mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge remote-tracking branch 'origin/master' into codex/tool-json-schema-dsl
# Conflicts: # docs/config-catalog.md # docs/cookbook/adding-a-tool.i18n.yaml # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # packages/core/tools/tests/tools.spec.ts
This commit is contained in:
@@ -26,7 +26,7 @@ The plugin also contributes the `tool:bash` prompt section (order 105): check th
|
||||
|
||||
### Managed shell environment
|
||||
|
||||
Every foreground and background model bash call receives a newly collected trusted `DSH_*` environment. `DSH_HOME` is the absolute Harness home resolved by [`@deepseek-ai/dsh-home`](../../util/home/README.md) (`dshHome` config, then ambient `$DSH_HOME`, then `~/.dsh`) and `DSH_SHELL=1` identifies the managed child. Agent calls additionally receive `DSH_SESSION_ID=agent.session.header.id`; when the active persistence seam locates a JSONL artifact they also receive `DSH_SESSION_JSONL=<absolute target path>`. The JSONL path is a location hint: it may not exist before the first flush or contain the current buffered turn, and it is not an authorization credential.
|
||||
Every foreground and background model bash call receives a newly collected trusted `DSH_*` environment. `DSH_HOME` is the absolute Harness home resolved by [`@deepseek-ai/dsh-paths`](../../util/paths/README.md) (`dshHome` config, then ambient `$DSH_HOME`, then `~/.dsh`) and `DSH_SHELL=1` identifies the managed child. Agent calls additionally receive `DSH_SESSION_ID=agent.session.header.id`; when the active persistence seam locates a JSONL artifact they also receive `DSH_SESSION_JSONL=<absolute target path>`. The JSONL path is a location hint: it may not exist before the first flush or contain the current buffered turn, and it is not an authorization credential.
|
||||
|
||||
`ctx.bashEnv` owns collection. Other plugins can register an effect-scoped contributor with a stable name, declared keys/descriptions, and `resolve(execution: ToolExecution)`; duplicate ownership and undeclared runtime keys fail loudly, while `list()` enumerates declarations without executing providers. Harness built-ins reserve `DSH_HOME`, `DSH_SHELL`, and `DSH_SESSION_ID`; tool-bash's persistence translator owns `DSH_SESSION_JSONL` by reading the backend-neutral `sessionPersistence.locate()` seam.
|
||||
|
||||
|
||||
@@ -29,12 +29,12 @@
|
||||
"peerDependencies": {
|
||||
"@deepseek-ai/dsh-agent": "^0.0.1",
|
||||
"@deepseek-ai/dsh-bash": "^0.0.1",
|
||||
"@deepseek-ai/dsh-home": "^0.0.1",
|
||||
"@deepseek-ai/dsh-invariants": "^0.0.1",
|
||||
"@deepseek-ai/dsh-llm": "^0.0.1",
|
||||
"@deepseek-ai/dsh-paths": "^0.0.1",
|
||||
"@deepseek-ai/dsh-sandbox": "^0.0.1",
|
||||
"@deepseek-ai/dsh-session-persistence": "^0.0.1",
|
||||
"@deepseek-ai/dsh-sandbox-policy": "^0.0.1",
|
||||
"@deepseek-ai/dsh-session-persistence": "^0.0.1",
|
||||
"@deepseek-ai/dsh-system-prompt": "^0.0.1",
|
||||
"@deepseek-ai/dsh-tasks": "^0.0.1",
|
||||
"@deepseek-ai/dsh-tools": "^0.0.1",
|
||||
@@ -50,9 +50,9 @@
|
||||
"@deepseek-ai/dsh-agent-loop-testkit": "workspace:^",
|
||||
"@deepseek-ai/dsh-bash": "workspace:^",
|
||||
"@deepseek-ai/dsh-bash-local": "workspace:^",
|
||||
"@deepseek-ai/dsh-home": "workspace:^",
|
||||
"@deepseek-ai/dsh-invariants": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-paths": "workspace:^",
|
||||
"@deepseek-ai/dsh-sandbox": "workspace:^",
|
||||
"@deepseek-ai/dsh-sandbox-policy": "workspace:^",
|
||||
"@deepseek-ai/dsh-session": "workspace:^",
|
||||
|
||||
@@ -23,7 +23,7 @@ import { ESCALATION_TARGETS, approveEscalation, validateEscalationArgs } from '@
|
||||
import { effectiveSandboxMode } from '@deepseek-ai/dsh-sandbox-policy'
|
||||
import { DSH_ENV_PREFIX } from '@deepseek-ai/dsh-bash'
