it('rejects an in-log anchor whose turn is still open', async () => { + const ctx = await composed() + const source = liveAgent(ctx, 'session-open', 1, true) + const anchor = source.events.at(-1)?.seq ?? 0 + const response = await api(ctx).sessions.fork(request({ sessionId: source.id, atSeq: anchor })) + expect(response.result).toMatchObject({ + ok: false, + error: { code: 'fork-unavailable', details: { sessionId: source.id } }, + }) + if (!response.result.ok) expect(response.result.error.message).toMatch(/has not completed/) + await ctx.fiber.dispose() + }) + + it('installs the latest logged model target before the child can run', async () => { + const ctx = await composed() + const source = liveAgent(ctx, 'session-routed', 1) + source.append('request/header', { + header: { + config: { + provider: 'inherited-provider', + model: 'inherited-model', + reasoningEffort: ReasoningEffortId('high'), + }, + }, + reason: 'initial', + }) + const response = await api(ctx).sessions.fork(request({ sessionId: source.id })) + expect(response.result.ok).toBe(true) + if (!response.result.ok) return + const child = ctx.agents.get(response.result.value.sessionId) + if (child === undefined) throw new Error('fork did not publish the child agent') + const assembly = await child.ctx.systemPrompt.assemble() + expect(assembly.variables).toMatchObject({ + provider: 'inherited-provider', + model: 'inherited-model', + }) + const fallback: LlmCallConfig = { provider: 'default-provider', model: 'default-model' } + await expect(agentEvents(child.ctx, child).waterfall( + 'agent/request', 1, 0, new AbortController().signal, () => Promise.resolve(fallback), + )).resolves.toMatchObject({ + provider: 'inherited-provider', + model: 'inherited-model', + reasoningEffort: 'high', + }) + await ctx.fiber.dispose() + }) +}) diff --git a/packages/host/apiproxy/tests/client-handler.spec.ts b/packages/host/apiproxy/tests/client-handler.spec.ts index 2981c9ddea..b7ace8f832 100644 --- a/packages/host/apiproxy/tests/client-handler.spec.ts +++ b/packages/host/apiproxy/tests/client-handler.spec.ts @@ -111,6 +111,21 @@ describe('unary round trip', () => { expect(response.result).toEqual({ ok: true, value: { items: [{ sessionId: 's1', updatedAt: 7, running: false, blank: false }] } }) }) + it('routes session fork with its optional cut anchor through the wire', async () => { + let seen: RpcRequest<{ sessionId: SessionId; atSeq?: number }> | undefined + const api = scriptedApi({ + sessions: { + fork: (request) => { + seen = request + return ok(request, { sessionId: sid('s-child') }) + }, + }, + }) + const response = await client(api).sessions.fork({ sessionId: sid('s-parent'), atSeq: 7 }) + expect(seen?.payload).toEqual({ sessionId: 's-parent', atSeq: 7 }) + expect(response.result).toEqual({ ok: true, value: { sessionId: 's-child' } }) + }) + it('routes workspace rename, delete, and insertSessionBefore through the wire', async () => { const api = scriptedApi() const c = client(api) From 7d27c928515b755a7acec908f1337ec0c2a07d2c Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Thu, 30 Jul 2026 13:27:02 +0800 Subject: [PATCH 16/24] test(web): cover row fork in the real app --- apps/web/tests/message-actions.e2e.ts | 30 ++++++++++++++++++- .../message-actions/fork.expected.md | 5 ++-- .../snapshots/message-actions/ui.expected.md | 3 +- .../apiproxy/tests/api-proxy-fork.spec.ts | 16 ++++++++-- 4 files changed, 48 insertions(+), 6 deletions(-) diff --git a/apps/web/tests/message-actions.e2e.ts b/apps/web/tests/message-actions.e2e.ts index d3c4f45fd7..679fdfbc65 100644 --- a/apps/web/tests/message-actions.e2e.ts +++ b/apps/web/tests/message-actions.e2e.ts @@ -87,13 +87,41 @@ describe('web e2e: message IconActions and clocks on settled history', () => { await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE) }) - it.skipIf(MODE === 'record')('forks the session through the settled user-message action', async () => { + it.skipIf(MODE === 'record')('forks through the settled-message and session-row actions', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-message-fork')) await page.getByRole('button', { name: '在新对话中分支' }).first().click() await expect.poll( () => scaffold.ctx.agents.list().find(agent => agent.session.header.parentSession === SessionId(SEED_ID)), { timeout: 15_000 }, ).toBeDefined() + await expect.poll( + () => page.locator('[role="treeitem"]').count(), + { timeout: 10_000 }, + ).toBe(3) + await expect.poll( + () => page.locator('[role="treeitem"][aria-selected="true"]').count(), + { timeout: 10_000 }, + ).toBe(1) + // The row action owns a distinct ui-workspace injection from the message + // action above, so exercise both through the loaded app before capture. + const sourceRow = page.locator('[role="treeitem"][aria-expanded="true"]').last() + const rowBox = await sourceRow.boundingBox() + if (rowBox === null) throw new Error('fork source row has no layout box') + const actionButton = sourceRow.locator('button[aria-label^="Session actions for "]') + await sourceRow.hover({ position: { x: rowBox.width - 16, y: rowBox.height / 2 } }) + await expect.poll(() => actionButton.isVisible(), { timeout: 2_000 }).toBe(true) + const buttonBox = await actionButton.boundingBox() + if (buttonBox === null) throw new Error('fork source row action has no layout box') + await page.mouse.click(buttonBox.x + buttonBox.width / 2, buttonBox.y + buttonBox.height / 2) + await page.getByRole('menuitem', { name: 'Fork session' }).click() + await expect.poll( + () => scaffold.ctx.agents.list().filter(agent => agent.session.header.parentSession !== undefined).length, + { timeout: 15_000 }, + ).toBe(2) + await expect.poll( + () => page.locator('[role="treeitem"]').count(), + { timeout: 10_000 }, + ).toBe(4) await expect.poll( () => page.locator('[role="treeitem"][aria-selected="true"]').count(), { timeout: 10_000 }, diff --git a/apps/web/tests/snapshots/message-actions/fork.expected.md b/apps/web/tests/snapshots/message-actions/fork.expected.md index 2afb7d4d23..5255632c3a 100644 --- a/apps/web/tests/snapshots/message-actions/fork.expected.md +++ b/apps/web/tests/snapshots/message-actions/fork.expected.md @@ -1,9 +1,10 @@ - tree "Sessions": - - treeitem "Ungrouped 2 sessions" [expanded]: + - treeitem "Ungrouped 3 sessions" [expanded]: - img - - text: Ungrouped 2 sessions + - text: Ungrouped 3 sessions - treeitem "Collapse Use the read tool twice 1min" [expanded]: - button "Collapse": - img - text: Use the read tool twice 1min - treeitem "Use the read tool twice now" [selected] + - treeitem "Use the read tool twice now" diff --git a/apps/web/tests/snapshots/message-actions/ui.expected.md b/apps/web/tests/snapshots/message-actions/ui.expected.md index e21b3782a8..19ba02d99d 100644 --- a/apps/web/tests/snapshots/message-actions/ui.expected.md +++ b/apps/web/tests/snapshots/message-actions/ui.expected.md @@ -31,7 +31,7 @@ - img - button "在新对话中分支": - img -- text: {{clock}} cache hit 98% · 15,962 tokens · 1 turns · 2 steps +- text: {{clock}} - textbox "Message the agent" - button "Add attachment": - img @@ -41,3 +41,4 @@ - text: deepseek-v4-flash - img - button "Send message" [disabled] +- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok diff --git a/packages/host/apiproxy/tests/api-proxy-fork.spec.ts b/packages/host/apiproxy/tests/api-proxy-fork.spec.ts index 64cb1188f5..797bca29f2 100644 --- a/packages/host/apiproxy/tests/api-proxy-fork.spec.ts +++ b/packages/host/apiproxy/tests/api-proxy-fork.spec.ts @@ -82,7 +82,9 @@ describe('sessions.fork', () => { expect(response.result.ok).toBe(true) if (!response.result.ok) return const child = ctx.sessions.get(response.result.value.sessionId) - expect(child?.events.length).toBe(3) + expect(child?.events.map(event => event.type)).toEqual([ + 'turn/start', 'user/message', 'turn/end', 'session/end-seed', + ]) expect(child?.header.parentSession).toBe(source.id) expect(child?.header.cwd).toBe('/proj') await ctx.fiber.dispose() @@ -92,13 +94,23 @@ describe('sessions.fork', () => { const ctx = await composed() const source = liveAgent(ctx, 'session-tail', 2, true) const proxy = api(ctx) + const expectedTypes = [ + 'turn/start', 'user/message', 'turn/end', + 'turn/start', 'user/message', 'turn/end', + 'session/end-seed', + ] const omitted = await proxy.sessions.fork(request({ sessionId: source.id })) expect(omitted.result.ok).toBe(true) if (omitted.result.ok) { - expect(ctx.sessions.get(omitted.result.value.sessionId)?.events.length).toBe(6) + expect(ctx.sessions.get(omitted.result.value.sessionId)?.events.map(event => event.type)) + .toEqual(expectedTypes) } const pastEnd = await proxy.sessions.fork(request({ sessionId: source.id, atSeq: 999 })) expect(pastEnd.result.ok).toBe(true) + if (pastEnd.result.ok) { + expect(ctx.sessions.get(pastEnd.result.value.sessionId)?.events.map(event => event.type)) + .toEqual(expectedTypes) + } await ctx.fiber.dispose() }) From 2f8f47e50048d4998686000124e7a08d974a8b45 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Thu, 30 Jul 2026 20:29:29 +0800 Subject: [PATCH 17/24] feat(ui-workspace): flatten session fork rows --- ...n-list-browsing-and-manual-order.i18n.yaml | 6 +- ...-session-list-browsing-and-manual-order.md | 14 +- ...ssion-list-browsing-and-manual-order.zh.md | 14 +- packages/client/ui-workspace/README.i18n.yaml | 4 +- packages/client/ui-workspace/README.md | 2 +- packages/client/ui-workspace/README.zh.md | 2 +- .../src/client/WorkspaceBrowser.tsx | 41 +---- .../src/client/rows/Rows.module.css | 36 +--- .../ui-workspace/src/client/rows/Rows.tsx | 64 ++------ .../client/ui-workspace/src/client/tree.ts | 155 +++--------------- .../client/ui-workspace/tests/rows.spec.tsx | 94 ++++------- .../client/ui-workspace/tests/tree.spec.ts | 18 +- .../tests/workspace-browser.spec.tsx | 8 +- 13 files changed, 110 insertions(+), 348 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.i18n.yaml b/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.i18n.yaml index 590d9227b8..ebc2df795a 100644 --- a/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.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 -2026-07-25-session-list-browsing-and-manual-order.md: 586995bf459aeaee88672863977f7acf2a7061a3 -2026-07-25-session-list-browsing-and-manual-order.zh.md: 432d5167a57d30bc04a0b4faf213e4341f07bd2f +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.md +2026-07-25-session-list-browsing-and-manual-order.md: 831aa53e532a75392690c330837482bb0f9c32b1 +2026-07-25-session-list-browsing-and-manual-order.zh.md: 9ad074d59c13585aa4fca46ae4d40e2deb15cde6 diff --git a/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.md b/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.md index 586995bf45..831aa53e53 100644 --- a/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.md +++ b/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.md @@ -12,14 +12,14 @@ Two existing mechanisms stood in the way. First, the host durably promoted the a ## Decision -### Flat view and viewing state +### Flat rows and viewing state -The group-by menu offers two modes, WorkSpace / In one list. Flat mode renders every session (fork children included) as a top-level row, strictly newest-first by `updatedAt`, with no parent/child adjacency; the Intent placeholder renders as the first row. The mode choice persists in the browser (`dsh.workspace.view`) across reloads. +The group-by menu offers two modes, WorkSpace / In one list. WorkSpace mode renders peer session rows within each group in the manual order from `WorkspaceView.sessionIds`; In one list combines every session and sorts them strictly newest-first by `updatedAt`. Neither mode projects `parentId` into a list hierarchy; fork lineage remains session data only. [Web session fork actions](2026-07-27-web-session-fork-actions.md) define the complete fork behavior. The mode choice persists in the browser (`dsh.workspace.view`) across reloads. ### Row interactions - Session rows show a detail card after a 500ms hover dwell (full title / relative time / status line; the status line has only running/idle until the wire grows a status field). The card and the row menu are mutually exclusive: no card while a menu is open or a drag is in flight. -- Session-row … menu: Rename / Fork session / Delete session, visual-only this iteration; workspace-header … menu: Rename (wired) / Delete workspace (visual-only). Menus close when the pointer leaves them. +- Session-row … menu: Rename / Fork session / Delete session; Rename and Fork are wired, while Delete remains visual-only. The workspace-header … menu's Rename / Delete workspace actions are both wired. Menus close when the pointer leaves them. - Supporting primitives: `Menu` gains label entries, danger rows, and `closeOnPointerLeave`; a new `HoverCard` (portaled placement, open delay, disabled guard). ### workspace.rename @@ -30,7 +30,7 @@ The group-by menu offers two modes, WorkSpace / In one list. Flat mode renders e The `session/event` → `touchSession` activity-pinning chain is deleted wholesale; the workspace account order is now manually owned — new sessions prepend at attach, and explicit reordering goes through `workspace.insertSessionBefore({ workspaceId, sessionId, beforeSessionId? })` (DOM insertBefore semantics: with an anchor it inserts before it, omitted appends to the end). The entity throws a typed `WorkspaceMoveInvalidError` only for unaccounted session/anchor ids; the handler maps exactly that to the business code `workspace-move-invalid`, while storage failures stay internal. -The UI is HTML5 drag on root rows inside a group (workspace grouping only, outside search; fork children ride with their parent and are not draggable). Order authority stays entirely host-side: drop only sends the RPC, the client performs zero local reordering, and the view refreshes from the response upsert and the changed frame; a failed move changes nothing. The client's upsert rejects snapshots older (`updatedAt`) than the installed projection so a late unary response cannot roll back a newer frame. +The UI is HTML5 drag on session rows inside a group (workspace grouping only, outside search; fork children and their source sessions are ordered independently). Order authority stays entirely host-side: drop only sends the RPC, the client performs zero local reordering, and the view refreshes from the response upsert and the changed frame; a failed move changes nothing. The client's upsert rejects snapshots older (`updatedAt`) than the installed projection so a late unary response cannot roll back a newer frame. ### Shell/region split @@ -46,15 +46,15 @@ ui-sidebar shrinks to the column-geometry shell: brand row, fold state machine, **Keep the rename dialog in ui-sidebar (smallest change)** — that is the problem itself: workspace-domain dialogs scattered in a borrowed slot, with each addition (the Delete confirmation is coming) repeating the cross-package wiring. Review first considered moving only the rename modal; the ruling was to give the whole browsing region to ui-workspace and leave the shell geometry-only. -**Keep parent/child adjacency in flat mode** — contradicts strict recency (a child newer than its parent's sibling cannot slot adjacently), and the flat view's purpose is dropping the hierarchy; flattening fully and disabling drag in flat mode (no persistence carrier) is more consistent. +**Nest sessions by fork lineage in WorkSpace mode** — nesting makes the current child visible only while its ancestors are expanded and limits in-group manual ordering to root nodes; `parentId` is lineage data, not a list-navigation structure. Flattening all sessions into peer rows lets each row be opened, searched, and ordered independently; In one list still disables drag because it has no workspace persistence carrier. ## Consequences - Manual order is the sole authority over the workspace account: an order the user arranges is never scrambled by activity; the cost is losing float-to-top-on-activity, whose signal now rides the row status dot and time label. The `WorkspaceView.sessionIds` wire contract is reworded to the manual-order semantics. - The two-fact shell/region contract funnels every future workspace-domain feature (Delete confirmation, cross-group moves, Ungrouped adoption) into the single ui-workspace package; ui-sidebar no longer evolves with session-list features. - Flat mode supports neither reordering nor a create-in-workspace entry point (switching back to grouped view is required) — an accepted scope reduction. -- Wiring the three session-menu items and workspace Delete, and growing the wire status enum, remain future iterations. +- Wiring session Delete and growing the wire status enum remain future iterations. ## Testing -Package-level suites cover the derivations (deriveGroups/deriveFlat), row components, both apply registrations and passthroughs, host entity move semantics, and the rename/insertSessionBefore RPC implementations with their fixture stubs; the `apps/web` keyless snapshots regress the assembled application; delivery acceptance additionally runs a 12-item playwright (chromium headless) checklist (grouped default, flat switch and persistence, hover-card appearance and suppression, both menus, the full rename chain, drag persistence) and drives the real host over the wire for rename success / duplicate rejection / `workspace-move-invalid`. +Package-level suites cover the derivations (deriveGroups/deriveFlat), peer session rows, both apply registrations and passthroughs, host entity move semantics, and the rename/insertSessionBefore RPC implementations with their fixture stubs; the `apps/web` keyless snapshots regress the assembled application and pin that a fork does not introduce session expansion controls. diff --git a/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.zh.md b/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.zh.md index 432d5167a5..9ad074d59c 100644 --- a/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.zh.md +++ b/.