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 worktree/web-multimodal-image-input
# Conflicts: # apps/cli/src/web.ts # apps/web/tests/smoke-fixture.e2e.ts # docs/architecture.i18n.yaml # packages/client/connection/src/client/fixture.ts # packages/client/ui-conversation/README.md # packages/client/ui-conversation/package.json # packages/client/ui-conversation/src/client/apply.ts # packages/client/ui-conversation/src/client/chat/ChatView.tsx # packages/client/ui-conversation/src/client/chat/register.ts # packages/client/ui-conversation/src/client/contract/slots.ts # packages/client/ui-conversation/src/client/contract/views.ts # packages/client/ui-conversation/src/client/service.ts # packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx # packages/client/ui-conversation/src/client/stores.ts # packages/client/ui-conversation/tests/skeleton-branches.spec.tsx # packages/cordis/tool-cordis/src/api-catalog.ts # packages/host/runtime/src/boot.ts # packages/host/runtime/tests/host-runtime.spec.ts # pnpm-lock.yaml
This commit is contained in:
@@ -1,8 +1,9 @@
|
||||
/**
|
||||
* Tool-card view computation over the mux live path: three standard card types
|
||||
* arrive on the frame, a presenterless tool ships no view field, and a throwing
|
||||
* presenter soft-falls to no view (the event still ships). Result pairing works
|
||||
* both through the live open-call table and the backscan fallback after
|
||||
* arrive on the frame, a presenterless tool ships no view field, a call-only
|
||||
* presenter keeps raw result content out of the view payload, and a throwing
|
||||
* presenter soft-falls to no view (the event still ships). Result pairing
|
||||
* works both through the live open-call table and the backscan fallback after
|
||||
* turn/end cleared it.
|
||||
*/
|
||||
|
||||
@@ -12,7 +13,7 @@ import AgentRegistry from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import SessionStore from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import ToolRegistry, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
|
||||
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import type { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
@@ -24,13 +25,13 @@ import { createApiProxy } from '../src/api-proxy.ts'
|
||||
const reply = (text: string): Promise<ContentBlock[]> => Promise.resolve([{ type: 'text', text }])
|
||||
|
||||
function tool(name: string, presenters: Pick<ToolDefinition, 'presentCall' | 'presentResult'>): ToolDefinition {
|
||||
return {
|
||||
return defineContentToolFixture({
|
||||
name,
|
||||
description: `tool ${name}`,
|
||||
parameters: { type: 'object', properties: {} },
|
||||
parameters: {},
|
||||
execute: () => reply(`ran:${name}`),
|
||||
...presenters,
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
async function harness(): Promise<{ ctx: Context }> {
|
||||
@@ -50,6 +51,9 @@ async function harness(): Promise<{ ctx: Context }> {
|
||||
ctx.tools.register(tool('diffy', {
|
||||
presentCall: () => ({ card: 'diff', title: 'Write f.txt', diffs: [{ path: 'f.txt', oldText: null, newText: 'x' }] }),
|
||||
}))
|
||||
ctx.tools.register(tool('call-only', {
|
||||
presentCall: () => ({ card: 'generic', title: 'program', kind: 'execute', rawInput: 'return value' }),
|
||||
}))
|
||||
ctx.tools.register(tool('plain', {}))
|
||||
ctx.tools.register(tool('boom', {
|
||||
presentCall: () => { throw new Error('presenter exploded') },
|
||||
@@ -73,13 +77,16 @@ describe('mux live view computation', () => {
|
||||
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp' })
|
||||
const abort = new AbortController()
|
||||
const stream = api.events.mux({ rpcId: RpcId('t-mux'), payload: {} }, abort.signal)
|
||||
const collected = collect(stream, 7, abort)
|
||||
const collected = collect(stream, 9, abort)
|
||||
const rawResult = `RAW_RESULT:${'x'.repeat(64 * 1024)}`
|
||||
|
