Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(fs): harden directory listing and glob sampling

Browse Source
This commit is contained in:
NI0317
2026-07-28 13:01:26 +08:00
parent a9c0e00620
commit 717852423f
46 changed files with 480 additions and 219 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/config-catalog.md
View File

@@ -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

16
docs/tool-catalog.md
View File

@@ -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`