Merge remote-tracking branch 'origin/master' into fs-overwrite-diff-bound-v2
# Conflicts: # docs/subsystems/lsp.i18n.yaml # packages/fs/fs-local/README.i18n.yaml # packages/fs/fs-local/README.md # packages/fs/fs-local/README.zh.md # packages/fs/fs-local/src/index.ts
This commit is contained in:
@@ -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/fs-local/README.md
|
||||
README.md: 9efee1ed3c33c825b20b4565f3c6cef7200ce4a2
|
||||
README.zh.md: 5554017f3d528e25decffe2f866c843039bb0457
|
||||
README.md: 5b7bcda223dd5a1110c585196e870a06c8a12bd0
|
||||
README.zh.md: 20ed94b317cac763d4efe9326bf8ee52ae0c7355
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
English | [中文](README.zh.md)
|
||||
|
||||
The **local-filesystem implementation** of the `ctx.fs` provider seam ([`@deepseek-ai/dsh-fs`](../fs)). Backs the eight `FileSystem` primitives with the host filesystem; loading it as a plugin populates `ctx.fs`.
|
||||
The **local-filesystem implementation** of the `ctx.fs` provider seam ([`@deepseek-ai/dsh-fs`](../fs)). Backs the eleven `FileSystem` primitives with the host filesystem; loading it as a plugin populates `ctx.fs`.
|
||||
|
||||
```ts ignore-check
|
||||
import { LocalFileSystem } from '@deepseek-ai/dsh-fs-local'
|
||||
@@ -15,8 +15,9 @@ await ctx.plugin(LocalFileSystem, { cwd: process.cwd() })
|
||||
## Behavior
|
||||
|
||||
- **`resolve(path, opts?)`** — a relative `path` resolves against `opts.cwd` when the caller supplies one (the model-facing tools pass the calling agent's session cwd — see [the per-session cwd Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md)), else `config.cwd` (default `process.cwd()`); an absolute `path` ignores both. `opts.signal` is checked before and after local resolution, while a remote sibling backend may use it to abort its round-trip. The `targetKey` is the file's `realpath`, so two input paths reaching the same file through symlinks share one identity, and writes/edits land on the link target (preserving the link). A not-yet-existing path uses the realpathed parent directory plus basename when the parent exists; only an unresolvable parent falls back to the absolute path. `displayPath` is the absolute (un-resolved) path.
|
||||
- **Execution-world coordinates** — `processPath` exposes the target's canonical host path, `fileUrl` encodes that path through Node's platform-aware URL conversion, and `contains` uses platform path semantics to test identity or descendant containment without consumers parsing `targetKey`.
|
||||
- **`stat` / `lstat`** — return target metadata or `undefined` when absent. `stat` reports `FsInfo` for an already resolved target (`version` = an opaque token derived from bigint `dev:ino:size:mtimeNs:ctimeNs`, `type` of `file`/`directory`/`other`, byte `size`); path-shaped `lstat` reports `FsPathInfo` without following the final symlink and can therefore return `symlink`. Both check cancellation before and after their asynchronous metadata probe, so an abort that lands in flight reports `FS_ABORTED` rather than stale absence.
|
||||
- **`readText` / `streamText`** — UTF-8 only. `readText` reads the whole file; `streamText` streams it in chunks (cross-chunk decoding) so a huge file never has to be held whole in memory. Both reject invalid UTF-8 and NUL-byte binary samples (`FS_NOT_TEXT`) and non-regular targets. The `read` tool (`@deepseek-ai/dsh-tool-fs`) decides which to call by size and owns the line windowing.
|
||||
- **`readText` / `streamText`** — UTF-8 only. `readText` reads the whole file; `streamText` decodes chunks so a huge file need not be held whole in memory and consumers can enforce their own retention bounds. Both reject invalid UTF-8 and NUL-byte binary samples (`FS_NOT_TEXT`) and non-regular targets. The `read` tool (`@deepseek-ai/dsh-tool-fs`) owns line windowing.
