mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
test(tools): close persistent tool coverage gaps
This commit is contained in:
@@ -1593,7 +1593,7 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/pty/tool-bash-persistent/src/index.ts:382`](../packages/pty/tool-bash-persistent/src/index.ts)
|
||||
Source: [`packages/pty/tool-bash-persistent/src/index.ts:373`](../packages/pty/tool-bash-persistent/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tool-cordis`
|
||||
|
||||
|
||||
@@ -281,7 +281,7 @@ async function createFile(
|
||||
outcome = await ctx.fs.writeText(
|
||||
target,
|
||||
content,
|
||||
intent ?? { kind: 'createIfAbsent' },
|
||||
intent,
|
||||
exec.signal,
|
||||
sandboxPolicy,
|
||||
)
|
||||
|
||||
@@ -129,6 +129,24 @@ describe('tool-str-replace-editor', () => {
|
||||
kind: 'edit',
|
||||
locations: [{ path: '/workspace/a.txt', line: 1 }],
|
||||
})
|
||||
expect(ctx.tools.get('str_replace_editor')?.presentCall?.({
|
||||
command: 'create',
|
||||
path: '/workspace/empty.txt',
|
||||
})).toMatchObject({
|
||||
diffs: [{ path: '/workspace/empty.txt', oldText: null, newText: '' }],
|
||||
})
|
||||
expect(ctx.tools.get('str_replace_editor')?.presentCall?.({
|
||||
command: 'str_replace',
|
||||
path: '/workspace/a.txt',
|
||||
})).toMatchObject({
|
||||
diffs: [{ path: '/workspace/a.txt', oldText: null, newText: '' }],
|
||||
})
|
||||
expect(ctx.tools.get('str_replace_editor')?.presentCall?.({
|
||||
command: 'insert',
|
||||
path: '/workspace/a.txt',
|
||||
})).toMatchObject({
|
||||
locations: [{ path: '/workspace/a.txt' }],
|
||||
})
|
||||
})
|
||||
|
||||
it('creates, views, replaces, and inserts with the canonical model-facing output', async () => {
|
||||
@@ -192,7 +210,11 @@ describe('tool-str-replace-editor', () => {
|
||||
ctx.fs.listDir = async (target, signal) => {
|
||||
const entries = await listDir(target, signal)
|
||||
return target.displayPath === join(root, 'dir')
|
||||
? [...entries, { name: 'other', type: 'other', target: otherTarget }]
|
||||
? [
|
||||
{ name: 'same-target', type: 'other', target: otherTarget },
|
||||
{ name: 'other', type: 'other', target: otherTarget },
|
||||
...entries.toReversed(),
|
||||
]
|
||||
: entries
|
||||
}
|
||||
|
||||
@@ -235,6 +257,11 @@ describe('tool-str-replace-editor', () => {
|
||||
command: 'view',
|
||||
path: plain,
|
||||
}))).toContain(' 1 one')
|
||||
expect((await call(ctx, undefined, {
|
||||
command: 'create',
|
||||
path: join(root, 'ownerless.txt'),
|
||||
file_text: 'ownerless',
|
||||
})).isError).toBe(false)
|
||||
|
||||
await call(ctx, owner, {
|
||||
command: 'insert',
|
||||
@@ -382,6 +409,14 @@ describe('tool-str-replace-editor', () => {
|
||||
})).isError).toBe(false)
|
||||
expect(await readFile(existing, 'utf8')).toBe('after')
|
||||
|
||||
expect((await call(ctx, owner, {
|
||||
command: 'insert',
|
||||
path: existing,
|
||||
insert_line: 1,
|
||||
new_str: 'tail',
|
||||
})).isError).toBe(false)
|
||||
expect(await readFile(existing, 'utf8')).toBe('after\ntail')
|
||||
|
||||
expect((await call(ctx, owner, {
|
||||
command: 'create',
|
||||
path: created,
|
||||
@@ -400,19 +435,79 @@ describe('tool-str-replace-editor', () => {
|
||||
})
|
||||
expect(result.error).toMatchObject({ info: { code: 'FS_SANDBOX_DENIED' } })
|
||||
expect(text(result)).toContain('[sandbox: file access denied under read-only mode]')
|
||||
|
||||
const ownerless = await call(ctx, undefined, {
|
||||
command: 'create',
|
||||
path: join(root, 'ownerless-blocked.txt'),
|
||||
file_text: 'blocked',
|
||||
})
|
||||
expect(ownerless.error).toMatchObject({ info: { code: 'FS_SANDBOX_DENIED' } })
