refactor(fs-search): apply #1119 review fixes to the packaged-rg spawn

- delete the singleQuote shell-quoting helper and its bash-spawning tests
  (no in-repo consumers; no shell layer exists anymore)
- drop spill from both collect streams: the tool never reads a raw spill
  path, and a lossy stdout read is a pure SEARCH_RAW_OUTPUT_OVERFLOW error
- prepend --no-config so a host RIPGREP_CONFIG_PATH cannot inject a --pre
  preprocessor into the unconfined spawn
- promote graceMs and stderrMaxBytes to validated Config fields (defaults
  SEARCH_GRACE_MS / SEARCH_STDERR_MAX_BYTES) instead of inheriting
  bash-local's config
- correct the grep tool's JSDoc seam reference (bash -> subprocess)
- drop the dead exit-127/command-not-found classification branch
This commit is contained in:
Huanqi Cao
2026-08-01 21:56:16 +08:00
parent 36700f6916
commit a9871d4af1
14 changed files with 97 additions and 135 deletions
@@ -1,59 +0,0 @@
/**
* Unit tests for the shell-quoting safety boundary, plus a REAL round-trip:
* every adversarial value, quoted, must survive `bash -c "printf '%s' <quoted>"`
* byte-for-byte — proving the quoting is inert in an actual shell, not just
* against a mental model of one.
*/
import { describe, expect, it } from 'vitest'
import { spawnSync } from 'node:child_process'
import { singleQuote } from '@deepseek-ai/dsh-tool-fs-search'
/** Adversarial values a model could pass as pattern / path / include. */
const HOSTILE: readonly string[] = [
'plain',
'with spaces',
"it's got 'quotes'",
'"double quoted"',
'$(rm -rf /tmp/nope)',
'`touch /tmp/nope`',
'$HOME and ${PATH}',
'semi;colon && chain || pipe | bg &',
'newline\nin the middle',
'-leading-dash',
'--leading-double-dash',
'*?[a-z]{x,y}',
'!bang',
'\\backslash\\',
'~tilde',
'# not a comment',
'>redirect <input 2>&1',
]
describe('singleQuote', () => {
it('wraps a plain value in single quotes', () => {
expect(singleQuote('abc')).toBe("'abc'")
})
it("rewrites embedded single quotes as '\\''", () => {
expect(singleQuote("a'b")).toBe("'a'\\''b'")
expect(singleQuote("''")).toBe("''\\'''\\'''")
})
it.each(HOSTILE.map(value => [JSON.stringify(value), value] as const))(
'round-trips %s through a real bash -c unchanged',
(_label, value) => {
const result = spawnSync('bash', ['-c', `printf '%s' ${singleQuote(value)}`], { encoding: 'utf8' })
expect(result.status).toBe(0)
expect(result.stdout).toBe(value)
},
)
it('a quoted command substitution does not execute (the world stays untouched)', () => {
const canary = `/tmp/dsh-quote-canary-${process.pid}`
const result = spawnSync('bash', ['-c', `printf '%s' ${singleQuote(`$(touch ${canary})`)}`], { encoding: 'utf8' })
expect(result.stdout).toBe(`$(touch ${canary})`)
// The canary file must NOT exist — the substitution stayed literal.
expect(spawnSync('test', ['-e', canary]).status).not.toBe(0)
})
})
+23 -21
View File
@@ -291,6 +291,8 @@ describe('config validation', () => {
['grepMaxMatches', { grepMaxMatches: -1 }],
['grepMaxLineBytes', { grepMaxLineBytes: 1.5 }],
['rawOutputMaxBytes', { rawOutputMaxBytes: 0 }],
['graceMs', { graceMs: 0 }],
['stderrMaxBytes', { stderrMaxBytes: -1 }],
['timeoutMs', { timeoutMs: -100 }],
] as const)('rejects a non-positive or fractional %s at load', async (name, config) => {
const ctx = new Context()
@@ -372,16 +374,30 @@ describe('workdir derivation and signal forwarding', () => {
expect(subprocess.spawns[1]?.cwd).toBe(process.cwd())
})
it('spawns the packaged ripgrep binary with the fixed argv and budgeted collect streams', async () => {
const { ctx, subprocess } = await setup({ config: { rawOutputMaxBytes: 1234 } })
it('spawns the packaged ripgrep binary with --no-config, the fixed argv, and budgeted collect streams', async () => {
const { ctx, subprocess } = await setup({
config: { rawOutputMaxBytes: 1234, graceMs: 5000, stderrMaxBytes: 4096 },
})
subprocess.handler = () => runResult('', { exitCode: 1 })
await call(ctx, 'grep', { pattern: 'needle' })
const spec = subprocess.spawns[0]
expect(spec?.argv[0]).toBe(rgPath)
expect(spec?.argv).toEqual([rgPath, '--json', '--regexp=needle'])
// --no-config keeps a host RIPGREP_CONFIG_PATH from injecting a
// preprocessor into this unconfined spawn.