|
||||
- **`listDir`** — lists one directory level in stable `name.localeCompare()` order. Each entry carries the child basename, type, resolved child target (`displayPath` under the listed directory, `targetKey` as the realpath identity), and cheap stat metadata (`version`, plus `size` for regular files). It never opens or decodes file contents. Missing targets report `FS_NOT_FOUND`, file/special-file targets report `FS_NOT_DIRECTORY`, aborted calls report `FS_ABORTED`, permission failures report `FS_PERMISSION_DENIED`, and other listing or child metadata I/O failures report `FS_IO_ERROR`. Broken/disappeared children are returned as `other` without metadata, but permission/IO failures while resolving a child fail the whole listing with a structured `FsError`.
|
||||
- **`writeText`** — atomic: writes to a temp file opened exclusively (`wx`, `0o600`) inside a randomly-named private staging dir (`0o700`) next to the target, fsyncs, then renames over the target. An existing file's mode is preserved, while new files default to `0o600`; on Windows a new file inherits the destination directory's DACL, while replacement copies the target DACL onto the empty temp before writing and publishes through `ReplaceFileW` so the original access policy survives ([Windows DACL preservation Agent Note](../../../.agents/notes/implemented/bug-fix/2026-07-19-windows-atomic-write-dacl-preservation.md)). The `expected` guard is OPTIONAL: omitting it unconditionally creates-or-overwrites; `createIfAbsent` creates a missing target and rejects an existing one (`FS_NOT_OBSERVED`); `replaceIfVersion` replaces only at the observed version (a missing target or mismatch is `FS_STALE_VERSION`). An overwrite returns the prior text as its contextual diff basis only when both the opened prior file and UTF-8 replacement are strictly below `config.diffBasisMaxBytes` (default 10 MiB). The descriptor read enforces that limit even if an external writer replaces or changes the file size after the initial probe. Otherwise the provider returns `before: null`, so presentation uses its whole-file fallback.
|
||||
- **`editText`** — atomic literal read-modify-write over the same primitive, serialized per target by a mutation lock. The `expected` guard is OPTIONAL: when supplied it verifies the version BEFORE literal matching (a stale edit reports `FS_STALE_VERSION`, never `FS_EDIT_NOT_FOUND`/`FS_AMBIGUOUS_EDIT` against newer content); omitting it edits the current content unconditionally. A missing target reports `FS_STALE_VERSION` either way. LF-normalizes for matching, restores the file's dominant CRLF/LF style, and rejects empty `oldString` / zero matches (`FS_EDIT_NOT_FOUND`) or ambiguous multi-matches without `replace_all` (`FS_AMBIGUOUS_EDIT`).
|
||||
@@ -34,7 +35,7 @@ No direct invalidation; the named consumer owns any request-prefix changes.
|
||||
## Known Limitations and Deferred Work
|
||||
|
||||
- **`config.cwd` is not a sandbox** — it is a resolution default, not containment: absolute paths and `..` escape it. Enforce containment with a stricter `ctx.fs` backend or a permission plugin on the `tools/execute` waterfall ([capability-seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md#consequences)).
|
||||
- **Version tokens are `mtimeMs:size`** — an external change that preserves both within the filesystem's timestamp granularity defeats the stale guard.
|
||||
- **Version tokens depend on filesystem metadata** — they combine device, inode, size, nanosecond mtime, and nanosecond ctime; a storage layer that cannot update any of those facts for a rewrite can still defeat the stale guard.
|
||||
- **`editText` holds the whole file (plus the edited copy) in memory** — streaming exists only on the read path.
|
||||
- **A sub-limit overwrite still buffers a contextual basis** — `writeText` may retain up to just below `config.diffBasisMaxBytes` of prior text in addition to the caller-owned replacement; the bound does not cap the returned `after` value or presentation's whole-file fallback.
|
||||
- **Binary detection is asymmetric** — reads NUL-sample only the first 8192 bytes while edits scan the whole buffer, so a file with a late NUL reads fine but rejects edits.