|
||||
})
|
||||
|
||||
it('can preserve tabs outside the edited region', async () => {
|
||||
const { ctx, root, owner } = await setup({ expandTabsOnMutation: false })
|
||||
const path = join(root, 'Makefile')
|
||||
await writeFile(path, 'target:\n\told\n')
|
||||
await writeFile(path, 'target:\n\told\nremove\n')
|
||||
await call(ctx, owner, {
|
||||
command: 'str_replace',
|
||||
path,
|
||||
old_str: 'old',
|
||||
new_str: 'new',
|
||||
})
|
||||
expect(await readFile(path, 'utf8')).toBe('target:\n\tnew\n')
|
||||
await call(ctx, owner, {
|
||||
command: 'str_replace',
|
||||
path,
|
||||
old_str: 'remove\n',
|
||||
})
|
||||
await call(ctx, owner, {
|
||||
command: 'insert',
|
||||
path,
|
||||
insert_line: 1,
|
||||
new_str: '\tkept',
|
||||
})
|
||||
expect(await readFile(path, 'utf8')).toBe('target:\n\tkept\n\tnew\n')
|
||||
})
|
||||
|
||||
it('reports missing sandbox-policy composition during plugin startup', async () => {
|
||||
const root = await mkdtemp(join(tmpdir(), 'dsh-tool-str-replace-editor-missing-policy-'))
|
||||
roots.push(root)
|
||||
const ctx = new Context()
|
||||
contexts.push(ctx)
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(LocalFileSystem, { cwd: root })
|
||||
Object.defineProperty(ctx.fs, 'sandboxMode', { value: 'read-only' })
|
||||
|
||||
await expect(ctx.plugin(ToolStrReplaceEditor))
|
||||
.rejects.toThrow('the mounted filesystem confines but ctx.sandboxPolicy is missing')
|
||||
})
|
||||
|
||||
it('maps unexpected backend write failures for replace and insert', async () => {
|
||||
const { ctx, root, owner } = await setup()
|
||||
const path = join(root, 'backend-error.txt')
|
||||
await writeFile(path, 'old\n')
|
||||
ctx.fs.writeText = async () => {
|
||||
throw new Error('backend write failed')
|
||||
}
|
||||
|
||||
const replace = await call(ctx, owner, {
|
||||
command: 'str_replace',
|
||||
path,
|
||||
old_str: 'old',
|
||||
new_str: 'new',
|
||||
})
|
||||
expect(replace.isError).toBe(true)
|
||||
expect(text(replace)).toContain('backend write failed')
|
||||
|
||||
const insert = await call(ctx, owner, {
|
||||
command: 'insert',
|
||||
path,
|
||||
insert_line: 1,
|
||||
new_str: 'new',
|
||||
})
|
||||
expect(insert.isError).toBe(true)
|
||||
expect(text(insert)).toContain('backend write failed')
|
||||
})
|
||||
|
||||
it('rejects invalid plugin config', () => {
|
||||
|
||||
@@ -81,12 +81,7 @@ function wrapCommand(command: string, marker: CommandMarkers): string {
|
||||
}
|
||||
|
||||
function stripPrompt(text: string): string {
|
||||
let result = text
|
||||
while (result.endsWith(`${SHELL_PROMPT}\r\n`) || result.endsWith(`${SHELL_PROMPT}\n`)) {
|
||||
result = result.slice(0, result.endsWith('\r\n')
|
||||
? -SHELL_PROMPT.length - 2
|
||||
: -SHELL_PROMPT.length - 1)
|
||||
}
|
||||
let result = text.replace(/\r?\n$/, '')
|
||||
while (result.endsWith(SHELL_PROMPT)) {
|
||||
result = result.slice(0, -SHELL_PROMPT.length)
|
||||
}
|
||||
@@ -96,10 +91,9 @@ function stripPrompt(text: string): string {
|
||||
function commandOutput(
|
||||
snapshot: RetainedOutput,
|
||||
marker: CommandMarkers,
|
||||
): CapturedOutput | undefined {
|
||||
): CapturedOutput {
|
||||
const text = snapshot.text
|
||||
const end = text.lastIndexOf(marker.end)
|
||||
if (end < 0) return undefined
|
||||
const startMarker = text.lastIndexOf(marker.start, end)
|
||||
const start = startMarker < 0 ? 0 : startMarker + marker.start.length
|
||||
return {
|
||||
@@ -182,7 +176,6 @@ function persistentShells(ctx: Context, config: ResolvedConfig): PersistentShell
|
||||
const creating = new Set<Promise<PtySessionId>>()