|
||||
import type { DshEnvironment, DshEnvironmentKey } from '@deepseek-ai/dsh-bash'
|
||||
import { DSH_HOME_ENV, resolveDshHome } from '@deepseek-ai/dsh-home'
|
||||
import { DSH_HOME_ENV, resolveDshHome } from '@deepseek-ai/dsh-paths'
|
||||
import { processOutcome } from './background.ts'
|
||||
import { parseExitStatus, renderProcessRead, renderResult } from './render.ts'
|
||||
|
||||
@@ -357,7 +357,7 @@ export function apply(ctx: Context, config: Config = {}): void {
|
||||
agent: exec.agent,
|
||||
callId: exec.callId,
|
||||
toolName: 'bash',
|
||||
...exec.signal ? { signal: exec.signal } : {},
|
||||
signal: exec.signal,
|
||||
},
|
||||
)
|
||||
}
|
||||
@@ -422,8 +422,8 @@ export function apply(ctx: Context, config: Config = {}): void {
|
||||
if (tasks === undefined) {
|
||||
throw new Error('background tasks unavailable: load @deepseek-ai/dsh-tasks and @deepseek-ai/dsh-tool-tasks')
|
||||
}
|
||||
// Reject pre-start cancellation; returned tasks use their own lifecycle.
|
||||
if (exec.signal?.aborted) throw new Error('command aborted')
|
||||
// The caller owns cancellation until TaskService commits detached ownership.
|
||||
if (exec.signal.aborted) return []
|
||||
// Task preflight finishes before the starter can spawn a process.
|
||||
const id = tasks.start({
|
||||
kind: 'bash',
|
||||
@@ -442,7 +442,7 @@ export function apply(ctx: Context, config: Config = {}): void {
|
||||
}
|
||||
const result = await ctx.bash.run(ctx.bash.resolve({
|
||||
...request,
|
||||
...exec.signal ? { signal: exec.signal } : {},
|
||||
signal: exec.signal,
|
||||
}))
|
||||
if (result.aborted) throw new Error('command aborted')
|
||||
return [{ type: 'text', text: renderResult(result, escalationModes) }]
|
||||
|
||||
@@ -7,10 +7,13 @@ import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import type { ToolExecution } from '@deepseek-ai/dsh-tools'
|
||||
import { BashEnvRegistry } from '@deepseek-ai/dsh-tool-bash'
|
||||
|
||||
const testToolSignal = new AbortController().signal
|
||||
|
||||
afterEach(() => vi.unstubAllEnvs())
|
||||
|
||||
function execution(sessionId?: string): ToolExecution {
|
||||
return {
|
||||
signal: testToolSignal,
|
||||
token: Symbol('bash-env-test') as ToolExecution['token'],
|
||||
callId: CallId('bash-env-call'),
|
||||
name: 'bash',
|
||||
|
||||
@@ -7,7 +7,7 @@ import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import { BashExecutor } from '@deepseek-ai/dsh-bash'
|
||||
import type { BashExecRequest, BashExecSpec, BashProcess, BashProcessRead, BashRunResult } from '@deepseek-ai/dsh-bash'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import ToolRegistry, { TOOL_ABORTED, TOOL_ABORTED_BEFORE_DISPATCH } from '@deepseek-ai/dsh-tools'
|
||||
import AgentRegistry from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
|
||||
@@ -21,6 +21,8 @@ import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
|
||||
import { processOutcome } from '../src/background.ts'
|
||||
import { renderProcessRead, renderResult } from '../src/render.ts'
|
||||
|
||||
const testToolSignal = new AbortController().signal
|
||||
|
||||
const spillDir = mkdtempSync(join(tmpdir(), 'dsh-tool-bash-spec-'))
|
||||
|
||||
/** Foreground-only harness: no task runtime (backgrounding fails loud here). */
|
||||
@@ -67,7 +69,7 @@ function registerFakeAgent(ctx: Context, sessionId: string, inject: (...args: un
|
||||
}
|
||||
let callCounter = 0
|
||||
function call(ctx: Context, name: string, args: unknown, agent?: Agent) {
|
||||
return ctx.tools.execute({ callId: CallId(`call-${++callCounter}`), name, arguments: args, ...agent ? { agent } : {} })
|
||||
return ctx.tools.execute({ signal: testToolSignal, callId: CallId(`call-${++callCounter}`), name, arguments: args, ...agent ? { agent } : {} })