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
`ctx.fs` 提供方 seam([`@deepseek-ai/dsh-fs`](../fs))的**本地文件系统实现**。它使用宿主文件系统支持八个 `FileSystem` 原语;将其作为插件加载会填充 `ctx.fs`。
|
||||
`ctx.fs` 提供方 seam([`@deepseek-ai/dsh-fs`](../fs))的**本地文件系统实现**。它使用宿主文件系统支持十一个 `FileSystem` 原语;将其作为插件加载会填充 `ctx.fs`。
|
||||
|
||||
```ts ignore-check
|
||||
import { LocalFileSystem } from '@deepseek-ai/dsh-fs-local'
|
||||
@@ -15,26 +15,27 @@ await ctx.plugin(LocalFileSystem, { cwd: process.cwd() })
|
||||
## 行为
|
||||
|
||||
- **`resolve(path, opts?)`**:相对 `path` 在调用方提供 `opts.cwd` 时以该值为基准解析(面向模型的工具会传入调用 agent(智能体)的会话 cwd;见[每会话 cwd Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md)),否则以 `config.cwd` 为基准(默认 `process.cwd()`);绝对 `path` 会忽略两者。`opts.signal` 会在本地解析前后检查,远程同级后端则可以用它中止往返。`targetKey` 是文件的 `realpath`,因此经符号链接到达同一文件的两个输入路径会共享一个身份,写入/编辑落在链接目标上,同时保留链接。尚不存在的路径在父目录存在时使用 realpath 后的父目录加 basename;只有父目录无法解析时才回退到绝对路径。`displayPath` 是绝对但未经解析的路径。
|
||||
- **`stat` / `lstat`**:返回目标元数据;目标不存在时返回 `undefined`。`stat` 为已解析目标报告 `FsInfo`(`version` 是由 bigint `dev:ino:size:mtimeNs:ctimeNs` 派生的不透明 token,`type` 为 `file`/`directory`/`other`,`size` 以字节计);路径形态的 `lstat` 不跟随最后一个符号链接,报告 `FsPathInfo`,因此可以返回 `symlink`。两者都会在异步元数据探测前后检查取消,因此异步探测进行期间发生的中止会报告 `FS_ABORTED`,而非已失效的「不存在」结果。
|
||||
- **`readText` / `streamText`**:只支持 UTF-8。`readText` 读取整个文件;`streamText` 按分片流式读取(跨分片解码),因此超大文件无需整体保存在内存中。两者都会拒绝无效 UTF-8、包含 NUL 字节的二进制样本(`FS_NOT_TEXT`)以及非普通文件目标。`read` 工具(`@deepseek-ai/dsh-tool-fs`)按大小决定调用哪个方法,并负责行窗口逻辑。
|
||||
- **执行世界坐标**:`processPath` 公开目标的规范化宿主路径,`fileUrl` 通过 Node 的平台感知 URL 转换对该路径编码,`contains` 则使用平台路径语义检查身份相等或后代包含关系,消费方无需解析 `targetKey`。
|
||||
- **`stat` / `lstat`**:返回目标元数据;目标不存在时返回 `undefined`。`stat` 为已解析目标报告 `FsInfo`(`version` 是由 bigint `dev:ino:size:mtimeNs:ctimeNs` 派生的不透明 token,`type` 为 `file`/`directory`/`other`,`size` 以字节计);路径形态的 `lstat` 不跟随最后一个符号链接,报告 `FsPathInfo`,因此可以返回 `symlink`。两者都会在异步元数据探测前后检查取消,因此飞行中的中止会报告 `FS_ABORTED`,而非陈旧的不存在结果。
|
||||
- **`readText` / `streamText`**:只支持 UTF-8。`readText` 读取整个文件;`streamText` 按分片解码,因此超大文件无需整体保存在内存中,消费方也可以执行各自的保留上限。两者都会拒绝无效 UTF-8、包含 NUL 字节的二进制样本(`FS_NOT_TEXT`)以及非普通文件目标。`read` 工具(`@deepseek-ai/dsh-tool-fs`)拥有行窗口逻辑。
|
||||