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.zh.md @@ -12,14 +12,14 @@ Status: implemented ## Decision -### 平铺视图与浏览态 +### 平铺行与浏览态 -group-by 菜单提供 WorkSpace / In one list 两种模式。平铺模式把所有 session(含 fork 子)一律作为顶层行,严格按 `updatedAt` 新→旧排序,不保持父子相邻;Intent 占位行渲染在列表首行。模式选择持久化在浏览器(`dsh.workspace.view`),刷新保持。 +group-by 菜单提供 WorkSpace / In one list 两种模式。WorkSpace 模式按 `WorkspaceView.sessionIds` 的手动序在各组内展示同级 session 行；In one list 把所有 session 合并后严格按 `updatedAt` 新→旧排序。两种模式都不把 `parentId` 投影成列表层级，fork 谱系只保留为 session 数据；完整 fork 行为由 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)定义。模式选择持久化在浏览器(`dsh.workspace.view`),刷新保持。 ### 行交互 - session 行悬停 500ms 出详情卡(全名/相对时间/状态行;状态本期只有 running/idle 两态,枚举扩展待 wire 增补 status 字段)。卡片与行菜单互斥:菜单开启或拖拽进行中不出卡。 -- session 行 … 菜单:Rename / Fork session / Delete session,本期纯视觉;workspace 组头 … 菜单:Rename(已接线)/ Delete workspace(纯视觉)。菜单鼠标移出即关。 +- session 行 … 菜单:Rename / Fork session / Delete session，其中 Rename 与 Fork 已接线，Delete 仍为纯视觉；workspace 组头 … 菜单的 Rename / Delete workspace 均已接线。菜单鼠标移出即关。 - 支撑件:`Menu` 新增 label 条目、danger 行、`closeOnPointerLeave`;新增 `HoverCard`(portal 定位、开启延时、disabled 守卫)。 ### workspace.rename @@ -30,7 +30,7 @@ group-by 菜单提供 WorkSpace / In one list 两种模式。平铺模式把所 `session/event` → `touchSession` 活动置顶链整体删除;workspace 账本序改为纯手动拥有——新 session attach 时前插,显式重排走 `workspace.insertSessionBefore({ workspaceId, sessionId, beforeSessionId? })`(DOM insertBefore 语义:锚给了插锚前,缺省 append 到末尾)。实体只对不在账的 session/锚抛类型化的 `WorkspaceMoveInvalidError`,handler 仅把它映射为业务码 `workspace-move-invalid`,存储故障保持 internal。 -UI 为组内 root 行的 HTML5 拖拽(仅 workspace 分组、非搜索态;fork 子随父不单独拖)。顺序权威完全在 host:drop 只发 RPC,client 零本地重排,视图靠响应体 upsert 与 changed 帧刷新;失败即无事发生。client 的 upsert 拒绝比已装载投影更旧(`updatedAt`)的快照,防迟到的一元响应回滚更新的帧。 +UI 为组内 session 行的 HTML5 拖拽(仅 workspace 分组、非搜索态；fork 子与源会话一样独立排序)。顺序权威完全在 host:drop 只发 RPC,client 零本地重排,视图靠响应体 upsert 与 changed 帧刷新;失败即无事发生。client 的 upsert 拒绝比已装载投影更旧(`updatedAt`)的快照,防迟到的一元响应回滚更新的帧。 ### 壳/区域切分 @@ -46,15 +46,15 @@ ui-sidebar 缩为列几何壳:品牌行、折叠状态机、New Session、Settin **rename 对话框留在 ui-sidebar(最小改动)** —— 正是问题本身:workspace 域的对话框散落在借来的坑里,每加一个(Delete 确认框将至)都重演跨包接线。评审中先议了「只挪 rename Modal」的中间态,最终裁定整个浏览区域归 ui-workspace,壳只留几何。 -**平铺模式保持父子相邻成组** —— 与「严格按时间」矛盾(子新于兄则插不进相邻位),且平铺本意就是取消层级;拉平并禁用平铺下的拖拽(无持久化载体)更一致。 +**WorkSpace 模式按 fork 谱系嵌套 session** —— 嵌套会让当前子会话依赖祖先展开态才能可见，也让组内手动序只能移动根节点；`parentId` 是 lineage 数据，不是列表导航结构。所有 session 拍平成同级行后，每行都可独立打开、搜索与排序；In one list 仍因没有 workspace 持久化载体而禁用拖拽。 ## Consequences - 手动序是唯一的 workspace 账本序权威:用户排好的顺序不再被活动打乱;代价是「最近活跃浮到最上」的行为消失,活跃感知转由行内状态点与时间标签承担。`WorkspaceView.sessionIds` 的 wire 契约随之改为手动序措辞。 - 壳/区域两事实契约把 workspace 域的后续功能(Delete 确认、跨组移动、Ungrouped 收编)全部收进 ui-workspace 单包;ui-sidebar 不再随 session 列表功能演进。 - 平铺模式不支持排序与分组入口(建到指定 workspace 需切回分组视图),是拍板接受的范围收窄。 -- session 菜单三项与 workspace Delete 的功能接线、状态枚举扩 wire,留待后续迭代。 +- session Delete 的功能接线与状态枚举扩 wire,留待后续迭代。 ## Testing -包级用例覆盖派生(deriveGroups/deriveFlat)、行组件、两处 apply 注册与透传、host 实体移位语义、rename/insertSessionBefore 的 RPC 实现与 fixture 桩;`apps/web` keyless snapshot 回归覆盖装配后的应用;交付验收另以 playwright(chromium headless)过 12 项清单(分组默认、平铺切换与持久化、hover 卡出现与抑制、双菜单、rename 全链、拖拽落盘),并对真 host 直打 wire 验证 rename 成功/重名拒绝/`workspace-move-invalid` 三径。 +包级用例覆盖派生(deriveGroups/deriveFlat)、同级 session 行、两处 apply 注册与透传、host 实体移位语义、rename/insertSessionBefore 的 RPC 实现与 fixture 桩；`apps/web` keyless snapshot 回归覆盖装配后的应用，并钉住 fork 后没有 session 展开控件。 diff --git a/packages/client/ui-workspace/README.i18n.yaml b/packages/client/ui-workspace/README.i18n.yaml index a8f5d98981..1223fcc0f9 100644 --- a/packages/client/ui-workspace/README.i18n.yaml +++ b/packages/client/ui-workspace/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-workspace/README.md -README.md: f0dbd3de4ac5b7934b4077b2986f5def5be329c8 -README.zh.md: b9f068c6d1709f0a01d22c3fb1cdc391764d666b +README.md: 2a4e544250756db50b19bc101c19ac79505a3d6c +README.zh.md: 7ae2b0e196a98d1375e9073146bb8119ea8cbe90 diff --git a/packages/client/ui-workspace/README.md b/packages/client/ui-workspace/README.md index f0dbd3de4a..2a4e544250 100644 --- a/packages/client/ui-workspace/README.md +++ b/packages/client/ui-workspace/README.md @@ -6,7 +6,7 @@ Shared Workspace picker plugin. `WorkspaceBrowser` is registered into the sideba The picker lists real Host Workspace entities through the global `useWorkspaces` hook. Selecting a Workspace invokes the slot owner's `onPick` callback to retarget the frontend Session object. Each registration declares a **directory-flow child hole** (`single` kind: `conversation.hero.workspace.directoryFlow` / `sidebar.workspaces.directoryFlow`) that the composed picker package's client half fills with its picking interaction — the [`-native`](../../host/directory-picker-native/README.md) backend's renderless OS-chooser driver today, an in-app browsing dialog under a `-browse` composition. The flat **Open local folder...** action renders only while the surface's hole is occupied (occupancy read per menu render; an empty hole means the composition has no picking affordance — the seam's documented no-flow default). This package owns the trigger and the adoption: the occupant reports one picked path per open through the hole's owner conversation (`open`/`busy`/`onPicked`/`onCancel`/`onError`), and the owner adopts it through the object layer, selecting the committed Workspace only after its list projection has refreshed; cancellation is silent, and errors land in the retryable folder dialog whose **Choose again** reopens the flow. **Create a new workspace** retains the name dialog and disables names already present in that list, while the Host remains authoritative for concurrent or non-UI callers. The runtime Session and Workspace services own materialization. The Workspace row's Delete action opens a confirmation that states the retention boundary, blocks duplicate submission, and keeps failures open; success removes the group while its Sessions remain under Ungrouped. The Session row's Rename action opens the same browser-owned dialog pattern prefilled with the row's display title: no client-side conflict rule exists (the host normalizes and may reject with `title-invalid`, rendered in the dialog alert), and confirming an unchanged title is deliberately allowed — it pins the current automatic title against regeneration. -The Session row's Fork action forks at the source's last completed turn and opens the child; the lineage-aware tree nests it beneath the source. A failure leaves the current selection unchanged. +The Session row's Fork action forks at the source's last completed turn and opens the child; the source and child always appear as peer rows within a workspace group, with lineage retained only as session data. A failure leaves the current selection unchanged. Both target slots are declared by other plugins, so `apply` registers through declaration-aware deferral and re-registers after a declaring slot is restored. diff --git a/packages/client/ui-workspace/README.zh.md b/packages/client/ui-workspace/README.zh.md index b9f068c6d1..7ae2b0e196 100644 --- a/packages/client/ui-workspace/README.zh.md +++ b/packages/client/ui-workspace/README.zh.md @@ -6,7 +6,7 @@ 该选择器通过全局 `useWorkspaces` hook 列出真实的 Host Workspace 实体。选择 Workspace 会调用 slot owner 的 `onPick` 回调，重新定位前端 Session 对象。每个注册各自声明一个**目录流子洞**（`single` kind：`conversation.hero.workspace.directoryFlow`／`sidebar.workspaces.directoryFlow`），由组合的选择器包 client half 填入其选取交互——今天是 [`-native`](../../host/directory-picker-native/README.md) 后端的无渲染 OS 选择器驱动，`-browse` 组合下则是应用内浏览对话框。平铺显示的 **打开本地文件夹…** 操作仅在本表层的洞被占用时渲染（每次菜单渲染读取占用状态；洞为空意味着该组合没有选目录能力——seam 文档化的无流程默认行为）。本包持有触发与接纳：占用者经洞的 owner 会话（`open`/`busy`/`onPicked`/`onCancel`/`onError`）每次打开上报一个所选路径，owner 通过对象层接纳它，并等待 Workspace 列表投影刷新后才选中已提交的 Workspace；取消操作不会显示提示，错误落入可重试的文件夹对话框，其 **重新选择** 会重新打开流程。**创建新工作区** 操作保留名称对话框，并禁用列表中已有的名称，而 Host 对并发或非 UI 调用方仍具有最终决定权。运行时 Session 与 Workspace 服务负责物化。Workspace 行内的 Delete 操作会打开确认框，说明保留边界、阻止重复提交，并在失败时保持打开；成功后，该分组会被移除，其 Session 则留在 Ungrouped 下。Session 行内的 Rename 操作打开同款浏览器持有的对话框，并以该行的显示标题预填：客户端不设名称冲突规则（host 负责规范化，可能以 `title-invalid` 拒绝，错误渲染在对话框告警区）；确认未修改的标题是有意允许的——这正是把当前自动标题钉住、不再被重新生成覆盖的手势。 -Session 行内的 Fork 操作在源会话最后一个已完成轮次处 fork 并打开子会话；感知谱系的树会将子会话嵌套在源会话下。失败不会改变当前选中项。 +Session 行内的 Fork 操作在源会话最后一个已完成轮次处 fork 并打开子会话；源会话与子会话在 workspace 组内始终作为同级行展示，谱系只保留为 session 数据。失败不会改变当前选中项。 两个目标 slot 都由其他插件声明，因此 `apply` 通过声明感知的延迟机制完成注册，并在声明该 slot 的插件恢复后重新注册。 diff --git a/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx b/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx index 933b49bdf0..60b57e0b06 100644 --- a/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx +++ b/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx @@ -104,7 +104,6 @@ function SessionTree({ const list = useSessions(s => s) const current = list.current const [expandedProjects, setExpandedProjects] = useState([]) - const [expandedSessions, setExpandedSessions] = useState([]) // Transient drag viewing state (never store-bound; order truth stays Host-side). const [drag, setDrag] = useState(null) const currentGroup = current === undefined @@ -115,27 +114,9 @@ function SessionTree({ if (current === undefined || currentGroup === undefined) return setExpandedProjects(l => (l.includes(currentGroup) ? l : [...l, currentGroup])) }, [current, currentGroup]) - // The selected session must be visible: unfold its ancestor chain (fork - // lands the child under a possibly folded parent row). - const currentAncestors = useMemo(() => { - const chain: string[] = [] - let cursor = current === undefined ? undefined : list.byId[current]?.parentId - while (cursor !== undefined && !chain.includes(cursor)) { - chain.push(cursor) - cursor = list.byId[cursor]?.parentId - } - return chain - }, [current, list]) - useEffect(() => { - if (currentAncestors.length === 0) return - setExpandedSessions((l) => { - const missing = currentAncestors.filter(id => !l.includes(id)) - return missing.length === 0 ? l : [...l, ...missing] - }) - }, [currentAncestors]) const groups = useMemo( - () => deriveGroups(list, workspaces, { expandedProjects, expandedSessions, query }), - [list, workspaces, expandedProjects, expandedSessions, query], + () => deriveGroups(list, workspaces, { expandedProjects, query }), + [list, workspaces, expandedProjects, query], ) const now = Date.now() @@ -146,7 +127,7 @@ function SessionTree({

{query === '' ? 'No sessions yet' : 'No matches'}
)} {groups.map(group => ( - // Group section: header row + expanded session subtree. The + // Group section: header row + expanded top-level session rows. The // inter-group breathing room (former flat-list batch separator) // is the section's own margin (WorkspaceBrowser.module.css).
@@ -170,7 +151,7 @@ function SessionTree({ }} /> {group.sessions.map((node, index) => { - // Draggable: real-workspace group roots outside search. The drag + // Draggable: real-workspace session rows outside search. The drag // never leaves its group — rows of other groups show no markers // and reject drops (visual movement confined to this section). const draggable = group.workspaceId !== undefined && query === '' @@ -188,15 +169,15 @@ function SessionTree({ drop: (half: 'before' | 'after') => { /* v8 ignore next -- narrowing guard: Rows gates drop on `active`, which is false while the drag state is null. */ if (drag === null) return - const roots = group.sessions + const sessions = group.sessions // Anchor = the row the insert line points at ('after' means // the next root; end-of-list omits the anchor → append). - const anchor = half === 'before' ? node.id : roots[index + 1]?.id + const anchor = half === 'before' ? node.id : sessions[index + 1]?.id setDrag(null) if (anchor === drag.sessionId) return // No-op when the drop lands back on the source position. - const sourceIndex = roots.findIndex(r => r.id === drag.sessionId) - const anchorIndex = anchor === undefined ? roots.length : roots.findIndex(r => r.id === anchor) + const sourceIndex = sessions.findIndex(r => r.id === drag.sessionId) + const anchorIndex = anchor === undefined ? sessions.length : sessions.findIndex(r => r.id === anchor) if (sourceIndex !== -1 && (anchorIndex === sourceIndex || anchorIndex === sourceIndex + 1)) return insertSessionBefore(drag.workspaceId, drag.sessionId, anchor).catch((reason: unknown) => { console.warn('session reorder rejected:', reason) @@ -208,13 +189,11 @@ function SessionTree({ { setExpandedSessions(l => toggled(l, id)) }} drag={dragProps} /> ) @@ -242,15 +221,11 @@ function FlatList({ useSessions, open, forkSession, onSessionRename, query }: Pi {}} - flat /> ))}
diff --git a/packages/client/ui-workspace/src/client/rows/Rows.module.css b/packages/client/ui-workspace/src/client/rows/Rows.module.css index 5a5cac914e..f64849e1c5 100644 --- a/packages/client/ui-workspace/src/client/rows/Rows.module.css +++ b/packages/client/ui-workspace/src/client/rows/Rows.module.css @@ -39,9 +39,7 @@ height: 20px; } -/* Session cell (figma): pad 8, adjacent 16px twist + status slots, then a 4px - gap to the title — the slots butt together, so the row gap is zeroed and - the title carries its own margins. */ +/* Session cell (figma): pad 8, a 16px status slot, then a 4px title gap. */ .sessionRow { height: 34px; gap: 0; @@ -168,7 +166,7 @@ background: var(--dsw-alias-interactive-bg-hover); } -/* Drag reorder insert line (workspace-group roots): 2px accent above or +/* Drag reorder insert line (workspace-group session rows): 2px accent above or below the hovered row, drawn with box-shadow so no layout shift. */ .sessionRow.dropBefore { box-shadow: 0 -2px 0 0 var(--dsw-alias-state-business-primary); @@ -233,33 +231,9 @@ color: var(--dsw-alias-label-primary); } -/* Session expand twist occupies the leading 16px slot; keep a spacer when absent - so titles align across sibling rows. Duplicates the .iconButton reset instead - of `composes:` — the tsdown CSS-modules pipeline drops composes mappings, which - left the raw UA button box showing. */ -.twist { - flex: none; - display: inline-flex; - align-items: center; - justify-content: center; - width: 16px; - height: 20px; - border: none; - border-radius: 4px; - padding: 0; - background: transparent; - cursor: pointer; -} - -.twist:hover { - color: var(--dsw-alias-label-primary); -} - -/* Chevrons and tree twists ride the caption grey (#ADB2B8); the folder glyph - stays one step darker (tertiary, #81858C) per the cell spec. Declared last - to win over the composed .iconButton color. */ -.chevron, -.twist { +/* Chevrons ride the caption grey (#ADB2B8); the folder glyph stays one step + darker (tertiary, #81858C) per the cell spec. */ +.chevron { color: var(--dsw-alias-label-caption); } diff --git a/packages/client/ui-workspace/src/client/rows/Rows.tsx b/packages/client/ui-workspace/src/client/rows/Rows.tsx index 657585f075..6dceec4ef6 100644 --- a/packages/client/ui-workspace/src/client/rows/Rows.tsx +++ b/packages/client/ui-workspace/src/client/rows/Rows.tsx @@ -16,9 +16,6 @@ import type { GroupNode, SessionNode } from '../tree.ts' import { formatRelativeTime } from '../tree.ts' import css from './Rows.module.css' -/** Indent step per tree level: one 16px slot (figma session cell). */ -const INDENT_STEP = 16 - const SESSION_MENU_ITEMS = [ { id: 'rename', label: 'Rename', icon: }, { id: 'fork', label: 'Fork session', icon: }, @@ -135,16 +132,12 @@ export function ProjectRowItem({ group, onToggle, onCreate, actions }: { } /** - * One session subtree: the node's own 34px row (indent by depth, expand - * twist when it has children, running dot, relative time) plus its visible - * children, recursively — the component tree mirrors the derived tree. + * One top-level 34px session row with running dot and relative time. * @param props.node - derived session node. - * @param props.depth - 0 = directly under the group header. * @param props.currentId - selected session id (row highlight). * @param props.now - epoch ms for relative-time formatting. * @param props.onOpen - open a session by id. - * @param props.onToggle - unfold/fold a subtree by id. - * @returns the node's row followed by its children. + * @returns the session row. */ /** Hover-card body: full title, relative time, and the status line (running/idle until wire status lands). */ function SessionHoverContent({ node, now }: { node: SessionNode; now: number }) { @@ -161,7 +154,7 @@ function SessionHoverContent({ node, now }: { node: SessionNode; now: number }) } /** - * Root-row drag wiring supplied by the group owner (workspace groups only). + * Session-row drag wiring supplied by the group owner (workspace groups only). * `drop` reports the half of the row the pointer released on: 'before' * inserts above this row, 'after' below it (the owner resolves the anchor). */ @@ -184,9 +177,8 @@ function rowHalf(e: { clientY: number; currentTarget: HTMLElement }): 'before' | return e.clientY < rect.top + rect.height / 2 ? 'before' : 'after' } -export function SessionNodeItem({ node, depth, currentId, now, onOpen, onRename, onFork, onToggle, drag, flat = false }: { +export function SessionNodeItem({ node, currentId, now, onOpen, onRename, onFork, drag }: { node: SessionNode - depth: number currentId: string | undefined now: number onOpen: (id: SessionNode['id']) => void @@ -194,18 +186,13 @@ export function SessionNodeItem({ node, depth, currentId, now, onOpen, onRename, onRename: (id: SessionNode['id'], currentTitle: string) => void /** Fork a session at its last completed turn (row menu action). */ onFork: (id: SessionNode['id']) => void - onToggle: (id: SessionNode['id']) => void - /** Present only on draggable rows (workspace-group roots outside search). */ + /** Present only on draggable rows (workspace-group sessions outside search). */ drag?: RowDragProps | undefined - /** Flat-list variant: no twist slot (figma flat cell) — titles align on the status slot. */ - flat?: boolean }) { const row = node const selected = node.id === currentId const [menuOpen, setMenuOpen] = useState(false) - // Rail (figma session cell: pad 8, twist slot 16, status slot 16, gap 4 to - // the title): both slots are always reserved so titles align whether or not - // the twist/dot is lit. Extra depth rides the left padding. + // Figma session cell: pad 8, status slot 16, then a 4px title gap. const ownRow = (
