description	kind
The model-facing read, read_image, write, and edit tools for users and maintainers composing or debugging filesystem access for agents.	package-reference

@deepseek-ai/dsh-tool-fs

English | 中文

Summary

dsh-tool-fs provides the model-facing filesystem tools — read, read_image, write, and edit — and their executor. With them the model reads files with line numbers, creates or replaces them atomically, and applies targeted literal edits; results are capped and failures carry stable codes with recovery instructions, all backed by a mounted ctx.fs backend. The read-before-edit policy lives in a separate plugin (dsh-fs-observation-policy), so omitting it yields unconditional, still-atomic mutations. read_image appears while a durable attachment store is mounted and refuses execution unless the routed model declares image input. Choose this package when the model should read, create, replace, or edit UTF-8 text files; discovery (glob/grep) is a sibling package.

Use this package
Understand the implementation
Further Exploration
Model Experience
Known Limitations and Deferred Work
Dev Note

Use this package

Mount the tools after a ctx.fs backend and, for read-before-write/edit behavior, the policy plugin. The model then gets line-numbered reads, atomic writes and edits, and — with an attachment store mounted — image reads; every result is capped, and failures carry stable codes with recovery instructions.

Minimal composition

A backend, the policy plugin, then the tools; the attachment store is optional and enables read_image.

- name: '@deepseek-ai/dsh-fs-local'
- name: '@deepseek-ai/dsh-fs-observation-policy'
- name: '@deepseek-ai/dsh-tool-fs'

The policy plugin is optional: without it the tools run against the bare provider (unconditional write, overwrite, and edit with no observed-state). A deployment that loads these tools is expected to also load it, so the behavior is read-before-write/edit. read_image registers only while a durable ctx.attachments service is mounted; execution additionally refuses on a route whose exact model does not declare image input, so a text route's durable history stays free of image blocks.

The tools

Tool	Arguments	Behavior
`read`	`file_path`, `offset?`, `limit?`	Line-numbered UTF-8 content with a pagination footer; `offset` is 1-based and `limit` defaults to and caps at the configured `readLimit`
`read_image`	`file_path`	Reads and persists a PNG/JPEG/WebP/GIF source; normalization can downscale it before the next model request, so the model need not create a thumbnail first
`write`	`file_path`, `content`	Creates or fully replaces a file; with the policy plugin, overwriting requires a prior `read` at the unchanged version, creating does not
`edit`	`file_path`, `old_string`, `new_string`, `replace_all?`	Literal replacement requiring a unique match unless `replace_all` is true; with the policy plugin, requires a prior `read` and an unchanged file

Field names are snake_case to match Claude Code and existing harness tool schemas. Successes return compact envelopes — a read window, an image reference, or a Created file/Updated file confirmation — and write/edit derive replayable diff-card metadata for UI presentation.

Configuration

All keys are optional; the defaults are the shipped read caps.

Key	Default	Meaning
`readLimit`	`2000`	Default and maximum lines returned by one `read` call
`readMaxLineLength`	`2000`	Characters kept per line before truncation
`readMaxBytes`	`51200`	Byte cap on one `read` call's selected lines; overflow ends the window with a capped footer
`readStreamMinSize`	`10485760`	Files at or above this size (or of unknown size) stream instead of loading whole into memory

The generated configuration catalog is the exhaustive source for every accepted field and its JSDoc.

Policy and sandbox behavior

With the policy plugin mounted, write and edit obtain their guard from the fs/* intent slots, so an unread target or a stale observation fails with FS_NOT_OBSERVED or FS_STALE_VERSION and a recovery instruction. Under a confining backend (fs-sandbox), write/edit additionally advertise sandbox_permissions and justification; a denied mutation returns the [sandbox: file access denied under <mode> mode] marker with the same-turn escalation hint, and an approved retry may stamp a strictly wider mode for that one call.

Failures and recovery

Failures are normalized as Error: <message> with a structured code preserved for callers. Stable messages include file_path must be a non-empty string, limit must be less than or equal to <max>, cannot read "<path>": not found, cannot read "<path>": not a regular file, and the image-route refusal cannot read "<path>" as an image: model "<model>" does not declare image input; switch to an image-capable model to read images. Guarded-mutation failures append their remedy: FS_STALE_VERSION gets — re-read the file, then retry, FS_NOT_OBSERVED gets — read the file, then retry. After the reread confirms absence, edit reports FS_NOT_FOUND instead of repeating a stale remedy, while write uses guarded creation.

Understand the implementation

Implementation internals — click to expand

This section explains the design decisions behind the tool suite and points at the code that realizes them; the observable behavior is fully covered in Use this package.