||||
const session = ctx.sessions.create()
|
||||
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
session.append('tool/call', { turn: 1, step: 1, callId: CallId('c-gen'), name: 'gen', arguments: '{}' })
|
||||
session.append('tool/call', { turn: 1, step: 1, callId: CallId('c-term'), name: 'term', arguments: '{"cmd":"echo hi"}' })
|
||||
session.append('tool/call', { turn: 1, step: 1, callId: CallId('c-diff'), name: 'diffy', arguments: '{}' })
|
||||
session.append('tool/call', { turn: 1, step: 1, callId: CallId('c-call-only'), name: 'call-only', arguments: '{}' })
|
||||
session.append('tool/result', { turn: 1, step: 1, callId: CallId('c-call-only'), content: [{ type: 'text', text: rawResult }], isError: false }, { surfaceOp: 'append' })
|
||||
session.append('tool/call', { turn: 1, step: 1, callId: CallId('c-plain'), name: 'plain', arguments: '{}' })
|
||||
session.append('tool/call', { turn: 1, step: 1, callId: CallId('c-boom'), name: 'boom', arguments: '{}' })
|
||||
session.append('tool/result', { turn: 1, step: 1, callId: CallId('c-gen'), content: [{ type: 'text', text: 'ok' }], isError: false }, { surfaceOp: 'append' })
|
||||
@@ -93,6 +100,15 @@ describe('mux live view computation', () => {
|
||||
expect(byCall.get('tool/call:c-gen')?.view).toEqual({ for: 'call', view: { card: 'generic', title: 'gen call' } })
|
||||
expect(byCall.get('tool/call:c-term')?.view).toEqual({ for: 'call', view: { card: 'terminal', title: 'echo hi' } })
|
||||
expect(byCall.get('tool/call:c-diff')?.view?.view.card).toBe('diff')
|
||||
expect(byCall.get('tool/call:c-call-only')?.view).toEqual({
|
||||
for: 'call',
|
||||
view: { card: 'generic', title: 'program', kind: 'execute', rawInput: 'return value' },
|
||||
})
|
||||
const callOnlyResult = byCall.get('tool/result:c-call-only')
|
||||
expect('view' in (callOnlyResult ?? {})).toBe(false)
|
||||
const serializedResult = JSON.stringify(callOnlyResult)
|
||||
expect(serializedResult.indexOf(rawResult)).toBeGreaterThanOrEqual(0)
|
||||
expect(serializedResult.indexOf(rawResult)).toBe(serializedResult.lastIndexOf(rawResult))
|
||||
// No presenter → the frame carries no view property at all.
|
||||
expect('view' in (byCall.get('tool/call:c-plain') ?? {})).toBe(false)
|
||||
// Throwing presenter → soft-fall: event ships, no view.
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { existsSync, mkdtempSync, readFileSync } from 'node:fs'
|
||||
import { existsSync, mkdirSync, mkdtempSync, readFileSync, writeFileSync } from 'node:fs'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
|
||||
@@ -15,6 +15,8 @@ import { bootHost, startHost, type HostHandle, type RunningHost } from '../src/i
|
||||
|
||||
/** Scripted adapter: each model call consumes the next chunk list; 'hang' streams then waits for abort. */
|
||||
class ScriptedAdapter extends LlmAdapter {
|
||||
readonly requests: GenerateOptions[] = []
|
||||
|
||||
constructor(
|
||||
private script: (StreamChunk[] | 'hang')[],
|
||||
private readonly inputModalities: readonly ModelModality[] = ['text', 'image'],
|
||||
@@ -31,6 +33,7 @@ class ScriptedAdapter extends LlmAdapter {
|
||||
}
|
||||
|
||||
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
this.requests.push(options)
|
||||
const entry = this.script.shift()
|
||||
if (!entry) throw new Error('ScriptedAdapter: script exhausted')
|
||||
if (entry === 'hang') {
|
||||
@@ -92,7 +95,12 @@ afterEach(async () => {
|
||||
|
||||
async function boot(script: (StreamChunk[] | 'hang')[] = []): Promise<RunningHost> {
|
||||
host = await startHost({
|
||||
boot: { persistenceRoot: mkdtempSync(join(tmpdir(), 'dsh-host-runtime-')), provider: 'scripted', model: 'test-model' },
|
||||
boot: {
|
||||
persistenceRoot: mkdtempSync(join(tmpdir(), 'dsh-host-runtime-')),
|
||||
workspaceContext: false,
|
||||
provider: 'scripted',
|
||||
model: 'test-model',
|
||||
},
|
||||