{ onOpen(node.id) }} draggable={drag !== undefined} onDragStart={drag === undefined @@ -241,18 +226,6 @@ export function SessionNodeItem({ node, depth, currentId, now, onOpen, onRename, drag.drop(rowHalf(e)) }} > - {row.hasChildren && !flat - ? ( - - ) - : null} {row.running && } {row.title} {formatRelativeTime(row.updatedAt, now)} @@ -283,25 +256,10 @@ export function SessionNodeItem({ node, depth, currentId, now, onOpen, onRename,
) return ( - <> - } - disabled={menuOpen || drag?.active === true} - /> - {node.children.map(child => ( - - ))} - + } + disabled={menuOpen || drag?.active === true} + /> ) } diff --git a/packages/client/ui-workspace/src/client/tree.ts b/packages/client/ui-workspace/src/client/tree.ts index de47454d84..3f30064269 100644 --- a/packages/client/ui-workspace/src/client/tree.ts +++ b/packages/client/ui-workspace/src/client/tree.ts @@ -11,20 +11,15 @@ export const UNGROUPED_KEY = '' /** Display label for the ungrouped bucket row. */ export const UNGROUPED_LABEL = 'Ungrouped' -/** One session node of a group's visible tree (34px row; children render indented one step). */ +/** One top-level session row in a group or the flat list. */ export interface SessionNode { id: SessionId title: string - /** Visible children, already expansion/search-filtered (empty when folded). */ - children: readonly SessionNode[] - /** The session HAS children in the data (the twist renders even while folded). */ - hasChildren: boolean - expanded: boolean running: boolean updatedAt: number } -/** One workspace group section: header row facts + the visible session tree. */ +/** One workspace group section: header row facts + visible top-level session rows. */ export interface GroupNode { /** Group key: the workspace id or {@link UNGROUPED_KEY}. */ key: string @@ -39,14 +34,13 @@ export interface GroupNode { expanded: boolean /** The group contains the selected session (active folder tint; supplied here so the renderer never scans). */ containsCurrent: boolean - /** Visible roots (empty while the group is folded). */ + /** Visible session rows (empty while the group is folded). */ sessions: readonly SessionNode[] } -/** Viewing state consumed by the derivation — the component's local useState arrays, taken as-is. */ +/** Viewing state consumed by the derivation. */ export interface TreeView { expandedProjects: readonly string[] - expandedSessions: readonly string[] query: string } @@ -56,9 +50,7 @@ interface Group { cwd: string | undefined createdAt: number | undefined label: string - summaries: Map - roots: SessionId[] - children: Map + sessions: SessionSummary[] } /** @@ -89,7 +81,7 @@ function sessionTitle(session: SessionSummary): string { return session.blank ? 'New Session' : session.displayTitle } -/** Build one group's parent/child tree from an ordered member list. */ +/** Build one group without projecting session lineage into presentation. */ function buildGroup( key: string, workspaceId: WorkspaceId | undefined, @@ -99,54 +91,11 @@ function buildGroup( members: readonly SessionSummary[], order: 'account' | 'recency', ): Group { - const summaries = new Map(members.map(m => [m.id, m])) - const children = new Map() - const roots: SessionSummary[] = [] - for (const m of members) { - // A session is a tree child only when its parent lives in the same - // group; cross-group or unknown parents degrade to group roots. - if (m.parentId !== undefined && m.parentId !== m.id && summaries.has(m.parentId)) { - const kids = children.get(m.parentId) - if (kids === undefined) children.set(m.parentId, [m.id]) - else kids.push(m.id) - } else { - roots.push(m) - } - } - // Workspace order is the member iteration order (workspace.sessionIds), so - // attached groups keep insertion order; Ungrouped sorts by recency. - if (order === 'recency') { - roots.sort(byRecency) - for (const kids of children.values()) { - kids.sort((a, b) => { - const sa = summaries.get(a) - const sb = summaries.get(b) - /* v8 ignore next -- unreachable: kid ids are inserted alongside their summaries. */ - if (sa === undefined || sb === undefined) return 0 - return byRecency(sa, sb) - }) - } - } - const rootIds = roots.map(r => r.id) - // parentId cycles (host bug) leave members unreachable from any root; - // surface them as extra roots — the flatten walk's visited set stops - // loops. Each node sits in at most one kids list and roots have no - // in-group parent, so the scan pushes every reachable node exactly once. - const reachable = new Set(rootIds) - const stack = [...rootIds] - while (stack.length > 0) { - const top = stack.pop() - /* v8 ignore next -- unreachable: the loop condition guarantees a non-empty stack. */ - if (top === undefined) break - for (const kid of children.get(top) ?? []) { - reachable.add(kid) - stack.push(kid) - } - } - for (const m of members) { - if (!reachable.has(m.id)) rootIds.push(m.id) - } - return { key, workspaceId, cwd, createdAt, label, summaries, roots: rootIds, children } + const sessions = [...members] + // Workspace order is workspace.sessionIds; only Ungrouped lacks an account + // order and therefore falls back to recency. + if (order === 'recency') sessions.sort(byRecency) + return { key, workspaceId, cwd, createdAt, label, sessions } } /** @@ -181,72 +130,24 @@ function groupByWorkspace(list: SessionListState, workspaces: readonly Workspace return groups } -function sessionNode(s: SessionSummary, children: readonly SessionNode[], hasChildren: boolean, expanded: boolean): SessionNode { +function sessionNode(s: SessionSummary): SessionNode { return { id: s.id, title: sessionTitle(s), - children, - hasChildren, - expanded, running: s.running, updatedAt: s.updatedAt, } } -function buildVisible(g: Group, expandedSessions: ReadonlySet): SessionNode[] { - const visited = new Set() - const walk = (id: SessionId): SessionNode | null => { - if (visited.has(id)) return null - visited.add(id) - const s = g.summaries.get(id) - /* v8 ignore next -- unreachable: walked ids come from the grouped summaries. */ - if (s === undefined) return null - const kids = g.children.get(id) ?? [] - const expanded = expandedSessions.has(id) - const children = expanded ? kids.map(walk).filter((n): n is SessionNode => n !== null) : [] - return sessionNode(s, children, kids.length > 0, expanded) - } - return g.roots.map(walk).filter((n): n is SessionNode => n !== null) -} - -/** Matched sessions plus their ancestor chains (forced visible under search). */ -function searchVisible(g: Group, q: string): Set { - const visible = new Set() - for (const m of g.summaries.values()) { - if (!sessionTitle(m).toLowerCase().includes(q)) continue - let cur: SessionSummary | undefined = m - while (cur !== undefined && !visible.has(cur.id)) { - visible.add(cur.id) - cur = cur.parentId !== undefined && cur.parentId !== cur.id ? g.summaries.get(cur.parentId) : undefined - } - } - return visible -} - -function buildSearch(g: Group, visible: ReadonlySet): SessionNode[] { - const visited = new Set() - const walk = (id: SessionId): SessionNode | null => { - if (visited.has(id) || !visible.has(id)) return null - visited.add(id) - const s = g.summaries.get(id) - /* v8 ignore next -- unreachable: walked ids come from the grouped summaries. */ - if (s === undefined) return null - const kids = (g.children.get(id) ?? []).filter(kid => visible.has(kid)) - const children = kids.map(walk).filter((n): n is SessionNode => n !== null) - return sessionNode(s, children, kids.length > 0, kids.length > 0) - } - return g.roots.map(walk).filter((n): n is SessionNode => n !== null) -} - /** - * Derive the nested workspace browser group structure. + * Derive the workspace browser groups with every session as a top-level row. * * Normal mode: every group shows; sessions populate under expanded groups, - * descending only into expanded sessions. Search mode (non-blank query, + * preserving Host account order. Search mode (non-blank query, * case-insensitive display-title substring): expansion state is ignored — - * matched sessions and their ancestor chains are forced visible, groups - * without a display-title or label hit are dropped, and a label-only hit - * keeps the bare group header. Blank sessions are excluded everywhere. + * matching sessions are forced visible, groups without a display-title or + * label hit are dropped, and a label-only hit + * keeps the bare group header. Non-current blank sessions are excluded. * @param list - sessions list snapshot (`current` feeds containsCurrent). * @param workspaces - real workspaces in stable Host order. * @param view - local expansion arrays and search query. @@ -259,7 +160,6 @@ export function deriveGroups( ): GroupNode[] { const q = view.query.trim().toLowerCase() const expandedProjects = new Set(view.expandedProjects) - const expandedSessions = new Set(view.expandedSessions) const currentGroup = list.current === undefined ? undefined : (workspaces.find(w => w.sessionIds.includes(list.current as SessionId))?.workspaceId as string | undefined) @@ -274,24 +174,24 @@ export function deriveGroups( cwd: g.cwd, createdAt: g.createdAt, label: g.label, - sessionCount: g.summaries.size, + sessionCount: g.sessions.length, expanded, containsCurrent: g.key === currentGroup, - sessions: expanded ? buildVisible(g, expandedSessions) : [], + sessions: expanded ? g.sessions.map(sessionNode) : [], }) } else { - const visible = searchVisible(g, q) - if (visible.size === 0 && !g.label.toLowerCase().includes(q)) continue + const matches = g.sessions.filter(session => sessionTitle(session).toLowerCase().includes(q)) + if (matches.length === 0 && !g.label.toLowerCase().includes(q)) continue groups.push({ key: g.key, workspaceId: g.workspaceId, cwd: g.cwd, createdAt: g.createdAt, label: g.label, - sessionCount: g.summaries.size, - expanded: visible.size > 0, + sessionCount: g.sessions.length, + expanded: matches.length > 0, containsCurrent: g.key === currentGroup, - sessions: buildSearch(g, visible), + sessions: matches.map(sessionNode), }) } } @@ -301,9 +201,8 @@ export function deriveGroups( /** * Derive the flat session list ("In one list" mode): every session — fork * children included — as a top-level row, strictly newest-first. No grouping, - * no parent/child adjacency; rows reuse SessionNode with children always - * empty so the renderer stays branch-free. Search mode filters by - * case-insensitive display-title substring. + * no parent/child adjacency. Search mode filters by case-insensitive + * display-title substring. * @param list - sessions list snapshot. * @param view - the search query (expansion state does not apply). * @returns flat rows in render order. @@ -318,7 +217,7 @@ export function deriveFlat(list: SessionListState, view: Pick rows.push(s) } rows.sort(byRecency) - return rows.map(s => sessionNode(s, [], false, false)) + return rows.map(sessionNode) } /** diff --git a/packages/client/ui-workspace/tests/rows.spec.tsx b/packages/client/ui-workspace/tests/rows.spec.tsx index 44a311d6d3..3be85a7646 100644 --- a/packages/client/ui-workspace/tests/rows.spec.tsx +++ b/packages/client/ui-workspace/tests/rows.spec.tsx @@ -56,46 +56,22 @@ describe('workspace browser rows', () => { expect(onToggle).toHaveBeenCalledOnce() }) - it('renders and operates selected, running, recursive Session nodes', () => { - const child: SessionNode = { - id: sid('child'), title: 'Child', children: [], hasChildren: false, - expanded: false, running: false, updatedAt: 0, - } - const parent: SessionNode = { - id: sid('parent'), title: 'Parent', children: [child], hasChildren: true, - expanded: true, running: true, updatedAt: 0, + it('renders and opens a selected running Session row', () => { + const node: SessionNode = { + id: sid('session'), title: 'Session', running: true, updatedAt: 0, } const onOpen = vi.fn() - const onToggle = vi.fn() - const view = render( - , + render( + , ) - const parentRow = screen.getByText('Parent').closest('[role="treeitem"]')! - const childRow = screen.getByText('Child').closest('[role="treeitem"]')! - expect(parentRow.getAttribute('aria-selected')).toBe('true') - expect(parentRow.getAttribute('aria-expanded')).toBe('true') - expect(childRow.getAttribute('aria-selected')).toBe('false') - expect(childRow.hasAttribute('aria-expanded')).toBe(false) - - fireEvent.click(screen.getByRole('button', { name: 'Collapse' })) - expect(onToggle).toHaveBeenCalledWith(parent.id) - expect(onOpen).not.toHaveBeenCalled() - fireEvent.click(parentRow) - fireEvent.click(childRow) - expect(onOpen.mock.calls).toEqual([[parent.id], [child.id]]) - - view.rerender( - , - ) - expect(screen.getByRole('button', { name: 'Expand' })).toBeTruthy() - expect(screen.getByRole('treeitem').getAttribute('aria-selected')).toBe('false') - expect(screen.getByRole('treeitem').style.paddingLeft).toBe('24px') + const row = screen.getByRole('treeitem') + expect(row.getAttribute('aria-selected')).toBe('true') + expect(row.hasAttribute('aria-expanded')).toBe(false) + expect(screen.queryByRole('button', { name: /Expand|Collapse/ })).toBeNull() + fireEvent.click(row) + expect(onOpen).toHaveBeenCalledWith(node.id) }) it('workspace row menu opens on the ellipsis, renames, and shows the danger delete row', () => { @@ -161,11 +137,10 @@ describe('workspace browser rows', () => { const onRename = vi.fn() const onFork = vi.fn() const node: SessionNode = { - id: sid('s1'), title: 'One', children: [], hasChildren: false, - expanded: false, running: false, updatedAt: 0, + id: sid('s1'), title: 'One', running: false, updatedAt: 0, } - render() + render() fireEvent.click(screen.getByRole('button', { name: 'Session actions for One' })) expect(onOpen).not.toHaveBeenCalled() expect(screen.getByRole('menuitem', { name: 'Delete session' }).className).toMatch(/danger/) @@ -187,25 +162,14 @@ describe('workspace browser rows', () => { expect(screen.queryByRole('menu')).toBeNull() }) - it('flat variant renders no twist even for a parent and ignores toggling', () => { - const node: SessionNode = { - id: sid('p'), title: 'Parent', children: [], hasChildren: true, - expanded: false, running: false, updatedAt: 0, - } - render() - expect(screen.queryByRole('button', { name: 'Expand' })).toBeNull() - }) - it('shows the hover card after the dwell and suppresses it while the row menu is open', () => { vi.useFakeTimers() try { const node: SessionNode = { - id: sid('s1'), title: 'Hovered', children: [], hasChildren: false, - expanded: false, running: true, updatedAt: 0, + id: sid('s1'), title: 'Hovered', running: true, updatedAt: 0, } - render() + render() const wrapper = screen.getByRole('treeitem').parentElement as HTMLElement fireEvent.pointerEnter(wrapper) act(() => { vi.advanceTimersByTime(500) }) @@ -228,11 +192,10 @@ describe('workspace browser rows', () => { vi.useFakeTimers() try { const node: SessionNode = { - id: sid('s1'), title: 'Quiet', children: [], hasChildren: false, - expanded: false, running: false, updatedAt: 0, + id: sid('s1'), title: 'Quiet', running: false, updatedAt: 0, } - render() + render() fireEvent.pointerEnter(screen.getByRole('treeitem').parentElement as HTMLElement) act(() => { vi.advanceTimersByTime(500) }) expect(screen.getByText('Idle')).toBeTruthy() @@ -244,13 +207,12 @@ describe('workspace browser rows', () => { it('draggable row wires start/end and gates hover/drop on an active same-group drag', () => { const node: SessionNode = { - id: sid('s1'), title: 'Drag me', children: [], hasChildren: false, - expanded: false, running: false, updatedAt: 0, + id: sid('s1'), title: 'Drag me', running: false, updatedAt: 0, } const inactive = dragProps() const { rerender } = render( - , + , ) const row = screen.getByRole('treeitem') stubRect(row) @@ -267,8 +229,8 @@ describe('workspace browser rows', () => { const active = dragProps({ active: true, marker: 'before' }) rerender( - , + , ) stubRect(screen.getByRole('treeitem')) // Top half hovers/drops 'before'; bottom half 'after' (row mid = 117). @@ -281,8 +243,8 @@ describe('workspace browser rows', () => { const after = dragProps({ active: true, marker: 'after' }) rerender( - , + , ) expect(screen.getByRole('treeitem').className).toMatch(/dropAfter/) }) diff --git a/packages/client/ui-workspace/tests/tree.spec.ts b/packages/client/ui-workspace/tests/tree.spec.ts index eb34f633d8..aa5828e8ac 100644 --- a/packages/client/ui-workspace/tests/tree.spec.ts +++ b/packages/client/ui-workspace/tests/tree.spec.ts @@ -21,7 +21,7 @@ const workspace = (id: string, sessionIds: string[]): WorkspaceView => ({ sessionIds: sessionIds.map(sid), createdAt: '2026-01-01T00:00:00.000Z', updatedAt: '2026-01-01T00:00:00.000Z', }) const view = (expandedProjects: readonly string[] = [], query = '') => ({ - expandedProjects, expandedSessions: [] as string[], query, + expandedProjects, query, }) describe('deriveGroups', () => { @@ -74,7 +74,7 @@ describe('deriveGroups', () => { expect(groups[0]!.sessionCount).toBe(1) }) - it('builds, sorts, expands, and cycle-guards an ungrouped session tree', () => { + it('ignores fork lineage and sorts every ungrouped session as a top-level row', () => { const parent = summary('parent', 1) const oldChild = { ...summary('old-child', 10), parentId: parent.id } const newChild = { ...summary('new-child', 20), parentId: parent.id } @@ -87,15 +87,13 @@ describe('deriveGroups', () => { const groups = deriveGroups( list(parent, oldChild, newChild, tieB, tieA, self, orphan, cycleA, cycleB), [], - { expandedProjects: [UNGROUPED_KEY], expandedSessions: [parent.id, cycleA.id, cycleB.id], query: '' }, + { expandedProjects: [UNGROUPED_KEY], query: '' }, ) expect(groups).toHaveLength(1) expect(groups[0]!.sessions.map(node => node.id)).toEqual([ - sid('orphan'), sid('self'), parent.id, sid('cycle-a'), - ]) - expect(groups[0]!.sessions[2]!.children.map(node => node.id)).toEqual([ newChild.id, tieA.id, tieB.id, oldChild.id, + cycleB.id, cycleA.id, orphan.id, self.id, parent.id, ]) // Equal timestamps use ids as a deterministic tiebreak in either input order. @@ -113,7 +111,7 @@ describe('deriveGroups', () => { expect(groups[0]!.sessions.map(node => node.id)).toEqual([sid('present')]) }) - it('searches descendants with ancestors and handles cycles, self parents, and label-only hits', () => { + it('searches rows independently of lineage and keeps label-only hits', () => { const root = { ...summary('root', 1), displayTitle: 'Ancestor' } const match = { ...summary('match', 2), displayTitle: 'Needle child', parentId: root.id } const sibling = { ...summary('sibling', 3), displayTitle: 'Other child', parentId: root.id } @@ -124,8 +122,8 @@ describe('deriveGroups', () => { const sessions = list(root, match, sibling, self, orphan, cycleA, cycleB) const groups = deriveGroups(sessions, [workspace('project', sessions.ids)], view([], 'needle')) - expect(groups[0]!.sessions.flatMap(node => [node.id, ...node.children.map(child => child.id)])).toEqual([ - root.id, match.id, self.id, orphan.id, cycleA.id, cycleB.id, + expect(groups[0]!.sessions.map(node => node.id)).toEqual([ + match.id, self.id, orphan.id, cycleA.id, cycleB.id, ]) const labelOnly = deriveGroups( @@ -157,8 +155,6 @@ describe('deriveFlat', () => { const tieA = summary('tie-a', 20) const rows = deriveFlat(list(parent, child, tieB, tieA), { query: '' }) expect(rows.map(row => row.id)).toEqual([sid('child'), sid('tie-a'), sid('tie-b'), sid('parent')]) - // Rows are branch-free: no children, no expansion. - expect(rows.every(row => row.children.length === 0 && !row.hasChildren && !row.expanded)).toBe(true) }) it('search filters by case-insensitive display-title substring', () => { diff --git a/packages/client/ui-workspace/tests/workspace-browser.spec.tsx b/packages/client/ui-workspace/tests/workspace-browser.spec.tsx index d0535ecdfa..a6603593cc 100644 --- a/packages/client/ui-workspace/tests/workspace-browser.spec.tsx +++ b/packages/client/ui-workspace/tests/workspace-browser.spec.tsx @@ -125,7 +125,7 @@ describe('WorkspaceBrowser', () => { expect(screen.queryByText('alpha-s')).toBeNull() }) - it('unfolds a session subtree through the row twist', () => { + it('renders a fork child as a top-level row without a session twist', () => { const parent = summary('parent-s', 2) const child = { ...summary('child-s', 1), parentId: parent.id } mount({ @@ -133,11 +133,9 @@ describe('WorkspaceBrowser', () => { useWorkspaces: hook(workspaceState([workspace('alpha', ['parent-s', 'child-s'])])), }) fireEvent.click(screen.getByText('alpha')) - expect(screen.queryByText('child-s')).toBeNull() - fireEvent.click(screen.getByRole('button', { name: 'Expand' })) expect(screen.getByText('child-s')).toBeTruthy() - fireEvent.click(screen.getByRole('button', { name: 'Collapse' })) - expect(screen.queryByText('child-s')).toBeNull() + expect(screen.queryByRole('button', { name: /Expand|Collapse/ })).toBeNull() + expect(screen.getByText('child-s').closest('[role="treeitem"]')?.getAttribute('draggable')).toBe('true') }) it('auto-expands the selected session group and starts a session from the group ＋', () => { From 213de9a7373529f45e7969b903c96f8dbe82d86c Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Thu, 30 Jul 2026 20:30:02 +0800 Subject: [PATCH 18/24] feat(ui-conversation): wire assistant session forks --- ...6-07-27-web-session-fork-actions.i18n.yaml | 6 ++++ .../2026-07-27-web-session-fork-actions.md | 33 +++++++++++++++++++ .../2026-07-27-web-session-fork-actions.zh.md | 33 +++++++++++++++++++ ...b-message-icon-actions-and-clock.i18n.yaml | 4 +-- ...7-29-web-message-icon-actions-and-clock.md | 6 ++-- ...9-web-message-icon-actions-and-clock.zh.md | 6 ++-- apps/web/tests/message-actions.e2e.ts | 8 +++-- .../message-actions/fork.expected.md | 5 +-- .../src/client/chat/AssistantMarkdown.tsx | 7 +++- .../src/client/chat/ChatView.tsx | 2 ++ .../src/client/chat/MessageIconActions.tsx | 4 +-- .../ui-conversation/tests/chat-view.spec.tsx | 10 ++++++ 12 files changed, 107 insertions(+), 17 deletions(-) create mode 100644 .agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.i18n.yaml create mode 100644 .agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.md create mode 100644 .agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.zh.md diff --git a/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.i18n.yaml b/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.i18n.yaml new file mode 100644 index 0000000000..976dcc1d1d --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.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/2026-07-27-web-session-fork-actions.md +2026-07-27-web-session-fork-actions.md: 90d2f9a8085cf1f1d2656bb442eee1e4116bb91a +2026-07-27-web-session-fork-actions.zh.md: f0642d17fdb6030dea16ff1440c730c605fec13d diff --git a/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.md b/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.md new file mode 100644 index 0000000000..90d2f9a808 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.md @@ -0,0 +1,33 @@ +# Agent Note: Web session fork actions + +Status: implemented + +English | [中文](2026-07-27-web-session-fork-actions.zh.md) + +## Problem + +The Session store already provides a fork primitive that creates a child session from a completed-turn prefix, but the Web client has no unified interaction contract. The Session-row menu can express only “branch from the latest completed turn,” while message IconActions need to express “branch from the turn containing this message”; if the two entry points independently interpret the boundary, switching, and failure behavior, the same user action acquires two sets of semantics. Nesting a fork child beneath its source session also makes the newly selected child visible only while its ancestors are expanded and weakens the workspace manual-order model. + +## Decision + +The Web Session-row menu and message IconActions share the client runtime's `sessions.fork` action. A Session row passes `{ sessionId }`, so it forks at the source session's last completed turn; a user message or settled assistant content message passes `{ sessionId, atSeq: node.seq }`, so it forks at the turn containing that event. On success, the client first adds the child session to its local list and then opens it; on failure, it leaves the source session and current selection unchanged. + +`forkAt(seq)` touches the session service only in ui-conversation's apply injection layer; message components report only the event `seq`. Session rows likewise initiate the operation only through ui-workspace's injected callback. Neither presentation package owns session mutation state or duplicates the host's boundary evaluation. + +Session lineage is not projected into a list hierarchy. WorkSpace mode displays source sessions and all fork children as peer rows in the manual order from `WorkspaceView.sessionIds`; every row can be opened, searched, and dragged independently. In one list mode continues to sort strictly by `updatedAt`; the Ungrouped group also sorts by recency when no workspace ledger is available. `parentId` remains available for lineage, tool presentation, and later queries, but does not control session-list visibility. + +## Alternatives considered + +**Wire only the Session-row menu.** Rejected: at a message, the user has already selected more precise context; forcing them back to the list can only degrade the boundary to the latest completed turn, while the visible message branch icon would remain non-responsive. + +**Allow branching only from user messages.** Rejected: settled assistant content also has a stable event `seq`, and the host places it in its containing completed turn; making only one of two visually identical branch buttons work would create an invisible behavioral difference. + +**Nest fork children beneath their source by `parentId`.** Rejected: lineage is not navigation ownership; nesting requires automatic ancestor expansion to reveal the current item and prevents children from participating in the workspace's peer manual order. + +**Call the session service directly from message components.** Rejected: client components must not touch `ctx` or business services; injected callbacks keep mutation in the apply world and leave components driven purely by props. + +## Consequences + +Users can create forks from Session rows, user messages, or settled assistant content messages; all three entry points ultimately use the same runtime/host operation. Message entry points preserve the exact event boundary, while the list entry point preserves the “latest completed turn” shortcut. Every fork child immediately appears as an ordinary peer row, so the list no longer needs session expansion state, recursive nodes, or twist controls. + +Fork failures stay silent and preserve the source selection, preventing a derivation action from disrupting the current reading position; this tradeoff also means the UI does not yet expose a failure reason or retry entry point. Package tests separately pin the two message `seq` paths and the peer-list derivation; `apps/web/tests/message-actions.e2e.ts` exercises assistant-message branching and Session-row menu branching through the assembled application. diff --git a/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.zh.md b/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.zh.md new file mode 100644 index 0000000000..f0642d17fd --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.zh.md @@ -0,0 +1,33 @@ +# Agent Note: Web session fork 操作 + +Status: implemented + +[English](2026-07-27-web-session-fork-actions.md) | 中文 + +## Problem + +Session store 已提供按完成轮前缀创建子会话的 fork 原语，但 Web 端没有一份统一的交互契约。Session 行菜单只能表达「从最新完成轮分支」，消息 IconActions 还需要表达「从这条消息所在轮分支」；如果两处各自解释边界、切换与失败行为，同一个用户动作会形成两套语义。把 fork 子会话嵌套在源会话下还会让新选中的子会话依赖祖先展开态才能看见，并削弱 workspace 的手动排序模型。 + +## Decision + +Web 的 session 行菜单与消息 IconActions 共用 client runtime 的 `sessions.fork` 操作。Session 行传 `{ sessionId }`，因此在源会话最后一个已完成轮次处分支；用户消息与已定稿 assistant 内容消息传 `{ sessionId, atSeq: node.seq }`，因此在包含该事件的轮次处分支。成功后 client 先把子会话纳入本地列表，再打开子会话；失败时保持源会话与当前选择不变。 + +`forkAt(seq)` 只在 ui-conversation 的 apply 注入层接触 session 服务，消息组件只回传事件 `seq`。Session 行同理只通过 ui-workspace 的注入回调发起操作；两个呈现包都不持有 session mutation 状态，也不复制 host 的边界求值。 + +Session lineage 不投影成列表层级。WorkSpace 模式按 `WorkspaceView.sessionIds` 的手动序把源会话与所有 fork 子会话显示为同级行，每行都可独立打开、搜索和拖拽；In one list 模式继续按 `updatedAt` 严格排序；Ungrouped 组在没有 workspace 账本时也按 recency 排序。`parentId` 仍用于 lineage、工具呈现和后续查询，但不控制 session 列表可见性。 + +## Alternatives considered + +**只接 session 行菜单。** 否决：用户在消息处已经选择了更精确的上下文，强迫其回到列表只能退化为最新完成轮，且已展示的消息分支图标会成为无响应控件。 + +**只允许用户消息分支。** 否决：已定稿 assistant 内容同样有稳定事件 `seq`，host 会把它归入所属完成轮；让两个外观相同的分支按钮只有一个可用会制造不可见的行为差异。 + +**按 `parentId` 把 fork 子会话嵌套在源会话下。** 否决：lineage 不是导航所有权；嵌套要求自动展开祖先才能看见当前项，并让子会话无法参与 workspace 的同级手动排序。 + +**由消息组件直接调用 session 服务。** 否决：client 组件不得接触 `ctx` 或业务服务；注入回调让 mutation 留在 apply 世界，组件保持纯 props。 + +## Consequences + +用户可从 session 行、用户消息或已定稿 assistant 内容消息创建分支，三处最终走同一个 runtime/host 操作；消息点位保留精确事件边界，列表点位保留「最新完成轮」快捷语义。所有 fork 子会话立即作为普通同级行出现，列表不再需要 session 展开状态、递归节点或 twist 控件。 + +Fork 失败保持静默并保留源选择，避免一个派生操作破坏当前阅读位置；该取舍也意味着 UI 暂不提供失败原因或重试入口。Package tests 分别钉住两种消息 `seq` 与同级列表派生，`apps/web/tests/message-actions.e2e.ts` 通过装配后的应用执行 assistant 消息分支与 session 行菜单分支。 diff --git a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.i18n.yaml b/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.i18n.yaml index de8869a96a..f2e1183fe5 100644 --- a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.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/2026-07-29-web-message-icon-actions-and-clock.md -2026-07-29-web-message-icon-actions-and-clock.md: e79662056792c3ab413468ad038dec40455be767 -2026-07-29-web-message-icon-actions-and-clock.zh.md: 72d3b4e0cda19438f2f46fd402b3b76de3726ae5 +2026-07-29-web-message-icon-actions-and-clock.md: ccc9b127d2fcf276fa415ec0ede8b062e45f3df5 +2026-07-29-web-message-icon-actions-and-clock.zh.md: fb4b82a22478b2de38755368ec48a5dca420e79d diff --git a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.md b/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.md index e796620567..ccc9b127d2 100644 --- a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.md +++ b/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.md @@ -12,7 +12,7 @@ The web chat user bubble already had copy / branch / edit IconActions but no clo **User bubbles prepend a date-aware local clock to the existing IconActions row; finalized assistant *content* nodes (non-empty text blocks) append a copy / branch / clock row with `margin-top: 16px`; both seats stay visible whenever mounted and re-format at the next local midnight.** -Both seats format `node.time` through `formatMessageClock`: same calendar day → `HH:mm`, earlier this year → `M月D日 HH:mm`, other years → `YYYY年M月D日 HH:mm`. `useCalendarDay` is a component-local day tick (timeout to the next local midnight) so memoized rows re-render when the calendar day changes without a new framework hook. `MessageItem` places the label before copy (figma `388:20051`). `AssistantMarkdown` places it after branch (figma `43:32997`) only when `streaming` is false, the event time is known, and the node has non-empty text content; Think-only nodes and the streaming tail omit the row. Copy writes joined text blocks. Branch stays a chrome stub. Clipboard write and the clock helpers live in `message-chrome.ts`. The assembled surface is pinned by `apps/web/tests/message-actions.e2e.ts` (cold-seeded history + aria golden); aria normalization collapses every clock shape to `{{clock}}`. +Both seats format `node.time` through `formatMessageClock`: same calendar day → `HH:mm`, earlier this year → `M月D日 HH:mm`, other years → `YYYY年M月D日 HH:mm`. `useCalendarDay` is a component-local day tick (timeout to the next local midnight) so memoized rows re-render when the calendar day changes without a new framework hook. `MessageItem` places the label before copy (figma `388:20051`). `AssistantMarkdown` places it after branch (figma `43:32997`) only when `streaming` is false, the event time is known, and the node has non-empty text content; Think-only nodes and the streaming tail omit the row. Copy writes joined text blocks. Both message rows pass their event's `seq` to the same fork callback; [Web session fork actions](2026-07-27-web-session-fork-actions.md) define the real mutation contract. Clipboard write and the clock helpers live in `message-chrome.ts`. The assembled surface is pinned by `apps/web/tests/message-actions.e2e.ts` (cold-seeded history + aria golden); aria normalization collapses every clock shape to `{{clock}}`. ## Alternatives considered @@ -22,10 +22,10 @@ Both seats format `node.time` through `formatMessageClock`: same calendar day **Hover-reveal the action row on hover-capable pointers.** Rejected: once the row exists it should stay discoverable; opacity hiding made the chrome easy to miss and required parent hover selectors that duplicated the mount gate. -**Wire branch to a real session fork.** Rejected for this change: same rationale as the archived [user IconActions note](../../archived/feature/2026-07-27-user-message-icon-actions.md) — the mutation path is unspecified; the button reserves the design seat. +**Let the IconActions decision also define session fork semantics.** Rejected: this note owns only message chrome, clocks, and mount gating; boundary selection, failure behavior, and switching semantics belong to the separate [Web session fork actions](2026-07-27-web-session-fork-actions.md), keeping presentation components from becoming a second home for session mutation. **Publish the calendar day through a chat store or inject hook.