Design concept

The tools are the executor; policy is an event gate. The tools inject no policy service and inspect no cache — each mutation asks the single intent slot for its guard through ctx.waterfall, and each operation emits fs/observed only after it succeeded. Reads do exactly one provider stat (type and size routing plus the observed version); mutations do none, because the guard comes from the intent slot and the provider re-checks under its lock.

Source map

File	Role
`src/index.ts`	Plugin entry: `Config`, tool composition, `read_image` attachments gate
`src/read.ts`	`read` executor: one stat, streaming decision, window build, observation
`src/read-image.ts`	`read_image` executor: route and media-type gates, bounded bytes, attachment save
`src/write.ts`	`write` executor: intent waterfall, atomic write, observation
`src/edit.ts`	`edit` executor: intent waterfall, literal edit, observation
`src/read-render.ts`	Cordis-free windowing and envelope formatting
`src/sandbox.ts`	Escalation API shared by `write`/`edit`: policy resolution and denial-marker mapping
`src/error.ts`	Model-facing remedy appended to `FS_STALE_VERSION` and `FS_NOT_OBSERVED`

Per-tool flow

All four tools share one flow shape: resolve the path with the calling session's cwd, run the applicable gate, perform exactly one provider operation, and emit fs/observed only after success. read and read_image pay one stat for type and size routing; write and edit pay none because their guard comes from the intent slot, and provider failures surface as typed FsError results. The per-tool executors live in src/read.ts, src/read-image.ts, src/write.ts, and src/edit.ts.

Observation and concurrency

fs/observed fires after the operation succeeded via a plain ctx.emit; a listener is contractually a synchronous, side-effect-only recorder, so 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, and both mutation tools remain exclusive.

Further Exploration

Read these pages when the package-level contract is not enough. They move from the tools to the contract, backends, and policy they compose with.

Filesystem subsystem — exhaustive provider contract, policy events, and error taxonomy.
dsh-fs — the ctx.fs contract these tools consume.
fs-local — the host-filesystem backend these tools run against.
fs-sandbox — the sandbox-enforcing backend that adds the escalation fields.
fs-observation-policy — the policy plugin that guards mutations through the fs/* events.
Generated tool catalog — the exhaustive schemas this package registers.

Model Experience

System prompt

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.

Read guidance

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.

Write guidance

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-observation-policy requires it) and prefer edit for targeted changes.

Edit guidance

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-observation-policy requires it), unless you just created or edited it in this session.

Token effect

Only a failing call adds these retained tokens.

KV Cache effect

Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries.

Known Limitations and Deferred Work

These limits define when the tool suite is a poor fit or needs special operational care. They are current package constraints, not a general filesystem comparison or a task backlog.

No model-facing directory listing ships — ctx.fs.listDir serves provider code such as skill discovery, while the sibling dsh-tool-fs-search package supplies ripgrep-backed glob and grep rather than extending the filesystem seam.
read handles UTF-8 text files only — images use the separate extension-routed read_image tool; PDF, audio, and video remain deferred. A directory target is FS_NOT_REGULAR_FILE.
Extension-declared media type — the extension selects the declared type and the attachment store's magic-byte validation stays authoritative; a correctly formatted image under a wrong extension is refused with the rename remedy rather than sniffed.
No inline image preview on the tool-result card — UI surfaces render the image result generically (the durable reference, not pixels); inline rendering is deferred to the UI packages.
No attachment-region tool — an agent may crop an image through another available tool when it has a filesystem path; a pasted or dragged image without a path cannot be re-read at higher resolution.
No timeout surface — read/write/edit take no timeout argument and declare no timeout budget; cancellation rides exec.signal only (provider rationale).

Dev Note

Working context for maintainers — click to expand

None.

README.md

@deepseek-ai/dsh-tool-fs

Summary

Table of Contents

Use this package

Minimal composition

The tools

Configuration

Policy and sandbox behavior

Failures and recovery

Understand the implementation

Design concept

Source map

Per-tool flow

Observation and concurrency

Further Exploration

Model Experience

System prompt

What the model sees

Read guidance

Write guidance

Edit guidance

Token effect

KV Cache effect

Tool schemas

What the model sees

Token effect

KV Cache effect

Read result

What the model sees

Token effect

KV Cache effect

Image read result

What the model sees

Token effect

KV Cache effect

Write and edit results

What the model sees

Token effect

KV Cache effect

Tool errors

What the model sees

Token effect

KV Cache effect

Known Limitations and Deferred Work

Dev Note