expect(spec?.argv).toEqual([rgPath, '--no-config', '--json', '--regexp=needle'])
expect(spec?.stdio.stdin).toBe('ignore')
// stdout gets the tool's parse budget; stderr is a diagnostic excerpt.
// stdout gets the tool's parse budget; stderr is a diagnostic excerpt;
// both are the seam's diagnostic-tail shape (no spill files requested).
expect((spec?.stdio.stdout as { maxBytes: number }).maxBytes).toBe(1234)
expect((spec?.stdio.stderr as { maxBytes: number }).maxBytes).toBe(4096)
expect(spec?.graceMs).toBe(5_000)
})
it('defaults the stderr tail budget and grace period when the config omits them', async () => {
const { ctx, subprocess } = await setup()
subprocess.handler = () => runResult('', { exitCode: 1 })
await call(ctx, 'grep', { pattern: 'needle' })
const spec = subprocess.spawns[0]
expect((spec?.stdio.stderr as { maxBytes: number }).maxBytes).toBe(64 * 1024)
expect(spec?.graceMs).toBe(3_000)
})
@@ -430,7 +446,7 @@ describe('workdir derivation and signal forwarding', () => {
const controller = new AbortController()
controller.abort()
const exec = { signal: controller.signal, name: 'glob', callId: CallId('direct-pre-abort') } as unknown as ToolExecution
await expect(runRipgrep(ctx, exec, 'glob', ['--files'], 1_000_000)).rejects
await expect(runRipgrep(ctx, exec, 'glob', ['--files'], 1_000_000, 3_000, 64 * 1024)).rejects
.toMatchObject({ name: 'SearchError', code: 'SEARCH_ABORTED' })
})
@@ -489,20 +505,6 @@ describe('exit semantics and failure classification', () => {
expect(result.error).toMatchObject({ info: { code: 'SEARCH_INVALID_PATTERN' } })
})
it('a failed ripgrep launch classifies as SEARCH_FAILED naming ripgrep', async () => {
const { ctx, subprocess } = await setup()
subprocess.handler = () => runResult('', { exitCode: 127, stderr: { text: 'sh: rg: command not found' } })
const result = await call(ctx, 'glob', { pattern: '*' })
expect(result.error).toMatchObject({ info: { code: 'SEARCH_FAILED' } })
expect(text(result)).toContain('requires ripgrep (rg)')
// The same classification holds from either evidence alone: the 127 exit
// with silent stderr, or a shell's command-not-found text on another exit.
subprocess.handler = () => runResult('', { exitCode: 127 })
expect(text(await call(ctx, 'glob', { pattern: '*' }))).toContain('requires ripgrep (rg)')
subprocess.handler = () => runResult('', { exitCode: 2, stderr: { text: 'sh: rg: command not found' } })
expect(text(await call(ctx, 'grep', { pattern: 'x' }))).toContain('requires ripgrep (rg)')
})
it('other nonzero exits are SEARCH_FAILED carrying the stderr excerpt', async () => {
const { ctx, subprocess } = await setup()
subprocess.handler = () => runResult('', { exitCode: 2, stderr: { text: 'rg: missing.dir: IO error: no such file or directory' } })
@@ -682,7 +684,7 @@ describe('glob results', () => {
subprocess.handler = () => runResult('sub/a.ts\n')
const result = await call(ctx, 'glob', { pattern: '*.ts', path: 'sub' })
expect(result.isError).toBe(false)
expect(subprocess.spawns[0]?.argv).toEqual([rgPath, '--files', '--glob=*.ts', '--sort=modified', '--no-ignore', '--hidden',
expect(subprocess.spawns[0]?.argv).toEqual([rgPath, '--no-config', '--files', '--glob=*.ts', '--sort=modified', '--no-ignore', '--hidden',
'--glob=!**/.git', '--glob=!**/.git/**',
'--glob=!**/.svn', '--glob=!**/.svn/**',
'--glob=!**/.hg', '--glob=!**/.hg/**',