Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: unify agent and session identity

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-14 01:59:21 +08:00
parent 7a33ee94be
commit 709cc7200e
105 changed files with 899 additions and 948 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/coding-agent/tests/code-mode.e2e.ts
View File

@@ -4,11 +4,12 @@ import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore from '@deepseek-ai/dsh-session'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
@@ -72,7 +73,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
it('collapses the wire tool list to [run_code], bridges sub-calls, and returns curated output', async () => {
workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-e2e-'))
ctx = await codeModeHarness(workdir)
const agent = ctx.agentLoop.create(AgentId('e2e-code-mode'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { model: 'deepseek-v4-flash' })
agent.send([{
type: 'text',

4
examples/coding-agent/tests/coding-task.e2e.ts
View File

@@ -4,8 +4,8 @@ import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'
/**
* The swebench-style smoke test: a real model fixes a real bug in a temp
@@ -54,7 +54,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test
expect(before.status).not.toBe(0)
ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
const agent = ctx.agentLoop.create(AgentId('e2e-task'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('e2e-task'), { model: 'deepseek-v4-flash' })
agent.send([{
type: 'text',

4
examples/coding-agent/tests/compaction.e2e.ts
View File

@@ -3,8 +3,8 @@ import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'
/**
* The compaction smoke test: a real model runs a multi-step bash task with a
@@ -64,7 +64,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
},
persistenceRoot: join(workdir, '.sessions'),
})
const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { model: 'deepseek-v4-flash' })
agent.send([{
type: 'text',

4
examples/coding-agent/tests/full-loop.e2e.ts
View File

@@ -3,8 +3,8 @@ import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'
/**
* The first place a REAL model meets the REAL bash tool: the cheap canary
@@ -28,7 +28,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas
it('runs a bash command on request and reports its output', async () => {
workdir = await mkdtemp(join(tmpdir(), 'dsh-full-loop-e2e-'))
ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
const agent = ctx.agentLoop.create(AgentId('e2e-loop'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { model: 'deepseek-v4-flash' })
agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])
await waitForIdle(ctx, agent)

3
examples/coding-agent/tests/resume.e2e.ts
View File

@@ -4,7 +4,6 @@ import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import type { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { SessionId } from '@deepseek-ai/dsh-session'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
@@ -40,7 +39,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
// log on disk survives.
ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root })
const first = (await ctx.agents.create({
agentId: AgentId('resume-1'),
sessionId: SESSION_ID,
agentOptions: { model: 'deepseek-v4-flash' },
})).agent as ReactLoopAgent
@@ -54,7 +52,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
// run 1's exchange as conversation history.
ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root })
const resumed = (await ctx.agents.resume({
agentId: AgentId('resume-2'),
resumeSessionId: SESSION_ID,
agentOptions: { model: 'deepseek-v4-flash' },
})).agent as ReactLoopAgent

4
examples/coding-agent/tests/todo-write.e2e.ts
View File

@@ -3,8 +3,8 @@ import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { codingHarness, TODO_SYSTEM_PROMPT, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'
/**
* A REAL model drives the REAL todo_write tool: verify the WORLD (the session
@@ -26,7 +26,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a
it('appends a todo/write event with the model-produced task list', async () => {
workdir = await mkdtemp(join(tmpdir(), 'dsh-todo-write-e2e-'))
ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT })
const agent = ctx.agentLoop.create(AgentId('e2e-todo'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { model: 'deepseek-v4-flash' })
agent.send([{ type: 'text', text:
'Use the todo_write tool to record a plan of exactly two steps: first '

8
examples/cordis-agent/tests/cordis-tools.e2e.ts
View File

@@ -1,8 +1,8 @@
import { afterEach, describe, expect, it, vi } from 'vitest'
import type { Context } from 'cordis'
import { CallId } from '@deepseek-ai/dsh-llm'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { cordisHarness, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'
/**
* With-key smoke for the self-referential cordis tools: a REAL model drives
@@ -38,7 +38,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
it('mounts a status listener whose tagged output actually fires, then unmounts it', async () => {
ctx = await cordisHarness()
const log = vi.spyOn(console, 'log').mockImplementation(() => {})
const agent = ctx.agentLoop.create(AgentId('cordis-e2e-listener'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-listener'), { model: 'deepseek-v4-flash' })
agent.send([{
type: 'text',
@@ -66,7 +66,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
it('builds itself a reverse_text tool and actually calls it', async () => {
ctx = await cordisHarness()
const agent = ctx.agentLoop.create(AgentId('cordis-e2e-selftool'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-selftool'), { model: 'deepseek-v4-flash' })
agent.send([{
type: 'text',
@@ -114,7 +114,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
it('composes two mounts through provide/inject, and unmounting the provider parks the consumer', async () => {
ctx = await cordisHarness()
const agent = ctx.agentLoop.create(AgentId('cordis-e2e-compose'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-compose'), { model: 'deepseek-v4-flash' })
agent.send([{
type: 'text',