|
||||
}
|
||||
|
||||
function text(result: { content: { type: string; text?: string }[] }): string {
|
||||
@@ -179,7 +181,11 @@ async function setupSandboxed(withApproval = false) {
|
||||
return { ctx, bash: ctx.bash as RecordingSandboxExecutor }
|
||||
}
|
||||
|
||||
function sandboxAgent(mode?: 'read-only' | 'workspace-write' | 'danger-full-access', ctx?: Context): Agent {
|
||||
function sandboxAgent(
|
||||
mode?: 'read-only' | 'workspace-write' | 'danger-full-access',
|
||||
ctx?: Context,
|
||||
onAppend?: (type: string) => void,
|
||||
): Agent {
|
||||
const events: Array<{ type: string; data?: Record<string, unknown> }> = [{ type: 'turn/start' }]
|
||||
if (mode !== undefined) events.push({ type: 'sandbox/mode', data: { mode } })
|
||||
const id = SessionId('sandbox-session')
|
||||
@@ -193,6 +199,7 @@ function sandboxAgent(mode?: 'read-only' | 'workspace-write' | 'danger-full-acce
|
||||
append: (type: string, data: Record<string, unknown>) => {
|
||||
const event = { type, data }
|
||||
events.push(event)
|
||||
onAppend?.(type)
|
||||
return event
|
||||
},
|
||||
},
|
||||
@@ -451,7 +458,7 @@ describe('background execution through the task runtime', () => {
|
||||
expect(text(result)).toContain('background tasks unavailable: load @deepseek-ai/dsh-tasks and @deepseek-ai/dsh-tool-tasks')
|
||||
})
|
||||
|
||||
it('a pre-aborted call refuses to start: isError, no process spawned', async () => {
|
||||
it('a pre-aborted call is skipped before the process starts', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
@@ -470,7 +477,8 @@ describe('background execution through the task runtime', () => {
|
||||
signal: controller.signal,
|
||||
})
|
||||
expect(result.isError).toBe(true)
|
||||
expect(text(result)).toContain('command aborted')
|
||||
expect(result.error).toEqual({ name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH })
|
||||
expect(text(result)).toBe('Error: tool call aborted before dispatch')
|
||||
expect((ctx.bash as CountingStartExecutor).starts).toBe(0)
|
||||
})
|
||||
|
||||
@@ -597,6 +605,29 @@ describe('sandbox escalation through the generic task producer', () => {
|
||||
expect(bash.modes).toEqual(['workspace-write', 'workspace-write'])
|
||||
})
|
||||
|
||||
it('does not publish detached work when cancellation follows the escalation grant', async () => {
|
||||
const { ctx, bash } = await setupSandboxed(true)
|
||||
const controller = new AbortController()
|
||||
const agent = sandboxAgent(undefined, ctx, (type) => {
|
||||
if (type === 'approval/decided') controller.abort()
|
||||
})
|
||||
ctx.agents.register(agent)
|
||||
ctx.on('approval/request', () => Promise.resolve<ApprovalOutcome>('allowed-once'))
|
||||
const start = vi.spyOn(bash, 'start')
|
||||
|
||||
const result = await ctx.tools.execute({
|
||||
callId: CallId('cancelled-escalation-background'),
|
||||
name: 'bash',
|
||||
arguments: { ...escalate, run_in_background: true },
|
||||
agent,
|
||||
signal: controller.signal,
|
||||
})
|
||||
|
||||
expect(result.error).toEqual({ name: 'AbortError', code: TOOL_ABORTED })
|
||||
expect(text(result)).toBe('Error: tool call aborted')
|
||||
expect(start).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it('uses the session override for ordinary calls and evaluates widening against it', async () => {
|
||||
const { ctx, bash } = await setupSandboxed(true)
|
||||
const agent = sandboxAgent('workspace-write')
|
||||
@@ -730,7 +761,7 @@ describe('session-cwd routing (per-session workdir)', () => {
|
||||
it('falls back to the executor default when the agent has no session cwd', async () => {
|
||||
const ctx = await setup()
|
||||
// No exec.agent at all → executor uses its config/process.cwd() default.
