Merge branch 'codex/tool-json-schema-dsl' into codex/canonical-tool-output
# Conflicts: # .agents/notes/implemented/feature/2026-06-30-interception-seams.md # docs/config-catalog.md # docs/cookbook/adding-a-tool.i18n.yaml # docs/cookbook/adding-a-tool.md # docs/cookbook/adding-a-tool.zh.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/tools.md # docs/event-producer-consumer.md # docs/persistence-catalog.md # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl # packages/bash/tool-bash/src/index.ts # packages/core/agent-loop/src/tool-calls.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/tool-calls.spec.ts # packages/core/tools/README.md # packages/core/tools/src/index.ts # packages/core/tools/tests/code-mode.spec.ts # packages/core/tools/tests/tools.spec.ts # packages/fs/tool-fs-search/tests/integration.spec.ts # packages/fs/tool-fs-search/tests/tools.spec.ts # packages/fs/tool-fs/tests/integration.spec.ts # packages/mcp/mcp-client/src/tools.ts # packages/timeout/timeout-policy/tests/timeout-policy.spec.ts # packages/web/tool-web/tests/integration.spec.ts # packages/web/tool-web/tests/tool-web.spec.ts
This commit is contained in:
Tianyi Cui
@@ -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 {
|
||||
@@ -185,7 +187,11 @@ 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')
|
||||
@@ -199,6 +205,7 @@ 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
|
||||
},
|
||||
},
|
||||
@@ -469,7 +476,7 @@ 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)
|
||||
@@ -488,7 +495,11 @@ 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({
|
||||
message: 'tool call aborted before dispatch',
|
||||
info: { 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)
|
||||
})
|
||||
|
||||
@@ -615,6 +626,32 @@ 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({
|
||||
message: 'tool call aborted',
|
||||
info: { 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')
|
||||
@@ -764,7 +801,7 @@ 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)
|
||||
})
|
||||
@@ -1046,6 +1083,7 @@ 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' },
|
||||
@@ -1066,6 +1104,7 @@ 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: {
|
||||
@@ -1092,6 +1131,7 @@ 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' },
|
||||
@@ -1113,6 +1153,7 @@ 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' },
|
||||
@@ -1143,6 +1184,7 @@ 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: {
|
||||
@@ -1164,6 +1206,7 @@ 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: {
|
||||
|
||||
Reference in New Issue
Block a user