** Rejected: the day tick is presentation-only local state with no cross-entry consumers; a component-local timeout matches the client rule that behavioral hooks may own state that does not subscribe to an external source. ## Consequences -Settled assistant content answers expose copy and the event clock as soon as the row mounts; Think-only nodes stay chrome-free; branch stays a stub. User and assistant clocks share the same day/year widening rules and refresh after midnight without a message mutation. Per-message paging remains a deferred footer seat in the package README. Package tests pin the three clock shapes, the midnight widen, and the content-only assistant gate; the web e2e scenario pins the assembled IconActions chrome. +Settled assistant content answers expose copy, branch, and the event clock as soon as the row mounts; Think-only nodes stay chrome-free. User and assistant clocks share the same day/year widening rules and refresh after midnight without a message mutation. Per-message paging remains a deferred footer seat in the package README. Package tests pin the three clock shapes, the midnight widen, the content-only assistant gate, and the respective event `seq` values passed by the user and assistant branch buttons; the web e2e scenario pins the assembled IconActions chrome. diff --git a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.zh.md b/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.zh.md index 72d3b4e0cd..fb4b82a224 100644 --- a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.zh.md +++ b/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.zh.md @@ -12,7 +12,7 @@ Web 聊天的用户气泡已有复制／分支／编辑 IconActions，但没有 **用户气泡在既有 IconActions 行前追加感知日期的本地时钟；已定稿的 assistant *内容*节点（非空 text 块）在正文下追加带 `margin-top: 16px` 的复制／分支／时钟；两边只要挂载就保持可见，并在下一个本地午夜重新格式化。** -两边都通过 `formatMessageClock` 格式化 `node.time`：同一日历日 → `HH:mm`，同年更早 → `M月D日 HH:mm`，跨年 → `YYYY年M月D日 HH:mm`。`useCalendarDay` 是组件本地的日刻度（定时到下一个本地午夜），因此 memo 行在日历日变化时会重渲染，且不新增框架 hook。`MessageItem` 把标签放在复制之前（figma `388:20051`）。`AssistantMarkdown` 把它放在分支之后（figma `43:32997`），且仅在 `streaming` 为 false、已知事件时间、且节点含非空 text 内容时渲染；纯 Think 节点与流式尾部省略该行。复制写入拼接后的 text 块。分支仍是 chrome stub。剪贴板写入与时钟辅助函数放在 `message-chrome.ts`。组装面由 `apps/web/tests/message-actions.e2e.ts`（冷 seed 历史 + aria golden）钉住；aria 归一化把每种时钟形态折叠为 `{{clock}}`。 +两边都通过 `formatMessageClock` 格式化 `node.time`：同一日历日 → `HH:mm`，同年更早 → `M月D日 HH:mm`，跨年 → `YYYY年M月D日 HH:mm`。`useCalendarDay` 是组件本地的日刻度（定时到下一个本地午夜），因此 memo 行在日历日变化时会重渲染，且不新增框架 hook。`MessageItem` 把标签放在复制之前（figma `388:20051`）。`AssistantMarkdown` 把它放在分支之后（figma `43:32997`），且仅在 `streaming` 为 false、已知事件时间、且节点含非空 text 内容时渲染；纯 Think 节点与流式尾部省略该行。复制写入拼接后的 text 块。两种消息行都把自己的事件 `seq` 交给同一个 fork 回调；真实 mutation 契约由 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)定义。剪贴板写入与时钟辅助函数放在 `message-chrome.ts`。组装面由 `apps/web/tests/message-actions.e2e.ts`（冷 seed 历史 + aria golden）钉住；aria 归一化把每种时钟形态折叠为 `{{clock}}`。 ## 曾考虑的方案 @@ -22,10 +22,10 @@ Web 聊天的用户气泡已有复制／分支／编辑 IconActions，但没有 **在具备 hover 能力的指针上用 hover 才揭示操作行。** 否决：行一旦存在就应保持可发现；用 opacity 隐藏容易漏看，且需要父级 hover 选择器重复挂载门控。 -**把分支接到真实的会话 fork。** 本次否决：与已归档的[用户 IconActions 笔记](../../archived/feature/2026-07-27-user-message-icon-actions.md)同一理由——变更路径尚未规定；按钮只预留设计座位。 +**由 IconActions 决策同时定义 session fork 语义。** 否决：本笔记只拥有消息 chrome、时钟与挂载门控；边界选择、失败行为和切换语义属于独立的 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)，避免展示组件成为 session mutation 的第二正家。 **通过 chat store 或 inject hook 发布日历日。** 否决：日刻度只是展示层本地状态，没有跨入口消费者；组件本地 timeout 符合「行为 hook 可拥有不订阅外部源的状态」这一客户端规则。 ## 后果 -已定稿的 assistant 内容回答在行挂载后立刻暴露复制与事件时钟；纯 Think 节点不带 chrome；分支仍为 stub。用户与 assistant 时钟共用同一套跨天／跨年加宽规则，并在午夜后无需消息变更即可刷新。逐消息分页仍是包 README 中的暂缓 footer 座位。包级测试钉住三种时钟形态、午夜加宽与 assistant 仅内容门控；Web e2e 场景钉住组装后的 IconActions chrome。 +已定稿的 assistant 内容回答在行挂载后立刻暴露复制、分支与事件时钟；纯 Think 节点不带 chrome。用户与 assistant 时钟共用同一套跨天／跨年加宽规则，并在午夜后无需消息变更即可刷新。逐消息分页仍是包 README 中的暂缓 footer 座位。包级测试钉住三种时钟形态、午夜加宽、assistant 仅内容门控，以及 user/assistant 分支按钮各自传递的事件 `seq`；Web e2e 场景钉住组装后的 IconActions chrome。 diff --git a/apps/web/tests/message-actions.e2e.ts b/apps/web/tests/message-actions.e2e.ts index 679fdfbc65..9b02c5bc73 100644 --- a/apps/web/tests/message-actions.e2e.ts +++ b/apps/web/tests/message-actions.e2e.ts @@ -89,7 +89,9 @@ describe('web e2e: message IconActions and clocks on settled history', () => { it.skipIf(MODE === 'record')('forks through the settled-message and session-row actions', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-message-fork')) - await page.getByRole('button', { name: '在新对话中分支' }).first().click() + // Exercise the assistant action specifically; package coverage pins the + // user action separately at its own event seq. + await page.getByRole('button', { name: '在新对话中分支' }).last().click() await expect.poll( () => scaffold.ctx.agents.list().find(agent => agent.session.header.parentSession === SessionId(SEED_ID)), { timeout: 15_000 }, @@ -104,7 +106,9 @@ describe('web e2e: message IconActions and clocks on settled history', () => { ).toBe(1) // The row action owns a distinct ui-workspace injection from the message // action above, so exercise both through the loaded app before capture. - const sourceRow = page.locator('[role="treeitem"][aria-expanded="true"]').last() + const sourceRow = page.locator('[role="treeitem"]') + .filter({ has: page.locator('button[aria-label^="Session actions for "]') }) + .last() const rowBox = await sourceRow.boundingBox() if (rowBox === null) throw new Error('fork source row has no layout box') const actionButton = sourceRow.locator('button[aria-label^="Session actions for "]') diff --git a/apps/web/tests/snapshots/message-actions/fork.expected.md b/apps/web/tests/snapshots/message-actions/fork.expected.md index 5255632c3a..8e07129bfd 100644 --- a/apps/web/tests/snapshots/message-actions/fork.expected.md +++ b/apps/web/tests/snapshots/message-actions/fork.expected.md @@ -2,9 +2,6 @@ - treeitem "Ungrouped 3 sessions" [expanded]: - img - text: Ungrouped 3 sessions - - treeitem "Collapse Use the read tool twice 1min" [expanded]: - - button "Collapse": - - img - - text: Use the read tool twice 1min - treeitem "Use the read tool twice now" [selected] - treeitem "Use the read tool twice now" + - treeitem "Use the read tool twice 1min" diff --git a/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.tsx b/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.tsx index 904aeee0d8..7de69083ac 100644 --- a/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.tsx +++ b/packages/client/ui-conversation/src/client/chat/AssistantMarkdown.tsx @@ -23,6 +23,10 @@ export interface AssistantMarkdownProps { interrupted?: boolean | undefined /** Unix epoch ms for the finalized IconActions clock; omitted while streaming. */ time?: number | undefined + /** Event sequence used as the fork boundary; omitted while streaming. */ + seq?: number | undefined + /** Fork the session through the turn containing this finalized message. */ + onFork?: ((seq: number) => void) | undefined } function firstLine(text: string): string { @@ -60,7 +64,7 @@ function ThinkRow({ text, running }: { text: string; running: boolean }) { } export const AssistantMarkdown = memo(function AssistantMarkdown({ - blocks, streaming, interrupted, time, + blocks, streaming, interrupted, time, seq, onFork, }: AssistantMarkdownProps) { const last = blocks.length - 1 // Tool-call heads render as tool rows in the chat view's grouping pass, so @@ -91,6 +95,7 @@ export const AssistantMarkdown = memo(function AssistantMarkdown({ text={copyText(blocks)} time={time} clock="end" + onBranch={onFork === undefined || seq === undefined ? undefined : () => { onFork(seq) }} className={css.actions} /> )} diff --git a/packages/client/ui-conversation/src/client/chat/ChatView.tsx b/packages/client/ui-conversation/src/client/chat/ChatView.tsx index 68b9b71cb8..2941348eb1 100644 --- a/packages/client/ui-conversation/src/client/chat/ChatView.tsx +++ b/packages/client/ui-conversation/src/client/chat/ChatView.tsx @@ -377,6 +377,8 @@ export function ChatView({ useSession, useSessions, useStore, renderSlot, sessio streaming={false} interrupted={node.interrupted} time={node.time} + seq={node.seq} + onFork={forkAt} /> ) } diff --git a/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx b/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx index 124371f2da..3075c258a6 100644 --- a/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx +++ b/packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx @@ -1,5 +1,5 @@ // Shared IconActions chrome for user and assistant messages: copy live, -// branch wired through onBranch (stub without it), date-aware clock, +// branch wired through onBranch, date-aware clock, // optional edit stub. import { useCallback } from 'react' @@ -19,7 +19,7 @@ export interface MessageIconActionsProps { clock: 'start' | 'end' /** When true, append the stub edit control (user bubble). */ edit?: boolean | undefined - /** Fork the session at this message; absent leaves the branch control a stub. */ + /** Fork the session at this message. */ onBranch?: (() => void) | undefined /** Parent layout class composed onto the actions row. */ className?: string | undefined diff --git a/packages/client/ui-conversation/tests/chat-view.spec.tsx b/packages/client/ui-conversation/tests/chat-view.spec.tsx index 960f954d61..59025b6b21 100644 --- a/packages/client/ui-conversation/tests/chat-view.spec.tsx +++ b/packages/client/ui-conversation/tests/chat-view.spec.tsx @@ -196,6 +196,16 @@ describe('ChatView', () => { expect(view.getByText('run a')).toBeTruthy() }) + it('forks from both user and finalized assistant message actions at their event seq', () => { + const h = makeHarness({ nodes: [user(1, 'question'), assistant(2, 'answer')] }) + const view = render() + const buttons = view.getAllByRole('button', { name: '在新对话中分支' }) + expect(buttons).toHaveLength(2) + fireEvent.click(buttons[0]!) + fireEvent.click(buttons[1]!) + expect(h.forkAt.mock.calls).toEqual([[1], [2]]) + }) + it('renders assistant Markdown across history, streaming, final, and interrupted states while user text stays literal', () => { const markdown = '# Rendered\n\n- **one**\n- `two`' const h = makeHarness({ nodes: [user(1, markdown), assistant(2, markdown)] }) From 3b370549a1a5d526cdf65a969c45120cb0f7f473 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Thu, 30 Jul 2026 21:16:02 +0800 Subject: [PATCH 19/24] feat(client): increment forked session titles --- ...6-07-27-web-session-fork-actions.i18n.yaml | 4 +- .../2026-07-27-web-session-fork-actions.md | 6 +- .../2026-07-27-web-session-fork-actions.zh.md | 6 +- apps/web/tests/message-actions.e2e.ts | 4 +- .../message-actions/fork.expected.md | 4 +- packages/client/runtime/README.i18n.yaml | 4 +- packages/client/runtime/README.md | 2 +- packages/client/runtime/README.zh.md | 2 +- .../runtime/src/client/contract/sessions.ts | 8 ++- .../runtime/src/client/sessions/service.ts | 47 ++++++++++++-- .../runtime/tests/sessions-service.spec.ts | 65 ++++++++++++++++++- packages/client/test-runtime/src/sessions.ts | 4 +- .../test-runtime/tests/runtime.spec.tsx | 6 +- .../client/ui-conversation/README.i18n.yaml | 4 +- packages/client/ui-conversation/README.md | 2 +- packages/client/ui-conversation/README.zh.md | 2 +- .../ui-conversation/src/client/apply.ts | 4 +- .../tests/apply-inject.spec.tsx | 7 ++ packages/client/ui-workspace/README.i18n.yaml | 4 +- packages/client/ui-workspace/README.md | 2 +- packages/client/ui-workspace/README.zh.md | 2 +- .../client/ui-workspace/src/client/index.ts | 4 +- .../client/ui-workspace/tests/apply.spec.ts | 18 ++++- 23 files changed, 167 insertions(+), 44 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.i18n.yaml b/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.i18n.yaml index 976dcc1d1d..e4b5cd7778 100644 --- a/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.md -2026-07-27-web-session-fork-actions.md: 90d2f9a8085cf1f1d2656bb442eee1e4116bb91a -2026-07-27-web-session-fork-actions.zh.md: f0642d17fdb6030dea16ff1440c730c605fec13d +2026-07-27-web-session-fork-actions.md: b5dc7e820de069a68b38ed87c7d29ffbdb4867bc +2026-07-27-web-session-fork-actions.zh.md: 774cd74d69eb02d43ca01c8ec7ba1cf94c24b1dc diff --git a/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.md b/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.md index 90d2f9a808..b5dc7e820d 100644 --- a/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.md +++ b/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.md @@ -10,7 +10,7 @@ The Session store already provides a fork primitive that creates a child session ## Decision -The Web Session-row menu and message IconActions share the client runtime's `sessions.fork` action. A Session row passes `{ sessionId }`, so it forks at the source session's last completed turn; a user message or settled assistant content message passes `{ sessionId, atSeq: node.seq }`, so it forks at the turn containing that event. On success, the client first adds the child session to its local list and then opens it; on failure, it leaves the source session and current selection unchanged. +The Web Session-row menu and message IconActions share the client runtime's `sessions.fork` action. A Session row passes `{ sessionId, increaseTitle: true }`, so it forks at the source session's last completed turn; a user message or settled assistant content message passes `{ sessionId, atSeq: node.seq, increaseTitle: true }`, so it forks at the turn containing that event. Only the client consumes `increaseTitle`: after adding the child session to its local list, the client increments a trailing `(N)` or `（N）` in the source session's persisted title without changing bracket style, appends ` (1)` to an unnumbered title, and skips the rename when no persisted title exists; the Host fork request still contains only `sessionId` and the optional `atSeq`. The caller opens the child only after the rename succeeds; a fork or rename failure leaves the source session and current selection unchanged, while a child created before a rename failure remains in the list. `forkAt(seq)` touches the session service only in ui-conversation's apply injection layer; message components report only the event `seq`. Session rows likewise initiate the operation only through ui-workspace's injected callback. Neither presentation package owns session mutation state or duplicates the host's boundary evaluation. @@ -28,6 +28,6 @@ Session lineage is not projected into a list hierarchy. WorkSpace mode displays ## Consequences -Users can create forks from Session rows, user messages, or settled assistant content messages; all three entry points ultimately use the same runtime/host operation. Message entry points preserve the exact event boundary, while the list entry point preserves the “latest completed turn” shortcut. Every fork child immediately appears as an ordinary peer row, so the list no longer needs session expansion state, recursive nodes, or twist controls. +Users can create forks from Session rows, user messages, or settled assistant content messages; all three entry points ultimately use the same runtime/host operation. Message entry points preserve the exact event boundary, while the list entry point preserves the “latest completed turn” shortcut. Successive fork titles increment through `(1)`, `(2)`, and so on instead of repeatedly appending `(1)`; titles with fullwidth parentheses retain that style. Every fork child immediately appears as an ordinary peer row, so the list no longer needs session expansion state, recursive nodes, or twist controls. -Fork failures stay silent and preserve the source selection, preventing a derivation action from disrupting the current reading position; this tradeoff also means the UI does not yet expose a failure reason or retry entry point. Package tests separately pin the two message `seq` paths and the peer-list derivation; `apps/web/tests/message-actions.e2e.ts` exercises assistant-message branching and Session-row menu branching through the assembled application. +Fork and child-rename failures stay silent and preserve the source selection, preventing a derivation action from disrupting the current reading position; this tradeoff also means the UI does not yet expose a failure reason or retry entry point. Package tests separately pin the two message `seq` paths, title increments, and the peer-list derivation; `apps/web/tests/message-actions.e2e.ts` exercises assistant-message branching and Session-row menu branching through the assembled application. diff --git a/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.zh.md b/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.zh.md index f0642d17fd..774cd74d69 100644 --- a/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.zh.md +++ b/.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.zh.md @@ -10,7 +10,7 @@ Session store 已提供按完成轮前缀创建子会话的 fork 原语，但 We ## Decision -Web 的 session 行菜单与消息 IconActions 共用 client runtime 的 `sessions.fork` 操作。Session 行传 `{ sessionId }`，因此在源会话最后一个已完成轮次处分支；用户消息与已定稿 assistant 内容消息传 `{ sessionId, atSeq: node.seq }`，因此在包含该事件的轮次处分支。成功后 client 先把子会话纳入本地列表，再打开子会话；失败时保持源会话与当前选择不变。 +Web 的 session 行菜单与消息 IconActions 共用 client runtime 的 `sessions.fork` 操作。