|
||||
const ownerCleanupInstalled = new WeakSet<Agent>()
|
||||
const lifecycle = new AbortController()
|
||||
let disposed = false
|
||||
|
||||
const close = async (owner: Agent, id: PtySessionId, reason: string): Promise<void> => {
|
||||
if (!ctx.pty.list(owner).some(snapshot => snapshot.sessionId === id)) return
|
||||
@@ -190,7 +183,6 @@ function persistentShells(ctx: Context, config: ResolvedConfig): PersistentShell
|
||||
}
|
||||
|
||||
ctx.effect(() => async () => {
|
||||
disposed = true
|
||||
lifecycle.abort(new Error('tool-bash-persistent disposed during shell creation'))
|
||||
await Promise.allSettled([...creating])
|
||||
const closing = [...live].map(async ([owner, id]) => { await close(owner, id, 'tool-bash-persistent disposed') })
|
||||
@@ -206,7 +198,6 @@ function persistentShells(ctx: Context, config: ResolvedConfig): PersistentShell
|
||||
}
|
||||
|
||||
const get = (owner: Agent, signal: AbortSignal): Promise<PtySessionId> => {
|
||||
if (disposed) return Promise.reject(new Error('tool-bash-persistent is disposed'))
|
||||
const existing = pending.get(owner)
|
||||
if (existing !== undefined) return existing
|
||||
const combinedSignal = AbortSignal.any([signal, lifecycle.signal])
|
||||
@@ -302,7 +293,7 @@ async function executeCommand(
|
||||
}
|
||||
if (latest.text.includes(marker.end)) {
|
||||
const complete = commandOutput(retainedScrollback(ctx, owner, id, latest), marker)
|
||||
if (complete !== undefined) return renderCaptured(complete, config.maxOutputChars)
|
||||
return renderCaptured(complete, config.maxOutputChars)
|
||||
}
|
||||
if (result.sessionStatus.kind === 'exited') {
|
||||
const snapshot = retainedScrollback(ctx, owner, id, latest)
|
||||
|
||||
@@ -87,6 +87,7 @@ type StubMode =
|
||||
| 'spawn-error'
|
||||
| 'send-error'
|
||||
| 'prompt-after-idle'
|
||||
| 'empty-page-after-latest'
|
||||
|
||||
class StubPtySession implements PtyBackendSession {
|
||||
readonly motd = '__DSH_PERSISTENT_BASH_PROMPT__ '
|
||||
@@ -168,19 +169,22 @@ class StubPtySession implements PtyBackendSession {
|
||||
return this.operation(Promise.resolve(this.result(output, 'stdin_read')))
|
||||
}
|
||||
|
||||
read(_request: PtyReadRequest) {
|
||||
read(request: PtyReadRequest) {
|
||||
if (this.mode === 'empty-read') {
|
||||
return { text: '', totalLines: 0, lineBegin: 0, lineEnd: 0, truncated: false }
|
||||
}
|
||||
if (this.mode === 'stalled-read') {
|
||||
return { text: 'stalled', totalLines: 1, lineBegin: 0, lineEnd: 0, truncated: false }
|
||||
}
|
||||
if (this.mode === 'empty-page-after-latest' && (request.offset ?? 0) > 0) {
|
||||
return { text: '', totalLines: 2, lineBegin: 1, lineEnd: 1, truncated: false }
|
||||
}
|
||||
const lines = this.scrollback.split('\n')
|
||||
return {
|
||||
text: this.scrollback,
|
||||
totalLines: lines.length,
|
||||
totalLines: this.mode === 'empty-page-after-latest' ? lines.length + 1 : lines.length,
|
||||
lineBegin: 0,
|
||||
lineEnd: lines.length,
|
||||
lineEnd: this.mode === 'empty-page-after-latest' ? 1 : lines.length,
|
||||
truncated: this.historyTruncated,
|
||||
}
|
||||
}
|
||||
@@ -329,6 +333,9 @@ describe('tool-bash-persistent', () => {
|
||||
|
||||
session.mode = 'stalled-read'
|
||||
expect(text(await call(ctx, owner, 'stalled page'))).toContain('hello from stub')
|
||||
|
||||
session.mode = 'empty-page-after-latest'
|
||||
expect(text(await call(ctx, owner, 'empty continuation page'))).toContain('hello from stub')
|
||||
})
|
||||
|
||||
it('sanitizes a prompt fallback reached after multiple polling rounds', async () => {
|
||||
|
||||
Reference in New Issue
Block a user