|
||||
const result = await ctx.tools.execute({ callId: CallId('cwd-noagent'), name: 'bash', arguments: { command: 'pwd', description: 'pwd' } })
|
||||
const result = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('cwd-noagent'), name: 'bash', arguments: { command: 'pwd', description: 'pwd' } })
|
||||
expect(result.isError).toBe(false)
|
||||
expect(text(result).trim().length).toBeGreaterThan(0)
|
||||
})
|
||||
@@ -1012,6 +1043,7 @@ describe('the model-facing bash tool builds its request from named args only (no
|
||||
const path = ctx.sessionPersistence.locate(agent.session.header)?.path
|
||||
|
||||
await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('session-env-fg'),
|
||||
name: 'bash',
|
||||
arguments: { command: 'true', description: 'run command' },
|
||||
@@ -1032,6 +1064,7 @@ describe('the model-facing bash tool builds its request from named args only (no
|
||||
const path = ctx.sessionPersistence.locate(agent.session.header)?.path
|
||||
|
||||
await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('session-env-bg'),
|
||||
name: 'bash',
|
||||
arguments: {
|
||||
@@ -1058,6 +1091,7 @@ describe('the model-facing bash tool builds its request from named args only (no
|
||||
const ambient = process.env.DSH_SESSION_ID
|
||||
|
||||
await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('session-env-id-only'),
|
||||
name: 'bash',
|
||||
arguments: { command: 'true', description: 'run command' },
|
||||
@@ -1079,6 +1113,7 @@ describe('the model-facing bash tool builds its request from named args only (no
|
||||
|
||||
for (const [callId, agent] of [['parent', parent], ['child', child]] as const) {
|
||||
await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId(`session-env-${callId}`),
|
||||
name: 'bash',
|
||||
arguments: { command: 'true', description: 'run command' },
|
||||
@@ -1109,6 +1144,7 @@ describe('the model-facing bash tool builds its request from named args only (no
|
||||
// This preserves the request shape; it is not a security boundary because shell syntax can
|
||||
// already set environment variables or feed stdin.
|
||||
await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('no-forward-1'),
|
||||
name: 'bash',
|
||||
arguments: {
|
||||
@@ -1130,6 +1166,7 @@ describe('the model-facing bash tool builds its request from named args only (no
|
||||
it('a background bash call likewise carries no trusted-only fields', async () => {
|
||||
const { ctx, bash } = await setupRecording()
|
||||
const result = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('no-forward-2'),
|
||||
name: 'bash',
|
||||
arguments: {
|
||||
|
||||
@@ -33,7 +33,7 @@
|
||||
"path": "../../bash/bash"
|
||||
},
|
||||
{
|
||||
"path": "../../util/home"
|
||||
"path": "../../util/paths"
|
||||
},
|
||||
{
|
||||
"path": "../../tasks/tasks"
|
||||
|
||||
Reference in New Issue
Block a user