Session 行传 `{ sessionId, increaseTitle: true }`，因此在源会话最后一个已完成轮次处分支；用户消息与已定稿 assistant 内容消息传 `{ sessionId, atSeq: node.seq, increaseTitle: true }`，因此在包含该事件的轮次处分支。`increaseTitle` 只由 client 消费：子会话进入本地列表后，client 把源会话持久化标题尾部的 `(N)` 或 `（N）` 递增并保留括号样式，无编号时追加 ` (1)`，没有持久化标题时不改名；Host fork 请求仍只有 `sessionId` 与可选的 `atSeq`。改名成功后调用方才打开子会话；fork 或改名失败时保持源会话与当前选择不变，改名失败时已创建的子会话仍留在列表中。 `forkAt(seq)` 只在 ui-conversation 的 apply 注入层接触 session 服务，消息组件只回传事件 `seq`。Session 行同理只通过 ui-workspace 的注入回调发起操作；两个呈现包都不持有 session mutation 状态，也不复制 host 的边界求值。 @@ -28,6 +28,6 @@ Session lineage 不投影成列表层级。WorkSpace 模式按 `WorkspaceView.se ## Consequences -用户可从 session 行、用户消息或已定稿 assistant 内容消息创建分支，三处最终走同一个 runtime/host 操作；消息点位保留精确事件边界，列表点位保留「最新完成轮」快捷语义。所有 fork 子会话立即作为普通同级行出现，列表不再需要 session 展开状态、递归节点或 twist 控件。 +用户可从 session 行、用户消息或已定稿 assistant 内容消息创建分支，三处最终走同一个 runtime/host 操作；消息点位保留精确事件边界，列表点位保留「最新完成轮」快捷语义。连续 fork 的标题按 `(1)`、`(2)` 递增，而不是重复追加 `(1)`；全角括号标题保持全角样式。所有 fork 子会话立即作为普通同级行出现，列表不再需要 session 展开状态、递归节点或 twist 控件。 -Fork 失败保持静默并保留源选择，避免一个派生操作破坏当前阅读位置；该取舍也意味着 UI 暂不提供失败原因或重试入口。Package tests 分别钉住两种消息 `seq` 与同级列表派生，`apps/web/tests/message-actions.e2e.ts` 通过装配后的应用执行 assistant 消息分支与 session 行菜单分支。 +Fork 与子会话改名失败都保持静默并保留源选择，避免一个派生操作破坏当前阅读位置；该取舍也意味着 UI 暂不提供失败原因或重试入口。Package tests 分别钉住两种消息 `seq`、标题递增与同级列表派生，`apps/web/tests/message-actions.e2e.ts` 通过装配后的应用执行 assistant 消息分支与 session 行菜单分支。 diff --git a/apps/web/tests/message-actions.e2e.ts b/apps/web/tests/message-actions.e2e.ts index 9b02c5bc73..650c089d32 100644 --- a/apps/web/tests/message-actions.e2e.ts +++ b/apps/web/tests/message-actions.e2e.ts @@ -106,9 +106,7 @@ describe('web e2e: message IconActions and clocks on settled history', () => { ).toBe(1) // The row action owns a distinct ui-workspace injection from the message // action above, so exercise both through the loaded app before capture. - const sourceRow = page.locator('[role="treeitem"]') - .filter({ has: page.locator('button[aria-label^="Session actions for "]') }) - .last() + const sourceRow = page.locator('[role="treeitem"][aria-selected="true"]') const rowBox = await sourceRow.boundingBox() if (rowBox === null) throw new Error('fork source row has no layout box') const actionButton = sourceRow.locator('button[aria-label^="Session actions for "]') diff --git a/apps/web/tests/snapshots/message-actions/fork.expected.md b/apps/web/tests/snapshots/message-actions/fork.expected.md index 8e07129bfd..d20754711d 100644 --- a/apps/web/tests/snapshots/message-actions/fork.expected.md +++ b/apps/web/tests/snapshots/message-actions/fork.expected.md @@ -2,6 +2,6 @@ - treeitem "Ungrouped 3 sessions" [expanded]: - img - text: Ungrouped 3 sessions - - treeitem "Use the read tool twice now" [selected] - - treeitem "Use the read tool twice now" + - treeitem "Use the read tool twice (2) now" [selected] + - treeitem "Use the read tool twice (1) now" - treeitem "Use the read tool twice 1min" diff --git a/packages/client/runtime/README.i18n.yaml b/packages/client/runtime/README.i18n.yaml index 4ef6fd488c..e82da5cc62 100644 --- a/packages/client/runtime/README.i18n.yaml +++ b/packages/client/runtime/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/runtime/README.md -README.md: db6388dccee6e065066cc70e141073d99822ce0f -README.zh.md: e1b6902d0d30972bd613553081e0f0e8d5da2a05 +README.md: b85deeec92fd4da1f342b5536757692f594853a5 +README.zh.md: 2dbb66c56ad5687fb299fe030d0abfe451004a62 diff --git a/packages/client/runtime/README.md b/packages/client/runtime/README.md index db6388dcce..b85deeec92 100644 --- a/packages/client/runtime/README.md +++ b/packages/client/runtime/README.md @@ -30,7 +30,7 @@ SlotsService gives the renderer separate bare observables for `useSessions` and ## Session forking -`ISessions.fork({sessionId, atSeq?})` resolves only after the child summary is locally addressable, carrying source lineage and cwd with `blank: false`; callers choose whether to open it. A `workspace-attach-failed` response still identifies a child already published by the Host, so `SessionManager` reconciles that partial success before `SessionForkError` reaches the caller instead of making a retry create a duplicate child. +`ISessions.fork({sessionId, atSeq?, increaseTitle?})` resolves only after the child summary is locally addressable, carrying source lineage and cwd with `blank: false`; callers choose whether to open it. With `increaseTitle: true`, the client renames the child from the source session's persisted title: a trailing `(N)` or `（N）` is incremented without changing bracket style, while any other title gets ` (1)` appended; the rename is skipped when the source has no persisted title, and a rename failure rejects the promise but leaves the created child in place. This option is not sent in the Host fork request. A `workspace-attach-failed` response still identifies a child already published by the Host, so `SessionManager` reconciles that partial success before `SessionForkError` reaches the caller instead of making a retry create a duplicate child. ## Session model selection diff --git a/packages/client/runtime/README.zh.md b/packages/client/runtime/README.zh.md index e1b6902d0d..2dbb66c56a 100644 --- a/packages/client/runtime/README.zh.md +++ b/packages/client/runtime/README.zh.md @@ -30,7 +30,7 @@ SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸 ## 会话 fork -`ISessions.fork({sessionId, atSeq?})` 只在子会话摘要已能在本地寻址后才完成；该摘要携带源会话的谱系和 cwd，且 `blank: false`，由调用方决定是否打开。即使响应为 `workspace-attach-failed`，其中仍会标识 Host 已发布的子会话，因此 `SessionManager` 会先将这一部分成功对账，再让 `SessionForkError` 到达调用方，避免重试创建重复的子会话。 +`ISessions.fork({sessionId, atSeq?, increaseTitle?})` 只在子会话摘要已能在本地寻址后才完成；该摘要携带源会话的谱系和 cwd，且 `blank: false`，由调用方决定是否打开。`increaseTitle: true` 会在 client 端把源会话的持久化标题改名到子会话：尾部 `(N)` 或 `（N）` 递增并保留括号样式，其余标题追加 ` (1)`；源会话没有持久化标题时跳过改名，改名失败时拒绝 promise 但保留已创建的子会话。该选项不会进入 Host fork 请求。即使响应为 `workspace-attach-failed`，其中仍会标识 Host 已发布的子会话，因此 `SessionManager` 会先将这一部分成功对账，再让 `SessionForkError` 到达调用方，避免重试创建重复的子会话。 ## 会话模型选择 diff --git a/packages/client/runtime/src/client/contract/sessions.ts b/packages/client/runtime/src/client/contract/sessions.ts index 1b59c3c27c..280bc602eb 100644 --- a/packages/client/runtime/src/client/contract/sessions.ts +++ b/packages/client/runtime/src/client/contract/sessions.ts @@ -32,12 +32,14 @@ export interface ISessions { /** * Fork a session from a completed-turn prefix of the source; on resolution * the child is in the list store and `open()` can target it. - * @param opts - source session id and the optional event seq anchoring the + * @param opts - source session id, the optional event seq anchoring the * cut (the boundary is the first turn/end at or after it; an in-log - * anchor in an open turn is unavailable rather than clipped backward). + * anchor in an open turn is unavailable rather than clipped backward), + * and whether to increment an inherited durable title before resolving. * @returns the child session id. + * @throws when the fork fails, or when a requested child-title rename fails after creation. */ - fork(opts: { sessionId: SessionId; atSeq?: number }): Promise + fork(opts: { sessionId: SessionId; atSeq?: number; increaseTitle?: boolean }): Promise /** * Register a per-session standard-props provider (hooks become `use` * selector hooks on the render side; props spread verbatim). diff --git a/packages/client/runtime/src/client/sessions/service.ts b/packages/client/runtime/src/client/sessions/service.ts index 741aba4c24..342fc3b62e 100644 --- a/packages/client/runtime/src/client/sessions/service.ts +++ b/packages/client/runtime/src/client/sessions/service.ts @@ -137,6 +137,24 @@ function displayTitleOf(title: string | undefined, cwd: string | undefined, id: return id } +/** + * Increment a trailing fork number while preserving its half-width or + * full-width parentheses; an unnumbered title starts with ` (1)`. + * @param title - source session's durable title. + * @returns the title assigned to the fork child. + */ +function increasedForkTitle(title: string): string { + const ascii = /^(.*?)\((\d+)\)$/u.exec(title) + if (ascii?.[1] !== undefined && ascii[2] !== undefined) { + return `${ascii[1]}(${BigInt(ascii[2]) + 1n})` + } + const fullWidth = /^(.*?)（(\d+)）$/u.exec(title) + if (fullWidth?.[1] !== undefined && fullWidth[2] !== undefined) { + return `${fullWidth[1]}（${BigInt(fullWidth[2]) + 1n}）` + } + return `${title} (1)` +} + interface ScopeRecord { fiber: Fiber ctx: Context @@ -337,17 +355,36 @@ export class SessionsService implements ISessions { * Fork a session from a completed-turn prefix of the source (same * synchronous-addressability guarantee as {@link SessionsService.create}: * on resolution the child is in the list store and open() can target it). - * @param opts - source session id and the optional event seq anchoring the + * @param opts - source session id, the optional event seq anchoring the * cut (the boundary is the first turn/end at or after it; an in-log - * anchor in an open turn is unavailable rather than clipped backward). + * anchor in an open turn is unavailable rather than clipped backward), + * and whether to increment an inherited durable title before resolving. * @returns the child session id. * @throws {SessionForkError} with the source id. + * @throws {Error} when a requested child-title rename fails after creation. */ - async fork(opts: { sessionId: SessionId; atSeq?: number }): Promise { - const result = await this.manager.fork(opts) + async fork(opts: { + sessionId: SessionId + atSeq?: number + increaseTitle?: boolean + }): Promise { + const sourceTitle = opts.increaseTitle + ? this.list.getSnapshot().byId[opts.sessionId]?.title + : undefined + const result = await this.manager.fork({ + sessionId: opts.sessionId, + ...(opts.atSeq === undefined ? {} : { atSeq: opts.atSeq }), + }) if (!result.ok) throw new SessionForkError(result.error, opts.sessionId) this.projectList() - return result.value.sessionId + const childId = result.value.sessionId + if (sourceTitle !== undefined) { + const child = this.binding(childId)?.session + if (child === undefined) throw new Error(`fork child "${childId}" is not locally addressable`) + const renamed = await child.rename(increasedForkTitle(sourceTitle)) + if (!renamed.ok) throw new Error(`fork child rename failed: ${renamed.error.code}: ${renamed.error.message}`) + } + return childId } /** diff --git a/packages/client/runtime/tests/sessions-service.spec.ts b/packages/client/runtime/tests/sessions-service.spec.ts index 09076bace7..8687f208f0 100644 --- a/packages/client/runtime/tests/sessions-service.spec.ts +++ b/packages/client/runtime/tests/sessions-service.spec.ts @@ -10,7 +10,7 @@ import { Context } from 'cordis' import { afterEach, describe, expect, it, vi } from 'vitest' import type { SessionId } from '@deepseek-ai/dsh-client-connection/client' import { SessionCreateError, SessionsService, scopeOf } from '../src/client/sessions/service.ts' -import { FakeApiClient, deferred, ok } from './fake-api.ts' +import { FakeApiClient, deferred, err, ok } from './fake-api.ts' const sid = (s: string): SessionId => s as SessionId @@ -399,6 +399,69 @@ describe('create', () => { }) }) +describe('fork', () => { + it.each([ + ['Roadmap', 'Roadmap (1)'], + ['Roadmap (1)', 'Roadmap (2)'], + ['计划（1）', '计划（2）'], + ['计划 （9）', '计划 （10）'], + ])('increments the durable title %j after the child is published', async (sourceTitle, childTitle) => { + const b = bench() + b.svc.handleMuxEnvelope({ + rpcId: 'source-title' as never, + payload: { type: 'session/projection', sessionId: sid('source'), key: 'title', value: sourceTitle, seq: 2 } as never, + }) + await feedList(b, [{ id: 'source', cwd: '/work' }]) + b.api.onFork = () => Promise.resolve(ok({ sessionId: sid('child') })) + b.api.onRename = (payload) => { + const { title } = payload as { title: string } + return Promise.resolve(ok({ title, seq: 3 })) + } + + await expect(b.svc.fork({ + sessionId: sid('source'), atSeq: 7, increaseTitle: true, + })).resolves.toBe('child') + + expect(b.api.callsOf('session.fork')).toEqual([{ sessionId: 'source', atSeq: 7 }]) + expect(b.api.callsOf('session.rename')).toEqual([{ sessionId: 'child', title: childTitle }]) + await Promise.resolve() + expect(b.svc.list.getSnapshot().byId[sid('child')]).toMatchObject({ + title: childTitle, + displayTitle: childTitle, + parentId: 'source', + }) + }) + + it('does not rename without the title policy or a durable source title', async () => { + const b = bench() + await feedList(b, [{ id: 'source', cwd: '/work' }]) + b.api.onFork = () => Promise.resolve(ok({ sessionId: sid('child') })) + await expect(b.svc.fork({ sessionId: sid('source'), increaseTitle: true })).resolves.toBe('child') + expect(b.api.callsOf('session.rename')).toEqual([]) + + b.api.onFork = () => Promise.resolve(ok({ sessionId: sid('child-2') })) + await expect(b.svc.fork({ sessionId: sid('source') })).resolves.toBe('child-2') + expect(b.api.callsOf('session.rename')).toEqual([]) + }) + + it('rejects when child rename fails while keeping the published child addressable', async () => { + const b = bench() + b.svc.handleMuxEnvelope({ + rpcId: 'source-title' as never, + payload: { type: 'session/projection', sessionId: sid('source'), key: 'title', value: 'Roadmap', seq: 2 } as never, + }) + await feedList(b, [{ id: 'source' }]) + b.api.onFork = () => Promise.resolve(ok({ sessionId: sid('child') })) + b.api.onRename = () => Promise.resolve(err({ + code: 'title-invalid', message: 'rejected', details: { sessionId: sid('child') }, + })) + + await expect(b.svc.fork({ sessionId: sid('source'), increaseTitle: true })) + .rejects.toThrow('fork child rename failed: title-invalid: rejected') + expect(b.svc.binding(sid('child'))).toBeDefined() + }) +}) + describe('scope lifecycle rides the list mirror (entity parity: no client-side pre-birth)', () => { it('a session-added frame births the row (blank) and makes the scope resolvable; removal prunes it', async () => { const b = bench() diff --git a/packages/client/test-runtime/src/sessions.ts b/packages/client/test-runtime/src/sessions.ts index f585772b38..f40f9a14a5 100644 --- a/packages/client/test-runtime/src/sessions.ts +++ b/packages/client/test-runtime/src/sessions.ts @@ -395,10 +395,10 @@ export class TestSessions implements ISessions { /** * Recorded fork stub: no child materializes (benches asserting the full * fork flow drive the production service; this face only proves the call). - * @param opts - source session id and optional cut anchor. + * @param opts - source session id, optional cut anchor, and client title policy. * @returns the source id (no child record is created). */ - fork(opts: { sessionId: SessionId; atSeq?: number }): Promise { + fork(opts: { sessionId: SessionId; atSeq?: number; increaseTitle?: boolean }): Promise { this.calls.push({ method: 'fork', args: [opts] }) return Promise.resolve(opts.sessionId) } diff --git a/packages/client/test-runtime/tests/runtime.spec.tsx b/packages/client/test-runtime/tests/runtime.spec.tsx index eddc6efe76..62bab2845a 100644 --- a/packages/client/test-runtime/tests/runtime.spec.tsx +++ b/packages/client/test-runtime/tests/runtime.spec.tsx @@ -211,11 +211,13 @@ describe('sessions', () => { runtime.sessions.clear() await runtime.flush() expect(runtime.sessions.list.getSnapshot().current).toBeUndefined() - await expect(runtime.sessions.fork({ sessionId: 's1' as SessionId, atSeq: 7 })).resolves.toBe('s1') + await expect(runtime.sessions.fork({ + sessionId: 's1' as SessionId, atSeq: 7, increaseTitle: true, + })).resolves.toBe('s1') expect(runtime.sessions.calls).toEqual([ { method: 'open', args: ['s1'] }, { method: 'clear', args: [] }, - { method: 'fork', args: [{ sessionId: 's1', atSeq: 7 }] }, + { method: 'fork', args: [{ sessionId: 's1', atSeq: 7, increaseTitle: true }] }, ]) await runtime.dispose() }) diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml index d5d1dcfbfb..086c63f2ad 100644 --- a/packages/client/ui-conversation/README.i18n.yaml +++ b/packages/client/ui-conversation/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-conversation/README.md -README.md: 02834be207e45bb1ff65b75a0c75a884db3be315 -README.zh.md: 84f9d79660207a68305d75ac0e7deaecdedf00d6 +README.md: 95f336b9bce82cbf6daf0fdb016f52de9b13c8d5 +README.zh.md: 948da361400a1207fcc582b3d874ab7fb98f27de diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md index 02834be207..95f336b9bc 100644 --- a/packages/client/ui-conversation/README.md +++ b/packages/client/ui-conversation/README.md @@ -38,7 +38,7 @@ None; this package neither assembles nor sends a provider request. - **Stats-line durations cover the in-window flow only** — LLM and tool wall times fold the snapshot's assistant `timing` and tool call/result pairs, so nodes outside the loaded event window (older history) are not counted. - **Details panel is the minimal form and currently has no entry point** — selected call args/result raw display; the Input/Output/Metadata switch, Prev/Next stepping, and See-in-trajectory deep link are deferred. Tool rows stopped being details-panel click targets and nothing replaced that gesture, so `ChatViewInjected.openDetails` is implemented but uncalled and the panel (including its terminal card) is unreachable in the assembled application; its rendering stays covered by mounting it with a selection directly. -- **Assistant per-message paging is a reserved slot** — drawn in the design, not implemented. The finalized content IconActions row (copy / branch / clock) ships under text output only; branch forks through the turn containing that message and opens the child, while a fork failure leaves the source selected. +- **Assistant per-message paging is a reserved slot** — drawn in the design, not implemented. The finalized content IconActions row (copy / branch / clock) ships under text output only; branch forks through the turn containing that message, increments the inherited title on the client, and then opens the child, while a fork or rename failure leaves the source selected. - **The sparkle icon for the others tool row is a hand-drawn approximation** — the design glyph's vector geometry is not exportable locally; promotion into ui-primitives waits on an exact export. - **The approval panel's "Always allow this type" is deferred** — durable grants need a grant-storage design; only allow-once/reject answer today. - **TodoPanel truncates long item text to one ellipsized line** — the figma strip has no wrap or expand affordance; full text is not readable inline. diff --git a/packages/client/ui-conversation/README.zh.md b/packages/client/ui-conversation/README.zh.md index 84f9d79660..948da36140 100644 --- a/packages/client/ui-conversation/README.zh.md +++ b/packages/client/ui-conversation/README.zh.md @@ -38,7 +38,7 @@ todo 两个面就是在该形状上的两个注册项，都是普通注册方插 - **统计行的耗时只覆盖窗口内消息流**：LLM（大语言模型）与工具墙钟时间由快照的 assistant `timing` 与工具 call/result 配对折算，落在已加载事件窗口之外的节点（更早的历史）不计入。 - **详情面板是最小形态，且当前没有入口**：以原始形式显示已选择调用的参数／结果；Input/Output/Metadata 切换、Prev/Next 步进与 See-in-trajectory 深链接暂缓实现。工具行已不再是详情面板的点击目标，且没有任何手势接替它，因此 `ChatViewInjected.openDetails` 虽已实现却无人调用，该面板（含其终端卡片）在组装后的应用中不可达；其渲染仍由直接以选中态挂载它来覆盖。 -- **assistant 逐消息分页是预留 slot**：设计中已有图稿，尚未实现。已定稿的内容 IconActions 行（复制／分支／时钟）只挂在 text 输出下；分支会 fork 到包含该消息的轮次末尾并打开子会话，而 fork 失败时源会话保持选中。 +- **assistant 逐消息分页是预留 slot**：设计中已有图稿，尚未实现。已定稿的内容 IconActions 行（复制／分支／时钟）只挂在 text 输出下；分支会 fork 到包含该消息的轮次末尾，在 client 端递增继承标题后打开子会话，而 fork 或改名失败时源会话保持选中。 - **others 工具行的闪光图标是手绘近似版本**：无法在本地导出设计字形的矢量几何；等到存在精确导出后再将其提升到 ui-primitives。 - **审批面板的「始终允许此类」暂缓**：持久授权需要授权存储设计；今天只能回答允许一次／拒绝。 - **TodoPanel 将过长条目截成单行省略号**：figma 条没有换行或展开入口，完整文本无法在行内读完。 diff --git a/packages/client/ui-conversation/src/client/apply.ts b/packages/client/ui-conversation/src/client/apply.ts index ca0159ce3d..9c2008f092 100644 --- a/packages/client/ui-conversation/src/client/apply.ts +++ b/packages/client/ui-conversation/src/client/apply.ts @@ -263,10 +263,10 @@ export function apply(ctx: Context): void { }, loadOlder: () => { void scoped.loadOlder() }, forkAt: (seq) => { - sessions.fork({ sessionId, atSeq: seq }) + sessions.fork({ sessionId, atSeq: seq, increaseTitle: true }) .then((childId) => { sessions.open(childId) }) .catch(() => { - // Fork failure keeps the source view untouched (composer-stop posture). + // Fork or child-rename failure keeps the source view untouched. }) }, } diff --git a/packages/client/ui-conversation/tests/apply-inject.spec.tsx b/packages/client/ui-conversation/tests/apply-inject.spec.tsx index 87ec0dfde7..c9dd4c37f9 100644 --- a/packages/client/ui-conversation/tests/apply-inject.spec.tsx +++ b/packages/client/ui-conversation/tests/apply-inject.spec.tsx @@ -122,6 +122,13 @@ describe('conversation slot inject surface', () => { const chatView = b.chatViewSurface(ROOT) chatView.injected.loadOlder() expect(b.sessionFake.loadOlder).toHaveBeenCalledTimes(1) + chatView.injected.forkAt(17) + await vi.waitFor(() => { + expect(b.runtime.sessions.calls).toContainEqual({ method: 'open', args: [ROOT] }) + }) + expect(b.runtime.sessions.calls).toContainEqual({ + method: 'fork', args: [{ sessionId: ROOT, atSeq: 17, increaseTitle: true }], + }) await b.runtime.dispose() }) diff --git a/packages/client/ui-workspace/README.i18n.yaml b/packages/client/ui-workspace/README.i18n.yaml index 1223fcc0f9..a50419efb6 100644 --- a/packages/client/ui-workspace/README.i18n.yaml +++ b/packages/client/ui-workspace/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-workspace/README.md -README.md: 2a4e544250756db50b19bc101c19ac79505a3d6c -README.zh.md: 7ae2b0e196a98d1375e9073146bb8119ea8cbe90 +README.md: 860c24b8a25a1e9968261f586c16163579131a1c +README.zh.md: 5a8e88051fc6f4fd46c5f2f6dcdc185eb4559ac6 diff --git a/packages/client/ui-workspace/README.md b/packages/client/ui-workspace/README.md index 2a4e544250..860c24b8a2 100644 --- a/packages/client/ui-workspace/README.md +++ b/packages/client/ui-workspace/README.md @@ -6,7 +6,7 @@ Shared Workspace picker plugin. `WorkspaceBrowser` is registered into the sideba The picker lists real Host Workspace entities through the global `useWorkspaces` hook. Selecting a Workspace invokes the slot owner's `onPick` callback to retarget the frontend Session object. Each registration declares a **directory-flow child hole** (`single` kind: `conversation.hero.workspace.directoryFlow` / `sidebar.workspaces.directoryFlow`) that the composed picker package's client half fills with its picking interaction — the [`-native`](../../host/directory-picker-native/README.md) backend's renderless OS-chooser driver today, an in-app browsing dialog under a `-browse` composition. The flat **Open local folder...** action renders only while the surface's hole is occupied (occupancy read per menu render; an empty hole means the composition has no picking affordance — the seam's documented no-flow default). This package owns the trigger and the adoption: the occupant reports one picked path per open through the hole's owner conversation (`open`/`busy`/`onPicked`/`onCancel`/`onError`), and the owner adopts it through the object layer, selecting the committed Workspace only after its list projection has refreshed; cancellation is silent, and errors land in the retryable folder dialog whose **Choose again** reopens the flow. **Create a new workspace** retains the name dialog and disables names already present in that list, while the Host remains authoritative for concurrent or non-UI callers. The runtime Session and Workspace services own materialization. The Workspace row's Delete action opens a confirmation that states the retention boundary, blocks duplicate submission, and keeps failures open; success removes the group while its Sessions remain under Ungrouped. The Session row's Rename action opens the same browser-owned dialog pattern prefilled with the row's display title: no client-side conflict rule exists (the host normalizes and may reject with `title-invalid`, rendered in the dialog alert), and confirming an unchanged title is deliberately allowed — it pins the current automatic title against regeneration. -The Session row's Fork action forks at the source's last completed turn and opens the child; the source and child always appear as peer rows within a workspace group, with lineage retained only as session data. A failure leaves the current selection unchanged. +The Session row's Fork action forks at the source's last completed turn, increments the inherited persisted title on the client, and then opens the child; a trailing ASCII or fullwidth parenthesized number is incremented in the same style, while an unnumbered title gets ` (1)` appended. The source and child always appear as peer rows within a workspace group, with lineage retained only as session data. A fork or rename failure leaves the current selection unchanged; after a rename failure, the created child remains in the list. Both target slots are declared by other plugins, so `apply` registers through declaration-aware deferral and re-registers after a declaring slot is restored. diff --git a/packages/client/ui-workspace/README.zh.md b/packages/client/ui-workspace/README.zh.md index 7ae2b0e196..5a8e88051f 100644 --- a/packages/client/ui-workspace/README.zh.md +++ b/packages/client/ui-workspace/README.zh.md @@ -6,7 +6,7 @@ 该选择器通过全局 `useWorkspaces` hook 列出真实的 Host Workspace 实体。选择 Workspace 会调用 slot owner 的 `onPick` 回调，重新定位前端 Session 对象。每个注册各自声明一个**目录流子洞**（`single` kind：`conversation.hero.workspace.directoryFlow`／`sidebar.workspaces.directoryFlow`），由组合的选择器包 client half 填入其选取交互——今天是 [`-native`](../../host/directory-picker-native/README.md) 后端的无渲染 OS 选择器驱动，`-browse` 组合下则是应用内浏览对话框。平铺显示的 **打开本地文件夹…** 操作仅在本表层的洞被占用时渲染（每次菜单渲染读取占用状态；洞为空意味着该组合没有选目录能力——seam 文档化的无流程默认行为）。本包持有触发与接纳：占用者经洞的 owner 会话（`open`/`busy`/`onPicked`/`onCancel`/`onError`）每次打开上报一个所选路径，owner 通过对象层接纳它，并等待 Workspace 列表投影刷新后才选中已提交的 Workspace；取消操作不会显示提示，错误落入可重试的文件夹对话框，其 **重新选择** 会重新打开流程。**创建新工作区** 操作保留名称对话框，并禁用列表中已有的名称，而 Host 对并发或非 UI 调用方仍具有最终决定权。运行时 Session 与 Workspace 服务负责物化。Workspace 行内的 Delete 操作会打开确认框，说明保留边界、阻止重复提交，并在失败时保持打开；成功后，该分组会被移除，其 Session 则留在 Ungrouped 下。Session 行内的 Rename 操作打开同款浏览器持有的对话框，并以该行的显示标题预填：客户端不设名称冲突规则（host 负责规范化，可能以 `title-invalid` 拒绝，错误渲染在对话框告警区）；确认未修改的标题是有意允许的——这正是把当前自动标题钉住、不再被重新生成覆盖的手势。 -Session 行内的 Fork 操作在源会话最后一个已完成轮次处 fork 并打开子会话；源会话与子会话在 workspace 组内始终作为同级行展示，谱系只保留为 session 数据。失败不会改变当前选中项。 +Session 行内的 Fork 操作在源会话最后一个已完成轮次处 fork，在 client 端递增继承的持久化标题后再打开子会话；尾部半角或全角括号编号会原样式递增，无编号标题追加 ` (1)`。源会话与子会话在 workspace 组内始终作为同级行展示，谱系只保留为 session 数据。Fork 或改名失败都不会改变当前选中项，改名失败时已创建的子会话仍会留在列表中。 两个目标 slot 都由其他插件声明，因此 `apply` 通过声明感知的延迟机制完成注册，并在声明该 slot 的插件恢复后重新注册。 diff --git a/packages/client/ui-workspace/src/client/index.ts b/packages/client/ui-workspace/src/client/index.ts index f7ced8016a..79a275eafa 100644 --- a/packages/client/ui-workspace/src/client/index.ts +++ b/packages/client/ui-workspace/src/client/index.ts @@ -60,10 +60,10 @@ export function apply(ctx: ClientContext): void { if (!result.ok) throw new Error(result.error.message) }, forkSession: (sessionId) => { - ctx.sessions.fork({ sessionId }) + ctx.sessions.fork({ sessionId, increaseTitle: true }) .then((childId) => { ctx.sessions.open(childId) }) .catch(() => { - // Fork failure keeps the list untouched (composer-stop posture). + // Fork or child-rename failure keeps the current selection. }) }, renameWorkspace: async (workspaceId, title) => { await ctx.workspaces.rename(workspaceId, title) }, diff --git a/packages/client/ui-workspace/tests/apply.spec.ts b/packages/client/ui-workspace/tests/apply.spec.ts index 817416663e..257f98a1d6 100644 --- a/packages/client/ui-workspace/tests/apply.spec.ts +++ b/packages/client/ui-workspace/tests/apply.spec.ts @@ -19,11 +19,17 @@ async function bench() { const insertSessionBefore = vi.fn(async () => ({})) const open = vi.fn() const clear = vi.fn() + const renameSession = vi.fn(async (title: string) => ({ ok: true, value: { title, seq: 1 } })) + const binding = vi.fn(() => ({ session: { rename: renameSession } })) + const fork = vi.fn(async () => 'forked' as never) ctx.provide('workspaces', { create, startSession, rename, insertSessionBefore, } as never) - ctx.provide('sessions', { open, clear } as never) - return { ctx, slots: ctx.get('slots') as SlotsService, create, startSession, rename, insertSessionBefore, open, clear } + ctx.provide('sessions', { open, clear, binding, fork } as never) + return { + ctx, slots: ctx.get('slots') as SlotsService, create, startSession, rename, + insertSessionBefore, open, clear, renameSession, binding, fork, + } } type HoleName = 'sidebar.workspaces' | 'conversation.hero.workspace' | 'conversation.empty.workspace' @@ -66,6 +72,14 @@ describe('ui-workspace apply', () => { expect(b.startSession).toHaveBeenLastCalledWith(undefined) browser.open('session' as never) expect(b.open).toHaveBeenCalledWith('session') + await browser.renameSession('session' as never, 'renamed session') + expect(b.binding).toHaveBeenCalledWith('session') + expect(b.renameSession).toHaveBeenCalledWith('renamed session') + browser.forkSession('session' as never) + await vi.waitFor(() => { + expect(b.open).toHaveBeenCalledWith('forked') + }) + expect(b.fork).toHaveBeenCalledWith({ sessionId: 'session', increaseTitle: true }) await browser.renameWorkspace('ws' as never, 'renamed') expect(b.rename).toHaveBeenCalledWith('ws', 'renamed') await browser.insertSessionBefore('ws' as never, 's1' as never, 's2' as never) From 30cda487eafd17ee5ee1d77b294f3e3fd7642e59 Mon Sep 17 00:00:00 2001 From: Turtle Date: Thu, 30 Jul 2026 21:34:15 +0800 Subject: [PATCH 20/24] fix(cli): map @deepseek-ai/dsh-tui/prompt to source in tsconfig paths The tui.cordis.yml entry for @deepseek-ai/dsh-tui/prompt had no tsconfig paths mapping: the @deepseek-ai/dsh-* wildcard substitutes tui/prompt whole into nonexistent candidates, so the tsx source launch fell back to package exports and required built lib/prompt.js. pnpm dsh failed at startup on every clean tree (fresh worktrees) with 'plugin(s) failed to load'. --- tsconfig.base.json | 1 + 1 file changed, 1 insertion(+) diff --git a/tsconfig.base.json b/tsconfig.base.json index 527dc44758..801ed2dc66 100644 --- a/tsconfig.base.json +++ b/tsconfig.base.json @@ -58,6 +58,7 @@ "@deepseek-ai/dsh-llm/brand": ["./packages/llm/llm/src/brand.ts"], "@deepseek-ai/dsh-llm/message": ["./packages/llm/llm/src/message.ts"], "@deepseek-ai/dsh-commands/brand": ["./packages/ui/commands/src/brand.ts"], + "@deepseek-ai/dsh-tui/prompt": ["./packages/ui/tui/src/prompt.ts"], "@deepseek-ai/dsh-tools/presentation": ["./packages/core/tools/src/presentation.ts"], "@deepseek-ai/dsh-user-approval/types": ["./packages/ui/user-approval/src/types.ts"], "@deepseek-ai/dsh-user-interaction/types": ["./packages/ui/user-interaction/src/types.ts"], From 37116d0b0adae58e7e6a5b279e8004e9eb7d81a5 Mon Sep 17 00:00:00 2001 From: Turtle Date: Thu, 30 Jul 2026 21:34:23 +0800 Subject: [PATCH 21/24] test(scripts): gate source-plane resolution of configured plugins verify-cordis-config now requires every configured specifier of a local workspace package to resolve through the tsconfig.base.json paths facade to a .ts/.tsx source file. A failed resolution or a .d.ts hit (the exports fallback into built lib/types) fails the gate, so a missing paths mapping is a red gate instead of a clean-tree-only startup crash masked by built trees in CI. Removing the dsh-tui/prompt mapping reproduces the failure. Agent Note records the decision and alternatives. --- ...fig-source-plane-resolution-gate.i18n.yaml | 6 +++ ...dis-config-source-plane-resolution-gate.md | 27 ++++++++++ ...-config-source-plane-resolution-gate.zh.md | 27 ++++++++++ scripts/verify-cordis-config.ts | 52 +++++++++++++++++++ 4 files changed, 112 insertions(+) create mode 100644 .agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.i18n.yaml create mode 100644 .agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.md create mode 100644 .agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.zh.md diff --git a/.agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.i18n.yaml b/.agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.i18n.yaml new file mode 100644 index 0000000000..9b7308098b --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.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/process/2026-07-30-cordis-config-source-plane-resolution-gate.md +2026-07-30-cordis-config-source-plane-resolution-gate.md: f9070d39559948ef27f96df5afccd7c4e076f131 +2026-07-30-cordis-config-source-plane-resolution-gate.zh.md: fac6c4047d334d7dd0685aa270234fee3d15dba8 diff --git a/.agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.md b/.agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.md new file mode 100644 index 0000000000..f9070d3955 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.md @@ -0,0 +1,27 @@ +# Agent Note: verify-cordis-config gates source-plane resolution of configured plugins + +Status: implemented + +English | [中文](2026-07-30-cordis-config-source-plane-resolution-gate.zh.md) + +## Problem + +`apps/cli/config/tui.cordis.yml` gained the `@deepseek-ai/dsh-tui/prompt` entry without a matching tsconfig `paths` mapping. The generic `@deepseek-ai/dsh-*` wildcard substitutes `tui/prompt` whole into its `/*/src` candidates, none of which exist, so the [tsx source launch](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md) fell back to package `exports` and resolved `lib/prompt.js` — an artifact-plane file. Every environment with a built `lib/` (developer trees after `pnpm build`) booted fine, and the e2e workflow runs the keyless TUI PTY smoke in `lib` mode (`DSH_EXAMPLE_MODE=lib`, built bin under plain Node) so CI never exercises the source vector at all — while every clean checkout failed `pnpm dsh` at startup with `plugin(s) failed to load: @deepseek-ai/dsh-tui/prompt`. No gate checked the source plane, so the breakage shipped silently and surfaced only in fresh worktrees. + +## Decision + +`scripts/verify-cordis-config.ts` (`validateSourcePlaneResolution`) requires every configured specifier of a local workspace package — harness packages and vendored Cordis alike — to resolve through the `tsconfig.base.json` `paths` facade to a `.ts`/`.tsx` source file, using `ts.resolveModuleName` from the repository root. A failed resolution or a `.d.ts` hit (the `exports` fallback into built `lib/types`) fails `verify-cordis-config`, naming the config files and the specifier. The missing `@deepseek-ai/dsh-tui/prompt` mapping is added next to the other explicit subpath entries; removing it reproduces the gate failure. + +## Alternatives considered + +**Rely on the keyless TUI PTY smoke.** In default source mode it boots the real tree through the source vector and does catch the failure — but only on a clean tree. CI's e2e workflow runs it exclusively in `lib` mode (the built bin resolving real package `exports`), so no CI line runs the source vector, and developer trees with a stale `lib/` stay masked locally. Adding a source-mode CI smoke proves one composition per run; the static gate covers every shipped and example config. + +**Broaden the `dsh-source-launch-smoke` compat test to full boot.