})
|
||||
host.ctx.llm.registerAdapter(['scripted'], new ScriptedAdapter(script))
|
||||
return host
|
||||
@@ -100,12 +108,25 @@ async function boot(script: (StreamChunk[] | 'hang')[] = []): Promise<RunningHos
|
||||
|
||||
describe('bootHost / startHost', () => {
|
||||
it('falls back to the deepseek defaults and disposes idempotently', async () => {
|
||||
const handle: HostHandle = await bootHost({ persistenceRoot: mkdtempSync(join(tmpdir(), 'dsh-boot-')) })
|
||||
const handle: HostHandle = await bootHost({
|
||||
persistenceRoot: mkdtempSync(join(tmpdir(), 'dsh-boot-')),
|
||||
workspaceContext: false,
|
||||
})
|
||||
expect(handle.defaults).toMatchObject({ provider: 'deepseek', model: 'deepseek-v4-flash' })
|
||||
expect(typeof handle.defaults.cwd).toBe('string')
|
||||
await handle.dispose()
|
||||
})
|
||||
|
||||
it('uses the JSONL backend compressed default', async () => {
|
||||
const handle: HostHandle = await bootHost({
|
||||
persistenceRoot: mkdtempSync(join(tmpdir(), 'dsh-boot-zstd-')),
|
||||
workspaceContext: false,
|
||||
})
|
||||
const session = handle.ctx.sessions.create()
|
||||
expect(handle.ctx.sessionPersistence.locate(session.header)?.path).toMatch(/\.jsonl\.zstd$/)
|
||||
await handle.dispose()
|
||||
})
|
||||
|
||||
it('startHost assembles api + handler over the same defaults and dedupes dispose', async () => {
|
||||
const running = await boot()
|
||||
expect(running.defaults).toMatchObject({ provider: 'scripted', model: 'test-model' })
|
||||
@@ -133,6 +154,7 @@ describe('bootHost / startHost', () => {
|
||||
it('mounts configured pi-ai providers while accepting an explicit empty list', async () => {
|
||||
const empty = await bootHost({
|
||||
persistenceRoot: mkdtempSync(join(tmpdir(), 'dsh-boot-pi-empty-')),
|
||||
workspaceContext: false,
|
||||
piAiProviders: [],
|
||||
})
|
||||
expect(empty.ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }])
|
||||
@@ -140,11 +162,47 @@ describe('bootHost / startHost', () => {
|
||||
|
||||
const configured = await bootHost({
|
||||
persistenceRoot: mkdtempSync(join(tmpdir(), 'dsh-boot-pi-')),
|
||||
workspaceContext: false,
|
||||
piAiProviders: [{ provider: 'openai' }],
|
||||
})
|
||||
expect(configured.ctx.llm.listProviders()).toContainEqual({ id: 'openai', name: 'openai' })
|
||||
await configured.dispose()
|
||||
})
|
||||
|
||||
it('routes workspace instructions through the assembled agent request prefix', async () => {
|
||||
const workspace = mkdtempSync(join(tmpdir(), 'dsh-host-workspace-'))
|
||||
mkdirSync(join(workspace, '.git'))
|
||||
writeFileSync(join(workspace, 'AGENTS.md'), 'host-workspace-context-probe\n')
|
||||
const adapter = new ScriptedAdapter([textResponse('done')])
|
||||
host = await startHost({
|
||||
boot: {
|
||||
persistenceRoot: mkdtempSync(join(tmpdir(), 'dsh-host-workspace-sessions-')),
|
||||
workspaceContext: { dshHome: join(workspace, '.dsh'), maxBytes: 65_536 },
|
||||
provider: 'scripted',
|
||||
model: 'test-model',
|
||||
cwd: workspace,
|
||||
},
|
||||
})
|
||||
host.ctx.llm.registerAdapter(['scripted'], adapter)
|
||||
const { sessionId } = expectOk(await host.api.sessions.create(request({})))
|
||||
const agent = host.ctx.agents.get(sessionId) as Agent
|
||||
const idle = waitForIdle(host.ctx, agent)
|
||||
|
||||
expectOk(await host.api.sessions.prompt(request({
|
||||
sessionId,
|
||||
mode: 'queue' as const,
|
||||
content: [{ type: 'text' as const, text: 'go' }],
|
||||
})))
|
||||
await idle
|
||||
|
||||
const requestText = adapter.requests[0]?.messages
|
||||
.flatMap(message => message.content)
|
||||
.filter(block => block.type === 'text')
|
||||
.map(block => block.text)
|
||||
.join('\n') ?? ''
|
||||
expect(requestText).toContain('Instructions from: AGENTS.md')
|
||||
expect(requestText).toContain('host-workspace-context-probe')
|
||||
})
|
||||
})
|
||||
|
||||