- **`listDir`**:按稳定的 `name.localeCompare()` 顺序列出一层目录。每个条目携带子项 basename、类型、解析后的子目标(`displayPath` 位于所列目录下,`targetKey` 是 realpath 身份)和低成本 stat 元数据(`version`,普通文件另有 `size`)。它绝不会打开或解码文件内容。缺失目标报告 `FS_NOT_FOUND`,文件/特殊文件目标报告 `FS_NOT_DIRECTORY`,已中止调用报告 `FS_ABORTED`,权限失败报告 `FS_PERMISSION_DENIED`,其他列出或子项元数据 I/O 失败报告 `FS_IO_ERROR`。损坏/消失的子项以无元数据的 `other` 返回,但解析子项时出现权限/I/O 失败会让整个列表以结构化 `FsError` 失败。
|
||||
- **`writeText`**:原子写入。它会向排他打开的临时文件(`wx`、`0o600`)写入;该文件位于目标旁随机命名的私有暂存目录(`0o700`)内。完成写入和 fsync 后,以 rename 覆盖目标。现有文件的 mode 会保留,新文件默认为 `0o600`;Windows 上的新文件继承目标目录的 DACL,而替换会在写入前把目标 DACL 复制到空临时文件,并通过 `ReplaceFileW` 发布,使原访问策略得以保留(见 [Windows DACL 保留 Agent Note](../../../.agents/notes/implemented/bug-fix/2026-07-19-windows-atomic-write-dacl-preservation.md))。`expected` 防护是可选(OPTIONAL)的:省略时无条件创建或覆盖;`createIfAbsent` 创建缺失目标并拒绝现有目标(`FS_NOT_OBSERVED`);`replaceIfVersion` 只在观察到的版本上替换(目标缺失或版本不匹配均为 `FS_STALE_VERSION`)。仅当打开后的旧文件和 UTF-8 替换内容都严格低于 `config.diffBasisMaxBytes`(默认 10 MiB)时,覆写才返回旧文本作为上下文 diff 基础。即使外部写入方在初次探测后替换文件或改变文件大小,文件描述符读取仍会强制执行该上限;否则提供方返回 `before: null`,由展示层使用整文件回退。
|
||||
- **`editText`**:在同一原语之上执行原子式的字面量读取-修改-写入,并通过变更锁按目标串行化。`expected` 防护是可选(OPTIONAL)的:提供时,会在字面量匹配之前校验版本(陈旧编辑报告 `FS_STALE_VERSION`,绝不会针对较新内容报告 `FS_EDIT_NOT_FOUND`/`FS_AMBIGUOUS_EDIT`);省略时,无条件编辑当前内容。无论哪种情况,目标缺失都报告 `FS_STALE_VERSION`。匹配时规范化为 LF,随后恢复文件主要的 CRLF/LF 风格;空 `oldString` / 零匹配报告 `FS_EDIT_NOT_FOUND`,未设置 `replace_all` 的多个匹配则报告 `FS_AMBIGUOUS_EDIT`。
|
||||
- **`writeText`**:原子写入。它会向排他打开的临时文件(`wx`、`0o600`)写入;该文件位于目标旁随机命名的私有暂存目录(`0o700`)内。完成写入和 fsync 后,以 rename 覆盖目标。现有文件的 mode 会保留,新文件默认为 `0o600`;Windows 上的新文件继承目标目录的 DACL,而替换会在写入前把目标 DACL 复制到空临时文件,并通过 `ReplaceFileW` 发布,使原访问政策得以保留(见 [Windows DACL 保留 Agent Note](../../../.agents/notes/implemented/bug-fix/2026-07-19-windows-atomic-write-dacl-preservation.md))。`expected` 防护是可选的:省略时无条件创建或覆盖;`createIfAbsent` 创建缺失目标并拒绝现有目标(`FS_NOT_OBSERVED`);`replaceIfVersion` 只在观察到的版本上替换(目标缺失或版本不匹配均为 `FS_STALE_VERSION`)。仅当打开后的旧文件和 UTF-8 替换内容都严格低于 `config.diffBasisMaxBytes`(默认 10 MiB)时,覆写才返回旧文本作为上下文 diff 基础。即使外部写入方在初次探测后替换文件或改变文件大小,文件描述符读取仍会强制执行该上限;否则提供方返回 `before: null`,由展示层使用整文件回退。
|
||||