** The node-compat smoke asserts only the TTY refusal, which happens before plugin loading. A full keyless boot per matrix line duplicates the PTY smoke at higher cost and, like it, proves one composition rather than every shipped and example config. + +**A `@deepseek-ai/dsh-*/prompt`-style wildcard mapping.** Fixes this one subpath but not the class; the next single-file subpath export (`/surface`, `/message`, …) regresses identically. The static gate covers all current and future configured specifiers. + +## Consequences + +- A configured workspace specifier that resolves only through built `lib/` is now a red `verify-cordis-config` (in `hygiene` and CI) instead of a clean-tree-only startup crash. +- New single-file subpath exports referenced from a cordis.yml need an explicit `tsconfig.base.json` `paths` entry at introduction time; the gate message says so. +- The gate resolves with `tsconfig.base.json` options only; a specifier needing client-only compiler options to resolve would fail it, which matches the facade's role as the single resolution surface for tsx and vitest. diff --git a/.agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.zh.md b/.agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.zh.md new file mode 100644 index 0000000000..fac6c4047d --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.zh.md @@ -0,0 +1,27 @@ +# Agent Note: verify-cordis-config 对配置中插件的源码面解析实施门禁 + +Status: implemented + +[English](2026-07-30-cordis-config-source-plane-resolution-gate.md) | 中文 + +## 问题 + +`apps/cli/config/tui.cordis.yml` 新增了 `@deepseek-ai/dsh-tui/prompt` 配置项，却没有对应的 tsconfig `paths` 映射。通用的 `@deepseek-ai/dsh-*` 通配符会把 `tui/prompt` 整体代入其 `/*/src` 候选路径，而这些路径全都不存在，因此 [tsx 源码启动](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md)会回退到包（package）的 `exports`，解析出产物面文件 `lib/prompt.js`。任何带有已构建 `lib/` 的环境（开发者目录树运行 `pnpm build` 后）都能正常启动，而 e2e 工作流以 `lib` 模式（`DSH_EXAMPLE_MODE=lib`，构建产物 bin 在普通 Node 下运行）执行无密钥 TUI PTY 冒烟测试，因此 CI 根本不会经过源码启动向量——与此同时，所有干净检出环境中的 `pnpm dsh` 都会在启动时失败，并报错 `plugin(s) failed to load: @deepseek-ai/dsh-tui/prompt`。当时没有门禁检查源码面，因此该故障未被发现便进入发布版本，仅在新的 worktree 中暴露。 + +## 决策 + +`scripts/verify-cordis-config.ts`（`validateSourcePlaneResolution`）要求配置中凡是引用本地 workspace 包的模块说明符（包括 harness 包与纳入 vendor 的 Cordis）都必须通过 `tsconfig.base.json` 的 `paths` 外观层（facade）解析到 `.ts`/`.tsx` 源文件；解析以仓库根目录为起点，调用 `ts.resolveModuleName` 完成。解析失败或命中 `.d.ts`（即经 `exports` 回退到构建出的 `lib/types`）都会使 `verify-cordis-config` 失败，并列出配置文件与模块说明符。缺失的 `@deepseek-ai/dsh-tui/prompt` 映射已添加在其他显式子路径条目旁；删除该映射即可复现门禁失败。 + +## 备选方案 + +**依赖无密钥 TUI PTY 冒烟测试。** 在默认源码模式下，该测试通过源码向量启动真实目录树，确实能捕获这个故障，但仅限干净目录树。CI 的 e2e 工作流只以 `lib` 模式运行它（构建产物 bin 通过真实的包 `exports` 解析），因此没有任何 CI 环节执行源码向量，而带有过期 `lib/` 的开发者目录树在本地也仍被掩盖。为 CI 增加一个源码模式冒烟测试，每次也只能证明一种组合；静态门禁则覆盖所有随产品发布的配置与示例配置。 + +**将 `dsh-source-launch-smoke` 兼容性测试扩展为完整启动。** node-compat 冒烟测试只断言 TTY 拒绝，而该拒绝发生在插件加载之前。每条矩阵版本线都执行一次完整的无密钥启动，会以更高成本重复 PTY 冒烟测试，而且同样只能验证一种组合，无法覆盖所有随产品发布的配置与示例配置。 + +**使用类似 `@deepseek-ai/dsh-*/prompt` 的通配符映射。** 这能修复当前子路径，却不能杜绝这一类问题；下一个单文件子路径导出（`/surface`、`/message` 等）仍会以同样方式复发。静态门禁覆盖当前及未来配置中引用的所有模块说明符。 + +## 结果 + +- 配置中的 workspace 模块说明符若只能通过构建后的 `lib/` 解析，现在会导致 `verify-cordis-config` 门禁失败（在 `hygiene` 和 CI 中执行），而不再成为只在干净目录树中出现的启动崩溃。 +- cordis.yml 中引用新的单文件子路径导出时，必须同步为 `tsconfig.base.json` 添加显式 `paths` 条目；门禁消息会明确提示这一要求。 +- 门禁只使用 `tsconfig.base.json` 的选项执行解析；如果某个模块说明符需要仅客户端可用的编译器选项才能解析，门禁就会失败。这符合该外观层作为 tsx 与 vitest 唯一解析入口的定位。 diff --git a/scripts/verify-cordis-config.ts b/scripts/verify-cordis-config.ts index 1e0127a826..bda0d5ecfc 100644 --- a/scripts/verify-cordis-config.ts +++ b/scripts/verify-cordis-config.ts @@ -60,6 +60,7 @@ for (const file of files) { errors.push(...validateExampleResolution()) errors.push(...validateAppResolution()) +errors.push(...validateSourcePlaneResolution()) if (errors.length > 0) { console.error('verify-cordis-config: invalid Loader metadata or plugin package resolution:') @@ -138,6 +139,57 @@ function validateAppResolution(): string[] { return missingPluginDependencies(references, dependencies, 'apps/cli/package.json') } +/** + * Every configured specifier of a local workspace package must resolve through + * the tsconfig `paths` facade to a `.ts`/`.tsx` source file. The `dsh` source + * launch (tsx) and vitest resolve in the source plane; without a `paths` match + * they fall back to package `exports`, which reach built `lib/` — present on a + * built dev tree, absent on a clean one — so a missing mapping boots locally + * yet breaks every clean checkout. Anything but a `.ts`/`.tsx` hit (a `.d.ts` + * or `.js` under built `lib/`) is that artifact-plane fallback, not source. + */ +function validateSourcePlaneResolution(): string[] { + const violations: string[] = [] + const localPackages = localPackageDirectories() + const config = ts.readConfigFile(resolve(root, 'tsconfig.base.json'), path => ts.sys.readFile(path)) + if (config.error !== undefined) { + throw new Error(ts.flattenDiagnosticMessageText(config.error.messageText, '\n')) + } + const { options, errors: optionErrors } = ts.convertCompilerOptionsFromJson( + (config.config as { compilerOptions?: unknown }).compilerOptions, + root, + 'tsconfig.base.json', + ) + if (optionErrors.length > 0) { + throw new Error(optionErrors.map(error => ts.flattenDiagnosticMessageText(error.messageText, '\n')).join('\n')) + } + // convertCompilerOptionsFromJson leaves `pathsBasePath` unset, so relative + // `paths` targets resolve against the host's current directory; anchor it to + // the repository root to keep the gate cwd-independent. + const host: ts.ModuleResolutionHost = { + fileExists: path => ts.sys.fileExists(path), + readFile: path => ts.sys.readFile(path), + directoryExists: path => ts.sys.directoryExists(path), + getCurrentDirectory: () => root, + } + const sourceExtensions = new Set([ts.Extension.Ts, ts.Extension.Tsx]) + const containingFile = resolve(root, 'scripts/verify-cordis-config.ts') + const locationsBySpecifier = new Map>() + for (const reference of pluginReferences) { + const packageName = packageNameFromSpecifier(reference.name) + if (packageName === undefined || !localPackages.has(packageName)) continue + const locations = locationsBySpecifier.get(reference.name) ?? new Set() + locations.add(reference.file) + locationsBySpecifier.set(reference.name, locations) + } + for (const [specifier, locations] of locationsBySpecifier) { + const resolved = ts.resolveModuleName(specifier, containingFile, options, host).resolvedModule + if (resolved !== undefined && sourceExtensions.has(resolved.extension)) continue + violations.push(`${[...locations].join(', ')}: ${specifier} does not resolve to workspace source through tsconfig.base.json paths (add a mapping so the tsx source launch does not depend on built lib/)`) + } + return violations +} + function missingPluginDependencies( references: readonly PluginReference[], dependencies: Readonly>, From 72220dd821f690bb1d5d1ff4204711a04bf638e5 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 30 Jul 2026 22:17:42 +0800 Subject: [PATCH 22/24] fix(fs-search): drop exhausted glob sample groups Keep only groups with another path in the active round. This bounds skewed sampling by paths visited instead of rescanning every singleton for every late-group item. --- packages/fs/tool-fs-search/src/glob.ts | 28 ++++++++++++------- .../fs/tool-fs-search/tests/tools.spec.ts | 13 +++++++++ 2 files changed, 31 insertions(+), 10 deletions(-) diff --git a/packages/fs/tool-fs-search/src/glob.ts b/packages/fs/tool-fs-search/src/glob.ts index c9806b7bd8..97d0d904bb 100644 --- a/packages/fs/tool-fs-search/src/glob.ts +++ b/packages/fs/tool-fs-search/src/glob.ts @@ -150,27 +150,35 @@ function topLevelSegment(path: string): string { * @returns the page grouped by top-level entry, with the shown/total top-level spread. */ export function sampleAcrossTopLevel(paths: readonly string[], maxItems: number, root = '.'): GlobSample { + type ActiveGroup = { key: string; items: string[]; index: number; current: string } const groups = new Map() + let active: ActiveGroup[] = [] for (const path of paths) { const key = topLevelSegment(relativeToSearchRoot(path, root)) const group = groups.get(key) - if (group === undefined) groups.set(key, [path]) - else group.push(path) + if (group === undefined) { + const items = [path] + groups.set(key, items) + active.push({ key, items, index: 0, current: path }) + } else { + group.push(path) + } } - let rounds = 0 - for (const group of groups.values()) rounds = Math.max(rounds, group.length) const taken = new Map() let count = 0 - for (let round = 0; round < rounds && count < maxItems; round += 1) { - for (const [key, group] of groups) { + while (active.length > 0 && count < maxItems) { + const nextActive: ActiveGroup[] = [] + for (const { key, items, index, current } of active) { if (count >= maxItems) break - const path = group[round] - if (path === undefined) continue count += 1 const bucket = taken.get(key) - if (bucket === undefined) taken.set(key, [path]) - else bucket.push(path) + if (bucket === undefined) taken.set(key, [current]) + else bucket.push(current) + const nextIndex = index + 1 + const nextPath = items[nextIndex] + if (nextPath !== undefined) nextActive.push({ key, items, index: nextIndex, current: nextPath }) } + active = nextActive } return { items: [...taken.values()].flat(), shown: taken.size, total: groups.size } } diff --git a/packages/fs/tool-fs-search/tests/tools.spec.ts b/packages/fs/tool-fs-search/tests/tools.spec.ts index da273ec2a2..5055db7c9c 100644 --- a/packages/fs/tool-fs-search/tests/tools.spec.ts +++ b/packages/fs/tool-fs-search/tests/tools.spec.ts @@ -538,6 +538,19 @@ describe('cross-directory sampling', () => { expect(sampleAcrossTopLevel(paths, 3)).toEqual({ items: ['solo/a', 'many/b', 'many/c'], 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}`), + ] + expect(sampleAcrossTopLevel(paths, paths.length - 1)).toMatchObject({ + shown: singletonCount + 1, + total: singletonCount + 1, + items: { length: paths.length - 1 }, + }) + }, 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 }) From 48b0cb25fd1ad02bcfa63c6246d2b7924c228493 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 30 Jul 2026 22:20:15 +0800 Subject: [PATCH 23/24] fix(fs-search): respect platform path separators Group paths using node:path.sep so POSIX backslashes remain filename characters while Windows continues to treat them as separators. --- .../acp-agent/tests/fixtures/fs-search-bin/rg | 2 ++ .../snapshots/fs-glob-sampling/session.jsonl | 2 +- packages/fs/tool-fs-search/src/glob.ts | 22 ++++++++++++++----- .../fs/tool-fs-search/tests/tools.spec.ts | 20 ++++++++++++++--- 4 files changed, 36 insertions(+), 10 deletions(-) diff --git a/examples/acp-agent/tests/fixtures/fs-search-bin/rg b/examples/acp-agent/tests/fixtures/fs-search-bin/rg index cd5703bbf7..181ad68837 100755 --- a/examples/acp-agent/tests/fixtures/fs-search-bin/rg +++ b/examples/acp-agent/tests/fixtures/fs-search-bin/rg @@ -3,6 +3,8 @@ 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/session.jsonl b/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl index 85ef5dfe1a..8579543459 100644 --- a/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl @@ -11,7 +11,7 @@ {"type":"assistant/chunk","seq":9,"time":1785218400010,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":10,"time":1785218400011,"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":"d8c174b5-2f08-49b3-80d5-a69aabefbd7a"},"usage":{"inputTokens":1,"outputTokens":1}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"} {"type":"tool/call","seq":11,"time":1785218400012,"data":{"turn":1,"step":1,"callId":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\"}"}} -{"type":"tool/result","seq":12,"time":1785218400013,"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\nsrc/index.ts\ndocs/guide.md\ntest/spec.ts\n\n(Showing 4 of 6 paths, sampled across 4 of the 4 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.)"}],"isError":false}],"role":"user","id":"e9711775-0ea5-4383-a562-76a6b49a4742"}},"sourceEventSeqs":[11],"surfaceOp":"append"} +{"type":"tool/result","seq":12,"time":1785218400013,"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":"e9711775-0ea5-4383-a562-76a6b49a4742"}},"sourceEventSeqs":[11],"surfaceOp":"append"} {"type":"step/end","seq":13,"time":1785218400014,"data":{"turn":1,"step":1}} {"type":"step/start","seq":14,"time":1785218400015,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":15,"time":1785218400016,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} diff --git a/packages/fs/tool-fs-search/src/glob.ts b/packages/fs/tool-fs-search/src/glob.ts index 97d0d904bb..d934e76d21 100644 --- a/packages/fs/tool-fs-search/src/glob.ts +++ b/packages/fs/tool-fs-search/src/glob.ts @@ -9,6 +9,7 @@ */ import type { Context } from 'cordis' +import { sep } from 'node:path' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView } from '@deepseek-ai/dsh-tools' import type { SpillRef } from '@deepseek-ai/dsh-spill' @@ -112,16 +113,25 @@ export interface GlobSample { /** Remove the displayed search-root prefix before choosing a top-level group. */ function relativeToSearchRoot(path: string, root: string): string { - if (root === '.') return path.replace(/^\.[\\/]/, '') - const trimmedRoot = root.replace(/[\\/]+$/, '') - if (trimmedRoot.length === 0) return path.replace(/^[\\/]+/, '') + if (root === '.') return path.startsWith(`.${sep}`) ? path.slice(2) : path + let rootEnd = root.length + while (rootEnd > 0 && root[rootEnd - 1] === sep) rootEnd -= 1 + const trimmedRoot = root.slice(0, rootEnd) + if (trimmedRoot.length === 0) return stripLeadingSeparators(path) if (path === trimmedRoot) return '' - if (path.startsWith(`${trimmedRoot}/`) || path.startsWith(`${trimmedRoot}\\`)) { + if (path.startsWith(`${trimmedRoot}${sep}`)) { return path.slice(trimmedRoot.length + 1) } return path } +/** Strip only separators recognized by the execution platform. */ +function stripLeadingSeparators(path: string): string { + let start = 0 + while (path[start] === sep) start += 1 + return path.slice(start) +} + /** * The leading path segment of one display path — the top-level entry, relative * to the search root, that the path sits under. A path with no separator is its @@ -131,8 +141,8 @@ function relativeToSearchRoot(path: string, root: string): string { * empty group. */ function topLevelSegment(path: string): string { - const trimmed = path.replace(/^[\\/]+/, '') - const cut = trimmed.search(/[\\/]/) + const trimmed = stripLeadingSeparators(path) + const cut = trimmed.indexOf(sep) return cut === -1 ? trimmed : trimmed.slice(0, cut) } diff --git a/packages/fs/tool-fs-search/tests/tools.spec.ts b/packages/fs/tool-fs-search/tests/tools.spec.ts index 5055db7c9c..a0d3cdf38c 100644 --- a/packages/fs/tool-fs-search/tests/tools.spec.ts +++ b/packages/fs/tool-fs-search/tests/tools.spec.ts @@ -12,7 +12,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import { join } from 'node:path' +import { join, sep } from 'node:path' 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' @@ -582,14 +582,28 @@ describe('cross-directory sampling', () => { .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(['C:\\root\\a\\one', 'C:\\root\\b\\two'], 2, 'C:\\root')) - .toEqual({ items: ['C:\\root\\a\\one', 'C:\\root\\b\\two'], shown: 2, total: 2 }) + const rooted = [ + ['root', 'a', 'one'].join(sep), + ['root', 'a', 'two'].join(sep), + ['root', 'b', 'three'].join(sep), + ] + 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(['src'], 1, 'src')) .toEqual({ items: ['src'], shown: 1, total: 1 }) }) + it.skipIf(process.platform === 'win32')('treats POSIX backslashes as filename characters', () => { + const paths = ['old\\one', 'old\\two', 'src/a'] + expect(sampleAcrossTopLevel(paths, 2)).toEqual({ + items: ['old\\one', 'old\\two'], + shown: 2, + total: 3, + }) + }) + it('handles more top-level groups than the JavaScript argument limit', () => { const paths = Array.from({ length: 125_000 }, (_, index) => `dir-${index}/file.txt`) expect(sampleAcrossTopLevel(paths, 100)).toMatchObject({ shown: 100, total: 125_000 }) From 58513ee12665e166af1eeed6ab3f3ea1c46a7b68 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 30 Jul 2026 23:42:54 +0800 Subject: [PATCH 24/24] fix(config): map directory picker auto to source --- tsconfig.base.json | 1 + 1 file changed, 1 insertion(+) diff --git a/tsconfig.base.json b/tsconfig.base.json index f5f5c0a3ba..5a69af958d 100644 --- a/tsconfig.base.json +++ b/tsconfig.base.json @@ -121,6 +121,7 @@ "@deepseek-ai/dsh-host-apiproxy": ["./packages/host/apiproxy/src"], "@deepseek-ai/dsh-host-directory-picker": ["./packages/host/directory-picker/src"], "@deepseek-ai/dsh-host-directory-picker/*": ["./packages/host/directory-picker/src/*"], + "@deepseek-ai/dsh-host-directory-picker-auto": ["./packages/host/directory-picker-auto/src"], "@deepseek-ai/dsh-host-directory-picker-browse": ["./packages/host/directory-picker-browse/src"], "@deepseek-ai/dsh-host-directory-picker-browse/*": ["./packages/host/directory-picker-browse/src/*"], "@deepseek-ai/dsh-host-directory-picker-native": ["./packages/host/directory-picker-native/src"],