Merge remote-tracking branch 'origin/codex/enforce-tool-cancellation' into worktree/explicit-turn-signal

# Conflicts:
#	docs/architecture.md
#	docs/cordis-catalog/events.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/cordis/tool-cordis/src/api-catalog.ts
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/src/loop.ts
#	packages/core/agent/README.md
#	packages/examples/cli-demo/src/cli.ts
#	packages/ui/tui/tests/tui.spec.ts
This commit is contained in:
Tianyi Cui
2026-07-21 00:02:17 +08:00
191 changed files with 5505 additions and 728 deletions

View File

@@ -10,6 +10,8 @@ import type { ToolExecution } from '@deepseek-ai/dsh-tools'
import { afterEach, describe, expect, it, vi } from 'vitest'
import * as cliDemo from '../src/index.ts'
const testToolSignal = new AbortController().signal
const contexts: Context[] = []
async function skillConfig(catalogDescriptionMaxLength?: number): Promise<NonNullable<cliDemo.Config['skills']>> {
@@ -124,6 +126,7 @@ describe('dsh-cli-demo app composition', () => {
expect(ctx.get('agentLoop')?.config.maxParallelToolCalls).toBe(3)
const execution: ToolExecution = {
signal: testToolSignal,
token: Symbol('cli-demo-dsh-home-test') as ToolExecution['token'],
callId: CallId('cli-demo-dsh-home'),
name: 'bash',
@@ -141,11 +144,12 @@ describe('dsh-cli-demo app composition', () => {
})
const wait = vi.spyOn(ctx.tasks, 'wait')
await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('cli-demo-task-config'),
name: 'task_output',
arguments: { task_id: id, wait: true },
})
expect(wait).toHaveBeenCalledWith(id, 7, undefined, undefined)
expect(wait).toHaveBeenCalledWith(id, 7, undefined, testToolSignal)
})
it('accepts false to keep task services without model-facing task controls', async () => {

View File

@@ -70,6 +70,15 @@ function toolResponse(usage: TokenUsage): StreamChunk[] {
]
}
function failedResponse(usage: TokenUsage): StreamChunk[] {
return [
{ type: 'block-start', index: 0, blockType: 'text' },
{ type: 'text-delta', index: 0, text: 'discarded' },
{ type: 'usage', usage },
{ type: 'finish', reason: { kind: 'error', failure: { message: 'temporary', code: 'SERVER' } } },
]
}
function reasoningResponse(text: string): StreamChunk[] {
return [
{ type: 'block-start', index: 0, blockType: 'reasoning' },
@@ -98,6 +107,7 @@ async function harness(script: readonly ScriptEntry[]): Promise<Harness> {
persistenceRoot: root,
skills: { local: { dshHome: join(skillHome, '.dsh'), agentsHome: join(skillHome, '.agents') } },
workspaceContext: false,
llmRetry: { initialDelayMs: 1, maxDelayMs: 1, jitterRatio: 0 },
})
await new Promise(resolve => setTimeout(resolve, 80))
ctx.llm.registerAdapter(['mock'], new ScriptedAdapter(script))
@@ -323,6 +333,21 @@ describe('runOneShot and executeCli', () => {
})
})
it('counts a failed retry attempt once even though it has no assistant message', async () => {
const failed = { inputTokens: 11, outputTokens: 2, cacheReadTokens: 3 }
const recovered = { inputTokens: 7, outputTokens: 5, reasoningTokens: 4 }
const { ctx } = await harness([failedResponse(failed), textResponse('done', recovered)])
const result = await runOneShot(ctx, { task: 'task' })
expect(result.usage).toEqual({
inputTokens: 18,
outputTokens: 7,
cacheReadTokens: 3,
reasoningTokens: 4,
})
})
it('keeps the prior text when a later assistant message has no text blocks', async () => {
const { ctx } = await harness([
toolResponse({ inputTokens: 1, outputTokens: 1 }),
@@ -463,6 +488,7 @@ describe('formatTurnFailure', () => {
[{ kind: 'aborted' }, 'was aborted'],
[{ kind: 'aborted' }, 'was aborted'],
[{ kind: 'error', step: 2, message: 'bad' }, 'failed at step 2: bad'],
[{ kind: 'error', step: 3, failure: { message: 'provider bad', code: 'SERVER' } }, 'failed at step 3: provider bad'],
[{ kind: 'disposed' }, 'was disposed'],
[{ kind: 'max-tokens' }, 'output-token limit'],
[{ kind: 'rejected', reason: 'policy' }, 'was rejected: policy'],