describe('host.describe', () => {
|
||||
@@ -158,6 +216,7 @@ describe('host.describe', () => {
|
||||
host = await startHost({
|
||||
boot: {
|
||||
persistenceRoot: mkdtempSync(join(tmpdir(), 'dsh-host-describe-missing-model-')),
|
||||
workspaceContext: false,
|
||||
provider: 'scripted',
|
||||
model: 'missing-model',
|
||||
},
|
||||
@@ -239,7 +298,7 @@ describe('sessions.prompt / cancel', () => {
|
||||
const persistenceRoot = mkdtempSync(join(tmpdir(), 'dsh-image-session-'))
|
||||
const dshHome = mkdtempSync(join(tmpdir(), 'dsh-image-home-'))
|
||||
host = await startHost({
|
||||
boot: { persistenceRoot, dshHome, provider: 'scripted', model: 'test-model' },
|
||||
boot: { persistenceRoot, workspaceContext: false, dshHome, provider: 'scripted', model: 'test-model' },
|
||||
})
|
||||
host.ctx.llm.registerAdapter(['scripted'], new ScriptedAdapter([textResponse('seen')]))
|
||||
const { sessionId } = expectOk(await host.api.sessions.create(request({})))
|
||||
@@ -404,7 +463,7 @@ describe('sessions.prompt / cancel', () => {
|
||||
const persistenceRoot = mkdtempSync(join(tmpdir(), 'dsh-text-session-'))
|
||||
const dshHome = mkdtempSync(join(tmpdir(), 'dsh-text-home-'))
|
||||
host = await startHost({
|
||||
boot: { persistenceRoot, dshHome, provider: 'scripted', model: 'test-model' },
|
||||
boot: { persistenceRoot, workspaceContext: false, dshHome, provider: 'scripted', model: 'test-model' },
|
||||
})
|
||||
host.ctx.llm.registerAdapter(['scripted'], new ScriptedAdapter([], ['text']))
|
||||
const { sessionId } = expectOk(await host.api.sessions.create(request({})))
|
||||
@@ -423,7 +482,7 @@ describe('sessions.prompt / cancel', () => {
|
||||
const persistenceRoot = mkdtempSync(join(tmpdir(), 'dsh-routed-session-'))
|
||||
const dshHome = mkdtempSync(join(tmpdir(), 'dsh-routed-home-'))
|
||||
host = await startHost({
|
||||
boot: { persistenceRoot, dshHome, provider: 'scripted', model: 'test-model' },
|
||||
boot: { persistenceRoot, workspaceContext: false, dshHome, provider: 'scripted', model: 'test-model' },
|
||||
})
|
||||
host.ctx.llm.registerAdapter(['scripted'], new ScriptedAdapter([], ['text']))
|
||||
host.ctx.llm.registerAdapter(
|
||||
@@ -451,6 +510,7 @@ describe('sessions.prompt / cancel', () => {
|
||||
host = await startHost({
|
||||
boot: {
|
||||
persistenceRoot: mkdtempSync(join(tmpdir(), 'dsh-host-route-default-')),
|
||||
workspaceContext: false,
|
||||
provider: 'scripted',
|
||||
model: 'test-model',
|
||||
},
|
||||
@@ -487,7 +547,9 @@ describe('sessions.prompt / cancel', () => {
|
||||
describe('sessions.history', () => {
|
||||
it('implicitly resumes a cold session, deduplicating concurrent calls to one attach', async () => {
|
||||
const persistenceRoot = mkdtempSync(join(tmpdir(), 'dsh-host-resume-'))
|
||||
const first = await startHost({ boot: { persistenceRoot, provider: 'scripted', model: 'test-model' } })
|
||||
const first = await startHost({
|
||||
boot: { persistenceRoot, workspaceContext: false, provider: 'scripted', model: 'test-model' },
|
||||
})
|
||||
first.ctx.llm.registerAdapter(['scripted'], new ScriptedAdapter([textResponse('persisted')]))
|
||||
const { sessionId } = expectOk(await first.api.sessions.create(request({})))
|
||||
const agent = first.ctx.agents.get(sessionId) as Agent
|
||||
@@ -496,7 +558,9 @@ describe('sessions.history', () => {
|
||||
await idle
|
||||
await first.dispose()
|
||||
|
||||
host = await startHost({ boot: { persistenceRoot, provider: 'scripted', model: 'test-model' } })
|
||||
host = await startHost({
|
||||
boot: { persistenceRoot, workspaceContext: false, provider: 'scripted', model: 'test-model' },
|
||||
})
|
||||
host.ctx.llm.registerAdapter(['scripted'], new ScriptedAdapter([]))
|
||||
expect(host.ctx.agents.get(sessionId)).toBeUndefined()
|
||||
const [a, b] = await Promise.all([
|
||||
|
||||
Reference in New Issue
Block a user