- **`editText`**:在同一原语之上依次执行原子的字面量读取、修改和写入,并通过变更锁按目标串行化。`expected` 防护是可选的:提供时,会在字面量匹配之前校验版本(陈旧编辑报告 `FS_STALE_VERSION`,绝不会针对较新内容报告 `FS_EDIT_NOT_FOUND`/`FS_AMBIGUOUS_EDIT`);省略时,无条件编辑当前内容。无论哪种情况,目标缺失都报告 `FS_STALE_VERSION`。匹配时规范化为 LF,随后恢复文件主要的 CRLF/LF 风格;空 `oldString` / 零匹配报告 `FS_EDIT_NOT_FOUND`,未设置 `replace_all` 的多个匹配则报告 `FS_AMBIGUOUS_EDIT`。
|
||||
|
||||
包根目录的 SDK 接口包含默认/具名 `LocalFileSystem` 类和 `Config`。原始 I/O 位于 `src/fsio.ts`(不依赖 Cordis,单独进行单元测试);`src/index.ts` 是轻量服务接线。
|
||||
包根 SDK 接口包含默认/具名 `LocalFileSystem` 类和 `Config`。原始 I/O 位于 `src/fsio.ts`(不依赖 Cordis,单独进行单元测试);`src/index.ts` 是轻量服务接线。
|
||||
|
||||
## 模型体验
|
||||
|
||||
通过 [`dsh-tool-fs`](../tool-fs/README.md) 间接产生影响;该消费方在有上限的保留结果中渲染本提供方带行窗口的 UTF-8 内容、变更确认和精确提供方消息,而版本、原子写入机制和目录元数据仍属内部实现。
|
||||
通过 [`dsh-tool-fs`](../tool-fs/README.md) 间接产生影响;该消费方把本提供方带行窗口的 UTF-8 内容、变更确认和精确提供方消息渲染为有上限且保留的结果,而版本、原子写入机制和目录元数据保持内部可见。
|
||||
|
||||
#### KV Cache 影响
|
||||
|
||||
不会直接使缓存失效;具名消费方负责请求前缀的任何变化。
|
||||
|
||||
## 已知限制与暂缓事项
|
||||
## 已知限制与延期工作
|
||||
|
||||
- **`config.cwd` 不是沙箱**:它是解析默认值,而非约束;绝对路径和 `..` 可以逃逸。请使用更严格的 `ctx.fs` 后端或 `tools/execute` waterfall(瀑布式事件)上的权限插件实施约束(见[能力 seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md#consequences))。
|
||||
- **版本 token 是 `mtimeMs:size`**:如果外部变更在文件系统时间戳粒度内保持两者不变,就能绕过陈旧防护。
|
||||
- **版本 token 依赖文件系统元数据**:它们组合设备、inode、大小、纳秒级 mtime 和纳秒级 ctime;如果存储层在重写时无法更新其中任何一项事实,仍可能绕过陈旧防护。
|
||||
- **`editText` 会把整个文件及编辑后的副本保存在内存中**:只有读取路径支持流式处理。
|
||||
- **低于上限的覆写仍会缓冲上下文基础**:`writeText` 除调用方持有的替换内容外,最多还会保留略低于 `config.diffBasisMaxBytes` 的旧文本;该上限不限制返回的 `after` 值,也不限制展示层的整文件回退。
|
||||
- **二进制检测不对称**:读取只对前 8192 字节执行 NUL 采样,编辑则扫描整个 buffer,因此 NUL 出现在后部的文件可以读取,但编辑会被拒绝。
|
||||
|
||||
@@ -6,7 +6,8 @@
|
||||
|
||||
import { Context } from 'cordis'
|
||||
import { constants as bufferConstants } from 'node:buffer'
|
||||
import { resolve } from 'node:path'
|
||||
import { isAbsolute, relative, resolve, sep } from 'node:path'
|
||||
import { pathToFileURL } from 'node:url'
|
||||
import z from 'schemastery'
|
||||
import { FileSystem, FsError, FsVersion } from '@deepseek-ai/dsh-fs'
|
||||
import type {
|
||||
@@ -108,6 +109,19 @@ export class LocalFileSystem extends FileSystem {
|
||||
return { targetKey: local.targetKey, displayPath: local.displayPath }
