feat(fs-search): spawn the packaged ripgrep binary through the subprocess seam

glob/grep now run the @vscode/ripgrep binary via ctx.subprocess with a plain
argv vector: no system rg install, no shell layer, unconditional registration.
The load-time command -v rg probe and the bash-seam coupling are removed;
timeouts ride the cooperative exec.signal plus the seam's terminate
escalation. The fs-glob-sampling ACP snapshot executes the real packaged
binary against an mtime-pinned fixture. Adds the packaged-ripgrep-search
Agent Note, updates the roster-note facts and both shipped-composition e2es,
and regenerates the doc catalogs and third-party notices (surfacing
pre-existing manifest drift plus the new @vscode/ripgrep row; the notices
generator also learns pnpm 11's truncated virtual-store names).
This commit is contained in:
Huanqi Cao
2026-08-01 18:04:38 +08:00
parent de520bee24
commit 18700f428d
32 changed files with 923 additions and 699 deletions

View File

@@ -16,8 +16,6 @@ import SessionQuerySqlite from '@deepseek-ai/dsh-session-query-sqlite'
import GoalService from '@deepseek-ai/dsh-goal'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools'
import { BashExecutor } from '@deepseek-ai/dsh-bash'
import type { BashExecRequest, BashExecSpec, BashProcess, BashRunResult } from '@deepseek-ai/dsh-bash'
import LocalBashExecutor from '@deepseek-ai/dsh-bash-local'
import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local'
import LocalFileSystem from '@deepseek-ai/dsh-fs-local'
@@ -55,44 +53,6 @@ import * as ToolWorkflow from '@deepseek-ai/dsh-tool-workflow'
const root = resolve(import.meta.dirname, '..')
const OUT = 'docs/tool-catalog.md'
const CATALOG_RG_PROBE_COMMAND = 'command -v rg >/dev/null 2>&1'
/**
* Minimal bash service for harvesting `dsh-tool-fs-search` schemas. The search
* plugin now probes `rg` at registration time, but the generated catalog must
* remain independent of the host PATH and never execute a real search.
*/
class CatalogSearchBashExecutor extends BashExecutor {
override resolve(request: BashExecRequest): BashExecSpec {
return {
command: request.command,
workdir: request.workdir ?? root,
timeoutMs: request.timeoutMs ?? 60_000,
stdoutMaxBytes: request.stdoutMaxBytes ?? 64_000,
signal: request.signal,
sandboxPolicy: request.sandboxPolicy,
}
}
override run(spec: BashExecSpec): Promise<BashRunResult> {
if (spec.command !== CATALOG_RG_PROBE_COMMAND) {
throw new Error(`gen-tool-catalog: unexpected search bash command during schema harvest: ${spec.command}`)
}
return Promise.resolve({
exitCode: 0,
signal: null,
timedOut: false,
aborted: false,
timeoutMs: spec.timeoutMs,
stdout: { text: '', truncated: false },
stderr: { text: '', truncated: false },
})
}
override start(): BashProcess {
throw new Error('gen-tool-catalog: search schema harvest must not start background processes')
}
}
/**
* Register the descriptor needed to mount schema-producing consumers. Declares
@@ -264,19 +224,19 @@ const TOOL_PACKAGES: ToolPackage[] = [
pkg: '@deepseek-ai/dsh-tool-fs-search',
dir: 'tool-fs-search',
source: 'packages/fs/tool-fs-search/src/index.ts',
requires: ['ctx.tools', 'ctx.bash', 'ctx.systemPrompt'],
requires: ['ctx.tools', 'ctx.subprocess', 'ctx.systemPrompt'],
writes: ['tool/call', 'tool/result'],
async mount(ctx) {
// The tools inject `bash` (search executes fixed `rg` commands through
// the executor seam, not ctx.fs). Use a catalog-only executor so the
// registration-time `rg` probe stays deterministic and the generator
// 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)
// The tools inject `subprocess` (search spawns the packaged ripgrep
// binary through the seam, not ctx.fs); registration itself never
// spawns, so the real local service is inert here. `ctx.spillStore` is
// optional (read via ctx.get) and does not affect the schemas, so no
// spill backend is mounted.
await ctx.plugin(LocalSubprocessService)
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). 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.',
'glob and grep are unconditional discovery tools that spawn the packaged ripgrep binary (`@vscode/ripgrep`) through ctx.subprocess as ordinary foreground calls (never background tasks) — no host `rg` install and no shell layer. 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',