|
||||
}
|
||||
|
||||
override processPath(target: FsTarget): string {
|
||||
return String(target.targetKey)
|
||||
}
|
||||
|
||||
override fileUrl(target: FsTarget): string {
|
||||
return pathToFileURL(this.processPath(target)).href
|
||||
}
|
||||
|
||||
override contains(parent: FsTarget, child: FsTarget): boolean {
|
||||
const path = relative(this.processPath(parent), this.processPath(child))
|
||||
return path === '' || (path !== '..' && !path.startsWith(`..${sep}`) && !isAbsolute(path))
|
||||
}
|
||||
|
||||
override async stat(target: FsTarget, signal?: AbortSignal): Promise<FsInfo | undefined> {
|
||||
if (signal?.aborted) throw new FsError('stat aborted', 'FS_ABORTED')
|
||||
const info = await probe(target.targetKey)
|
||||
|
||||
@@ -11,6 +11,7 @@ import { constants as bufferConstants } from 'node:buffer'
|
||||
import { mkdir, mkdtemp, readFile, realpath, rm, stat, symlink, unlink, utimes, writeFile } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { pathToFileURL } from 'node:url'
|
||||
import { Context } from 'cordis'
|
||||
import { LocalFileSystem } from '@deepseek-ai/dsh-fs-local'
|
||||
import { FsVersion } from '@deepseek-ai/dsh-fs'
|
||||
@@ -112,6 +113,20 @@ describe('resolve', () => {
|
||||
|
||||
await expect(pending).rejects.toMatchObject({ code: 'FS_ABORTED' })
|
||||
})
|
||||
|
||||
it('projects process paths, file URLs, and canonical containment', async () => {
|
||||
await mkdir(join(dir, 'nested'))
|
||||
await writeFile(join(dir, 'nested', 'file.txt'), 'text')
|
||||
const root = await fs.resolve('.')
|
||||
const child = await fs.resolve('nested/file.txt')
|
||||
const outside = await fs.resolve('..')
|
||||
|
||||
expect(fs.processPath(child)).toBe(await realpath(join(dir, 'nested', 'file.txt')))
|
||||
expect(fs.fileUrl(child)).toBe(pathToFileURL(await realpath(join(dir, 'nested', 'file.txt'))).href)
|
||||
expect(fs.contains(root, root)).toBe(true)
|
||||
expect(fs.contains(root, child)).toBe(true)
|
||||
expect(fs.contains(root, outside)).toBe(false)
|
||||
})
|
||||
})
|
||||
|
||||
describe('stat', () => {
|
||||
|
||||
Reference in New Issue
Block a user